[Qemu-devel] [RFC][PATCH 8/8 v3] introduce a new monitor command 'dump' to dump guest's memory

[Wen Congyang]

Signed-off-by: Wen Congyang <address@hidden>
---
 Makefile.target |    8 +-
 dump.c          |  452 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 dump.h          |    4 +
 hmp-commands.hx |   16 ++
 monitor.c       |    3 +
 qmp-commands.hx |   24 +++
 6 files changed, 503 insertions(+), 4 deletions(-)
 create mode 100644 dump.c

diff --git a/Makefile.target b/Makefile.target
index 29562ad..f7cc2b9 100644
--- a/Makefile.target
+++ b/Makefile.target
@@ -110,7 +110,7 @@ $(call set-vpath, 
$(SRC_PATH)/linux-user:$(SRC_PATH)/linux-user/$(TARGET_ABI_DIR
 QEMU_CFLAGS+=-I$(SRC_PATH)/linux-user/$(TARGET_ABI_DIR) 
-I$(SRC_PATH)/linux-user
 obj-y = main.o syscall.o strace.o mmap.o signal.o thunk.o \
       elfload.o linuxload.o uaccess.o gdbstub.o cpu-uname.o \
-      user-exec.o $(oslib-obj-y)
+      user-exec.o $(oslib-obj-y) dump.o
 
 obj-$(TARGET_HAS_BFLT) += flatload.o
 
@@ -148,7 +148,7 @@ LDFLAGS+=-Wl,-segaddr,__STD_PROG_ZONE,0x1000 -image_base 
0x0e000000
 LIBS+=-lmx
 
 obj-y = main.o commpage.o machload.o mmap.o signal.o syscall.o thunk.o \
-        gdbstub.o user-exec.o
+        gdbstub.o user-exec.o dump.o
 
 obj-i386-y += ioport-user.o
 
@@ -170,7 +170,7 @@ $(call set-vpath, $(SRC_PATH)/bsd-user)
 QEMU_CFLAGS+=-I$(SRC_PATH)/bsd-user -I$(SRC_PATH)/bsd-user/$(TARGET_ARCH)
 
 obj-y = main.o bsdload.o elfload.o mmap.o signal.o strace.o syscall.o \
-        gdbstub.o uaccess.o user-exec.o
+        gdbstub.o uaccess.o user-exec.o dump.o
 
 obj-i386-y += ioport-user.o
 
@@ -186,7 +186,7 @@ endif #CONFIG_BSD_USER
 # System emulator target
 ifdef CONFIG_SOFTMMU
 
