diff mbox series

[v4,11/19] vhost: introduce postcopy's advise message

Message ID 20181008152557.14275-12-maxime.coquelin@redhat.com (mailing list archive)
State Superseded, archived
Delegated to: Maxime Coquelin
Headers
Series vhost: add postcopy live-migration support |

Checks

Context Check Description
ci/Intel-compilation success Compilation OK

Commit Message

Maxime Coquelin Oct. 8, 2018, 3:25 p.m. UTC 
  This patch opens a userfaultfd and sends it back to Qemu's
VHOST_USER_POSTCOPY_ADVISE request.

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
---
 lib/librte_vhost/vhost.h      |  2 ++
 lib/librte_vhost/vhost_user.c | 49 +++++++++++++++++++++++++++++++++++
 lib/librte_vhost/vhost_user.h |  3 ++-
 3 files changed, 53 insertions(+), 1 deletion(-)

Comments

Ilya Maximets Oct. 8, 2018, 4:22 p.m. UTC | #1 
On 08.10.2018 18:25, Maxime Coquelin wrote:
> This patch opens a userfaultfd and sends it back to Qemu's
> VHOST_USER_POSTCOPY_ADVISE request.
> 
> Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
> Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
> ---
>  lib/librte_vhost/vhost.h      |  2 ++
>  lib/librte_vhost/vhost_user.c | 49 +++++++++++++++++++++++++++++++++++
>  lib/librte_vhost/vhost_user.h |  3 ++-
>  3 files changed, 53 insertions(+), 1 deletion(-)
> 
> diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h
> index 25ffd7614..21722d8a8 100644
> --- a/lib/librte_vhost/vhost.h
> +++ b/lib/librte_vhost/vhost.h
> @@ -363,6 +363,8 @@ struct virtio_net {
>  	int			slave_req_fd;
>  	rte_spinlock_t		slave_req_lock;
>  
> +	int			postcopy_ufd;
> +
>  	/*
>  	 * Device id to identify a specific backend device.
>  	 * It's set to -1 for the default software implementation.
> diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c
> index 20f38267d..3cdd2af28 100644
> --- a/lib/librte_vhost/vhost_user.c
> +++ b/lib/librte_vhost/vhost_user.c
> @@ -24,13 +24,19 @@
>  #include <stdlib.h>
>  #include <string.h>
>  #include <unistd.h>
> +#include <fcntl.h>
> +#include <sys/ioctl.h>
>  #include <sys/mman.h>
>  #include <sys/types.h>
>  #include <sys/stat.h>
> +#include <sys/syscall.h>
>  #include <assert.h>
>  #ifdef RTE_LIBRTE_VHOST_NUMA
>  #include <numaif.h>
>  #endif
> +#ifdef RTE_LIBRTE_VHOST_POSTCOPY
> +#include <linux/userfaultfd.h>
> +#endif
>  
>  #include <rte_common.h>
>  #include <rte_malloc.h>
> @@ -69,6 +75,7 @@ static const char *vhost_message_str[VHOST_USER_MAX] = {
>  	[VHOST_USER_IOTLB_MSG]  = "VHOST_USER_IOTLB_MSG",
>  	[VHOST_USER_CRYPTO_CREATE_SESS] = "VHOST_USER_CRYPTO_CREATE_SESS",
>  	[VHOST_USER_CRYPTO_CLOSE_SESS] = "VHOST_USER_CRYPTO_CLOSE_SESS",
> +	[VHOST_USER_POSTCOPY_ADVISE]  = "VHOST_USER_POSTCOPY_ADVISE",
>  };
>  
>  /* The possible results of a message handling function */
> @@ -130,6 +137,11 @@ vhost_backend_cleanup(struct virtio_net *dev)
>  		close(dev->slave_req_fd);
>  		dev->slave_req_fd = -1;
>  	}
> +
> +	if (dev->postcopy_ufd >= 0) {
> +		close(dev->postcopy_ufd);
> +		dev->postcopy_ufd = -1;
> +	}
>  }
>  
>  /*
> @@ -1508,6 +1520,42 @@ vhost_user_iotlb_msg(struct virtio_net **pdev, struct VhostUserMsg *msg,
>  	return VH_RESULT_OK;
>  }
>  
> +static int
> +vhost_user_set_postcopy_advise(struct virtio_net **pdev,
> +			struct VhostUserMsg *msg,
> +			int main_fd __rte_unused)
> +{
> +	struct virtio_net *dev = *pdev;
> +#ifdef RTE_LIBRTE_VHOST_POSTCOPY
> +	struct uffdio_api api_struct;
> +
> +	dev->postcopy_ufd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
> +
> +	if (dev->postcopy_ufd == -1) {
> +		RTE_LOG(ERR, VHOST_CONFIG, "Userfaultfd not available: %s\n",
> +				strerror(errno));
> +		return VH_RESULT_ERR;
> +	}
> +	api_struct.api = UFFD_API;
> +	api_struct.features = 0;
> +	if (ioctl(dev->postcopy_ufd, UFFDIO_API, &api_struct)) {
> +		RTE_LOG(ERR, VHOST_CONFIG, "UFFDIO_API ioctl failure: %s\n",
> +				strerror(errno));
> +		close(dev->postcopy_ufd);

