From 9c53a1792a5e6c708897d0cb17f2a4509e499a52 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 31 Oct 2016 14:58:40 +0100 Subject: xen: introduce xenbus_read_unsigned() There are multiple instances of code reading an optional unsigned parameter from Xenstore via xenbus_scanf(). Instead of repeating the same code over and over add a service function doing the job. Signed-off-by: Juergen Gross Reviewed-by: David Vrabel --- drivers/xen/xenbus/xenbus_xs.c | 15 +++++++++++++++ include/xen/xenbus.h | 4 ++++ 2 files changed, 19 insertions(+) diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index 22f7cd711c57..99dfdfae42c6 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -559,6 +559,21 @@ int xenbus_scanf(struct xenbus_transaction t, } EXPORT_SYMBOL_GPL(xenbus_scanf); +/* Read an (optional) unsigned value. */ +unsigned int xenbus_read_unsigned(const char *dir, const char *node, + unsigned int default_val) +{ + unsigned int val; + int ret; + + ret = xenbus_scanf(XBT_NIL, dir, node, "%u", &val); + if (ret <= 0) + val = default_val; + + return val; +} +EXPORT_SYMBOL_GPL(xenbus_read_unsigned); + /* Single printf and write: returns -errno or 0. */ int xenbus_printf(struct xenbus_transaction t, const char *dir, const char *node, const char *fmt, ...) diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h index 32b944b7cebd..271ba62503c7 100644 --- a/include/xen/xenbus.h +++ b/include/xen/xenbus.h @@ -151,6 +151,10 @@ __scanf(4, 5) int xenbus_scanf(struct xenbus_transaction t, const char *dir, const char *node, const char *fmt, ...); +/* Read an (optional) unsigned value. */ +unsigned int xenbus_read_unsigned(const char *dir, const char *node, + unsigned int default_val); + /* Single printf and write: returns -errno or 0. */ __printf(4, 5) int xenbus_printf(struct xenbus_transaction t, -- cgit v1.2.3 From 8235777b2068e3280b6fa1413f1940ade31f0adf Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 31 Oct 2016 14:58:40 +0100 Subject: xen: make use of xenbus_read_unsigned() in xen-blkback Use xenbus_read_unsigned() instead of xenbus_scanf() when possible. This requires to change the type of one read from int to unsigned, but this case has been wrong before: negative values are not allowed for the modified case. Cc: konrad.wilk@oracle.com Cc: roger.pau@citrix.com Signed-off-by: Juergen Gross Acked-by: David Vrabel --- drivers/block/xen-blkback/xenbus.c | 36 ++++++++++++++---------------------- 1 file changed, 14 insertions(+), 22 deletions(-) diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index 3cc6d1d86f1e..415e79b69d34 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -533,13 +533,11 @@ static void xen_blkbk_discard(struct xenbus_transaction xbt, struct backend_info struct xenbus_device *dev = be->dev; struct xen_blkif *blkif = be->blkif; int err; - int state = 0, discard_enable; + int state = 0; struct block_device *bdev = be->blkif->vbd.bdev; struct request_queue *q = bdev_get_queue(bdev); - err = xenbus_scanf(XBT_NIL, dev->nodename, "discard-enable", "%d", - &discard_enable); - if (err == 1 && !discard_enable) + if (!xenbus_read_unsigned(dev->nodename, "discard-enable", 1)) return; if (blk_queue_discard(q)) { @@ -1039,30 +1037,24 @@ static int connect_ring(struct backend_info *be) xenbus_dev_fatal(dev, err, "unknown fe protocol %s", protocol); return -ENOSYS; } - err = xenbus_scanf(XBT_NIL, dev->otherend, - "feature-persistent", "%u", &pers_grants); - if (err <= 0) - pers_grants = 0; - + pers_grants = xenbus_read_unsigned(dev->otherend, "feature-persistent", + 0); be->blkif->vbd.feature_gnt_persistent = pers_grants; be->blkif->vbd.overflow_max_grants = 0; /* * Read the number of hardware queues from frontend. */ - err = xenbus_scanf(XBT_NIL, dev->otherend, "multi-queue-num-queues", - "%u", &requested_num_queues); - if (err < 0) { - requested_num_queues = 1; - } else { - if (requested_num_queues > xenblk_max_queues - || requested_num_queues == 0) { - /* Buggy or malicious guest. */ - xenbus_dev_fatal(dev, err, - "guest requested %u queues, exceeding the maximum of %u.", - requested_num_queues, xenblk_max_queues); - return -ENOSYS; - } + requested_num_queues = xenbus_read_unsigned(dev->otherend, + "multi-queue-num-queues", + 1); + if (requested_num_queues > xenblk_max_queues + || requested_num_queues == 0) { + /* Buggy or malicious guest. */ + xenbus_dev_fatal(dev, err, + "guest requested %u queues, exceeding the maximum of %u.", + requested_num_queues, xenblk_max_queues); + return -ENOSYS; } be->blkif->nr_rings = requested_num_queues; if (xen_blkif_alloc_rings(be->blkif)) -- cgit v1.2.3 From f27dc1ac56865c2cc43d0ec3110a2b4a95b04e1d Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 31 Oct 2016 14:58:40 +0100 Subject: xen: make use of xenbus_read_unsigned() in xen-blkfront Use xenbus_read_unsigned() instead of xenbus_scanf() when possible. This requires to change the type of some reads from int to unsigned, but these cases have been wrong before: negative values are not allowed for the modified cases. Cc: konrad.wilk@oracle.com Cc: roger.pau@citrix.com Signed-off-by: Juergen Gross Acked-by: David Vrabel --- drivers/block/xen-blkfront.c | 81 ++++++++++++++------------------------------ 1 file changed, 26 insertions(+), 55 deletions(-) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 9908597c5209..2ee9646d8a5f 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -1758,17 +1758,13 @@ static int talk_to_blkback(struct xenbus_device *dev, const char *message = NULL; struct xenbus_transaction xbt; int err; - unsigned int i, max_page_order = 0; - unsigned int ring_page_order = 0; + unsigned int i, max_page_order; + unsigned int ring_page_order; - err = xenbus_scanf(XBT_NIL, info->xbdev->otherend, - "max-ring-page-order", "%u", &max_page_order); - if (err != 1) - info->nr_ring_pages = 1; - else { - ring_page_order = min(xen_blkif_max_ring_order, max_page_order); - info->nr_ring_pages = 1 << ring_page_order; - } + max_page_order = xenbus_read_unsigned(info->xbdev->otherend, + "max-ring-page-order", 0); + ring_page_order = min(xen_blkif_max_ring_order, max_page_order); + info->nr_ring_pages = 1 << ring_page_order; for (i = 0; i < info->nr_rings; i++) { struct blkfront_ring_info *rinfo = &info->rinfo[i]; @@ -1877,18 +1873,14 @@ again: static int negotiate_mq(struct blkfront_info *info) { - unsigned int backend_max_queues = 0; - int err; + unsigned int backend_max_queues; unsigned int i; BUG_ON(info->nr_rings); /* Check if backend supports multiple queues. */ - err = xenbus_scanf(XBT_NIL, info->xbdev->otherend, - "multi-queue-max-queues", "%u", &backend_max_queues); - if (err < 0) - backend_max_queues = 1; - + backend_max_queues = xenbus_read_unsigned(info->xbdev->otherend, + "multi-queue-max-queues", 1); info->nr_rings = min(backend_max_queues, xen_blkif_max_queues); /* We need at least one ring. */ if (!info->nr_rings) @@ -2195,7 +2187,6 @@ static void blkfront_setup_discard(struct blkfront_info *info) int err; unsigned int discard_granularity; unsigned int discard_alignment; - unsigned int discard_secure; info->feature_discard = 1; err = xenbus_gather(XBT_NIL, info->xbdev->otherend, @@ -2206,10 +2197,9 @@ static void blkfront_setup_discard(struct blkfront_info *info) info->discard_granularity = discard_granularity; info->discard_alignment = discard_alignment; } - err = xenbus_scanf(XBT_NIL, info->xbdev->otherend, - "discard-secure", "%u", &discard_secure); - if (err > 0) - info->feature_secdiscard = !!discard_secure; + info->feature_secdiscard = + !!xenbus_read_unsigned(info->xbdev->otherend, "discard-secure", + 0); } static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo) @@ -2301,16 +2291,11 @@ out_of_memory: */ static void blkfront_gather_backend_features(struct blkfront_info *info) { - int err; - int barrier, flush, discard, persistent; unsigned int indirect_segments; info->feature_flush = 0; info->feature_fua = 0; - err = xenbus_scanf(XBT_NIL, info->xbdev->otherend, - "feature-barrier", "%d", &barrier); - /* * If there's no "feature-barrier" defined, then it means * we're dealing with a very old backend which writes @@ -2318,7 +2303,7 @@ static void blkfront_gather_backend_features(struct blkfront_info *info) * * If there are barriers, then we use flush. */ - if (err > 0 && barrier) { + if (xenbus_read_unsigned(info->xbdev->otherend, "feature-barrier", 0)) { info->feature_flush = 1; info->feature_fua = 1; } @@ -2327,35 +2312,23 @@ static void blkfront_gather_backend_features(struct blkfront_info *info) * And if there is "feature-flush-cache" use that above * barriers. */ - err = xenbus_scanf(XBT_NIL, info->xbdev->otherend, - "feature-flush-cache", "%d", &flush); - - if (err > 0 && flush) { + if (xenbus_read_unsigned(info->xbdev->otherend, "feature-flush-cache", + 0)) { info->feature_flush = 1; info->feature_fua = 0; } - err = xenbus_scanf(XBT_NIL, info->xbdev->otherend, - "feature-discard", "%d", &discard); - - if (err > 0 && discard) + if (xenbus_read_unsigned(info->xbdev->otherend, "feature-discard", 0)) blkfront_setup_discard(info); - err = xenbus_scanf(XBT_NIL, info->xbdev->otherend, - "feature-persistent", "%d", &persistent); - if (err <= 0) - info->feature_persistent = 0; - else - info->feature_persistent = persistent; + info->feature_persistent = + xenbus_read_unsigned(info->xbdev->otherend, + "feature-persistent", 0); - err = xenbus_scanf(XBT_NIL, info->xbdev->otherend, - "feature-max-indirect-segments", "%u", - &indirect_segments); - if (err <= 0) - info->max_indirect_segments = 0; - else - info->max_indirect_segments = min(indirect_segments, - xen_blkif_max_segments); + indirect_segments = xenbus_read_unsigned(info->xbdev->otherend, + "feature-max-indirect-segments", 0); + info->max_indirect_segments = min(indirect_segments, + xen_blkif_max_segments); } /* @@ -2420,11 +2393,9 @@ static void blkfront_connect(struct blkfront_info *info) * provide this. Assume physical sector size to be the same as * sector_size in that case. */ - err = xenbus_scanf(XBT_NIL, info->xbdev->otherend, - "physical-sector-size", "%u", &physical_sector_size); - if (err != 1) - physical_sector_size = sector_size; - + physical_sector_size = xenbus_read_unsigned(info->xbdev->otherend, + "physical-sector-size", + sector_size); blkfront_gather_backend_features(info); for (i = 0; i < info->nr_rings; i++) { err = blkfront_setup_indirect(&info->rinfo[i]); -- cgit v1.2.3 From 0240933469ea4cc1aa1c32867349c4aa718fe264 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 31 Oct 2016 14:58:40 +0100 Subject: xen: make use of xenbus_read_unsigned() in xen-tpmfront Use xenbus_read_unsigned() instead of xenbus_scanf() when possible. This requires to change the type of one read from int to unsigned, but this case has been wrong before: negative values are not allowed for the modified case. Cc: peterhuewe@gmx.de Cc: tpmdd@selhorst.net Cc: jarkko.sakkinen@linux.intel.com Cc: jgunthorpe@obsidianresearch.com Cc: tpmdd-devel@lists.sourceforge.net Signed-off-by: Juergen Gross Reviewed-by: Jarkko Sakkinen Acked-by: David Vrabel --- drivers/char/tpm/xen-tpmfront.