X-Git-Url: https://git.proxmox.com/?a=blobdiff_plain;f=dump.c;h=80a9116c778830728e0b541383b2fbd52d8e2e99;hb=8d07d6c46597a885eb38d99cc6fff399ce69cd21;hp=2bf8d8d99423a364e6916c766733f97828afb0d5;hpb=8dacfcb407aa83664bd875123d2ec86612758c22;p=qemu.git

diff --git a/dump.c b/dump.c
index 2bf8d8d99..80a9116c7 100644
--- a/dump.c
+++ b/dump.c
@@ -14,16 +14,16 @@
 #include "qemu-common.h"
 #include "elf.h"
 #include "cpu.h"
-#include "cpu-all.h"
-#include "targphys.h"
-#include "monitor.h"
-#include "kvm.h"
-#include "dump.h"
-#include "sysemu.h"
-#include "memory_mapping.h"
-#include "error.h"
+#include "exec/cpu-all.h"
+#include "exec/hwaddr.h"
+#include "monitor/monitor.h"
+#include "sysemu/kvm.h"
+#include "sysemu/dump.h"
+#include "sysemu/sysemu.h"
+#include "sysemu/memory_mapping.h"
+#include "sysemu/cpus.h"
+#include "qapi/error.h"
 #include "qmp-commands.h"
-#include "gdbstub.h"
 
 static uint16_t cpu_convert_to_target16(uint16_t val, int endian)
 {
@@ -59,17 +59,18 @@ static uint64_t cpu_convert_to_target64(uint64_t val, int endian)
 }
 
 typedef struct DumpState {
+    GuestPhysBlockList guest_phys_blocks;
     ArchDumpInfo dump_info;
     MemoryMappingList list;
     uint16_t phdr_num;
     uint32_t sh_info;
     bool have_section;
     bool resume;
-    size_t note_size;
-    target_phys_addr_t memory_offset;
+    ssize_t note_size;
+    hwaddr memory_offset;
     int fd;
 
-    RAMBlock *block;
+    GuestPhysBlock *next_block;
     ram_addr_t start;
     bool has_filter;
     int64_t begin;
@@ -81,6 +82,7 @@ static int dump_cleanup(DumpState *s)
 {
     int ret = 0;
 
+    guest_phys_blocks_free(&s->guest_phys_blocks);
     memory_mapping_list_free(&s->list);
     if (s->fd != -1) {
         close(s->fd);
@@ -100,18 +102,11 @@ static void dump_error(DumpState *s, const char *reason)
 static int fd_write_vmcore(void *buf, size_t size, void *opaque)
 {
     DumpState *s = opaque;
-    int fd = s->fd;
-    size_t writen_size;
+    size_t written_size;
 
-    /* The fd may be passed from user, and it can be non-blocked */
-    while (size) {
-        writen_size = qemu_write_full(fd, buf, size);
-        if (writen_size != size && errno != EAGAIN) {
-            return -1;
-        }
-
-        buf += writen_size;
-        size -= writen_size;
+    written_size = qemu_write_full(s->fd, buf, size);
+    if (written_size != size) {
+        return -1;
     }
 
     return 0;
@@ -194,7 +189,8 @@ static int write_elf32_header(DumpState *s)
 }
 
 static int write_elf64_load(DumpState *s, MemoryMapping *memory_mapping,
-                            int phdr_index, target_phys_addr_t offset)
+                            int phdr_index, hwaddr offset,
+                            hwaddr filesz)
 {
     Elf64_Phdr phdr;
     int ret;
@@ -204,15 +200,12 @@ static int write_elf64_load(DumpState *s, MemoryMapping *memory_mapping,
     phdr.p_type = cpu_convert_to_target32(PT_LOAD, endian);
     phdr.p_offset = cpu_convert_to_target64(offset, endian);
     phdr.p_paddr = cpu_convert_to_target64(memory_mapping->phys_addr, endian);
-    if (offset == -1) {
-        /* When the memory is not stored into vmcore, offset will be -1 */
-        phdr.p_filesz = 0;
-    } else {
-        phdr.p_filesz = cpu_convert_to_target64(memory_mapping->length, endian);
-    }
+    phdr.p_filesz = cpu_convert_to_target64(filesz, endian);
     phdr.p_memsz = cpu_convert_to_target64(memory_mapping->length, endian);
     phdr.p_vaddr = cpu_convert_to_target64(memory_mapping->virt_addr, endian);
 
