From 34c06254ff82a815fdccdfae7517a06c9b768cee Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 5 Nov 2015 00:12:24 -0500 Subject: cgroup: fix cftype->file_offset handling 6f60eade2433 ("cgroup: generalize obtaining the handles of and notifying cgroup files") introduced cftype->file_offset so that the handles for per-css file instances can be recorded. These handles then can be used, for example, to generate file modified notifications. Unfortunately, it made the wrong assumption that files are created once for a given css and removed on its destruction. Due to the dependencies among subsystems, a css may be hidden from userland and then later shown again. This is implemented by removing and re-creating the affected files, so the associated kernfs_node for a given cgroup file may change over time. This incorrect assumption led to the corruption of css->files lists. Reimplement cftype->file_offset handling so that cgroup_file->kn is protected by a lock and updated as files are created and destroyed. This also makes keeping them on per-cgroup list unnecessary. Signed-off-by: Tejun Heo Reported-by: James Sedgwick Fixes: 6f60eade2433 ("cgroup: generalize obtaining the handles of and notifying cgroup files") Acked-by: Johannes Weiner Acked-by: Zefan Li --- include/linux/cgroup-defs.h | 4 ---- include/linux/cgroup.h | 14 +------------- 2 files changed, 1 insertion(+), 17 deletions(-) (limited to 'include') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 60d44b26276d..869fd4a3d28e 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -90,7 +90,6 @@ enum { */ struct cgroup_file { /* do not access any fields from outside cgroup core */ - struct list_head node; /* anchored at css->files */ struct kernfs_node *kn; }; @@ -134,9 +133,6 @@ struct cgroup_subsys_state { */ u64 serial_nr; - /* all cgroup_files associated with this css */ - struct list_head files; - /* percpu_ref killing and RCU release */ struct rcu_head rcu_head; struct work_struct destroy_work; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 22e3754f89c5..f64083030ad5 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -88,6 +88,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from); int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_rm_cftypes(struct cftype *cfts); +void cgroup_file_notify(struct cgroup_file *cfile); char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen); int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry); @@ -516,19 +517,6 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp) pr_cont_kernfs_path(cgrp->kn); } -/** - * cgroup_file_notify - generate a file modified event for a cgroup_file - * @cfile: target cgroup_file - * - * @cfile must have been obtained by setting cftype->file_offset. - */ -static inline void cgroup_file_notify(struct cgroup_file *cfile) -{ - /* might not have been created due to one of the CFTYPE selector flags */ - if (cfile->kn) - kernfs_notify(cfile->kn); -} - #else /* !CONFIG_CGROUPS */ struct cgroup_subsys_state; -- cgit v1.2.3 From 614e4c4ebc75517295bccd29b20ddbc5b52af6fc Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Thu, 12 Nov 2015 11:00:04 +0100 Subject: perf/core: Robustify the perf_cgroup_from_task() RCU checks This patch reinforces the lockdep checks performed by perf_cgroup_from_tsk() by passing the perf_event_context whenever possible. It is okay to not hold the RCU read lock when we know we hold the ctx->lock. This patch makes sure this property holds. In some functions, such as perf_cgroup_sched_in(), we do not pass the context because we are sure we are holding the RCU read lock. Signed-off-by: Stephane Eranian Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vince Weaver Cc: edumazet@google.com Link: http://lkml.kernel.org/r/1447322404-10920-3-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/perf_event_intel_cqm.c | 2 +- include/linux/perf_event.h | 6 ++++-- kernel/events/core.c | 20 +++++++++++++------- 3 files changed, 18 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c index 377e8f8ed391..a316ca96f1b6 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c +++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c @@ -298,7 +298,7 @@ static bool __match_event(struct perf_event *a, struct perf_event *b) static inline struct perf_cgroup *event_to_cgroup(struct perf_event *event) { if (event->attach_state & PERF_ATTACH_TASK) - return perf_cgroup_from_task(event->hw.target); + return perf_cgroup_from_task(event->hw.target, event->ctx); return event->cgrp; } diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index d841d33bcdc9..f9828a48f16a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -697,9 +697,11 @@ struct perf_cgroup { * if there is no cgroup event for the current CPU context. */ static inline struct perf_cgroup * -perf_cgroup_from_task(struct task_struct *task) +perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx) { - return container_of(task_css(task, perf_event_cgrp_id), + return container_of(task_css_check(task, perf_event_cgrp_id, + ctx ? lockdep_is_held(&ctx->lock) + : true), struct perf_cgroup, css); } #endif /* CONFIG_CGROUP_PERF */ diff --git a/kernel/events/core.c b/kernel/events/core.c index 60e71ca42c22..1ac857aff7b0 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -435,7 +435,7 @@ static inline void update_cgrp_time_from_event(struct perf_event *event) if (!is_cgroup_event(event)) return; - cgrp = perf_cgroup_from_task(current); + cgrp = perf_cgroup_from_task(current, event->ctx); /* * Do not update time when cgroup is not active */ @@ -458,7 +458,7 @@ perf_cgroup_set_timestamp(struct task_struct *task, if (!task || !ctx->nr_cgroups) return; - cgrp = perf_cgroup_from_task(task); + cgrp = perf_cgroup_from_task(task, ctx); info = this_cpu_ptr(cgrp->info); info->timestamp = ctx->timestamp; } @@ -521,8 +521,10 @@ static void perf_cgroup_switch(struct task_struct *task, int mode) * set cgrp before ctxsw in to allow * event_filter_match() to not have to pass * task around + * we pass the cpuctx->ctx to perf_cgroup_from_task() + * because cgorup events are only per-cpu */ - cpuctx->cgrp = perf_cgroup_from_task(task); + cpuctx->cgrp = perf_cgroup_from_task(task, &cpuctx->ctx); cpu_ctx_sched_in(cpuctx, EVENT_ALL, task); } perf_pmu_enable(cpuctx->ctx.pmu); @@ -542,15 +544,17 @@ static inline void perf_cgroup_sched_out(struct task_struct *task, rcu_read_lock(); /* * we come here when we know perf_cgroup_events > 0 + * we do not need to pass the ctx here because we know + * we are holding the rcu lock */ - cgrp1 = perf_cgroup_from_task(task); + cgrp1 = perf_cgroup_from_task(task, NULL); /* * next is NULL when called from perf_event_enable_on_exec() * that will systematically cause a cgroup_switch() */ if (next) - cgrp2 = perf_cgroup_from_task(next); + cgrp2 = perf_cgroup_from_task(next, NULL); /* * only schedule out current cgroup events if we know @@ -572,11 +576,13 @@ static inline void perf_cgroup_sched_in(struct task_struct *prev, rcu_read_lock(); /* * we come here when we know perf_cgroup_events > 0 + * we do not need to pass the ctx here because we know + * we are holding the rcu lock */ - cgrp1 = perf_cgroup_from_task(task); + cgrp1 = perf_cgroup_from_task(task, NULL); /* prev can never be NULL */ - cgrp2 = perf_cgroup_from_task(prev); + cgrp2 = perf_cgroup_from_task(prev, NULL); /* * only need to schedule in cgroup events if we are changing -- cgit v1.2.3 From 90eec103b96e30401c0b846045bf8a1c7159b6da Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 16 Nov 2015 11:08:45 +0100 Subject: treewide: Remove old email address There were still a number of references to my old Red Hat email address in the kernel source. Remove these while keeping the Red Hat copyright notices intact. Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Signed-off-by: Ingo Molnar --- arch/blackfin/kernel/perf_event.c | 2 +- arch/sh/kernel/perf_event.c | 2 +- arch/sparc/kernel/perf_event.c | 2 +- arch/tile/kernel/perf_event.c | 2 +- arch/x86/kernel/cpu/perf_event.c | 2 +- arch/x86/kernel/cpu/perf_event.h | 2 +- arch/x86/kernel/irq_work.c | 2 +- include/asm-generic/tlb.h | 2 +- include/linux/jump_label.h | 2 +- include/linux/lockdep.h | 2 +- include/linux/proportions.h | 2 +- include/linux/uprobes.h | 2 +- kernel/events/callchain.c | 2 +- kernel/events/core.c | 2 +- kernel/events/ring_buffer.c | 2 +- kernel/events/uprobes.c | 2 +- kernel/irq_work.c | 2 +- kernel/jump_label.c | 2 +- kernel/locking/lockdep.c | 2 +- kernel/locking/lockdep_proc.c | 2 +- kernel/sched/clock.c | 2 +- kernel/sched/fair.c | 2 +- kernel/trace/trace_event_perf.c | 2 +- lib/btree.c | 2 +- lib/proportions.c | 2 +- mm/page-writeback.c | 2 +- 26 files changed, 26 insertions(+), 26 deletions(-) (limited to 'include') diff --git a/arch/blackfin/kernel/perf_event.c b/arch/blackfin/kernel/perf_event.c index 1e9c8b0bf486..170d786807c4 100644 --- a/arch/blackfin/kernel/perf_event.c +++ b/arch/blackfin/kernel/perf_event.c @@ -14,7 +14,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, * * ppc: diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c index 7cfd7f153966..4dca18347ee9 100644 --- a/arch/sh/kernel/perf_event.c +++ b/arch/sh/kernel/perf_event.c @@ -10,7 +10,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, * * ppc: diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c index b0da5aedb336..3091267c5cc3 100644 --- a/arch/sparc/kernel/perf_event.c +++ b/arch/sparc/kernel/perf_event.c @@ -9,7 +9,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra */ #include diff --git a/arch/tile/kernel/perf_event.c b/arch/tile/kernel/perf_event.c index bb509cee3b59..8767060d70fb 100644 --- a/arch/tile/kernel/perf_event.c +++ b/arch/tile/kernel/perf_event.c @@ -21,7 +21,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, * Copyright (C) 2009 Google, Inc., Stephane Eranian */ diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index 4562cf070c27..2bf79d7c97df 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -5,7 +5,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, * Copyright (C) 2009 Google, Inc., Stephane Eranian * diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index ffa7a92025e1..ab18b8a91583 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -5,7 +5,7 @@ * Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar * Copyright (C) 2009 Jaswinder Singh Rajput * Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter - * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra * Copyright (C) 2009 Intel Corporation, * Copyright (C) 2009 Google, Inc., Stephane Eranian * diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c index dc5fa6a1e8d6..3512ba607361 100644 --- a/arch/x86/kernel/irq_work.c +++ b/arch/x86/kernel/irq_work.c @@ -1,7 +1,7 @@ /* * x86 specific code for irq_work * - * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra */ #include diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index db284bff29dc..9dbb739cafa0 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -5,7 +5,7 @@ * Copyright 2001 Red Hat, Inc. * Based on code from mm/memory.c Copyright Linus Torvalds and others. * - * Copyright 2011 Red Hat, Inc., Peter Zijlstra + * Copyright 2011 Red Hat, Inc., Peter Zijlstra * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h index 8dde55974f18..0536524bb9eb 100644 --- a/include/linux/jump_label.h +++ b/include/linux/jump_label.h @@ -5,7 +5,7 @@ * Jump label support * * Copyright (C) 2009-2012 Jason Baron - * Copyright (C) 2011-2012 Peter Zijlstra + * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra * * DEPRECATED API: * diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 70400dc7660f..c57e424d914b 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -2,7 +2,7 @@ * Runtime locking correctness validator * * Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * see Documentation/locking/lockdep-design.txt for more details. */ diff --git a/include/linux/proportions.h b/include/linux/proportions.h index 5440f64d2942..21221338ad18 100644 --- a/include/linux/proportions.h +++ b/include/linux/proportions.h @@ -1,7 +1,7 @@ /* * FLoating proportions * - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * This file contains the public data structure and API definitions. */ diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 0bdc72f36905..4a29c75b146e 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -21,7 +21,7 @@ * Authors: * Srikar Dronamraju * Jim Keniston - * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra */ #include diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c index d659487254d5..9c418002b8c1 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -3,7 +3,7 @@ * * Copyright (C) 2008 Thomas Gleixner * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar - * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra * Copyright © 2009 Paul Mackerras, IBM Corp. * * For licensing details see kernel-base/COPYING diff --git a/kernel/events/core.c b/kernel/events/core.c index 1ac857aff7b0..5854fcf7f05a 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3,7 +3,7 @@ * * Copyright (C) 2008 Thomas Gleixner * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar - * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra * Copyright © 2009 Paul Mackerras, IBM Corp. * * For licensing details see kernel-base/COPYING diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index b5d1ea79c595..adfdc0536117 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -3,7 +3,7 @@ * * Copyright (C) 2008 Thomas Gleixner * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar - * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra * Copyright © 2009 Paul Mackerras, IBM Corp. * * For licensing details see kernel-base/COPYING diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 4e5e9798aa0c..7dad84913abf 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -19,7 +19,7 @@ * Authors: * Srikar Dronamraju * Jim Keniston - * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra */ #include diff --git a/kernel/irq_work.c b/kernel/irq_work.c index cbf9fb899d92..bcf107ce0854 100644 --- a/kernel/irq_work.c +++ b/kernel/irq_work.