[RFC v13][PATCH 07/14] Restore memory address space

From: Oren Laadan
Date: Tue Jan 27 2009 - 12:14:25 EST


Restoring the memory address space begins with nuking the existing one
of the current process, and then reading the VMA state and contents.
Call do_mmap_pgoffset() for each VMA and then read in the data.

Changelog[v13]:
- Avoid access to hh->vma_type after the header is freed
- Test for no vma's in exit_mmap() before calling unmap_vma() (or it
may crash if restart fails after having removed all vma's)

Changelog[v12]:
- Replace obsolete cr_debug() with pr_debug()

Changelog[v9]:
- Introduce cr_ctx_checkpoint() for checkpoint-specific ctx setup

Changelog[v7]:
- Fix argument given to kunmap_atomic() in memory dump/restore

Changelog[v6]:
- Balance all calls to cr_hbuf_get() with matching cr_hbuf_put()
(even though it's not really needed)

Changelog[v5]:
- Improve memory restore code (following Dave Hansen's comments)
- Change dump format (and code) to allow chunks of <vaddrs, pages>
instead of one long list of each
- Memory restore now maps user pages explicitly to copy data into them,
instead of reading directly to user space; got rid of mprotect_fixup()

Changelog[v4]:
- Use standard list_... for cr_pgarr


Signed-off-by: Oren Laadan <orenl@xxxxxxxxxxxxxxx>
Acked-by: Serge Hallyn <serue@xxxxxxxxxx>
Signed-off-by: Dave Hansen <dave@xxxxxxxxxxxxxxxxxx>
---
arch/x86/include/asm/checkpoint_hdr.h | 5 +
arch/x86/mm/restart.c | 58 +++++
checkpoint/Makefile | 2 +-
checkpoint/checkpoint_arch.h | 2 +
checkpoint/checkpoint_mem.h | 5 +
checkpoint/restart.c | 51 +++++
checkpoint/rstr_mem.c | 386 +++++++++++++++++++++++++++++++++
include/linux/checkpoint.h | 4 +
mm/mmap.c | 2 +-
9 files changed, 513 insertions(+), 2 deletions(-)
create mode 100644 checkpoint/rstr_mem.c

diff --git a/arch/x86/include/asm/checkpoint_hdr.h b/arch/x86/include/asm/checkpoint_hdr.h
index eb95705..6185548 100644
--- a/arch/x86/include/asm/checkpoint_hdr.h
+++ b/arch/x86/include/asm/checkpoint_hdr.h
@@ -102,4 +102,9 @@ struct cr_hdr_mm_context {
__s16 nldt;
} __attribute__((aligned(8)));

+#ifdef __KERNEL__
+/* misc prototypes from kernel (not defined elsewhere) */
+asmlinkage int sys_modify_ldt(int func, void __user *ptr, unsigned long bytecount);
+#endif
+
#endif /* __ASM_X86_CKPT_HDR__H */
diff --git a/arch/x86/mm/restart.c b/arch/x86/mm/restart.c
index f5c3f16..a682a1d 100644
--- a/arch/x86/mm/restart.c
+++ b/arch/x86/mm/restart.c
@@ -232,3 +232,61 @@ int cr_read_head_arch(struct cr_ctx *ctx)