+    assert(memory_mapping->length >= filesz);
+
     ret = fd_write_vmcore(&phdr, sizeof(Elf64_Phdr), s);
     if (ret < 0) {
         dump_error(s, "dump: failed to write program header table.\n");
@@ -223,7 +216,8 @@ static int write_elf64_load(DumpState *s, MemoryMapping *memory_mapping,
 }
 
 static int write_elf32_load(DumpState *s, MemoryMapping *memory_mapping,
-                            int phdr_index, target_phys_addr_t offset)
+                            int phdr_index, hwaddr offset,
+                            hwaddr filesz)
 {
     Elf32_Phdr phdr;
     int ret;
@@ -233,15 +227,12 @@ static int write_elf32_load(DumpState *s, MemoryMapping *memory_mapping,
     phdr.p_type = cpu_convert_to_target32(PT_LOAD, endian);
     phdr.p_offset = cpu_convert_to_target32(offset, endian);
     phdr.p_paddr = cpu_convert_to_target32(memory_mapping->phys_addr, endian);
-    if (offset == -1) {
-        /* When the memory is not stored into vmcore, offset will be -1 */
-        phdr.p_filesz = 0;
-    } else {
-        phdr.p_filesz = cpu_convert_to_target32(memory_mapping->length, endian);
-    }
+    phdr.p_filesz = cpu_convert_to_target32(filesz, endian);
     phdr.p_memsz = cpu_convert_to_target32(memory_mapping->length, endian);
     phdr.p_vaddr = cpu_convert_to_target32(memory_mapping->virt_addr, endian);
 
+    assert(memory_mapping->length >= filesz);
+
     ret = fd_write_vmcore(&phdr, sizeof(Elf32_Phdr), s);
     if (ret < 0) {
         dump_error(s, "dump: failed to write program header table.\n");
@@ -255,7 +246,7 @@ static int write_elf64_note(DumpState *s)
 {
     Elf64_Phdr phdr;
     int endian = s->dump_info.d_endian;
-    target_phys_addr_t begin = s->memory_offset - s->note_size;
+    hwaddr begin = s->memory_offset - s->note_size;
     int ret;
 
     memset(&phdr, 0, sizeof(Elf64_Phdr));
@@ -275,23 +266,28 @@ static int write_elf64_note(DumpState *s)
     return 0;
 }
 
+static inline int cpu_index(CPUState *cpu)
+{
+    return cpu->cpu_index + 1;
+}
+
 static int write_elf64_notes(DumpState *s)
 {
-    CPUArchState *env;
+    CPUState *cpu;
     int ret;
     int id;
 
-    for (env = first_cpu; env != NULL; env = env->next_cpu) {
-        id = cpu_index(env);
-        ret = cpu_write_elf64_note(fd_write_vmcore, env, id, s);
+    CPU_FOREACH(cpu) {
+        id = cpu_index(cpu);
+        ret = cpu_write_elf64_note(fd_write_vmcore, cpu, id, s);
         if (ret < 0) {
             dump_error(s, "dump: failed to write elf notes.\n");
             return -1;
         }
     }
 
-    for (env = first_cpu; env != NULL; env = env->next_cpu) {
-        ret = cpu_write_elf64_qemunote(fd_write_vmcore, env, s);
+    CPU_FOREACH(cpu) {
+        ret = cpu_write_elf64_qemunote(fd_write_vmcore, cpu, s);
         if (ret < 0) {
             dump_error(s, "dump: failed to write CPU status.\n");
             return -1;
@@ -303,7 +299,7 @@ static int write_elf64_notes(DumpState *s)
 
 static int write_elf32_note(DumpState *s)
 {
-    target_phys_addr_t begin = s->memory_offset - s->note_size;
+    hwaddr begin = s->memory_offset - s->note_size;
     Elf32_Phdr phdr;
     int endian = s->dump_info.d_endian;
     int ret;
@@ -327,21 +323,21 @@ static int write_elf32_note(DumpState *s)
 
 static int write_elf32_notes(DumpState *s)
 {
-    CPUArchState *env;
+    CPUState *cpu;
     int ret;
     int id;
 
-    for (env = first_cpu; env != NULL; env = env->next_cpu) {
-        id = cpu_index(env);
-        ret = cpu_write_elf32_note(fd_write_vmcore, env, id, s);
+    CPU_FOREACH(cpu) {
+        id = cpu_index(cpu);
+        ret = cpu_write_elf32_note(fd_write_vmcore, cpu, id, s);
         if (ret < 0) {
             dump_error(s, "dump: failed to write elf notes.\n");
             return -1;
         }
     }
 
