diff options
Diffstat (limited to 'fs/proc/task_mmu.c')
| -rw-r--r-- | fs/proc/task_mmu.c | 1145 |
1 files changed, 857 insertions, 288 deletions
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 71e5039d940d..81dfc26bfae8 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -14,7 +14,7 @@ #include <linux/rmap.h> #include <linux/swap.h> #include <linux/sched/mm.h> -#include <linux/swapops.h> +#include <linux/leafops.h> #include <linux/mmu_notifier.h> #include <linux/page_idle.h> #include <linux/shmem_fs.h> @@ -22,12 +22,16 @@ #include <linux/pkeys.h> #include <linux/minmax.h> #include <linux/overflow.h> +#include <linux/buildid.h> #include <asm/elf.h> #include <asm/tlb.h> #include <asm/tlbflush.h> #include "internal.h" +#define SENTINEL_VMA_END -1 +#define SENTINEL_VMA_GATE -2 + #define SEQ_PUT_DEC(str, val) \ seq_put_decimal_ull_width(m, str, (val) << (PAGE_SHIFT-10), 8) void task_mem(struct seq_file *m, struct mm_struct *mm) @@ -35,9 +39,9 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) unsigned long text, lib, swap, anon, file, shmem; unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss; - anon = get_mm_counter(mm, MM_ANONPAGES); - file = get_mm_counter(mm, MM_FILEPAGES); - shmem = get_mm_counter(mm, MM_SHMEMPAGES); + anon = get_mm_counter_sum(mm, MM_ANONPAGES); + file = get_mm_counter_sum(mm, MM_FILEPAGES); + shmem = get_mm_counter_sum(mm, MM_SHMEMPAGES); /* * Note: to minimize their overhead, mm maintains hiwater_vm and @@ -58,7 +62,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm) text = min(text, mm->exec_vm << PAGE_SHIFT); lib = (mm->exec_vm << PAGE_SHIFT) - text; - swap = get_mm_counter(mm, MM_SWAPENTS); + swap = get_mm_counter_sum(mm, MM_SWAPENTS); SEQ_PUT_DEC("VmPeak:\t", hiwater_vm); SEQ_PUT_DEC(" kB\nVmSize:\t", total_vm); SEQ_PUT_DEC(" kB\nVmLck:\t", mm->locked_vm); @@ -91,12 +95,12 @@ unsigned long task_statm(struct mm_struct *mm, unsigned long *shared, unsigned long *text, unsigned long *data, unsigned long *resident) { - *shared = get_mm_counter(mm, MM_FILEPAGES) + - get_mm_counter(mm, MM_SHMEMPAGES); + *shared = get_mm_counter_sum(mm, MM_FILEPAGES) + + get_mm_counter_sum(mm, MM_SHMEMPAGES); *text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> PAGE_SHIFT; *data = mm->data_vm + mm->stack_vm; - *resident = *shared + get_mm_counter(mm, MM_ANONPAGES); + *resident = *shared + get_mm_counter_sum(mm, MM_ANONPAGES); return mm->total_vm; } @@ -126,16 +130,143 @@ static void release_task_mempolicy(struct proc_maps_private *priv) } #endif -static struct vm_area_struct *proc_get_vma(struct proc_maps_private *priv, - loff_t *ppos) +#ifdef CONFIG_PER_VMA_LOCK + +static void reset_lock_ctx(struct proc_maps_locking_ctx *lock_ctx) +{ + lock_ctx->locked_vma = NULL; + lock_ctx->mmap_locked = false; +} + +static void unlock_ctx_vma(struct proc_maps_locking_ctx *lock_ctx) +{ + if (lock_ctx->locked_vma) { + vma_end_read(lock_ctx->locked_vma); + lock_ctx->locked_vma = NULL; + } +} + +static const struct seq_operations proc_pid_maps_op; + +static inline bool lock_vma_range(struct seq_file *m, + struct proc_maps_locking_ctx *lock_ctx) +{ + /* + * smaps and numa_maps perform page table walk, therefore require + * mmap_lock but maps can be read with locking just the vma and + * walking the vma tree under rcu read protection. + */ + if (m->op != &proc_pid_maps_op) { + if (mmap_read_lock_killable(lock_ctx->mm)) + return false; + + lock_ctx->mmap_locked = true; + } else { + rcu_read_lock(); + reset_lock_ctx(lock_ctx); + } + + return true; +} + +static inline void unlock_vma_range(struct proc_maps_locking_ctx *lock_ctx) +{ + if (lock_ctx->mmap_locked) { + mmap_read_unlock(lock_ctx->mm); + } else { + unlock_ctx_vma(lock_ctx); + rcu_read_unlock(); + } +} + +static struct vm_area_struct *get_next_vma(struct proc_maps_private *priv, + loff_t last_pos) +{ + struct proc_maps_locking_ctx *lock_ctx = &priv->lock_ctx; + struct vm_area_struct *vma; + + if (lock_ctx->mmap_locked) + return vma_next(&priv->iter); + + unlock_ctx_vma(lock_ctx); + vma = lock_next_vma(lock_ctx->mm, &priv->iter, last_pos); + if (!IS_ERR_OR_NULL(vma)) + lock_ctx->locked_vma = vma; + + return vma; +} + +static inline bool fallback_to_mmap_lock(struct proc_maps_private *priv, + loff_t pos) +{ + struct proc_maps_locking_ctx *lock_ctx = &priv->lock_ctx; + + if (lock_ctx->mmap_locked) + return false; + + rcu_read_unlock(); + mmap_read_lock(lock_ctx->mm); + /* Reinitialize the iterator after taking mmap_lock */ + vma_iter_set(&priv->iter, pos); + lock_ctx->mmap_locked = true; + + return true; +} + +#else /* CONFIG_PER_VMA_LOCK */ + +static inline bool lock_vma_range(struct seq_file *m, + struct proc_maps_locking_ctx *lock_ctx) +{ + return mmap_read_lock_killable(lock_ctx->mm) == 0; +} + +static inline void unlock_vma_range(struct proc_maps_locking_ctx *lock_ctx) +{ + mmap_read_unlock(lock_ctx->mm); +} + +static struct vm_area_struct *get_next_vma(struct proc_maps_private *priv, + loff_t last_pos) { - struct vm_area_struct *vma = vma_next(&priv->iter); + return vma_next(&priv->iter); +} + +static inline bool fallback_to_mmap_lock(struct proc_maps_private *priv, + loff_t pos) +{ + return false; +} +#endif /* CONFIG_PER_VMA_LOCK */ + +static struct vm_area_struct *proc_get_vma(struct seq_file *m, loff_t *ppos) +{ + struct proc_maps_private *priv = m->private; + struct vm_area_struct *vma; + +retry: + vma = get_next_vma(priv, *ppos); + /* EINTR of EAGAIN is possible */ + if (IS_ERR(vma)) { + if (PTR_ERR(vma) == -EAGAIN && fallback_to_mmap_lock(priv, *ppos)) + goto retry; + + return vma; + } + + /* Store previous position to be able to restart if needed */ + priv->last_pos = *ppos; if (vma) { - *ppos = vma->vm_start; + /* + * Track the end of the reported vma to ensure position changes + * even if previous vma was merged with the next vma and we + * found the extended vma with the same vm_start. + */ + *ppos = vma->vm_end; } else { - *ppos = -2UL; - vma = get_gate_vma(priv->mm); + *ppos = SENTINEL_VMA_GATE; + vma = get_gate_vma(priv->lock_ctx.mm); } return vma; @@ -144,58 +275,66 @@ static struct vm_area_struct *proc_get_vma(struct