From dd935f44a40f8fb02aff2cc0df2269c92422df1c Mon Sep 17 00:00:00 2001 From: Josh Durgin Date: Wed, 28 Aug 2013 21:43:09 -0700 Subject: libceph: add function to ensure notifies are complete Without a way to flush the osd client's notify workqueue, a watch event that is unregistered could continue receiving callbacks indefinitely. Unregistering the event simply means no new notifies are added to the queue, but there may still be events in the queue that will call the watch callback for the event. If the queue is flushed after the event is unregistered, the caller can be sure no more watch callbacks will occur for the canceled watch. Signed-off-by: Josh Durgin Reviewed-by: Sage Weil Reviewed-by: Alex Elder --- include/linux/ceph/osd_client.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index ce6df39f60ff..8f47625a0661 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -335,6 +335,8 @@ extern int ceph_osdc_wait_request(struct ceph_osd_client *osdc, struct ceph_osd_request *req); extern void ceph_osdc_sync(struct ceph_osd_client *osdc); +extern void ceph_osdc_flush_notifies(struct ceph_osd_client *osdc); + extern int ceph_osdc_readpages(struct ceph_osd_client *osdc, struct ceph_vino vino, struct ceph_file_layout *layout, -- cgit v1.2.3 From 7bd36014460f793c19e7d6c94dab67b0afcfcb7f Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 11 Sep 2013 16:50:56 -0700 Subject: timekeeping: Fix HRTICK related deadlock from ntp lock changes Gerlando Falauto reported that when HRTICK is enabled, it is possible to trigger system deadlocks. These were hard to reproduce, as HRTICK has been broken in the past, but seemed to be connected to the timekeeping_seq lock. Since seqlock/seqcount's aren't supported w/ lockdep, I added some extra spinlock based locking and triggered the following lockdep output: [ 15.849182] ntpd/4062 is trying to acquire lock: [ 15.849765] (&(&pool->lock)->rlock){..-...}, at: [] __queue_work+0x145/0x480 [ 15.850051] [ 15.850051] but task is already holding lock: [ 15.850051] (timekeeper_lock){-.-.-.}, at: [] do_adjtimex+0x7f/0x100 [ 15.850051] Chain exists of: &(&pool->lock)->rlock --> &p->pi_lock --> timekeeper_lock [ 15.850051] Possible unsafe locking scenario: [ 15.850051] [ 15.850051] CPU0 CPU1 [ 15.850051] ---- ---- [ 15.850051] lock(timekeeper_lock); [ 15.850051] lock(&p->pi_lock); [ 15.850051] lock(timekeeper_lock); [ 15.850051] lock(&(&pool->lock)->rlock); [ 15.850051] [ 15.850051] *** DEADLOCK *** The deadlock was introduced by 06c017fdd4dc48451a ("timekeeping: Hold timekeepering locks in do_adjtimex and hardpps") in 3.10 This patch avoids this deadlock, by moving the call to schedule_delayed_work() outside of the timekeeper lock critical section. Reported-by: Gerlando Falauto Tested-by: Lin Ming Signed-off-by: John Stultz Cc: Mathieu Desnoyers Cc: stable #3.11, 3.10 Link: http://lkml.kernel.org/r/1378943457-27314-1-git-send-email-john.stultz@linaro.org Signed-off-by: Ingo Molnar --- include/linux/timex.h | 1 + kernel/time/ntp.c | 6 ++---- kernel/time/timekeeping.c | 2 ++ 3 files changed, 5 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/timex.h b/include/linux/timex.h index b3726e61368e..dd3edd7dfc94 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -141,6 +141,7 @@ extern int do_adjtimex(struct timex *); extern void hardpps(const struct timespec *, const struct timespec *); int read_current_timer(unsigned long *timer_val); +void ntp_notify_cmos_timer(void); /* The clock frequency of the i8253/i8254 PIT */ #define PIT_TICK_RATE 1193182ul diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 8f5b3b98577b..bb2215174f05 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -516,13 +516,13 @@ static void sync_cmos_clock(struct work_struct *work) schedule_delayed_work(&sync_cmos_work, timespec_to_jiffies(&next)); } -static void notify_cmos_timer(void) +void ntp_notify_cmos_timer(void) { schedule_delayed_work(&sync_cmos_work, 0); } #else -static inline void notify_cmos_timer(void) { } +void ntp_notify_cmos_timer(void) { } #endif @@ -687,8 +687,6 @@ int __do_adjtimex(struct timex *txc, struct timespec *ts, s32 *time_tai) if (!