The following changes since commit 00928a421d47f49691cace1207481b7aad31b1f1:

Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20180626' into staging (2018-06-26 18:23:49 +0100)

git://github.com/stefanha/qemu.git tags/block-pull-request

for you to fetch changes up to ed6e2161715c527330f936d44af4c547f25f687e:

linux-aio: properly bubble up errors from initialization (2018-06-27 13:06:34 +0100)

* Gracefully handle Linux AIO init failure

Nishanth Aravamudan (1):

linux-aio: properly bubble up errors from initialization

Stefan Hajnoczi (1):

compiler: add a sizeof_field() macro

include/block/aio.h | 3 +++

include/block/raw-aio.h | 2 +-

include/hw/xen/io/ring.h | 2 +-

include/qemu/compiler.h | 2 ++

accel/tcg/translate-all.c | 2 +-

block/file-posix.c | 33 ++++++++++++++++++++++++++++-----

block/linux-aio.c | 12 +++++++++---

hw/display/xenfb.c | 4 ++--

hw/net/rocker/rocker_of_dpa.c | 2 +-

hw/net/virtio-net.c | 2 +-

stubs/linux-aio.c | 2 +-

target/i386/kvm.c | 2 +-

target/ppc/arch_dump.c | 10 +++++-----

target/s390x/arch_dump.c | 20 ++++++++++----------

util/async.c | 14 +++++++++++---

15 files changed, 77 insertions(+), 35 deletions(-)

2.17.1

Determining the size of a field is useful when you don't have a struct

variable handy. Open-coding this is ugly.

This patch adds the sizeof_field() macro, which is similar to

typeof_field(). Existing instances are updated to use the macro.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

Reviewed-by: John Snow <jsnow@redhat.com>

Message-id: 20180614164431.29305-1-stefanha@redhat.com

include/hw/xen/io/ring.h | 2 +-

include/qemu/compiler.h | 2 ++

accel/tcg/translate-all.c | 2 +-

hw/display/xenfb.c | 4 ++--

hw/net/rocker/rocker_of_dpa.c | 2 +-

hw/net/virtio-net.c | 2 +-

target/i386/kvm.c | 2 +-

target/ppc/arch_dump.c | 10 +++++-----

target/s390x/arch_dump.c | 20 ++++++++++----------

9 files changed, 24 insertions(+), 22 deletions(-)

diff --git a/include/hw/xen/io/ring.h b/include/hw/xen/io/ring.h

--- a/include/hw/xen/io/ring.h

+++ b/include/hw/xen/io/ring.h

@@ -XXX,XX +XXX,XX @@ typedef unsigned int RING_IDX;

*/

#define __CONST_RING_SIZE(_s, _sz) \

(__RD32(((_sz) - offsetof(struct _s##_sring, ring)) / \

-     sizeof(((struct _s##_sring *)0)->ring[0])))

+ sizeof_field(struct _s##_sring, ring[0])))

/*

* The same for passing in an actual pointer instead of a name tag.

*/

diff --git a/include/qemu/compiler.h b/include/qemu/compiler.h

--- a/include/qemu/compiler.h

+++ b/include/qemu/compiler.h

@@ -XXX,XX +XXX,XX @@

(type *) ((char *) __mptr - offsetof(type, member));})

#endif

+#define sizeof_field(type, field) sizeof(((type *)0)->field)

+

/* Convert from a base type to a parent type, with compile time checking. */

#ifdef __GNUC__

#define DO_UPCAST(type, field, dev) ( __extension__ ( { \

diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c

--- a/accel/tcg/translate-all.c

+++ b/accel/tcg/translate-all.c

@@ -XXX,XX +XXX,XX @@ struct page_collection {

/* Make sure all possible CPU event bits fit in tb->trace_vcpu_dstate */

QEMU_BUILD_BUG_ON(CPU_TRACE_DSTATE_MAX_EVENTS >

- sizeof(((TranslationBlock *)0)->trace_vcpu_dstate)

+ sizeof_field(TranslationBlock, trace_vcpu_dstate)

* BITS_PER_BYTE);

/*

diff --git a/hw/display/xenfb.c b/hw/display/xenfb.c

--- a/hw/display/xenfb.c

+++ b/hw/display/xenfb.c

@@ -XXX,XX +XXX,XX @@ static int xenfb_configure_fb(struct XenFB *xenfb, size_t fb_len_lim,

int width, int height, int depth,

size_t fb_len, int offset, int row_stride)

- size_t mfn_sz = sizeof(*((struct xenfb_page *)0)->pd);

- size_t pd_len = sizeof(((struct xenfb_page *)0)->pd) / mfn_sz;

