This ioctl can be used to watch the process's memory and perform
atomic operations which aren't possible through procfs. Three
operations have been implemented:
- PAGEMAP_SD_GET gets the soft dirty pages in a address range.
- PAGEMAP_SD_CLEAR clears the soft dirty bit from dirty pages in a
address range.
- PAGEMAP_SD_GET_AND_CLEAR gets and clears the soft dirty bit in a
address range.
struct pagemap_sd_args is used as the argument of the IOCTL. In this
struct:
- The range is specified through start and len.
- The output buffer and size is specified as vec and vec_len.
- The flags can be specified in the flags field. Currently only one
PAGEMAP_SD_NO_REUSED_REGIONS is supported which can be specified to
ignore the VMA dirty flags.
This is based on a patch from Gabriel Krisman Bertazi.
Signed-off-by: Muhammad Usama Anjum <[email protected]>
---
Changes in v3:
- Tighten the user-kernel interface by using explicit types and add more
error checking
Changes in v2:
- Convert the interface from syscall to ioctl
- Remove pidfd support as it doesn't make sense in ioctl
---
fs/proc/task_mmu.c | 260 ++++++++++++++++++++++++++++++++++
include/uapi/linux/fs.h | 23 +++
tools/include/uapi/linux/fs.h | 23 +++
3 files changed, 306 insertions(+)
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index f66674033207..33d3d5c2ab40 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -19,6 +19,8 @@
#include <linux/shmem_fs.h>
#include <linux/uaccess.h>
#include <linux/pkeys.h>
+#include <uapi/linux/fs.h>
+#include <linux/vmalloc.h>
#include <asm/elf.h>
#include <asm/tlb.h>
@@ -1775,11 +1777,269 @@ static int pagemap_release(struct inode *inode, struct file *file)
return 0;
}
+#ifdef CONFIG_MEM_SOFT_DIRTY
+#define IS_CLEAR_SD_OP(op) (op == PAGEMAP_SD_CLEAR || op == PAGEMAP_SD_GET_AND_CLEAR)
+#define IS_GET_SD_OP(op) (op == PAGEMAP_SD_GET || op == PAGEMAP_SD_GET_AND_CLEAR)
+#define PAGEMAP_SD_FLAGS_MASK (PAGEMAP_SD_NO_REUSED_REGIONS)
+
+struct pagemap_sd_private {
+ unsigned long start;
+ __u64 *vec;
+ unsigned long vec_len;
+ unsigned long index;
+ unsigned int op;
+ unsigned int flags;
+};
+
+static int pagemap_sd_pmd_entry(pmd_t *pmd, unsigned long addr,
+ unsigned long end, struct mm_walk *walk)
+{
+ struct pagemap_sd_private *p = walk->private;
+ struct vm_area_struct *vma = walk->vma;
+ unsigned long start = addr;
+ spinlock_t *ptl;
+ pte_t *pte;
+ int dirty;
+ bool dirty_vma = (p->flags & PAGEMAP_SD_NO_REUSED_REGIONS) ? 0 :
+ (vma->vm_flags & VM_SOFTDIRTY);
+
+ end = min(end, walk->vma->vm_end);
+ ptl = pmd_trans_huge_lock(pmd, vma);
+ if (ptl) {
+ if (dirty_vma || check_soft_dirty_pmd(vma, addr, pmd, false)) {
+ /*
+ * Break huge page into small pages if operation needs to be performed is
+ * on a portion of the huge page or the return buffer cannot store complete
+ * data. Then process this PMD as having normal pages.