return ret;
}
+
+int cr_read_mm_context(struct cr_ctx *ctx, struct mm_struct *mm, int rparent)
+{
+ struct cr_hdr_mm_context *hh = cr_hbuf_get(ctx, sizeof(*hh));
+ int n, parent, ret = -EINVAL;
+
+ parent = cr_read_obj_type(ctx, hh, sizeof(*hh), CR_HDR_MM_CONTEXT);
+ pr_debug("parent %d rparent %d nldt %d\n", parent, rparent, hh->nldt);
+ if (parent < 0) {
+ ret = parent;
+ goto out;
+ }
+ if (parent != rparent)
+ goto out;
+
+ if (hh->nldt < 0 || hh->ldt_entry_size != LDT_ENTRY_SIZE)
+ goto out;
+
+ /*
+ * to utilize the syscall modify_ldt() we first convert the data
+ * in the checkpoint image from 'struct desc_struct' to 'struct
+ * user_desc' with reverse logic of include/asm/desc.h:fill_ldt()
+ */
+
+ for (n = 0; n < hh->nldt; n++) {
+ struct user_desc info;
+ struct desc_struct desc;
+ mm_segment_t old_fs;
+
+ ret = cr_kread(ctx, &desc, LDT_ENTRY_SIZE);
+ if (ret < 0)
+ goto out;
+
+ info.entry_number = n;
+ info.base_addr = desc.base0 | (desc.base1 << 16);
+ info.limit = desc.limit0;
+ info.seg_32bit = desc.d;
+ info.contents = desc.type >> 2;
+ info.read_exec_only = (desc.type >> 1) ^ 1;
+ info.limit_in_pages = desc.g;
+ info.seg_not_present = desc.p ^ 1;
+ info.useable = desc.avl;
+
+ old_fs = get_fs();
+ set_fs(get_ds());
+ ret = sys_modify_ldt(1, (struct user_desc __user *) &info,
+ sizeof(info));
+ set_fs(old_fs);
+
+ if (ret < 0)
+ goto out;
+ }
+
+ ret = 0;
+ out:
+ cr_hbuf_put(ctx, sizeof(*hh));
+ return ret;
+}
diff --git a/checkpoint/Makefile b/checkpoint/Makefile
index 3a0df6d..ac35033 100644
--- a/checkpoint/Makefile
+++ b/checkpoint/Makefile
@@ -3,4 +3,4 @@
#

obj-$(CONFIG_CHECKPOINT_RESTART) += sys.o checkpoint.o restart.o \
- ckpt_mem.o
+ ckpt_mem.o rstr_mem.o
diff --git a/checkpoint/checkpoint_arch.h b/checkpoint/checkpoint_arch.h
index f06c7eb..39c8224 100644
--- a/checkpoint/checkpoint_arch.h
+++ b/checkpoint/checkpoint_arch.h
@@ -9,3 +9,5 @@ extern int cr_write_mm_context(struct cr_ctx *ctx,
extern int cr_read_head_arch(struct cr_ctx *ctx);
extern int cr_read_thread(struct cr_ctx *ctx);
extern int cr_read_cpu(struct cr_ctx *ctx);
+extern int cr_read_mm_context(struct cr_ctx *ctx,
+ struct mm_struct *mm, int parent);
diff --git a/checkpoint/checkpoint_mem.h b/checkpoint/checkpoint_mem.h
index 3e48bc4..de1d4c8 100644
--- a/checkpoint/checkpoint_mem.h
+++ b/checkpoint/checkpoint_mem.h
@@ -38,4 +38,9 @@ static inline int cr_pgarr_is_full(struct cr_pgarr *pgarr)
return (pgarr->nr_used == CR_PGARR_TOTAL);
}

+static inline int cr_pgarr_nr_free(struct cr_pgarr *pgarr)
+{
+ return CR_PGARR_TOTAL - pgarr->nr_used;
+}
+
#endif /* _CHECKPOINT_CKPT_MEM_H_ */
diff --git a/checkpoint/restart.c b/checkpoint/restart.c
index f40b619..536d017 100644
--- a/checkpoint/restart.c
+++ b/checkpoint/restart.c
@@ -120,6 +120,44 @@ int cr_read_string(struct cr_ctx *ctx, char *str, int len)
return ret;
}