+ size_t mfn_sz = sizeof_field(struct xenfb_page, pd[0]);

+ size_t pd_len = sizeof_field(struct xenfb_page, pd) / mfn_sz;

size_t fb_pages = pd_len * XC_PAGE_SIZE / mfn_sz;

size_t fb_len_max = fb_pages * XC_PAGE_SIZE;

int max_width, max_height;

diff --git a/hw/net/rocker/rocker_of_dpa.c b/hw/net/rocker/rocker_of_dpa.c

index XXXXXXX..XXXXXXX 100644

--- a/hw/net/rocker/rocker_of_dpa.c

+++ b/hw/net/rocker/rocker_of_dpa.c

@@ -XXX,XX +XXX,XX @@ typedef struct of_dpa_flow_key {

/* Width of key which includes field 'f' in u64s, rounded up */

#define FLOW_KEY_WIDTH(f) \

- DIV_ROUND_UP(offsetof(OfDpaFlowKey, f) + sizeof(((OfDpaFlowKey *)0)->f), \

+ DIV_ROUND_UP(offsetof(OfDpaFlowKey, f) + sizeof_field(OfDpaFlowKey, f), \

sizeof(uint64_t))

typedef struct of_dpa_flow_action {

diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c

index XXXXXXX..XXXXXXX 100644

--- a/hw/net/virtio-net.c

+++ b/hw/net/virtio-net.c

@@ -XXX,XX +XXX,XX @@

* 'container'.

*/

#define endof(container, field) \

- (offsetof(container, field) + sizeof(((container *)0)->field))

+ (offsetof(container, field) + sizeof_field(container, field))

typedef struct VirtIOFeature {

uint64_t flags;

diff --git a/target/i386/kvm.c b/target/i386/kvm.c

index XXXXXXX..XXXXXXX 100644

--- a/target/i386/kvm.c

+++ b/target/i386/kvm.c

@@ -XXX,XX +XXX,XX @@ static int kvm_put_fpu(X86CPU *cpu)

#define XSAVE_PKRU 672

#define XSAVE_BYTE_OFFSET(word_offset) \

- ((word_offset) * sizeof(((struct kvm_xsave *)0)->region[0]))

+ ((word_offset) * sizeof_field(struct kvm_xsave, region[0]))

#define ASSERT_OFFSET(word_offset, field) \

QEMU_BUILD_BUG_ON(XSAVE_BYTE_OFFSET(word_offset) != \

diff --git a/target/ppc/arch_dump.c b/target/ppc/arch_dump.c

index XXXXXXX..XXXXXXX 100644

--- a/target/ppc/arch_dump.c

+++ b/target/ppc/arch_dump.c

@@ -XXX,XX +XXX,XX @@ static const struct NoteFuncDescStruct {

int contents_size;

void (*note_contents_func)(NoteFuncArg *arg, PowerPCCPU *cpu);

} note_func[] = {

- {sizeof(((Note *)0)->contents.prstatus), ppc_write_elf_prstatus},

- {sizeof(((Note *)0)->contents.fpregset), ppc_write_elf_fpregset},

- {sizeof(((Note *)0)->contents.vmxregset), ppc_write_elf_vmxregset},

- {sizeof(((Note *)0)->contents.vsxregset), ppc_write_elf_vsxregset},

- {sizeof(((Note *)0)->contents.speregset), ppc_write_elf_speregset},

+ {sizeof_field(Note, contents.prstatus), ppc_write_elf_prstatus},

+ {sizeof_field(Note, contents.fpregset), ppc_write_elf_fpregset},

+ {sizeof_field(Note, contents.vmxregset), ppc_write_elf_vmxregset},

+ {sizeof_field(Note, contents.vsxregset), ppc_write_elf_vsxregset},

+ {sizeof_field(Note, contents.speregset), ppc_write_elf_speregset},

{ 0, NULL}

diff --git a/target/s390x/arch_dump.c b/target/s390x/arch_dump.c

index XXXXXXX..XXXXXXX 100644

--- a/target/s390x/arch_dump.c

+++ b/target/s390x/arch_dump.c

@@ -XXX,XX +XXX,XX @@ typedef struct NoteFuncDescStruct {

} NoteFuncDesc;

