| Message ID | 1501017730-12797-3-git-send-email-sstabellini@kernel.org (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On 7/25/2017 5:22 PM, Stefano Stabellini wrote: > Send a PVCALLS_SOCKET command to the backend, use the masked > req_prod_pvt as req_id. This way, req_id is guaranteed to be between 0 > and PVCALLS_NR_REQ_PER_RING. We already have a slot in the rsp array > ready for the response, and there cannot be two outstanding responses > with the same req_id. > > Wait for the response by waiting on the inflight_req waitqueue and > check for the req_id field in rsp[req_id]. Use atomic accesses to > read the field. Once a response is received, clear the corresponding rsp > slot by setting req_id to PVCALLS_INVALID_ID. Note that > PVCALLS_INVALID_ID is invalid only from the frontend point of view. It > is not part of the PVCalls protocol. > > pvcalls_front_event_handler is in charge of copying responses from the > ring to the appropriate rsp slot. It is done by copying the body of the > response first, then by copying req_id atomically. After the copies, > wake up anybody waiting on waitqueue. > > pvcallss_lock protects accesses to the ring. > > Signed-off-by: Stefano Stabellini <stefano@aporeto.com> > CC: boris.ostrovsky@oracle.com > CC: jgross@suse.com > --- > drivers/xen/pvcalls-front.c | 94 +++++++++++++++++++++++++++++++++++++++++++++ > drivers/xen/pvcalls-front.h | 8 ++++ > 2 files changed, 102 insertions(+) > create mode 100644 drivers/xen/pvcalls-front.h > > diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c > index 5e0b265..d1dbcf1 100644 > --- a/drivers/xen/pvcalls-front.c > +++ b/drivers/xen/pvcalls-front.c > @@ -20,6 +20,8 @@ > #include <xen/xenbus.h> > #include <xen/interface/io/pvcalls.h> > > +#include "pvcalls-front.h" > + > #define PVCALLS_INVALID_ID (UINT_MAX) > #define RING_ORDER XENBUS_MAX_RING_GRANT_ORDER > #define PVCALLS_NR_REQ_PER_RING __CONST_RING_SIZE(xen_pvcalls, XEN_PAGE_SIZE) > @@ -40,9 +42,101 @@ struct pvcalls_bedata { > > static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id) > { > + struct xenbus_device *dev = dev_id; > + struct pvcalls_bedata *bedata; > + struct xen_pvcalls_response *rsp; > + uint8_t *src, *dst; > + int req_id = 0, more = 0, done = 0; > + > + if (dev == NULL) > + return IRQ_HANDLED; > + > + bedata = dev_get_drvdata(&dev->dev); > + if (bedata == NULL) > + return IRQ_HANDLED; > + > +again: > + while (RING_HAS_UNCONSUMED_RESPONSES(&bedata->ring)) { > + rsp = RING_GET_RESPONSE(&bedata->ring, bedata->ring.rsp_cons); > + > + req_id = rsp->req_id; > + src = (uint8_t *)&bedata->rsp[req_id]; > + src += sizeof(rsp->req_id); > + dst = (uint8_t *)rsp; > + dst += sizeof(rsp->req_id); These two lines can be combined (both src and dst) > + 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(); > + WRITE_ONCE(bedata->rsp[req_id].req_id, rsp->req_id); > + > + done = 1; > + bedata->ring.rsp_cons++; > + } > + > + RING_FINAL_CHECK_FOR_RESPONSES(&bedata->ring, more); > + if (more) > + goto again; > + if (done) > + wake_up(&bedata->inflight_req); > return IRQ_HANDLED; > } > > +int pvcalls_front_socket(struct socket *sock) > +{ > + struct pvcalls_bedata *bedata; > + struct xen_pvcalls_request *req; > + int notify, req_id, ret; > + > + if (!pvcalls_front_dev) > + return -EACCES; > + /* > + * PVCalls only supports domain AF_INET, > + * type SOCK_STREAM and protocol 0 sockets for now. > + * > + * Check socket type here, AF_INET and protocol checks are done > + * by the caller. > + */ > + if (sock->type != SOCK_STREAM) > + return -ENOTSUPP; > + > + bedata = dev_get_drvdata(&pvcalls_front_dev->dev); > + > + spin_lock(&bedata->pvcallss_lock); > + req_id = bedata->ring.req_prod_pvt & (RING_SIZE(&bedata->ring) - 1); > + if (RING_FULL(&bedata->ring) || > + READ_ONCE(bedata->rsp[req_id].req_id) != PVCALLS_INVALID_ID) { > + spin_unlock(&bedata->pvcallss_lock); > + return -EAGAIN; > + } > + req = RING_GET_REQUEST(&bedata->ring, req_id); > + req->req_id = req_id; > + req->cmd = PVCALLS_SOCKET; > + req->u.socket.id = (uint64_t) sock; > + req->u.socket.domain = AF_INET; > + req->u.socket.type = SOCK_STREAM; > + req->u.socket.protocol = 0; > + > + bedata->ring.req_prod_pvt++; > + RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&bedata->ring, notify); > + spin_unlock(&bedata->pvcallss_lock); > + if (notify) > + notify_remote_via_irq(bedata->irq); > + > + if (wait_event_interruptible(bedata->inflight_req, > + READ_ONCE(bedata->rsp[req_id].req_id) == req_id) != 0) "!= 0" can be dropped -boris > + return -EINTR; > + > + ret = bedata->rsp[req_id].ret; > + /* read ret, then set this rsp slot to be reused */ > + smp_mb(); > + WRITE_ONCE(bedata->rsp[req_id].req_id, PVCALLS_INVALID_ID); > + > + 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 > new file mode 100644 > index 0000000..b7dabed > --- /dev/null > +++ b/drivers/xen/pvcalls-front.h > @@ -0,0 +1,8 @@ > +#ifndef __PVCALLS_FRONT_H__ > +#define __PVCALLS_FRONT_H__ > + > +#include <linux/net.h> > + > +int pvcalls_front_socket(struct socket *sock); > + > +#endif
On Wed, 26 Jul 2017, Boris Ostrovsky wrote: > On 7/25/2017 5:22 PM, Stefano Stabellini wrote: > > Send a PVCALLS_SOCKET command to the backend, use the masked > > req_prod_pvt as req_id. This way, req_id is guaranteed to be between 0 > > and PVCALLS_NR_REQ_PER_RING. We already have a slot in the rsp array > > ready for the response, and there cannot be two outstanding responses > > with the same req_id. > > > > Wait for the response by waiting on the inflight_req waitqueue and > > check for the req_id field in rsp[req_id]. Use atomic accesses to > > read the field. Once a response is received, clear the corresponding rsp > > slot by setting req_id to PVCALLS_INVALID_ID. Note that > > PVCALLS_INVALID_ID is invalid only from the frontend point of view. It > > is not part of the PVCalls protocol. > > > > pvcalls_front_event_handler is in charge of copying responses from the > > ring to the appropriate rsp slot. It is done by copying the body of the > > response first, then by copying req_id atomically. After the copies, > > wake up anybody waiting on waitqueue. > > > > pvcallss_lock protects accesses to the ring. > > > > Signed-off-by: Stefano Stabellini <stefano@aporeto.com> > > CC: boris.ostrovsky@oracle.com > > CC: jgross@suse.com > > --- > > drivers/xen/pvcalls-front.c | 94 > > +++++++++++++++++++++++++++++++++++++++++++++ > > drivers/xen/pvcalls-front.h | 8 ++++ > > 2 files changed, 102 insertions(+) > > create mode 100644 drivers/xen/pvcalls-front.h > > > > diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c > > index 5e0b265..d1dbcf1 100644 > > --- a/drivers/xen/pvcalls-front.c > > +++ b/drivers/xen/pvcalls-front.c > > @@ -20,6 +20,8 @@ > > #include <xen/xenbus.h> > > #include <xen/interface/io/pvcalls.h> > > +#include "pvcalls-front.h" > > + > > #define PVCALLS_INVALID_ID (UINT_MAX) > > #define RING_ORDER XENBUS_MAX_RING_GRANT_ORDER > > #define PVCALLS_NR_REQ_PER_RING __CONST_RING_SIZE(xen_pvcalls, > > XEN_PAGE_SIZE) > > @@ -40,9 +42,101 @@ struct pvcalls_bedata { > > static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id) > > { > > + struct xenbus_device *dev = dev_id; > > + struct pvcalls_bedata *bedata; > > + struct xen_pvcalls_response *rsp; > > + uint8_t *src, *dst; > > + int req_id = 0, more = 0, done = 0; > > + > > + if (dev == NULL) > > + return IRQ_HANDLED; > > + > > + bedata = dev_get_drvdata(&dev->dev); > > + if (bedata == NULL) > > + return IRQ_HANDLED; > > + > > +again: > > + while (RING_HAS_UNCONSUMED_RESPONSES(&bedata->ring)) { > > + rsp = RING_GET_RESPONSE(&bedata->ring, bedata->ring.rsp_cons); > > + > > + req_id = rsp->req_id; > > + src = (uint8_t *)&bedata->rsp[req_id]; > > + src += sizeof(rsp->req_id); > > + dst = (uint8_t *)rsp; > > + dst += sizeof(rsp->req_id); > > These two lines can be combined (both src and dst) I'll do that > > + 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(); > > + WRITE_ONCE(bedata->rsp[req_id].req_id, rsp->req_id); > > + > > + done = 1; > > + bedata->ring.rsp_cons++; > > + } > > + > > + RING_FINAL_CHECK_FOR_RESPONSES(&bedata->ring, more); > > + if (more) > > + goto again; > > + if (done) > > + wake_up(&bedata->inflight_req); > > return IRQ_HANDLED; > > } > > +int pvcalls_front_socket(struct socket *sock) > > +{ > > + struct pvcalls_bedata *bedata; > > + struct xen_pvcalls_request *req; > > + int notify, req_id, ret; > > + > > + if (!pvcalls_front_dev) > > + return -EACCES; > > + /* > > + * PVCalls only supports domain AF_INET, > > + * type SOCK_STREAM and protocol 0 sockets for now. > > + * > > + * Check socket type here, AF_INET and protocol checks are done > > + * by the caller. > > + */ > > + if (sock->type != SOCK_STREAM) > > + return -ENOTSUPP; > > + > > + bedata = dev_get_drvdata(&pvcalls_front_dev->dev); > > + > > + spin_lock(&bedata->pvcallss_lock); > > + req_id = bedata->ring.req_prod_pvt & (RING_SIZE(&bedata->ring) - 1); > > + if (RING_FULL(&bedata->ring) || > > + READ_ONCE(bedata->rsp[req_id].req_id) != PVCALLS_INVALID_ID) { > > + spin_unlock(&bedata->pvcallss_lock); > > + return -EAGAIN; > > + } > > + req = RING_GET_REQUEST(&bedata->ring, req_id); > > + req->req_id = req_id; > > + req->cmd = PVCALLS_SOCKET; > > + req->u.socket.id = (uint64_t) sock; > > + req->u.socket.domain = AF_INET; > > + req->u.socket.type = SOCK_STREAM; > > + req->u.socket.protocol = 0; > > + > > + bedata->ring.req_prod_pvt++; > > + RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&bedata->ring, notify); > > + spin_unlock(&bedata->pvcallss_lock); > > + if (notify) > > + notify_remote_via_irq(bedata->irq); > > + > > + if (wait_event_interruptible(bedata->inflight_req, > > + READ_ONCE(bedata->rsp[req_id].req_id) == req_id) != 0) > > "!= 0" can be dropped OK > > + return -EINTR; > > + > > + ret = bedata->rsp[req_id].ret; > > + /* read ret, then set this rsp slot to be reused */ > > + smp_mb(); > > + WRITE_ONCE(bedata->rsp[req_id].req_id, PVCALLS_INVALID_ID); > > + > > + 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 > > new file mode 100644 > > index 0000000..b7dabed > > --- /dev/null > > +++ b/drivers/xen/pvcalls-front.h > > @@ -0,0 +1,8 @@ > > +#ifndef __PVCALLS_FRONT_H__ > > +#define __PVCALLS_FRONT_H__ > > + > > +#include <linux/net.h> > > + > > +int pvcalls_front_socket(struct socket *sock); > > + > > +#endif >
diff --git a/drivers/xen/pvcalls-front.c b/drivers/xen/pvcalls-front.c index 5e0b265..d1dbcf1 100644 --- a/drivers/xen/pvcalls-front.c +++ b/drivers/xen/pvcalls-front.c @@ -20,6 +20,8 @@ #include <xen/xenbus.h> #include <xen/interface/io/pvcalls.h> +#include "pvcalls-front.h" + #define PVCALLS_INVALID_ID (UINT_MAX) #define RING_ORDER XENBUS_MAX_RING_GRANT_ORDER #define PVCALLS_NR_REQ_PER_RING __CONST_RING_SIZE(xen_pvcalls, XEN_PAGE_SIZE) @@ -40,9 +42,101 @@ struct pvcalls_bedata { static irqreturn_t pvcalls_front_event_handler(int irq, void *dev_id) { + struct xenbus_device *dev = dev_id; + struct pvcalls_bedata *bedata; + struct xen_pvcalls_response *rsp; + uint8_t *src, *dst; + int req_id = 0, more = 0, done = 0; + + if (dev == NULL) + return IRQ_HANDLED; + + bedata = dev_get_drvdata(&dev->dev); + if (bedata == NULL) + return IRQ_HANDLED; + +again: + while (RING_HAS_UNCONSUMED_RESPONSES(&bedata->ring)) { + rsp = RING_GET_RESPONSE(&bedata->ring, bedata->ring.rsp_cons); + + req_id = rsp->req_id; + src = (uint8_t *)&bedata->rsp[req_id]; + src += sizeof(rsp->req_id); + dst = (uint8_t *)rsp; + dst += 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(); + WRITE_ONCE(bedata->rsp[req_id].req_id, rsp->req_id); + + done = 1; + bedata->ring.rsp_cons++; + } + + RING_FINAL_CHECK_FOR_RESPONSES(&bedata->ring, more); + if (more) + goto again; + if (done) + wake_up(&bedata->inflight_req); return IRQ_HANDLED; } +int pvcalls_front_socket(struct socket *sock) +{ + struct pvcalls_bedata *bedata; + struct xen_pvcalls_request *req; + int notify, req_id, ret; + + if (!pvcalls_front_dev) + return -EACCES; + /* + * PVCalls only supports domain AF_INET, + * type SOCK_STREAM and protocol 0 sockets for now. + * + * Check socket type here, AF_INET and protocol checks are done + * by the caller. + */ + if (sock->type != SOCK_STREAM) + return -ENOTSUPP; + + bedata = dev_get_drvdata(&pvcalls_front_dev->dev); + + spin_lock(&bedata->pvcallss_lock); + req_id = bedata->ring.req_prod_pvt & (RING_SIZE(&bedata->ring) - 1); + if (RING_FULL(&bedata->ring) || + READ_ONCE(bedata->rsp[req_id].req_id) != PVCALLS_INVALID_ID) { + spin_unlock(&bedata->pvcallss_lock); + return -EAGAIN; + } + req = RING_GET_REQUEST(&bedata->ring, req_id); + req->req_id = req_id; + req->cmd = PVCALLS_SOCKET; + req->u.socket.id = (uint64_t) sock; + req->u.socket.domain = AF_INET; + req->u.socket.type = SOCK_STREAM; + req->u.socket.protocol = 0; + + bedata->ring.req_prod_pvt++; + RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(&bedata->ring, notify); + spin_unlock(&bedata->pvcallss_lock); + if (notify) + notify_remote_via_irq(bedata->irq); + + if (wait_event_interruptible(bedata->inflight_req, + READ_ONCE(bedata->rsp[req_id].req_id) == req_id) != 0) + return -EINTR; + + ret = bedata->rsp[req_id].ret; + /* read ret, then set this rsp slot to be reused */ + smp_mb(); + WRITE_ONCE(bedata->rsp[req_id].req_id, PVCALLS_INVALID_ID); + + 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 new file mode 100644 index 0000000..b7dabed --- /dev/null +++ b/drivers/xen/pvcalls-front.h @@ -0,0 +1,8 @@ +#ifndef __PVCALLS_FRONT_H__ +#define __PVCALLS_FRONT_H__ + +#include <linux/net.h> + +int pvcalls_front_socket(struct socket *sock); + +#endif
Send a PVCALLS_SOCKET command to the backend, use the masked req_prod_pvt as req_id. This way, req_id is guaranteed to be between 0 and PVCALLS_NR_REQ_PER_RING. We already have a slot in the rsp array ready for the response, and there cannot be two outstanding responses with the same req_id. Wait for the response by waiting on the inflight_req waitqueue and check for the req_id field in rsp[req_id]. Use atomic accesses to read the field. Once a response is received, clear the corresponding rsp slot by setting req_id to PVCALLS_INVALID_ID. Note that PVCALLS_INVALID_ID is invalid only from the frontend point of view. It is not part of the PVCalls protocol. pvcalls_front_event_handler is in charge of copying responses from the ring to the appropriate rsp slot. It is done by copying the body of the response first, then by copying req_id atomically. After the copies, wake up anybody waiting on waitqueue. pvcallss_lock protects accesses to the ring. Signed-off-by: Stefano Stabellini <stefano@aporeto.com> CC: boris.ostrovsky@oracle.com CC: jgross@suse.com --- drivers/xen/pvcalls-front.c | 94 +++++++++++++++++++++++++++++++++++++++++++++ drivers/xen/pvcalls-front.h | 8 ++++ 2 files changed, 102 insertions(+) create mode 100644 drivers/xen/pvcalls-front.h