From: Stefano Stabellini <sstabellini@kernel.org> To: xen-devel@lists.xen.org Cc: linux-kernel@vger.kernel.org, sstabellini@kernel.org, jgross@suse.com, boris.ostrovsky@oracle.com, Stefano Stabellini <stefano@aporeto.com> Subject: [PATCH v7 11/13] xen/pvcalls: implement poll command Date: Thu, 26 Oct 2017 12:11:50 -0700 [thread overview] Message-ID: <1509045112-9807-11-git-send-email-sstabellini@kernel.org> (raw) In-Reply-To: <1509045112-9807-1-git-send-email-sstabellini@kernel.org> For active sockets, check the indexes and use the inflight_conn_req waitqueue to wait. For passive sockets if an accept is outstanding (PVCALLS_FLAG_ACCEPT_INFLIGHT), check if it has been answered by looking at bedata->rsp[req_id]. If so, return POLLIN. Otherwise use the inflight_accept_req waitqueue. If no accepts are inflight, send PVCALLS_POLL to the backend. If we have outstanding POLL requests awaiting for a response use the inflight_req waitqueue: inflight_req is awaken when a new response is received; on wakeup we check whether the POLL response is arrived by looking at the PVCALLS_FLAG_POLL_RET flag. We set the flag from pvcalls_front_event_handler, if the response was for a POLL command. In pvcalls_front_event_handler, get the struct sock_mapping from the poll id (we previously converted struct sock_mapping* to uint64_t and used it as id). Signed-off-by: Stefano Stabellini <stefano@aporeto.com> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> CC: boris.ostrovsky@oracle.com CC: jgross@suse.com --- drivers/xen/pvcalls-front.c | 144 +++++++++++++++++++++++++++++++++++++++++--- drivers/xen/pvcalls-front.h | 3 + 2 files changed, 138 insertions(+), 9 deletions(-) diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c index 9a505cb..eab70ce 100644 --- a/drivers/xen/pvcalls-front.c +++ b/drivers/xen/pvcalls-front.c @@ -83,6 +83,8 @@ struct sock_mapping { * Only one poll operation can be inflight for a given socket. */ #define PVCALLS_FLAG_ACCEPT_INFLIGHT 0 +#define PVCALLS_FLAG_POLL_INFLIGHT 1 +#define PVCALLS_FLAG_POLL_RET 2 uint8_t flags; uint32_t inflight_req_id; struct sock_mapping *accept_map; @@ -154,15 +156,32 @@ static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id) rsp = RING_GET_RESPONSE(&bedata->ring, bedata->ring.rsp_cons); req_id = rsp->req_id; - dst = (uint8_t *)&bedata->rsp[req_id] + sizeof(rsp->req_id); - src = (uint8_t *)rsp + sizeof(rsp->req_id); - memcpy(dst, src, sizeof(*rsp) - sizeof(rsp->req_id)); - /* - * First copy the rest of the data, then req_id. It is - * paired with the barrier when accessing bedata->rsp. - */ - smp_wmb(); - bedata->rsp[req_id].req_id = rsp->req_id; + if (rsp->cmd == PVCALLS_POLL) { + struct sock_mapping *map = (struct sock_mapping *) + rsp->u.poll.id; + + clear_bit(PVCALLS_FLAG_POLL_INFLIGHT, + (void *)&map->passive.flags); + /* + * clear INFLIGHT, then set RET. It pairs with + * the checks at the beginning of + * pvcalls_front_poll_passive. + */ + smp_wmb(); + set_bit(PVCALLS_FLAG_POLL_RET, + (void *)&map->passive.flags); + } else { + dst = (uint8_t *)&bedata->rsp[req_id] + + sizeof(rsp->req_id); + src = (uint8_t *)rsp + sizeof(rsp->req_id); + memcpy(dst, src, sizeof(*rsp) - sizeof(rsp->req_id)); + /* + * First copy the rest of the data, then req_id. It is + * paired with the barrier when accessing bedata->rsp. + */ + smp_wmb(); + bedata->rsp[req_id].req_id = req_id; + } done = 1; bedata->ring.rsp_cons++; @@ -840,6 +859,113 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags) return ret; } +static unsigned int pvcalls_front_poll_passive(struct file *file, + struct pvcalls_bedata *bedata, + struct sock_mapping *map, + poll_table *wait) +{ + int notify, req_id, ret; + struct xen_pvcalls_request *req; + + if (test_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT, + (void *)&map->passive.flags)) { + uint32_t req_id = READ_ONCE(map->passive.inflight_req_id); + + if (req_id != PVCALLS_INVALID_ID && + READ_ONCE(bedata->rsp[req_id].req_id) == req_id) + return POLLIN | POLLRDNORM; + + poll_wait(file, &map->passive.inflight_accept_req, wait); + return 0; + } + + if (test_and_clear_bit(PVCALLS_FLAG_POLL_RET, + (void *)&map->passive.flags)) + return POLLIN | POLLRDNORM; + + /* + * First check RET, then INFLIGHT. No barriers necessary to + * ensure execution ordering because of the conditional + * instructions creating control dependencies. + */ + + if (test_and_set_bit(PVCALLS_FLAG_POLL_INFLIGHT, + (void *)&map->passive.flags)) { + poll_wait(file, &bedata->inflight_req, wait); + return 0; + } + + spin_lock(&bedata->socket_lock); + ret = get_request(bedata, &req_id); + if (ret < 0) { + spin_unlock(&bedata->socket_lock); + return ret; + } + req = RING_GET_REQUEST(&bedata->ring, req_id); + req->req_id = req_id; + req->cmd = PVCALLS_POLL; + req->u.poll.id = (uint64_t) map; + + bedata->ring.req_prod_pvt++; + RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&bedata->ring, notify); + spin_unlock(&bedata->socket_lock); + if (notify) + notify_remote_via_irq(bedata->irq); + + poll_wait(file, &bedata->inflight_req, wait); + return 0; +} + +static unsigned int pvcalls_front_poll_active(struct file *file, + struct pvcalls_bedata *bedata, + struct sock_mapping *map, + poll_table *wait) +{ + unsigned int mask = 0; + int32_t in_error, out_error; + struct pvcalls_data_intf *intf = map->active.ring; + + out_error = intf->out_error; + in_error = intf->in_error; + + poll_wait(file, &map->active.inflight_conn_req, wait); + if (pvcalls_front_write_todo(map)) + mask |= POLLOUT | POLLWRNORM; + if (pvcalls_front_read_todo(map)) + mask |= POLLIN | POLLRDNORM; + if (in_error != 0 || out_error != 0) + mask |= POLLERR; + + return mask; +} + +unsigned int pvcalls_front_poll(struct file *file, struct socket *sock, + poll_table *wait) +{ + struct pvcalls_bedata *bedata; + struct sock_mapping *map; + int ret; + + pvcalls_enter(); + if (!pvcalls_front_dev) { + pvcalls_exit(); + return POLLNVAL; + } + bedata = dev_get_drvdata(&pvcalls_front_dev->dev); + + map = (struct sock_mapping *) sock->sk->sk_send_head; + if (!map) { + pvcalls_exit(); + return POLLNVAL; + } + if (map->active_socket) + ret = pvcalls_front_poll_active(file, bedata, map, wait); + else + ret = pvcalls_front_poll_passive(file, bedata, map, wait); + pvcalls_exit(); + return ret; +} + static const struct xenbus_device_id pvcalls_front_ids[] = { { "pvcalls" }, { "" } diff --git a/drivers/xen/pvcalls-front.h b/drivers/xen/pvcalls-front.h index de24041..25e05b8 100644 --- a/drivers/xen/pvcalls-front.h +++ b/drivers/xen/pvcalls-front.h @@ -20,5 +20,8 @@ int pvcalls_front_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); +unsigned int pvcalls_front_poll(struct file *file, + struct socket *sock, + poll_table *wait); #endif -- 1.9.1