-obj-y = arch_init.o cpus.o monitor.o machine.o gdbstub.o balloon.o ioport.o
+obj-y = arch_init.o cpus.o monitor.o machine.o gdbstub.o balloon.o ioport.o 
dump.o
 # virtio has to be here due to weird dependency between PCI and virtio-net.
 # need to fix this properly
 obj-$(CONFIG_NO_PCI) += pci-stub.o
diff --git a/dump.c b/dump.c
new file mode 100644
index 0000000..81e466f
--- /dev/null
+++ b/dump.c
@@ -0,0 +1,452 @@
+/*
+ * QEMU dump
+ *
+ * Copyright Fujitsu, Corp. 2011
+ *
+ * Authors:
+ *     Wen Congyang <address@hidden>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu-common.h"
+#include <unistd.h>
+#include <elf.h>
+#include <sys/procfs.h>
+#include "cpu.h"
+#include "cpu-all.h"
+#include "targphys.h"
+#include "monitor.h"
+#include "kvm.h"
+#include "dump.h"
+#include "sysemu.h"
+#include "bswap.h"
+#include "memory_mapping.h"
+
+#define CPU_CONVERT_TO_TARGET16(val) \
+({ \
+    uint16_t _val = (val); \
+    if (endian == ELFDATA2LSB) { \
+        _val = cpu_to_le16(_val); \
+    } else {\
+        _val = cpu_to_be16(_val); \
+    } \
+    _val; \
+})
+
+#define CPU_CONVERT_TO_TARGET32(val) \
+({ \
+    uint32_t _val = (val); \
+    if (endian == ELFDATA2LSB) { \
+        _val = cpu_to_le32(_val); \
+    } else {\
+        _val = cpu_to_be32(_val); \
+    } \
+    _val; \
+})
+
+#define CPU_CONVERT_TO_TARGET64(val) \
+({ \
+    uint64_t _val = (val); \
+    if (endian == ELFDATA2LSB) { \
+        _val = cpu_to_le64(_val); \
+    } else {\
+        _val = cpu_to_be64(_val); \
+    } \
+    _val; \
+})
+
+static inline int cpuid(CPUState *env)
+{
+#if defined(CONFIG_USER_ONLY) && defined(CONFIG_USE_NPTL)
+    return env->host_tid;
+#else
+    return env->cpu_index + 1;
+#endif
+}
+
+static int write_elf64_header(Monitor *mon, int fd, int phdr_num, int machine,
+                              int endian)
+{
+    Elf64_Ehdr elf_header;
+    int ret;
+
+    memset(&elf_header, 0, sizeof(Elf64_Ehdr));
+    memcpy(&elf_header, ELFMAG, 4);
+    elf_header.e_ident[EI_CLASS] = ELFCLASS64;
+    elf_header.e_ident[EI_DATA] = endian;
+    elf_header.e_ident[EI_VERSION] = EV_CURRENT;
+    elf_header.e_type = CPU_CONVERT_TO_TARGET16(ET_CORE);
+    elf_header.e_machine = CPU_CONVERT_TO_TARGET16(machine);
+    elf_header.e_version = CPU_CONVERT_TO_TARGET32(EV_CURRENT);
+    elf_header.e_ehsize = CPU_CONVERT_TO_TARGET16(sizeof(elf_header));
+    elf_header.e_phoff = CPU_CONVERT_TO_TARGET64(sizeof(Elf64_Ehdr));
+    elf_header.e_phentsize = CPU_CONVERT_TO_TARGET16(sizeof(Elf64_Phdr));
+    elf_header.e_phnum = CPU_CONVERT_TO_TARGET16(phdr_num);
+
+    lseek(fd, 0, SEEK_SET);
+    ret = write(fd, &elf_header, sizeof(elf_header));
+    if (ret < 0) {
+        monitor_printf(mon, "dump: failed to write elf header.\n");
+        return -1;
+    }
+
+    return 0;
+}
+
+static int write_elf32_header(Monitor *mon, int fd, int phdr_num, int machine,
+                              int endian)
+{
+    Elf32_Ehdr elf_header;
+    int ret;
+
+    memset(&elf_header, 0, sizeof(Elf32_Ehdr));
+    memcpy(&elf_header, ELFMAG, 4);
+    elf_header.e_ident[EI_CLASS] = ELFCLASS32;
+    elf_header.e_ident[EI_DATA] = endian;
+    elf_header.e_ident[EI_VERSION] = EV_CURRENT;
+    elf_header.e_type = CPU_CONVERT_TO_TARGET16(ET_CORE);
+    elf_header.e_machine = CPU_CONVERT_TO_TARGET16(machine);
+    elf_header.e_version = CPU_CONVERT_TO_TARGET32(EV_CURRENT);
+    elf_header.e_ehsize = CPU_CONVERT_TO_TARGET16(sizeof(elf_header));
+    elf_header.e_phoff = CPU_CONVERT_TO_TARGET32(sizeof(Elf32_Ehdr));
+    elf_header.e_phentsize = CPU_CONVERT_TO_TARGET16(sizeof(Elf32_Phdr));
+    elf_header.e_phnum = CPU_CONVERT_TO_TARGET16(phdr_num);
+
+    lseek(fd, 0, SEEK_SET);
+    ret = write(fd, &elf_header, sizeof(elf_header));
+    if (ret < 0) {
+        monitor_printf(mon, "dump: failed to write elf header.\n");
+        return -1;
+    }
+
+    return 0;
+}
+
+static int write_elf64_load(Monitor *mon, int fd, MemoryMapping 
*memory_mapping,
+                            int phdr_index, target_phys_addr_t offset,
+                            int endian)
+{
+    Elf64_Phdr phdr;
+    off_t phdr_offset;
+    int ret;
+
+    memset(&phdr, 0, sizeof(Elf64_Phdr));
+    phdr.p_type = CPU_CONVERT_TO_TARGET32(PT_LOAD);
+    phdr.p_offset = CPU_CONVERT_TO_TARGET64(offset);
+    phdr.p_paddr = CPU_CONVERT_TO_TARGET64(memory_mapping->phys_addr);
+    if (offset == -1) {
+        phdr.p_filesz = 0;
+    } else {
+        phdr.p_filesz = CPU_CONVERT_TO_TARGET64(memory_mapping->length);
+    }
+    phdr.p_memsz = CPU_CONVERT_TO_TARGET64(memory_mapping->length);
