[Qemu-devel] [PATCH 06/10] qga: implement qmp_guest_get_memory_blocks() for Linux with sysfs

[Michael Roth <mdroth@linux.vnet.ibm.com>]

From: zhanghailiang <zhang.zhanghailiang@huawei.com>

We can get guest's memory block information by using command
"guest-get-memory-blocks", the returned value contains a list of memory block
info, such as phys-index, online state, can-offline info.

Signed-off-by: zhanghailiang <zhang.zhanghailiang@huawei.com>

*replaced guest-triggerable assertion with an error msg

Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
 qga/commands-posix.c | 234 ++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 233 insertions(+), 1 deletion(-)

diff --git a/qga/commands-posix.c b/qga/commands-posix.c
index 0ce27a4..6cd21b2 100644
--- a/qga/commands-posix.c
+++ b/qga/commands-posix.c
@@ -1992,9 +1992,241 @@ out:
     }
 }
 
+static void ga_read_sysfs_file(int dirfd, const char *pathname, char *buf,
+                               int size, Error **errp)
+{
+    int fd;
+    int res;
+
+    errno = 0;
+    fd = openat(dirfd, pathname, O_RDONLY);
+    if (fd == -1) {
+        error_setg_errno(errp, errno, "open sysfs file \"%s\"", pathname);
+        return;
+    }
+
+    res = pread(fd, buf, size, 0);
+    if (res == -1) {
+        error_setg_errno(errp, errno, "pread sysfs file \"%s\"", pathname);
+    } else if (res == 0) {
+        error_setg(errp, "pread sysfs file \"%s\": unexpected EOF", pathname);
+    }
+    close(fd);
+}
+
+static void ga_write_sysfs_file(int dirfd, const char *pathname,
+                                const char *buf, int size, Error **errp)
+{
+    int fd;
+
+    errno = 0;
+    fd = openat(dirfd, pathname, O_WRONLY);
+    if (fd == -1) {
+        error_setg_errno(errp, errno, "open sysfs file \"%s\"", pathname);
+        return;
+    }
+
+    if (pwrite(fd, buf, size, 0) == -1) {
+        error_setg_errno(errp, errno, "pwrite sysfs file \"%s\"", pathname);
+    }
+
+    close(fd);
+}
+
+/* Transfer online/offline status between @mem_blk and the guest system.
+ *
+ * On input either @errp or *@errp must be NULL.
+ *
+ * In system-to-@mem_blk direction, the following @mem_blk fields are accessed:
+ * - R: mem_blk->phys_index
+ * - W: mem_blk->online
+ * - W: mem_blk->can_offline
+ *
+ * In @mem_blk-to-system direction, the following @mem_blk fields are accessed:
+ * - R: mem_blk->phys_index
+ * - R: mem_blk->online
+ *-  R: mem_blk->can_offline
+ * Written members remain unmodified on error.
+ */
+static void transfer_memory_block(GuestMemoryBlock *mem_blk, bool sys2memblk,
+                                  GuestMemoryBlockResponse *result,
+                                  Error **errp)
+{
+    char *dirpath;
+    int dirfd;
+    char *status;
+    Error *local_err = NULL;
+
+    if (!sys2memblk) {
+        DIR *dp;
+
+        if (!result) {
+            error_setg(errp, "Internal error, 'result' should not be NULL");
+            return;
+        }
+        errno = 0;
+        dp = opendir("/sys/devices/system/memory/");
+         /* if there is no 'memory' directory in sysfs,
+         * we think this VM does not support online/offline memory block,
+         * any other solution?
+         */
+        if (!dp && errno == ENOENT) {
+            result->response =
+                GUEST_MEMORY_BLOCK_RESPONSE_TYPE_OPERATION_NOT_SUPPORTED;
+            goto out1;
+        }
+        closedir(dp);
+    }
+
+    dirpath = g_strdup_printf("/sys/devices/system/memory/memory%" PRId64 "/",
+                              mem_blk->phys_index);
+    dirfd = open(dirpath, O_RDONLY | O_DIRECTORY);
+    if (dirfd == -1) {
+        if (sys2memblk) {
+            error_setg_errno(errp, errno, "open(\"%s\")", dirpath);
+        } else {
+            if (errno == ENOENT) {
+                result->response = GUEST_MEMORY_BLOCK_RESPONSE_TYPE_NOT_FOUND;
+            } else {
+                result->response =
+                    GUEST_MEMORY_BLOCK_RESPONSE_TYPE_OPERATION_FAILED;
+            }
+        }
+        g_free(dirpath);
+        goto out1;
+    }
+    g_free(dirpath);
+
+    status = g_malloc0(10);
+    ga_read_sysfs_file(dirfd, "state", status, 10, &local_err);