WARNING: multiple messages have this Message-ID (diff)
From: Stefano Stabellini <sstabellini@kernel.org> To: xen-devel@lists.xen.org Cc: jgross@suse.com, Stefano Stabellini <stefano@aporeto.com>, boris.ostrovsky@oracle.com, sstabellini@kernel.org, linux-kernel@vger.kernel.org Subject: [PATCH v7 11/13] xen/pvcalls: implement poll command Date: Thu, 26 Oct 2017 12:11:50 -0700 [thread overview] Message-ID: <1509045112-9807-11-git-send-email-sstabellini@kernel.org> (raw) In-Reply-To: <1509045112-9807-1-git-send-email-sstabellini@kernel.org> For active sockets, check the indexes and use the inflight_conn_req waitqueue to wait. For passive sockets if an accept is outstanding (PVCALLS_FLAG_ACCEPT_INFLIGHT), check if it has been answered by looking at bedata->rsp[req_id]. If so, return POLLIN. Otherwise use the inflight_accept_req waitqueue. If no accepts are inflight, send PVCALLS_POLL to the backend. If we have outstanding POLL requests awaiting for a response use the inflight_req waitqueue: inflight_req is awaken when a new response is received; on wakeup we check whether the POLL response is arrived by looking at the PVCALLS_FLAG_POLL_RET flag. We set the flag from pvcalls_front_event_handler, if the response was for a POLL command. In pvcalls_front_event_handler, get the struct sock_mapping from the poll id (we previously converted struct sock_mapping* to uint64_t and used it as id). Signed-off-by: Stefano Stabellini <stefano@aporeto.com> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com> CC: boris.ostrovsky@oracle.com CC: jgross@suse.com --- drivers/xen/pvcalls-front.c | 144 +++++++++++++++++++++++++++++++++++++++++--- drivers/xen/pvcalls-front.h | 3 + 2 files changed, 138 insertions(+), 9 deletions(-) diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c index 9a505cb..eab70ce 100644 --- a/drivers/xen/pvcalls-front.c +++ b/drivers/xen/pvcalls-front.c @@ -83,6 +83,8 @@ struct sock_mapping { * Only one poll operation can be inflight for a given socket. */ #define PVCALLS_FLAG_ACCEPT_INFLIGHT 0 +#define PVCALLS_FLAG_POLL_INFLIGHT 1 +#define PVCALLS_FLAG_POLL_RET 2 uint8_t flags; uint32_t inflight_req_id; struct sock_mapping *accept_map; @@ -154,15 +156,32 @@ static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id) rsp = RING_GET_RESPONSE(&bedata->ring, bedata->ring.rsp_cons); req_id = rsp->req_id; - dst = (uint8_t *)&bedata->rsp[req_id] + sizeof(rsp->req_id); - src = (uint8_t *)rsp + sizeof(rsp->req_id); - memcpy(dst, src, sizeof(*rsp) - sizeof(rsp->req_id)); - /* - * First copy the rest of the data, then req_id. It is - * paired with the barrier when accessing bedata->rsp. - */ - smp_wmb(); - bedata->rsp[req_id].req_id = rsp->req_id; + if (rsp->cmd == PVCALLS_POLL) { + struct sock_mapping *map = (struct sock_mapping *) + rsp->u.poll.id; + + clear_bit(PVCALLS_FLAG_POLL_INFLIGHT, + (void *)&map->passive.flags); + /* + * clear INFLIGHT, then set RET. It pairs with + * the checks at the beginning of + * pvcalls_front_poll_passive. + */ + smp_wmb(); + set_bit(PVCALLS_FLAG_POLL_RET, + (void *)&map->passive.flags); + } else { + dst = (uint8_t *)&bedata->rsp[req_id] + + sizeof(rsp->req_id); + src = (uint8_t *)rsp + sizeof(rsp->req_id); + memcpy(dst, src, sizeof(*rsp) - sizeof(rsp->req_id)); + /* + * First copy the rest of the data, then req_id. It is + * paired with the barrier when accessing bedata->rsp. + */ + smp_wmb(); + bedata->rsp[req_id].req_id = req_id; + } done = 1; bedata->ring.rsp_cons++; @@ -840,6 +859,113 @@ int pvcalls_front_accept(struct socket *sock, struct socket *newsock, int flags) return ret; } +static unsigned int pvcalls_front_poll_passive(struct file *file, + struct pvcalls_bedata *bedata, + struct sock_mapping *map, + poll_table *wait) +{ + int notify, req_id, ret; + struct xen_pvcalls_request *req; + + if (test_bit(PVCALLS_FLAG_ACCEPT_INFLIGHT, + (void *)&map->passive.flags)) { + uint32_t req_id = READ_ONCE(map->passive.inflight_req_id); + + if (req_id != PVCALLS_INVALID_ID && + READ_ONCE(bedata->rsp[req_id].req_id) == req_id) + return POLLIN | POLLRDNORM; + + poll_wait(file, &map->passive.inflight_accept_req, wait); + return 0; + } + + if (test_and_clear_bit(PVCALLS_FLAG_POLL_RET, + (void *)&map->passive.flags)) + return POLLIN | POLLRDNORM; + + /* + * First check RET, then INFLIGHT. No barriers necessary to + * ensure execution ordering because of the conditional + * instructions creating control dependencies. + */ + + if (test_and_set_bit(PVCALLS_FLAG_POLL_INFLIGHT, + (void *)&map->passive.flags)) { + poll_wait(file, &bedata->inflight_req, wait); + return 0; + } + + spin_lock(&bedata->socket_lock); + ret = get_request(bedata, &req_id); + if (ret < 0) { + spin_unlock(&bedata->socket_lock); + return ret; + } + req = RING_GET_REQUEST(&bedata->ring, req_id); + req->req_id = req_id; + req->cmd = PVCALLS_POLL; + req->u.poll.id = (uint64_t) map; + + bedata->ring.req_prod_pvt++; + RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&bedata->ring, notify); + spin_unlock(&bedata->socket_lock); + if (notify) + notify_remote_via_irq(bedata->irq); + + poll_wait(file, &bedata->inflight_req, wait); + return 0; +} + +static unsigned int pvcalls_front_poll_active(struct file *file, + struct pvcalls_bedata *bedata, + struct sock_mapping *map, + poll_table *wait) +{ + unsigned int mask = 0; + int32_t in_error, out_error; + struct pvcalls_data_intf *intf = map->active.ring; + + out_error = intf->out_error; + in_error = intf->in_error; + + poll_wait(file, &map->active.inflight_conn_req, wait); + if (pvcalls_front_write_todo(map)) + mask |= POLLOUT | POLLWRNORM; + if (pvcalls_front_read_todo(map)) + mask |= POLLIN | POLLRDNORM; + if (in_error != 0 || out_error != 0) + mask |= POLLERR; + + return mask; +} + +unsigned int pvcalls_front_poll(struct file *file, struct socket *sock, + poll_table *wait) +{ + struct pvcalls_bedata *bedata; + struct sock_mapping *map; + int ret; + + pvcalls_enter(); + if (!pvcalls_front_dev) { + pvcalls_exit(); + return POLLNVAL; + } + bedata = dev_get_drvdata(&pvcalls_front_dev->dev); + + map = (struct sock_mapping *) sock->sk->sk_send_head; + if (!map) { + pvcalls_exit(); + return POLLNVAL; + } + if (map->active_socket) + ret = pvcalls_front_poll_active(file, bedata, map, wait); + else + ret = pvcalls_front_poll_passive(file, bedata, map, wait); + pvcalls_exit(); + return ret; +} + static const struct xenbus_device_id pvcalls_front_ids[] = { { "pvcalls" }, { "" } diff --git a/drivers/xen/pvcalls-front.h b/drivers/xen/pvcalls-front.h index de24041..25e05b8 100644 --- a/drivers/xen/pvcalls-front.h +++ b/drivers/xen/pvcalls-front.h @@ -20,5 +20,8 @@ int pvcalls_front_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); +unsigned int pvcalls_front_poll(struct file *file, + struct socket *sock, + poll_table *wait); #endif -- 1.9.1 _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org https://lists.xen.org/xen-devel