+    phdr.p_vaddr = CPU_CONVERT_TO_TARGET64(memory_mapping->virt_addr);
+
+    phdr_offset = sizeof(Elf64_Ehdr) + sizeof(Elf64_Phdr)*phdr_index;
+    lseek(fd, phdr_offset, SEEK_SET);
+    ret = write(fd, &phdr, sizeof(Elf64_Phdr));
+    if (ret < 0) {
+        monitor_printf(mon, "dump: failed to write program header table.\n");
+        return -1;
+    }
+
+    return 0;
+}
+
+static int write_elf32_load(Monitor *mon, int fd, MemoryMapping 
*memory_mapping,
+                            int phdr_index, target_phys_addr_t offset,
+                            int endian)
+{
+    Elf32_Phdr phdr;
+    off_t phdr_offset;
+    int ret;
+
+    memset(&phdr, 0, sizeof(Elf32_Phdr));
+    phdr.p_type = CPU_CONVERT_TO_TARGET32(PT_LOAD);
+    phdr.p_offset = CPU_CONVERT_TO_TARGET32(offset);
+    phdr.p_paddr = CPU_CONVERT_TO_TARGET32(memory_mapping->phys_addr);
+    if (offset == -1) {
+        phdr.p_filesz = 0;
+    } else {
+        phdr.p_filesz = CPU_CONVERT_TO_TARGET32(memory_mapping->length);
+    }
+    phdr.p_memsz = CPU_CONVERT_TO_TARGET32(memory_mapping->length);
+    phdr.p_vaddr = CPU_CONVERT_TO_TARGET32(memory_mapping->virt_addr);
+
+    phdr_offset = sizeof(Elf32_Ehdr) + sizeof(Elf32_Phdr)*phdr_index;
+    lseek(fd, phdr_offset, SEEK_SET);
+    ret = write(fd, &phdr, sizeof(Elf32_Phdr));
+    if (ret < 0) {
+        monitor_printf(mon, "dump: failed to write program header table.\n");
+        return -1;
+    }
+
+    return 0;
+}
+
+static int write_elf64_notes(Monitor *mon, int fd, int phdr_index,
+                             target_phys_addr_t *offset, int endian)
+{
+    CPUState *env;
+    int ret;
+    target_phys_addr_t begin = *offset;
+    Elf64_Phdr phdr;
+    off_t phdr_offset;
+    int id;
+
+    for (env = first_cpu; env != NULL; env = env->next_cpu) {
+        id = cpuid(env);
+        ret = cpu_write_elf64_note(mon, fd, env, id, offset);
+        if (ret < 0) {
+            monitor_printf(mon, "dump: failed to write elf notes.\n");
+            return -1;
+        }
+    }
+
+    memset(&phdr, 0, sizeof(Elf64_Phdr));
+    phdr.p_type = CPU_CONVERT_TO_TARGET32(PT_NOTE);
+    phdr.p_offset = CPU_CONVERT_TO_TARGET64(begin);
+    phdr.p_paddr = 0;
+    phdr.p_filesz = CPU_CONVERT_TO_TARGET64(*offset - begin);
+    phdr.p_memsz = CPU_CONVERT_TO_TARGET64(*offset - begin);
+    phdr.p_vaddr = 0;
+
+    phdr_offset = sizeof(Elf64_Ehdr);
+    lseek(fd, phdr_offset, SEEK_SET);
+    ret = write(fd, &phdr, sizeof(Elf64_Phdr));
+    if (ret < 0) {
+        monitor_printf(mon, "dump: failed to write program header table.\n");
+        return -1;
+    }
+
+    return 0;
+}
+
+static int write_elf32_notes(Monitor *mon, int fd, int phdr_index,
+                             target_phys_addr_t *offset, int endian)
+{
+    CPUState *env;
+    int ret;
+    target_phys_addr_t begin = *offset;
+    Elf32_Phdr phdr;
+    off_t phdr_offset;
+    int id;
+
+    for (env = first_cpu; env != NULL; env = env->next_cpu) {
+        id = cpuid(env);
+        ret = cpu_write_elf32_note(mon, fd, env, id, offset);
+        if (ret < 0) {
+            monitor_printf(mon, "dump: failed to write elf notes.\n");
+            return -1;
+        }
+    }
+
+    memset(&phdr, 0, sizeof(Elf32_Phdr));
+    phdr.p_type = CPU_CONVERT_TO_TARGET32(PT_NOTE);
+    phdr.p_offset = CPU_CONVERT_TO_TARGET32(begin);
+    phdr.p_paddr = 0;
+    phdr.p_filesz = CPU_CONVERT_TO_TARGET32(*offset - begin);
+    phdr.p_memsz = CPU_CONVERT_TO_TARGET32(*offset - begin);
+    phdr.p_vaddr = 0;
+
+    phdr_offset = sizeof(Elf32_Ehdr);
+    lseek(fd, phdr_offset, SEEK_SET);
+    ret = write(fd, &phdr, sizeof(Elf32_Phdr));
+    if (ret < 0) {
+        monitor_printf(mon, "dump: failed to write program header table.\n");
+        return -1;
+    }
+
+    return 0;
+}
+
+static int write_data(Monitor *mon, int fd, void *buf, int length,
+                      target_phys_addr_t *offset)
+{
+    int ret;
+
+    lseek(fd, *offset, SEEK_SET);
+    ret = write(fd, buf, length);
+    if (ret < 0) {
+        monitor_printf(mon, "dump: failed to save memory.\n");
+        return -1;
+    }
+
+    *offset += length;
+    return 0;
+}
+
+/* write the memroy to vmcore. 1 page per I/O. */
+static int write_memory(Monitor *mon, int fd, RAMBlock *block,
+                        target_phys_addr_t *offset)
+{
+    int i, ret;
+
+    for (i = 0; i < block->length / TARGET_PAGE_SIZE; i++) {
+        ret = write_data(mon, fd, block->host + i * TARGET_PAGE_SIZE,
+                         TARGET_PAGE_SIZE, offset);
+        if (ret < 0) {