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra * * Provides a framework for enqueueing and running callbacks from hardirq * context. The enqueueing is NMI-safe. diff --git a/kernel/jump_label.c b/kernel/jump_label.c index f7dd15d537f9..05254eeb4b4e 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -2,7 +2,7 @@ * jump label support * * Copyright (C) 2009 Jason Baron - * Copyright (C) 2011 Peter Zijlstra + * Copyright (C) 2011 Peter Zijlstra * */ #include diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index deae3907ac1e..60ace56618f6 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -6,7 +6,7 @@ * Started by Ingo Molnar: * * Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * this code maps all the lock dependencies as they occur in a live kernel * and will warn about the following classes of locking bugs: diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index d83d798bef95..dbb61a302548 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -6,7 +6,7 @@ * Started by Ingo Molnar: * * Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * Code for /proc/lockdep and /proc/lockdep_stats: * diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index c0a205101c23..caf4041f5b0a 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -1,7 +1,7 @@ /* * sched_clock for unstable cpu clocks * - * Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra * * Updates and enhancements: * Copyright (C) 2008 Red Hat, Inc. Steven Rostedt diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index f04fda8f669c..90e26b11deaa 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -17,7 +17,7 @@ * Copyright (C) 2007, Thomas Gleixner * * Adaptive scheduling granularity, math enhancements by Peter Zijlstra - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra */ #include diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index abfc903e741e..cc9f7a9319be 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -1,7 +1,7 @@ /* * trace event based perf event profiling/tracing * - * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra + * Copyright (C) 2009 Red Hat Inc, Peter Zijlstra * Copyright (C) 2009-2010 Frederic Weisbecker */ diff --git a/lib/btree.c b/lib/btree.c index 4264871ea1a0..f93a945274af 100644 --- a/lib/btree.c +++ b/lib/btree.c @@ -5,7 +5,7 @@ * * Copyright (c) 2007-2008 Joern Engel * Bits and pieces stolen from Peter Zijlstra's code, which is - * Copyright 2007, Red Hat Inc. Peter Zijlstra + * Copyright 2007, Red Hat Inc. Peter Zijlstra * GPLv2 * * see http://programming.kicks-ass.net/kernel-patches/vma_lookup/btree.patch diff --git a/lib/proportions.c b/lib/proportions.c index 6f724298f67a..efa54f259ea9 100644 --- a/lib/proportions.c +++ b/lib/proportions.c @@ -1,7 +1,7 @@ /* * Floating proportions * - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * Description: * diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 3e4d65445fa7..d15d88c8efa1 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2,7 +2,7 @@ * mm/page-writeback.c * * Copyright (C) 2002, Linus Torvalds. - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * Contains functions related to writing back dirty pages at the * address_space level. -- cgit v1.2.3 From 1f7dd3e5a6e4f093017fff12232572ee1aa4639b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Dec 2015 10:18:21 -0500 Subject: cgroup: fix handling of multi-destination migration from subtree_control enabling Consider the following v2 hierarchy. P0 (+memory) --- P1 (-memory) --- A \- B P0 has memory enabled in its subtree_control while P1 doesn't. If both A and B contain processes, they would belong to the memory css of P1. Now if memory is enabled on P1's subtree_control, memory csses should be created on both A and B and A's processes should be moved to the former and B's processes the latter. IOW, enabling controllers can cause atomic migrations into different csses. The core cgroup migration logic has been updated accordingly but the controller migration methods haven't and still assume that all tasks migrate to a single target css; furthermore, the methods were fed the css in which subtree_control was updated which is the parent of the target csses. pids controller depends on the migration methods to move charges and this made the controller attribute charges to the wrong csses often triggering the following warning by driving a counter negative. WARNING: CPU: 1 PID: 1 at kernel/cgroup_pids.c:97 pids_cancel.constprop.6+0x31/0x40() Modules linked in: CPU: 1 PID: 1 Comm: systemd Not tainted 4.4.0-rc1+ #29 ... ffffffff81f65382 ffff88007c043b90 ffffffff81551ffc 0000000000000000 ffff88007c043bc8 ffffffff810de202 ffff88007a752000 ffff88007a29ab00 ffff88007c043c80 ffff88007a1d8400 0000000000000001 ffff88007c043bd8 Call Trace: [] dump_stack+0x4e/0x82 [] warn_slowpath_common+0x82/0xc0 [] warn_slowpath_null+0x1a/0x20 [] pids_cancel.constprop.6+0x31/0x40 [] pids_can_attach+0x6d/0xf0 [] cgroup_taskset_migrate+0x6c/0x330 [] cgroup_migrate+0xf5/0x190 [] cgroup_attach_task+0x176/0x200 [] __cgroup_procs_write+0x2ad/0x460 [] cgroup_procs_write+0x14/0x20 [] cgroup_file_write+0x35/0x1c0 [] kernfs_fop_write+0x141/0x190 [] __vfs_write+0x28/0xe0 [] vfs_write+0xac/0x1a0 [] SyS_write+0x49/0xb0 [] entry_SYSCALL_64_fastpath+0x12/0x76 This patch fixes the bug by removing @css parameter from the three migration methods, ->can_attach, ->cancel_attach() and ->attach() and updating cgroup_taskset iteration helpers also return the destination css in addition to the task being migrated. All controllers are updated accordingly. * Controllers which don't care whether there are one or multiple target csses can be converted trivially. cpu, io, freezer, perf, netclassid and netprio fall in this category. * cpuset's current implementation assumes that there's single source and destination and thus doesn't support v2 hierarchy already. The only change made by this patchset is how that single destination css is obtained. * memory migration path already doesn't do anything on v2. How the single destination css is obtained is updated and the prep stage of mem_cgroup_can_attach() is reordered to accomodate the change. * pids is the only controller which was affected by this bug. It now correctly handles multi-destination migrations and no longer causes counter underflow from incorrect accounting. Signed-off-by: Tejun Heo Reported-and-tested-by: Daniel Wagner Cc: Aleksa Sarai --- block/blk-cgroup.c | 6 +++--- include/linux/cgroup-defs.h | 9 +++------ include/linux/cgroup.h | 33 +++++++++++++++++++++----------- kernel/cgroup.c | 43 +++++++++++++++++++++++++++++++++--------- kernel/cgroup_freezer.c | 6 +++--- kernel/cgroup_pids.c | 16 ++++++++-------- kernel/cpuset.c | 33 ++++++++++++++++++++------------ kernel/events/core.c | 6 +++--- kernel/sched/core.c | 12 ++++++------ mm/memcontrol.c | 45 ++++++++++++++++++++++---------------------- net/core/netclassid_cgroup.c | 11 ++++++----- net/core/netprio_cgroup.c | 9 +++++---- 12 files changed, 137 insertions(+), 92 deletions(-) (limited to 'include') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 5bcdfc10c23a..5a37188b559f 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1127,15 +1127,15 @@ void blkcg_exit_queue(struct request_queue *q) * of the main cic data structures. For now we allow a task to change * its cgroup only if it's the only owner of its ioc. */ -static int blkcg_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int blkcg_can_attach(struct cgroup_taskset *tset) { struct task_struct *task; + struct cgroup_subsys_state *dst_css; struct io_context *ioc; int ret = 0; /* task_lock() is needed to avoid races with exit_io_context() */ - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, dst_css, tset) { task_lock(task); ioc = task->io_context; if (ioc && atomic_read(&ioc->nr_tasks) > 1) diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 869fd4a3d28e..06b77f9dd3f2 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -422,12 +422,9 @@ struct cgroup_subsys { void (*css_reset)(struct cgroup_subsys_state *css); void (*css_e_css_changed)(struct cgroup_subsys_state *css); - int (*can_attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); - void (*cancel_attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); - void (*attach)(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset); + int (*can_attach)(struct cgroup_taskset *tset); + void (*cancel_attach)(struct cgroup_taskset *tset); + void (*attach)(struct cgroup_taskset *tset); int (*can_fork)(struct task_struct *task, void **priv_p); void (*cancel_fork)(struct task_struct *task, void *priv); void (*fork)(struct task_struct *task, void *priv); diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index f64083030ad5..cb91b44f5f78 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -120,8 +120,10 @@ struct cgroup_subsys_state *css_rightmost_descendant(struct cgroup_subsys_state struct cgroup_subsys_state *css_next_descendant_post(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *css); -struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset); -struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset); +struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, + struct cgroup_subsys_state **dst_cssp); +struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, + struct cgroup_subsys_state **dst_cssp); void css_task_iter_start(struct cgroup_subsys_state *css, struct css_task_iter *it); @@ -236,30 +238,39 @@ void css_task_iter_end(struct css_task_iter *it); /** * cgroup_taskset_for_each - iterate cgroup_taskset * @task: the loop cursor + * @dst_css: the destination css * @tset: taskset to iterate * * @tset may contain multiple tasks and they may belong to multiple - * processes. When there are multiple tasks in @tset, if a task of a - * process is in @tset, all tasks of the process are in @tset. Also, all - * are guaranteed to share the same source and destination csses. + * processes. + * + * On the v2 hierarchy, there may be tasks from multiple processes and they + * may not share the source or destination csses. + * + * On traditional hierarchies, when there are multiple tasks in @tset, if a + * task of a process is in @tset, all tasks of the process are in @tset. + * Also, all are guaranteed to share the same source and destination csses. * * Iteration is not in any specific order. */ -#define cgroup_taskset_for_each(task, tset) \ - for ((task) = cgroup_taskset_first((tset)); (task); \ - (task) = cgroup_taskset_next((tset))) +#define cgroup_taskset_for_each(task, dst_css, tset) \ + for ((task) = cgroup_taskset_first((tset), &(dst_css)); \ + (task); \ + (task) = cgroup_taskset_next((tset), &(dst_css))) /** * cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset * @leader: the loop cursor + * @dst_css: the destination css * @tset: takset to iterate * * Iterate threadgroup leaders of @tset. For single-task migrations, @tset * may not contain any. */ -#define cgroup_taskset_for_each_leader(leader, tset) \ - for ((leader) = cgroup_taskset_first((tset)); (leader); \ - (leader) = cgroup_taskset_next((tset))) \ +#define cgroup_taskset_for_each_leader(leader, dst_css, tset) \ + for ((leader) = cgroup_taskset_first((tset), &(dst_css)); \ + (leader); \ + (leader) = cgroup_taskset_next((tset), &(dst_css))) \ if ((leader) != (leader)->group_leader) \ ; \ else diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 5cea63fe4095..470f6536b9e8 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2237,6 +2237,9 @@ struct cgroup_taskset { struct list_head src_csets; struct list_head dst_csets; + /* the subsys currently being processed */ + int ssid; + /* * Fields for cgroup_taskset_*() iteration. * @@ -2299,25 +2302,29 @@ static void cgroup_taskset_add(struct task_struct *task, /** * cgroup_taskset_first - reset taskset and return the first task * @tset: taskset of interest + * @dst_cssp: output variable for the destination css * * @tset iteration is initialized and the first task is returned. */ -struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset) +struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, + struct cgroup_subsys_state **dst_cssp) { tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node); tset->cur_task = NULL; - return cgroup_taskset_next(tset); + return cgroup_taskset_next(tset, dst_cssp); } /** * cgroup_taskset_next - iterate to the next task in taskset * @tset: taskset of interest + * @dst_cssp: output variable for the destination css * * Return the next task in @tset. Iteration must have been initialized * with cgroup_taskset_first(). */ -struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset) +struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, + struct cgroup_subsys_state **dst_cssp) { struct css_set *cset = tset->cur_cset; struct task_struct *task = tset->cur_task; @@ -2332,6 +2339,18 @@ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset) if (&task->cg_list != &cset->mg_tasks) { tset->cur_cset = cset; tset->cur_task = task; + + /* + * This function may be called both before and + * after cgroup_taskset_migrate(). The two cases + * can be distinguished by looking at whether @cset + * has its ->mg_dst_cset set. + */ + if (cset->mg_dst_cset) + *dst_cssp = cset->mg_dst_cset->subsys[tset->ssid]; + else + *dst_cssp = cset->subsys[tset->ssid]; + return task; } @@ -2367,7 +2386,8 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset, /* check that we can legitimately attach to the cgroup */ for_each_e_css(css, i, dst_cgrp) { if (css->ss->can_attach) { - ret = css->ss->can_attach(css, tset); + tset->ssid = i; + ret = css->ss->can_attach(tset); if (ret) { failed_css = css; goto out_cancel_attach; @@ -2400,9 +2420,12 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset, */ tset->csets = &tset->dst_csets; - for_each_e_css(css, i, dst_cgrp) - if (css->ss->attach) - css->ss->attach(css, tset); + for_each_e_css(css, i, dst_cgrp) { + if (css->ss->attach) { + tset->ssid = i; + css->ss->attach(tset); + } + } ret = 0; goto out_release_tset; @@ -2411,8 +2434,10 @@ out_cancel_attach: for_each_e_css(css, i, dst_cgrp) { if (css == failed_css) break; - if (css->ss->cancel_attach) - css->ss->cancel_attach(css, tset); + if (css->ss->cancel_attach) { + tset->ssid = i; + css->ss->cancel_attach(tset); + } } out_release_tset: spin_lock_bh(&css_set_lock); diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index ff02a8e51bb3..2d3df82c54f2 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -155,10 +155,10 @@ static void freezer_css_free(struct cgroup_subsys_state *css) * @freezer->lock. freezer_attach() makes the new tasks conform to the * current state and all following state changes can see the new tasks. */ -static void freezer_attach(struct cgroup_subsys_state *new_css, - struct cgroup_taskset *tset) +static void freezer_attach(struct cgroup_taskset *tset) { struct task_struct *task; + struct cgroup_subsys_state *new_css; mutex_lock(&freezer_mutex); @@ -172,7 +172,7 @@ static void freezer_attach(struct cgroup_subsys_state *new_css, * current state before executing the following - !frozen tasks may * be visible in a FROZEN cgroup and frozen tasks in a THAWED one. */ - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, new_css, tset) { struct freezer *freezer = css_freezer(new_css); if (!(freezer->state & CGROUP_FREEZING)) { diff --git a/kernel/cgroup_pids.c b/kernel/cgroup_pids.c index de3359a48dbb..8e27fc5dbb20 100644 --- a/kernel/cgroup_pids.c +++ b/kernel/cgroup_pids.c @@ -162,13 +162,13 @@ revert: return -EAGAIN; } -static int pids_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int pids_can_attach(struct cgroup_taskset *tset) { - struct pids_cgroup *pids = css_pids(css); struct task_struct *task; + struct cgroup_subsys_state *dst_css; - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, dst_css, tset) { + struct pids_cgroup *pids = css_pids(dst_css); struct cgroup_subsys_state *old_css; struct pids_cgroup *old_pids; @@ -187,13 +187,13 @@ static int pids_can_attach(struct cgroup_subsys_state *css, return 0; } -static void pids_cancel_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void pids_cancel_attach(struct cgroup_taskset *tset) { - struct pids_cgroup *pids = css_pids(css); struct task_struct *task; + struct cgroup_subsys_state *dst_css; - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, dst_css, tset) { + struct pids_cgroup *pids = css_pids(dst_css); struct cgroup_subsys_state *old_css; struct pids_cgroup *old_pids; diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 10ae73611d80..02a8ea5c9963 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1429,15 +1429,16 @@ static int fmeter_getrate(struct fmeter *fmp) static struct cpuset *cpuset_attach_old_cs; /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ -static int cpuset_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int cpuset_can_attach(struct cgroup_taskset *tset) { - struct cpuset *cs = css_cs(css); + struct cgroup_subsys_state *css; + struct cpuset *cs; struct task_struct *task; int ret; /* used later by cpuset_attach() */ - cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset)); + cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css)); + cs = css_cs(css); mutex_lock(&cpuset_mutex); @@ -1447,7 +1448,7 @@ static int cpuset_can_attach(struct cgroup_subsys_state *css, (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))) goto out_unlock; - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, css, tset) { ret = task_can_attach(task, cs->cpus_allowed); if (ret) goto out_unlock; @@ -1467,9 +1468,14 @@ out_unlock: return ret; } -static void cpuset_cancel_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void cpuset_cancel_attach(struct cgroup_taskset *tset) { + struct cgroup_subsys_state *css; + struct cpuset *cs; + + cgroup_taskset_first(tset, &css); + cs = css_cs(css); + mutex_lock(&cpuset_mutex); css_cs(css)->attach_in_progress--; mutex_unlock(&cpuset_mutex); @@ -1482,16 +1488,19 @@ static void cpuset_cancel_attach(struct cgroup_subsys_state *css, */ static cpumask_var_t cpus_attach; -static void cpuset_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void cpuset_attach(struct cgroup_taskset *tset) { /* static buf protected by cpuset_mutex */ static nodemask_t cpuset_attach_nodemask_to; struct task_struct *task; struct task_struct *leader; - struct cpuset *cs = css_cs(css); + struct cgroup_subsys_state *css; + struct cpuset *cs; struct cpuset *oldcs = cpuset_attach_old_cs; + cgroup_taskset_first(tset, &css); + cs = css_cs(css); + mutex_lock(&cpuset_mutex); /* prepare for attach */ @@ -1502,7 +1511,7 @@ static void cpuset_attach(struct cgroup_subsys_state *css, guarantee_online_mems(cs, &cpuset_attach_nodemask_to); - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, css, tset) { /* * can_attach beforehand should guarantee that this doesn't * fail. TODO: have a better way to handle failure here @@ -1518,7 +1527,7 @@ static void cpuset_attach(struct cgroup_subsys_state *css, * sleep and should be moved outside migration path proper. */ cpuset_attach_nodemask_to = cs->effective_mems; - cgroup_taskset_for_each_leader(leader, tset) { + cgroup_taskset_for_each_leader(leader, css, tset) { struct mm_struct *mm = get_task_mm(leader); if (mm) { diff --git a/kernel/events/core.c b/kernel/events/core.c index 36babfd20648..026305dfe523 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -9456,12 +9456,12 @@ static int __perf_cgroup_move(void *info) return 0; } -static void perf_cgroup_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void perf_cgroup_attach(struct cgroup_taskset *tset) { struct task_struct *task; + struct cgroup_subsys_state *css; - cgroup_taskset_for_each(task, tset) + cgroup_taskset_for_each(task, css, tset) task_function_call(task, __perf_cgroup_move, task); } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 4d568ac9319e..a9db4819e586 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -8217,12 +8217,12 @@ static void cpu_cgroup_fork(struct task_struct *task, void *private) sched_move_task(task); } -static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int cpu_cgroup_can_attach(struct cgroup_taskset *tset) { struct task_struct *task; + struct cgroup_subsys_state *css; - cgroup_taskset_for_each(task, tset) { + cgroup_taskset_for_each(task, css, tset) { #ifdef CONFIG_RT_GROUP_SCHED if (!sched_rt_can_attach(css_tg(css), task)) return -EINVAL; @@ -8235,12 +8235,12 @@ static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css, return 0; } -static void cpu_cgroup_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void cpu_cgroup_attach(struct cgroup_taskset *tset) { struct task_struct *task; + struct cgroup_subsys_state *css; - cgroup_taskset_for_each(task, tset) + cgroup_taskset_for_each(task, css, tset) sched_move_task(task); } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9acfb165eb52..c92a65b2b4ab 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4779,23 +4779,18 @@ static void mem_cgroup_clear_mc(void) spin_unlock(&mc.lock); } -static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int mem_cgroup_can_attach(struct cgroup_taskset *tset) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct cgroup_subsys_state *css; + struct mem_cgroup *memcg; struct mem_cgroup *from; struct task_struct *leader, *p; struct mm_struct *mm; unsigned long move_flags; int ret = 0; - /* - * We are now commited to this value whatever it is. Changes in this - * tunable will only affect upcoming migrations, not the current one. - * So we need to save it, and keep it going. - */ - move_flags = READ_ONCE(memcg->move_charge_at_immigrate); - if (!move_flags) + /* charge immigration isn't supported on the default hierarchy */ + if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return 0; /* @@ -4805,13 +4800,23 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, * multiple. */ p = NULL; - cgroup_taskset_for_each_leader(leader, tset) { + cgroup_taskset_for_each_leader(leader, css, tset) { WARN_ON_ONCE(p); p = leader; + memcg = mem_cgroup_from_css(css); } if (!p) return 0; + /* + * We are now commited to this value whatever it is. Changes in this + * tunable will only affect upcoming migrations, not the current one. + * So we need to save it, and keep it going. + */ + move_flags = READ_ONCE(memcg->move_charge_at_immigrate); + if (!move_flags) + return 0; + from = mem_cgroup_from_task(p); VM_BUG_ON(from == memcg); @@ -4842,8 +4847,7 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, return ret; } -static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset) { if (mc.to) mem_cgroup_clear_mc(); @@ -4985,10 +4989,10 @@ retry: atomic_dec(&mc.from->moving_account); } -static void mem_cgroup_move_task(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void mem_cgroup_move_task(struct cgroup_taskset *tset) { - struct task_struct *p = cgroup_taskset_first(tset); + struct cgroup_subsys_state *css; + struct task_struct *p = cgroup_taskset_first(tset, &css); struct mm_struct *mm = get_task_mm(p); if (mm) { @@ -5000,17 +5004,14 @@ static void mem_cgroup_move_task(struct cgroup_subsys_state *css, mem_cgroup_clear_mc(); } #else /* !CONFIG_MMU */ -static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int mem_cgroup_can_attach(struct cgroup_taskset *tset) { return 0; } -static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset) { } -static void mem_cgroup_move_task(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void mem_cgroup_move_task(struct cgroup_taskset *tset) { } #endif diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c index 6441f47b1a8f..81cb3c72efe8 100644 --- a/net/core/netclassid_cgroup.c +++ b/net/core/netclassid_cgroup.c @@ -67,14 +67,15 @@ static int update_classid(const void *v, struct file *file, unsigned n) return 0; } -static void cgrp_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void cgrp_attach(struct cgroup_taskset *tset) { - struct cgroup_cls_state *cs = css_cls_state(css); - void *v = (void *)(unsigned long)cs->classid; struct task_struct *p; + struct cgroup_subsys_state *css; + + cgroup_taskset_for_each(p, css, tset) { + struct cgroup_cls_state *cs = css_cls_state(css); + void *v = (void *)(unsigned long)cs->classid; - cgroup_taskset_for_each(p, tset) { task_lock(p); iterate_fd(p->files, 0, update_classid, v); task_unlock(p); diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index cbd0a199bf52..40fd09fe06ae 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -218,13 +218,14 @@ static int update_netprio(const void *v, struct file *file, unsigned n) return 0; } -static void net_prio_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void net_prio_attach(struct cgroup_taskset *tset) { struct task_struct *p; - void *v = (void *)(unsigned long)css->cgroup->id; + struct cgroup_subsys_state *css; + + cgroup_taskset_for_each(p, css, tset) { + void *v = (void *)(unsigned long)css->cgroup->id; - cgroup_taskset_for_each(p, tset) { task_lock(p); iterate_fd(p->files, 0, update_netprio, v); task_unlock(p); -- cgit v1.2.3 From ae5515d66362b9d96cdcfce504567f0b8b7bd83e Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Fri, 4 Dec 2015 08:38:42 -0700 Subject: Revert: "vfio: Include No-IOMMU mode" Revert commit 033291eccbdb ("vfio: Include No-IOMMU mode") due to lack of a user. This was originally intended to fill a need for the DPDK driver, but uptake has been slow so rather than support an unproven kernel interface revert it and revisit when userspace catches up. Signed-off-by: Alex Williamson --- drivers/vfio/Kconfig | 15 ---- drivers/vfio/pci/vfio_pci.c | 8 +- drivers/vfio/vfio.c | 186 ++------------------------------------------ include/linux/vfio.h | 3 - include/uapi/linux/vfio.h | 7 -- 5 files changed, 10 insertions(+), 209 deletions(-) (limited to 'include') diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig index da6e2ce77495..850d86ca685b 100644 --- a/drivers/vfio/Kconfig +++ b/drivers/vfio/Kconfig @@ -31,21 +31,6 @@ menuconfig VFIO If you don't know what to do here, say N. -menuconfig VFIO_NOIOMMU - bool "VFIO No-IOMMU support" - depends on VFIO - help - VFIO is built on the ability to isolate devices using the IOMMU. - Only with an IOMMU can userspace access to DMA capable devices be - considered secure. VFIO No-IOMMU mode enables IOMMU groups for - devices without IOMMU backing for the purpose of re-using the VFIO - infrastructure in a non-secure mode. Use of this mode will result - in an unsupportable kernel and will therefore taint the kernel. - Device assignment to virtual machines is also not possible with - this mode since there is no IOMMU to provide DMA translation. - - If you don't know what to do here, say N. - source "drivers/vfio/pci/Kconfig" source "drivers/vfio/platform/Kconfig" source "virt/lib/Kconfig" diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 2760a7ba3f30..56bf6dbb93db 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -940,13 +940,13 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL) return -EINVAL; - group = vfio_iommu_group_get(&pdev->dev); + group = iommu_group_get(&pdev->dev); if (!group) return -EINVAL; vdev = kzalloc(sizeof(*vdev), GFP_KERNEL); if (!vdev) { - vfio_iommu_group_put(group, &pdev->dev); + iommu_group_put(group); return -ENOMEM; } @@ -957,7 +957,7 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev); if (ret) { - vfio_iommu_group_put(group, &pdev->dev); + iommu_group_put(group); kfree(vdev); return ret; } @@ -993,7 +993,7 @@ static void vfio_pci_remove(struct pci_dev *pdev) if (!vdev) return; - vfio_iommu_group_put(pdev->dev.iommu_group, &pdev->dev); + iommu_group_put(pdev->dev.iommu_group); kfree(vdev); if (vfio_pci_is_vga(pdev)) { diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 9da0703e09d0..6070b793cbcb 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -62,7 +62,6 @@ struct vfio_container { struct rw_semaphore group_lock; struct vfio_iommu_driver *iommu_driver; void *iommu_data; - bool noiommu; }; struct vfio_unbound_dev { @@ -85,7 +84,6 @@ struct vfio_group { struct list_head unbound_list; struct mutex unbound_lock; atomic_t opened; - bool noiommu; }; struct vfio_device { @@ -97,147 +95,6 @@ struct vfio_device { void *device_data; }; -#ifdef CONFIG_VFIO_NOIOMMU -static bool noiommu __read_mostly; -module_param_named(enable_unsafe_noiommu_support, - noiommu, bool, S_IRUGO | S_IWUSR); -MODULE_PARM_DESC(enable_unsafe_noiommu_mode, "Enable UNSAFE, no-IOMMU mode. This mode provides no device isolation, no DMA translation, no host kernel protection, cannot be used for device assignment to virtual machines, requires RAWIO permissions, and will taint the kernel. If you do not know what this is for, step away. (default: false)"); -#endif - -/* - * vfio_iommu_group_{get,put} are only intended for VFIO bus driver probe - * and remove functions, any use cases other than acquiring the first - * reference for the purpose of calling vfio_add_group_dev() or removing - * that symmetric reference after vfio_del_group_dev() should use the raw - * iommu_group_{get,put} functions. In particular, vfio_iommu_group_put() - * removes the device from the dummy group and cannot be nested. - */ -struct iommu_group *vfio_iommu_group_get(struct device *dev) -{ - struct iommu_group *group; - int __maybe_unused ret; - - group = iommu_group_get(dev); - -#ifdef CONFIG_VFIO_NOIOMMU - /* - * With noiommu enabled, an IOMMU group will be created for a device - * that doesn't already have one and doesn't have an iommu_ops on their - * bus. We use iommu_present() again in the main code to detect these - * fake groups. - */ - if (group || !noiommu || iommu_present(dev->bus)) - return group; - - group = iommu_group_alloc(); - if (IS_ERR(group)) - return NULL; - - iommu_group_set_name(group, "vfio-noiommu"); - ret = iommu_group_add_device(group, dev); - iommu_group_put(group); - if (ret) - return NULL; - - /* - * Where to taint? At this point we've added an IOMMU group for a - * device that is not backed by iommu_ops, therefore any iommu_ - * callback using iommu_ops can legitimately Oops. So, while we may - * be about to give a DMA capable device to a user without IOMMU - * protection, which is clearly taint-worthy, let's go ahead and do - * it here. - */ - add_taint(TAINT_USER, LOCKDEP_STILL_OK); - dev_warn(dev, "Adding kernel taint for vfio-noiommu group on device\n"); -#endif - - return group; -} -EXPORT_SYMBOL_GPL(vfio_iommu_group_get); - -void vfio_iommu_group_put(struct iommu_group *group, struct device *dev) -{ -#ifdef CONFIG_VFIO_NOIOMMU - if (!iommu_present(dev->bus)) - iommu_group_remove_device(dev); -#endif - - iommu_group_put(group); -} -EXPORT_SYMBOL_GPL(vfio_iommu_group_put); - -#ifdef CONFIG_VFIO_NOIOMMU -static void *vfio_noiommu_open(unsigned long arg) -{ - if (arg != VFIO_NOIOMMU_IOMMU) - return ERR_PTR(-EINVAL); - if (!capable(CAP_SYS_RAWIO)) - return ERR_PTR(-EPERM); - - return NULL; -} - -static void vfio_noiommu_release(void *iommu_data) -{ -} - -static long vfio_noiommu_ioctl(void *iommu_data, - unsigned int cmd, unsigned long arg) -{ - if (cmd == VFIO_CHECK_EXTENSION) - return arg == VFIO_NOIOMMU_IOMMU ? 1 : 0; - - return -ENOTTY; -} - -static int vfio_iommu_present(struct device *dev, void *unused) -{ - return iommu_present(dev->bus) ? 1 : 0; -} - -static int vfio_noiommu_attach_group(void *iommu_data, - struct iommu_group *iommu_group) -{ - return iommu_group_for_each_dev(iommu_group, NULL, - vfio_iommu_present) ? -EINVAL : 0; -} - -static void vfio_noiommu_detach_group(void *iommu_data, - struct iommu_group *iommu_group) -{ -} - -static struct vfio_iommu_driver_ops vfio_noiommu_ops = { - .name = "vfio-noiommu", - .owner = THIS_MODULE, - .open = vfio_noiommu_open, - .release = vfio_noiommu_release, - .ioctl = vfio_noiommu_ioctl, - .attach_group = vfio_noiommu_attach_group, - .detach_group = vfio_noiommu_detach_group, -}; - -static struct vfio_iommu_driver vfio_noiommu_driver = { - .ops = &vfio_noiommu_ops, -}; - -/* - * Wrap IOMMU drivers, the noiommu driver is the one and only driver for - * noiommu groups (and thus containers) and not available for normal groups. - */ -#define vfio_for_each_iommu_driver(con, pos) \ - for (pos = con->noiommu ? &vfio_noiommu_driver : \ - list_first_entry(&vfio.iommu_drivers_list, \ - struct vfio_iommu_driver, vfio_next); \ - (con->noiommu ? pos != NULL : \ - &pos->vfio_next != &vfio.iommu_drivers_list); \ - pos = con->noiommu ? NULL : list_next_entry(pos, vfio_next)) -#else -#define vfio_for_each_iommu_driver(con, pos) \ - list_for_each_entry(pos, &vfio.iommu_drivers_list, vfio_next) -#endif - - /** * IOMMU driver registration */ @@ -342,8 +199,7 @@ static void vfio_group_unlock_and_free(struct vfio_group *group) /** * Group objects - create, release, get, put, search */ -static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group, - bool noiommu) +static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group) { struct vfio_group *group, *tmp; struct device *dev; @@ -361,7 +217,6 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group, atomic_set(&group->container_users, 0); atomic_set(&group->opened, 0); group->iommu_group = iommu_group; - group->noiommu = noiommu; group->nb.notifier_call = vfio_iommu_group_notifier; @@ -397,8 +252,7 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group, dev = device_create(vfio.class, NULL, MKDEV(MAJOR(vfio.group_devt), minor), - group, "%s%d", noiommu ? "noiommu-" : "", - iommu_group_id(iommu_group)); + group, "%d", iommu_group_id(iommu_group)); if (IS_ERR(dev)) { vfio_free_group_minor(minor); vfio_group_unlock_and_free(group); @@ -786,8 +640,7 @@ int vfio_add_group_dev(struct device *dev, group = vfio_group_get_from_iommu(iommu_group); if (!group) { - group = vfio_create_group(iommu_group, - !iommu_present(dev->bus)); + group = vfio_create_group(iommu_group); if (IS_ERR(group)) { iommu_group_put(iommu_group); return PTR_ERR(group); @@ -999,7 +852,8 @@ static long vfio_ioctl_check_extension(struct vfio_container *container, */ if (!driver) { mutex_lock(&vfio.iommu_drivers_lock); - vfio_for_each_iommu_driver(container, driver) { + list_for_each_entry(driver, &vfio.iommu_drivers_list, + vfio_next) { if (!try_module_get(driver->ops->owner)) continue; @@ -1068,7 +922,7 @@ static long vfio_ioctl_set_iommu(struct vfio_container *container, } mutex_lock(&vfio.iommu_drivers_lock); - vfio_for_each_iommu_driver(container, driver) { + list_for_each_entry(driver, &vfio.iommu_drivers_list, vfio_next) { void *data; if (!try_module_get(driver->ops->owner)) @@ -1333,9 +1187,6 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd) if (atomic_read(&group->container_users)) return -EINVAL; - if (group->noiommu && !capable(CAP_SYS_RAWIO)) - return -EPERM; - f = fdget(container_fd); if (!f.file) return -EBADF; @@ -1351,13 +1202,6 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd) down_write(&container->group_lock); - /* Real groups and fake groups cannot mix */ - if (!list_empty(&container->group_list) && - container->noiommu != group->noiommu) { - ret = -EPERM; - goto unlock_out; - } - driver = container->iommu_driver; if (driver) { ret = driver->ops->attach_group(container->iommu_data, @@ -1367,7 +1211,6 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd) } group->container = container; - container->noiommu = group->noiommu; list_add(&group->container_next, &container->group_list); /* Get a reference on the container and mark a user within the group */ @@ -1398,9 +1241,6 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf) !group->container->iommu_driver || !vfio_group_viable(group)) return -EINVAL; - if (group->noiommu && !capable(CAP_SYS_RAWIO)) - return -EPERM; - device = vfio_device_get_from_name(group, buf); if (!device) return -ENODEV; @@ -1443,10 +1283,6 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf) fd_install(ret, filep); - if (group->noiommu) - dev_warn(device->dev, "vfio-noiommu device opened by user " - "(%s:%d)\n", current->comm, task_pid_nr(current)); - return ret; } @@ -1535,11 +1371,6 @@ static int vfio_group_fops_open(struct inode *inode, struct file *filep) if (!group) return -ENODEV; - if (group->noiommu && !capable(CAP_SYS_RAWIO)) { - vfio_group_put(group); - return -EPERM; - } - /* Do we need multiple instances of the group open? Seems not. */ opened = atomic_cmpxchg(&group->opened, 0, 1); if (opened) { @@ -1702,11 +1533,6 @@ struct vfio_group *vfio_group_get_external_user(struct file *filep) if (!atomic_inc_not_zero(&group->container_users)) return ERR_PTR(-EINVAL); - if (group->noiommu) { - atomic_dec(&group->container_users); - return ERR_PTR(-EPERM); - } - if (!group->container->iommu_driver || !vfio_group_viable(group)) { atomic_dec(&group->container_users); diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 610a86a892b8..ddb440975382 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -44,9 +44,6 @@ struct vfio_device_ops { void (*request)(void *device_data, unsigned int count); }; -extern struct iommu_group *vfio_iommu_group_get(struct device *dev); -extern void vfio_iommu_group_put(struct iommu_group *group, struct device *dev); - extern int vfio_add_group_dev(struct device *dev, const struct vfio_device_ops *ops, void *device_data); diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 751b69f858c8..9fd7b5d8df2f 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -38,13 +38,6 @@ #define VFIO_SPAPR_TCE_v2_IOMMU 7 -/* - * The No-IOMMU IOMMU offers no translation or isolation for devices and - * supports no ioctls outside of VFIO_CHECK_EXTENSION. Use of VFIO's No-IOMMU - * code will taint the host kernel and should be used with extreme caution. - */ -#define VFIO_NOIOMMU_IOMMU 8 - /* * The IOCTL interface is designed for extensibility by embedding the * structure length (argsz) and flags into structures passed between -- cgit v1.2.3 From 