static const NoteFuncDesc note_core[] = {

- {sizeof(((Note *)0)->contents.prstatus), s390x_write_elf64_prstatus},

- {sizeof(((Note *)0)->contents.fpregset), s390x_write_elf64_fpregset},

+ {sizeof_field(Note, contents.prstatus), s390x_write_elf64_prstatus},

+ {sizeof_field(Note, contents.fpregset), s390x_write_elf64_fpregset},

{ 0, NULL}

static const NoteFuncDesc note_linux[] = {

- {sizeof(((Note *)0)->contents.prefix), s390x_write_elf64_prefix},

- {sizeof(((Note *)0)->contents.ctrs), s390x_write_elf64_ctrs},

- {sizeof(((Note *)0)->contents.timer), s390x_write_elf64_timer},

- {sizeof(((Note *)0)->contents.todcmp), s390x_write_elf64_todcmp},

- {sizeof(((Note *)0)->contents.todpreg), s390x_write_elf64_todpreg},

- {sizeof(((Note *)0)->contents.vregslo), s390x_write_elf64_vregslo},

- {sizeof(((Note *)0)->contents.vregshi), s390x_write_elf64_vregshi},

- {sizeof(((Note *)0)->contents.gscb), s390x_write_elf64_gscb},

+ {sizeof_field(Note, contents.prefix), s390x_write_elf64_prefix},

+ {sizeof_field(Note, contents.ctrs), s390x_write_elf64_ctrs},

+ {sizeof_field(Note, contents.timer), s390x_write_elf64_timer},

+ {sizeof_field(Note, contents.todcmp), s390x_write_elf64_todcmp},

+ {sizeof_field(Note, contents.todpreg), s390x_write_elf64_todpreg},

+ {sizeof_field(Note, contents.vregslo), s390x_write_elf64_vregslo},

+ {sizeof_field(Note, contents.vregshi), s390x_write_elf64_vregshi},

+ {sizeof_field(Note, contents.gscb), s390x_write_elf64_gscb},

{ 0, NULL}

};

2.17.1

From: Nishanth Aravamudan <naravamudan@digitalocean.com>

laio_init() can fail for a couple of reasons, which will lead to a NULL

pointer dereference in laio_attach_aio_context().

To solve this, add a aio_setup_linux_aio() function which is called

early in raw_open_common. If this fails, propagate the error up. The

signature of aio_get_linux_aio() was not modified, because it seems

preferable to return the actual errno from the possible failing

initialization calls.

Additionally, when the AioContext changes, we need to associate a

LinuxAioState with the new AioContext. Use the bdrv_attach_aio_context

callback and call the new aio_setup_linux_aio(), which will allocate a

new AioContext if needed, and return errors on failures. If it fails for

any reason, fallback to threaded AIO with an error message, as the

device is already in-use by the guest.

Add an assert that aio_get_linux_aio() cannot return NULL.

Signed-off-by: Nishanth Aravamudan <naravamudan@digitalocean.com>

Message-id: 20180622193700.6523-1-naravamudan@digitalocean.com

include/block/aio.h | 3 +++

include/block/raw-aio.h | 2 +-

block/file-posix.c | 33 ++++++++++++++++++++++++++++-----

block/linux-aio.c | 12 +++++++++---

stubs/linux-aio.c | 2 +-

util/async.c | 14 +++++++++++---

6 files changed, 53 insertions(+), 13 deletions(-)

@@ -XXX,XX +XXX,XX @@ GSource *aio_get_g_source(AioContext *ctx);

/* Return the ThreadPool bound to this AioContext */

struct ThreadPool *aio_get_thread_pool(AioContext *ctx);

+/* Setup the LinuxAioState bound to this AioContext */

+struct LinuxAioState *aio_setup_linux_aio(AioContext *ctx, Error **errp);

+

/* Return the LinuxAioState bound to this AioContext */

struct LinuxAioState *aio_get_linux_aio(AioContext *ctx);

diff --git a/include/block/raw-aio.h b/include/block/raw-aio.h

index XXXXXXX..XXXXXXX 100644

--- a/include/block/raw-aio.h

+++ b/include/block/raw-aio.h

@@ -XXX,XX +XXX,XX @@

/* linux-aio.c - Linux native implementation */

#ifdef CONFIG_LINUX_AIO

typedef struct LinuxAioState LinuxAioState;

-LinuxAioState *laio_init(void);

+LinuxAioState *laio_init(Error **errp);

void laio_cleanup(LinuxAioState *s);

int coroutine_fn laio_co_submit(BlockDriverState *bs, LinuxAioState *s, int fd,

uint64_t offset, QEMUIOVector *qiov, int type);

diff --git a/block/file-posix.c b/block/file-posix.c

index XXXXXXX..XXXXXXX 100644

--- a/block/file-posix.c

+++ b/block/file-posix.c

@@ -XXX,XX +XXX,XX @@ static int raw_open_common(BlockDriverState *bs, QDict *options,

#ifdef CONFIG_LINUX_AIO

/* Currently Linux does AIO only for files opened with O_DIRECT */

- if (s->use_linux_aio && !(s->open_flags & O_DIRECT)) {

- error_setg(errp, "aio=native was specified, but it requires "