proc_maps_private *priv, static void *m_start(struct seq_file *m, loff_t *ppos) { struct proc_maps_private *priv = m->private; - unsigned long last_addr = *ppos; + struct proc_maps_locking_ctx *lock_ctx; + loff_t last_addr = *ppos; struct mm_struct *mm; /* See m_next(). Zero at the start or after lseek. */ - if (last_addr == -1UL) + if (last_addr == SENTINEL_VMA_END) return NULL; priv->task = get_proc_task(priv->inode); if (!priv->task) return ERR_PTR(-ESRCH); - mm = priv->mm; + lock_ctx = &priv->lock_ctx; + mm = lock_ctx->mm; if (!mm || !mmget_not_zero(mm)) { put_task_struct(priv->task); priv->task = NULL; return NULL; } - if (mmap_read_lock_killable(mm)) { + if (!lock_vma_range(m, lock_ctx)) { mmput(mm); put_task_struct(priv->task); priv->task = NULL; return ERR_PTR(-EINTR); } - vma_iter_init(&priv->iter, mm, last_addr); + /* + * Reset current position if last_addr was set before + * and it's not a sentinel. + */ + if (last_addr > 0) + *ppos = last_addr = priv->last_pos; + vma_iter_init(&priv->iter, mm, (unsigned long)last_addr); hold_task_mempolicy(priv); - if (last_addr == -2UL) + if (last_addr == SENTINEL_VMA_GATE) return get_gate_vma(mm); - return proc_get_vma(priv, ppos); + return proc_get_vma(m, ppos); } static void *m_next(struct seq_file *m, void *v, loff_t *ppos) { - if (*ppos == -2UL) { - *ppos = -1UL; + if (*ppos == SENTINEL_VMA_GATE) { + *ppos = SENTINEL_VMA_END; return NULL; } - return proc_get_vma(m->private, ppos); + return proc_get_vma(m, ppos); } static void m_stop(struct seq_file *m, void *v) { struct proc_maps_private *priv = m->private; - struct mm_struct *mm = priv->mm; + struct mm_struct *mm = priv->lock_ctx.mm; if (!priv->task) return; release_task_mempolicy(priv); - mmap_read_unlock(mm); + unlock_vma_range(&priv->lock_ctx); mmput(mm); put_task_struct(priv->task); priv->task = NULL; @@ -210,9 +349,9 @@ static int proc_maps_open(struct inode *inode, struct file *file, return -ENOMEM; priv->inode = inode; - priv->mm = proc_mem_open(inode, PTRACE_MODE_READ); - if (IS_ERR(priv->mm)) { - int err = PTR_ERR(priv->mm); + priv->lock_ctx.mm = proc_mem_open(inode, PTRACE_MODE_READ); + if (IS_ERR(priv->lock_ctx.mm)) { + int err = PTR_ERR(priv->lock_ctx.mm); seq_release_private(inode, file); return err; @@ -226,8 +365,8 @@ static int proc_map_release(struct inode *inode, struct file *file) struct seq_file *seq = file->private_data; struct proc_maps_private *priv = seq->private; - if (priv->mm) - mmdrop(priv->mm); + if (priv->lock_ctx.mm) + mmdrop(priv->lock_ctx.mm); return seq_release_private(inode, file); } @@ -239,6 +378,67 @@ static int do_maps_open(struct inode *inode, struct file *file, sizeof(struct proc_maps_private)); } +static void get_vma_name(struct vm_area_struct *vma, + const struct path **path, + const char **name, + const char **name_fmt) +{ + struct anon_vma_name *anon_name = vma->vm_mm ? anon_vma_name(vma) : NULL; + + *name = NULL; + *path = NULL; + *name_fmt = NULL; + + /* + * Print the dentry name for named mappings, and a + * special [heap] marker for the heap: + */ + if (vma->vm_file) { + /* + * If user named this anon shared memory via + * prctl(PR_SET_VMA ..., use the provided name. + */ + if (anon_name) { + *name_fmt = "[anon_shmem:%s]"; + *name = anon_name->name; + } else { + *path = file_user_path(vma->vm_file); + } + return; + } + + if (vma->vm_ops && vma->vm_ops->name) { + *name = vma->vm_ops->name(vma); + if (*name) + return; + } + + *name = arch_vma_name(vma); + if (*name) + return; + + if (!vma->vm_mm) { + *name = "[vdso]"; + return; + } + + if (vma_is_initial_heap(vma)) { + *name = "[heap]"; + return; + } + + if (vma_is_initial_stack(vma)) { + *name = "[stack]"; + return; + } + + if (anon_name) { + *name_fmt = "[anon:%s]"; + *name = anon_name->name; + return; + } +} + static void show_vma_header_prefix(struct seq_file *m, unsigned long start, unsigned long end, vm_flags_t flags, unsigned long long pgoff, @@ -262,17 +462,15 @@ static void show_vma_header_prefix(struct seq_file *m, static void show_map_vma(struct seq_file *m, struct vm_area_struct *vma) { - struct anon_vma_name *anon_name = NULL; - struct mm_struct *mm = vma->vm_mm; - struct file *file = vma->vm_file; + const struct path *path; + const char *name_fmt, *name; vm_flags_t flags = vma->vm_flags; unsigned long ino = 0; unsigned long long pgoff = 0; unsigned long start, end; dev_t dev = 0; - const char *name = NULL; - if (file) { + if (vma->vm_file) { const struct inode *inode = file_user_inode(vma->vm_file); dev = inode->i_sb->s_dev; @@ -283,57 +481,15 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma) start = vma->vm_start; end = vma->vm_end; show_vma_header_prefix(m, start, end, flags, pgoff, dev, ino); - if (mm) - anon_name = anon_vma_name(vma); - /* - * Print the dentry name for named mappings, and a - * special [heap] marker for the heap: - */ - if (file) { + get_vma_name(vma, &path, &name, &name_fmt); + if (path) { seq_pad(m, ' '); - /* - * If user named this anon shared memory via - * prctl(PR_SET_VMA ..., use the provided name. - */ - if (anon_name) - seq_printf(m, "[anon_shmem:%s]", anon_name->name); - else - seq_path(m, file_user_path(file), "\n"); - goto done; - } - - if (vma->vm_ops && vma->vm_ops->name) { - name = vma->vm_ops->name(vma); - if (name) - goto done; - } - - name = arch_vma_name(vma); - if (!name) { - if (!mm) { - name = "[vdso]"; - goto done; - } - - if (vma_is_initial_heap(vma)) { - name = "[heap]"; - goto done; - } - - if (vma_is_initial_stack(vma)) { - name = "[stack]"; - goto done; - } - - if (anon_name) { - seq_pad(m, ' '); - seq_printf(m, "[anon:%s]", anon_name->name); - } - } - -done: - if (name) { + seq_path(m, path, "\n"); + } else if (name_fmt) { + seq_pad(m, ' '); + seq_printf(m, name_fmt, name); + } else if (name) { seq_pad(m, ' '); seq_puts(m, name); } @@ -358,11 +514,315 @@ static int pid_maps_open(struct inode *inode, struct file *file) return do_maps_open(inode, file, &proc_pid_maps_op); } +#define PROCMAP_QUERY_VMA_FLAGS ( \ + PROCMAP_QUERY_VMA_READABLE | \ + PROCMAP_QUERY_VMA_WRITABLE | \ + PROCMAP_QUERY_VMA_EXECUTABLE | \ + PROCMAP_QUERY_VMA_SHARED \ +) + +#define