7c23b7c1996597dd9d60bb282fb5fa1be6ebd18b Mon Sep 17 00:00:00 2001 From: "Lu, Han" Date: Mon, 7 Dec 2015 15:59:13 +0800 Subject: ALSA: hda - Fix playback noise with 24/32 bit sample size on BXT In BXT-P A0, HD-Audio DMA requests is later than expected, and makes an audio stream sensitive to system latencies when 24/32 bits are playing. Adjusting threshold of DMA fifo to force the DMA request sooner to improve latency tolerance at the expense of power. v2: move Intel specific code to hda_intel.c Signed-off-by: Lu, Han Signed-off-by: Takashi Iwai --- include/sound/hda_register.h | 3 +++ sound/pci/hda/hda_intel.c | 23 +++++++++++++++++++++++ 2 files changed, 26 insertions(+) (limited to 'include') diff --git a/include/sound/hda_register.h b/include/sound/hda_register.h index 2ae8812d7b1a..94dc6a9772e0 100644 --- a/include/sound/hda_register.h +++ b/include/sound/hda_register.h @@ -93,6 +93,9 @@ enum { SDI0, SDI1, SDI2, SDI3, SDO0, SDO1, SDO2, SDO3 }; #define AZX_REG_HSW_EM4 0x100c #define AZX_REG_HSW_EM5 0x1010 +/* Skylake/Broxton display HD-A controller Extended Mode registers */ +#define AZX_REG_SKL_EM4L 0x1040 + /* PCI space */ #define AZX_PCIREG_TCSEL 0x44 diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 963f82430938..bff5c8b329d1 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -355,6 +355,8 @@ enum { ((pci)->device == 0x0d0c) || \ ((pci)->device == 0x160c)) +#define IS_BROXTON(pci) ((pci)->device == 0x5a98) + static char *driver_short_names[] = { [AZX_DRIVER_ICH] = "HDA Intel", [AZX_DRIVER_PCH] = "HDA Intel PCH", @@ -506,15 +508,36 @@ static void azx_init_pci(struct azx *chip) } } +/* + * In BXT-P A0, HD-Audio DMA requests is later than expected, + * and makes an audio stream sensitive to system latencies when + * 24/32 bits are playing. + * Adjusting threshold of DMA fifo to force the DMA request + * sooner to improve latency tolerance at the expense of power. + */ +static void bxt_reduce_dma_latency(struct azx *chip) +{ + u32 val; + + val = azx_readl(chip, SKL_EM4L); + val &= (0x3 << 20); + azx_writel(chip, SKL_EM4L, val); +} + static void hda_intel_init_chip(struct azx *chip, bool full_reset) { struct hdac_bus *bus = azx_bus(chip); + struct pci_dev *pci = chip->pci; if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) snd_hdac_set_codec_wakeup(bus, true); azx_init_chip(chip, full_reset); if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) snd_hdac_set_codec_wakeup(bus, false); + + /* reduce dma latency to avoid noise */ + if (IS_BROXTON(pci)) + bxt_reduce_dma_latency(chip); } /* calculate runtime delay from LPIB */ -- cgit v1.2.3 From ea013a9b205b47b1fcbc72522146fad560af0712 Mon Sep 17 00:00:00 2001 From: Andreas Werner Date: Fri, 4 Dec 2015 18:12:49 +0100 Subject: libata-eh.c: Introduce new ata port flag for controller which lockup on read log page Some controller lockup on a ata_read_log_page. Add new ata port flag ATA_FLAG_NO_LOG_PAGE which can used to blacklist a controller. If this flag is set, any attempt to read a log page returns an error without actually issuing the command. Signed-off-by: Andreas Werner Signed-off-by: Tejun Heo --- drivers/ata/libata-eh.c | 8 ++++++++ include/linux/libata.h | 1 + 2 files changed, 9 insertions(+) (limited to 'include') diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index cb0508af1459..961acc788f44 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -1505,12 +1505,20 @@ static const char *ata_err_string(unsigned int err_mask) unsigned int ata_read_log_page(struct ata_device *dev, u8 log, u8 page, void *buf, unsigned int sectors) { + unsigned long ap_flags = dev->link->ap->flags; struct ata_taskfile tf; unsigned int err_mask; bool dma = false; DPRINTK("read log page - log 0x%x, page 0x%x\n", log, page); + /* + * Return error without actually issuing the command on controllers + * which e.g. lockup on a read log page. + */ + if (ap_flags & ATA_FLAG_NO_LOG_PAGE) + return AC_ERR_DEV; + retry: ata_tf_init(dev, &tf); if (dev->dma_mode && ata_id_has_read_log_dma_ext(dev->id) && diff --git a/include/linux/libata.h b/include/linux/libata.h index 83577f8fd15b..600c1e0626a5 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -210,6 +210,7 @@ enum { ATA_FLAG_SLAVE_POSS = (1 << 0), /* host supports slave dev */ /* (doesn't imply presence) */ ATA_FLAG_SATA = (1 << 1), + ATA_FLAG_NO_LOG_PAGE = (1 << 5), /* do not issue log page read */ ATA_FLAG_NO_ATAPI = (1 << 6), /* No ATAPI support */ ATA_FLAG_PIO_DMA = (1 << 7), /* PIO cmds via DMA */ ATA_FLAG_PIO_LBA48 = (1 << 8), /* Host DMA engine is LBA28 only */ -- cgit v1.2.3 From 57b4bd06ff0372fe1e3617889c4b37fbd500364a Mon Sep 17 00:00:00 2001 From: Matias Bjørling Date: Sun, 6 Dec 2015 11:25:47 +0100 Subject: lightnvm: comments on constants MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It is not obvious what NVM_IO_* and NVM_BLK_T_* are used for. Make sure to comment them appropriately as the other constants. Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- include/linux/lightnvm.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index c6916aec43b6..935ef3844c05 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -50,9 +50,16 @@ enum { NVM_IO_DUAL_ACCESS = 0x1, NVM_IO_QUAD_ACCESS = 0x2, + /* NAND Access Modes */ NVM_IO_SUSPEND = 0x80, NVM_IO_SLC_MODE = 0x100, NVM_IO_SCRAMBLE_DISABLE = 0x200, + + /* Block Types */ + NVM_BLK_T_FREE = 0x0, + NVM_BLK_T_BAD = 0x1, + NVM_BLK_T_DEV = 0x2, + NVM_BLK_T_HOST = 0x4, }; struct nvm_id_group { -- cgit v1.2.3 From 16f26c3aa9b9c36a9d1092ae3258461d1008481e Mon Sep 17 00:00:00 2001 From: Matias Bjørling Date: Sun, 6 Dec 2015 11:25:48 +0100 Subject: lightnvm: replace req queue with nvmdev for lld MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In the case where a request queue is passed to the low lever lightnvm device drive integration, the device driver might pass its admin commands through another queue. Instead pass nvm_dev, and let the low level drive the appropriate queue. Reported-by: Christoph Hellwig Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- drivers/block/null_blk.c | 9 +++++---- drivers/lightnvm/core.c | 7 +++---- drivers/lightnvm/gennvm.c | 8 ++++---- drivers/lightnvm/rrpc.c | 2 +- drivers/nvme/host/lightnvm.c | 24 +++++++++++++----------- include/linux/lightnvm.h | 14 +++++++------- 6 files changed, 33 insertions(+), 31 deletions(-) (limited to 'include') diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c index 0c3940ec5e62..7981b7407305 100644 --- a/drivers/block/null_blk.c +++ b/drivers/block/null_blk.c @@ -444,8 +444,9 @@ static void null_lnvm_end_io(struct request *rq, int error) blk_put_request(rq); } -static int null_lnvm_submit_io(struct request_queue *q, struct nvm_rq *rqd) +static int null_lnvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd) { + struct request_queue *q = dev->q; struct request *rq; struct bio *bio = rqd->bio; @@ -470,7 +471,7 @@ static int null_lnvm_submit_io(struct request_queue *q, struct nvm_rq *rqd) return 0; } -static int null_lnvm_id(struct request_queue *q, struct nvm_id *id) +static int null_lnvm_id(struct nvm_dev *dev, struct nvm_id *id) { sector_t size = gb * 1024 * 1024 * 1024ULL; sector_t blksize; @@ -523,7 +524,7 @@ static int null_lnvm_id(struct request_queue *q, struct nvm_id *id) return 0; } -static void *null_lnvm_create_dma_pool(struct request_queue *q, char *name) +static void *null_lnvm_create_dma_pool(struct nvm_dev *dev, char *name) { mempool_t *virtmem_pool; @@ -541,7 +542,7 @@ static void null_lnvm_destroy_dma_pool(void *pool) mempool_destroy(pool); } -static void *null_lnvm_dev_dma_alloc(struct request_queue *q, void *pool, +static void *null_lnvm_dev_dma_alloc(struct nvm_dev *dev, void *pool, gfp_t mem_flags, dma_addr_t *dma_handler) { return mempool_alloc(pool, mem_flags); diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c index 86ce887b2ed6..4a8d1fe34c4e 100644 --- a/drivers/lightnvm/core.c +++ b/drivers/lightnvm/core.c @@ -74,7 +74,7 @@ EXPORT_SYMBOL(nvm_unregister_target); void *nvm_dev_dma_alloc(struct nvm_dev *dev, gfp_t mem_flags, dma_addr_t *dma_handler) { - return dev->ops->dev_dma_alloc(dev->q, dev->ppalist_pool, mem_flags, + return dev->ops->dev_dma_alloc(dev, dev->ppalist_pool, mem_flags, dma_handler); } EXPORT_SYMBOL(nvm_dev_dma_alloc); @@ -246,7 +246,7 @@ static int nvm_init(struct nvm_dev *dev) if (!dev->q || !dev->ops) return ret; - if (dev->ops->identity(dev->q, &dev->identity)) { + if (dev->ops->identity(dev, &dev->identity)) { pr_err("nvm: device could not be identified\n"); goto err; } @@ -326,8 +326,7 @@ int nvm_register(struct request_queue *q, char *disk_name, } if (dev->ops->max_phys_sect > 1) { - dev->ppalist_pool = dev->ops->create_dma_pool(dev->q, - "ppalist"); + dev->ppalist_pool = dev->ops->create_dma_pool(dev, "ppalist"); if (!dev->ppalist_pool) { pr_err("nvm: could not create ppa pool\n"); ret = -ENOMEM; diff --git a/drivers/lightnvm/gennvm.c b/drivers/lightnvm/gennvm.c index ce6025487a5c..52b513a65946 100644 --- a/drivers/lightnvm/gennvm.c +++ b/drivers/lightnvm/gennvm.c @@ -195,7 +195,7 @@ static int gennvm_blocks_init(struct nvm_dev *dev, struct gen_nvm *gn) } if (dev->ops->get_l2p_tbl) { - ret = dev->ops->get_l2p_tbl(dev->q, 0, dev->total_pages, + ret = dev->ops->get_l2p_tbl(dev, 0, dev->total_pages, gennvm_block_map, dev); if (ret) { pr_err("gennvm: could not read L2P table.\n"); @@ -346,7 +346,7 @@ static int gennvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd) gennvm_generic_to_addr_mode(dev, rqd); rqd->dev = dev; - return dev->ops->submit_io(dev->q, rqd); + return dev->ops->submit_io(dev, rqd); } static void gennvm_blk_set_type(struct nvm_dev *dev, struct ppa_addr *ppa, @@ -382,7 +382,7 @@ static void gennvm_mark_blk_bad(struct nvm_dev *dev, struct nvm_rq *rqd) if (!dev->ops->set_bb_tbl) return; - if (dev->ops->set_bb_tbl(dev->q, rqd, 1)) + if (dev->ops->set_bb_tbl(dev, rqd, 1)) return; gennvm_addr_to_generic_mode(dev, rqd); @@ -450,7 +450,7 @@ static int gennvm_erase_blk(struct nvm_dev *dev, struct nvm_block *blk, gennvm_generic_to_addr_mode(dev, &rqd); - ret = dev->ops->erase_block(dev->q, &rqd); + ret = dev->ops->erase_block(dev, &rqd); if (plane_cnt) nvm_dev_dma_free(dev, rqd.ppa_list, rqd.dma_ppa_list); diff --git a/drivers/lightnvm/rrpc.c b/drivers/lightnvm/rrpc.c index cf1a4a515b76..134e4faba482 100644 --- a/drivers/lightnvm/rrpc.c +++ b/drivers/lightnvm/rrpc.c @@ -1016,7 +1016,7 @@ static int rrpc_map_init(struct rrpc *rrpc) return 0; /* Bring up the mapping table from device */ - ret = dev->ops->get_l2p_tbl(dev->q, 0, dev->total_pages, + ret = dev->ops->get_l2p_tbl(dev, 0, dev->total_pages, rrpc_l2p_update, rrpc); if (ret) { pr_err("nvm: rrpc: could not read L2P table.\n"); diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c index 762c9a7cbfa6..15f2acb4d5cd 100644 --- a/drivers/nvme/host/lightnvm.c +++ b/drivers/nvme/host/lightnvm.c @@ -271,9 +271,9 @@ static int init_grps(struct nvm_id *nvm_id, struct nvme_nvm_id *nvme_nvm_id) return 0; } -static int nvme_nvm_identity(struct request_queue *q, struct nvm_id *nvm_id) +static int nvme_nvm_identity(struct nvm_dev *nvmdev, struct nvm_id *nvm_id) { - struct nvme_ns *ns = q->queuedata; + struct nvme_ns *ns = nvmdev->q->queuedata; struct nvme_dev *dev = ns->dev; struct nvme_nvm_id *nvme_nvm_id; struct nvme_nvm_command c = {}; @@ -308,10 +308,10 @@ out: return ret; } -static int nvme_nvm_get_l2p_tbl(struct request_queue *q, u64 slba, u32 nlb, +static int nvme_nvm_get_l2p_tbl(struct nvm_dev *nvmdev, u64 slba, u32 nlb, nvm_l2p_update_fn *update_l2p, void *priv) { - struct nvme_ns *ns = q->queuedata; + struct nvme_ns *ns = nvmdev->q->queuedata; struct nvme_dev *dev = ns->dev; struct nvme_nvm_command c = {}; u32 len = queue_max_hw_sectors(dev->admin_q) << 9; @@ -415,10 +415,10 @@ out: return ret; } -static int nvme_nvm_set_bb_tbl(struct request_queue *q, struct nvm_rq *rqd, +static int nvme_nvm_set_bb_tbl(struct nvm_dev *nvmdev, struct nvm_rq *rqd, int type) { - struct nvme_ns *ns = q->queuedata; + struct nvme_ns *ns = nvmdev->q->queuedata; struct nvme_dev *dev = ns->dev; struct nvme_nvm_command c = {}; int ret = 0; @@ -463,8 +463,9 @@ static void nvme_nvm_end_io(struct request *rq, int error) blk_mq_free_request(rq); } -static int nvme_nvm_submit_io(struct request_queue *q, struct nvm_rq *rqd) +static int nvme_nvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd) { + struct request_queue *q = dev->q; struct nvme_ns *ns = q->queuedata; struct request *rq; struct bio *bio = rqd->bio; @@ -502,8 +503,9 @@ static int nvme_nvm_submit_io(struct request_queue *q, struct nvm_rq *rqd) return 0; } -static int nvme_nvm_erase_block(struct request_queue *q, struct nvm_rq *rqd) +static int nvme_nvm_erase_block(struct nvm_dev *dev, struct nvm_rq *rqd) { + struct request_queue *q = dev->q; struct nvme_ns *ns = q->queuedata; struct nvme_nvm_command c = {}; @@ -515,9 +517,9 @@ static int nvme_nvm_erase_block(struct request_queue *q, struct nvm_rq *rqd) return