Need to clear dev->postcopy_ufd value to avoid accidental closing of some
other fd on backend cleanup.

> +		return VH_RESULT_ERR;
> +	}
> +	msg->fds[0] = dev->postcopy_ufd;
> +	msg->fd_num = 1;
> +
> +	return VH_RESULT_REPLY;
> +#else
> +	dev->postcopy_ufd = -1;
> +	msg->fd_num = 0;
> +
> +	return VH_RESULT_ERR;
> +#endif
> +}
> +
>  typedef int (*vhost_message_handler_t)(struct virtio_net **pdev,
>  					struct VhostUserMsg *msg,
>  					int main_fd);
> @@ -1535,6 +1583,7 @@ static vhost_message_handler_t vhost_message_handlers[VHOST_USER_MAX] = {
>  	[VHOST_USER_NET_SET_MTU] = vhost_user_net_set_mtu,
>  	[VHOST_USER_SET_SLAVE_REQ_FD] = vhost_user_set_req_fd,
>  	[VHOST_USER_IOTLB_MSG] = vhost_user_iotlb_msg,
> +	[VHOST_USER_POSTCOPY_ADVISE] = vhost_user_set_postcopy_advise,
>  };
>  
>  
> diff --git a/lib/librte_vhost/vhost_user.h b/lib/librte_vhost/vhost_user.h
> index dd0262f8f..2030b40a5 100644
> --- a/lib/librte_vhost/vhost_user.h
> +++ b/lib/librte_vhost/vhost_user.h
> @@ -50,7 +50,8 @@ typedef enum VhostUserRequest {
>  	VHOST_USER_IOTLB_MSG = 22,
>  	VHOST_USER_CRYPTO_CREATE_SESS = 26,
>  	VHOST_USER_CRYPTO_CLOSE_SESS = 27,
> -	VHOST_USER_MAX = 28
> +	VHOST_USER_POSTCOPY_ADVISE = 28,
> +	VHOST_USER_MAX = 29
>  } VhostUserRequest;
>  
>  typedef enum VhostUserSlaveRequest {
>
Maxime Coquelin Oct. 9, 2018, 7:59 a.m. UTC | #2 
On 10/08/2018 06:22 PM, Ilya Maximets wrote:
> On 08.10.2018 18:25, Maxime Coquelin wrote:
>> This patch opens a userfaultfd and sends it back to Qemu's
>> VHOST_USER_POSTCOPY_ADVISE request.
>>
>> Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
>> Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
>> ---
>>   lib/librte_vhost/vhost.h      |  2 ++
>>   lib/librte_vhost/vhost_user.c | 49 +++++++++++++++++++++++++++++++++++
>>   lib/librte_vhost/vhost_user.h |  3 ++-
>>   3 files changed, 53 insertions(+), 1 deletion(-)
>>
>> diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h
>> index 25ffd7614..21722d8a8 100644
>> --- a/lib/librte_vhost/vhost.h
>> +++ b/lib/librte_vhost/vhost.h
>> @@ -363,6 +363,8 @@ struct virtio_net {
>>   	int			slave_req_fd;
>>   	rte_spinlock_t		slave_req_lock;
>>   
>> +	int			postcopy_ufd;
>> +
>>   	/*
>>   	 * Device id to identify a specific backend device.
>>   	 * It's set to -1 for the default software implementation.
>> diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c
>> index 20f38267d..3cdd2af28 100644
>> --- a/lib/librte_vhost/vhost_user.c
>> +++ b/lib/librte_vhost/vhost_user.c
>> @@ -24,13 +24,19 @@
>>   #include <stdlib.h>
>>   #include <string.h>
>>   #include <unistd.h>
>> +#include <fcntl.h>
>> +#include <sys/ioctl.h>
>>   #include <sys/mman.h>
>>   #include <sys/types.h>
>>   #include <sys/stat.h>
>> +#include <sys/syscall.h>
>>   #include <assert.h>
>>   #ifdef RTE_LIBRTE_VHOST_NUMA
>>   #include <numaif.h>
>>   #endif
>> +#ifdef RTE_LIBRTE_VHOST_POSTCOPY
>> +#include <linux/userfaultfd.h>
>> +#endif
>>   
>>   #include <rte_common.h>
>>   #include <rte_malloc.h>
>> @@ -69,6 +75,7 @@ static const char *vhost_message_str[VHOST_USER_MAX] = {
>>   	[VHOST_USER_IOTLB_MSG]  = "VHOST_USER_IOTLB_MSG",
>>   	[VHOST_USER_CRYPTO_CREATE_SESS] = "VHOST_USER_CRYPTO_CREATE_SESS",
>>   	[VHOST_USER_CRYPTO_CLOSE_SESS] = "VHOST_USER_CRYPTO_CLOSE_SESS",
>> +	[VHOST_USER_POSTCOPY_ADVISE]  = "VHOST_USER_POSTCOPY_ADVISE",
>>   };
>>   
>>   /* The possible results of a message handling function */
>> @@ -130,6 +137,11 @@ vhost_backend_cleanup(struct virtio_net *dev)
>>   		close(dev->slave_req_fd);
>>   		dev->slave_req_fd = -1;
>>   	}
>> +
>> +	if (dev->postcopy_ufd >= 0) {
>> +		close(dev->postcopy_ufd);
>> +		dev->postcopy_ufd = -1;
>> +	}
>>   }
>>   
>>   /*
>> @@ -1508,6 +1520,42 @@ vhost_user_iotlb_msg(struct virtio_net **pdev, struct VhostUserMsg *msg,
>>   	return VH_RESULT_OK;
>>   }
>>   
>> +static int
>> +vhost_user_set_postcopy_advise(struct virtio_net **pdev,
>> +			struct VhostUserMsg *msg,
>> +			int main_fd __rte_unused)
>> +{
>> +	struct virtio_net *dev = *pdev;
>> +#ifdef RTE_LIBRTE_VHOST_POSTCOPY
>> +	struct uffdio_api api_struct;
>> +
>> +	dev->postcopy_ufd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
>> +
>> +	if (dev->postcopy_ufd == -1) {
>> +		RTE_LOG(ERR, VHOST_CONFIG, "Userfaultfd not available: %s\n",
>> +				strerror(errno));
>> +		return VH_RESULT_ERR;
>> +	}
>> +	api_struct.api = UFFD_API;
>> +	api_struct.features = 0;
>> +	if (ioctl(dev->postcopy_ufd, UFFDIO_API, &api_struct)) {
>> +		RTE_LOG(ERR, VHOST_CONFIG, "UFFDIO_API ioctl failure: %s\n",
>> +				strerror(errno));
>> +		close(dev->postcopy_ufd);
> 
> Need to clear dev->postcopy_ufd value to avoid accidental closing of some
> other fd on backend cleanup.