PROCMAP_QUERY_VALID_FLAGS_MASK ( \ + PROCMAP_QUERY_COVERING_OR_NEXT_VMA | \ + PROCMAP_QUERY_FILE_BACKED_VMA | \ + PROCMAP_QUERY_VMA_FLAGS \ +) + +#ifdef CONFIG_PER_VMA_LOCK + +static int query_vma_setup(struct proc_maps_locking_ctx *lock_ctx) +{ + reset_lock_ctx(lock_ctx); + + return 0; +} + +static void query_vma_teardown(struct proc_maps_locking_ctx *lock_ctx) +{ + if (lock_ctx->mmap_locked) { + mmap_read_unlock(lock_ctx->mm); + lock_ctx->mmap_locked = false; + } else { + unlock_ctx_vma(lock_ctx); + } +} + +static struct vm_area_struct *query_vma_find_by_addr(struct proc_maps_locking_ctx *lock_ctx, + unsigned long addr) +{ + struct mm_struct *mm = lock_ctx->mm; + struct vm_area_struct *vma; + struct vma_iterator vmi; + + if (lock_ctx->mmap_locked) + return find_vma(mm, addr); + + /* Unlock previously locked VMA and find the next one under RCU */ + unlock_ctx_vma(lock_ctx); + rcu_read_lock(); + vma_iter_init(&vmi, mm, addr); + vma = lock_next_vma(mm, &vmi, addr); + rcu_read_unlock(); + + if (!vma) + return NULL; + + if (!IS_ERR(vma)) { + lock_ctx->locked_vma = vma; + return vma; + } + + if (PTR_ERR(vma) == -EAGAIN) { + /* Fallback to mmap_lock on vma->vm_refcnt overflow */ + mmap_read_lock(mm); + vma = find_vma(mm, addr); + lock_ctx->mmap_locked = true; + } + + return vma; +} + +#else /* CONFIG_PER_VMA_LOCK */ + +static int query_vma_setup(struct proc_maps_locking_ctx *lock_ctx) +{ + return mmap_read_lock_killable(lock_ctx->mm); +} + +static void query_vma_teardown(struct proc_maps_locking_ctx *lock_ctx) +{ + mmap_read_unlock(lock_ctx->mm); +} + +static struct vm_area_struct *query_vma_find_by_addr(struct proc_maps_locking_ctx *lock_ctx, + unsigned long addr) +{ + return find_vma(lock_ctx->mm, addr); +} + +#endif /* CONFIG_PER_VMA_LOCK */ + +static struct vm_area_struct *query_matching_vma(struct proc_maps_locking_ctx *lock_ctx, + unsigned long addr, u32 flags) +{ + struct vm_area_struct *vma; + +next_vma: + vma = query_vma_find_by_addr(lock_ctx, addr); + if (IS_ERR(vma)) + return vma; + + if (!vma) + goto no_vma; + + /* user requested only file-backed VMA, keep iterating */ + if ((flags & PROCMAP_QUERY_FILE_BACKED_VMA) && !vma->vm_file) + goto skip_vma; + + /* VMA permissions should satisfy query flags */ + if (flags & PROCMAP_QUERY_VMA_FLAGS) { + u32 perm = 0; + + if (flags & PROCMAP_QUERY_VMA_READABLE) + perm |= VM_READ; + if (flags & PROCMAP_QUERY_VMA_WRITABLE) + perm |= VM_WRITE; + if (flags & PROCMAP_QUERY_VMA_EXECUTABLE) + perm |= VM_EXEC; + if (flags & PROCMAP_QUERY_VMA_SHARED) + perm |= VM_MAYSHARE; + + if ((vma->vm_flags & perm) != perm) + goto skip_vma; + } + + /* found covering VMA or user is OK with the matching next VMA */ + if ((flags & PROCMAP_QUERY_COVERING_OR_NEXT_VMA) || vma->vm_start <= addr) + return vma; + +skip_vma: + /* + * If the user needs closest matching VMA, keep iterating. + */ + addr = vma->vm_end; + if (flags & PROCMAP_QUERY_COVERING_OR_NEXT_VMA) + goto next_vma; + +no_vma: + return ERR_PTR(-ENOENT); +} + +static int do_procmap_query(struct mm_struct *mm, void __user *uarg) +{ + struct proc_maps_locking_ctx lock_ctx = { .mm = mm }; + struct procmap_query karg; + struct vm_area_struct *vma; + const char *name = NULL; + char build_id_buf[BUILD_ID_SIZE_MAX], *name_buf = NULL; + __u64 usize; + int err; + + if (copy_from_user(&usize, (void __user *)uarg, sizeof(usize))) + return -EFAULT; + /* argument struct can never be that large, reject abuse */ + if (usize > PAGE_SIZE) + return -E2BIG; + /* argument struct should have at least query_flags and query_addr fields */ + if (usize < offsetofend(struct procmap_query, query_addr)) + return -EINVAL; + err = copy_struct_from_user(&karg, sizeof(karg), uarg, usize); + if (err) + return err; + + /* reject unknown flags */ + if (karg.query_flags & ~PROCMAP_QUERY_VALID_FLAGS_MASK) + return -EINVAL; + /* either both buffer address and size are set, or both should be zero */ + if (!!karg.vma_name_size != !!karg.vma_name_addr) + return -EINVAL; + if (!!karg.build_id_size != !!karg.build_id_addr) + return -EINVAL; + + if (!mm || !mmget_not_zero(mm)) + return -ESRCH; + + err = query_vma_setup(&lock_ctx); + if (err) { + mmput(mm); + return err; + } + + vma = query_matching_vma(&lock_ctx, karg.query_addr, karg.query_flags); + if (IS_ERR(vma)) { + err = PTR_ERR(vma); + vma = NULL; + goto out; + } + + karg.vma_start = vma->vm_start; + karg.vma_end = vma->vm_end; + + karg.vma_flags = 0; + if (vma->vm_flags & VM_READ) + karg.vma_flags |= PROCMAP_QUERY_VMA_READABLE; + if (vma->vm_flags & VM_WRITE) + karg.vma_flags |= PROCMAP_QUERY_VMA_WRITABLE; + if (vma->vm_flags & VM_EXEC) + karg.vma_flags |= PROCMAP_QUERY_VMA_EXECUTABLE; + if (vma->vm_flags & VM_MAYSHARE) + karg.vma_flags |= PROCMAP_QUERY_VMA_SHARED; + + karg.vma_page_size = vma_kernel_pagesize(vma); + + if (vma->vm_file) { + const struct inode *inode = file_user_inode(vma->vm_file); + + karg.vma_offset = ((__u64)vma->vm_pgoff) << PAGE_SHIFT; + karg.dev_major = MAJOR(inode->i_sb->s_dev); + karg.dev_minor = MINOR(inode->i_sb->s_dev); + karg.inode = inode->i_ino; + } else { + karg.vma_offset = 0; + karg.dev_major = 0; + karg.dev_minor = 0; + karg.inode = 0; + } + + if (karg.build_id_size) { + __u32 build_id_sz; + + err = build_id_parse(vma, build_id_buf, &build_id_sz); + if (err) { + karg.build_id_size = 0; + } else { + if (karg.build_id_size < build_id_sz) { + err = -ENAMETOOLONG; + goto out; + } + karg.build_id_size = build_id_sz; + } + } + + if (karg.vma_name_size) { + size_t name_buf_sz = min_t(size_t, PATH_MAX, karg.vma_name_size); + const struct path *path; + const char *name_fmt; + size_t name_sz = 0; + + get_vma_name(vma, &path, &name, &name_fmt); + + if (path || name_fmt || name) { + name_buf = kmalloc(name_buf_sz, GFP_KERNEL); + if (!name_buf) { + err = -ENOMEM; + goto out; + } + } + if (path) { + name = d_path(path, name_buf, name_buf_sz); + if (IS_ERR(name)) { + err = PTR_ERR(name); + goto out; + } + name_sz = name_buf + name_buf_sz - name; + } else if (name || name_fmt) { + name_sz = 1 + snprintf(name_buf, name_buf_sz, name_fmt ?: "%s", name); + name = name_buf; + } + if (name_sz > name_buf_sz) { + err = -ENAMETOOLONG; + goto out; + } + karg.vma_name_size = name_sz; + } + + /* unlock vma or mmap_lock, and put mm_struct before copying data to user */ + query_vma_teardown(&lock_ctx); + mmput(mm); + + if (karg.vma_name_size && copy_to_user(u64_to_user_ptr(karg.vma_name_addr), + name, karg.vma_name_size)) { + kfree(name_buf); + return -EFAULT; + } + kfree(name_buf); + + if (karg.build_id_size && copy_to_user(u64_to_user_ptr(karg.build_id_addr), + build_id_buf, karg.build_id_size)) + return -EFAULT; + + if (copy_to_user(uarg, &karg, min_t(size_t, sizeof(karg), usize))) + return -EFAULT; + + return 0; + +out: + query_vma_teardown(&lock_ctx); + mmput(mm); + kfree(name_buf); + return err; +} + +static long procfs_procmap_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct seq_file *seq = file->private_data; + struct proc_maps_private *priv = seq->private; + + switch (cmd) { + case PROCMAP_QUERY: + /* priv->lock_ctx.mm is set during file open operation */ + return do_procmap_query(priv->lock_ctx.mm, (void __user *)arg); + default: + return -ENOIOCTLCMD; + } +} + const struct file_operations proc_pid_maps_operations = { .open = pid_maps_open, .read = seq_read, .llseek = seq_lseek, .release = proc_map_release, + .unlocked_ioctl = procfs_procmap_ioctl, + .compat_ioctl = compat_ptr_ioctl, }; /* @@ -442,11 +902,13 @@ static void smaps_page_accumulate(struct mem_size_stats *mss, static void smaps_account(struct mem_size_stats *mss, struct page *page, bool compound, bool young, bool dirty, bool locked, - bool migration) + bool present) { struct folio *folio = page_folio(page); int i, nr = compound ? compound_nr(page) : 1; unsigned long size = nr * PAGE_SIZE; + bool exclusive; + int mapcount; /* * First accumulate quantities that depend only on |size| and the type @@ -471,29 +933,45 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page, * Then accumulate quantities that may depend on sharing, or that may * differ page-by-page. * - * refcount == 1 guarantees the page is mapped exactly once. - * If any subpage of the compound page mapped with PTE it would elevate - * the refcount. + * refcount == 1 for present entries guarantees that the folio is mapped + * exactly once. For large folios this implies that exactly one + * PTE/PMD/... maps (a part of) this folio. + * + * Treat all non-present entries (where relying on the mapcount and + * refcount doesn't make sense) as "maybe shared, but not sure how + * often". We treat device private entries as being fake-present. * - * The page_mapcount() is called to get a snapshot of the mapcount. - * Without holding the page lock this snapshot can be slightly wrong as - * we cannot always read the mapcount atomically. It is not safe to - * call page_mapcount() even with PTL held if the page is not mapped, - * especially for migration entries. Treat regular migration entries - * as mapcount == 1. + * Note that it would not be safe to read the mapcount especially for + * pages referenced by migration entries, even with the PTL held. */ - if ((folio_ref_count(folio) == 1) || migration) { + if (folio_ref_count(folio) == 1 || !present) { smaps_page_accumulate(mss, folio, size, size << PSS_SHIFT, - dirty, locked, true); + dirty, locked, present); return; } + + if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) { + mapcount = folio_average_page_mapcount(folio); + exclusive = !folio_maybe_mapped_shared(folio); + } + + /* + * We obtain a snapshot of the mapcount. Without holding the folio lock + * this snapshot can be slightly wrong as we cannot always read the + * mapcount atomically. + */ for (i = 0; i < nr; i++, page++) { - int mapcount = page_mapcount(page); unsigned long pss = PAGE_SIZE << PSS_SHIFT; + + if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) { + mapcount = folio_precise_page_mapcount(folio, page); + exclusive = mapcount < 2; + } + if (mapcount >= 2) pss /= mapcount; smaps_page_accumulate(mss, folio, PAGE_SIZE, pss, - dirty, locked, mapcount < 2); + dirty, locked, exclusive); } } @@ -531,21 +1009,24 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, struct vm_area_struct *vma = walk->vma; bool locked = !!(vma->vm_flags & VM_LOCKED); struct page *page = NULL; - bool migration = false, young = false, dirty = false; + bool present = false, young = false, dirty = false; pte_t ptent = ptep_get(pte); if (pte_present(ptent)) { page = vm_normal_page(vma, addr, ptent); young = pte_young(ptent); dirty = pte_dirty(ptent); - } else if (is_swap_pte(ptent)) { - swp_entry_t swpent = pte_to_swp_entry(ptent); + present = true; + } else if (pte_none(ptent)) { + smaps_pte_hole_lookup(addr, walk); + } else { + const softleaf_t entry = softleaf_from_pte(ptent); - if (!non_swap_entry(swpent)) { + if (softleaf_is_swap(entry)) { int mapcount; mss->swap += PAGE_SIZE; - mapcount = swp_swapcount(swpent); + mapcount = swp_swapcount(entry); if (mapcount >= 2) { u64 pss_delta = (u64)PAGE_SIZE << PSS_SHIFT; @@ -554,20 +1035,17 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, } else { mss->swap_pss += (u64)PAGE_SIZE << PSS_SHIFT; } - } else if (is_pfn_swap_entry(swpent)) { - if (is_migration_entry(swpent)) - migration = true; - page = pfn_swap_entry_to_page(swpent); + } else if (softleaf_has_pfn(entry)) { + if (softleaf_is_device_private(entry)) + present = true; + page = softleaf_to_page(entry); } - } else { - smaps_pte_hole_lookup(addr, walk); - return; } if (!page) return; - smaps_account(mss, page, false, young, dirty, locked, migration); + smaps_account(mss, page, false, young, dirty, locked, present); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -578,18 +1056,19 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, struct vm_area_struct *vma = walk->vma; bool locked = !!