nvme_submit_sync_cmd(q, (struct nvme_command *)&c, NULL, 0); } -static void *nvme_nvm_create_dma_pool(struct request_queue *q, char *name) +static void *nvme_nvm_create_dma_pool(struct nvm_dev *nvmdev, char *name) { - struct nvme_ns *ns = q->queuedata; + struct nvme_ns *ns = nvmdev->q->queuedata; struct nvme_dev *dev = ns->dev; return dma_pool_create(name, dev->dev, PAGE_SIZE, PAGE_SIZE, 0); @@ -530,7 +532,7 @@ static void nvme_nvm_destroy_dma_pool(void *pool) dma_pool_destroy(dma_pool); } -static void *nvme_nvm_dev_dma_alloc(struct request_queue *q, void *pool, +static void *nvme_nvm_dev_dma_alloc(struct nvm_dev *dev, void *pool, gfp_t mem_flags, dma_addr_t *dma_handler) { return dma_pool_alloc(pool, mem_flags, dma_handler); diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index 935ef3844c05..034117b3be5f 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -183,17 +183,17 @@ struct nvm_block; typedef int (nvm_l2p_update_fn)(u64, u32, __le64 *, void *); typedef int (nvm_bb_update_fn)(struct ppa_addr, int, u8 *, void *); -typedef int (nvm_id_fn)(struct request_queue *, struct nvm_id *); -typedef int (nvm_get_l2p_tbl_fn)(struct request_queue *, u64, u32, +typedef int (nvm_id_fn)(struct nvm_dev *, struct nvm_id *); +typedef int (nvm_get_l2p_tbl_fn)(struct nvm_dev *, u64, u32, nvm_l2p_update_fn *, void *); typedef int (nvm_op_bb_tbl_fn)(struct nvm_dev *, struct ppa_addr, int, nvm_bb_update_fn *, void *); -typedef int (nvm_op_set_bb_fn)(struct request_queue *, struct nvm_rq *, int); -typedef int (nvm_submit_io_fn)(struct request_queue *, struct nvm_rq *); -typedef int (nvm_erase_blk_fn)(struct request_queue *, struct nvm_rq *); -typedef void *(nvm_create_dma_pool_fn)(struct request_queue *, char *); +typedef int (nvm_op_set_bb_fn)(struct nvm_dev *, struct nvm_rq *, int); +typedef int (nvm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *); +typedef int (nvm_erase_blk_fn)(struct nvm_dev *, struct nvm_rq *); +typedef void *(nvm_create_dma_pool_fn)(struct nvm_dev *, char *); typedef void (nvm_destroy_dma_pool_fn)(void *); -typedef void *(nvm_dev_dma_alloc_fn)(struct request_queue *, void *, gfp_t, +typedef void *(nvm_dev_dma_alloc_fn)(struct nvm_dev *, void *, gfp_t, dma_addr_t *); typedef void (nvm_dev_dma_free_fn)(void *, void*, dma_addr_t); -- cgit v1.2.3 From d144da8c6f51f48ec39d891ea9dff80169c45f3b Mon Sep 17 00:00:00 2001 From: Mike Marciniszyn Date: Mon, 2 Nov 2015 12:13:25 -0500 Subject: IB/core: use RCU for uverbs id lookup The current implementation gets a spin_lock, and at any scale with qib and hfi1 post send, the lock contention grows exponentially with the number of QPs. idr_find() is RCU compatibile, so read doesn't need the lock. Change to use rcu_read_lock() and rcu_read_unlock() in __idr_get_uobj(). kfree_rcu() is used to insure a grace period between the idr removal and actual free. Reviewed-by: Ira Weiny Signed-off-by: Mike Marciniszyn Reviewed-By: Jason Gunthorpe Signed-off-by: Doug Ledford --- drivers/infiniband/core/uverbs_cmd.c | 12 +++++++----- include/rdma/ib_verbs.h | 1 + 2 files changed, 8 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 4cb8e9d9966c..1c02deab068f 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -62,9 +62,11 @@ static struct uverbs_lock_class rule_lock_class = { .name = "RULE-uobj" }; * The ib_uobject locking scheme is as follows: * * - ib_uverbs_idr_lock protects the uverbs idrs themselves, so it - * needs to be held during all idr operations. When an object is + * needs to be held during all idr write operations. When an object is * looked up, a reference must be taken on the object's kref before - * dropping this lock. + * dropping this lock. For read operations, the rcu_read_lock() + * and rcu_write_lock() but similarly the kref reference is grabbed + * before the rcu_read_unlock(). * * - Each object also has an rwsem. This rwsem must be held for * reading while an operation that uses the object is performed. @@ -96,7 +98,7 @@ static void init_uobj(struct ib_uobject *uobj, u64 user_handle, static void release_uobj(struct kref *kref) { - kfree(container_of(kref, struct ib_uobject, ref)); + kfree_rcu(container_of(kref, struct ib_uobject, ref), rcu); } static void put_uobj(struct ib_uobject *uobj) @@ -145,7 +147,7 @@ static struct ib_uobject *__idr_get_uobj(struct idr *idr, int id, { struct ib_uobject *uobj; - spin_lock(&ib_uverbs_idr_lock); + rcu_read_lock(); uobj = idr_find(idr, id); if (uobj) { if (uobj->context == context) @@ -153,7 +155,7 @@ static struct ib_uobject *__idr_get_uobj(struct idr *idr, int id, else uobj = NULL; } - spin_unlock(&ib_uverbs_idr_lock); + rcu_read_unlock(); return uobj; } diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 9a68a19532ba..120da1d7f57e 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1271,6 +1271,7 @@ struct ib_uobject { int id; /* index into kernel idr */ struct kref ref; struct rw_semaphore mutex; /* protects .live */ + struct rcu_head rcu; /* kfree_rcu() overhead */ int live; }; -- cgit v1.2.3 From 533708867dd6388f643f12c87465b59e732d729d Mon Sep 17 00:00:00 2001 From: Hal Rosenstock Date: Fri, 13 Nov 2015 15:22:22 -0500 Subject: IB/mad: Require CM send method for everything except ClassPortInfo Receipt of CM MAD with other than the Send method for an attribute other than the ClassPortInfo attribute is invalid. CM attributes other than ClassPortInfo only use the send method. The SRP initiator does not maintain a timeout policy for CM connect requests relies on the CM layer to do that. The result was that the SRP initiator hung as the connect request never completed. A new SRP target has been observed to respond to Send CM REQ with GetResp of CM REQ with bad status. This is non conformant with IBA spec but exposes a vulnerability in the current MAD/CM code which will respond to the incoming GetResp of CM REQ as if it was a valid incoming Send of CM REQ rather than tossing this on the floor. It also causes the MAD layer not to retransmit the original REQ even though it has not received a REP. Reviewed-by: Sagi Grimberg Signed-off-by: Hal Rosenstock Reviewed-by: Ira Weiny Signed-off-by: Doug Ledford --- drivers/infiniband/core/mad.c | 5 +++++ include/rdma/ib_mad.h | 2 ++ 2 files changed, 7 insertions(+) (limited to 'include') diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c index 8d8af7a41a30..2281de122038 100644 --- a/drivers/infiniband/core/mad.c +++ b/drivers/infiniband/core/mad.c @@ -1811,6 +1811,11 @@ static int validate_mad(const struct ib_mad_hdr *mad_hdr, if (qp_num == 0) valid = 1; } else { + /* CM attributes other than ClassPortInfo only use Send method */ + if ((mad_hdr->mgmt_class == IB_MGMT_CLASS_CM) && + (mad_hdr->attr_id != IB_MGMT_CLASSPORTINFO_ATTR_ID) && + (mad_hdr->method != IB_MGMT_METHOD_SEND)) + goto out; /* Filter GSI packets sent to QP0 */ if (qp_num != 0) valid = 1; diff --git a/include/rdma/ib_mad.h b/include/rdma/ib_mad.h index 188df91d5851..ec9b44dd3d80 100644 --- a/include/rdma/ib_mad.h +++ b/include/rdma/ib_mad.h @@ -237,6 +237,8 @@ struct ib_vendor_mad { u8 data[IB_MGMT_VENDOR_DATA]; }; +#define IB_MGMT_CLASSPORTINFO_ATTR_ID cpu_to_be16(0x0001) + struct ib_class_port_info { u8 base_version; u8 class_version; -- cgit v1.2.3 From a5e14ba334e202c58e45ef47414ec94c585c1a8c Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Wed, 28 Oct 2015 13:28:15 +0200 Subject: mlx4: Expose correct max_sge_rd limit mlx4 devices (ConnectX-2, ConnectX-3) has a limitation where rdma read work queue entries cannot exceed 512 bytes. A rdma_read wqe needs to fit in 512 bytes: - wqe control segment (16 bytes) - rdma segment (16 bytes) - scatter elements (16 bytes each) So max_sge_rd should be: (512 - 16 - 16) / 16 = 30. Signed-off-by: Sagi Grimberg Reviewed-by: Steve Wise Signed-off-by: Doug Ledford --- drivers/infiniband/hw/mlx4/main.c | 2 +- include/linux/mlx4/device.h | 11 +++++++++++ 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index f567160a4a56..97d6878f9938 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -456,7 +456,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev, props->max_qp_wr = dev->dev->caps.max_wqes - MLX4_IB_SQ_MAX_SPARE; props->max_sge = min(dev->dev->caps.max_sq_sg, dev->dev->caps.max_rq_sg); - props->max_sge_rd = props->max_sge; + props->max_sge_rd = MLX4_MAX_SGE_RD; props->max_cq = dev->dev->quotas.cq; props->max_cqe = dev->dev->caps.max_cqes; props->max_mr = dev->dev->quotas.mpt; diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 7501626ab529..d3133be12d92 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -426,6 +426,17 @@ enum { MLX4_MAX_FAST_REG_PAGES = 511, }; +enum { + /* + * Max wqe size for rdma read is 512 bytes, so this + * limits our max_sge_rd as the wqe needs to fit: + * - ctrl segment (16 bytes) + * - rdma segment (16 bytes) + * - scatter elements (16 bytes each) + */ + MLX4_MAX_SGE_RD = (512 - 16 - 16) / 16 +}; + enum { MLX4_DEV_PMC_SUBTYPE_GUID_INFO = 0x14, MLX4_DEV_PMC_SUBTYPE_PORT_INFO = 0x15, -- cgit v1.2.3 From 4c3141e09cfa6460bfcd5e90f73e498db654c917 Mon Sep 17 00:00:00 2001 From: Carlo Caione Date: Tue, 1 Dec 2015 17:24:17 +0100 Subject: of/irq: Export of_irq_find_parent again of_irq_find_parent was made static since it had no users outside of of_irq.c. Export it again since we are going to use it again. Signed-off-by: Carlo Caione [robh: move of_irq_find_parent to correct ifdef section] Signed-off-by: Rob Herring --- drivers/of/irq.c | 3 ++- include/linux/of_irq.h | 6 ++++++ 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/of/irq.c b/drivers/of/irq.c index 902b89be7217..4fa916dffc91 100644 --- a/drivers/of/irq.c +++ b/drivers/of/irq.c @@ -53,7 +53,7 @@ EXPORT_SYMBOL_GPL(irq_of_parse_and_map); * Returns a pointer to the interrupt parent node, or NULL if the interrupt * parent could not be determined. */ -static struct device_node *of_irq_find_parent(struct device_node *child) +struct device_node *of_irq_find_parent(struct device_node *child) { struct device_node *p; const __be32 *parp; @@ -77,6 +77,7 @@ static struct device_node *of_irq_find_parent(struct device_node *child) return p; } +EXPORT_SYMBOL_GPL(of_irq_find_parent); /** * of_irq_parse_raw - Low level interrupt tree parsing diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index 039f2eec49ce..f648acf27ed7 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -46,6 +46,7 @@ extern int of_irq_get(struct device_node *dev, int index); extern int of_irq_get_byname(struct device_node *dev, const char *name); extern int of_irq_to_resource_table(struct device_node *dev, struct resource *res, int nr_irqs); +extern struct device_node *of_irq_find_parent(struct device_node *child); extern struct irq_domain *of_msi_get_domain(struct device *dev, struct device_node *np, enum irq_domain_bus_token token); @@ -70,6 +71,11 @@ static inline int of_irq_to_resource_table(struct device_node *dev, { return 0; } +static inline void *of_irq_find_parent(struct device_node *child) +{ + return NULL; +} + static inline struct irq_domain *of_msi_get_domain(struct device *dev, struct device_node *np, enum irq_domain_bus_token token) -- cgit v1.2.3 From eaddb5725357e9f05ffe5d271630f8197d089da4 Mon Sep 17 00:00:00 2001 From: Rob Herring Date: Wed, 9 Dec 2015 09:11:10 -0600 Subject: of/irq: move of_msi_map_rid declaration to the correct ifdef section In checking fixes for of_irq_find_parent declaration location, I found that of_msi_map_rid is also wrong. of_msi_map_rid is not implemented for Sparc, so it should not be in the Sparc specific section of the header. Move it to just depend on OF_IRQ. Cc: Frank Rowand Signed-off-by: Rob Herring --- include/linux/of_irq.h | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'include') diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index f648acf27ed7..1e0deb8e8494 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -53,6 +53,7 @@ extern struct irq_domain *of_msi_get_domain(struct device *dev, extern struct irq_domain *of_msi_map_get_device_domain(struct device *dev, u32 rid); extern void of_msi_configure(struct device *dev, struct device_node *np); +u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in); #else static inline int of_irq_count(struct device_node *dev) { @@ -90,6 +91,11 @@ static inline struct irq_domain *of_msi_map_get_device_domain(struct device *dev static inline void of_msi_configure(struct device *dev, struct device_node *np) { } +static inline u32 of_msi_map_rid(struct device *dev, + struct device_node *msi_np, u32 rid_in) +{ + return rid_in; +} #endif #if defined(CONFIG_OF_IRQ) || defined(CONFIG_SPARC) @@ -99,7 +105,6 @@ static inline void of_msi_configure(struct device *dev, struct device_node *np) * so declare it here regardless of the CONFIG_OF_IRQ setting. */ extern unsigned int irq_of_parse_and_map(struct device_node *node, int index); -u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in); #else /* !CONFIG_OF && !CONFIG_SPARC */ static inline unsigned int irq_of_parse_and_map(struct device_node *dev, @@ -107,12 +112,6 @@ static inline unsigned int irq_of_parse_and_map(struct device_node *dev, { return 0; } - -static inline u32 of_msi_map_rid(struct device *dev, - struct device_node *msi_np, u32 rid_in) -{ - return rid_in; -} #endif /* !CONFIG_OF */ #endif /* __OF_IRQ_H */ -- cgit v1.2.3 From d7e35dfa2531b53618b9e6edcd8752ce988ac555 Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Thu, 3 Dec 2015 22:04:01 -0500 Subject: bitops.h: correctly handle rol32 with 0 byte shift ROL on a 32 bit integer with a shift of 32 or more is undefined and the result is arch-dependent. Avoid this by handling the trivial case of roling by 0 correctly. The trivial solution of checking if shift is 0 breaks gcc's detection of this code as a ROL instruction, which is unacceptable. This bug was reported and fixed in GCC (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=57157): The standard rotate idiom, (x << n) | (x >> (32 - n)) is recognized by gcc (for concreteness, I discuss only the case that x is an uint32_t here). However, this is portable C only for n in the range 0 < n < 32. For n == 0, we get x >> 32 which gives undefined behaviour according to the C standard (6.5.7, Bitwise shift operators). To portably support n == 0, one has to write the rotate as something like (x << n) | (x >> ((-n) & 31)) And this is apparently not recognized by gcc. Note that this is broken on older GCCs and will result in slower ROL. Acked-by: Linus Torvalds Signed-off-by: Sasha Levin Signed-off-by: Linus Torvalds --- include/linux/bitops.