[PULL v2 09/31] exec: fetch the alignment of Linux devdax pmem character device nodes

[Paolo Bonzini]

From: Jingqi Liu <jingqi.liu@intel.com>

If the backend file is devdax pmem character device, the alignment
specified by the option 'align=NUM' in the '-object memory-backend-file'
needs to match the alignment requirement of the devdax pmem character device.

This patch uses the interfaces of libdaxctl to fetch the devdax pmem file
'align', so that we can compare it with the NUM of 'align=NUM'.
The NUM needs to be larger than or equal to the devdax pmem file 'align'.

It also fixes the problem that mmap() returns failure in qemu_ram_mmap()
when the NUM of 'align=NUM' is less than the devdax pmem file 'align'.

Suggested-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Joao Martins <joao.m.martins@oracle.com>
Signed-off-by: Jingqi Liu <jingqi.liu@intel.com>
Message-Id: <20200429085011.63752-2-jingqi.liu@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 exec.c | 54 +++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 53 insertions(+), 1 deletion(-)

diff --git a/exec.c b/exec.c
index d6712fba7e..21926dc9c7 100644
--- a/exec.c
+++ b/exec.c
@@ -77,6 +77,10 @@
 
 #include "monitor/monitor.h"
 
+#ifdef CONFIG_LIBDAXCTL
+#include <daxctl/libdaxctl.h>
+#endif
+
 //#define DEBUG_SUBPAGE
 
 #if !defined(CONFIG_USER_ONLY)
@@ -1745,6 +1749,46 @@ static int64_t get_file_size(int fd)
     return size;
 }
 
+static int64_t get_file_align(int fd)
+{
+    int64_t align = -1;
+#if defined(__linux__) && defined(CONFIG_LIBDAXCTL)
+    struct stat st;
+
+    if (fstat(fd, &st) < 0) {
+        return -errno;
+    }
+
+    /* Special handling for devdax character devices */
+    if (S_ISCHR(st.st_mode)) {
+        g_autofree char *path = NULL;
+        g_autofree char *rpath = NULL;
+        struct daxctl_ctx *ctx;
+        struct daxctl_region *region;
+        int rc = 0;
+
+        path = g_strdup_printf("/sys/dev/char/%d:%d",
+                    major(st.st_rdev), minor(st.st_rdev));
+        rpath = realpath(path, NULL);
+
+        rc = daxctl_new(&ctx);
+        if (rc) {
+            return -1;
+        }
+
+        daxctl_region_foreach(ctx, region) {
+            if (strstr(rpath, daxctl_region_get_path(region))) {
+                align = daxctl_region_get_align(region);
+                break;
+            }
+        }
+        daxctl_unref(ctx);
+    }
+#endif /* defined(__linux__) && defined(CONFIG_LIBDAXCTL) */
+
+    return align;
+}
+
 static int file_ram_open(const char *path,
                          const char *region_name,
                          bool *created,
@@ -2296,7 +2340,7 @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, 
MemoryRegion *mr,
 {
     RAMBlock *new_block;
     Error *local_err = NULL;
-    int64_t file_size;
+    int64_t file_size, file_align;
 
     /* Just support these ram flags by now. */
     assert((ram_flags & ~(RAM_SHARED | RAM_PMEM)) == 0);
@@ -2332,6 +2376,14 @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, 
MemoryRegion *mr,
         return NULL;
     }
 
+    file_align = get_file_align(fd);
+    if (file_align > 0 && mr && file_align > mr->align) {
+        error_setg(errp, "backing store align 0x%" PRIx64
+                   " is larger than 'align' option 0x%" PRIx64,
+                   file_align, mr->align);
+        return NULL;
+    }
+
     new_block = g_malloc0(sizeof(*new_block));
     new_block->mr = mr;
     new_block->used_length = size;
-- 
2.26.2