From e6b72ee88a56bcfe63f72e9c30766484c45bec72 Mon Sep 17 00:00:00 2001 From: Artem Savkov Date: Tue, 26 Sep 2017 18:35:45 +0200 Subject: netfilter: ebtables: fix race condition in frame_filter_net_init() It is possible for ebt_in_hook to be triggered before ebt_table is assigned resulting in a NULL-pointer dereference. Make sure hooks are registered as the last step. Fixes: aee12a0a3727 ("ebtables: remove nf_hook_register usage") Signed-off-by: Artem Savkov Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_bridge/ebtables.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index 2c2a5514b0df..528b24c78308 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -108,9 +108,10 @@ struct ebt_table { #define EBT_ALIGN(s) (((s) + (__alignof__(struct _xt_align)-1)) & \ ~(__alignof__(struct _xt_align)-1)) -extern struct ebt_table *ebt_register_table(struct net *net, - const struct ebt_table *table, - const struct nf_hook_ops *); +extern int ebt_register_table(struct net *net, + const struct ebt_table *table, + const struct nf_hook_ops *ops, + struct ebt_table **res); extern void ebt_unregister_table(struct net *net, struct ebt_table *table, const struct nf_hook_ops *); extern unsigned int ebt_do_table(struct sk_buff *skb, -- cgit v1.3-8-gc7d7 From 192b2d78722ffea188e5ec6ae5d55010dce05a4b Mon Sep 17 00:00:00 2001 From: "K. Y. Srinivasan" Date: Fri, 29 Sep 2017 21:09:36 -0700 Subject: Drivers: hv: vmbus: Fix bugs in rescind handling This patch addresses the following bugs in the current rescind handling code: 1. Fixes a race condition where we may be invoking hv_process_channel_removal() on an already freed channel. 2. Prevents indefinite wait when rescinding sub-channels by correctly setting the probe_complete state. I would like to thank Dexuan for patiently reviewing earlier versions of this patch and identifying many of the issues fixed here. Greg, please apply this to 4.14-final. Fixes: '54a66265d675 ("Drivers: hv: vmbus: Fix rescind handling")' Signed-off-by: K. Y. Srinivasan Reviewed-by: Dexuan Cui Cc: stable@vger.kernel.org # (4.13 and above) Signed-off-by: Greg Kroah-Hartman --- drivers/hv/channel.c | 6 +++--- drivers/hv/channel_mgmt.c | 37 ++++++++++++++++++------------------- drivers/hv/vmbus_drv.c | 3 +-- include/linux/hyperv.h | 2 +- 4 files changed, 23 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c index efd5db743319..894b67ac2cae 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -640,6 +640,7 @@ void vmbus_close(struct vmbus_channel *channel) */ return; } + mutex_lock(&vmbus_connection.channel_mutex); /* * Close all the sub-channels first and then close the * primary channel. @@ -648,16 +649,15 @@ void vmbus_close(struct vmbus_channel *channel) cur_channel = list_entry(cur, struct vmbus_channel, sc_list); vmbus_close_internal(cur_channel); if (cur_channel->rescind) { - mutex_lock(&vmbus_connection.channel_mutex); - hv_process_channel_removal(cur_channel, + hv_process_channel_removal( cur_channel->offermsg.child_relid); - mutex_unlock(&vmbus_connection.channel_mutex); } } /* * Now close the primary. */ vmbus_close_internal(channel); + mutex_unlock(&vmbus_connection.channel_mutex); } EXPORT_SYMBOL_GPL(vmbus_close); diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index bcbb031f7263..018d2e0f8ec5 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -159,7 +159,7 @@ static void vmbus_rescind_cleanup(struct vmbus_channel *channel) spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags); - + channel->rescind = true; list_for_each_entry(msginfo, &vmbus_connection.chn_msg_list, msglistentry) { @@ -381,14 +381,21 @@ static void vmbus_release_relid(u32 relid) true); } -void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid) +void hv_process_channel_removal(u32 relid) { unsigned long flags; - struct vmbus_channel *primary_channel; + struct vmbus_channel *primary_channel, *channel; - BUG_ON(!channel->rescind); BUG_ON(!mutex_is_locked(&vmbus_connection.channel_mutex)); + /* + * Make sure channel is valid as we may have raced. + */ + channel = relid2channel(relid); + if (!channel) + return; + + BUG_ON(!channel->rescind); if (channel->target_cpu != get_cpu()) { put_cpu(); smp_call_function_single(channel->target_cpu, @@ -515,6 +522,7 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel) if (!fnew) { if (channel->sc_creation_callback != NULL) channel->sc_creation_callback(newchannel); + newchannel->probe_done = true; return; } @@ -834,7 +842,6 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr) { struct vmbus_channel_rescind_offer *rescind; struct vmbus_channel *channel; - unsigned long flags; struct device *dev; rescind = (struct vmbus_channel_rescind_offer *)hdr; @@ -873,16 +880,6 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr) return; } - spin_lock_irqsave(&channel->lock, flags); - channel->rescind = true; - spin_unlock_irqrestore(&channel->lock, flags); - - /* - * Now that we have posted the rescind state, perform - * rescind related cleanup. - */ - vmbus_rescind_cleanup(channel); - /* * Now wait for offer handling to complete. */ @@ -901,6 +898,7 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr) if (channel->device_obj) { if (channel->chn_rescind_callback) { channel->chn_rescind_callback(channel); + vmbus_rescind_cleanup(channel); return; } /* @@ -909,6 +907,7 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr) */ dev = get_device(&channel->device_obj->device); if (dev) { + vmbus_rescind_cleanup(channel); vmbus_device_unregister(channel->device_obj); put_device(dev); } @@ -921,16 +920,16 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr) * 1. Close all sub-channels first * 2. Then close the primary channel. */ + mutex_lock(&vmbus_connection.channel_mutex); + vmbus_rescind_cleanup(channel); if (channel->state == CHANNEL_OPEN_STATE) { /* * The channel is currently not open; * it is safe for us to cleanup the channel. */ - mutex_lock(&vmbus_connection.channel_mutex); - hv_process_channel_removal(channel, - channel->offermsg.child_relid); - mutex_unlock(&vmbus_connection.channel_mutex); + hv_process_channel_removal(rescind->child_relid); } + mutex_unlock(&vmbus_connection.channel_mutex); } } diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index a9d49f6f6501..937801ac2fe0 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -768,8 +768,7 @@ static void vmbus_device_release(struct device *device) struct vmbus_channel *channel = hv_dev->channel; mutex_lock(&vmbus_connection.channel_mutex); - hv_process_channel_removal(channel, - channel->offermsg.child_relid); + hv_process_channel_removal(channel->offermsg.child_relid); mutex_unlock(&vmbus_connection.channel_mutex); kfree(hv_dev); diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index c458d7b7ad19..6431087816ba 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1403,7 +1403,7 @@ extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf, const int *srv_version, int srv_vercnt, int *nego_fw_version, int *nego_srv_version); -void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid); +void hv_process_channel_removal(u32 relid); void vmbus_setevent(struct vmbus_channel *channel); /* -- cgit v1.3-8-gc7d7 From 98589a0998b8b13c4a8fa1ccb0e62751a019faa5 Mon Sep 17 00:00:00 2001 From: Shmulik Ladkani Date: Mon, 9 Oct 2017 15:27:15 +0300 Subject: netfilter: xt_bpf: Fix XT_BPF_MODE_FD_PINNED mode of 'xt_bpf_info_v1' Commit 2c16d6033264 ("netfilter: xt_bpf: support ebpf") introduced support for attaching an eBPF object by an fd, with the 'bpf_mt_check_v1' ABI expecting the '.fd' to be specified upon each IPT_SO_SET_REPLACE call. However this breaks subsequent iptables calls: # iptables -A INPUT -m bpf --object-pinned /sys/fs/bpf/xxx -j ACCEPT # iptables -A INPUT -s 5.6.7.8 -j ACCEPT iptables: Invalid argument. Run `dmesg' for more information. That's because iptables works by loading existing rules using IPT_SO_GET_ENTRIES to userspace, then issuing IPT_SO_SET_REPLACE with the replacement set. However, the loaded 'xt_bpf_info_v1' has an arbitrary '.fd' number (from the initial "iptables -m bpf" invocation) - so when 2nd invocation occurs, userspace passes a bogus fd number, which leads to 'bpf_mt_check_v1' to fail. One suggested solution [1] was to hack iptables userspace, to perform a "entries fixup" immediatley after IPT_SO_GET_ENTRIES, by opening a new, process-local fd per every 'xt_bpf_info_v1' entry seen. However, in [2] both Pablo Neira Ayuso and Willem de Bruijn suggested to depricate the xt_bpf_info_v1 ABI dealing with pinned ebpf objects. This fix changes the XT_BPF_MODE_FD_PINNED behavior to ignore the given '.fd' and instead perform an in-kernel lookup for the bpf