-    for (env = first_cpu; env != NULL; env = env->next_cpu) {
-        ret = cpu_write_elf32_qemunote(fd_write_vmcore, env, s);
+    CPU_FOREACH(cpu) {
+        ret = cpu_write_elf32_qemunote(fd_write_vmcore, cpu, s);
         if (ret < 0) {
             dump_error(s, "dump: failed to write CPU status.\n");
             return -1;
@@ -395,14 +391,14 @@ static int write_data(DumpState *s, void *buf, int length)
 }
 
 /* write the memroy to vmcore. 1 page per I/O. */
-static int write_memory(DumpState *s, RAMBlock *block, ram_addr_t start,
+static int write_memory(DumpState *s, GuestPhysBlock *block, ram_addr_t start,
                         int64_t size)
 {
     int64_t i;
     int ret;
 
     for (i = 0; i < size / TARGET_PAGE_SIZE; i++) {
-        ret = write_data(s, block->host + start + i * TARGET_PAGE_SIZE,
+        ret = write_data(s, block->host_addr + start + i * TARGET_PAGE_SIZE,
                          TARGET_PAGE_SIZE);
         if (ret < 0) {
             return ret;
@@ -410,7 +406,7 @@ static int write_memory(DumpState *s, RAMBlock *block, ram_addr_t start,
     }
 
     if ((size % TARGET_PAGE_SIZE) != 0) {
-        ret = write_data(s, block->host + start + i * TARGET_PAGE_SIZE,
+        ret = write_data(s, block->host_addr + start + i * TARGET_PAGE_SIZE,
                          size % TARGET_PAGE_SIZE);
         if (ret < 0) {
             return ret;
@@ -420,57 +416,71 @@ static int write_memory(DumpState *s, RAMBlock *block, ram_addr_t start,
     return 0;
 }
 
-/* get the memory's offset in the vmcore */
-static target_phys_addr_t get_offset(target_phys_addr_t phys_addr,
-                                     DumpState *s)
+/* get the memory's offset and size in the vmcore */
+static void get_offset_range(hwaddr phys_addr,
+                             ram_addr_t mapping_length,
+                             DumpState *s,
+                             hwaddr *p_offset,
+                             hwaddr *p_filesz)
 {
-    RAMBlock *block;
-    target_phys_addr_t offset = s->memory_offset;
+    GuestPhysBlock *block;
+    hwaddr offset = s->memory_offset;
     int64_t size_in_block, start;
 
+    /* When the memory is not stored into vmcore, offset will be -1 */
+    *p_offset = -1;
+    *p_filesz = 0;
+
     if (s->has_filter) {
         if (phys_addr < s->begin || phys_addr >= s->begin + s->length) {
-            return -1;
+            return;
         }
     }
 
-    QLIST_FOREACH(block, &ram_list.blocks, next) {
+    QTAILQ_FOREACH(block, &s->guest_phys_blocks.head, next) {
         if (s->has_filter) {
-            if (block->offset >= s->begin + s->length ||
-                block->offset + block->length <= s->begin) {
+            if (block->target_start >= s->begin + s->length ||
+                block->target_end <= s->begin) {
                 /* This block is out of the range */
                 continue;
             }
 
-            if (s->begin <= block->offset) {
-                start = block->offset;
+            if (s->begin <= block->target_start) {
+                start = block->target_start;
             } else {
                 start = s->begin;
             }
 
-            size_in_block = block->length - (start - block->offset);
-            if (s->begin + s->length < block->offset + block->length) {
-                size_in_block -= block->offset + block->length -
-                                 (s->begin + s->length);
+            size_in_block = block->target_end - start;
+            if (s->begin + s->length < block->target_end) {
+                size_in_block -= block->target_end - (s->begin + s->length);
             }
         } else {
-            start = block->offset;
-            size_in_block = block->length;
+            start = block->target_start;
+            size_in_block = block->target_end - block->target_start;
         }
 
         if (phys_addr >= start && phys_addr < start + size_in_block) {
-            return phys_addr - start + offset;
+            *p_offset = phys_addr - start + offset;
+
+            /* The offset range mapped from the vmcore file must not spill over
+             * the GuestPhysBlock, clamp it. The rest of the mapping will be
+             * zero-filled in memory at load time; see
+             * <http://refspecs.linuxbase.org/elf/gabi4+/ch5.pheader.html>.
+             */
+            *p_filesz = phys_addr + mapping_length <= start + size_in_block ?
+                        mapping_length :
+                        size_in_block - (phys_addr - start);
+            return;
         }
 
         offset += size_in_block;
     }
-
-    return -1;
 }
 
 static int write_elf_loads(DumpState *s)
 {
-    target_phys_addr_t offset;
+    hwaddr offset, filesz;
     MemoryMapping *memory_mapping;
     uint32_t phdr_index = 1;
     int ret;
@@ -483,11 +493,15 @@ static int write_elf_loads(DumpState *s)
     }
 