- "cache.direct=on, which was not specified.");

- ret = -EINVAL;

- goto fail;

+ if (s->use_linux_aio) {

+ if (!(s->open_flags & O_DIRECT)) {

+ error_setg(errp, "aio=native was specified, but it requires "

+ "cache.direct=on, which was not specified.");

+ ret = -EINVAL;

+ goto fail;

+ }

+ if (!aio_setup_linux_aio(bdrv_get_aio_context(bs), errp)) {

+ error_prepend(errp, "Unable to use native AIO: ");

+ goto fail;

+ }

}

#else

if (s->use_linux_aio) {

@@ -XXX,XX +XXX,XX @@ static BlockAIOCB *raw_aio_flush(BlockDriverState *bs,

return paio_submit(bs, s->fd, 0, NULL, 0, cb, opaque, QEMU_AIO_FLUSH);

}

+static void raw_aio_attach_aio_context(BlockDriverState *bs,

+ AioContext *new_context)

+#ifdef CONFIG_LINUX_AIO

+ BDRVRawState *s = bs->opaque;

+ if (s->use_linux_aio) {

+ Error *local_err;

+ if (!aio_setup_linux_aio(new_context, &local_err)) {

+ error_reportf_err(local_err, "Unable to use native AIO, "

+ "falling back to thread pool: ");

+ s->use_linux_aio = false;

+ }

+ }

+#endif

static void raw_close(BlockDriverState *bs)

{

BDRVRawState *s = bs->opaque;

@@ -XXX,XX +XXX,XX @@ BlockDriver bdrv_file = {

.bdrv_refresh_limits = raw_refresh_limits,

.bdrv_io_plug = raw_aio_plug,

.bdrv_io_unplug = raw_aio_unplug,

+ .bdrv_attach_aio_context = raw_aio_attach_aio_context,

.bdrv_truncate = raw_truncate,

.bdrv_getlength = raw_getlength,

diff --git a/block/linux-aio.c b/block/linux-aio.c

index XXXXXXX..XXXXXXX 100644

--- a/block/linux-aio.c

+++ b/block/linux-aio.c

@@ -XXX,XX +XXX,XX @@

#include "block/raw-aio.h"

#include "qemu/event_notifier.h"

#include "qemu/coroutine.h"

+#include "qapi/error.h"

#include <libaio.h>

@@ -XXX,XX +XXX,XX @@ void laio_attach_aio_context(LinuxAioState *s, AioContext *new_context)

qemu_laio_poll_cb);

}

-LinuxAioState *laio_init(void)

+LinuxAioState *laio_init(Error **errp)

{

+ int rc;

LinuxAioState *s;

s = g_malloc0(sizeof(*s));

- if (event_notifier_init(&s->e, false) < 0) {

+ rc = event_notifier_init(&s->e, false);

+ if (rc < 0) {

+ error_setg_errno(errp, -rc, "failed to to initialize event notifier");

goto out_free_state;

}

- if (io_setup(MAX_EVENTS, &s->ctx) != 0) {

+ rc = io_setup(MAX_EVENTS, &s->ctx);

+ if (rc < 0) {

+ error_setg_errno(errp, -rc, "failed to create linux AIO context");

goto out_close_efd;

}

diff --git a/stubs/linux-aio.c b/stubs/linux-aio.c

index XXXXXXX..XXXXXXX 100644

--- a/stubs/linux-aio.c

+++ b/stubs/linux-aio.c

@@ -XXX,XX +XXX,XX @@ void laio_attach_aio_context(LinuxAioState *s, AioContext *new_context)

abort();

}

-LinuxAioState *laio_init(void)

+LinuxAioState *laio_init(Error **errp)

{

abort();

}

@@ -XXX,XX +XXX,XX @@ ThreadPool *aio_get_thread_pool(AioContext *ctx)

}

#ifdef CONFIG_LINUX_AIO

-LinuxAioState *aio_get_linux_aio(AioContext *ctx)

+LinuxAioState *aio_setup_linux_aio(AioContext *ctx, Error **errp)

if (!ctx->linux_aio) {

- ctx->linux_aio = laio_init();

- laio_attach_aio_context(ctx->linux_aio, ctx);

+ ctx->linux_aio = laio_init(errp);

+ if (ctx->linux_aio) {

+ laio_attach_aio_context(ctx->linux_aio, ctx);

+ }

return ctx->linux_aio;

}

+

+LinuxAioState *aio_get_linux_aio(AioContext *ctx)

+ assert(ctx->linux_aio);

+ return ctx->linux_aio;

#endif

void aio_notify(AioContext *ctx)

2.17.1