object given the provided '.path'. It also defines an alias for the XT_BPF_MODE_FD_PINNED mode, named XT_BPF_MODE_PATH_PINNED, to better reflect the fact that the user is expected to provide the path of the pinned object. Existing XT_BPF_MODE_FD_ELF behavior (non-pinned fd mode) is preserved. References: [1] https://marc.info/?l=netfilter-devel&m=150564724607440&w=2 [2] https://marc.info/?l=netfilter-devel&m=150575727129880&w=2 Reported-by: Rafael Buchbinder Signed-off-by: Shmulik Ladkani Acked-by: Willem de Bruijn Acked-by: Daniel Borkmann Signed-off-by: Pablo Neira Ayuso --- include/linux/bpf.h | 5 +++++ include/uapi/linux/netfilter/xt_bpf.h | 1 + kernel/bpf/inode.c | 1 + net/netfilter/xt_bpf.c | 22 ++++++++++++++++++++-- 4 files changed, 27 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8390859e79e7..f1af7d63d678 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -368,6 +368,11 @@ static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages) { } +static inline int bpf_obj_get_user(const char __user *pathname) +{ + return -EOPNOTSUPP; +} + static inline struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key) { diff --git a/include/uapi/linux/netfilter/xt_bpf.h b/include/uapi/linux/netfilter/xt_bpf.h index b97725af2ac0..da161b56c79e 100644 --- a/include/uapi/linux/netfilter/xt_bpf.h +++ b/include/uapi/linux/netfilter/xt_bpf.h @@ -23,6 +23,7 @@ enum xt_bpf_modes { XT_BPF_MODE_FD_PINNED, XT_BPF_MODE_FD_ELF, }; +#define XT_BPF_MODE_PATH_PINNED XT_BPF_MODE_FD_PINNED struct xt_bpf_info_v1 { __u16 mode; diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index e833ed914358..be1dde967208 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -363,6 +363,7 @@ out: putname(pname); return ret; } +EXPORT_SYMBOL_GPL(bpf_obj_get_user); static void bpf_evict_inode(struct inode *inode) { diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c index 38986a95216c..29123934887b 100644 --- a/net/netfilter/xt_bpf.c +++ b/net/netfilter/xt_bpf.c @@ -8,6 +8,7 @@ */ #include +#include #include #include #include @@ -49,6 +50,22 @@ static int __bpf_mt_check_fd(int fd, struct bpf_prog **ret) return 0; } +static int __bpf_mt_check_path(const char *path, struct bpf_prog **ret) +{ + mm_segment_t oldfs = get_fs(); + int retval, fd; + + set_fs(KERNEL_DS); + fd = bpf_obj_get_user(path); + set_fs(oldfs); + if (fd < 0) + return fd; + + retval = __bpf_mt_check_fd(fd, ret); + sys_close(fd); + return retval; +} + static int bpf_mt_check(const struct xt_mtchk_param *par) { struct xt_bpf_info *info = par->matchinfo; @@ -66,9 +83,10 @@ static int bpf_mt_check_v1(const struct xt_mtchk_param *par) return __bpf_mt_check_bytecode(info->bpf_program, info->bpf_program_num_elem, &info->filter); - else if (info->mode == XT_BPF_MODE_FD_PINNED || - info->mode == XT_BPF_MODE_FD_ELF) + else if (info->mode == XT_BPF_MODE_FD_ELF) return __bpf_mt_check_fd(info->fd, &info->filter); + else if (info->mode == XT_BPF_MODE_PATH_PINNED) + return __bpf_mt_check_path(info->path, &info->filter); else return -EINVAL; } -- cgit v1.3-8-gc7d7 From d153b153446f7d8832bb2ebd92309c8a6003b3bb Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 27 Sep 2017 11:35:30 +0200 Subject: sched/core: Fix wake_affine() performance regression Eric reported a sysbench regression against commit: 3fed382b46ba ("sched/numa: Implement NUMA node level wake_affine()") Similarly, Rik was looking at the NAS-lu.C benchmark, which regressed against his v3.10 enterprise kernel. PRE (current tip/master): ivb-ep sysbench: 2: [30 secs] transactions: 64110 (2136.94 per sec.) 5: [30 secs] transactions: 143644 (4787.99 per sec.) 10: [30 secs] transactions: 274298 (9142.93 per sec.) 20: [30 secs] transactions: 418683 (13955.45 per sec.) 40: [30 secs] transactions: 320731 (10690.15 per sec.) 80: [30 secs] transactions: 355096 (11834.28 per sec.) hsw-ex NAS: OMP_PROC_BIND/lu.C.x_threads_144_run_1.log: Time in seconds = 18.01 OMP_PROC_BIND/lu.C.x_threads_144_run_2.log: Time in seconds = 17.89 OMP_PROC_BIND/lu.C.x_threads_144_run_3.log: Time in seconds = 17.93 lu.C.x_threads_144_run_1.log: Time in seconds = 434.68 lu.C.x_threads_144_run_2.log: Time in seconds = 405.36 lu.C.x_threads_144_run_3.log: Time in seconds = 433.83 POST (+patch): ivb-ep sysbench: 2: [30 secs] transactions: 64494 (2149.75 per sec.) 5: [30 secs] transactions: 