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/drivers/char/tpm/xen-tpmfront.c b/drivers/char/tpm/xen-tpmfront.c index 62028f483bba..50072cc4fe5c 100644 --- a/drivers/char/tpm/xen-tpmfront.c +++ b/drivers/char/tpm/xen-tpmfront.c @@ -337,18 +337,14 @@ static int tpmfront_resume(struct xenbus_device *dev) static void backend_changed(struct xenbus_device *dev, enum xenbus_state backend_state) { - int val; - switch (backend_state) { case XenbusStateInitialised: case XenbusStateConnected: if (dev->state == XenbusStateConnected) break; - if (xenbus_scanf(XBT_NIL, dev->otherend, - "feature-protocol-v2", "%d", &val) < 0) - val = 0; - if (!val) { + if (!xenbus_read_unsigned(dev->otherend, "feature-protocol-v2", + 0)) { xenbus_dev_fatal(dev, -EINVAL, "vTPM protocol 2 required"); return; -- cgit v1.2.3 From 81362c6f159dcb59fadd60927aa00497d715ca80 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 31 Oct 2016 14:58:40 +0100 Subject: xen: make use of xenbus_read_unsigned() in xen-kbdfront Use xenbus_read_unsigned() instead of xenbus_scanf() when possible. This requires to change the type of the reads from int to unsigned, but these cases have been wrong before: negative values are not allowed for the modified cases. Cc: dmitry.torokhov@gmail.com Cc: linux-input@vger.kernel.org Signed-off-by: Juergen Gross Acked-by: David Vrabel --- drivers/input/misc/xen-kbdfront.c | 13 +++++-------- 1 file changed, 5 insertions(+), 8 deletions(-) diff --git a/drivers/input/misc/xen-kbdfront.c b/drivers/input/misc/xen-kbdfront.c index 227fbd2dbb71..3900875dec10 100644 --- a/drivers/input/misc/xen-kbdfront.c +++ b/drivers/input/misc/xen-kbdfront.c @@ -108,7 +108,8 @@ static irqreturn_t input_handler(int rq, void *dev_id) static int xenkbd_probe(struct xenbus_device *dev, const struct xenbus_device_id *id) { - int ret, i, abs; + int ret, i; + unsigned int abs; struct xenkbd_info *info; struct input_dev *kbd, *ptr; @@ -127,8 +128,7 @@ static int xenkbd_probe(struct xenbus_device *dev, if (!info->page) goto error_nomem; - if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-abs-pointer", "%d", &abs) < 0) - abs = 0; + abs = xenbus_read_unsigned(dev->otherend, "feature-abs-pointer", 0); if (abs) { ret = xenbus_write(XBT_NIL, dev->nodename, "request-abs-pointer", "1"); @@ -322,11 +322,8 @@ static void xenkbd_backend_changed(struct xenbus_device *dev, case XenbusStateInitWait: InitWait: - ret = xenbus_scanf(XBT_NIL, info->xbdev->otherend, - "feature-abs-pointer", "%d", &val); - if (ret < 0) - val = 0; - if (val) { + if (xenbus_read_unsigned(info->xbdev->otherend, + "feature-abs-pointer", 0)) { ret = xenbus_write(XBT_NIL, info->xbdev->nodename, "request-abs-pointer", "1"); if (ret) -- cgit v1.2.3 From f95842e7a9f235ef3b7d6d4b70fee2244149f1e7 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 31 Oct 2016 14:58:41 +0100 Subject: xen: make use of xenbus_read_unsigned() in xen-netback Use xenbus_read_unsigned() instead of xenbus_scanf() when possible. This requires to change the type of some reads from int to unsigned, but these cases have been wrong before: negative values are not allowed for the modified cases. Cc: wei.liu2@citrix.com Cc: paul.durrant@citrix.com Cc: netdev@vger.kernel.org Signed-off-by: Juergen Gross Reviewed-by: Paul Durrant Acked-by: David Vrabel --- drivers/net/xen-netback/xenbus.c | 50 +++++++++++----------------------------- 1 file changed, 14 insertions(+), 36 deletions(-) diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index 8674e188b697..7356e00fac54 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -785,12 +785,9 @@ static void xen_mcast_ctrl_changed(struct xenbus_watch *watch, struct xenvif *vif = container_of(watch, struct xenvif, mcast_ctrl_watch); struct xenbus_device *dev = xenvif_to_xenbus_device(vif); - int val; - if (xenbus_scanf(XBT_NIL, dev->otherend, - "request-multicast-control", "%d", &val) < 0) - val = 0; - vif->multicast_control = !!val; + vif->multicast_control = !!xenbus_read_unsigned(dev->otherend, + "request-multicast-control", 0); } static int xen_register_mcast_ctrl_watch(struct xenbus_device *dev, @@ -934,12 +931,9 @@ static void connect(struct backend_info *be) /* Check whether the frontend requested multiple queues * and read the number requested. */ - err = xenbus_scanf(XBT_NIL, dev->otherend, - "multi-queue-num-queues", - "%u", &requested_num_queues); - if (err < 0) { - requested_num_queues = 1; /* Fall back to single queue */ - } else if (requested_num_queues > xenvif_max_queues) { + requested_num_queues = xenbus_read_unsigned(dev->otherend, + "multi-queue-num-queues", 1); + if (requested_num_queues > xenvif_max_queues) { /* buggy or malicious guest */ xenbus_dev_fatal(dev, err, "guest requested %u queues, exceeding the maximum of %u.", @@ -1134,7 +1128,7 @@ static int read_xenbus_vif_flags(struct backend_info *be) struct xenvif *vif = be->vif; struct xenbus_device *dev = be->dev; unsigned int rx_copy; - int err, val; + int err; err = xenbus_scanf(XBT_NIL, dev->otherend, "request-rx-copy", "%u", &rx_copy); @@ -1150,10 +1144,7 @@ static int read_xenbus_vif_flags(struct backend_info *be) if (!rx_copy) return -EOPNOTSUPP; - if (xenbus_scanf(XBT_NIL, dev->otherend, - "feature-rx-notify", "%d", &val) < 0) - val = 0; - if (!val) { + if (!xenbus_read_unsigned(dev->otherend, "feature-rx-notify", 0)) { /* - Reduce drain timeout to poll more frequently for * Rx requests. * - Disable Rx stall detection. @@ -1162,34 +1153,21 @@ static int read_xenbus_vif_flags(struct backend_info *be) be->vif->stall_timeout = 0; } - if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-sg", - "%d", &val) < 0) - val = 0; - vif->can_sg = !!val; + vif->can_sg = !!xenbus_read_unsigned(dev->otherend, "feature-sg", 0); vif->gso_mask = 0; - if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv4", - "%d", &val) < 0) - val = 0; - if (val) + if (xenbus_read_unsigned(dev->otherend, "feature-gso-tcpv4", 0)) vif->gso_mask |= GSO_BIT(TCPV4); - if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-gso-tcpv6", - "%d", &val) < 0) - val = 0; - if (val) + if (xenbus_read_unsigned(dev->otherend, "feature-gso-tcpv6", 0)) vif->gso_mask |= GSO_BIT(TCPV6); - if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-no-csum-offload", - "%d", &val) < 0) - val = 0; - vif->ip_csum = !val; + vif->ip_csum = !xenbus_read_unsigned(dev->otherend, + "feature-no-csum-offload", 0); - if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-ipv6-csum-offload", - "%d", &val) < 0) - val = 0; - vif->ipv6_csum = !!val; + vif->ipv6_csum = !!xenbus_read_unsigned(dev->otherend, + "feature-ipv6-csum-offload", 0); return 0; } -- cgit v1.2.3 From 2890ea5c13321d26732c4520649681965480ee1c Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 31 Oct 2016 14:58:41 +0100 Subject: xen: make use of xenbus_read_unsigned() in xen-netfront Use xenbus_read_unsigned() instead of xenbus_scanf() when possible. This requires to change the type of some reads from int to unsigned, but these cases have been wrong before: negative values are not allowed for the modified cases. Cc: netdev@vger.kernel.org Signed-off-by: Juergen Gross Acked-by: David Vrabel --- drivers/net/xen-netfront.c | 67 +++++++++++++--------------------------------- 1 file changed, 18 insertions(+), 49 deletions(-) diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index e17879dd5d5a..95d664e3d09c 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -1169,43 +1169,23 @@ static netdev_features_t xennet_fix_features(struct net_device *dev, netdev_features_t features) { struct netfront_info *np = netdev_priv(dev); - int val; - if (features & NETIF_F_SG) { - if (xenbus_scanf(XBT_NIL, np->xbdev->otherend, "feature-sg", - "%d", &val) < 0) - val = 0; + if (features & NETIF_F_SG && + !xenbus_read_unsigned(np->xbdev->otherend, "feature-sg", 0)) + features &= ~NETIF_F_SG; - if (!val) - features &= ~NETIF_F_SG; - } - - if (features & NETIF_F_IPV6_CSUM) { - if (xenbus_scanf(XBT_NIL, np->xbdev->otherend, - "feature-ipv6-csum-offload", "%d", &val) < 0) - val = 0; - - if (!val) - features &= ~NETIF_F_IPV6_CSUM; - } - - if (features & NETIF_F_TSO) { - if (xenbus_scanf(XBT_NIL, np->xbdev->otherend, - "feature-gso-tcpv4", "%d", &val) < 0) - val = 0; + if (features & NETIF_F_IPV6_CSUM && + !xenbus_read_unsigned(np->xbdev->otherend, + "feature-ipv6-csum-offload", 0)) + features &= ~NETIF_F_IPV6_CSUM; - if (!val) - features &= ~NETIF_F_TSO; - } + if (features & NETIF_F_TSO && + !xenbus_read_unsigned(np->xbdev->otherend, "feature-gso-tcpv4", 0)) + features &= ~NETIF_F_TSO; - if (features & NETIF_F_TSO6) { - if (xenbus_scanf(XBT_NIL, np->xbdev->otherend, - "feature-gso-tcpv6", "%d", &val) < 0) - val = 0; - - if (!val) - features &= ~NETIF_F_TSO6; - } + if (features & NETIF_F_TSO6 && + !xenbus_read_unsigned(np->xbdev->otherend, "feature-gso-tcpv6", 0)) + features &= ~NETIF_F_TSO6; return features; } @@ -1821,18 +1801,13 @@ static int talk_to_netback(struct xenbus_device *dev, info->netdev->irq = 0; /* Check if backend supports multiple queues */ - err = xenbus_scanf(XBT_NIL, info->xbdev->otherend, - "multi-queue-max-queues", "%u", &max_queues); - if (err < 0) - max_queues = 1; + max_queues = xenbus_read_unsigned(info->xbdev->otherend, + "multi-queue-max-queues", 1); num_queues = min(max_queues, xennet_max_queues); /* Check feature-split-event-channels */ - err = xenbus_scanf(XBT_NIL, info->xbdev->otherend, - "feature-split-event-channels", "%u", - &feature_split_evtchn); - if (err < 0) - feature_split_evtchn = 0; + feature_split_evtchn = xenbus_read_unsigned(info->xbdev->otherend, + "feature-split-event-channels", 0); /* Read mac addr. */ err = xen_net_read_mac(dev, info->netdev->dev_addr); @@ -1966,16 +1941,10 @@ static int xennet_connect(struct net_device *dev) struct netfront_info *np = netdev_priv(dev); unsigned int num_queues = 0; int err; - unsigned int feature_rx_copy; unsigned int j = 0; struct netfront_queue *queue = NULL; - err = xenbus_scanf(XBT_NIL, np->xbdev->otherend, - "feature-rx-copy", "%u", &feature_rx_copy); - if (err != 1) - feature_rx_copy = 0; - - if (!feature_rx_copy) { + if (!xenbus_read_unsigned(np->xbdev->otherend, "feature-rx-copy", 0)) { dev_info(&dev->dev, "backend does not support copying receive path\n"); return -ENODEV; -- cgit v1.2.3 From 58faf07b76817782ea20c392639569ea613cd439 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 31 Oct 2016 14:58:41 +0100 Subject: xen: make use of xenbus_read_unsigned() in xen-pcifront Use xenbus_read_unsigned() instead of xenbus_scanf() when possible. This requires to change the type of the read from int to unsigned, but this case has been wrong before: negative values are not allowed for the modified case. Cc: bhelgaas@google.com Cc: linux-pci@vger.kernel.org Signed-off-by: Juergen Gross Acked-by: Bjorn Helgaas Acked-by: David Vrabel --- drivers/pci/xen-pcifront.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c index d6ff5e82377d..8fc2e9532575 100644 --- a/drivers/pci/xen-pcifront.c +++ b/drivers/pci/xen-pcifront.c @@ -1038,10 +1038,8 @@ static int pcifront_detach_devices(struct pcifront_device *pdev) err = -ENOMEM; goto out; } - err = xenbus_scanf(XBT_NIL, pdev->xdev->otherend, str, "%d", - &state); - if (err != 1) - state = XenbusStateUnknown; + state = xenbus_read_unsigned(pdev->xdev->otherend, str, + XenbusStateUnknown); if (state != XenbusStateClosing) continue; -- cgit v1.2.3 From 1080b38db49f7e3075aa9cd5a87f1587282cc0b0 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 31 Oct 2016 14:58:41 +0100 Subject: xen: make use of xenbus_read_unsigned() in xen-scsifront Use xenbus_read_unsigned() instead of xenbus_scanf() when possible. Signed-off-by: Juergen Gross Acked-by: David Vrabel --- drivers/scsi/xen-scsifront.