(vma->vm_flags & VM_LOCKED); struct page *page = NULL; + bool present = false; struct folio *folio; - bool migration = false; + if (pmd_none(*pmd)) + return; if (pmd_present(*pmd)) { page = vm_normal_page_pmd(vma, addr, *pmd); - } else if (unlikely(thp_migration_supported() && is_swap_pmd(*pmd))) { - swp_entry_t entry = pmd_to_swp_entry(*pmd); + present = true; + } else if (unlikely(thp_migration_supported())) { + const softleaf_t entry = softleaf_from_pmd(*pmd); - if (is_migration_entry(entry)) { - migration = true; - page = pfn_swap_entry_to_page(entry); - } + if (softleaf_has_pfn(entry)) + page = softleaf_to_page(entry); } if (IS_ERR_OR_NULL(page)) return; @@ -604,7 +1083,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, mss->file_thp += HPAGE_PMD_SIZE; smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd), - locked, migration); + locked, present); } #else static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, @@ -644,8 +1123,15 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) { /* * Don't forget to update Documentation/ on changes. + * + * The length of the second argument of mnemonics[] + * needs to be 3 instead of previously set 2 + * (i.e. from [BITS_PER_LONG][2] to [BITS_PER_LONG][3]) + * to avoid spurious + * -Werror=unterminated-string-initialization warning + * with GCC 15 */ - static const char mnemonics[BITS_PER_LONG][2] = { + static const char mnemonics[BITS_PER_LONG][3] = { /* * In case if we meet a flag we don't know about. */ @@ -661,6 +1147,7 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) [ilog2(VM_MAYSHARE)] = "ms", [ilog2(VM_GROWSDOWN)] = "gd", [ilog2(VM_PFNMAP)] = "pf", + [ilog2(VM_MAYBE_GUARD)] = "gu", [ilog2(VM_LOCKED)] = "lo", [ilog2(VM_IO)] = "io", [ilog2(VM_SEQ_READ)] = "sr", @@ -696,17 +1183,22 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) [ilog2(VM_PKEY_BIT0)] = "", [ilog2(VM_PKEY_BIT1)] = "", [ilog2(VM_PKEY_BIT2)] = "", +#if CONFIG_ARCH_PKEY_BITS > 3 [ilog2(VM_PKEY_BIT3)] = "", -#if VM_PKEY_BIT4 +#endif +#if CONFIG_ARCH_PKEY_BITS > 4 [ilog2(VM_PKEY_BIT4)] = "", #endif #endif /* CONFIG_ARCH_HAS_PKEYS */ #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR [ilog2(VM_UFFD_MINOR)] = "ui", #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ -#ifdef CONFIG_X86_USER_SHADOW_STACK +#ifdef CONFIG_ARCH_HAS_USER_SHADOW_STACK [ilog2(VM_SHADOW_STACK)] = "ss", #endif +#if defined(CONFIG_64BIT) || defined(CONFIG_PPC32) + [ilog2(VM_DROPPABLE)] = "dp", +#endif #ifdef CONFIG_64BIT [ilog2(VM_SEALED)] = "sl", #endif @@ -717,11 +1209,8 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma) for (i = 0; i < BITS_PER_LONG; i++) { if (!mnemonics[i][0]) continue; - if (vma->vm_flags & (1UL << i)) { - seq_putc(m, mnemonics[i][0]); - seq_putc(m, mnemonics[i][1]); - seq_putc(m, ' '); - } + if (vma->vm_flags & (1UL << i)) + seq_printf(m, "%s ", mnemonics[i]); } seq_putc(m, '\n'); } @@ -733,24 +1222,32 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask, { struct mem_size_stats *mss = walk->private; struct vm_area_struct *vma = walk->vma; - pte_t ptent = huge_ptep_get(pte); struct folio *folio = NULL; + bool present = false; + spinlock_t *ptl; + pte_t ptent; + ptl = huge_pte_lock(hstate_vma(vma), walk->mm, pte); + ptent = huge_ptep_get(walk->mm, addr, pte); if (pte_present(ptent)) { folio = page_folio(pte_page(ptent)); - } else if (is_swap_pte(ptent)) { - swp_entry_t swpent = pte_to_swp_entry(ptent); + present = true; + } else { + const softleaf_t entry = softleaf_from_pte(ptent); - if (is_pfn_swap_entry(swpent)) - folio = pfn_swap_entry_folio(swpent); + if (softleaf_has_pfn(entry)) + folio = softleaf_to_folio(entry); } + if (folio) { - if (folio_likely_mapped_shared(folio) || + /* We treat non-present entries as "maybe shared". */ + if (!present || folio_maybe_mapped_shared(folio) || hugetlb_pmd_shared(pte)) mss->shared_hugetlb += huge_page_size(hstate_vma(vma)); else mss->private_hugetlb += huge_page_size(hstate_vma(vma)); } + spin_unlock(ptl); return 0; } #else @@ -874,8 +1371,8 @@ static int show_smap(struct seq_file *m, void *v) __show_smap(m, &mss, false); seq_printf(m, "THPeligible: %8u\n", - !!thp_vma_allowable_orders(vma, vma->vm_flags, - TVA_SMAPS | TVA_ENFORCE_SYSFS, THP_ORDERS_ALL)); + !!thp_vma_allowable_orders(vma, vma->vm_flags, TVA_SMAPS, + THP_ORDERS_ALL)); if (arch_pkeys_enabled()) seq_printf(m, "ProtectionKey: %8u\n", vma_pkey(vma)); @@ -888,7 +1385,7 @@ static int show_smaps_rollup(struct seq_file *m, void *v) { struct proc_maps_private *priv = m->private; struct mem_size_stats mss = {}; - struct mm_struct *mm = priv->mm; + struct mm_struct *mm = priv->lock_ctx.mm; struct vm_area_struct *vma; unsigned long vma_start = 0, last_vma_end = 0; int ret = 0; @@ -1033,9 +1530,9 @@ static int smaps_rollup_open(struct inode *inode, struct file *file) goto out_free; priv->inode = inode; - priv->mm = proc_mem_open(inode, PTRACE_MODE_READ); - if (IS_ERR(priv->mm)) { - ret = PTR_ERR(priv->mm); + priv->lock_ctx.mm = proc_mem_open(inode, PTRACE_MODE_READ); + if (IS_ERR_OR_NULL(priv->lock_ctx.mm)) { + ret = priv->lock_ctx.mm ? PTR_ERR(priv->lock_ctx.mm) : -ESRCH; single_release(inode, file); goto out_free; @@ -1053,8 +1550,8 @@ static int smaps_rollup_release(struct inode *inode, struct file *file) struct seq_file *seq = file->private_data; struct proc_maps_private *priv = seq->private; - if (priv->mm) - mmdrop(priv->mm); + if (priv->lock_ctx.mm) + mmdrop(priv->lock_ctx.mm); kfree(priv); return single_release(inode, file); @@ -1087,27 +1584,27 @@ struct clear_refs_private { enum clear_refs_types type; }; -#ifdef CONFIG_MEM_SOFT_DIRTY - static inline bool pte_is_pinned(struct vm_area_struct *vma, unsigned long addr, pte_t pte) { - struct page *page; + struct folio *folio; if (!pte_write(pte)) return false; if (!is_cow_mapping(vma->vm_flags)) return false; - if (likely(!