(time_status & STA_NANO)) txc->time.tv_usec /= NSEC_PER_USEC; - notify_cmos_timer(); - return result; } diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 48b9fffabdc2..947ba25a95a0 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1703,6 +1703,8 @@ int do_adjtimex(struct timex *txc) write_seqcount_end(&timekeeper_seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); + ntp_notify_cmos_timer(); + return ret; } -- cgit v1.2.3 From 331415ff16a12147d57d5c953f3a961b7ede348b Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 11 Sep 2013 21:56:50 +0200 Subject: HID: provide a helper for validating hid reports Many drivers need to validate the characteristics of their HID report during initialization to avoid misusing the reports. This adds a common helper to perform validation of the report exisitng, the field existing, and the expected number of values within the field. Signed-off-by: Kees Cook Cc: stable@vger.kernel.org Reviewed-by: Benjamin Tissoires Signed-off-by: Jiri Kosina --- drivers/hid/hid-core.c | 58 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/hid.h | 4 ++++ 2 files changed, 62 insertions(+) (limited to 'include/linux') diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index ae88a97f976e..be52c06dbe30 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -801,6 +801,64 @@ int hid_parse_report(struct hid_device *hid, __u8 *start, unsigned size) } EXPORT_SYMBOL_GPL(hid_parse_report); +static const char * const hid_report_names[] = { + "HID_INPUT_REPORT", + "HID_OUTPUT_REPORT", + "HID_FEATURE_REPORT", +}; +/** + * hid_validate_values - validate existing device report's value indexes + * + * @device: hid device + * @type: which report type to examine + * @id: which report ID to examine (0 for first) + * @field_index: which report field to examine + * @report_counts: expected number of values + * + * Validate the number of values in a given field of a given report, after + * parsing. + */ +struct hid_report *hid_validate_values(struct hid_device *hid, + unsigned int type, unsigned int id, + unsigned int field_index, + unsigned int report_counts) +{ + struct hid_report *report; + + if (type > HID_FEATURE_REPORT) { + hid_err(hid, "invalid HID report type %u\n", type); + return NULL; + } + + if (id >= HID_MAX_IDS) { + hid_err(hid, "invalid HID report id %u\n", id); + return NULL; + } + + /* + * Explicitly not using hid_get_report() here since it depends on + * ->numbered being checked, which may not always be the case when + * drivers go to access report values. + */ + report = hid->report_enum[type].report_id_hash[id]; + if (!report) { + hid_err(hid, "missing %s %u\n", hid_report_names[type], id); + return NULL; + } + if (report->maxfield <= field_index) { + hid_err(hid, "not enough fields in %s %u\n", + hid_report_names[type], id); + return NULL; + } + if (report->field[field_index]->report_count < report_counts) { + hid_err(hid, "not enough values in %s %u field %u\n", + hid_report_names[type], id, field_index); + return NULL; + } + return report; +} +EXPORT_SYMBOL_GPL(hid_validate_values); + /** * hid_open_report - open a driver-specific device report * diff --git a/include/linux/hid.h b/include/linux/hid.h index ee1ffc5e19c9..31b9d299ef6c 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -756,6 +756,10 @@ u8 *hid_alloc_report_buf(struct