+    if (local_err) {
+        /* treat with sysfs file that not exist in old kernel */
+        if (errno == ENOENT) {
+            error_free(local_err);
+            if (sys2memblk) {
+                mem_blk->online = true;
+                mem_blk->can_offline = false;
+            } else if (!mem_blk->online) {
+                result->response =
+                    GUEST_MEMORY_BLOCK_RESPONSE_TYPE_OPERATION_NOT_SUPPORTED;
+            }
+        } else {
+            if (sys2memblk) {
+                error_propagate(errp, local_err);
+            } else {
+                result->response =
+                    GUEST_MEMORY_BLOCK_RESPONSE_TYPE_OPERATION_FAILED;
+            }
+        }
+        goto out2;
+    }
+
+    if (sys2memblk) {
+        char removable = '0';
+
+        mem_blk->online = (strncmp(status, "online", 6) == 0);
+
+        ga_read_sysfs_file(dirfd, "removable", &removable, 1, &local_err);
+        if (local_err) {
+            /* if no 'removable' file, it does't support offline mem blk */
+            if (errno == ENOENT) {
+                error_free(local_err);
+                mem_blk->can_offline = false;
+            } else {
+                error_propagate(errp, local_err);
+            }
+        } else {
+            mem_blk->can_offline = (removable != '0');
+        }
+    } else {
+        if (mem_blk->online != (strncmp(status, "online", 6) == 0)) {
+            char *new_state = mem_blk->online ? g_strdup("online") :
+                                                g_strdup("offline");
+
+            ga_write_sysfs_file(dirfd, "state", new_state, strlen(new_state),
+                                &local_err);
+            g_free(new_state);
+            if (local_err) {
+                error_free(local_err);
+                result->response =
+                    GUEST_MEMORY_BLOCK_RESPONSE_TYPE_OPERATION_FAILED;
+                goto out2;
+            }
+
+            result->response = GUEST_MEMORY_BLOCK_RESPONSE_TYPE_SUCCESS;
+            result->has_error_code = false;
+        } /* otherwise pretend successful re-(on|off)-lining */
+    }
+    g_free(status);
+    close(dirfd);
+    return;
+
+out2:
+    g_free(status);
+    close(dirfd);
+out1:
+    if (!sys2memblk) {
+        result->has_error_code = true;
+        result->error_code = errno;
+    }
+}
+
 GuestMemoryBlockList *qmp_guest_get_memory_blocks(Error **errp)
 {
-    error_set(errp, QERR_UNSUPPORTED);
+    GuestMemoryBlockList *head, **link;
+    Error *local_err = NULL;
+    struct dirent *de;
+    DIR *dp;
+
+    head = NULL;
+    link = &head;
+
+    dp = opendir("/sys/devices/system/memory/");
+    if (!dp) {
+        error_setg_errno(errp, errno, "Can't open directory"
+                         "\"/sys/devices/system/memory/\"\n");
+        return NULL;
+    }
+
+    /* Note: the phys_index of memory block may be discontinuous,
+     * this is because a memblk is the unit of the Sparse Memory design, which
+     * allows discontinuous memory ranges (ex. NUMA), so here we should
+     * traverse the memory block directory.
+     */
+    while ((de = readdir(dp)) != NULL) {
+        GuestMemoryBlock *mem_blk;
+        GuestMemoryBlockList *entry;
+
+        if ((strncmp(de->d_name, "memory", 6) != 0) ||
+            !(de->d_type & DT_DIR)) {
+            continue;
+        }
+
+        mem_blk = g_malloc0(sizeof *mem_blk);
+        /* The d_name is "memoryXXX",  phys_index is block id, same as XXX */
+        mem_blk->phys_index = strtoul(&de->d_name[6], NULL, 10);
+        mem_blk->has_can_offline = true; /* lolspeak ftw */
+        transfer_memory_block(mem_blk, true, NULL, &local_err);
+
+        entry = g_malloc0(sizeof *entry);
+        entry->value = mem_blk;
+
+        *link = entry;
+        link = &entry->next;
+    }
+
+    closedir(dp);
+    if (local_err == NULL) {
+        /* there's no guest with zero memory blocks */
+        if (head == NULL) {
+            error_setg(errp, "guest reported zero memory blocks!");
+            return;
+        }
+        return head;
+    }
+
+    qapi_free_GuestMemoryBlockList(head);
+    error_propagate(errp, local_err);
     return NULL;
 }
 
-- 
1.9.1