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/scsi/xen-scsifront.c b/drivers/scsi/xen-scsifront.c index 9dc8687bf048..7e817c64f385 100644 --- a/drivers/scsi/xen-scsifront.c +++ b/drivers/scsi/xen-scsifront.c @@ -1060,13 +1060,9 @@ static void scsifront_read_backend_params(struct xenbus_device *dev, struct vscsifrnt_info *info) { unsigned int sg_grant, nr_segs; - int ret; struct Scsi_Host *host = info->host; - ret = xenbus_scanf(XBT_NIL, dev->otherend, "feature-sg-grant", "%u", - &sg_grant); - if (ret != 1) - sg_grant = 0; + sg_grant = xenbus_read_unsigned(dev->otherend, "feature-sg-grant", 0); nr_segs = min_t(unsigned int, sg_grant, SG_ALL); nr_segs = max_t(unsigned int, nr_segs, VSCSIIF_SG_TABLESIZE); nr_segs = min_t(unsigned int, nr_segs, -- cgit v1.2.3 From eaf46e181ec3cc3b6eafdbe8e30fb5a03ebbde68 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 31 Oct 2016 14:58:41 +0100 Subject: xen: make use of xenbus_read_unsigned() in xen-fbfront Use xenbus_read_unsigned() instead of xenbus_scanf() when possible. This requires to change the type of the reads from int to unsigned, but these cases have been wrong before: negative values are not allowed for the modified cases. Cc: tomi.valkeinen@ti.com Cc: linux-fbdev@vger.kernel.org Signed-off-by: Juergen Gross Acked-by: David Vrabel --- drivers/video/fbdev/xen-fbfront.c | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-) diff --git a/drivers/video/fbdev/xen-fbfront.c b/drivers/video/fbdev/xen-fbfront.c index 0567d517eed3..d0115a7af0a9 100644 --- a/drivers/video/fbdev/xen-fbfront.c +++ b/drivers/video/fbdev/xen-fbfront.c @@ -633,7 +633,6 @@ static void xenfb_backend_changed(struct xenbus_device *dev, enum xenbus_state backend_state) { struct xenfb_info *info = dev_get_drvdata(&dev->dev); - int val; switch (backend_state) { case XenbusStateInitialising: @@ -657,16 +656,12 @@ InitWait: if (dev->state != XenbusStateConnected) goto InitWait; /* no InitWait seen yet, fudge it */ - if (xenbus_scanf(XBT_NIL, info->xbdev->otherend, - "request-update", "%d", &val) < 0) - val = 0; - if (val) + if (xenbus_read_unsigned(info->xbdev->otherend, + "request-update", 0)) info->update_wanted = 1; - if (xenbus_scanf(XBT_NIL, dev->otherend, - "feature-resize", "%d", &val) < 0) - val = 0; - info->feature_resize = val; + info->feature_resize = xenbus_read_unsigned(dev->otherend, + "feature-resize", 0); break; case XenbusStateClosed: -- cgit v1.2.3 From 4e81f1caa7ff77f7fd31bd31f84b1a0dcfc8184e Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 31 Oct 2016 14:58:41 +0100 Subject: xen: make use of xenbus_read_unsigned() in xen-pciback Use xenbus_read_unsigned() instead of xenbus_scanf() when possible. This requires to change the type of the read from int to unsigned, but this case has been wrong before: negative values are not allowed for the modified case. Signed-off-by: Juergen Gross Acked-by: David Vrabel --- drivers/xen/xen-pciback/xenbus.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/drivers/xen/xen-pciback/xenbus.c b/drivers/xen/xen-pciback/xenbus.c index 5ce878c51d03..3f0aee0a068b 100644 --- a/drivers/xen/xen-pciback/xenbus.c +++ b/drivers/xen/xen-pciback/xenbus.c @@ -362,7 +362,7 @@ static int xen_pcibk_reconfigure(struct xen_pcibk_device *pdev) int err = 0; int num_devs; int domain, bus, slot, func; - int substate; + unsigned int substate; int i, len; char state_str[64]; char dev_str[64]; @@ -395,10 +395,8 @@ static int xen_pcibk_reconfigure(struct xen_pcibk_device *pdev) "configuration"); goto out; } - err = xenbus_scanf(XBT_NIL, pdev->xdev->nodename, state_str, - "%d", &substate); - if (err != 1) - substate = XenbusStateUnknown; + substate = xenbus_read_unsigned(pdev->xdev->nodename, state_str, + XenbusStateUnknown); switch (substate) { case XenbusStateInitialising: -- cgit v1.2.3 From 999c9af9e3a2535d9ad41182e93eb128e587eb84 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 31 Oct 2016 14:58:42 +0100 Subject: xen: make use of xenbus_read_unsigned() in xenbus Use xenbus_read_unsigned() instead of xenbus_scanf() when possible. This requires to change the type of the reads from int to unsigned, but these cases have been wrong before: negative values are not allowed for the modified cases. Signed-off-by: Juergen Gross Acked-by: David Vrabel --- drivers/xen/xenbus/xenbus_probe_backend.c | 8 +------- drivers/xen/xenbus/xenbus_xs.c | 7 +++---- 2 files changed, 4 insertions(+), 11 deletions(-) diff --git a/drivers/xen/xenbus/xenbus_probe_backend.c b/drivers/xen/xenbus/xenbus_probe_backend.c index 04f7f85a5edf..37929df829a3 100644 --- a/drivers/xen/xenbus/xenbus_probe_backend.c +++ b/drivers/xen/xenbus/xenbus_probe_backend.c @@ -224,13 +224,7 @@ static int read_frontend_details(struct xenbus_device *xendev) int xenbus_dev_is_online(struct xenbus_device *dev) { - int rc, val; - - rc = xenbus_scanf(XBT_NIL, dev->nodename, "online", "%d", &val); - if (rc != 1) - val = 0; /* no online node present */ - - return val; + return !!xenbus_read_unsigned(dev->nodename, "online", 0); } EXPORT_SYMBOL_GPL(xenbus_dev_is_online); diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index 99dfdfae42c6..6afb993c5809 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -687,7 +687,7 @@ static bool xen_strict_xenbus_quirk(void) } static void xs_reset_watches(void) { - int err, supported = 0; + int err; if (!xen_hvm_domain() || xen_initial_domain()) return; @@ -695,9 +695,8 @@ static void xs_reset_watches(void) if (xen_strict_xenbus_quirk()) return; - err = xenbus_scanf(XBT_NIL, "control", - "platform-feature-xs_reset_watches", "%d", &supported); - if (err != 1 || !supported) + if (!xenbus_read_unsigned("control", + "platform-feature-xs_reset_watches", 0)) return; err = xs_error(xs_single(XBT_NIL, XS_RESET_WATCHES, "", NULL)); -- cgit v1.2.3 From 0f06ac3b6616b9793b3fb5c398d94044a0423492 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Thu, 10 Nov 2016 09:55:42 +0100 Subject: xen-netback: fix error handling output The connect function prints an unintialized error code after an earlier initialization was removed: drivers/net/xen-netback/xenbus.c: In function 'connect': drivers/net/xen-netback/xenbus.c:938:3: error: 'err' may be used uninitialized in this function [-Werror=maybe-uninitialized] This prints it as -EINVAL instead, which seems to be the most appropriate error code. Before the patch that caused the warning, this would print a positive number returned by vsscanf() instead, which is also wrong. We probably don't need a backport though, as fixing the warning here should be sufficient. Fixes: f95842e7a9f2 ("xen: make use of xenbus_read_unsigned() in xen-netback") Fixes: 8d3d53b3e433 ("xen-netback: Add support for multiple queues") Signed-off-by: Arnd Bergmann Reviewed-by: Paul Durrant Signed-off-by: Juergen Gross --- drivers/net/xen-netback/xenbus.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index 7356e00fac54..bfed79877b8a 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -935,7 +935,7 @@ static void connect(struct backend_info *be) "multi-queue-num-queues", 1); if (requested_num_queues > xenvif_max_queues) { /* buggy or malicious guest */ - xenbus_dev_fatal(dev, err, + xenbus_dev_fatal(dev, -EINVAL, "guest requested %u queues, exceeding the maximum of %u.", requested_num_queues, xenvif_max_queues); return; -- cgit v1.2.3 From 1ea55e8078a4fede5c21ea195d4e96091240a6ad Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Mon, 14 Nov 2016 20:52:26 +0800 Subject: xen-platform: use builtin_pci_driver Use builtin_pci_driver() helper to simplify the code. Signed-off-by: Geliang Tang Reviewed-by: Juergen Gross Signed-off-by: Juergen Gross --- drivers/xen/platform-pci.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/drivers/xen/platform-pci.c b/drivers/xen/platform-pci.c index b59c9455aae1..112ce422dc22 100644 --- a/drivers/xen/platform-pci.c +++ b/drivers/xen/platform-pci.c @@ -125,8 +125,4 @@ static struct pci_driver platform_driver = { .id_table = platform_pci_tbl, }; -static int __init platform_pci_init(void) -{ - return pci_register_driver(&platform_driver); -} -device_initcall(platform_pci_init); +builtin_pci_driver(platform_driver); -- cgit v1.2.3 From f97df70b1c879f764f88b25b0e67b03a5213968a Mon Sep 17 00:00:00 2001 From: Seth Forshee Date: Mon, 14 Nov 2016 11:12:56 +0000 Subject: xenfs: Use proc_create_mount_point() to create /proc/xen Mounting proc in user namespace containers fails if the xenbus filesystem is mounted on /proc/xen because this directory fails the "permanently empty" test. proc_create_mount_point() exists specifically to create such mountpoints in proc but is currently proc-internal. Export this interface to modules, then use it in xenbus when creating /proc/xen. Signed-off-by: Seth Forshee Signed-off-by: David Vrabel Signed-off-by: Juergen Gross --- drivers/xen/xenbus/xenbus_probe.c | 2 +- fs/proc/generic.c | 1 + fs/proc/internal.h | 1 - include/linux/proc_fs.h | 2 ++ 4 files changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index 33a31cfef55d..b5c1dec4a7c2 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -826,7 +826,7 @@ static int __init xenbus_init(void) * Create xenfs mountpoint in /proc for compatibility with * utilities that expect to find "xenbus" under "/proc/xen". */ - proc_mkdir("xen", NULL); + proc_create_mount_point("xen"); #endif out_error: diff --git a/fs/proc/generic.c b/fs/proc/generic.c index 5f2dc2032c79..7eb3cefcf2a3 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -479,6 +479,7 @@ struct proc_dir_entry *proc_create_mount_point(const char *name) } return ent; } +EXPORT_SYMBOL(proc_create_mount_point); struct proc_dir_entry *proc_create_data(const char *name, umode_t mode, struct proc_dir_entry *parent, diff --git a/fs/proc/internal.h b/fs/proc/internal.h index 5378441ec1b7..7de679572111 100644 --- a/fs/proc/internal.h +++ b/fs/proc/internal.h @@ -195,7 +195,6 @@ static inline bool is_empty_pde(const struct proc_dir_entry *pde) { return S_ISDIR(pde->mode) && !pde->proc_iops; } -struct proc_dir_entry *proc_create_mount_point(const char *name); /* * inode.c diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index b97bf2ef996e..8bd2f726436a 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -21,6 +21,7 @@ extern struct proc_dir_entry *proc_mkdir_data(const char *, umode_t, struct proc_dir_entry *, void *); extern struct proc_dir_entry *proc_mkdir_mode(const char *, umode_t, struct proc_dir_entry *); +struct proc_dir_entry *proc_create_mount_point(const char *name); extern struct proc_dir_entry *proc_create_data(const char *, umode_t, struct proc_dir_entry *, @@ -56,6 +57,7 @@ static inline struct proc_dir_entry *proc_symlink(const char *name, struct proc_dir_entry *parent,const char *dest) { return NULL;} static inline struct proc_dir_entry *proc_mkdir(const char *name, struct proc_dir_entry *parent) {return NULL;} +static inline struct proc_dir_entry *proc_create_mount_point(const char *name) { return NULL; } static inline struct proc_dir_entry *proc_mkdir_data(const char *name, umode_t mode, struct proc_dir_entry *parent, void *data) { return NULL; } static inline struct proc_dir_entry *proc_mkdir_mode(const char *name, -- cgit v1.2.3 From 30b6b22f4e6ebe285ad22657fb3818e03c394bb1 Mon Sep 17 00:00:00 2001 From: David Vrabel Date: Thu, 17 Nov 2016 12:12:22 +0000 Subject: MAINTAINERS: update XEN HYPERVISOR INTERFACE I am no longer in a postion to be a maintainer of the Xen subsystem. Signed-off-by: David Vrabel Acked-by: Juergen Gross Acked-by: Boris Ostrovsky Signed-off-by: Juergen Gross --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 411e3b87b8c2..2dcccf202086 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13195,7 +13195,6 @@ F: drivers/media/tuners/tuner-xc2028.