145114 (4836.99 per sec.) 10: [30 secs] transactions: 278311 (9276.69 per sec.) 20: [30 secs] transactions: 437169 (14571.60 per sec.) 40: [30 secs] transactions: 669837 (22326.73 per sec.) 80: [30 secs] transactions: 631739 (21055.88 per sec.) hsw-ex NAS: lu.C.x_threads_144_run_1.log: Time in seconds = 23.36 lu.C.x_threads_144_run_2.log: Time in seconds = 22.96 lu.C.x_threads_144_run_3.log: Time in seconds = 22.52 This patch takes out all the shiny wake_affine() stuff and goes back to utter basics. Between the two CPUs involved with the wakeup (the CPU doing the wakeup and the CPU we ran on previously) pick the CPU we can run on _now_. This restores much of the regressions against the older kernels, but leaves some ground in the overloaded case. The default-enabled WA_WEIGHT (which will be introduced in the next patch) is an attempt to address the overloaded situation. Reported-by: Eric Farman Signed-off-by: Peter Zijlstra (Intel) Cc: Christian Borntraeger Cc: Linus Torvalds Cc: Matthew Rosato Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Cc: jinpuwang@gmail.com Cc: vcaputo@pengaru.com Fixes: 3fed382b46ba ("sched/numa: Implement NUMA node level wake_affine()") Signed-off-by: Ingo Molnar --- include/linux/sched/topology.h | 8 --- kernel/sched/fair.c | 126 +++++------------------------------------ kernel/sched/features.h | 1 + 3 files changed, 16 insertions(+), 119 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index d7b6dab956ec..7d065abc7a47 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -71,14 +71,6 @@ struct sched_domain_shared { atomic_t ref; atomic_t nr_busy_cpus; int has_idle_cores; - - /* - * Some variables from the most recent sd_lb_stats for this domain, - * used by wake_affine(). - */ - unsigned long nr_running; - unsigned long load; - unsigned long capacity; }; struct sched_domain { diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 70ba32e08a23..28cabed85387 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5356,115 +5356,36 @@ static int wake_wide(struct task_struct *p) return 1; } -struct llc_stats { - unsigned long nr_running; - unsigned long load; - unsigned long capacity; - int has_capacity; -}; - -static bool get_llc_stats(struct llc_stats *stats, int cpu) -{ - struct sched_domain_shared *sds = rcu_dereference(per_cpu(sd_llc_shared, cpu)); - - if (!sds) - return false; - - stats->nr_running = READ_ONCE(sds->nr_running); - stats->load = READ_ONCE(sds->load); - stats->capacity = READ_ONCE(sds->capacity); - stats->has_capacity = stats->nr_running < per_cpu(sd_llc_size, cpu); - - return true; -} - /* - * Can a task be moved from prev_cpu to this_cpu without causing a load - * imbalance that would trigger the load balancer? + * The purpose of wake_affine() is to quickly determine on which CPU we can run + * soonest. For the purpose of speed we only consider the waking and previous + * CPU. * - * Since we're running on 'stale' values, we might in fact create an imbalance - * but recomputing these values is expensive, as that'd mean iteration 2 cache - * domains worth of CPUs. + * wake_affine_idle() - only considers 'now', it check if the waking CPU is (or + * will be) idle. */ + static bool -wake_affine_llc(struct sched_domain *sd, struct task_struct *p, - int this_cpu, int prev_cpu, int sync) +wake_affine_idle(struct sched_domain *sd, struct task_struct *p, + int this_cpu, int prev_cpu, int sync) { - struct llc_stats prev_stats, this_stats; - s64 this_eff_load, prev_eff_load; - unsigned long task_load; - - if (!get_llc_stats(&prev_stats, prev_cpu) || - !get_llc_stats(&this_stats, this_cpu)) - return false; - - /* - * If sync wakeup then subtract the (maximum possible) - * effect of the currently running task from the load - * of the current LLC. - */ - if (sync) { - unsigned long current_load = task_h_load(current); - - /* in this case load hits 0 and this LLC is considered 'idle' */ - if (current_load > this_stats.load) - return true; - - this_stats.load -= current_load; - } - - /* - * The has_capacity stuff is not SMT aware, but by trying to balance - * the nr_running on both ends we try and fill the domain at equal - * rates, thereby first consuming cores before siblings. - */ - - /* if the old cache has capacity, stay there */ - if (prev_stats.has_capacity && prev_stats.nr_running < this_stats.nr_running+1) - return false; - - /* if this cache has capacity, come here */ - if (this_stats.has_capacity && this_stats.nr_running+1 < prev_stats.nr_running) + if (idle_cpu(this_cpu)) return true; - /* - * Check to see if we can move the load without causing too much - * imbalance. - */ - task_load = task_h_load(p); - - this_eff_load = 100; - this_eff_load *= prev_stats.capacity; - - prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2; - prev_eff_load *= this_stats.capacity; - - this_eff_load *= this_stats.load + task_load; - prev_eff_load *= prev_stats.load - task_load; + if (sync && cpu_rq(this_cpu)->nr_running == 1) + return true; - return this_eff_load <= prev_eff_load; + return false; } static int wake_affine(struct sched_domain *sd, struct task_struct *p, int prev_cpu, int sync) { int this_cpu = smp_processor_id(); - bool affine; - - /* - * Default to no affine wakeups; wake_affine() should not effect a task - * placement the load-balancer feels inclined to undo. The conservative - * option is therefore to not move tasks when they wake up. - */ - affine = false; + bool affine = false; - /* - * If the wakeup is across cache domains, try to evaluate if movement - * makes sense, otherwise rely on select_idle_siblings() to do - * placement inside the cache domain. - */ - if (!cpus_share_cache(prev_cpu, this_cpu)) - affine = wake_affine_llc(sd, p, this_cpu, prev_cpu, sync); + if (sched_feat(WA_IDLE) && !affine) + affine = wake_affine_idle(sd, p, this_cpu, prev_cpu, sync); schedstat_inc(p->se.statistics.nr_wakeups_affine_attempts); if (affine) { @@ -7600,7 +7521,6 @@ static inline enum fbq_type fbq_classify_rq(struct rq *rq) */ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sds) { - struct sched_domain_shared *shared = env->sd->shared; struct sched_domain *child = env->sd->child; struct sched_group *sg = env->sd->groups; struct sg_lb_stats *local = &sds->local_stat; @@ -7672,22 +7592,6 @@ next_group: if (env->dst_rq->rd->overload != overload) env->dst_rq->rd->overload = overload; } - - if (!shared) - return; - - /* - * Since these are sums over groups they can contain some CPUs - * multiple times for the NUMA domains. - * - * Currently only wake_affine_llc() and find_busiest_group() - * uses these numbers, only the last is affected by this problem. - * - * XXX fix that. - */ - WRITE_ONCE(shared->nr_running, sds->total_running); - WRITE_ONCE(shared->load, sds->total_load); - WRITE_ONCE(shared->capacity, sds->total_capacity); } /** diff --git a/kernel/sched/features.h b/kernel/sched/features.h index d3fb15555291..0a519f8c224d 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -81,3 +81,4 @@ SCHED_FEAT(RT_RUNTIME_SHARE, true) SCHED_FEAT(LB_MIN, false) SCHED_FEAT(ATTACH_AGE_LOAD, true) +SCHED_FEAT(WA_IDLE, true) -- cgit v1.3-8-gc7d7 From 8a1ac5dc7be09883051b1bf89a5e57d7ad850fa5 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 13 Oct 2017 15:57:40 -0700 Subject: include/linux/of.h: provide of_n_{addr,size}_cells wrappers for !CONFIG_OF The pci-rcar driver is enabled for compile tests, and this has shown that the driver cannot build without CONFIG_OF, following the inclusion of commit f8f2fe7355fb ("PCI: rcar: Use new OF interrupt mapping when possible"): drivers/pci/host/pcie-rcar.c: In function 'pci_dma_range_parser_init': drivers/pci/host/pcie-rcar.c:1039:2: error: implicit declaration of function 'of_n_addr_cells' [-Werror=implicit-function-declaration] parser->pna = of_n_addr_cells(node); ^ As pointed out by Ben Dooks and Geert Uytterhoeven, this is actually supposed to build fine, which we can achieve if we make the declaration of of_irq_parse_and_map_pci conditional on CONFIG_OF and provide an empty inline function otherwise, as we do for a lot of other of interfaces. This lets us build the rcar_pci driver again without CONFIG_OF for build testing. All platforms using this driver select OF, so this doesn't change anything for the users. [akpm@linux-foundation.org: be consistent with surrounding code] Link: http://lkml.kernel.org/r/20170911200805.3363318-1-arnd@arndb.de Fixes: c25da4778803 ("PCI: rcar: Add Renesas R-Car PCIe driver") Signed-off-by: Arnd Bergmann Reviewed-by: Frank Rowand Acked-by: Geert Uytterhoeven Cc: Bjorn Helgaas Cc: Magnus Damm Cc: Ben Dooks Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/of.