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags))) + if (likely(!mm_flags_test(MMF_HAS_PINNED, vma->vm_mm))) return false; - page = vm_normal_page(vma, addr, pte); - if (!page) + folio = vm_normal_folio(vma, addr, pte); + if (!folio) return false; - return page_maybe_dma_pinned(page); + return folio_maybe_dma_pinned(folio); } static inline void clear_soft_dirty(struct vm_area_struct *vma, unsigned long addr, pte_t *pte) { + if (!pgtable_supports_soft_dirty()) + return; /* * The soft-dirty tracker uses #PF-s to catch writes * to pages, so write-protect the pte as well. See the @@ -1116,6 +1613,9 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma, */ pte_t ptent = ptep_get(pte); + if (pte_none(ptent)) + return; + if (pte_present(ptent)) { pte_t old_pte; @@ -1125,24 +1625,21 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma, ptent = pte_wrprotect(old_pte); ptent = pte_clear_soft_dirty(ptent); ptep_modify_prot_commit(vma, addr, pte, old_pte, ptent); - } else if (is_swap_pte(ptent)) { + } else { ptent = pte_swp_clear_soft_dirty(ptent); set_pte_at(vma->vm_mm, addr, pte, ptent); } } -#else -static inline void clear_soft_dirty(struct vm_area_struct *vma, - unsigned long addr, pte_t *pte) -{ -} -#endif -#if defined(CONFIG_MEM_SOFT_DIRTY) && defined(CONFIG_TRANSPARENT_HUGEPAGE) +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp) { pmd_t old, pmd = *pmdp; + if (!pgtable_supports_soft_dirty()) + return; + if (pmd_present(pmd)) { /* See comment in change_huge_pmd() */ old = pmdp_invalidate(vma, addr, pmdp); @@ -1155,7 +1652,7 @@ static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma, pmd = pmd_clear_soft_dirty(pmd); set_pmd_at(vma->vm_mm, addr, pmdp, pmd); - } else if (is_migration_entry(pmd_to_swp_entry(pmd))) { + } else if (pmd_is_migration_entry(pmd)) { pmd = pmd_swp_clear_soft_dirty(pmd); set_pmd_at(vma->vm_mm, addr, pmdp, pmd); } @@ -1354,6 +1851,7 @@ struct pagemapread { #define PM_SOFT_DIRTY BIT_ULL(55) #define PM_MMAP_EXCLUSIVE BIT_ULL(56) #define PM_UFFD_WP BIT_ULL(57) +#define PM_GUARD_REGION BIT_ULL(58) #define PM_FILE BIT_ULL(61) #define PM_SWAP BIT_ULL(62) #define PM_PRESENT BIT_ULL(63) @@ -1373,6 +1871,13 @@ static int add_to_pagemap(pagemap_entry_t *pme, struct pagemapread *pm) return 0; } +static bool __folio_page_mapped_exclusively(struct folio *folio, struct page *page) +{ + if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) + return folio_precise_page_mapcount(folio, page) == 1; + return !folio_maybe_mapped_shared(folio); +} + static int pagemap_pte_hole(unsigned long start, unsigned long end, __always_unused int depth, struct mm_walk *walk) { @@ -1418,7 +1923,10 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm, { u64 frame = 0, flags = 0; struct page *page = NULL; - bool migration = false; + struct folio *folio; + + if (pte_none(pte)) + goto out; if (pte_present(pte)) { if (pm->show_pfn) @@ -1429,122 +1937,149 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm, flags |= PM_SOFT_DIRTY; if (pte_uffd_wp(pte)) flags |= PM_UFFD_WP; - } else if (is_swap_pte(pte)) { - swp_entry_t entry; + } else { + softleaf_t entry; + if (pte_swp_soft_dirty(pte)) flags |= PM_SOFT_DIRTY; if (pte_swp_uffd_wp(pte)) flags |= PM_UFFD_WP; - entry = pte_to_swp_entry(pte); + entry = softleaf_from_pte(pte); if (pm->show_pfn) { pgoff_t offset; + /* * For PFN swap offsets, keeping the offset field * to be PFN only to be compatible with old smaps. */ - if (is_pfn_swap_entry(entry)) - offset = swp_offset_pfn(entry); + if (softleaf_has_pfn(entry)) + offset = softleaf_to_pfn(entry); else offset = swp_offset(entry); frame = swp_type(entry) | (offset << MAX_SWAPFILES_SHIFT); } flags |= PM_SWAP; - migration = is_migration_entry(entry); - if (is_pfn_swap_entry(entry)) - page = pfn_swap_entry_to_page(entry); - if (pte_marker_entry_uffd_wp(entry)) + if (softleaf_has_pfn(entry)) + page = softleaf_to_page(entry); + if (softleaf_is_uffd_wp_marker(entry)) flags |= PM_UFFD_WP; + if (softleaf_is_guard_marker(entry)) + flags |= PM_GUARD_REGION; } - if (page && !PageAnon(page)) - flags |= PM_FILE; - if (page && !migration && page_mapcount(page) == 1) - flags |= PM_MMAP_EXCLUSIVE; + if (page) { + folio = page_folio(page); + if (!folio_test_anon(folio)) + flags |= PM_FILE; + if ((flags & PM_PRESENT) && + __folio_page_mapped_exclusively(folio, page)) + flags |= PM_MMAP_EXCLUSIVE; + } + +out: if (vma->vm_flags & VM_SOFTDIRTY) flags |= PM_SOFT_DIRTY; return make_pme(frame, flags); } -static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, - struct mm_walk *walk) +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static int pagemap_pmd_range_thp(pmd_t *pmdp, unsigned long addr, + unsigned long end, struct vm_area_struct *vma, + struct pagemapread *pm) { - struct vm_area_struct *vma = walk->vma; - struct pagemapread *pm = walk->private; - spinlock_t *ptl; - pte_t *pte, *orig_pte; + unsigned int idx = (addr & ~PMD_MASK) >> PAGE_SHIFT; + u64 flags = 0, frame = 0; + pmd_t pmd = *pmdp; + struct page *page = NULL; + struct folio *folio = NULL; int err = 0; -#ifdef CONFIG_TRANSPARENT_HUGEPAGE - bool migration = false; - ptl = pmd_trans_huge_lock(pmdp, vma); - if (ptl) { - u64 flags = 0, frame = 0; - pmd_t pmd = *pmdp; - struct page *page = NULL; + if (vma->vm_flags & VM_SOFTDIRTY) + flags |= PM_SOFT_DIRTY; - if (vma->vm_flags & VM_SOFTDIRTY) + if (pmd_none(pmd)) + goto populate_pagemap; + + if (pmd_present(pmd)) { + page = pmd_page(pmd); + + flags |= PM_PRESENT; + if (pmd_soft_dirty(pmd)) flags |= PM_SOFT_DIRTY; + if (pmd_uffd_wp(pmd)) + flags |= PM_UFFD_WP; + if (pm->show_pfn) + frame = pmd_pfn(pmd) + idx; + } else if (thp_migration_supported()) { + const softleaf_t entry = softleaf_from_pmd(pmd); + unsigned long offset; - if (pmd_present(pmd)) { - page = pmd_page(pmd); - - flags |= PM_PRESENT; - if (pmd_soft_dirty(pmd)) - flags |= PM_SOFT_DIRTY; - if (pmd_uffd_wp(pmd)) - flags |= PM_UFFD_WP; - if (pm->show_pfn) - frame = pmd_pfn(pmd) + - ((addr & ~PMD_MASK) >> PAGE_SHIFT); - } -#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION - else if (is_swap_pmd(pmd)) { - swp_entry_t entry = pmd_to_swp_entry(pmd); - unsigned long offset; - - if (pm->show_pfn) { - if (is_pfn_swap_entry(entry)) - offset = swp_offset_pfn(entry); - else - offset = swp_offset(entry); - offset = offset + - ((addr & ~PMD_MASK) >> PAGE_SHIFT); - frame = swp_type(entry) | - (offset << MAX_SWAPFILES_SHIFT); - } - flags |= PM_SWAP; - if (pmd_swp_soft_dirty(pmd)) - flags |= PM_SOFT_DIRTY; - if (pmd_swp_uffd_wp(pmd)) - flags |= PM_UFFD_WP; - VM_BUG_ON(!is_pmd_migration_entry(pmd)); - migration = is_migration_entry(entry); - page = pfn_swap_entry_to_page(entry); + if (pm->show_pfn) { + if (softleaf_has_pfn(entry)) + offset = softleaf_to_pfn(entry) + idx; + else + offset = swp_offset(entry) + idx; + frame = swp_type(entry) | + (offset << MAX_SWAPFILES_SHIFT); } -#endif + flags |= PM_SWAP; + if (pmd_swp_soft_dirty(pmd)) + flags |= PM_SOFT_DIRTY; + if (pmd_swp_uffd_wp(pmd)) + flags |= PM_UFFD_WP; + VM_WARN_ON_ONCE(!pmd_is_migration_entry(pmd)); + page = softleaf_to_page(entry); + } - if (page && !migration && page_mapcount(page) == 1) - flags |= PM_MMAP_EXCLUSIVE; + if (page) { + folio = page_folio(page); + if (!folio_test_anon(folio)) + flags |= PM_FILE; + } - for (; addr != end; addr += PAGE_SIZE) { - pagemap_entry_t pme = make_pme(frame, flags); +populate_pagemap: + for (; addr != end; addr += PAGE_SIZE, idx++) { + u64 cur_flags = flags; + pagemap_entry_t pme; - err = add_to_pagemap(&pme, pm); - if (err) - break; - if (pm->show_pfn) { - if (flags & PM_PRESENT) - frame++; - else if (flags & PM_SWAP) - frame += (1 << MAX_SWAPFILES_SHIFT); - } + if (folio && (flags & PM_PRESENT) && + __folio_page_mapped_exclusively(folio, page)) + cur_flags |= PM_MMAP_EXCLUSIVE; + + pme = make_pme(frame, cur_flags); + err = add_to_pagemap(&pme, pm); + if (err) + break; + if (pm->show_pfn) { + if (flags & PM_PRESENT) + frame++; + else if (flags & PM_SWAP) + frame += (1 << MAX_SWAPFILES_SHIFT); } + } + return err; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + struct vm_area_struct *vma = walk->vma; + struct pagemapread *pm = walk->private; + spinlock_t *ptl; + pte_t *pte, *orig_pte; + int err = 0; + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + ptl = pmd_trans_huge_lock(pmdp, vma); + if (ptl) { + err = pagemap_pmd_range_thp(pmdp, addr, end, vma, pm); spin_unlock(ptl); return err; } -#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ +#endif /* * We can assume that @vma always points to a valid one and @end never @@ -1579,20 +2114,22 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask, struct pagemapread *pm = walk->private; struct vm_area_struct *vma = walk->vma; u64 flags = 0, frame = 0; + spinlock_t *ptl; int err = 0; pte_t pte; if (vma->vm_flags & VM_SOFTDIRTY) flags |= PM_SOFT_DIRTY; - pte = huge_ptep_get(ptep); + ptl = huge_pte_lock(hstate_vma(vma), walk->mm, ptep); + pte = huge_ptep_get(walk->mm, addr, ptep); if (pte_present(pte)) { struct folio *folio = page_folio(pte_page(pte)); if (!folio_test_anon(folio)) flags |= PM_FILE; - if (!folio_likely_mapped_shared(folio) && + if (!folio_maybe_mapped_shared(folio) && !hugetlb_pmd_shared(ptep)) flags |= PM_MMAP_EXCLUSIVE; @@ -1612,11 +2149,12 @@ static int pagemap_hugetlb_range(pte_t *ptep, unsigned long hmask, err = add_to_pagemap(&pme, pm); if (err) - return err; + break; if (pm->show_pfn && (flags & PM_PRESENT)) frame++; } + spin_unlock(ptl); cond_resched(); return err; @@ -1644,7 +2182,8 @@ static const struct mm_walk_ops pagemap_ops = { * Bit 55 pte is soft-dirty (see Documentation/admin-guide/mm/soft-dirty.rst) * Bit 56 page exclusively mapped * Bit 57 pte is uffd-wp write-protected - * Bits 58-60 zero + * Bit 58 pte is a guard region + * Bits 59-60 zero * Bit 61 page is file-page or shared-anon * Bit 62 page swapped * Bit 63 page present @@ -1758,8 +2297,8 @@ static int pagemap_open(struct inode *inode, struct file *file) struct mm_struct *mm; mm = proc_mem_open(inode, PTRACE_MODE_READ); - if (IS_ERR(mm)) - return PTR_ERR(mm); + if (IS_ERR_OR_NULL(mm)) + return mm ? PTR_ERR(mm) : -ESRCH; file->private_data = mm; return 0; } @@ -1776,7 +2315,8 @@ static int pagemap_release(struct inode *inode, struct file *file) #define PM_SCAN_CATEGORIES (PAGE_IS_WPALLOWED | PAGE_IS_WRITTEN | \ PAGE_IS_FILE | PAGE_IS_PRESENT | \ PAGE_IS_SWAPPED | PAGE_IS_PFNZERO | \ - PAGE_IS_HUGE | PAGE_IS_SOFT_DIRTY) + PAGE_IS_HUGE | PAGE_IS_SOFT_DIRTY | \ + PAGE_IS_GUARD) #define PM_SCAN_FLAGS (PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC) struct pagemap_scan_private { @@ -1791,12 +2331,16 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p, struct vm_area_struct *vma, unsigned long addr, pte_t pte) { - unsigned long categories = 0; + unsigned long categories; + + if (pte_none(pte)) + return 0; if (pte_present(pte)) { struct page *page; - categories |= PAGE_IS_PRESENT; + categories = PAGE_IS_PRESENT; + if (!pte_uffd_wp(pte)) categories |= PAGE_IS_WRITTEN; @@ -1810,19 +2354,22 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p, categories |= PAGE_IS_PFNZERO; if (pte_soft_dirty(pte)) categories |= PAGE_IS_SOFT_DIRTY; - } else if (is_swap_pte(pte)) { - swp_entry_t swp; + } else { + softleaf_t entry; + + categories = PAGE_IS_SWAPPED; - categories |= PAGE_IS_SWAPPED; if (!pte_swp_uffd_wp_any(pte)) categories |= PAGE_IS_WRITTEN; - if (p->masks_of_interest & PAGE_IS_FILE) { - swp = pte_to_swp_entry(pte); - if (is_pfn_swap_entry(swp) && - !folio_test_anon(pfn_swap_entry_folio(swp))) - categories |= PAGE_IS_FILE; - } + entry = softleaf_from_pte(pte); + if (softleaf_is_guard_marker(entry)) + categories |= PAGE_IS_GUARD; + else if ((p->masks_of_interest & PAGE_IS_FILE) && + softleaf_has_pfn(entry) && + !folio_test_anon(softleaf_to_folio(entry))) + categories |= PAGE_IS_FILE; + if (pte_swp_soft_dirty(pte)) categories |= PAGE_IS_SOFT_DIRTY; } @@ -1839,12 +2386,12 @@ static void make_uffd_wp_pte(struct vm_area_struct *vma, old_pte = ptep_modify_prot_start(vma, addr, pte); ptent = pte_mkuffd_wp(old_pte); ptep_modify_prot_commit(vma, addr, pte, old_pte, ptent); - } else if (is_swap_pte(ptent)) { - ptent = pte_swp_mkuffd_wp(ptent); - set_pte_at(vma->vm_mm, addr, pte, ptent); - } else { + } else if (pte_none(ptent)) { set_pte_at(vma->vm_mm, addr, pte, make_pte_marker(PTE_MARKER_UFFD_WP)); + } else { + ptent = pte_swp_mkuffd_wp(ptent); + set_pte_at(vma->vm_mm, addr, pte, ptent); } } @@ -1855,6 +2402,9 @@ static unsigned long pagemap_thp_category(struct pagemap_scan_private *p, { unsigned long categories = PAGE_IS_HUGE; + if (pmd_none(pmd)) + return categories; + if (pmd_present(pmd)) { struct page *page; @@ -1868,13 +2418,11 @@ static unsigned long pagemap_thp_category(struct pagemap_scan_private *p, categories |= PAGE_IS_FILE; } - if (is_zero_pfn(pmd_pfn(pmd))) + if (is_huge_zero_pmd(pmd)) categories |= PAGE_IS_PFNZERO; if (pmd_soft_dirty(pmd)) categories |= PAGE_IS_SOFT_DIRTY; - } else