util/mmap-alloc: fix hugetlb support on ppc64

Since commit 8561c9244ddf1122d "exec: allocate PROT_NONE pages on top of
RAM", it is no longer possible to back guest RAM with hugepages on ppc64
hosts:

mmap(NULL, 285212672, PROT_NONE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) =
0x3fff57000000
mmap(0x3fff57000000, 268435456, PROT_READ|PROT_WRITE,
MAP_PRIVATE|MAP_FIXED, 19, 0) = -1 EBUSY (Device or resource busy)

This is because on ppc64, Linux fixes a page size for a virtual address
at mmap time, so we can't switch a range of memory from anonymous
small pages to hugetlbs with MAP_FIXED.

See commit d0f13e3c20b6fb73ccb467bdca97fa7cf5a574cd
("[POWERPC] Introduce address space "slices"") in Linux
history for the details.

Detect this and create the PROT_NONE mapping using the same fd.

Naturally, this makes the guard page bigger with hugetlbfs.

Based on patch by Greg Kurz.

Acked-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Tested-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

1 files changed, 1 insertions, 23 deletions

diff --git a/util/oslib-posix.c b/util/oslib-posix.c
index 914cef5..d25f671 100644
--- a/util/oslib-posix.c
+++ b/util/oslib-posix.c
@@ -46,7 +46,6 @@ extern int daemon(int, int);
 #else
 #  define QEMU_VMALLOC_ALIGN getpagesize()
 #endif
-#define HUGETLBFS_MAGIC       0x958458f6
 
 #include <termios.h>
 #include <unistd.h>
@@ -65,7 +64,6 @@ extern int daemon(int, int);
 
 #ifdef CONFIG_LINUX
 #include <sys/syscall.h>
-#include <sys/vfs.h>
 #endif
 
 #ifdef __FreeBSD__
@@ -340,26 +338,6 @@ static void sigbus_handler(int signal)
     siglongjmp(sigjump, 1);
 }
 
-static size_t fd_getpagesize(int fd)
-{
-#ifdef CONFIG_LINUX
-    struct statfs fs;
-    int ret;
-
-    if (fd != -1) {
-        do {
-            ret = fstatfs(fd, &fs);
-        } while (ret != 0 && errno == EINTR);
-
-        if (ret == 0 && fs.f_type == HUGETLBFS_MAGIC) {
-            return fs.f_bsize;
-        }
-    }
-#endif
-
-    return getpagesize();
-}
-
 void os_mem_prealloc(int fd, char *area, size_t memory)
 {
     int ret;
@@ -387,7 +365,7 @@ void os_mem_prealloc(int fd, char *area, size_t memory)
         exit(1);
     } else {
         int i;
-        size_t hpagesize = fd_getpagesize(fd);
+        size_t hpagesize = qemu_fd_getpagesize(fd);
         size_t numpages = DIV_ROUND_UP(memory, hpagesize);
 
         /* MAP_POPULATE silently ignores failures */