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/of.h b/include/linux/of.h index cfc34117fc92..b240ed69dc96 100644 --- a/include/linux/of.h +++ b/include/linux/of.h @@ -734,6 +734,16 @@ static inline struct device_node *of_get_cpu_node(int cpu, return NULL; } +static inline int of_n_addr_cells(struct device_node *np) +{ + return 0; + +} +static inline int of_n_size_cells(struct device_node *np) +{ + return 0; +} + static inline int of_property_read_u64(const struct device_node *np, const char *propname, u64 *out_value) { -- cgit v1.3-8-gc7d7 From e8c97af0c1f23d6ffedcaa3918861f2595e1db62 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 13 Oct 2017 15:58:11 -0700 Subject: linux/kernel.h: add/correct kernel-doc notation Add kernel-doc notation for some macros. Correct kernel-doc comments & typos for a few macros. Link: http://lkml.kernel.org/r/76fa1403-1511-be4c-e9c4-456b43edfad3@infradead.org Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 90 +++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 74 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 0ad4c3044cf9..91189bb0c818 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -44,6 +44,12 @@ #define STACK_MAGIC 0xdeadbeef +/** + * REPEAT_BYTE - repeat the value @x multiple times as an unsigned long value + * @x: value to repeat + * + * NOTE: @x is not checked for > 0xff; larger values produce odd results. + */ #define REPEAT_BYTE(x) ((~0ul / 0xff) * (x)) /* @a is a power of 2 value */ @@ -57,6 +63,10 @@ #define READ 0 #define WRITE 1 +/** + * ARRAY_SIZE - get the number of elements in array @arr + * @arr: array to be sized + */ #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr)) #define u64_to_user_ptr(x) ( \ @@ -76,7 +86,15 @@ #define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1) #define round_down(x, y) ((x) & ~__round_mask(x, y)) +/** + * FIELD_SIZEOF - get the size of a struct's field + * @t: the target struct + * @f: the target struct's field + * Return: the size of @f in the struct definition without having a + * declared instance of @t. + */ #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) + #define DIV_ROUND_UP __KERNEL_DIV_ROUND_UP #define DIV_ROUND_DOWN_ULL(ll, d) \ @@ -107,7 +125,7 @@ /* * Divide positive or negative dividend by positive or negative divisor * and round to closest integer. Result is undefined for negative - * divisors if he dividend variable type is unsigned and for negative + * divisors if the dividend variable type is unsigned and for negative * dividends if the divisor variable type is unsigned. */ #define DIV_ROUND_CLOSEST(x, divisor)( \ @@ -247,13 +265,13 @@ extern int _cond_resched(void); * @ep_ro: right open interval endpoint * * Perform a "reciprocal multiplication" in order to "scale" a value into - * range [0, ep_ro), where the upper interval endpoint is right-open. + * range [0, @ep_ro), where the upper interval endpoint is right-open. * This is useful, e.g. for accessing a index of an array containing - * ep_ro elements, for example. Think of it as sort of modulus, only that + * @ep_ro elements, for example. Think of it as sort of modulus, only that * the result isn't that of modulo. ;) Note that if initial input is a * small value, then result will return 0. * - * Return: a result based on val in interval [0, ep_ro). + * Return: a result based on @val in interval [0, @ep_ro). */ static inline u32 reciprocal_scale(u32 val, u32 ep_ro) { @@ -618,8 +636,8 @@ do { \ * trace_printk - printf formatting in the ftrace buffer * @fmt: the printf format for printing * - * Note: __trace_printk is an internal function for trace_printk and - * the @ip is passed in via the trace_printk macro. + * Note: __trace_printk is an internal function for trace_printk() and + * the @ip is passed in via the trace_printk() macro. * * This function allows a kernel developer to debug fast path sections * that printk is not appropriate for. By scattering in various @@ -629,7 +647,7 @@ do { \ * This is intended as a debugging tool for the developer only. * Please refrain from leaving trace_printks scattered around in * your code. (Extra memory is used for special buffers that are - * allocated when trace_printk() is used) + * allocated when trace_printk() is used.) * * A little optization trick is done here. If there's only one * argument, there's