+/**
+ * cr_read_fname - read a file name
+ * @ctx: checkpoint context
+ * @fname: buffer
+ * @n: buffer length
+ */
+int cr_read_fname(struct cr_ctx *ctx, char *fname, int flen)
+{
+ return cr_read_buf_type(ctx, fname, &flen, CR_HDR_FNAME);
+}
+
+/**
+ * cr_read_open_fname - read a file name and open a file
+ * @ctx: checkpoint context
+ * @flags: file flags
+ * @mode: file mode
+ */
+struct file *cr_read_open_fname(struct cr_ctx *ctx, int flags, int mode)
+{
+ struct file *file;
+ char *fname;
+ int ret;
+
+ fname = kmalloc(PATH_MAX, GFP_KERNEL);
+ if (!fname)
+ return ERR_PTR(-ENOMEM);
+
+ ret = cr_read_fname(ctx, fname, PATH_MAX);
+ pr_debug("fname '%s' flags %#x mode %#x\n", fname, flags, mode);
+ if (ret >= 0)
+ file = filp_open(fname, flags, mode);
+ else
+ file = ERR_PTR(ret);
+
+ kfree(fname);
+ return file;
+}
+
/* read the checkpoint header */
static int cr_read_head(struct cr_ctx *ctx)
{
@@ -219,6 +257,10 @@ static int cr_read_task(struct cr_ctx *ctx)
pr_debug("task_struct: ret %d\n", ret);
if (ret < 0)
goto out;
+ ret = cr_read_mm(ctx);
+ pr_debug("memory: ret %d\n", ret);
+ if (ret < 0)
+ goto out;
ret = cr_read_thread(ctx);
pr_debug("thread: ret %d\n", ret);
if (ret < 0)
@@ -230,10 +272,19 @@ static int cr_read_task(struct cr_ctx *ctx)
return ret;
}

+/* setup restart-specific parts of ctx */
+static int cr_ctx_restart(struct cr_ctx *ctx)
+{
+ return 0;
+}
+
int do_restart(struct cr_ctx *ctx, pid_t pid)
{
int ret;