hid_report *report, gfp_t flags); struct hid_device *hid_allocate_device(void); struct hid_report *hid_register_report(struct hid_device *device, unsigned type, unsigned id); int hid_parse_report(struct hid_device *hid, __u8 *start, unsigned size); +struct hid_report *hid_validate_values(struct hid_device *hid, + unsigned int type, unsigned int id, + unsigned int field_index, + unsigned int report_counts); int hid_open_report(struct hid_device *device); int hid_check_keys_pressed(struct hid_device *hid); int hid_connect(struct hid_device *hid, unsigned int connect_mask); -- cgit v1.2.3 From 35e4237973665c8a1ad4e3f7a7cb87573deaa24a Mon Sep 17 00:00:00 2001 From: Joseph Gasparakis Date: Fri, 13 Sep 2013 07:34:13 -0700 Subject: vxlan: Fix sparse warnings This patch fixes sparse warnings when incorrectly handling the port number and using int instead of unsigned int iterating through &vn->sock_list[]. Keeping the port as __be16 also makes things clearer wrt endianess. Also, it was pointed out that vxlan_get_rx_port() had unnecessary checks which got removed. Signed-off-by: Joseph Gasparakis Signed-off-by: Jeff Kirsher Signed-off-by: David S. Miller --- drivers/net/vxlan.c | 18 ++++++++---------- include/linux/netdevice.h | 8 ++++---- 2 files changed, 12 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index bf64b4191dcc..2400b1beddd5 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -564,7 +564,7 @@ static void vxlan_notify_add_rx_port(struct sock *sk) struct net_device *dev; struct net *net = sock_net(sk); sa_family_t sa_family = sk->sk_family; - u16 port = htons(inet_sk(sk)->inet_sport); + __be16 port = inet_sk(sk)->inet_sport; rcu_read_lock(); for_each_netdev_rcu(net, dev) { @@ -581,7 +581,7 @@ static void vxlan_notify_del_rx_port(struct sock *sk) struct net_device *dev; struct net *net = sock_net(sk); sa_family_t sa_family = sk->sk_family; - u16 port = htons(inet_sk(sk)->inet_sport); + __be16 port = inet_sk(sk)->inet_sport; rcu_read_lock(); for_each_netdev_rcu(net, dev) { @@ -2021,7 +2021,8 @@ static struct device_type vxlan_type = { }; /* Calls the ndo_add_vxlan_port of the caller in order to - * supply the listening VXLAN udp ports. + * supply the listening VXLAN udp ports. Callers are expected + * to implement the ndo_add_vxlan_port. */ void vxlan_get_rx_port(struct net_device *dev) { @@ -2029,16 +2030,13 @@ void vxlan_get_rx_port(struct net_device *dev) struct net *net = dev_net(dev); struct vxlan_net *vn = net_generic(net, vxlan_net_id); sa_family_t sa_family; - u16 port; - int i; - - if (!dev || !dev->netdev_ops || !dev->netdev_ops->ndo_add_vxlan_port) - return; + __be16 port; + unsigned int i; spin_lock(&vn->sock_lock); for (i = 0; i < PORT_HASH_SIZE; ++i) { - hlist_for_each_entry_rcu(vs, vs_head(net, i), hlist) { - port = htons(inet_sk(vs->sock->sk)->inet_sport); + hlist_for_each_entry_rcu(vs, &vn->sock_list[i], hlist) { + port = inet_sk(vs->sock->sk)->inet_sport; sa_family = vs->sock->sk->sk_family; dev->netdev_ops->ndo_add_vxlan_port(dev, sa_family, port); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 041b42a305f6..3de49aca4519 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -950,14 +950,14 @@ struct netdev_phys_port_id { * multiple net devices on single physical port. * * void (*ndo_add_vxlan_port)(struct net_device *dev, - * sa_family_t sa_family, __u16 port); + * sa_family_t sa_family, __be16 port); * Called by vxlan to notiy a driver about the UDP port and socket * address family that vxlan is listnening to. It is called only when * a new port starts listening. The operation is protected by the * vxlan_net->sock_lock. * * void (*ndo_del_vxlan_port)(struct net_device *dev, - * sa_family_t sa_family, __u16 port); + * sa_family_t