+            return -1;
+        }
+    }
+
+    if ((block->length % TARGET_PAGE_SIZE) != 0) {
+        ret = write_data(mon, fd, block->host + i * TARGET_PAGE_SIZE,
+                        block->length % TARGET_PAGE_SIZE, offset);
+        if (ret < 0) {
+            return -1;
+        }
+    }
+
+    return 0;
+}
+
+/* get the memory's offset in the vmcore */
+static target_phys_addr_t get_offset(target_phys_addr_t phys_addr,
+                                     target_phys_addr_t memory_offset)
+{
+    RAMBlock *block;
+    target_phys_addr_t offset = memory_offset;
+
+    QLIST_FOREACH(block, &ram_list.blocks, next) {
+        if (phys_addr >= block->offset &&
+            phys_addr < block->offset + block->length) {
+            return phys_addr - block->offset + offset;
+        }
+        offset += block->length;
+    }
+
+    return -1;
+}
+
+static int create_vmcore(Monitor *mon, int fd)
+{
+    CPUState *env;
+    target_phys_addr_t offset, memory_offset;
+    int phdr_num, phdr_index;
+    RAMBlock *block;
+    int ret;
+    MemoryMappingList list;
+    MemoryMapping *memory_mapping;
+    DumpInfo info;
+
+    for (env = first_cpu; env != NULL; env = env->next_cpu) {
+        cpu_synchronize_state(env);
+    }
+
+    list.num = 0;
+    QTAILQ_INIT(&list.head);
+    get_memory_mapping(&list);
+
+    ret = cpu_get_dump_info(&info);
+    if (ret < 0) {
+        monitor_printf(mon, "dump: unsupported target.\n");
+        goto error;
+    }
+
+    phdr_num = 1; /* PT_NOTE */
+    /* the type of phdr->num is uint16_t, so we should avoid overflow */
+    if (list.num > (1 << 16) - 2) {
+        phdr_num = (1 << 16) - 1;
+    } else {
+        phdr_num += list.num;
+    }
+
+    /* write elf header to vmcore */
+    if (info.d_class == ELFCLASS64) {
+        ret = write_elf64_header(mon, fd, phdr_num, info.d_machine,
+                                 info.d_endian);
+    } else {
+        ret = write_elf32_header(mon, fd, phdr_num, info.d_machine,
+                                 info.d_endian);
+    }
+    if (ret < 0) {
+        goto error;
+    }
+
+    /* write elf notes to vmcore */
+    phdr_index = 0;
+    if (info.d_class == ELFCLASS64) {
+        offset = sizeof(Elf64_Ehdr) + sizeof(Elf64_Phdr)*phdr_num;
+        ret = write_elf64_notes(mon, fd, phdr_index++, &offset, info.d_endian);
+    } else {
+        offset = sizeof(Elf32_Ehdr) + sizeof(Elf32_Phdr)*phdr_num;
+        ret = write_elf32_notes(mon, fd, phdr_index++, &offset, info.d_endian);
+    }
+
+    if (ret < 0) {
+        goto error;
+    }
+
+    memory_offset = offset;
+    /* write all memory to vmcore */
+    QLIST_FOREACH(block, &ram_list.blocks, next) {
+        ret = write_memory(mon, fd, block, &offset);
+        if (ret < 0) {
+            goto error;
+        }
+    }
+
+    /* write PT_LOAD program header to vmcore */
+    QTAILQ_FOREACH(memory_mapping, &list.head, next) {
+        offset = get_offset(memory_mapping->phys_addr, memory_offset);
+        if (info.d_class == ELFCLASS64) {
+            ret = write_elf64_load(mon, fd, memory_mapping, phdr_index++,
+                                   offset, info.d_endian);
+        } else {
+            ret = write_elf32_load(mon, fd, memory_mapping, phdr_index++,
+                                   offset, info.d_endian);
+        }
+        if (ret < 0) {
+            goto error;
+        }
+    }
+
+    free_memory_mapping_list(&list);
+    return 0;
+
+error:
+    free_memory_mapping_list(&list);
+    return -1;
+}
+
+int do_dump(Monitor *mon, const QDict *qdict, QObject **ret_data)
+{
+    const char *file = qdict_get_str(qdict, "file");
+    const char *p;
+    int fd = -1;
+
+#if !defined(WIN32)
+    if (strstart(file, "fd:", &p)) {
+        fd = monitor_get_fd(mon, p);
+        if (fd == -1) {
+            monitor_printf(mon, "dump: invalid file descriptor"
+                           " identifier\n");
+            return -1;
+        }
+    }
+#endif
+
+    if  (strstart(file, "file:", &p)) {
+        fd = open(p, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY);
+        if (fd < 0) {
+            monitor_printf(mon, "dump: failed to open %s\n", p);
+            return -1;
+        }
+    }
+
+    if (fd == -1) {
+        monitor_printf(mon, "unknown dump protocol: %s\n", file);
+        return -1;
+    }
+
+    vm_stop(RUN_STATE_PAUSED);
+    if (create_vmcore(mon, fd) < 0) {
+        return -1;
+    }
+
+    return 0;
+}
diff --git a/dump.h b/dump.h
index a37de45..0280215 100644
--- a/dump.h
+++ b/dump.h
@@ -1,10 +1,14 @@
 #ifndef DUMP_H
 #define DUMP_H
 