* XEN HYPERVISOR INTERFACE M: Boris Ostrovsky -M: David Vrabel M: Juergen Gross L: xen-devel@lists.xenproject.org (moderated for non-subscribers) T: git git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip.git -- cgit v1.2.3 From 1eb08545c0a3a2249ad53e393383cc06163d0d16 Mon Sep 17 00:00:00 2001 From: Quentin Lambert Date: Sat, 19 Nov 2016 19:22:56 +0100 Subject: xen-scsifront: Add a missing call to kfree Most error branches following the call to kmalloc contain a call to kfree. This patch add these calls where they are missing. This issue was found with Hector. Signed-off-by: Quentin Lambert Reviewed-by: Juergen Gross Signed-off-by: Juergen Gross --- drivers/scsi/xen-scsifront.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/scsi/xen-scsifront.c b/drivers/scsi/xen-scsifront.c index 7e817c64f385..c01316c6c7b1 100644 --- a/drivers/scsi/xen-scsifront.c +++ b/drivers/scsi/xen-scsifront.c @@ -627,6 +627,7 @@ static int scsifront_action_handler(struct scsi_cmnd *sc, uint8_t act) if (scsifront_enter(info)) { spin_unlock_irq(host->host_lock); + kfree(shadow); return FAILED; } -- cgit v1.2.3 From 30faaafdfa0c754c91bac60f216c9f34a2bfdf7e Mon Sep 17 00:00:00 2001 From: Boris Ostrovsky Date: Mon, 21 Nov 2016 09:56:06 -0500 Subject: xen/gntdev: Use VM_MIXEDMAP instead of VM_IO to avoid NUMA balancing Commit 9c17d96500f7 ("xen/gntdev: Grant maps should not be subject to NUMA balancing") set VM_IO flag to prevent grant maps from being subjected to NUMA balancing. It was discovered recently that this flag causes get_user_pages() to always fail with -EFAULT. check_vma_flags __get_user_pages __get_user_pages_locked __get_user_pages_unlocked get_user_pages_fast iov_iter_get_pages dio_refill_pages do_direct_IO do_blockdev_direct_IO do_blockdev_direct_IO ext4_direct_IO_read generic_file_read_iter aio_run_iocb (which can happen if guest's vdisk has direct-io-safe option). To avoid this let's use VM_MIXEDMAP flag instead --- it prevents NUMA balancing just as VM_IO does and has no effect on check_vma_flags(). Cc: stable@vger.kernel.org Reported-by: Olaf Hering Suggested-by: Hugh Dickins Signed-off-by: Boris Ostrovsky Acked-by: Hugh Dickins Tested-by: Olaf Hering Signed-off-by: Juergen Gross --- drivers/xen/gntdev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c index bb952121ea94..2ef2b61b69df 100644 --- a/drivers/xen/gntdev.c +++ b/drivers/xen/gntdev.c @@ -1007,7 +1007,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma) vma->vm_ops = &gntdev_vmops; - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP | VM_IO; + vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP | VM_MIXEDMAP; if (use_ptemod) vma->vm_flags |= VM_DONTCOPY; -- cgit v1.2.3 From b36585a0a3c169612f3105139464a2da1d3ecc03 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Wed, 23 Nov 2016 13:38:45 +0100 Subject: xen/events: use xen_vcpu_id mapping for EVTCHNOP_status EVTCHNOP_status hypercall returns Xen's idea of vcpu id so we need to compare it against xen_vcpu_id mapping, not the Linux cpu id. Suggested-by: Radim Krcmar Signed-off-by: Vitaly Kuznetsov Reviewed-by: Boris Ostrovsky Signed-off-by: Juergen Gross --- drivers/xen/events/events_base.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index 9ecfcdcdd6d6..137bd0e799e7 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -948,7 +948,7 @@ static int find_virq(unsigned int virq, unsigned int cpu) continue; if (status.status != EVTCHNSTAT_virq) continue; - if (status.u.virq == virq && status.vcpu == cpu) { + if (status.u.virq == virq && status.vcpu == xen_vcpu_nr(cpu)) { rc = port; break; } -- cgit v1.2.3 From 2fbadc3002c5f172d20aa2e7e48920c5f14ed11f Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 2 Dec 2016 14:19:35 +0000 Subject: arm/arm64: xen: Move shared architecture headers to include/xen/arm ARM and arm64 Xen ports share a number of headers, leading to packaging issues when these headers needs to be exported, as it breaks the reasonable requirement that an architecture port has self-contained headers. Fix the issue by moving the 5 header files to include/xen/arm, and keep local placeholders to include the relevant files. Signed-off-by: Marc Zyngier Reviewed-by: Stefano Stabellini --- arch/arm/include/asm/xen/hypercall.h | 88 +-------------------- arch/arm/include/asm/xen/hypervisor.h | 40 +--------- arch/arm/include/asm/xen/interface.h | 86 +------------------- arch/arm/include/asm/xen/page-coherent.h | 99 +---------------------- arch/arm/include/asm/xen/page.h | 123 +---------------------------- arch/arm64/include/asm/xen/hypercall.h | 2 +- arch/arm64/include/asm/xen/hypervisor.h | 2 +- arch/arm64/include/asm/xen/interface.h | 2 +- arch/arm64/include/asm/xen/page-coherent.h | 2 +- arch/arm64/include/asm/xen/page.h | 2 +- include/xen/arm/hypercall.h | 87 ++++++++++++++++++++ include/xen/arm/hypervisor.h | 39 +++++++++ include/xen/arm/interface.h | 85 ++++++++++++++++++++ include/xen/arm/page-coherent.h | 98 +++++++++++++++++++++++ include/xen/arm/page.h | 122 ++++++++++++++++++++++++++++ 15 files changed, 441 insertions(+), 436 deletions(-) create mode 100644 include/xen/arm/hypercall.h create mode 100644 include/xen/arm/hypervisor.h create mode 100644 include/xen/arm/interface.h create mode 100644 include/xen/arm/page-coherent.h create mode 100644 include/xen/arm/page.h diff --git a/arch/arm/include/asm/xen/hypercall.h b/arch/arm/include/asm/xen/hypercall.h index 9d874db13c0e..3522cbaed316 100644 --- a/arch/arm/include/asm/xen/hypercall.h +++ b/arch/arm/include/asm/xen/hypercall.h @@ -1,87 +1 @@ -/****************************************************************************** - * hypercall.h - * - * Linux-specific hypervisor handling. - * - * Stefano Stabellini , Citrix, 2012 - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version 2 - * as published by the Free Software Foundation; or, when distributed - * separately from the Linux kernel or incorporated into other - * software packages, subject to the following license: - * - * Permission is hereby granted, free of charge, to any person obtaining a copy - * of this source file (the "Software"), to deal in the Software without - * restriction, including without limitation the rights to use, copy, modify, - * merge, publish, distribute, sublicense, and/or sell copies of the Software, - * and to permit persons to whom the Software is furnished to do so, subject to - * the following conditions: - * - * The above copyright notice and this permission notice shall be included in - * all copies or substantial portions of the Software. - * - * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR - * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, - * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE - * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER - * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING - * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS - * IN THE SOFTWARE. - */ - -#ifndef _ASM_ARM_XEN_HYPERCALL_H -#define _ASM_ARM_XEN_HYPERCALL_H - -#include - -#include -#include -#include - -long privcmd_call(unsigned call, unsigned long a1, - unsigned long a2, unsigned long a3, - unsigned long a4, unsigned long a5); -int HYPERVISOR_xen_version(int cmd, void *arg); -int HYPERVISOR_console_io(int cmd, int count, char *str); -int HYPERVISOR_grant_table_op(unsigned int cmd, void *uop, unsigned int count); -int HYPERVISOR_sched_op(int cmd, void *arg); -int HYPERVISOR_event_channel_op(int cmd, void *arg); -unsigned long HYPERVISOR_hvm_op(int op, void *arg); -int HYPERVISOR_memory_op(unsigned int cmd, void *arg); -int HYPERVISOR_physdev_op(int cmd, void *arg); -int HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args); -int HYPERVISOR_tmem_op(void *arg); -int HYPERVISOR_vm_assist(unsigned int cmd, unsigned int type); -int HYPERVISOR_platform_op_raw(void *arg); -static inline int HYPERVISOR_platform_op(struct xen_platform_op *op) -{ - op->interface_version = XENPF_INTERFACE_VERSION; - return HYPERVISOR_platform_op_raw(op); -} -int HYPERVISOR_multicall(struct multicall_entry *calls, uint32_t nr); - -static inline int -HYPERVISOR_suspend(unsigned long start_info_mfn) -{ - struct sched_shutdown r = { .reason = SHUTDOWN_suspend }; - - /* start_info_mfn is unused on ARM */ - return HYPERVISOR_sched_op(SCHEDOP_shutdown, &r); -} - -static inline void -MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va, - unsigned int new_val, unsigned long flags) -{ - BUG(); -} - -static inline void -MULTI_mmu_update(struct multicall_entry *mcl, struct mmu_update *req, - int count, int *success_count, domid_t domid) -{ - BUG(); -} - -#endif /* _ASM_ARM_XEN_HYPERCALL_H */ +#include diff --git a/arch/arm/include/asm/xen/hypervisor.h b/arch/arm/include/asm/xen/hypervisor.h index 95251512e2c4..d6e7709d0688 100644 --- a/arch/arm/include/asm/xen/hypervisor.h +++ b/arch/arm/include/asm/xen/hypervisor.h @@ -1,39 +1 @@ -#ifndef _ASM_ARM_XEN_HYPERVISOR_H -#define _ASM_ARM_XEN_HYPERVISOR_H - -#include - -extern struct shared_info *HYPERVISOR_shared_info; -extern struct start_info *xen_start_info; - -/* Lazy mode for batching updates / context switch */ -enum paravirt_lazy_mode { - PARAVIRT_LAZY_NONE, - PARAVIRT_LAZY_MMU, - PARAVIRT_LAZY_CPU, -}; - -static inline enum paravirt_lazy_mode paravirt_get_lazy_mode(void) -{ - return PARAVIRT_LAZY_NONE; -} - -extern struct dma_map_ops *xen_dma_ops; - -#ifdef CONFIG_XEN -void __init xen_early_init(void); -#else -static inline void xen_early_init(void) { return; } -#endif - -#ifdef CONFIG_HOTPLUG_CPU -static inline void xen_arch_register_cpu(int num) -{ -} - -static inline void xen_arch_unregister_cpu(int num) -{ -} -#endif - -#endif /* _ASM_ARM_XEN_HYPERVISOR_H */ +#include diff --git a/arch/arm/include/asm/xen/interface.h b/arch/arm/include/asm/xen/interface.h index 75d596862892..88c0d75da190 100644 --- a/arch/arm/include/asm/xen/interface.h +++ b/arch/arm/include/asm/xen/interface.h @@ -1,85 +1 @@ -/****************************************************************************** - * Guest OS interface to ARM Xen. - * - * Stefano Stabellini , Citrix, 2012 - */ - -#ifndef _ASM_ARM_XEN_INTERFACE_H -#define _ASM_ARM_XEN_INTERFACE_H - -#include - -#define uint64_aligned_t uint64_t __attribute__((aligned(8))) - -#define __DEFINE_GUEST_HANDLE(name, type) \ - typedef struct { union { type *p; uint64_aligned_t q; }; } \ - __guest_handle_ ## name - -#define DEFINE_GUEST_HANDLE_STRUCT(name) \ - __DEFINE_GUEST_HANDLE(name, struct name) -#define DEFINE_GUEST_HANDLE(name) __DEFINE_GUEST_HANDLE(name, name) -#define GUEST_HANDLE(name) __guest_handle_ ## name - -#define set_xen_guest_handle(hnd, val) \ - do { \ - if (sizeof(hnd) == 8) \ - *(uint64_t *)&(hnd) = 0; \ - (hnd).p = val; \ - } while (0) - -#define __HYPERVISOR_platform_op_raw __HYPERVISOR_platform_op - -#ifndef __ASSEMBLY__ -/* Explicitly size integers that represent pfns in the interface with - * Xen so that we can have one ABI that works for 32 and 64 bit guests. - * Note that this means that the xen_pfn_t type may be capable of - * representing pfn's which the guest cannot represent in its own pfn - * type. However since pfn space is controlled by the guest this is - * fine since it simply wouldn't be able to create any sure pfns in - * the first place. - */ -typedef uint64_t xen_pfn_t; -#define PRI_xen_pfn "llx" -typedef uint64_t xen_ulong_t; -#define