+ ret = cr_ctx_restart(ctx);
+ if (ret < 0)
+ goto out;
ret = cr_read_head(ctx);
if (ret < 0)
goto out;
diff --git a/checkpoint/rstr_mem.c b/checkpoint/rstr_mem.c
new file mode 100644
index 0000000..4d5ce1a
--- /dev/null
+++ b/checkpoint/rstr_mem.c
@@ -0,0 +1,386 @@
+/*
+ * Restart memory contents
+ *
+ * Copyright (C) 2008 Oren Laadan
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License. See the file COPYING in the main directory of the Linux
+ * distribution for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/fcntl.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/pagemap.h>
+#include <linux/mm_types.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/err.h>
+#include <linux/checkpoint.h>
+#include <linux/checkpoint_hdr.h>
+
+#include "checkpoint_arch.h"
+#include "checkpoint_mem.h"
+
+/*
+ * Unlike checkpoint, restart is executed in the context of each restarting
+ * process: vma regions are restored via a call to mmap(), and the data is
+ * read into the address space of the current process.
+ */
+
+/**
+ * cr_read_pages_vaddrs - read addresses of pages to page-array chain
+ * @ctx - restart context
+ * @nr_pages - number of address to read
+ */
+static int cr_read_pages_vaddrs(struct cr_ctx *ctx, unsigned long nr_pages)
+{
+ struct cr_pgarr *pgarr;
+ unsigned long *vaddrp;
+ int nr, ret;
+
+ while (nr_pages) {
+ pgarr = cr_pgarr_current(ctx);
+ if (!pgarr)
+ return -ENOMEM;
+ nr = cr_pgarr_nr_free(pgarr);
+ if (nr > nr_pages)
+ nr = nr_pages;
+ vaddrp = &pgarr->vaddrs[pgarr->nr_used];
+ ret = cr_kread(ctx, vaddrp, nr * sizeof(unsigned long));
+ if (ret < 0)
+ return ret;
+ pgarr->nr_used += nr;
+ nr_pages -= nr;
+ }
+ return 0;
+}
+
+static int cr_page_read(struct cr_ctx *ctx, struct page *page, char *buf)
+{
+ void *ptr;
+ int ret;
+
+ ret = cr_kread(ctx, buf, PAGE_SIZE);
+ if (ret < 0)
+ return ret;
+
+ ptr = kmap_atomic(page, KM_USER1);
+ memcpy(ptr, buf, PAGE_SIZE);
+ kunmap_atomic(ptr, KM_USER1);
+
+ return 0;
+}
+
+/**
+ * cr_read_pages_contents - read in data of pages in page-array chain
+ * @ctx - restart context
+ */
+static int cr_read_pages_contents(struct cr_ctx *ctx)
+{
+ struct mm_struct *mm = current->mm;
+ struct cr_pgarr *pgarr;
+ unsigned long *vaddrs;
+ char *buf;
+ int i, ret = 0;
+
+ buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ if (!buf)
+ return -ENOMEM;
+
+ down_read(&mm->mmap_sem);
+ list_for_each_entry_reverse(pgarr, &ctx->pgarr_list, list) {
+ vaddrs = pgarr->vaddrs;
+ for (i = 0; i < pgarr->nr_used; i++) {
+ struct page *page;
+
+ ret = get_user_pages(current, mm, vaddrs[i],
+ 1, 1, 1, &page, NULL);
+ if (ret < 0)
+ goto out;
+
+ ret = cr_page_read(ctx, page, buf);
+ page_cache_release(page);
+
+ if (ret < 0)
+ goto out;
+ }
+ }
+
+ out:
+ up_read(&mm->mmap_sem);
+ kfree(buf);
+ return 0;
+}
+
+/**
+ * cr_read_private_vma_contents - restore contents of a VMA with private memory
+ * @ctx - restart context
+ *
+ * Reads a header that specifies how many pages will follow, then reads
+ * a list of virtual addresses into ctx->pgarr_list page-array chain,
+ * followed by the actual contents of the corresponding pages. Iterates
+ * these steps until reaching a header specifying "0" pages, which marks
+ * the end of the contents.
+ */
+static int cr_read_private_vma_contents(struct cr_ctx *ctx)
+{
+ struct cr_hdr_pgarr *hh;
+ unsigned long nr_pages;
+ int parent, ret = 0;
+
+ while (1) {
+ hh = cr_hbuf_get(ctx, sizeof(*hh));
