#include <linux/highmem.h>
#include <linux/ptrace.h>
#include <linux/pagemap.h>
+#include <linux/ptrace.h>
#include <linux/mempolicy.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/seq_file.h>
#include <asm/elf.h>
#include <asm/uaccess.h>
#include <asm/tlbflush.h>
#include "internal.h"
-char *task_mem(struct mm_struct *mm, char *buffer)
+void task_mem(struct seq_file *m, struct mm_struct *mm)
{
unsigned long data, text, lib;
unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;
data = mm->total_vm - mm->shared_vm - mm->stack_vm;
text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10;
lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text;
- buffer += sprintf(buffer,
+ seq_printf(m,
"VmPeak:\t%8lu kB\n"
"VmSize:\t%8lu kB\n"
"VmLck:\t%8lu kB\n"
data << (PAGE_SHIFT-10),
mm->stack_vm << (PAGE_SHIFT-10), text, lib,
(PTRS_PER_PTE*sizeof(pte_t)*mm->nr_ptes) >> 10);
- return buffer;
}
unsigned long task_vsize(struct mm_struct *mm)
return mm->total_vm;
}
-int proc_exe_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt)
+int proc_exe_link(struct inode *inode, struct path *path)
{
struct vm_area_struct * vma;
int result = -ENOENT;
}
if (vma) {
- *mnt = mntget(vma->vm_file->f_path.mnt);
- *dentry = dget(vma->vm_file->f_path.dentry);
+ *path = vma->vm_file->f_path;
+ path_get(&vma->vm_file->f_path);
result = 0;
}
}
static int do_maps_open(struct inode *inode, struct file *file,
- struct seq_operations *ops)
+ const struct seq_operations *ops)
{
struct proc_maps_private *priv;
int ret = -ENOMEM;
*/
if (file) {
pad_len_spaces(m, len);
- seq_path(m, file->f_path.mnt, file->f_path.dentry, "\n");
+ seq_path(m, &file->f_path, "\n");
} else {
const char *name = arch_vma_name(vma);
if (!name) {
return 0;
}
-static struct seq_operations proc_pid_maps_op = {
+static const struct seq_operations proc_pid_maps_op = {
.start = m_start,
.next = m_next,
.stop = m_stop,
*/
#define PSS_SHIFT 12
+#ifdef CONFIG_PROC_PAGE_MONITOR
struct mem_size_stats
{
struct vm_area_struct *vma;
return ret;
}
-static struct seq_operations proc_pid_smaps_op = {
+static const struct seq_operations proc_pid_smaps_op = {
.start = m_start,
.next = m_next,
.stop = m_stop,
.write = clear_refs_write,
};
+struct pagemapread {
+ char __user *out, *end;
+};
+
+#define PM_ENTRY_BYTES sizeof(u64)
+#define PM_RESERVED_BITS 3
+#define PM_RESERVED_OFFSET (64 - PM_RESERVED_BITS)
+#define PM_RESERVED_MASK (((1LL<<PM_RESERVED_BITS)-1) << PM_RESERVED_OFFSET)
+#define PM_SPECIAL(nr) (((nr) << PM_RESERVED_OFFSET) | PM_RESERVED_MASK)
+#define PM_NOT_PRESENT PM_SPECIAL(1LL)
+#define PM_SWAP PM_SPECIAL(2LL)
+#define PM_END_OF_BUFFER 1
+
+static int add_to_pagemap(unsigned long addr, u64 pfn,
+ struct pagemapread *pm)
+{
+ /*
+ * Make sure there's room in the buffer for an
+ * entire entry. Otherwise, only copy part of
+ * the pfn.
+ */
+ if (pm->out + PM_ENTRY_BYTES >= pm->end) {
+ if (copy_to_user(pm->out, &pfn, pm->end - pm->out))
+ return -EFAULT;
+ pm->out = pm->end;
+ return PM_END_OF_BUFFER;
+ }
+
+ if (put_user(pfn, pm->out))
+ return -EFAULT;
+ pm->out += PM_ENTRY_BYTES;
+ return 0;
+}
+
+static int pagemap_pte_hole(unsigned long start, unsigned long end,
+ void *private)
+{
+ struct pagemapread *pm = private;
+ unsigned long addr;
+ int err = 0;
+ for (addr = start; addr < end; addr += PAGE_SIZE) {
+ err = add_to_pagemap(addr, PM_NOT_PRESENT, pm);
+ if (err)
+ break;
+ }
+ return err;
+}
+
+u64 swap_pte_to_pagemap_entry(pte_t pte)
+{
+ swp_entry_t e = pte_to_swp_entry(pte);
+ return PM_SWAP | swp_type(e) | (swp_offset(e) << MAX_SWAPFILES_SHIFT);
+}
+
+static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+ void *private)
+{
+ struct pagemapread *pm = private;
+ pte_t *pte;
+ int err = 0;
+
+ for (; addr != end; addr += PAGE_SIZE) {
+ u64 pfn = PM_NOT_PRESENT;
+ pte = pte_offset_map(pmd, addr);
+ if (is_swap_pte(*pte))
+ pfn = swap_pte_to_pagemap_entry(*pte);
+ else if (pte_present(*pte))
+ pfn = pte_pfn(*pte);
+ /* unmap so we're not in atomic when we copy to userspace */
+ pte_unmap(pte);
+ err = add_to_pagemap(addr, pfn, pm);
+ if (err)
+ return err;
+ }
+
+ cond_resched();
+
+ return err;
+}
+
+static struct mm_walk pagemap_walk = {
+ .pmd_entry = pagemap_pte_range,
+ .pte_hole = pagemap_pte_hole
+};
+
+/*
+ * /proc/pid/pagemap - an array mapping virtual pages to pfns
+ *
+ * For each page in the address space, this file contains one 64-bit
+ * entry representing the corresponding physical page frame number
+ * (PFN) if the page is present. If there is a swap entry for the
+ * physical page, then an encoding of the swap file number and the
+ * page's offset into the swap file are returned. If no page is
+ * present at all, PM_NOT_PRESENT is returned. This allows determining
+ * precisely which pages are mapped (or in swap) and comparing mapped
+ * pages between processes.