+ */
+ if ((IS_CLEAR_SD_OP(p->op) && (end - addr < HPAGE_SIZE)) ||
+ (IS_GET_SD_OP(p->op) && (p->index + HPAGE_SIZE/PAGE_SIZE > p->vec_len))) {
+ spin_unlock(ptl);
+ split_huge_pmd(vma, pmd, addr);
+ goto process_smaller_pages;
+ } else {
+ dirty = check_soft_dirty_pmd(vma, addr, pmd, IS_CLEAR_SD_OP(p->op));
+ if (IS_GET_SD_OP(p->op) && (dirty_vma || dirty)) {
+ for (; addr != end && p->index < p->vec_len;
+ addr += PAGE_SIZE)
+ p->vec[p->index++] = addr - p->start;
+ }
+ }
+ }
+ spin_unlock(ptl);
+ return 0;
+ }
+
+process_smaller_pages:
+ if (pmd_trans_unstable(pmd))
+ return 0;
+
+ pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+ for (; addr != end; pte++, addr += PAGE_SIZE) {
+ dirty = check_soft_dirty(vma, addr, pte, IS_CLEAR_SD_OP(p->op));
+
+ if (IS_GET_SD_OP(p->op) && (dirty_vma || dirty)) {
+ p->vec[p->index++] = addr - p->start;
+ WARN_ON(p->index > p->vec_len);
+ }
+ }
+ pte_unmap_unlock(pte - 1, ptl);
+ cond_resched();
+
+ if (IS_CLEAR_SD_OP(p->op))
+ flush_tlb_mm_range(vma->vm_mm, start, end, PAGE_SHIFT, false);
+
+ return 0;
+}
+
+static int pagemap_sd_pte_hole(unsigned long addr, unsigned long end, int depth,
+ struct mm_walk *walk)
+{
+ struct pagemap_sd_private *p = walk->private;
+ struct vm_area_struct *vma = walk->vma;
+
+ if (p->flags & PAGEMAP_SD_NO_REUSED_REGIONS)
+ return 0;
+
+ if (vma && (vma->vm_flags & VM_SOFTDIRTY) && IS_GET_SD_OP(p->op)) {
+ for (; addr != end && p->index < p->vec_len; addr += PAGE_SIZE)
+ p->vec[p->index++] = addr - p->start;
+ }
+
+ return 0;
+}
+
+static int pagemap_sd_pre_vma(unsigned long start, unsigned long end, struct mm_walk *walk)
+{
+ struct pagemap_sd_private *p = walk->private;
+ struct vm_area_struct *vma = walk->vma;
+ int ret;
+ unsigned long end_cut = end;
+
+ if (p->flags & PAGEMAP_SD_NO_REUSED_REGIONS)
+ return 0;
+
+ if (IS_CLEAR_SD_OP(p->op) && (vma->vm_flags & VM_SOFTDIRTY)) {
+ if (vma->vm_start < start) {
+ ret = split_vma(vma->vm_mm, vma, start, 1);
+ if (ret)
+ return ret;
+ }
+
+ if (IS_GET_SD_OP(p->op))
+ end_cut = min(start + p->vec_len * PAGE_SIZE, end);
+
+ if (vma->vm_end > end_cut) {
+ ret = split_vma(vma->vm_mm, vma, end_cut, 0);
+ if (ret)
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
+static void pagemap_sd_post_vma(struct mm_walk *walk)
+{
+ struct pagemap_sd_private *p = walk->private;
+ struct vm_area_struct *vma = walk->vma;
+
+ if (p->flags & PAGEMAP_SD_NO_REUSED_REGIONS)
+ return;
+
+ if (IS_CLEAR_SD_OP(p->op) && (vma->vm_flags & VM_SOFTDIRTY)) {
+ vma->vm_flags &= ~VM_SOFTDIRTY;
+ vma_set_page_prot(vma);
+ }
+}
+
+static int pagemap_sd_pmd_test_walk(unsigned long start, unsigned long end,
+ struct mm_walk *walk)
+{
+ struct pagemap_sd_private *p = walk->private;
+ struct vm_area_struct *vma = walk->vma;
+
+ if (IS_GET_SD_OP(p->op) && (p->index == p->vec_len))
+ return -1;
+
+ if (vma->vm_flags & VM_PFNMAP)
+ return 1;
+
+ return 0;
+}
+
+static const struct mm_walk_ops pagemap_sd_ops = {
+ .test_walk = pagemap_sd_pmd_test_walk,
+ .pre_vma = pagemap_sd_pre_vma,
+ .pmd_entry = pagemap_sd_pmd_entry,
+ .pte_hole = pagemap_sd_pte_hole,
+ .post_vma = pagemap_sd_post_vma,
+};
+
+static long do_pagemap_sd_cmd(struct mm_struct *mm, unsigned int cmd, struct pagemap_sd_args *arg)
+{
+ struct pagemap_sd_private sd_data;
+ struct mmu_notifier_range range;
+ unsigned long start, end;
+ int ret;
+
+ start = (unsigned long)untagged_addr(arg->start);
+ if ((!IS_ALIGNED(start, PAGE_SIZE)) || (!access_ok((void __user *)start, arg->len)))
+ return -EINVAL;
+
+ if (IS_GET_SD_OP(cmd) &&
+ ((arg->vec_len == 0) || (!arg->vec) || (!access_ok((loff_t *)arg->vec, arg->vec_len))))
+ return -EINVAL;
+
+ if ((arg->flags & ~PAGEMAP_SD_FLAGS_MASK) || (arg->__reserved))
+ return -EINVAL;
+
+ end = start + arg->len;
+ sd_data.start = start;
+ sd_data.op = cmd;
+ sd_data.flags = arg->flags;
+ sd_data.index = 0;
+ sd_data.vec_len = arg->vec_len;
+
+ if (IS_GET_SD_OP(cmd)) {