PRI_xen_ulong "llx" -typedef int64_t xen_long_t; -#define PRI_xen_long "llx" -/* Guest handles for primitive C types. */ -__DEFINE_GUEST_HANDLE(uchar, unsigned char); -__DEFINE_GUEST_HANDLE(uint, unsigned int); -DEFINE_GUEST_HANDLE(char); -DEFINE_GUEST_HANDLE(int); -DEFINE_GUEST_HANDLE(void); -DEFINE_GUEST_HANDLE(uint64_t); -DEFINE_GUEST_HANDLE(uint32_t); -DEFINE_GUEST_HANDLE(xen_pfn_t); -DEFINE_GUEST_HANDLE(xen_ulong_t); - -/* Maximum number of virtual CPUs in multi-processor guests. */ -#define MAX_VIRT_CPUS 1 - -struct arch_vcpu_info { }; -struct arch_shared_info { }; - -/* TODO: Move pvclock definitions some place arch independent */ -struct pvclock_vcpu_time_info { - u32 version; - u32 pad0; - u64 tsc_timestamp; - u64 system_time; - u32 tsc_to_system_mul; - s8 tsc_shift; - u8 flags; - u8 pad[2]; -} __attribute__((__packed__)); /* 32 bytes */ - -/* It is OK to have a 12 bytes struct with no padding because it is packed */ -struct pvclock_wall_clock { - u32 version; - u32 sec; - u32 nsec; - u32 sec_hi; -} __attribute__((__packed__)); -#endif - -#endif /* _ASM_ARM_XEN_INTERFACE_H */ +#include diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h index 95ce6ac3a971..b3ef061d8b74 100644 --- a/arch/arm/include/asm/xen/page-coherent.h +++ b/arch/arm/include/asm/xen/page-coherent.h @@ -1,98 +1 @@ -#ifndef _ASM_ARM_XEN_PAGE_COHERENT_H -#define _ASM_ARM_XEN_PAGE_COHERENT_H - -#include -#include - -void __xen_dma_map_page(struct device *hwdev, struct page *page, - dma_addr_t dev_addr, unsigned long offset, size_t size, - enum dma_data_direction dir, unsigned long attrs); -void __xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle, - size_t size, enum dma_data_direction dir, - unsigned long attrs); -void __xen_dma_sync_single_for_cpu(struct device *hwdev, - dma_addr_t handle, size_t size, enum dma_data_direction dir); - -void __xen_dma_sync_single_for_device(struct device *hwdev, - dma_addr_t handle, size_t size, enum dma_data_direction dir); - -static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size, - dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs) -{ - return __generic_dma_ops(hwdev)->alloc(hwdev, size, dma_handle, flags, attrs); -} - -static inline void xen_free_coherent_pages(struct device *hwdev, size_t size, - void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs) -{ - __generic_dma_ops(hwdev)->free(hwdev, size, cpu_addr, dma_handle, attrs); -} - -static inline void xen_dma_map_page(struct device *hwdev, struct page *page, - dma_addr_t dev_addr, unsigned long offset, size_t size, - enum dma_data_direction dir, unsigned long attrs) -{ - unsigned long page_pfn = page_to_xen_pfn(page); - unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr); - unsigned long compound_pages = - (1<map_page(hwdev, page, offset, size, dir, attrs); - else - __xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs); -} - -static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle, - size_t size, enum dma_data_direction dir, unsigned long attrs) -{ - unsigned long pfn = PFN_DOWN(handle); - /* - * Dom0 is mapped 1:1, while the Linux page can be spanned accross - * multiple Xen page, it's not possible to have a mix of local and - * foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a - * foreign mfn will always return false. If the page is local we can - * safely call the native dma_ops function, otherwise we call the xen - * specific function. - */ - if (pfn_valid(pfn)) { - if (__generic_dma_ops(hwdev)->unmap_page) - __generic_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs); - } else - __xen_dma_unmap_page(hwdev, handle, size, dir, attrs); -} - -static inline void xen_dma_sync_single_for_cpu(struct device *hwdev, - dma_addr_t handle, size_t size, enum dma_data_direction dir) -{ - unsigned long pfn = PFN_DOWN(handle); - if (pfn_valid(pfn)) { - if (__generic_dma_ops(hwdev)->sync_single_for_cpu) - __generic_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir); - } else - __xen_dma_sync_single_for_cpu(hwdev, handle, size, dir); -} - -static inline void xen_dma_sync_single_for_device(struct device *hwdev, - dma_addr_t handle, size_t size, enum dma_data_direction dir) -{ - unsigned long pfn = PFN_DOWN(handle); - if (pfn_valid(pfn)) { - if (__generic_dma_ops(hwdev)->sync_single_for_device) - __generic_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir); - } else - __xen_dma_sync_single_for_device(hwdev, handle, size, dir); -} - -#endif /* _ASM_ARM_XEN_PAGE_COHERENT_H */ +#include diff --git a/arch/arm/include/asm/xen/page.h b/arch/arm/include/asm/xen/page.h index 415dbc6e43fd..31bbc803cecb 100644 --- a/arch/arm/include/asm/xen/page.h +++ b/arch/arm/include/asm/xen/page.h @@ -1,122 +1 @@ -#ifndef _ASM_ARM_XEN_PAGE_H -#define _ASM_ARM_XEN_PAGE_H - -#include -#include - -#include -#include -#include - -#include -#include - -#define phys_to_machine_mapping_valid(pfn) (1) - -/* Xen machine address */ -typedef struct xmaddr { - phys_addr_t maddr; -} xmaddr_t; - -/* Xen pseudo-physical address */ -typedef struct xpaddr { - phys_addr_t paddr; -} xpaddr_t; - -#define XMADDR(x) ((xmaddr_t) { .maddr = (x) }) -#define XPADDR(x) ((xpaddr_t) { .paddr = (x) }) - -#define INVALID_P2M_ENTRY (~0UL) - -/* - * The pseudo-physical frame (pfn) used in all the helpers is always based - * on Xen page granularity (i.e 4KB). - * - * A Linux page may be split across multiple non-contiguous Xen page so we - * have to keep track with frame based on 4KB page granularity. - * - * PV drivers should never make a direct usage of those helpers (particularly - * pfn_to_gfn and gfn_to_pfn). - */ - -unsigned long __pfn_to_mfn(unsigned long pfn); -extern struct rb_root phys_to_mach; - -/* Pseudo-physical <-> Guest conversion */ -static inline unsigned long pfn_to_gfn(unsigned long pfn) -{ - return pfn; -} - -static inline unsigned long gfn_to_pfn(unsigned long gfn) -{ - return gfn; -} - -/* Pseudo-physical <-> BUS conversion */ -static inline unsigned long pfn_to_bfn(unsigned long pfn) -{ - unsigned long mfn; - - if (phys_to_mach.rb_node != NULL) { - mfn = __pfn_to_mfn(pfn); - if (mfn != INVALID_P2M_ENTRY) - return mfn; - } - - return pfn; -} - -static inline unsigned long bfn_to_pfn(unsigned long bfn) -{ - return bfn; -} - -#define bfn_to_local_pfn(bfn) bfn_to_pfn(bfn) - -/* VIRT <-> GUEST conversion */ -#define virt_to_gfn(v) (pfn_to_gfn(virt_to_phys(v) >> XEN_PAGE_SHIFT)) -#define gfn_to_virt(m) (__va(gfn_to_pfn(m) << XEN_PAGE_SHIFT)) - -/* Only used in PV code. But ARM guests are always HVM. */ -static inline xmaddr_t arbitrary_virt_to_machine(void *vaddr) -{ - BUG(); -} - -/* TODO: this shouldn't be here but it is because the frontend drivers - * are using it (its rolled in headers) even though we won't hit the code path. - * So for right now just punt with this. - */ -static inline pte_t *lookup_address(unsigned long address, unsigned int *level) -{ - BUG(); - return NULL; -} - -extern int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, - struct gnttab_map_grant_ref *kmap_ops, - struct page **pages, unsigned int count); - -extern int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, - struct gnttab_unmap_grant_ref *kunmap_ops, - struct page **pages, unsigned int count); - -bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn); -bool __set_phys_to_machine_multi(unsigned long pfn, unsigned long mfn, - unsigned long nr_pages); - -static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) -{ - return __set_phys_to_machine(pfn, mfn); -} - -#define xen_remap(cookie, size) ioremap_cache((cookie), (size)) -#define xen_unmap(cookie) iounmap((cookie)) - -bool xen_arch_need_swiotlb(struct device *dev, - phys_addr_t phys, - dma_addr_t dev_addr); -unsigned long xen_get_swiotlb_free_pages(unsigned int order); - -#endif /* _ASM_ARM_XEN_PAGE_H */ +#include diff --git a/arch/arm64/include/asm/xen/hypercall.h b/arch/arm64/include/asm/xen/hypercall.h index 74b0c423ff5b..3522cbaed316 100644 --- a/arch/arm64/include/asm/xen/hypercall.h +++ b/arch/arm64/include/asm/xen/hypercall.h @@ -1 +1 @@ -#include <../../arm/include/asm/xen/hypercall.h> +#include diff --git a/arch/arm64/include/asm/xen/hypervisor.h b/arch/arm64/include/asm/xen/hypervisor.h index f263da8e8769..d6e7709d0688 100644 --- a/arch/arm64/include/asm/xen/hypervisor.h +++ b/arch/arm64/include/asm/xen/hypervisor.h @@ -1 +1 @@ -#include <../../arm/include/asm/xen/hypervisor.h> +#include diff --git a/arch/arm64/include/asm/xen/interface.h b/arch/arm64/include/asm/xen/interface.h index 44457aebeed4..88c0d75da190 100644 --- a/arch/arm64/include/asm/xen/interface.h +++ b/arch/arm64/include/asm/xen/interface.h @@ -1 +1 @@ -#include <../../arm/include/asm/xen/interface.h> +#include diff --git a/arch/arm64/include/asm/xen/page-coherent.h b/arch/arm64/include/asm/xen/page-coherent.h index 2052102b4e02..b3ef061d8b74 100644 --- a/arch/arm64/include/asm/xen/page-coherent.h +++ b/arch/arm64/include/asm/xen/page-coherent.h @@ -1 +1 @@ -#include <../../arm/include/asm/xen/page-coherent.h> +#include diff --git a/arch/arm64/include/asm/xen/page.h b/arch/arm64/include/asm/xen/page.h index bed87ec36780..31bbc803cecb 100644 --- a/arch/arm64/include/asm/xen/page.h +++ b/arch/arm64/include/asm/xen/page.h @@ -1 +1 @@ -#include <../../arm/include/asm/xen/page.h> +#include diff --git a/include/xen/arm/hypercall.h b/include/xen/arm/hypercall.h new file mode 100644 index 000000000000..9d874db13c0e --- /dev/null +++ b/include/xen/arm/hypercall.h @@ -0,0 +1,87 @@ +/****************************************************************************** + * hypercall.h + * + * Linux-specific hypervisor handling. + * + * Stefano Stabellini , Citrix, 2012 + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation; or, when distributed + * separately from the Linux kernel or incorporated into other + * software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#ifndef _ASM_ARM_XEN_HYPERCALL_H +#define _ASM_ARM_XEN_HYPERCALL_H + +#include + +#include +#include +#include + +long privcmd_call(unsigned call, unsigned long a1, + unsigned long a2, unsigned long a3, + unsigned long a4, unsigned long a5); +int HYPERVISOR_xen_version(int cmd, void *arg); +int HYPERVISOR_console_io(int cmd, int count, char *str); +int HYPERVISOR_grant_table_op(unsigned int cmd, void *uop, unsigned int count); +int HYPERVISOR_sched_op(int cmd, void *arg); +int HYPERVISOR_event_channel_op(int cmd, void *arg); +unsigned long HYPERVISOR_hvm_op(int op, void *arg); +int HYPERVISOR_memory_op(unsigned int cmd, void *arg); +int HYPERVISOR_physdev_op(int cmd, void *arg); +int HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args); +int HYPERVISOR_tmem_op(void *arg); +int HYPERVISOR_vm_assist(unsigned int cmd, unsigned int type); +int HYPERVISOR_platform_op_raw(void *arg); +static inline int HYPERVISOR_platform_op(struct xen_platform_op *op) +{ + op->interface_version = XENPF_INTERFACE_VERSION; + return HYPERVISOR_platform_op_raw(op); +} +int HYPERVISOR_multicall(struct multicall_entry *calls, uint32_t nr); + +static inline int +HYPERVISOR_suspend(unsigned long start_info_mfn) +{ + struct sched_shutdown r = { .reason = SHUTDOWN_suspend }; + + /* start_info_mfn is unused on ARM */ + return HYPERVISOR_sched_op(SCHEDOP_shutdown, &r); +} + +static inline void +MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va, + unsigned int new_val, unsigned long flags) +{ + BUG(); +} + +static inline void +MULTI_mmu_update(struct multicall_entry *mcl, struct mmu_update *req, + int count, int *success_count, domid_t domid) +{ + BUG(); +} + +#endif /* _ASM_ARM_XEN_HYPERCALL_H */ diff --git a/include/xen/arm/hypervisor.h b/include/xen/arm/hypervisor.h new file mode 100644 index 000000000000..95251512e2c4 --- /dev/null +++ b/include/xen/arm/hypervisor.h @@ -0,0 +1,39 @@ +#ifndef _ASM_ARM_XEN_HYPERVISOR_H +#define _ASM_ARM_XEN_HYPERVISOR_H + +#include + +extern struct shared_info *HYPERVISOR_shared_info; +extern struct start_info *xen_start_info; + +/* Lazy mode for batching updates / context switch */ +enum paravirt_lazy_mode { + PARAVIRT_LAZY_NONE, + PARAVIRT_LAZY_MMU, + PARAVIRT_LAZY_CPU, +}; + +static inline enum paravirt_lazy_mode paravirt_get_lazy_mode(void) +{ + return PARAVIRT_LAZY_NONE; +} + +extern struct dma_map_ops *xen_dma_ops; + +#ifdef CONFIG_XEN +void __init xen_early_init(void); +#else +static inline void xen_early_init(void) { return; } +#endif + +#ifdef CONFIG_HOTPLUG_CPU +static inline void xen_arch_register_cpu(int num) +{ +} + +static inline void xen_arch_unregister_cpu(int num) +{ +} +#endif + +#endif /* _ASM_ARM_XEN_HYPERVISOR_H */ diff --git a/include/xen/arm/interface.h b/include/xen/arm/interface.h new file mode 100644 index 000000000000..75d596862892 --- /dev/null +++ b/include/xen/arm/interface.h @@ -0,0 +1,85 @@ +/****************************************************************************** + * Guest OS interface to ARM Xen. + * + * Stefano Stabellini , Citrix, 2012 + */ + +#ifndef _ASM_ARM_XEN_INTERFACE_H +#define _ASM_ARM_XEN_INTERFACE_H + +#include + +#define uint64_aligned_t uint64_t __attribute__((aligned(8))) + +#define __DEFINE_GUEST_HANDLE(name, type) \ + typedef struct { union { type *p; uint64_aligned_t q; }; } \ + __guest_handle_ ## name + +#define DEFINE_GUEST_HANDLE_STRUCT(name) \ + __DEFINE_GUEST_HANDLE(name, struct name) +#define DEFINE_GUEST_HANDLE(name) __DEFINE_GUEST_HANDLE(name, name) +#define GUEST_HANDLE(name) __guest_handle_ ## name + +#define set_xen_guest_handle(hnd, val) \ + do { \ + if (sizeof(hnd) == 8) \ + *(uint64_t *)&(hnd) = 0; \ + (hnd).p = val; \ + } while (0) + +#define __HYPERVISOR_platform_op_raw __HYPERVISOR_platform_op + +#ifndef __ASSEMBLY__ +/* Explicitly size integers that represent pfns in the interface with + * Xen so that we can have one ABI that works for 32 and 64 bit guests. + * Note that this means that the xen_pfn_t type may be capable of + * representing pfn's which the guest cannot represent in its own pfn + * type. However since pfn space is controlled by the guest this is + * fine since it simply wouldn't be able to create any sure pfns in + * the first place. + */ +typedef uint64_t xen_pfn_t; +#define PRI_xen_pfn "llx" +typedef uint64_t xen_ulong_t; +#define PRI_xen_ulong "llx" +typedef int64_t xen_long_t; +#define PRI_xen_long "llx" +/* Guest handles for primitive C types. */ +__DEFINE_GUEST_HANDLE(uchar, unsigned char); +__DEFINE_GUEST_HANDLE(uint, unsigned int); +DEFINE_GUEST_HANDLE(char); +DEFINE_GUEST_HANDLE(int); +DEFINE_GUEST_HANDLE(void); +DEFINE_GUEST_HANDLE(uint64_t); +DEFINE_GUEST_HANDLE(uint32_t); +DEFINE_GUEST_HANDLE(xen_pfn_t); +DEFINE_GUEST_HANDLE(xen_ulong_t); + +/* Maximum number of virtual CPUs in multi-processor guests. */ +#define MAX_VIRT_CPUS 1 + +struct arch_vcpu_info { }; +struct arch_shared_info { }; + +/* TODO: Move pvclock definitions some place arch independent */ +struct pvclock_vcpu_time_info { + u32 version; + u32 pad0; + u64 tsc_timestamp; + u64 system_time; + u32 tsc_to_system_mul; + s8 tsc_shift; + u8 flags; + u8 pad[2]; +} __attribute__((__packed__)); /* 32 bytes */ + +/* It is OK to have a 12 bytes struct with no padding because it is packed */ +struct pvclock_wall_clock { + u32 version; + u32 sec; + u32 nsec; + u32 sec_hi; +} __attribute__((__packed__)); +#endif + +#endif /* _ASM_ARM_XEN_INTERFACE_H */ diff --git a/include/xen/arm/page-coherent.h b/include/xen/arm/page-coherent.h new file mode 100644 index 000000000000..95ce6ac3a971 --- /dev/null +++ b/include/xen/arm/page-coherent.h @@ -0,0 +1,98 @@ +#ifndef _ASM_ARM_XEN_PAGE_COHERENT_H +#define _ASM_ARM_XEN_PAGE_COHERENT_H + +#include +#include + +void __xen_dma_map_page(struct device *hwdev, struct page *page, + dma_addr_t dev_addr, unsigned long offset, size_t size, + enum dma_data_direction dir, unsigned long attrs); +void __xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle, + size_t size, enum dma_data_direction dir, + unsigned long attrs); +void __xen_dma_sync_single_for_cpu(struct device *hwdev, + dma_addr_t handle, size_t size, enum dma_data_direction dir); + +void __xen_dma_sync_single_for_device(struct device *hwdev, + dma_addr_t handle, size_t size, enum dma_data_direction dir); + +static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size, + dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs) +{ + return __generic_dma_ops(hwdev)->alloc(hwdev, size, dma_handle, flags, attrs); +} + +static inline void xen_free_coherent_pages(struct device *hwdev, size_t size, + void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs) +{ + __generic_dma_ops(hwdev)->free(hwdev, size, cpu_addr, dma_handle, attrs); +} + +static inline void xen_dma_map_page(struct device *hwdev, struct page *page, + dma_addr_t dev_addr, unsigned long offset, size_t size, + enum dma_data_direction dir, unsigned long attrs) +{ + unsigned long page_pfn = page_to_xen_pfn(page); + unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr); + unsigned long compound_pages = + (1<map_page(hwdev, page, offset, size, dir, attrs); + else + __xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs); +} + +static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle, + size_t size, enum dma_data_direction dir, unsigned long attrs) +{ + unsigned long pfn = PFN_DOWN(handle); + /* + * Dom0 is mapped 1:1, while the Linux page can be spanned accross + * multiple Xen page, it's not possible to have a mix of local and + * foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a + * foreign mfn will always return false. If the page is local we can + * safely call the native dma_ops function, otherwise we call the xen + * specific function. + */ + if (pfn_valid(pfn)) { + if (__generic_dma_ops(hwdev)->unmap_page) + __generic_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs); + } else + __xen_dma_unmap_page(hwdev, handle, size, dir, attrs); +} + +static inline void xen_dma_sync_single_for_cpu(struct device *hwdev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) +{ + unsigned long pfn = PFN_DOWN(handle); + if (pfn_valid(pfn)) { + if (__generic_dma_ops(hwdev)->sync_single_for_cpu) + __generic_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir); + } else + __xen_dma_sync_single_for_cpu(hwdev, handle, size, dir); +} + +static inline void xen_dma_sync_single_for_device(struct device *hwdev, + dma_addr_t handle, size_t size, enum dma_data_direction dir) +{ + unsigned long pfn = PFN_DOWN(handle); + if (pfn_valid(pfn)) { + if (__generic_dma_ops(hwdev)->sync_single_for_device) + __generic_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir); + } else + __xen_dma_sync_single_for_device(hwdev, handle, size, dir); +} + +#endif /* _ASM_ARM_XEN_PAGE_COHERENT_H */ diff --git a/include/xen/arm/page.h b/include/xen/arm/page.h new file mode 100644 index 000000000000..415dbc6e43fd --- /dev/null +++ b/include/xen/arm/page.h @@ -0,0 +1,122 @@ +#ifndef _ASM_ARM_XEN_PAGE_H +#define _ASM_ARM_XEN_PAGE_H + +#include +#include + +#include +#include +#include + +#include +#include + +#define phys_to_machine_mapping_valid(pfn) (1) + +/* Xen machine address */ +typedef struct xmaddr { + phys_addr_t maddr; +} xmaddr_t; + +/* Xen pseudo-physical address */ +typedef struct xpaddr { + phys_addr_t paddr; +} xpaddr_t; + +#define XMADDR(x) ((xmaddr_t) { .maddr = (x) }) +#define XPADDR(x) ((xpaddr_t) { .paddr = (x) }) + +#define INVALID_P2M_ENTRY (~0UL) + +/* + * The pseudo-physical frame (pfn) used in all the helpers is always based + * on Xen page granularity (i.e 4KB). + * + * A Linux page may be split across multiple non-contiguous Xen page so we + * have to keep track with frame based on 4KB page granularity. + * + * PV drivers should never make a direct usage of those helpers (particularly + * pfn_to_gfn and gfn_to_pfn). + */ + +unsigned long __pfn_to_mfn(unsigned long pfn); +extern struct rb_root phys_to_mach; + +/* Pseudo-physical <-> Guest conversion */ +static inline unsigned long pfn_to_gfn(unsigned long pfn) +{ + return pfn; +} + +static inline unsigned long gfn_to_pfn(unsigned long gfn) +{ + return gfn; +} + +/* Pseudo-physical <-> BUS conversion */ +static inline unsigned long pfn_to_bfn(unsigned long pfn) +{ + unsigned long mfn; + + if (phys_to_mach.rb_node != NULL) { + mfn = __pfn_to_mfn(pfn); + if (mfn != INVALID_P2M_ENTRY) + return mfn; + } + + return pfn; +} + +static inline unsigned long bfn_to_pfn(unsigned long bfn) +{ + return bfn; +} + +#define bfn_to_local_pfn(bfn) bfn_to_pfn(bfn) + +/* VIRT <-> GUEST conversion */ +#define virt_to_gfn(v) (pfn_to_gfn(virt_to_phys(v) >> XEN_PAGE_SHIFT)) +#define gfn_to_virt(m) (__va(gfn_to_pfn(m) << XEN_PAGE_SHIFT)) + +/* Only used in PV code. But ARM guests are always HVM. */ +static inline xmaddr_t arbitrary_virt_to_machine(void *vaddr) +{ + BUG(); +} + +/* TODO: this shouldn't be here but it is because the frontend drivers + * are using it (its rolled in headers) even though we won't hit the code path. + * So for right now just punt with this. + */ +static inline pte_t *lookup_address(unsigned long address, unsigned int *level) +{ + BUG(); + return NULL; +} + +extern int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, + struct gnttab_map_grant_ref *kmap_ops, + struct page **pages, unsigned int count); + +extern int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, + struct gnttab_unmap_grant_ref *kunmap_ops, + struct page **pages, unsigned int count); + +bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn); +bool __set_phys_to_machine_multi(unsigned long pfn, unsigned long mfn, + unsigned long nr_pages); + +static inline bool set_phys_to_machine(unsigned long pfn, unsigned long mfn) +{ + return __set_phys_to_machine(pfn, mfn); +} + +#define xen_remap(cookie, size) ioremap_cache((cookie), (size)) +#define xen_unmap(cookie) iounmap((cookie)) + +bool xen_arch_need_swiotlb(struct device *dev, + phys_addr_t phys, + dma_addr_t dev_addr); +unsigned long xen_get_swiotlb_free_pages(unsigned int order); + +#endif /* _ASM_ARM_XEN_PAGE_H */ -- cgit v1.2.3 From 24d5373dda7c00a438d26016bce140299fae675e Mon Sep 17 00:00:00 2001 From: Julien Grall Date: Wed, 7 Dec 2016 12:24:40 +0000 Subject: arm/xen: Use alloc_percpu rather than __alloc_percpu The function xen_guest_init is using __alloc_percpu with an alignment which are not power of two. However, the percpu allocator never supported alignments which are not power of two and has always behaved incorectly in thise case. Commit 3ca45a4 "percpu: ensure requested alignment is power of two" introduced a check which trigger a warning [1] when booting linux-next on Xen. But in reality this bug was always present. This can be fixed by replacing the call to __alloc_percpu with alloc_percpu. The latter will use an alignment which are a power of two. [1] [ 0.023921] illegal size (48) or align (48) for percpu allocation [ 0.024167] ------------[ cut here ]------------ [ 0.024344] WARNING: CPU: 0 PID: 1 at linux/mm/percpu.c:892 pcpu_alloc+0x88/0x6c0 [ 0.024584] Modules linked in: [ 0.024708] [ 