     QTAILQ_FOREACH(memory_mapping, &s->list.head, next) {
-        offset = get_offset(memory_mapping->phys_addr, s);
+        get_offset_range(memory_mapping->phys_addr,
+                         memory_mapping->length,
+                         s, &offset, &filesz);
         if (s->dump_info.d_class == ELFCLASS64) {
-            ret = write_elf64_load(s, memory_mapping, phdr_index++, offset);
+            ret = write_elf64_load(s, memory_mapping, phdr_index++, offset,
+                                   filesz);
         } else {
-            ret = write_elf32_load(s, memory_mapping, phdr_index++, offset);
+            ret = write_elf32_load(s, memory_mapping, phdr_index++, offset,
+                                   filesz);
         }
 
         if (ret < 0) {
@@ -598,26 +612,26 @@ static int dump_completed(DumpState *s)
     return 0;
 }
 
-static int get_next_block(DumpState *s, RAMBlock *block)
+static int get_next_block(DumpState *s, GuestPhysBlock *block)
 {
     while (1) {
-        block = QLIST_NEXT(block, next);
+        block = QTAILQ_NEXT(block, next);
         if (!block) {
             /* no more block */
             return 1;
         }
 
         s->start = 0;
-        s->block = block;
+        s->next_block = block;
         if (s->has_filter) {
-            if (block->offset >= s->begin + s->length ||
-                block->offset + block->length <= s->begin) {
+            if (block->target_start >= s->begin + s->length ||
+                block->target_end <= s->begin) {
                 /* This block is out of the range */
                 continue;
             }
 
-            if (s->begin > block->offset) {
-                s->start = s->begin - block->offset;
+            if (s->begin > block->target_start) {
+                s->start = s->begin - block->target_start;
             }
         }
 
@@ -628,18 +642,18 @@ static int get_next_block(DumpState *s, RAMBlock *block)
 /* write all memory to vmcore */
 static int dump_iterate(DumpState *s)
 {
-    RAMBlock *block;
+    GuestPhysBlock *block;
     int64_t size;
     int ret;
 
     while (1) {
-        block = s->block;
+        block = s->next_block;
 
-        size = block->length;
+        size = block->target_end - block->target_start;
         if (s->has_filter) {
             size -= s->start;
-            if (s->begin + s->length < block->offset + block->length) {
-                size -= block->offset + block->length - (s->begin + s->length);
+            if (s->begin + s->length < block->target_end) {
+                size -= block->target_end - (s->begin + s->length);
             }
         }
         ret = write_memory(s, block, s->start, size);
@@ -674,23 +688,23 @@ static int create_vmcore(DumpState *s)
 
 static ram_addr_t get_start_block(DumpState *s)
 {
-    RAMBlock *block;
+    GuestPhysBlock *block;
 
     if (!s->has_filter) {
-        s->block = QLIST_FIRST(&ram_list.blocks);
+        s->next_block = QTAILQ_FIRST(&s->guest_phys_blocks.head);
         return 0;
     }
 
-    QLIST_FOREACH(block, &ram_list.blocks, next) {
-        if (block->offset >= s->begin + s->length ||
-            block->offset + block->length <= s->begin) {
+    QTAILQ_FOREACH(block, &s->guest_phys_blocks.head, next) {
+        if (block->target_start >= s->begin + s->length ||
+            block->target_end <= s->begin) {
             /* This block is out of the range */
             continue;
         }
 
-        s->block = block;
-        if (s->begin > block->offset) {
-            s->start = s->begin - block->offset;
+        s->next_block = block;
+        if (s->begin > block->target_start) {
+            s->start = s->begin - block->target_start;
         } else {
             s->start = 0;
         }
@@ -703,8 +717,9 @@ static ram_addr_t get_start_block(DumpState *s)
 static int dump_init(DumpState *s, int fd, bool paging, bool has_filter,
                      int64_t begin, int64_t length, Error **errp)
 {
-    CPUArchState *env;
+    CPUState *cpu;
     int nr_cpus;
+    Error *err = NULL;
     int ret;
 
     if (runstate_is_running()) {
@@ -714,32 +729,35 @@ static int dump_init(DumpState *s, int fd, bool paging, bool has_filter,
         s->resume = false;
     }
 