Good catch, it will be fixed in v5.

Thanks!
Maxime
diff mbox series

Patch

diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h
index 25ffd7614..21722d8a8 100644
--- a/lib/librte_vhost/vhost.h
+++ b/lib/librte_vhost/vhost.h
@@ -363,6 +363,8 @@  struct virtio_net {
 	int			slave_req_fd;
 	rte_spinlock_t		slave_req_lock;
 
+	int			postcopy_ufd;
+
 	/*
 	 * Device id to identify a specific backend device.
 	 * It's set to -1 for the default software implementation.
diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c
index 20f38267d..3cdd2af28 100644
--- a/lib/librte_vhost/vhost_user.c
+++ b/lib/librte_vhost/vhost_user.c
@@ -24,13 +24,19 @@ 
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
+#include <fcntl.h>
+#include <sys/ioctl.h>
 #include <sys/mman.h>
 #include <sys/types.h>
 #include <sys/stat.h>
+#include <sys/syscall.h>
 #include <assert.h>
 #ifdef RTE_LIBRTE_VHOST_NUMA
 #include <numaif.h>
 #endif
+#ifdef RTE_LIBRTE_VHOST_POSTCOPY
+#include <linux/userfaultfd.h>
+#endif
 
 #include <rte_common.h>
 #include <rte_malloc.h>
@@ -69,6 +75,7 @@  static const char *vhost_message_str[VHOST_USER_MAX] = {
 	[VHOST_USER_IOTLB_MSG]  = "VHOST_USER_IOTLB_MSG",
 	[VHOST_USER_CRYPTO_CREATE_SESS] = "VHOST_USER_CRYPTO_CREATE_SESS",
 	[VHOST_USER_CRYPTO_CLOSE_SESS] = "VHOST_USER_CRYPTO_CLOSE_SESS",
+	[VHOST_USER_POSTCOPY_ADVISE]  = "VHOST_USER_POSTCOPY_ADVISE",
 };
 
 /* The possible results of a message handling function */
@@ -130,6 +137,11 @@  vhost_backend_cleanup(struct virtio_net *dev)
 		close(dev->slave_req_fd);
 		dev->slave_req_fd = -1;
 	}
+
+	if (dev->postcopy_ufd >= 0) {
+		close(dev->postcopy_ufd);
+		dev->postcopy_ufd = -1;
+	}
 }
 
 /*
@@ -1508,6 +1520,42 @@  vhost_user_iotlb_msg(struct virtio_net **pdev, struct VhostUserMsg *msg,
 	return VH_RESULT_OK;
 }
 
+static int
+vhost_user_set_postcopy_advise(struct virtio_net **pdev,
+			struct VhostUserMsg *msg,
+			int main_fd __rte_unused)
+{
+	struct virtio_net *dev = *pdev;
+#ifdef RTE_LIBRTE_VHOST_POSTCOPY
+	struct uffdio_api api_struct;
+
+	dev->postcopy_ufd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
+
+	if (dev->postcopy_ufd == -1) {
+		RTE_LOG(ERR, VHOST_CONFIG, "Userfaultfd not available: %s\n",
+				strerror(errno));
+		return VH_RESULT_ERR;
+	}
+	api_struct.api = UFFD_API;
+	api_struct.features = 0;
+	if (ioctl(dev->postcopy_ufd, UFFDIO_API, &api_struct)) {
+		RTE_LOG(ERR, VHOST_CONFIG, "UFFDIO_API ioctl failure: %s\n",
+				strerror(errno));
+		close(dev->postcopy_ufd);
+		return VH_RESULT_ERR;
+	}
+	msg->fds[0] = dev->postcopy_ufd;
+	msg->fd_num = 1;
+
+	return VH_RESULT_REPLY;
+#else
+	dev->postcopy_ufd = -1;
+	msg->fd_num = 0;
+
+	return VH_RESULT_ERR;
+#endif
+}
+
 typedef int (*vhost_message_handler_t)(struct virtio_net **pdev,
 					struct VhostUserMsg *msg,
 					int main_fd);
@@ -1535,6 +1583,7 @@  static vhost_message_handler_t vhost_message_handlers[VHOST_USER_MAX] = {
 	[VHOST_USER_NET_SET_MTU] = vhost_user_net_set_mtu,
 	[VHOST_USER_SET_SLAVE_REQ_FD] = vhost_user_set_req_fd,
 	[VHOST_USER_IOTLB_MSG] = vhost_user_iotlb_msg,
+	[VHOST_USER_POSTCOPY_ADVISE] = vhost_user_set_postcopy_advise,
 };
 
 
diff --git a/lib/librte_vhost/vhost_user.h b/lib/librte_vhost/vhost_user.h
index dd0262f8f..2030b40a5 100644
--- a/lib/librte_vhost/vhost_user.h
+++ b/lib/librte_vhost/vhost_user.h
@@ -50,7 +50,8 @@  typedef enum VhostUserRequest {
 	VHOST_USER_IOTLB_MSG = 22,
 	VHOST_USER_CRYPTO_CREATE_SESS = 26,
 	VHOST_USER_CRYPTO_CLOSE_SESS = 27,
-	VHOST_USER_MAX = 28
+	VHOST_USER_POSTCOPY_ADVISE = 28,
+	VHOST_USER_MAX = 29
 } VhostUserRequest;
 
 typedef enum VhostUserSlaveRequest {