if (is_swap_pmd(pmd)) { - swp_entry_t swp; - + } else { categories |= PAGE_IS_SWAPPED; if (!pmd_swp_uffd_wp(pmd)) categories |= PAGE_IS_WRITTEN; @@ -1882,9 +2430,10 @@ static unsigned long pagemap_thp_category(struct pagemap_scan_private *p, categories |= PAGE_IS_SOFT_DIRTY; if (p->masks_of_interest & PAGE_IS_FILE) { - swp = pmd_to_swp_entry(pmd); - if (is_pfn_swap_entry(swp) && - !folio_test_anon(pfn_swap_entry_folio(swp))) + const softleaf_t entry = softleaf_from_pmd(pmd); + + if (softleaf_has_pfn(entry) && + !folio_test_anon(softleaf_to_folio(entry))) categories |= PAGE_IS_FILE; } } @@ -1901,7 +2450,7 @@ static void make_uffd_wp_pmd(struct vm_area_struct *vma, old = pmdp_invalidate_ad(vma, addr, pmdp); pmd = pmd_mkuffd_wp(old); set_pmd_at(vma->vm_mm, addr, pmdp, pmd); - } else if (is_migration_entry(pmd_to_swp_entry(pmd))) { + } else if (pmd_is_migration_entry(pmd)) { pmd = pmd_swp_mkuffd_wp(pmd); set_pmd_at(vma->vm_mm, addr, pmdp, pmd); } @@ -1913,6 +2462,9 @@ static unsigned long pagemap_hugetlb_category(pte_t pte) { unsigned long categories = PAGE_IS_HUGE; + if (pte_none(pte)) + return categories; + /* * According to pagemap_hugetlb_range(), file-backed HugeTLB * page cannot be swapped. So PAGE_IS_FILE is not checked for @@ -1920,6 +2472,7 @@ static unsigned long pagemap_hugetlb_category(pte_t pte) */ if (pte_present(pte)) { categories |= PAGE_IS_PRESENT; + if (!huge_pte_uffd_wp(pte)) categories |= PAGE_IS_WRITTEN; if (!PageAnon(pte_page(pte))) @@ -1928,8 +2481,9 @@ static unsigned long pagemap_hugetlb_category(pte_t pte) categories |= PAGE_IS_PFNZERO; if (pte_soft_dirty(pte)) categories |= PAGE_IS_SOFT_DIRTY; - } else if (is_swap_pte(pte)) { + } else { categories |= PAGE_IS_SWAPPED; + if (!pte_swp_uffd_wp_any(pte)) categories |= PAGE_IS_WRITTEN; if (pte_swp_soft_dirty(pte)) @@ -1943,22 +2497,25 @@ static void make_uffd_wp_huge_pte(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t ptent) { - unsigned long psize; + const unsigned long psize = huge_page_size(hstate_vma(vma)); + softleaf_t entry; - if (is_hugetlb_entry_hwpoisoned(ptent) || is_pte_marker(ptent)) + if (huge_pte_none(ptent)) { + set_huge_pte_at(vma->vm_mm, addr, ptep, + make_pte_marker(PTE_MARKER_UFFD_WP), psize); return; + } - psize = huge_page_size(hstate_vma(vma)); + entry = softleaf_from_pte(ptent); + if (softleaf_is_hwpoison(entry) || softleaf_is_marker(entry)) + return; - if (is_hugetlb_entry_migration(ptent)) + if (softleaf_is_migration(entry)) set_huge_pte_at(vma->vm_mm, addr, ptep, pte_swp_mkuffd_wp(ptent), psize); - else if (!huge_pte_none(ptent)) + else huge_ptep_modify_prot_commit(vma, addr, ptep, ptent, huge_pte_mkuffd_wp(ptent)); - else - set_huge_pte_at(vma->vm_mm, addr, ptep, - make_pte_marker(PTE_MARKER_UFFD_WP), psize); } #endif /* CONFIG_HUGETLB_PAGE */ @@ -1968,6 +2525,9 @@ static void pagemap_scan_backout_range(struct pagemap_scan_private *p, { struct page_region *cur_buf = &p->vec_buf[p->vec_buf_index]; + if (!p->vec_buf) + return; + if (cur_buf->start != addr) cur_buf->end = addr; else @@ -2168,22 +2728,19 @@ static int pagemap_scan_pmd_entry(pmd_t *pmd, unsigned long start, spinlock_t *ptl; int ret; - arch_enter_lazy_mmu_mode(); - ret = pagemap_scan_thp_entry(pmd, start, end, walk); - if (ret != -ENOENT) { - arch_leave_lazy_mmu_mode(); + if (ret != -ENOENT) return ret; - } ret = 0; start_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, start, &ptl); if (!pte) { - arch_leave_lazy_mmu_mode(); walk->action = ACTION_AGAIN; return 0; } + arch_enter_lazy_mmu_mode(); + if ((p->arg.flags & PM_SCAN_WP_MATCHING) && !p->vec_out) { /* Fast path for performing exclusive WP */ for (addr = start; addr != end; pte++, addr += PAGE_SIZE) { @@ -2252,8 +2809,8 @@ flush_and_return: if (flush_end) flush_tlb_range(vma, start, addr); - pte_unmap_unlock(start_pte, ptl); arch_leave_lazy_mmu_mode(); + pte_unmap_unlock(start_pte, ptl); cond_resched(); return ret; @@ -2274,7 +2831,7 @@ static int pagemap_scan_hugetlb_entry(pte_t *ptep, unsigned long hmask, if (~p->arg.flags & PM_SCAN_WP_MATCHING) { /* Go the short route when not write-protecting pages. */ - pte = huge_ptep_get(ptep); + pte = huge_ptep_get(walk->mm, start, ptep); categories = p->cur_vma_category | pagemap_hugetlb_category(pte); if (!pagemap_scan_is_interesting_page(categories, p)) @@ -2286,7 +2843,7 @@ static int pagemap_scan_hugetlb_entry(pte_t *ptep, unsigned long hmask, i_mmap_lock_write(vma->vm_file->f_mapping); ptl = huge_pte_lock(hstate_vma(vma), vma->vm_mm, ptep); - pte = huge_ptep_get(ptep); + pte = huge_ptep_get(walk->mm, start, ptep); categories = p->cur_vma_category | pagemap_hugetlb_category(pte); if (!pagemap_scan_is_interesting_page(categories, p)) @@ -2378,8 +2935,10 @@ static int pagemap_scan_get_args(struct pm_scan_arg *arg, return -EFAULT; if (!arg->vec && arg->vec_len) return -EINVAL; + if (UINT_MAX == SIZE_MAX && arg->vec_len > SIZE_MAX) + return -EINVAL; if (arg->vec && !access_ok((void __user *)(long)arg->vec, - arg->vec_len * sizeof(struct page_region))) + size_mul(arg->vec_len, sizeof(struct page_region)))) return -EFAULT; /* Fixup default values */ @@ -2566,7 +3125,12 @@ static void gather_stats(struct page *page, struct numa_maps *md, int pte_dirty, unsigned long nr_pages) { struct folio *folio = page_folio(page); - int count = page_mapcount(page); + int count; + + if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) + count = folio_precise_page_mapcount(folio, page); + else + count = folio_average_page_mapcount(folio); md->pages += nr_pages; if (pte_dirty || folio_test_dirty(folio)) @@ -2682,17 +3246,22 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr, static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { - pte_t huge_pte = huge_ptep_get(pte); + pte_t huge_pte; struct numa_maps *md; struct page *page; + spinlock_t *ptl; + ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte); + huge_pte = huge_ptep_get(walk->mm, addr, pte); if (!pte_present(huge_pte)) - return 0; + goto out; page = pte_page(huge_pte); md = walk->private; gather_stats(page, md, pte_dirty(huge_pte), 1); +out: + spin_unlock(ptl); return 0; } |