+#include "qdict.h"
+
 typedef struct DumpInfo {
     int d_machine;  /* Architecture */
     int d_endian;   /* ELFDATA2LSB or ELFDATA2MSB */
     int d_class;    /* ELFCLASS32 or ELFCLASS64 */
 } DumpInfo;
 
+int do_dump(Monitor *mon, const QDict *qdict, QObject **ret_data);
+
 #endif
diff --git a/hmp-commands.hx b/hmp-commands.hx
index 14838b7..49faa01 100644
--- a/hmp-commands.hx
+++ b/hmp-commands.hx
@@ -767,6 +767,22 @@ Migrate to @var{uri} (using -d to not wait for completion).
 ETEXI
 
     {
+        .name       = "dump",
+        .args_type  = "file:s",
+        .params     = "file",
+        .help       = "dump to file",
+        .user_print = monitor_user_noop,
+        .mhandler.cmd_new = do_dump,
+    },
+
+
+STEXI
address@hidden dump @var{file}
address@hidden dump
+Dump to @var{file}.
+ETEXI
+
+    {
         .name       = "migrate_cancel",
         .args_type  = "",
         .params     = "",
diff --git a/monitor.c b/monitor.c
index 7334401..edd6aa7 100644
--- a/monitor.c
+++ b/monitor.c
@@ -73,6 +73,9 @@
 #endif
 #include "hw/lm32_pic.h"
 
+/* for dump */
+#include "dump.h"
+
 //#define DEBUG
 //#define DEBUG_COMPLETION
 
diff --git a/qmp-commands.hx b/qmp-commands.hx
index 7e3f4b9..34c7593 100644
--- a/qmp-commands.hx
+++ b/qmp-commands.hx
@@ -469,6 +469,30 @@ Notes:
 EQMP
 
     {
+        .name       = "dump",
+        .args_type  = "file:s",
+        .params     = "file",
+        .help       = "dump to file",
+        .user_print = monitor_user_noop,
+        .mhandler.cmd_new = do_dump,
+    },
+
+SQMP
+dump
+-------
+
+Dump to file.
+
+Arguments: None.
+
+Example:
+
+-> { "execute": "dump", "arguments": { "file": "fd:dump" } }
+<- { "return": {} }
+
+EQMP
+
+    {
         .name       = "migrate_cancel",
         .args_type  = "",
         .mhandler.cmd_new = qmp_marshal_input_migrate_cancel,
-- 
1.7.1