0.024804] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.9.0-rc7-next-20161128 #473 [ 0.025012] Hardware name: Foundation-v8A (DT) [ 0.025162] task: ffff80003d870000 task.stack: ffff80003d844000 [ 0.025351] PC is at pcpu_alloc+0x88/0x6c0 [ 0.025490] LR is at pcpu_alloc+0x88/0x6c0 [ 0.025624] pc : [] lr : [] pstate: 60000045 [ 0.025830] sp : ffff80003d847cd0 [ 0.025946] x29: ffff80003d847cd0 x28: 0000000000000000 [ 0.026147] x27: 0000000000000000 x26: 0000000000000000 [ 0.026348] x25: 0000000000000000 x24: 0000000000000000 [ 0.026549] x23: 0000000000000000 x22: 00000000024000c0 [ 0.026752] x21: ffff000008e97000 x20: 0000000000000000 [ 0.026953] x19: 0000000000000030 x18: 0000000000000010 [ 0.027155] x17: 0000000000000a3f x16: 00000000deadbeef [ 0.027357] x15: 0000000000000006 x14: ffff000088f79c3f [ 0.027573] x13: ffff000008f79c4d x12: 0000000000000041 [ 0.027782] x11: 0000000000000006 x10: 0000000000000042 [ 0.027995] x9 : ffff80003d847a40 x8 : 6f697461636f6c6c [ 0.028208] x7 : 6120757063726570 x6 : ffff000008f79c84 [ 0.028419] x5 : 0000000000000005 x4 : 0000000000000000 [ 0.028628] x3 : 0000000000000000 x2 : 000000000000017f [ 0.028840] x1 : ffff80003d870000 x0 : 0000000000000035 [ 0.029056] [ 0.029152] ---[ end trace 0000000000000000 ]--- [ 0.029297] Call trace: [ 0.029403] Exception stack(0xffff80003d847b00 to 0xffff80003d847c30) [ 0.029621] 7b00: 0000000000000030 0001000000000000 ffff80003d847cd0 ffff00000818e678 [ 0.029901] 7b20: 0000000000000002 0000000000000004 ffff000008f7c060 0000000000000035 [ 0.030153] 7b40: ffff000008f79000 ffff000008c4cd88 ffff80003d847bf0 ffff000008101778 [ 0.030402] 7b60: 0000000000000030 0000000000000000 ffff000008e97000 00000000024000c0 [ 0.030647] 7b80: 0000000000000000 0000000000000000 0000000000000000 0000000000000000 [ 0.030895] 7ba0: 0000000000000035 ffff80003d870000 000000000000017f 0000000000000000 [ 0.031144] 7bc0: 0000000000000000 0000000000000005 ffff000008f79c84 6120757063726570 [ 0.031394] 7be0: 6f697461636f6c6c ffff80003d847a40 0000000000000042 0000000000000006 [ 0.031643] 7c00: 0000000000000041 ffff000008f79c4d ffff000088f79c3f 0000000000000006 [ 0.031877] 7c20: 00000000deadbeef 0000000000000a3f [ 0.032051] [] pcpu_alloc+0x88/0x6c0 [ 0.032229] [] __alloc_percpu+0x18/0x20 [ 0.032409] [] xen_guest_init+0x174/0x2f4 [ 0.032591] [] do_one_initcall+0x38/0x130 [ 0.032783] [] kernel_init_freeable+0xe0/0x248 [ 0.032995] [] kernel_init+0x10/0x100 [ 0.033172] [] ret_from_fork+0x10/0x50 Reported-by: Wei Chen Link: https://lkml.org/lkml/2016/11/28/669 Signed-off-by: Julien Grall Signed-off-by: Stefano Stabellini Reviewed-by: Stefano Stabellini Cc: stable@vger.kernel.org --- arch/arm/xen/enlighten.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c index f193414d0f6f..4986dc0c1dff 100644 --- a/arch/arm/xen/enlighten.c +++ b/arch/arm/xen/enlighten.c @@ -372,8 +372,7 @@ static int __init xen_guest_init(void) * for secondary CPUs as they are brought up. * For uniformity we use VCPUOP_register_vcpu_info even on cpu0. */ - xen_vcpu_info = __alloc_percpu(sizeof(struct vcpu_info), - sizeof(struct vcpu_info)); + xen_vcpu_info = alloc_percpu(struct vcpu_info); if (xen_vcpu_info == NULL) return -ENOMEM; -- cgit v1.2.3 From 0fdb47440203ce06e09923c4d578cf3c20aef69a Mon Sep 17 00:00:00 2001 From: Pan Bian Date: Mon, 5 Dec 2016 16:23:05 +0800 Subject: xen: set error code on failures Variable rc is reset in the loop, and its value will be non-negative during the second and after repeat of the loop. If it fails to allocate memory then, it may return a non-negative integer, which indicates no error. This patch fixes the bug, assigning "-ENOMEM" to rc when kzalloc() or alloc_page() returns NULL, and removing the initialization of rc outside of the loop. Signed-off-by: Pan Bian Reviewed-by: Juergen Gross Signed-off-by: Juergen Gross --- drivers/xen/gntalloc.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/drivers/xen/gntalloc.c b/drivers/xen/gntalloc.c index 7a47c4c9fb1b..1bf55a32a4b3 100644 --- a/drivers/xen/gntalloc.c +++ b/drivers/xen/gntalloc.c @@ -127,18 +127,21 @@ static int add_grefs(struct ioctl_gntalloc_alloc_gref *op, struct gntalloc_gref *gref, *next; readonly = !(op->flags & GNTALLOC_FLAG_WRITABLE); - rc = -ENOMEM; for (i = 0; i < op->count; i++) { gref = kzalloc(sizeof(*gref), GFP_KERNEL); - if (!gref) + if (!gref) { + rc = -ENOMEM; goto undo; + } list_add_tail(&gref->next_gref, &queue_gref); list_add_tail(&gref->next_file, &queue_file); gref->users = 1; gref->file_index = op->index + i * PAGE_SIZE; gref->page = alloc_page(GFP_KERNEL|__GFP_ZERO); - if (!gref->page) + if (!gref->page) { + rc = -ENOMEM; goto undo; + } /* Grant foreign access to the page. */ rc = gnttab_grant_foreign_access(op->domid, -- cgit v1.2.3 From 2466d4b9d0c21e6c28cd63516dea65806bf5a307 Mon Sep 17 00:00:00 2001 From: Pan Bian Date: Mon, 5 Dec 2016 16:22:22 +0800 Subject: xen: xenbus: set error code on failure Variable err is initialized with 0. As a result, the return value may be 0 even if get_zeroed_page() fails to allocate memory. This patch fixes the bug, initializing err with "-ENOMEM". Signed-off-by: Pan Bian Reviewed-by: Juergen Gross Signed-off-by: Juergen Gross --- drivers/xen/xenbus/xenbus_probe.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index b5c1dec4a7c2..4bdf654041e9 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -702,7 +702,7 @@ device_initcall(xenbus_probe_initcall); */ static int __init xenstored_local_init(void) { - int err = 0; + int err = -ENOMEM; unsigned long page = 0; struct evtchn_alloc_unbound alloc_unbound; -- cgit v1.2.3 From 577f79e411b7a81a8ae7ae4daf5d4056ebbfbc58 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Tue, 6 Dec 2016 09:28:21 -0500 Subject: xen/pci: Bubble up error and fix description. The function is never called under PV guests, and only shows up when MSI (or MSI-X) cannot be allocated. Convert the message to include the error value. Signed-off-by: Konrad Rzeszutek Wilk Reviewed-by: Juergen Gross Signed-off-by: Juergen Gross --- arch/x86/pci/xen.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index bedfab98077a..e1fb269c87af 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -264,8 +264,8 @@ static int xen_hvm_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) return 0; error: - dev_err(&dev->dev, - "Xen PCI frontend has not registered MSI/MSI-X support!\n"); + dev_err(&dev->dev, "Failed to create MSI%s! ret=%d!\n", + type == PCI_CAP_ID_MSI ? "" : "-X", irq); return irq; } -- cgit v1.2.3 From 9d2f86c6cad5a8a3f0b38a80136ba68364ca7278 Mon Sep 17 00:00:00 2001 From: Alex Thorlton Date: Mon, 5 Dec 2016 11:49:13 -0600 Subject: x86: Make E820_X_MAX unconditionally larger than E820MAX It's really not necessary to limit E820_X_MAX to 128 in the non-EFI case. This commit drops E820_X_MAX's dependency on CONFIG_EFI, so that E820_X_MAX is always at least slightly larger than E820MAX. The real motivation behind this is actually to prevent some issues in the Xen kernel, where the XENMEM_machine_memory_map hypercall can produce an e820 map larger than 128 entries, even on systems where the original e820 table was quite a bit smaller than that, depending on how many IOAPICs are installed on the system. Signed-off-by: Alex Thorlton Suggested-by: Ingo Molnar Acked-by: Ingo Molnar Signed-off-by: Juergen Gross --- arch/x86/include/asm/e820.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index 476b574de99e..ec23d8e1297c 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -1,13 +1,17 @@ #ifndef _ASM_X86_E820_H #define _ASM_X86_E820_H -#ifdef CONFIG_EFI +/* + * E820_X_MAX is the maximum size of the extended E820 table. The extended + * table may contain up to 3 extra E820 entries per possible NUMA node, so we + * make room for 3 * MAX_NUMNODES possible entries, beyond the standard 128. + * Also note that E820_X_MAX *must* be defined before we include uapi/asm/e820.h. + */ #include #define E820_X_MAX (E820MAX + 3 * MAX_NUMNODES) -#else /* ! CONFIG_EFI */ -#define E820_X_MAX E820MAX -#endif + #include + #ifndef __ASSEMBLY__ /* see comment in arch/x86/kernel/e820.c */ extern struct e820map *e820; -- cgit v1.2.3 From 738662c35c491fc360bb6adcb8a0db88d87b5d88 Mon Sep 17 00:00:00 2001 From: Alex Thorlton Date: Mon, 5 Dec 2016 11:49:14 -0600 Subject: xen/x86: Increase xen_e820_map to E820_X_MAX possible entries On systems with sufficiently large e820 tables, and several IOAPICs, it is possible for the XENMEM_machine_memory_map callback (and its counterpart, XENMEM_memory_map) to attempt to return an e820 table with more than 128 entries. This callback adds entries to the BIOS-provided e820 table to account for IOAPIC registers, which, on sufficiently large systems, can result in an e820 table that is too large to copy back into xen_e820_map. This change simply increases the size of xen_e820_map to E820_X_MAX to ensure that there is enough room to store the entire e820 map returned from this callback. Signed-off-by: Alex Thorlton Suggested-by: Boris Ostrovsky Reviewed-by: Juergen Gross Acked-by: Ingo Molnar Signed-off-by: Juergen Gross --- arch/x86/xen/setup.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index f8960fca0827..8c394e30e5fe 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -41,7 +41,7 @@ struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata; unsigned long xen_released_pages; /* E820 map used during setting up memory. */ -static struct e820entry xen_e820_map[E820MAX] __initdata; +static struct e820entry xen_e820_map[E820_X_MAX] __initdata; static u32 xen_e820_map_entries __initdata; /* @@ -750,7 +750,7 @@ char * __init xen_memory_setup(void) max_pfn = min(max_pfn, xen_start_info->nr_pages); mem_end = PFN_PHYS(max_pfn); - memmap.nr_entries = E820MAX; + memmap.nr_entries = ARRAY_SIZE(xen_e820_map); set_xen_guest_handle(memmap.buffer, xen_e820_map); op = xen_initial_domain() ? @@ -923,7 +923,7 @@ char * __init xen_auto_xlated_memory_setup(void) int i; int rc; - memmap.nr_entries = E820MAX; + memmap.nr_entries = ARRAY_SIZE(xen_e820_map); set_xen_guest_handle(memmap.buffer, xen_e820_map); rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap); -- cgit v1.2.3 From 3da96be58f2c8aaa86cfe78b16f837e610dfcfe2 Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Fri, 2 Dec 2016 07:15:45 +0100 Subject: xen/scsifront: don't request a slot on the ring until request is ready Instead of requesting a new slot on the ring to the backend early, do so only after all has been setup for the request to be sent. This makes error handling easier as we don't need to undo the request id allocation and ring slot allocation. Suggested-by: Jan Beulich Signed-off-by: Juergen Gross Reviewed-by: Boris Ostrovsky Signed-off-by: Juergen Gross --- drivers/scsi/xen-scsifront.c | 188 +++++++++++++++++++------------------------ 1 file changed, 83 insertions(+), 105 deletions(-) diff --git a/drivers/scsi/xen-scsifront.c b/drivers/scsi/xen-scsifront.c index c01316c6c7b1..9aa1fe1fc939 100644 --- a/drivers/scsi/xen-scsifront.c +++ b/drivers/scsi/xen-scsifront.c @@ -79,10 +79,13 @@ struct vscsifrnt_shadow { /* command between backend and frontend */ unsigned char act; + uint8_t nr_segments; uint16_t rqid; + uint16_t ref_rqid; unsigned int nr_grants; /* number of grants in gref[] */ struct scsiif_request_segment *sg; /* scatter/gather elements */ + struct scsiif_request_segment seg[VSCSIIF_SG_TABLESIZE]; /* Do reset or abort function. */ wait_queue_head_t wq_reset; /* reset work queue */ @@ -172,68 +175,90 @@ static void scsifront_put_rqid(struct vscsifrnt_info *info, uint32_t id) scsifront_wake_up(info); } -static struct vscsiif_request *scsifront_pre_req(struct vscsifrnt_info *info) +static int scsifront_do_request(struct vscsifrnt_info *info, + struct vscsifrnt_shadow *shadow) { struct vscsiif_front_ring *ring = &(info->ring); struct vscsiif_request *ring_req; + struct scsi_cmnd *sc = shadow->sc; uint32_t id; + int i, notify; + + if (RING_FULL(&info->ring)) + return -EBUSY; id = scsifront_get_rqid(info); /* use id in response */ if (id >= VSCSIIF_MAX_REQS) - return NULL; + return -EBUSY; - ring_req = RING_GET_REQUEST(&(info->ring), ring->req_prod_pvt); + info->shadow[id] = shadow; + shadow->rqid = id; + ring_req = RING_GET_REQUEST(&(info->ring), ring->req_prod_pvt); ring->req_prod_pvt++; - ring_req->rqid = (uint16_t)id; + ring_req->rqid = id; + ring_req->act = shadow->act; + ring_req->ref_rqid = shadow->ref_rqid; + ring_req->nr_segments = shadow->nr_segments; - return ring_req; -} + ring_req->id = sc->device->id; + ring_req->lun = sc->device->lun; + ring_req->channel = sc->device->channel; + ring_req->cmd_len = sc->cmd_len; -static void scsifront_do_request(struct vscsifrnt_info *info) -{ - struct vscsiif_front_ring *ring = &(info->ring); - int notify; + BUG_ON(sc->cmd_len > VSCSIIF_MAX_COMMAND_SIZE); + + memcpy(ring_req->cmnd, sc->cmnd, sc->cmd_len); + + ring_req->sc_data_direction = (uint8_t)sc->sc_data_direction; + ring_req->timeout_per_command = sc->request->timeout / HZ; + + for (i = 0; i < (shadow->nr_segments & ~VSCSIIF_SG_GRANT); i++) + ring_req->seg[i] = shadow->seg[i]; RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(ring, notify); if (notify) notify_remote_via_irq(info->irq); + + return 0; } -static void scsifront_gnttab_done(struct vscsifrnt_info *info, uint32_t id) +static void scsifront_gnttab_done(struct vscsifrnt_info *info, + struct vscsifrnt_shadow *shadow) { - struct vscsifrnt_shadow *s = info->shadow[id]; int i; - if (s->sc->sc_data_direction == DMA_NONE) + if (shadow->sc->sc_data_direction == DMA_NONE) return; - for (i = 0; i < s->nr_grants; i++) { - if (unlikely(gnttab_query_foreign_access(s->gref[i]) != 0)) { + for (i = 0; i < shadow->nr_grants; i++) { + if (unlikely(gnttab_query_foreign_access(shadow->gref[i]))) { shost_printk(KERN_ALERT, info->host, KBUILD_MODNAME "grant still in use by backend\n"); BUG(); } - gnttab_end_foreign_access(s->gref[i], 0, 0UL); + gnttab_end_foreign_access(shadow->gref[i], 0, 0UL); } - kfree(s->sg); + kfree(shadow->sg); } static void scsifront_cdb_cmd_done(struct vscsifrnt_info *info, struct vscsiif_response *ring_rsp) { + struct vscsifrnt_shadow *shadow; struct scsi_cmnd *sc; uint32_t id; uint8_t sense_len; id = ring_rsp->rqid; - sc = info->shadow[id]->sc; + shadow = info->shadow[id]; + sc = shadow->sc; BUG_ON(sc == NULL); - scsifront_gnttab_done(info, id); + scsifront_gnttab_done(info, shadow); scsifront_put_rqid(info, id); sc->result = ring_rsp->rslt; @@ -366,7 +391,6 @@ static void scsifront_finish_all(struct vscsifrnt_info *info) static int map_data_for_request(struct vscsifrnt_info *info, struct scsi_cmnd *sc, - struct vscsiif_request *ring_req, struct vscsifrnt_shadow *shadow) { grant_ref_t gref_head; @@ -379,7 +403,6 @@ static int map_data_for_request(struct vscsifrnt_info *info, struct scatterlist *sg; struct scsiif_request_segment *seg; - ring_req->nr_segments = 0; if (sc->sc_data_direction == DMA_NONE || !data_len) return 0; @@ -398,7 +421,7 @@ static int map_data_for_request(struct vscsifrnt_info *info, if (!shadow->sg) return -ENOMEM; } - seg = shadow->sg ? : ring_req->seg; + seg = shadow->sg ? : shadow->seg; err = gnttab_alloc_grant_references(seg_grants + data_grants, &gref_head); @@ -423,9 +446,9 @@ static int map_data_for_request(struct vscsifrnt_info *info, info->dev->otherend_id, xen_page_to_gfn(page), 1); shadow->gref[ref_cnt] = ref; - ring_req->seg[ref_cnt].gref = ref; - ring_req->seg[ref_cnt].offset = (uint16_t)off; - ring_req->seg[ref_cnt].length = (uint16_t)bytes; + shadow->seg[ref_cnt].gref = ref; + shadow->seg[ref_cnt].offset = (uint16_t)off; + shadow->seg[ref_cnt].length = (uint16_t)bytes; page++; len -= bytes; @@ -473,44 +496,14 @@ static int map_data_for_request(struct vscsifrnt_info *info, } if (seg_grants) - ring_req->nr_segments = VSCSIIF_SG_GRANT | seg_grants; + shadow->nr_segments = VSCSIIF_SG_GRANT | seg_grants; else - ring_req->nr_segments = (uint8_t)ref_cnt; + shadow->nr_segments = (uint8_t)ref_cnt; shadow->nr_grants = ref_cnt; return 0; } -static struct vscsiif_request *scsifront_command2ring( - struct vscsifrnt_info *info, struct scsi_cmnd *sc, - struct vscsifrnt_shadow *shadow) -{ - struct vscsiif_request *ring_req; - - memset(shadow, 0, sizeof(*shadow)); - - ring_req = scsifront_pre_req(info); - if (!ring_req) - return NULL; - - info->shadow[ring_req->rqid] = shadow; - shadow->rqid = ring_req->rqid; - - ring_req->id = sc->device->id; - ring_req->lun = sc->device->lun; - ring_req->channel = sc->device->channel; - ring_req->cmd_len = sc->cmd_len; - - BUG_ON(sc->cmd_len > VSCSIIF_MAX_COMMAND_SIZE); - - memcpy(ring_req->cmnd, sc->cmnd, sc->cmd_len); - - ring_req->sc_data_direction = (uint8_t)sc->sc_data_direction; - ring_req->timeout_per_command = sc->request->timeout / HZ; - - return ring_req; -} - static int scsifront_enter(struct vscsifrnt_info *info) { if (info->pause) @@ -536,36 +529,25 @@ static int scsifront_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *sc) { struct vscsifrnt_info *info = shost_priv(shost); - struct vscsiif_request *ring_req; struct vscsifrnt_shadow *shadow = scsi_cmd_priv(sc); unsigned long flags; int err; - uint16_t rqid; + + sc->result = 0; + memset(shadow, 0, sizeof(*shadow)); + + shadow->sc = sc; + shadow->act = VSCSIIF_ACT_SCSI_CDB; spin_lock_irqsave(shost->host_lock, flags); if (scsifront_enter(info)) { spin_unlock_irqrestore(shost->host_lock, flags); return SCSI_MLQUEUE_HOST_BUSY; } - if (RING_FULL(&info->ring)) - goto busy; - ring_req = scsifront_command2ring(info, sc, shadow); - if (!ring_req) - goto busy; - - sc->result = 0; - - rqid = ring_req->rqid; - ring_req->act = VSCSIIF_ACT_SCSI_CDB; - - shadow->sc = sc; - shadow->act = VSCSIIF_ACT_SCSI_CDB; - - err = map_data_for_request(info, sc, ring_req, shadow); + err = map_data_for_request(info, sc, shadow); if (err < 0) { pr_debug("%s: err %d\n", __func__, err); - scsifront_put_rqid(info, rqid); scsifront_return(info); spin_unlock_irqrestore(shost->host_lock, flags); if (err == -ENOMEM) @@ -575,7 +557,11 @@ static int scsifront_queuecommand(struct Scsi_Host *shost, return 0; } - scsifront_do_request(info); + if (scsifront_do_request(info, shadow)) { + scsifront_gnttab_done(info, shadow); + goto busy; + } + scsifront_return(info); spin_unlock_irqrestore(shost->host_lock, flags); @@ -598,26 +584,30 @@ static int scsifront_action_handler(struct scsi_cmnd *sc, uint8_t act) struct Scsi_Host *host = sc->device->host; struct vscsifrnt_info *info = shost_priv(host); struct vscsifrnt_shadow *shadow, *s = scsi_cmd_priv(sc); - struct vscsiif_request *ring_req; int err = 0; - shadow = kmalloc(sizeof(*shadow), GFP_NOIO); + shadow = kzalloc(sizeof(*shadow), GFP_NOIO); if (!shadow) return FAILED; + shadow->act = act; + shadow->rslt_reset = RSLT_RESET_WAITING; + shadow->sc = sc; + shadow->ref_rqid = s->rqid; + init_waitqueue_head(&shadow->wq_reset); + spin_lock_irq(host->host_lock); for (;;) { - if (!RING_FULL(&info->ring)) { - ring_req = scsifront_command2ring(info, sc, shadow); - if (ring_req) - break; - } - if (err || info->pause) { - spin_unlock_irq(host->host_lock); - kfree(shadow); - return FAILED; - } + if (scsifront_enter(info)) + goto fail; + + if (!scsifront_do_request(info, shadow)) + break; + + scsifront_return(info); + if (err) + goto fail; info->wait_ring_available = 1; spin_unlock_irq(host->host_lock); err = wait_event_interruptible(info->wq_sync, @@ -625,23 +615,6 @@ static int scsifront_action_handler(struct scsi_cmnd *sc, uint8_t act) spin_lock_irq(host->host_lock); } - if (scsifront_enter(info)) { - spin_unlock_irq(host->host_lock); - kfree(shadow); - return FAILED; - } - - ring_req->act = act; - ring_req->ref_rqid = s->rqid; - - shadow->act = act; - shadow->rslt_reset = RSLT_RESET_WAITING; - init_waitqueue_head(&shadow->wq_reset); - - ring_req->nr_segments = 0; - - scsifront_do_request(info); - spin_unlock_irq(host->host_lock); err = wait_event_interruptible(shadow->wq_reset, shadow->wait_reset); spin_lock_irq(host->host_lock); @@ -660,6 +633,11 @@ static int scsifront_action_handler(struct scsi_cmnd *sc, uint8_t act) scsifront_return(info); spin_unlock_irq(host->host_lock); return err; + +fail: + spin_unlock_irq(host->host_lock); + kfree(shadow); + return FAILED; } static int scsifront_eh_abort_handler(struct scsi_cmnd *sc) -- cgit v1.2.3 From 581d21a2d02a798ee34e56dbfa13f891b3a90c30 Mon Sep 17 00:00:00 2001 From: David Vrabel Date: Fri, 9 Dec 2016 14:41:13 +0000 Subject: xenbus: fix deadlock on writes to /proc/xen/xenbus /proc/xen/xenbus does not work correctly. A read blocked waiting for a xenstore message holds the mutex needed for atomic file position updates. This blocks any writes on the same file handle, which can deadlock if the write is needed to unblock the read. Clear FMODE_ATOMIC_POS when opening this device to always get character device like sematics. Signed-off-by: David Vrabel Reviewed-by: Juergen Gross Signed-off-by: Juergen Gross --- drivers/xen/xenbus/xenbus_dev_frontend.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index 1e8be12ebb55..6c0ead4be784 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -538,6 +538,8 @@ static int xenbus_file_open(struct inode *inode, struct file *filp) nonseekable_open(inode, filp); + filp->f_mode &= ~FMODE_ATOMIC_POS; /* cdev-style semantics */ + u = kzalloc(sizeof(*u), GFP_KERNEL); if (u == NULL) return -ENOMEM; -- cgit v1.2.3 From 709613ad2b3c9eaeb2a3e24284b7c8feffc17326 Mon Sep 17 00:00:00 2001 From: Ross Lagerwall Date: Fri, 9 Dec 2016 17:10:22 +0000 Subject: xen/balloon: Only mark a page as managed when it is released Only mark a page as managed when it is released back to the allocator. This ensures that the managed page count does not get falsely increased when a VM is running. Correspondingly change it so that pages are marked as unmanaged after getting them from the allocator. Signed-off-by: Ross Lagerwall Reviewed-by: Boris Ostrovsky Signed-off-by: Juergen Gross --- drivers/xen/balloon.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index e4db19e88ab1..db107fa50ca1 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -180,7 +180,6 @@ static void __balloon_append(struct page *page) static void balloon_append(struct page *page) { __balloon_append(page); - adjust_managed_page_count(page, -1); } /* balloon_retrieve: rescue a page from the balloon, if it is not empty. */ @@ -201,8 +200,6 @@ static struct page *balloon_retrieve(bool require_lowmem) else balloon_stats.balloon_low--; - adjust_managed_page_count(page, 1); - return page; } @@ -478,7 +475,7 @@ static enum bp_state increase_reservation(unsigned long nr_pages) #endif /* Relinquish the page back to the allocator. */ - __free_reserved_page(page); + free_reserved_page(page); } balloon_stats.current_pages += rc; @@ -509,6 +506,7 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp) state = BP_EAGAIN; break; } + adjust_managed_page_count(page, -1); scrub_page(page); list_add(&page->lru, &pages); } -- cgit v1.2.3