+ sd_data.vec = vzalloc(arg->vec_len * sizeof(loff_t));
+ if (!sd_data.vec)
+ return -ENOMEM;
+ }
+
+ if (IS_CLEAR_SD_OP(cmd)) {
+ mmap_write_lock(mm);
+
+ mmu_notifier_range_init(&range, MMU_NOTIFY_SOFT_DIRTY, 0, NULL,
+ mm, start, end);
+ mmu_notifier_invalidate_range_start(&range);
+ inc_tlb_flush_pending(mm);
+ } else {
+ mmap_read_lock(mm);
+ }
+
+ ret = walk_page_range(mm, start, end, &pagemap_sd_ops, &sd_data);
+
+ if (IS_CLEAR_SD_OP(cmd)) {
+ mmu_notifier_invalidate_range_end(&range);
+ dec_tlb_flush_pending(mm);
+
+ mmap_write_unlock(mm);
+ } else {
+ mmap_read_unlock(mm);
+ }
+
+ if (ret < 0)
+ goto free_sd_data;
+
+ if (IS_GET_SD_OP(cmd)) {
+ ret = copy_to_user((loff_t *)arg->vec, sd_data.vec, sd_data.index * sizeof(loff_t));
+ if (ret) {
+ ret = -EIO;
+ goto free_sd_data;
+ }
+ ret = sd_data.index;
+ } else {
+ ret = 0;
+ }
+
+free_sd_data:
+ if (IS_GET_SD_OP(cmd))
+ vfree(sd_data.vec);
+
+ return ret;
+}
+
+static long pagemap_sd_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ struct pagemap_sd_args __user *uarg = (struct pagemap_sd_args __user *)arg;
+ struct mm_struct *mm = file->private_data;
+ struct pagemap_sd_args arguments;
+
+ switch (cmd) {
+ case PAGEMAP_SD_GET:
+ fallthrough;
+ case PAGEMAP_SD_CLEAR:
+ fallthrough;
+ case PAGEMAP_SD_GET_AND_CLEAR:
+ if (copy_from_user(&arguments, uarg, sizeof(struct pagemap_sd_args)))
+ return -EFAULT;
+ return do_pagemap_sd_cmd(mm, cmd, &arguments);
+ default:
+ return -EINVAL;
+ }
+}
+#endif /* CONFIG_MEM_SOFT_DIRTY */
+
const struct file_operations proc_pagemap_operations = {
.llseek = mem_lseek, /* borrow this */
.read = pagemap_read,
.open = pagemap_open,
.release = pagemap_release,
+#ifdef CONFIG_MEM_SOFT_DIRTY
+ .unlocked_ioctl = pagemap_sd_ioctl,
+ .compat_ioctl = pagemap_sd_ioctl,
+#endif /* CONFIG_MEM_SOFT_DIRTY */
};
#endif /* CONFIG_PROC_PAGE_MONITOR */
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index b7b56871029c..4f6d1c0ae524 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -305,4 +305,27 @@ typedef int __bitwise __kernel_rwf_t;
#define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
RWF_APPEND)
+/**
+ * struct pagemap_sd_args - Soft-dirty IOCTL argument
+ * @start: Starting address
+ * @len: Length of the region
+ * @vec: Output buffer address
+ * @vec_len: Length of the output buffer
+ * @flags: Special flags for the IOCTL
+ * @__reserved: Reserved member to preserve data alignment. Should be 0.
+ */
+struct pagemap_sd_args {
+ __u64 __user start;
+ __u64 len;
+ __u64 __user vec;
+ __u64 vec_len;
+ __u32 flags;
+ __u32 __reserved;
+};
+
+#define PAGEMAP_SD_GET _IOWR('f', 16, struct pagemap_sd_args)
+#define PAGEMAP_SD_CLEAR _IOWR('f', 17, struct pagemap_sd_args)
+#define PAGEMAP_SD_GET_AND_CLEAR _IOWR('f', 18, struct pagemap_sd_args)
+#define PAGEMAP_SD_NO_REUSED_REGIONS 0x1
+
#endif /* _UAPI_LINUX_FS_H */
diff --git a/tools/include/uapi/linux/fs.h b/tools/include/uapi/linux/fs.h
index b7b56871029c..4f6d1c0ae524 100644
--- a/tools/include/uapi/linux/fs.h
+++ b/tools/include/uapi/linux/fs.h
@@ -305,4 +305,27 @@ typedef int __bitwise __kernel_rwf_t;
#define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\
RWF_APPEND)
+/**
+ * struct pagemap_sd_args - Soft-dirty IOCTL argument
+ * @start: Starting address
+ * @len: Length of the region
+ * @vec: Output buffer address
+ * @vec_len: Length of the output buffer
+ * @flags: Special flags for the IOCTL
+ * @__reserved: Reserved member to preserve data alignment. Should be 0.
+ */
+struct pagemap_sd_args {
+ __u64 __user start;
+ __u64 len;
+ __u64 __user vec;
+ __u64 vec_len;
+ __u32 flags;
+ __u32 __reserved;
+};
+
+#define PAGEMAP_SD_GET _IOWR('f', 16, struct pagemap_sd_args)
+#define PAGEMAP_SD_CLEAR _IOWR('f', 17, struct pagemap_sd_args)
+#define PAGEMAP_SD_GET_AND_CLEAR _IOWR('f', 18, struct pagemap_sd_args)
+#define PAGEMAP_SD_NO_REUSED_REGIONS 0x1
+
#endif /* _UAPI_LINUX_FS_H */
--
2.30.2