+ parent = cr_read_obj_type(ctx, hh, sizeof(*hh), CR_HDR_PGARR);
+ if (parent != 0) {
+ if (parent < 0)
+ ret = parent;
+ else
+ ret = -EINVAL;
+ cr_hbuf_put(ctx, sizeof(*hh));
+ break;
+ }
+
+ pr_debug("nr_pages %ld\n", (unsigned long) hh->nr_pages);
+
+ nr_pages = hh->nr_pages;
+ cr_hbuf_put(ctx, sizeof(*hh));
+
+ if (!nr_pages)
+ break;
+
+ ret = cr_read_pages_vaddrs(ctx, nr_pages);
+ if (ret < 0)
+ break;
+ ret = cr_read_pages_contents(ctx);
+ if (ret < 0)
+ break;
+ cr_pgarr_reset_all(ctx);
+ }
+
+ return ret;
+}
+
+/**
+ * cr_calc_map_prot_bits - convert vm_flags to mmap protection
+ * orig_vm_flags: source vm_flags
+ */
+static unsigned long cr_calc_map_prot_bits(unsigned long orig_vm_flags)
+{
+ unsigned long vm_prot = 0;
+
+ if (orig_vm_flags & VM_READ)
+ vm_prot |= PROT_READ;
+ if (orig_vm_flags & VM_WRITE)
+ vm_prot |= PROT_WRITE;
+ if (orig_vm_flags & VM_EXEC)
+ vm_prot |= PROT_EXEC;
+ if (orig_vm_flags & PROT_SEM) /* only (?) with IPC-SHM */
+ vm_prot |= PROT_SEM;
+
+ return vm_prot;
+}
+
+/**
+ * cr_calc_map_flags_bits - convert vm_flags to mmap flags
+ * orig_vm_flags: source vm_flags
+ */
+static unsigned long cr_calc_map_flags_bits(unsigned long orig_vm_flags)
+{
+ unsigned long vm_flags = 0;
+
+ vm_flags = MAP_FIXED;
+ if (orig_vm_flags & VM_GROWSDOWN)
+ vm_flags |= MAP_GROWSDOWN;
+ if (orig_vm_flags & VM_DENYWRITE)
+ vm_flags |= MAP_DENYWRITE;
+ if (orig_vm_flags & VM_EXECUTABLE)
+ vm_flags |= MAP_EXECUTABLE;
+ if (orig_vm_flags & VM_MAYSHARE)
+ vm_flags |= MAP_SHARED;
+ else
+ vm_flags |= MAP_PRIVATE;
+
+ return vm_flags;
+}
+
+static int cr_read_vma(struct cr_ctx *ctx, struct mm_struct *mm)
+{
+ struct cr_hdr_vma *hh = cr_hbuf_get(ctx, sizeof(*hh));
+ unsigned long vm_size, vm_start, vm_flags, vm_prot, vm_pgoff;
+ unsigned long addr;
+ enum vm_type vma_type;
+ struct file *file = NULL;
+ int parent, ret = -EINVAL;
+
+ parent = cr_read_obj_type(ctx, hh, sizeof(*hh), CR_HDR_VMA);
+ if (parent < 0) {
+ ret = parent;
+ goto err;
+ } else if (parent != 0)
+ goto err;
+
+ pr_debug("vma %#lx-%#lx type %d\n", (unsigned long) hh->vm_start,
+ (unsigned long) hh->vm_end, (int) hh->vma_type);
+
+ if (hh->vm_end < hh->vm_start)
+ goto err;
+
+ vm_start = hh->vm_start;
+ vm_pgoff = hh->vm_pgoff;
+ vm_size = hh->vm_end - hh->vm_start;
+ vm_prot = cr_calc_map_prot_bits(hh->vm_flags);
+ vm_flags = cr_calc_map_flags_bits(hh->vm_flags);
+ vma_type = hh->vma_type;
+
+ cr_hbuf_put(ctx, sizeof(*hh));
+
+ switch (vma_type) {
+
+ case CR_VMA_ANON: /* anonymous private mapping */
+ if (vm_flags & VM_SHARED)
+ goto err;
+ /*
+ * vm_pgoff for anonymous mapping is the "global" page
+ * offset (namely from addr 0x0), so we force a zero
+ */
+ vm_pgoff = 0;
+ break;
+
+ case CR_VMA_FILE: /* private mapping from a file */
+ if (vm_flags & VM_SHARED)
+ goto err;
+ /*
+ * for private mapping using 'read-only' is sufficient
+ */
+ file = cr_read_open_fname(ctx, O_RDONLY, 0);
+ if (IS_ERR(file)) {
+ ret = PTR_ERR(file);
+ goto err;
+ }
+ break;
+
+ default:
+ goto err;
+
+ }
+
+
+ down_write(&mm->mmap_sem);
+ addr = do_mmap_pgoff(file, vm_start, vm_size,
+ vm_prot, vm_flags, vm_pgoff);
+ up_write(&mm->mmap_sem);
+ pr_debug("size %#lx prot %#lx flag %#lx pgoff %#lx => %#lx\n",
+ vm_size, vm_prot, vm_flags, vm_pgoff, addr);
+
+ /* the file (if opened) is now referenced by the vma */
+ if (file)
+ filp_close(file, NULL);
+
+ if (IS_ERR((void *) addr))
+ return PTR_ERR((void *) addr);
+
+ /*
+ * CR_VMA_ANON: read in memory as is
