| Message ID | 1235057376-22481-1-git-send-email-joerg.roedel@amd.com (mailing list archive) |
|---|---|
| State | Accepted |
| Headers | show |
Hi Joerg, On Thu, Feb 19, 2009 at 04:29:36PM +0100, Joerg Roedel wrote: > The current method of finding out the size of huge pages does not work > reliable anymore. Current Linux supports more than one huge page size > but /proc/meminfo only show one of the supported sizes. > To find out the real page size used can be found by calling statfs. This > patch changes kvm/qemu to use statfs instead of parsing /proc/meminfo. > > Signed-off-by: Joerg Roedel <joerg.roedel@amd.com> > + if (fs.f_type != HUGETLBFS_MAGIC) { > + fprintf(stderr, "Path not on HugeTLBFS: %s\n", path); > + return 0; > } Would be nicer to use standard page size (sysconf) in case its not a hugetlbfs mount, instead of failing. Useful for testing with shmem. > - size = strstr(buf, needle); > - if (!size) > - return 0; > - size += strlen(needle); > - hugepagesize = strtol(size, NULL, 0); > - return hugepagesize; > + return fs.f_bsize; > } > > static void *alloc_mem_area(size_t memory, unsigned long *len, const char *path) > @@ -4762,7 +4760,7 @@ static void *alloc_mem_area(size_t memory, unsigned long *len, const char *path) > if (asprintf(&filename, "%s/kvm.XXXXXX", path) == -1) > return NULL; > > - hpagesize = gethugepagesize() * 1024; > + hpagesize = gethugepagesize(path); > if (!hpagesize) > return NULL; Out of curiosity, your immediate reason for this patch is use of gbpages? -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Fri, Feb 20, 2009 at 09:18:42PM -0300, Marcelo Tosatti wrote: > Hi Joerg, > > On Thu, Feb 19, 2009 at 04:29:36PM +0100, Joerg Roedel wrote: > > The current method of finding out the size of huge pages does not work > > reliable anymore. Current Linux supports more than one huge page size > > but /proc/meminfo only show one of the supported sizes. > > To find out the real page size used can be found by calling statfs. This > > patch changes kvm/qemu to use statfs instead of parsing /proc/meminfo. > > > > Signed-off-by: Joerg Roedel <joerg.roedel@amd.com> > > > + if (fs.f_type != HUGETLBFS_MAGIC) { > > + fprintf(stderr, "Path not on HugeTLBFS: %s\n", path); > > + return 0; > > } > > Would be nicer to use standard page size (sysconf) in case its not a > hugetlbfs mount, instead of failing. Useful for testing with shmem. > > > - size = strstr(buf, needle); > > - if (!size) > > - return 0; > > - size += strlen(needle); > > - hugepagesize = strtol(size, NULL, 0); > > - return hugepagesize; > > + return fs.f_bsize; > > } > > > > static void *alloc_mem_area(size_t memory, unsigned long *len, const char *path) > > @@ -4762,7 +4760,7 @@ static void *alloc_mem_area(size_t memory, unsigned long *len, const char *path) > > if (asprintf(&filename, "%s/kvm.XXXXXX", path) == -1) > > return NULL; > > > > - hpagesize = gethugepagesize() * 1024; > > + hpagesize = gethugepagesize(path); > > if (!hpagesize) > > return NULL; > > Out of curiosity, your immediate reason for this patch is use of > gbpages? Yes. I am currently preparing patches to support gbpages in KVM. I think they will be ready for submission next week. The leak bugs were also found when I was debugging the code this week. My test system has 5 gbpages an leaking one or two of them is _really_ bad ;) Joerg -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/qemu/sysemu.h b/qemu/sysemu.h index 19464cf..4333495 100644 --- a/qemu/sysemu.h +++ b/qemu/sysemu.h @@ -99,7 +99,7 @@ extern int graphic_rotate; extern int no_quit; extern int semihosting_enabled; extern int old_param; -extern int hpagesize; +extern long hpagesize; extern const char *bootp_filename; #ifdef USE_KQEMU diff --git a/qemu/vl.c b/qemu/vl.c index bbd7aa3..b8c1162 100644 --- a/qemu/vl.c +++ b/qemu/vl.c @@ -61,6 +61,7 @@ #include <sys/ioctl.h> #include <sys/resource.h> #include <sys/socket.h> +#include <sys/vfs.h> #include <netinet/in.h> #include <net/if.h> #if defined(__NetBSD__) @@ -254,7 +255,7 @@ const char *mem_path = NULL; #ifdef MAP_POPULATE int mem_prealloc = 1; /* force preallocation of physical target memory */ #endif -int hpagesize = 0; +long hpagesize = 0; const char *cpu_vendor_string; #ifdef TARGET_ARM int old_param = 0; @@ -4717,32 +4718,29 @@ void qemu_get_launch_info(int *argc, char ***argv, int *opt_daemonize, const cha } #ifdef USE_KVM -static int gethugepagesize(void) + +#define HUGETLBFS_MAGIC 0x958458f6 + +static long gethugepagesize(const char *path) { - int ret, fd; - char buf[4096]; - const char *needle = "Hugepagesize:"; - char *size; - unsigned long hugepagesize; + struct statfs fs; + int ret; - fd = open("/proc/meminfo", O_RDONLY); - if (fd < 0) { - perror("open"); - exit(0); + do { + ret = statfs(path, &fs); + } while (ret != 0 && errno == EINTR); + + if (ret != 0) { + perror("statfs"); + return 0; } - ret = read(fd, buf, sizeof(buf)); - if (ret < 0) { - perror("read"); - exit(0); + if (fs.f_type != HUGETLBFS_MAGIC) { + fprintf(stderr, "Path not on HugeTLBFS: %s\n", path); + return 0; } - size = strstr(buf, needle); - if (!size) - return 0; - size += strlen(needle); - hugepagesize = strtol(size, NULL, 0); - return hugepagesize; + return fs.f_bsize; } static void *alloc_mem_area(size_t memory, unsigned long *len, const char *path) @@ -4762,7 +4760,7 @@ static void *alloc_mem_area(size_t memory, unsigned long *len, const char *path) if (asprintf(&filename, "%s/kvm.XXXXXX", path) == -1) return NULL; - hpagesize = gethugepagesize() * 1024; + hpagesize = gethugepagesize(path); if (!hpagesize) return NULL;
The current method of finding out the size of huge pages does not work reliable anymore. Current Linux supports more than one huge page size but /proc/meminfo only show one of the supported sizes. To find out the real page size used can be found by calling statfs. This patch changes kvm/qemu to use statfs instead of parsing /proc/meminfo. Signed-off-by: Joerg Roedel <joerg.roedel@amd.com> --- qemu/sysemu.h | 2 +- qemu/vl.c | 42 ++++++++++++++++++++---------------------- 2 files changed, 21 insertions(+), 23 deletions(-)