sa_family, __be16 port); * Called by vxlan to notify the driver about a UDP port and socket * address family that vxlan is not listening to anymore. The operation * is protected by the vxlan_net->sock_lock. @@ -1093,10 +1093,10 @@ struct net_device_ops { struct netdev_phys_port_id *ppid); void (*ndo_add_vxlan_port)(struct net_device *dev, sa_family_t sa_family, - __u16 port); + __be16 port); void (*ndo_del_vxlan_port)(struct net_device *dev, sa_family_t sa_family, - __u16 port); + __be16 port); }; /* -- cgit v1.2.3 From 0f1799ba1a5db4c48b72ac2da2dc70d8c190a73d Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Mon, 16 Sep 2013 20:04:53 +0200 Subject: netfilter: ipset: Consistent userspace testing with nomatch flag The "nomatch" commandline flag should invert the matching at testing, similarly to the --return-nomatch flag of the "set" match of iptables. Until now it worked with the elements with "nomatch" flag only. From now on it works with elements without the flag too, i.e: # ipset n test hash:net # ipset a test 10.0.0.0/24 nomatch # ipset t test 10.0.0.1 10.0.0.1 is NOT in set test. # ipset t test 10.0.0.1 nomatch 10.0.0.1 is in set test. # ipset a test 192.168.0.0/24 # ipset t test 192.168.0.1 192.168.0.1 is in set test. # ipset t test 192.168.0.1 nomatch 192.168.0.1 is NOT in set test. Before the patch the results were ... # ipset t test 192.168.0.1 192.168.0.1 is in set test. # ipset t test 192.168.0.1 nomatch 192.168.0.1 is in set test. Signed-off-by: Jozsef Kadlecsik --- include/linux/netfilter/ipset/ip_set.h | 6 ++++-- net/netfilter/ipset/ip_set_core.c | 3 +-- net/netfilter/ipset/ip_set_hash_ipportnet.c | 4 ++-- net/netfilter/ipset/ip_set_hash_net.c | 4 ++-- net/netfilter/ipset/ip_set_hash_netiface.c | 4 ++-- net/netfilter/ipset/ip_set_hash_netport.c | 4 ++-- 6 files changed, 13 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index d80e2753847c..9ac9fbde7b61 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -296,10 +296,12 @@ ip_set_eexist(int ret, u32 flags) /* Match elements marked with nomatch */ static inline bool -ip_set_enomatch(int ret, u32 flags, enum ipset_adt adt) +ip_set_enomatch(int ret, u32 flags, enum ipset_adt adt, struct ip_set *set) { return adt == IPSET_TEST && - ret == -ENOTEMPTY && ((flags >> 16) & IPSET_FLAG_NOMATCH); + (set->type->features & IPSET_TYPE_NOMATCH) && + ((flags >> 16) & IPSET_FLAG_NOMATCH) && + (ret > 0 || ret == -ENOTEMPTY); } /* Check the NLA_F_NET_BYTEORDER flag */ diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index f77139007983..c8c303c3386f 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1489,8 +1489,7 @@ ip_set_utest(struct sock *ctnl, struct sk_buff *skb, if (ret == -EAGAIN) ret = 1; - return (ret < 0 && ret != -ENOTEMPTY) ? ret : - ret > 0 ? 0 : -IPSET_ERR_EXIST; + return ret > 0 ? 0 : -IPSET_ERR_EXIST; } /* Get headed data of a set */ diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index c6a525373be4..f15f3e28b9c3 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -260,7 +260,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], e.ip = htonl(ip); e.ip2 = htonl(ip2_from & ip_set_hostmask(e.cidr + 1)); ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } @@ -544,7 +544,7 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index da740ceb56ae..223e9f546d0f 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -199,7 +199,7 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !tb[IPSET_ATTR_IP_TO]) { e.ip = htonl(ip & ip_set_hostmask(e.cidr)); ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret: ip_set_eexist(ret, flags) ? 