next prev parent reply other threads:[~2017-10-26 19:12 UTC|newest] Thread overview: 53+ messages / expand[flat|nested] mbox.gz Atom feed top 2017-10-26 19:11 [PATCH v7 00/13] introduce the Xen PV Calls frontend Stefano Stabellini 2017-10-26 19:11 ` [PATCH v7 01/13] xen/pvcalls: introduce the pvcalls xenbus frontend Stefano Stabellini 2017-10-26 19:11 ` Stefano Stabellini 2017-10-26 19:11 ` [PATCH v7 02/13] xen/pvcalls: implement frontend disconnect Stefano Stabellini 2017-10-26 19:11 ` Stefano Stabellini 2017-10-26 19:42 ` Boris Ostrovsky 2017-10-26 19:42 ` Boris Ostrovsky 2017-10-26 19:11 ` [PATCH v7 03/13] xen/pvcalls: connect to the backend Stefano Stabellini 2017-10-26 19:11 ` Stefano Stabellini 2017-10-26 19:11 ` [PATCH v7 04/13] xen/pvcalls: implement socket command and handle events Stefano Stabellini 2017-10-26 19:11 ` Stefano Stabellini 2017-10-26 19:11 ` [PATCH v7 05/13] xen/pvcalls: implement connect command Stefano Stabellini 2017-10-26 19:11 ` Stefano Stabellini 2017-10-26 19:11 ` [PATCH v7 06/13] xen/pvcalls: implement bind command Stefano Stabellini 2017-10-26 19:11 ` Stefano Stabellini 2017-10-26 19:11 ` [PATCH v7 07/13] xen/pvcalls: implement listen command Stefano Stabellini 2017-10-26 19:11 ` Stefano Stabellini 2017-10-26 19:11 ` [PATCH v7 08/13] xen/pvcalls: implement accept command Stefano Stabellini 2017-10-26 19:11 ` Stefano Stabellini 2017-10-26 19:11 ` [PATCH v7 09/13] xen/pvcalls: implement sendmsg Stefano Stabellini 2017-10-26 19:11 ` Stefano Stabellini 2017-10-26 19:11 ` [PATCH v7 10/13] xen/pvcalls: implement recvmsg Stefano Stabellini 2017-10-26 19:11 ` Stefano Stabellini 2017-10-26 19:11 ` Stefano Stabellini [this message] 2017-10-26 19:11 ` [PATCH v7 11/13] xen/pvcalls: implement poll command Stefano Stabellini 2017-10-26 19:11 ` [PATCH v7 12/13] xen/pvcalls: implement release command Stefano Stabellini 2017-10-26 19:11 ` Stefano Stabellini 2017-10-26 19:49 ` Boris Ostrovsky 2017-10-26 19:49 ` Boris Ostrovsky 2017-10-26 19:11 ` [PATCH v7 13/13] xen: introduce a Kconfig option to enable the pvcalls frontend Stefano Stabellini 2017-10-26 19:52 ` Boris Ostrovsky 2017-10-26 19:52 ` Boris Ostrovsky 2017-10-26 20:16 ` Stefano Stabellini 2017-10-26 20:16 ` Stefano Stabellini 2017-10-26 20:45 ` Boris Ostrovsky 2017-10-26 20:49 ` Stefano Stabellini 2017-10-26 20:49 ` Stefano Stabellini 2017-10-26 20:56 ` Boris Ostrovsky 2017-10-26 20:56 ` Boris Ostrovsky 2017-10-30 15:22 ` Boris Ostrovsky 2017-10-30 19:48 ` Stefano Stabellini 2017-10-30 19:48 ` Stefano Stabellini 2017-10-30 20:00 ` Boris Ostrovsky 2017-10-30 20:00 ` Boris Ostrovsky 2017-10-30 21:42 ` Stefano Stabellini 2017-10-30 21:42 ` Stefano Stabellini 2017-10-30 22:02 ` Boris Ostrovsky 2017-10-30 22:14 ` Stefano Stabellini 2017-10-30 22:14 ` Stefano Stabellini 2017-10-30 22:02 ` Boris Ostrovsky 2017-10-30 15:22 ` Boris Ostrovsky 2017-10-26 20:45 ` Boris Ostrovsky 2017-10-26 19:11 ` Stefano Stabellini
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=1509045112-9807-11-git-send-email-sstabellini@kernel.org \ --to=sstabellini@kernel.org \ --cc=boris.ostrovsky@oracle.com \ --cc=jgross@suse.com \ --cc=linux-kernel@vger.kernel.org \ --cc=stefano@aporeto.com \ --cc=xen-devel@lists.xen.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.