+ *
+ * Efficient users of this interface will use /proc/pid/maps to
+ * determine which areas of memory are actually mapped and llseek to
+ * skip over unmapped regions.
+ */
+static ssize_t pagemap_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode);
+ struct page **pages, *page;
+ unsigned long uaddr, uend;
+ struct mm_struct *mm;
+ struct pagemapread pm;
+ int pagecount;
+ int ret = -ESRCH;
+
+ if (!task)
+ goto out;
+
+ ret = -EACCES;
+ if (!ptrace_may_attach(task))
+ goto out;
+
+ ret = -EINVAL;
+ /* file position must be aligned */
+ if (*ppos % PM_ENTRY_BYTES)
+ goto out;
+
+ ret = 0;
+ mm = get_task_mm(task);
+ if (!mm)
+ goto out;
+
+ ret = -ENOMEM;
+ uaddr = (unsigned long)buf & PAGE_MASK;
+ uend = (unsigned long)(buf + count);
+ pagecount = (PAGE_ALIGN(uend) - uaddr) / PAGE_SIZE;
+ pages = kmalloc(pagecount * sizeof(struct page *), GFP_KERNEL);
+ if (!pages)
+ goto out_task;
+
+ down_read(¤t->mm->mmap_sem);
+ ret = get_user_pages(current, current->mm, uaddr, pagecount,
+ 1, 0, pages, NULL);
+ up_read(¤t->mm->mmap_sem);
+
+ if (ret < 0)
+ goto out_free;
+
+ pm.out = buf;
+ pm.end = buf + count;
+
+ if (!ptrace_may_attach(task)) {
+ ret = -EIO;
+ } else {
+ unsigned long src = *ppos;
+ unsigned long svpfn = src / PM_ENTRY_BYTES;
+ unsigned long start_vaddr = svpfn << PAGE_SHIFT;
+ unsigned long end_vaddr = TASK_SIZE_OF(task);
+
+ /* watch out for wraparound */
+ if (svpfn > TASK_SIZE_OF(task) >> PAGE_SHIFT)
+ start_vaddr = end_vaddr;
+
+ /*
+ * The odds are that this will stop walking way
+ * before end_vaddr, because the length of the
+ * user buffer is tracked in "pm", and the walk
+ * will stop when we hit the end of the buffer.
+ */
+ ret = walk_page_range(mm, start_vaddr, end_vaddr,
+ &pagemap_walk, &pm);
+ if (ret == PM_END_OF_BUFFER)
+ ret = 0;
+ /* don't need mmap_sem for these, but this looks cleaner */
+ *ppos += pm.out - buf;
+ if (!ret)
+ ret = pm.out - buf;
+ }
+
+ for (; pagecount; pagecount--) {
+ page = pages[pagecount-1];
+ if (!PageReserved(page))
+ SetPageDirty(page);
+ page_cache_release(page);
+ }
+ mmput(mm);
+out_free:
+ kfree(pages);
+out_task:
+ put_task_struct(task);
+out:
+ return ret;
+}
+
+const struct file_operations proc_pagemap_operations = {
+ .llseek = mem_lseek, /* borrow this */
+ .read = pagemap_read,
+};
+#endif /* CONFIG_PROC_PAGE_MONITOR */
+
#ifdef CONFIG_NUMA
extern int show_numa_map(struct seq_file *m, void *v);
return show_numa_map(m, v);
}
-static struct seq_operations proc_pid_numa_maps_op = {
+static const struct seq_operations proc_pid_numa_maps_op = {
.start = m_start,
.next = m_next,
.stop = m_stop,
.release = seq_release_private,
};
#endif
-
projects / ~andy / linux / blobdiff