0 : ret; } @@ -396,7 +396,7 @@ hash_net6_uadt(struct ip_set *set, struct nlattr *tb[], ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 84ae6f6ce624..7d798d5d5cd3 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -368,7 +368,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !tb[IPSET_ATTR_IP_TO]) { e.ip = htonl(ip & ip_set_hostmask(e.cidr)); ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } @@ -634,7 +634,7 @@ hash_netiface6_uadt(struct ip_set *set, struct nlattr *tb[], ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index 9a0869853be5..09d6690bee6f 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -244,7 +244,7 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !(with_ports || tb[IPSET_ATTR_IP_TO])) { e.ip = htonl(ip & ip_set_hostmask(e.cidr + 1)); ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } @@ -489,7 +489,7 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { ret = adtfn(set, &e, &ext, &ext, flags); - return ip_set_enomatch(ret, flags, adt) ? 1 : + return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; } -- cgit v1.2.3 From ba6a3541545542721ce821d1e7e5ce35752e6fdf Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Mon, 9 Sep 2013 13:52:33 +0200 Subject: KVM: mmu: allow page tables to be in read-only slots Page tables in a read-only memory slot will currently cause a triple fault because the page walker uses gfn_to_hva and it fails on such a slot. OVMF uses such a page table; however, real hardware seems to be fine with that as long as the accessed/dirty bits are set. Save whether the slot is readonly, and later check it when updating the accessed and dirty bits. Reviewed-by: Xiao Guangrong Reviewed-by: Gleb Natapov Signed-off-by: Paolo Bonzini --- arch/x86/kvm/paging_tmpl.h | 20 +++++++++++++++++++- include/linux/kvm_host.h | 1 + virt/kvm/kvm_main.c | 14 +++++++++----- 3 files changed, 29 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 043330159179..ad75d77999d0 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -99,6 +99,7 @@ struct guest_walker { pt_element_t prefetch_ptes[PTE_PREFETCH_NUM]; gpa_t pte_gpa[PT_MAX_FULL_LEVELS]; pt_element_t __user *ptep_user[PT_MAX_FULL_LEVELS]; + bool pte_writable[PT_MAX_FULL_LEVELS]; unsigned pt_access; unsigned pte_access; gfn_t gfn; @@ -235,6 +236,22 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu, if (pte == orig_pte) continue; + /* + * If the slot is read-only, simply do not process the accessed + * and dirty bits. This is the correct thing to do if the slot + * is ROM, and page tables in read-as-ROM/write-as-MMIO slots + * are only supported if the accessed and dirty bits are already + * set in the ROM (so that MMIO writes are never needed). + * + * Note that NPT does not allow this at all and faults, since + * it always wants nested page table entries for the guest + * page tables to be writable. And EPT works but will simply + * overwrite the read-only memory to set the accessed and dirty + * bits. + */ + if (unlikely(!walker->pte_writable[level - 1])) + continue; + ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index, orig_pte, pte); if (ret) return ret; @@ -309,7 +326,8 @@ retry_walk: goto error; real_gfn = gpa_to_gfn(real_gfn); - host_addr = gfn_to_hva(vcpu->kvm, real_gfn); + host_addr = gfn_to_hva_prot(vcpu->kvm, real_gfn, + &walker->pte_writable[walker->level - 1]); if (unlikely(kvm_is_error_hva(host_addr))) goto error; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index ca645a01d37a..0fbbc7aa02cb 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -533,6 +533,7 @@ int gfn_to_page_many_atomic(struct kvm *kvm, gfn_t gfn, struct page **pages, struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn); unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn); +unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable); unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn); void