+    /* If we use KVM, we should synchronize the registers before we get dump
+     * info or physmap info.
+     */
+    cpu_synchronize_all_states();
+    nr_cpus = 0;
+    CPU_FOREACH(cpu) {
+        nr_cpus++;
+    }
+
     s->errp = errp;
     s->fd = fd;
     s->has_filter = has_filter;
     s->begin = begin;
     s->length = length;
+
+    guest_phys_blocks_init(&s->guest_phys_blocks);
+    guest_phys_blocks_append(&s->guest_phys_blocks);
+
     s->start = get_start_block(s);
     if (s->start == -1) {
         error_set(errp, QERR_INVALID_PARAMETER, "begin");
         goto cleanup;
     }
 
-    /*
-     * get dump info: endian, class and architecture.
+    /* get dump info: endian, class and architecture.
      * If the target architecture is not supported, cpu_get_dump_info() will
      * return -1.
-     *
-     * if we use kvm, we should synchronize the register before we get dump
-     * info.
      */
-    nr_cpus = 0;
-    for (env = first_cpu; env != NULL; env = env->next_cpu) {
-        cpu_synchronize_state(env);
-        nr_cpus++;
-    }
-
-    ret = cpu_get_dump_info(&s->dump_info);
+    ret = cpu_get_dump_info(&s->dump_info, &s->guest_phys_blocks);
     if (ret < 0) {
         error_set(errp, QERR_UNSUPPORTED);
         goto cleanup;
@@ -747,7 +765,7 @@ static int dump_init(DumpState *s, int fd, bool paging, bool has_filter,
 
     s->note_size = cpu_get_note_size(s->dump_info.d_class,
                                      s->dump_info.d_machine, nr_cpus);
-    if (ret < 0) {
+    if (s->note_size < 0) {
         error_set(errp, QERR_UNSUPPORTED);
         goto cleanup;
     }
@@ -755,9 +773,13 @@ static int dump_init(DumpState *s, int fd, bool paging, bool has_filter,
     /* get memory mapping */
     memory_mapping_list_init(&s->list);
     if (paging) {
-        qemu_get_guest_memory_mapping(&s->list);
+        qemu_get_guest_memory_mapping(&s->list, &s->guest_phys_blocks, &err);
+        if (err != NULL) {
+            error_propagate(errp, err);
+            goto cleanup;
+        }
     } else {
-        qemu_get_guest_simple_memory_mapping(&s->list);
+        qemu_get_guest_simple_memory_mapping(&s->list, &s->guest_phys_blocks);
     }
 
     if (s->has_filter) {
@@ -809,6 +831,8 @@ static int dump_init(DumpState *s, int fd, bool paging, bool has_filter,
     return 0;
 
 cleanup:
+    guest_phys_blocks_free(&s->guest_phys_blocks);
+
     if (s->resume) {
         vm_start();
     }
@@ -836,9 +860,8 @@ void qmp_dump_guest_memory(bool paging, const char *file, bool has_begin,
 
 #if !defined(WIN32)
     if (strstart(file, "fd:", &p)) {
-        fd = monitor_get_fd(cur_mon, p);
+        fd = monitor_get_fd(cur_mon, p, errp);
         if (fd == -1) {
-            error_set(errp, QERR_FD_NOT_FOUND, p);
             return;
         }
     }
@@ -847,7 +870,7 @@ void qmp_dump_guest_memory(bool paging, const char *file, bool has_begin,
     if  (strstart(file, "file:", &p)) {
         fd = qemu_open(p, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY, S_IRUSR);
         if (fd < 0) {
-            error_set(errp, QERR_OPEN_FILE_FAILED, p);
+            error_setg_file_open(errp, errno, p);
             return;
         }
     }
@@ -857,7 +880,7 @@ void qmp_dump_guest_memory(bool paging, const char *file, bool has_begin,
         return;
     }
 
-    s = g_malloc(sizeof(DumpState));
+    s = g_malloc0(sizeof(DumpState));
 
     ret = dump_init(s, fd, paging, has_begin, begin, length, errp);
     if (ret < 0) {