no need to scan the string for printf formats. @@ -681,7 +699,7 @@ int __trace_printk(unsigned long ip, const char *fmt, ...); * the @ip is passed in via the trace_puts macro. * * This is similar to trace_printk() but is made for those really fast - * paths that a developer wants the least amount of "Heisenbug" affects, + * paths that a developer wants the least amount of "Heisenbug" effects, * where the processing of the print format is still too much. * * This function allows a kernel developer to debug fast path sections @@ -692,7 +710,7 @@ int __trace_printk(unsigned long ip, const char *fmt, ...); * This is intended as a debugging tool for the developer only. * Please refrain from leaving trace_puts scattered around in * your code. (Extra memory is used for special buffers that are - * allocated when trace_puts() is used) + * allocated when trace_puts() is used.) * * Returns: 0 if nothing was written, positive # if string was. * (1 when __trace_bputs is used, strlen(str) when __trace_puts is used) @@ -771,6 +789,12 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } t2 min2 = (y); \ (void) (&min1 == &min2); \ min1 < min2 ? min1 : min2; }) + +/** + * min - return minimum of two values of the same or compatible types + * @x: first value + * @y: second value + */ #define min(x, y) \ __min(typeof(x), typeof(y), \ __UNIQUE_ID(min1_), __UNIQUE_ID(min2_), \ @@ -781,12 +805,31 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } t2 max2 = (y); \ (void) (&max1 == &max2); \ max1 > max2 ? max1 : max2; }) + +/** + * max - return maximum of two values of the same or compatible types + * @x: first value + * @y: second value + */ #define max(x, y) \ __max(typeof(x), typeof(y), \ __UNIQUE_ID(max1_), __UNIQUE_ID(max2_), \ x, y) +/** + * min3 - return minimum of three values + * @x: first value + * @y: second value + * @z: third value + */ #define min3(x, y, z) min((typeof(x))min(x, y), z) + +/** + * max3 - return maximum of three values + * @x: first value + * @y: second value + * @z: third value + */ #define max3(x, y, z) max((typeof(x))max(x, y), z) /** @@ -805,8 +848,8 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } * @lo: lowest allowable value * @hi: highest allowable value * - * This macro does strict typechecking of lo/hi to make sure they are of the - * same type as val. See the unnecessary pointer comparisons. + * This macro does strict typechecking of @lo/@hi to make sure they are of the + * same type as @val. See the unnecessary pointer comparisons. */ #define clamp(val, lo, hi) min((typeof(val))max(val, lo), hi) @@ -816,11 +859,24 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } * * Or not use min/max/clamp at all, of course. */ + +/** + * min_t - return minimum of two values, using the specified type + * @type: data type to use + * @x: first value + * @y: second value + */ #define min_t(type, x, y) \ __min(type, type, \ __UNIQUE_ID(min1_), __UNIQUE_ID(min2_), \ x, y) +/** + * max_t - return maximum of two values, using the specified type + * @type: data type to use + * @x: first value + * @y: second value + */ #define max_t(type, x, y) \ __max(type, type, \ __UNIQUE_ID(min1_), __UNIQUE_ID(min2_), \ @@ -834,7 +890,7 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } * @hi: maximum allowable value * * This macro does no typechecking and uses temporary variables of type - * 'type' to make all the comparisons. + * @type to make all the comparisons. */ #define clamp_t(type, val, lo, hi) min_t(type, max_t(type, val, lo), hi) @@ -845,15 +901,17 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } * @hi: maximum allowable value * * This macro does no typechecking and uses temporary variables of whatever - * type the input argument 'val' is. This is useful when val is an unsigned - * type and min and max are literals that will otherwise be assigned a signed + * type the input argument @val is. This is useful when @val is an unsigned + * type and @lo and @hi are literals that will otherwise be assigned a signed * integer type. */ #define clamp_val(val, lo, hi) clamp_t(typeof(val), val, lo, hi) -/* - * swap - swap value of @a and @b +/** + * swap - swap values of @a and @b + * @a: first value + * @b: second value */ #define swap(a, b) \ do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) -- cgit v1.3-8-gc7d7 