kvm_release_page_clean(struct page *page); void kvm_release_page_dirty(struct page *page); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index bf040c4e02b3..979bff485fb0 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1058,11 +1058,15 @@ unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn) EXPORT_SYMBOL_GPL(gfn_to_hva); /* - * The hva returned by this function is only allowed to be read. - * It should pair with kvm_read_hva() or kvm_read_hva_atomic(). + * If writable is set to false, the hva returned by this function is only + * allowed to be read. */ -static unsigned long gfn_to_hva_read(struct kvm *kvm, gfn_t gfn) +unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable) { + struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); + if (writable) + *writable = !memslot_is_readonly(slot); + return __gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, NULL, false); } @@ -1430,7 +1434,7 @@ int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int r; unsigned long addr; - addr = gfn_to_hva_read(kvm, gfn); + addr = gfn_to_hva_prot(kvm, gfn, NULL); if (kvm_is_error_hva(addr)) return -EFAULT; r = kvm_read_hva(data, (void __user *)addr + offset, len); @@ -1468,7 +1472,7 @@ int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data, gfn_t gfn = gpa >> PAGE_SHIFT; int offset = offset_in_page(gpa); - addr = gfn_to_hva_read(kvm, gfn); + addr = gfn_to_hva_prot(kvm, gfn, NULL); if (kvm_is_error_hva(addr)) return -EFAULT; pagefault_disable(); -- cgit v1.2.3 From 75afb352991ff1cd3cf5955bfe611de6d83a0c87 Mon Sep 17 00:00:00 2001 From: Jun'ichi Nomura Date: Sat, 21 Sep 2013 13:57:47 -0600 Subject: block: Add nr_bios to block_rq_remap tracepoint Adding the number of bios in a remapped request to 'block_rq_remap' tracepoint. Request remapper clones bios in a request to track the completion status of each bio. So the number of bios can be useful information for investigation. Related discussions: http://www.redhat.com/archives/dm-devel/2013-August/msg00084.html http://www.redhat.com/archives/dm-devel/2013-September/msg00024.html Signed-off-by: Jun'ichi Nomura Acked-by: Mike Snitzer Cc: Jens Axboe Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 11 +++++++++++ include/trace/events/block.h | 6 ++++-- 2 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2fdb4a451b49..0e6f765aa1f5 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -862,6 +862,17 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq) return blk_queue_get_max_sectors(q, rq->cmd_flags); } +static inline unsigned int blk_rq_count_bios(struct request *rq) +{ + unsigned int nr_bios = 0; + struct bio *bio; + + __rq_for_each_bio(bio, rq) + nr_bios++; + + return nr_bios; +} + /* * Request issue related functions. */ diff --git a/include/trace/events/block.h b/include/trace/events/block.h index 60ae7c3db912..4c2301d2ef1a 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -618,6 +618,7 @@ TRACE_EVENT(block_rq_remap, __field( unsigned int, nr_sector ) __field( dev_t, old_dev ) __field( sector_t, old_sector ) + __field( unsigned int, nr_bios ) __array( char, rwbs, RWBS_LEN) ), @@ -627,15 +628,16 @@ TRACE_EVENT(block_rq_remap, __entry->nr_sector = blk_rq_sectors(rq); __entry->old_dev = dev; __entry->old_sector = from; + __entry->nr_bios = blk_rq_count_bios(rq); blk_fill_rwbs(__entry->rwbs, rq->cmd_flags, blk_rq_bytes(rq)); ), - TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu", + TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs, (unsigned long long)__entry->sector, __entry->nr_sector, MAJOR(__entry->old_dev), MINOR(__entry->old_dev), - (unsigned long long)__entry->old_sector) + (unsigned long long)__entry->old_sector, __entry->nr_bios) ); #endif /* _TRACE_BLOCK_H */ -- cgit v1.2.3