+ * CR_VMA_FILE: read in memory as is
+ * (more to follow ...)
+ */
+
+ switch (vma_type) {
+ case CR_VMA_ANON:
+ case CR_VMA_FILE:
+ /* standard case: read the data into the memory */
+ ret = cr_read_private_vma_contents(ctx);
+ break;
+ }
+
+ if (ret < 0)
+ return ret;
+
+ pr_debug("vma retval %d\n", ret);
+ return 0;
+
+ err:
+ cr_hbuf_put(ctx, sizeof(*hh));
+ return ret;
+}
+
+static int cr_destroy_mm(struct mm_struct *mm)
+{
+ struct vm_area_struct *vmnext = mm->mmap;
+ struct vm_area_struct *vma;
+ int ret;
+
+ while (vmnext) {
+ vma = vmnext;
+ vmnext = vmnext->vm_next;
+ ret = do_munmap(mm, vma->vm_start, vma->vm_end-vma->vm_start);
+ if (ret < 0) {
+ pr_debug("c/r: restart failed do_munmap (%d)\n", ret);
+ return ret;
+ }
+ }
+ return 0;
+}
+
+int cr_read_mm(struct cr_ctx *ctx)
+{
+ struct cr_hdr_mm *hh = cr_hbuf_get(ctx, sizeof(*hh));
+ struct mm_struct *mm;
+ int nr, parent, ret;
+
+ parent = cr_read_obj_type(ctx, hh, sizeof(*hh), CR_HDR_MM);
+ if (parent < 0) {
+ ret = parent;
+ goto out;
+ }
+
+ ret = -EINVAL;
+#if 0 /* activate when containers are used */
+ if (parent != task_pid_vnr(current))
+ goto out;
+#endif
+ pr_debug("map_count %d\n", hh->map_count);
+
+ /* XXX need more sanity checks */
+ if (hh->start_code > hh->end_code ||
+ hh->start_data > hh->end_data || hh->map_count < 0)
+ goto out;
+
+ mm = current->mm;
+
+ /* point of no return -- destruct current mm */
+ down_write(&mm->mmap_sem);
+ ret = cr_destroy_mm(mm);
+ if (ret < 0) {
+ up_write(&mm->mmap_sem);
+ goto out;
+ }
+ mm->start_code = hh->start_code;
+ mm->end_code = hh->end_code;
+ mm->start_data = hh->start_data;
+ mm->end_data = hh->end_data;
+ mm->start_brk = hh->start_brk;
+ mm->brk = hh->brk;
+ mm->start_stack = hh->start_stack;
+ mm->arg_start = hh->arg_start;
+ mm->arg_end = hh->arg_end;
+ mm->env_start = hh->env_start;
+ mm->env_end = hh->env_end;
+ up_write(&mm->mmap_sem);
+
+ /* FIX: need also mm->flags */
+
+ for (nr = hh->map_count; nr; nr--) {
+ ret = cr_read_vma(ctx, mm);
+ if (ret < 0)
+ goto out;
+ }
+
+ ret = cr_read_mm_context(ctx, mm, hh->objref);
+ out:
+ cr_hbuf_put(ctx, sizeof(*hh));
+ return ret;
+}
diff --git a/include/linux/checkpoint.h b/include/linux/checkpoint.h
index f8187ba..06b6e5a 100644
--- a/include/linux/checkpoint.h
+++ b/include/linux/checkpoint.h
@@ -59,6 +59,10 @@ extern int cr_read_buf_type(struct cr_ctx *ctx, void *buf, int *len, int type);
extern int cr_read_buffer(struct cr_ctx *ctx, void *buf, int *len);
extern int cr_read_string(struct cr_ctx *ctx, char *str, int len);

+extern int cr_read_fname(struct cr_ctx *ctx, char *fname, int n);
+extern struct file *cr_read_open_fname(struct cr_ctx *ctx,
+ int flags, int mode);
+
extern int do_checkpoint(struct cr_ctx *ctx, pid_t pid);
extern int cr_write_mm(struct cr_ctx *ctx, struct task_struct *t);

diff --git a/mm/mmap.c b/mm/mmap.c
index d4855a6..b98fb66 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2105,7 +2105,7 @@ void exit_mmap(struct mm_struct *mm)
tlb = tlb_gather_mmu(mm, 1);
/* Don't update_hiwater_rss(mm) here, do_exit already did */
/* Use -1 here to ensure all VMAs in the mm are unmapped */
- end = unmap_vmas(&tlb, vma, 0, -1, &nr_accounted, NULL);
+ end = vma ? unmap_vmas(&tlb, vma, 0, -1, &nr_accounted, NULL) : 0;
vm_unacct_memory(nr_accounted);
free_pgtables(tlb, vma, FIRST_USER_ADDRESS, 0);
tlb_finish_mmu(tlb, 0, end);
--
1.5.4.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/