From f892760aa66a2d657deaf59538fb69433036767c Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 13 Oct 2017 15:58:15 -0700 Subject: fs/mpage.c: fix mpage_writepage() for pages with buffers When using FAT on a block device which supports rw_page, we can hit BUG_ON(!PageLocked(page)) in try_to_free_buffers(). This is because we call clean_buffers() after unlocking the page we've written. Introduce a new clean_page_buffers() which cleans all buffers associated with a page and call it from within bdev_write_page(). [akpm@linux-foundation.org: s/PAGE_SIZE/~0U/ per Linus and Matthew] Link: http://lkml.kernel.org/r/20171006211541.GA7409@bombadil.infradead.org Signed-off-by: Matthew Wilcox Reported-by: Toshi Kani Reported-by: OGAWA Hirofumi Tested-by: Toshi Kani Acked-by: Johannes Thumshirn Cc: Ross Zwisler Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/block_dev.c | 6 ++++-- fs/mpage.c | 14 +++++++++++--- include/linux/buffer_head.h | 1 + 3 files changed, 16 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/fs/block_dev.c b/fs/block_dev.c index 93d088ffc05c..789f55e851ae 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -716,10 +716,12 @@ int bdev_write_page(struct block_device *bdev, sector_t sector, set_page_writeback(page); result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, true); - if (result) + if (result) { end_page_writeback(page); - else + } else { + clean_page_buffers(page); unlock_page(page); + } blk_queue_exit(bdev->bd_queue); return result; } diff --git a/fs/mpage.c b/fs/mpage.c index 37bb77c1302c..c991faec70b9 100644 --- a/fs/mpage.c +++ b/fs/mpage.c @@ -468,6 +468,16 @@ static void clean_buffers(struct page *page, unsigned first_unmapped) try_to_free_buffers(page); } +/* + * For situations where we want to clean all buffers attached to a page. + * We don't need to calculate how many buffers are attached to the page, + * we just need to specify a number larger than the maximum number of buffers. + */ +void clean_page_buffers(struct page *page) +{ + clean_buffers(page, ~0U); +} + static int __mpage_writepage(struct page *page, struct writeback_control *wbc, void *data) { @@ -605,10 +615,8 @@ alloc_new: if (bio == NULL) { if (first_unmapped == blocks_per_page) { if (!bdev_write_page(bdev, blocks[0] << (blkbits - 9), - page, wbc)) { - clean_buffers(page, first_unmapped); + page, wbc)) goto out; - } } bio = mpage_alloc(bdev, blocks[0] << (blkbits - 9), BIO_MAX_PAGES, GFP_NOFS|__GFP_HIGH); diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index c8dae555eccf..446b24cac67d 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -232,6 +232,7 @@ int generic_write_end(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page *, void *); void page_zero_new_buffers(struct page *page, unsigned from, unsigned to); +void clean_page_buffers(struct page *page); int cont_write_begin(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page **, void **, get_block_t *, loff_t *); -- cgit v1.3-8-gc7d7 From ca182551857cc2c1e6a2b7f1e72090a137a15008 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Fri, 13 Oct 2017 15:58:22 -0700 Subject: kmemleak: clear stale pointers from task stacks Kmemleak considers any pointers on task stacks as references. This patch clears newly allocated and reused vmap stacks. Link: http://lkml.kernel.org/r/150728990124.744199.8403409836394318684.stgit@buzz Signed-off-by: Konstantin Khlebnikov Acked-by: Catalin Marinas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/thread_info.h | 2 +- kernel/fork.c | 4 ++++ 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 905d769d8ddc..5f7eeab990fe 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -42,7 +42,7 @@ enum { #define THREAD_ALIGN THREAD_SIZE #endif -#ifdef CONFIG_DEBUG_STACK_USAGE +#if IS_ENABLED(CONFIG_DEBUG_STACK_USAGE) || IS_ENABLED(CONFIG_DEBUG_KMEMLEAK) # define THREADINFO_GFP (GFP_KERNEL_ACCOUNT | __GFP_NOTRACK | \ __GFP_ZERO) #else diff --git a/kernel/fork.c b/kernel/fork.c index e702cb9ffbd8..07cc743698d3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -215,6 +215,10 @@ static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node) if (!s) continue; +#ifdef CONFIG_DEBUG_KMEMLEAK + /* Clear stale pointers from reused stack. */ + memset(s->addr, 0, THREAD_SIZE); +#endif tsk->stack_vm_area = s; return s->addr; } -- cgit v1.3-8-gc7d7