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 2b8ed123ad36..defeaac0745f 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -107,7 +107,7 @@ static inline __u64 ror64(__u64 word, unsigned int shift) */ static inline __u32 rol32(__u32 word, unsigned int shift) { - return (word << shift) | (word >> (32 - shift)); + return (word << shift) | (word >> ((-shift) & 31)); } /** -- cgit v1.2.3 From 059393c5bdd1420bdf1bed2972f33196dff263ae Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 7 Dec 2015 10:11:11 +0000 Subject: irqchip/gic-v3: Add missing struct device_node declaration When the GICv3 header file is used in a C file that doesn't include any of the OF stuff, we end up with a bunch of ugly warnings. Let's keep GCC quiet by adding a forward declaration. Signed-off-by: Marc Zyngier Cc: Cc: Jason Cooper Link: http://lkml.kernel.org/r/1449483072-17694-2-git-send-email-marc.zyngier@arm.com Signed-off-by: Thomas Gleixner --- include/linux/irqchip/arm-gic-v3.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index c9ae0c6ec050..d5d798b35c1f 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -330,6 +330,7 @@ struct rdists { }; struct irq_domain; +struct device_node; int its_cpu_init(void); int its_init(struct device_node *node, struct rdists *rdists, struct irq_domain *domain); -- cgit v1.2.3 From ad87e03213b552a5c33d5e1e7a19a73768397010 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Thu, 10 Dec 2015 15:27:21 -0500 Subject: USB: add quirk for devices with broken LPM Some USB device / host controller combinations seem to have problems with Link Power Management. For example, Steinar found that his xHCI controller wouldn't handle bandwidth calculations correctly for two video cards simultaneously when LPM was enabled, even though the bus had plenty of bandwidth available. This patch introduces a new quirk flag for devices that should remain disabled for LPM, and creates quirk entries for Steinar's devices. Signed-off-by: Alan Stern Reported-by: Steinar H. Gunderson Cc: stable Signed-off-by: Greg Kroah-Hartman --- drivers/usb/core/hub.c | 7 ++++++- drivers/usb/core/quirks.c | 6 ++++++ include/linux/usb/quirks.h | 3 +++ 3 files changed, 15 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 585c3cb07da6..a5cc032ef77a 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -124,6 +124,10 @@ struct usb_hub *usb_hub_to_struct_hub(struct usb_device *hdev) int usb_device_supports_lpm(struct usb_device *udev) { + /* Some devices have trouble with LPM */ + if (udev->quirks & USB_QUIRK_NO_LPM) + return 0; + /* USB 2.1 (and greater) devices indicate LPM support through * their USB 2.0 Extended Capabilities BOS descriptor. */ @@ -4512,6 +4516,8 @@ hub_port_init(struct usb_hub *hub, struct usb_device *udev, int port1, goto fail; } + usb_detect_quirks(udev); + if (udev->wusb == 0 && le16_to_cpu(udev->descriptor.bcdUSB) >= 0x0201) { retval = usb_get_bos_descriptor(udev); if (!retval) { @@ -4710,7 +4716,6 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, if (status < 0) goto loop; - usb_detect_quirks(udev); if (udev->quirks & USB_QUIRK_DELAY_INIT) msleep(1000); diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index fcd6ac0c667f..6dc810bce295 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -202,6 +202,12 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x1a0a, 0x0200), .driver_info = USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL }, + /* Blackmagic Design Intensity Shuttle */ + { USB_DEVICE(0x1edb, 0xbd3b), .driver_info = USB_QUIRK_NO_LPM }, + + /* Blackmagic Design UltraStudio SDI */ + { USB_DEVICE(0x1edb, 0xbd4f), .driver_info = USB_QUIRK_NO_LPM }, + { } /* terminating entry must be last */ }; diff --git a/include/linux/usb/quirks.h b/include/linux/usb/quirks.h index 9948c874e3f1..1d0043dc34e4 100644 --- a/include/linux/usb/quirks.h +++ b/include/linux/usb/quirks.h @@ -47,4 +47,7 @@ /* device generates spurious wakeup, ignore remote wakeup capability */ #define USB_QUIRK_IGNORE_REMOTE_WAKEUP BIT(9) +/* device can't handle Link Power Management */ +#define USB_QUIRK_NO_LPM BIT(10) + #endif /* __LINUX_USB_QUIRKS_H */ -- cgit v1.2.3 From 98e89cf02aed11166698dd53c6f14865613babb3 Mon Sep 17 00:00:00 2001 From: Nicolas Iooss Date: Fri, 11 Dec 2015 13:40:43 -0800 Subject: mm: kmemleak: mark kmemleak_init prototype as __init The kmemleak_init() definition in mm/kmemleak.c is marked __init but its prototype in include/linux/kmemleak.h is marked __ref since commit a6186d89c913 ("kmemleak: Mark the early log buffer as __initdata"). This causes a section mismatch which is reported as a warning when building with clang -Wsection, because kmemleak_init() is declared in section .ref.text but defined in .init.text. Fix this by marking kmemleak_init() prototype __init. Signed-off-by: Nicolas Iooss Signed-off-by: Catalin Marinas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kmemleak.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h index d0a1f99e24e3..4894c6888bc6 100644 --- a/include/linux/kmemleak.h +++ b/include/linux/kmemleak.h @@ -25,7 +25,7 @@ #ifdef CONFIG_DEBUG_KMEMLEAK -extern void kmemleak_init(void) __ref; +extern void kmemleak_init(void) __init; extern void kmemleak_alloc(const void *ptr, size_t size, int min_count, gfp_t gfp) __ref; extern void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size, -- cgit v1.2.3 From 86fffe4a61dd972d5a4e23260d530be6da02f614 Mon Sep 17 00:00:00 2001 From: Chris Wilson Date: Fri, 11 Dec 2015 13:40:46 -0800 Subject: kernel: remove stop_machine() Kconfig dependency Currently the full stop_machine() routine is only enabled on SMP if module unloading is enabled, or if the CPUs are hotpluggable. This leads to configurations where stop_machine() is broken as it will then only run the callback on the local CPU with irqs disabled, and not stop the other CPUs or run the callback on them. For example, this breaks MTRR setup on x86 in certain configs since ea8596bb2d8d379 ("kprobes/x86: Remove unused text_poke_smp() and text_poke_smp_batch() functions") as the MTRR is only established on the boot CPU. This patch removes the Kconfig option for STOP_MACHINE and uses the SMP and HOTPLUG_CPU config options to compile the correct stop_machine() for the architecture, removing the false dependency on MODULE_UNLOAD in the process. Link: https://lkml.org/lkml/2014/10/8/124 References: https://bugs.freedesktop.org/show_bug.cgi?id=84794 Signed-off-by: Chris Wilson Acked-by: Ingo Molnar Cc: "Paul E. McKenney" Cc: Pranith Kumar Cc: Michal Hocko Cc: Vladimir Davydov Cc: Johannes Weiner Cc: H. Peter Anvin Cc: Tejun Heo Cc: Iulia Manda Cc: Andy Lutomirski Cc: Rusty Russell Cc: Peter Zijlstra Cc: Chuck Ebbert Cc: Oleg Nesterov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/stop_machine.h | 6 +++--- init/Kconfig | 7 ------- kernel/stop_machine.c | 4 ++-- 3 files changed, 5 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h index 0adedca24c5b..0e1b1540597a 100644 --- a/include/linux/stop_machine.h +++ b/include/linux/stop_machine.h @@ -99,7 +99,7 @@ static inline int try_stop_cpus(const struct cpumask *cpumask, * grabbing every spinlock (and more). So the "read" side to such a * lock is anything which disables preemption. */ -#if defined(CONFIG_STOP_MACHINE) && defined(CONFIG_SMP) +#if defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU) /** * stop_machine: freeze the machine on all CPUs and run this function @@ -118,7 +118,7 @@ int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus); -#else /* CONFIG_STOP_MACHINE && CONFIG_SMP */ +#else /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */ static inline int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) @@ -137,5 +137,5 @@ static inline int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, return stop_machine(fn, data, cpus); } -#endif /* CONFIG_STOP_MACHINE && CONFIG_SMP */ +#endif /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */ #endif /* _LINUX_STOP_MACHINE */ diff --git a/init/Kconfig b/init/Kconfig index c24b6f767bf0..235c7a2c0d20 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -2030,13 +2030,6 @@ config INIT_ALL_POSSIBLE it was better to provide this option than to break all the archs and have several arch maintainers pursuing me down dark alleys. -config STOP_MACHINE - bool - default y - depends on (SMP && MODULE_UNLOAD) || HOTPLUG_CPU - help - Need stop_machine() primitive. - source "block/Kconfig" config PREEMPT_NOTIFIERS diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 867bc20e1ef1..a3bbaee77c58 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -531,7 +531,7 @@ static int __init cpu_stop_init(void) } early_initcall(cpu_stop_init); -#ifdef CONFIG_STOP_MACHINE +#if defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU) static int __stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) { @@ -631,4 +631,4 @@ int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, return ret ?: done.ret; } -#endif /* CONFIG_STOP_MACHINE */ +#endif /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */ -- cgit v1.2.3 From dfd01f026058a59a513f8a365b439a0681b803af Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sun, 13 Dec 2015 22:11:16 +0100 Subject: sched/wait: Fix the signal handling fix Jan Stancek reported that I wrecked things for him by fixing things for Vladimir :/ His report was due to an UNINTERRUPTIBLE wait getting -EINTR, which should not be possible, however my previous patch made this possible by unconditionally checking signal_pending(). We cannot use current->state as was done previously, because the instruction after the store to that variable it can be changed. We must instead pass the initial state along and use that. Fixes: 68985633bccb ("sched/wait: Fix signal handling in bit wait helpers") Reported-by: Jan Stancek Reported-by: Chris Mason Tested-by: Jan Stancek Tested-by: Vladimir Murzin Tested-by: Chris Mason Reviewed-by: Paul Turner Cc: Ingo Molnar Cc: tglx@linutronix.de Cc: Oleg Nesterov Cc: hpa@zytor.com Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Linus Torvalds --- fs/cifs/inode.c | 6 +++--- fs/nfs/inode.c | 6 +++--- fs/nfs/internal.h | 2 +- fs/nfs/pagelist.c | 2 +- fs/nfs/pnfs.c | 4 ++-- include/linux/wait.h | 10 +++++----- kernel/sched/wait.c | 20 ++++++++++---------- net/sunrpc/sched.c | 6 +++--- 8 files changed, 28 insertions(+), 28 deletions(-) (limited to 'include') diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 6b66dd5d1540..a329f5ba35aa 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1831,11 +1831,11 @@ cifs_invalidate_mapping(struct inode *inode) * @word: long word containing the bit lock */ static int -cifs_wait_bit_killable(struct wait_bit_key *key) +cifs_wait_bit_killable(struct wait_bit_key *key, int mode) { - if (fatal_signal_pending(current)) - return -ERESTARTSYS; freezable_schedule_unsafe(); + if (signal_pending_state(mode, current)) + return -ERESTARTSYS; return 0; } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 31b0a52223a7..c7e8b87da5b2 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -75,11 +75,11 @@ nfs_fattr_to_ino_t(struct nfs_fattr *fattr) * nfs_wait_bit_killable - helper for functions that are sleeping on bit locks * @word: long word containing the bit lock */ -int nfs_wait_bit_killable(struct wait_bit_key *key) +int nfs_wait_bit_killable(struct wait_bit_key *key, int mode) { - if (fatal_signal_pending(current)) - return -ERESTARTSYS; freezable_schedule_unsafe(); + if (signal_pending_state(mode, current)) + return -ERESTARTSYS; return 0; } EXPORT_SYMBOL_GPL(nfs_wait_bit_killable); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 56cfde26fb9c..9dea85f7f918 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -379,7 +379,7 @@ extern int nfs_drop_inode(struct inode *); extern void nfs_clear_inode(struct inode *); extern void nfs_evict_inode(struct inode *); void nfs_zap_acl_cache(struct inode *inode); -extern int nfs_wait_bit_killable(struct wait_bit_key *key); +extern int nfs_wait_bit_killable(struct wait_bit_key *key, int mode); /* super.c */ extern const struct super_operations nfs_sops; diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index fe3ddd20ff89..452a011ba0d8 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -129,7 +129,7 @@ __nfs_iocounter_wait(struct nfs_io_counter *c) set_bit(NFS_IO_INPROGRESS, &c->flags); if (atomic_read(&c->io_count) == 0) break; - ret = nfs_wait_bit_killable(&q.key); + ret = nfs_wait_bit_killable(&q.key, TASK_KILLABLE); } while (atomic_read(&c->io_count) != 0 && !ret); finish_wait(wq, &q.wait); return ret; diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 5a8ae2125b50..bec0384499f7 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1466,11 +1466,11 @@ static bool pnfs_within_mdsthreshold(struct nfs_open_context *ctx, } /* stop waiting if someone clears NFS_LAYOUT_RETRY_LAYOUTGET bit. */ -static int pnfs_layoutget_retry_bit_wait(struct wait_bit_key *key) +static int pnfs_layoutget_retry_bit_wait(struct wait_bit_key *key, int mode) { if (!test_bit(NFS_LAYOUT_RETRY_LAYOUTGET, key->flags)) return 1; - return nfs_wait_bit_killable(key); + return nfs_wait_bit_killable(key, mode); } static bool pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo) diff --git a/include/linux/wait.h b/include/linux/wait.h index 1e1bf9f963a9..513b36f04dfd 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -145,7 +145,7 @@ __remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old) list_del(&old->task_list); } -typedef int wait_bit_action_f(struct wait_bit_key *); +typedef int wait_bit_action_f(struct wait_bit_key *, int mode); void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key); void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key); void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr, void *key); @@ -960,10 +960,10 @@ int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *key); } while (0) -extern int bit_wait(struct wait_bit_key *); -extern int bit_wait_io(struct wait_bit_key *); -extern int bit_wait_timeout(struct wait_bit_key *); -extern int bit_wait_io_timeout(struct wait_bit_key *); +extern int bit_wait(struct wait_bit_key *, int); +extern int bit_wait_io(struct wait_bit_key *, int); +extern int bit_wait_timeout(struct wait_bit_key *, int); +extern int bit_wait_io_timeout(struct wait_bit_key *, int); /** * wait_on_bit - wait for a bit to be cleared diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index f10bd873e684..f15d6b6a538a 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -392,7 +392,7 @@ __wait_on_bit(wait_queue_head_t *wq, struct wait_bit_queue *q, do { prepare_to_wait(wq, &q->wait, mode); if (test_bit(q->key.bit_nr, q->key.flags)) - ret = (*action)(&q->key); + ret = (*action)(&q->key, mode); } while (test_bit(q->key.bit_nr, q->key.flags) && !ret); finish_wait(wq, &q->wait); return ret; @@ -431,7 +431,7 @@ __wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q, prepare_to_wait_exclusive(wq, &q->wait, mode); if (!test_bit(q->key.bit_nr, q->key.flags)) continue; - ret = action(&q->key); + ret = action(&q->key, mode); if (!ret) continue; abort_exclusive_wait(wq, &q->wait, mode, &q->key); @@ -581,43 +581,43 @@ void wake_up_atomic_t(atomic_t *p) } EXPORT_SYMBOL(wake_up_atomic_t); -__sched int bit_wait(struct wait_bit_key *word) +__sched int bit_wait(struct wait_bit_key *word, int mode) { schedule(); - if (signal_pending(current)) + if (signal_pending_state(mode, current)) return -EINTR; return 0; } EXPORT_SYMBOL(bit_wait); -__sched int bit_wait_io(struct wait_bit_key *word) +__sched int bit_wait_io(struct wait_bit_key *word, int mode) { io_schedule(); - if (signal_pending(current)) + if (signal_pending_state(mode, current)) return -EINTR; return 0; } EXPORT_SYMBOL(bit_wait_io); -__sched int bit_wait_timeout(struct wait_bit_key *word) +__sched int bit_wait_timeout(struct wait_bit_key *word, int mode) { unsigned long now = READ_ONCE(jiffies); if (time_after_eq(now, word->timeout)) return -EAGAIN; schedule_timeout(word->timeout - now); - if (signal_pending(current)) + if (signal_pending_state(mode, current)) return -EINTR; return 0; } EXPORT_SYMBOL_GPL(bit_wait_timeout); -__sched int bit_wait_io_timeout(struct wait_bit_key *word) +__sched int bit_wait_io_timeout(struct wait_bit_key *word, int mode) { unsigned long now = READ_ONCE(jiffies); if (time_after_eq(now, word->timeout)) return -EAGAIN; io_schedule_timeout(word->timeout - now); - if (signal_pending(current)) + if (signal_pending_state(mode, current)) return -EINTR; return 0; } diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index f14f24ee9983..73ad57a59989 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -250,11 +250,11 @@ void rpc_destroy_wait_queue(struct rpc_wait_queue *queue) } EXPORT_SYMBOL_GPL(rpc_destroy_wait_queue); -static int rpc_wait_bit_killable(struct wait_bit_key *key) +static int rpc_wait_bit_killable(struct wait_bit_key *key, int mode) { - if (fatal_signal_pending(current)) - return -ERESTARTSYS; freezable_schedule_unsafe(); + if (signal_pending_state(mode, current)) + return -ERESTARTSYS; return 0; } -- cgit v1.2.3 From 5a023cdba50c5f5f2bc351783b3131699deb3937 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 30 Nov 2015 10:20:29 -0800 Subject: block: enable dax for raw block devices If an application wants exclusive access to all of the persistent memory provided by an NVDIMM namespace it can use this raw-block-dax facility to forgo establishing a filesystem. This capability is targeted primarily to hypervisors wanting to provision persistent memory for guests. It can be disabled / enabled dynamically via the new BLKDAXSET ioctl. Cc: Jeff Moyer Cc: Christoph Hellwig Cc: Dave Chinner Cc: Andrew Morton Cc: Ross Zwisler Reported-by: kbuild test robot Reviewed-by: Jan Kara Signed-off-by: Dan Williams --- block/ioctl.c | 61 ++++++++++++++++++++++++++++ fs/block_dev.c | 103 ++++++++++++++++++++++++++++++++++++++++++++---- include/linux/fs.h | 11 ++++++ include/uapi/linux/fs.h | 2 + 4 files changed, 169 insertions(+), 8 deletions(-) (limited to 'include') diff --git a/block/ioctl.c b/block/ioctl.c index 0918aed2d847..7a964d842913 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -406,6 +406,62 @@ static inline int is_unrecognized_ioctl(int ret) ret == -ENOIOCTLCMD; } +#ifdef CONFIG_FS_DAX +bool blkdev_dax_capable(struct block_device *bdev) +{ + struct gendisk *disk = bdev->bd_disk; + + if (!disk->fops->direct_access) + return false; + + /* + * If the partition is not aligned on a page boundary, we can't + * do dax I/O to it. + */ + if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512)) + || (bdev->bd_part->nr_sects % (PAGE_SIZE / 512))) + return false; + + return true; +} + +static int blkdev_daxset(struct block_device *bdev, unsigned long argp) +{ + unsigned long arg; + int rc = 0; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + + if (get_user(arg, (int __user *)(argp))) + return -EFAULT; + arg = !!arg; + if (arg == !!(bdev->bd_inode->i_flags & S_DAX)) + return 0; + + if (arg) + arg = S_DAX; + + if (arg && !blkdev_dax_capable(bdev)) + return -ENOTTY; + + mutex_lock(&bdev->bd_inode->i_mutex); + if (bdev->bd_map_count == 0) + inode_set_flags(bdev->bd_inode, arg, S_DAX); + else + rc = -EBUSY; + mutex_unlock(&bdev->bd_inode->i_mutex); + return rc; +} +#else +static int blkdev_daxset(struct block_device *bdev, int arg) +{ + if (arg) + return -ENOTTY; + return 0; +} +#endif + static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode, unsigned cmd, unsigned long arg) { @@ -568,6 +624,11 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, case BLKTRACESETUP: case BLKTRACETEARDOWN: return blk_trace_ioctl(bdev, cmd, argp); + case BLKDAXSET: + return blkdev_daxset(bdev, arg); + case BLKDAXGET: + return put_int(arg, !!(bdev->bd_inode->i_flags & S_DAX)); + break; case IOC_PR_REGISTER: return blkdev_pr_register(bdev, argp); case IOC_PR_RESERVE: diff --git a/fs/block_dev.c b/fs/block_dev.c index 52248bce42d2..5c0b2cba870e 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1235,8 +1235,11 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) } } - if (!ret) + if (!ret) { bd_set_size(bdev,(loff_t)get_capacity(disk)<<9); + if (!blkdev_dax_capable(bdev)) + bdev->bd_inode->i_flags &= ~S_DAX; + } /* * If the device is invalidated, rescan partition @@ -1250,6 +1253,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) else if (ret == -ENOMEDIUM) invalidate_partitions(disk, bdev); } + if (ret) goto out_clear; } else { @@ -1270,12 +1274,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) goto out_clear; } bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9); - /* - * If the partition is not aligned on a page - * boundary, we can't do dax I/O to it. - */ - if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512)) || - (bdev->bd_part->nr_sects % (PAGE_SIZE / 512))) + if (!blkdev_dax_capable(bdev)) bdev->bd_inode->i_flags &= ~S_DAX; } } else { @@ -1713,13 +1712,101 @@ static const struct address_space_operations def_blk_aops = { .is_dirty_writeback = buffer_check_dirty_writeback, }; +#ifdef CONFIG_FS_DAX +/* + * In the raw block case we do not need to contend with truncation nor + * unwritten file extents. Without those concerns there is no need for + * additional locking beyond the mmap_sem context that these routines + * are already executing under. + * + * Note, there is no protection if the block device is dynamically + * resized (partition grow/shrink) during a fault. A stable block device + * size is already not enforced in the blkdev_direct_IO path. + * + * For DAX, it is the responsibility of the block device driver to + * ensure the whole-disk device size is stable while requests are in + * flight. + * + * Finally, unlike the filemap_page_mkwrite() case there is no + * filesystem superblock to sync against freezing. We still include a + * pfn_mkwrite callback for dax drivers to receive write fault + * notifications. + */ +static int blkdev_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + return __dax_fault(vma, vmf, blkdev_get_block, NULL); +} + +static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, + pmd_t *pmd, unsigned int flags) +{ + return __dax_pmd_fault(vma, addr, pmd, flags, blkdev_get_block, NULL); +} + +static void blkdev_vm_open(struct vm_area_struct *vma) +{ + struct inode *bd_inode = bdev_file_inode(vma->vm_file); + struct block_device *bdev = I_BDEV(bd_inode); + + mutex_lock(&bd_inode->i_mutex); + bdev->bd_map_count++; + mutex_unlock(&bd_inode->i_mutex); +} + +static void blkdev_vm_close(struct vm_area_struct *vma) +{ + struct inode *bd_inode = bdev_file_inode(vma->vm_file); + struct block_device *bdev = I_BDEV(bd_inode); + + mutex_lock(&bd_inode->i_mutex); + bdev->bd_map_count--; + mutex_unlock(&bd_inode->i_mutex); +} + +static const struct vm_operations_struct blkdev_dax_vm_ops = { + .open = blkdev_vm_open, + .close = blkdev_vm_close, + .fault = blkdev_dax_fault, + .pmd_fault = blkdev_dax_pmd_fault, + .pfn_mkwrite = blkdev_dax_fault, +}; + +static const struct vm_operations_struct blkdev_default_vm_ops = { + .open = blkdev_vm_open, + .close = blkdev_vm_close, + .fault = filemap_fault, + .map_pages = filemap_map_pages, +}; + +static int blkdev_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct inode *bd_inode = bdev_file_inode(file); + struct block_device *bdev = I_BDEV(bd_inode); + + file_accessed(file); + mutex_lock(&bd_inode->i_mutex); + bdev->bd_map_count++; + if (IS_DAX(bd_inode)) { + vma->vm_ops = &blkdev_dax_vm_ops; + vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE; + } else { + vma->vm_ops = &blkdev_default_vm_ops; + } + mutex_unlock(&bd_inode->i_mutex); + + return 0; +} +#else +#define blkdev_mmap generic_file_mmap +#endif + const struct file_operations def_blk_fops = { .open = blkdev_open, .release = blkdev_close, .llseek = block_llseek, .read_iter = blkdev_read_iter, .write_iter = blkdev_write_iter, - .mmap = generic_file_mmap, + .mmap = blkdev_mmap, .fsync = blkdev_fsync, .unlocked_ioctl = block_ioctl, #ifdef CONFIG_COMPAT diff --git a/include/linux/fs.h b/include/linux/fs.h index 3aa514254161..96fabc93b583 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -482,6 +482,9 @@ struct block_device { int bd_fsfreeze_count; /* Mutex for freeze */ struct mutex bd_fsfreeze_mutex; +#ifdef CONFIG_FS_DAX + int bd_map_count; +#endif }; /* @@ -2264,6 +2267,14 @@ extern struct super_block *freeze_bdev(struct block_device *); extern void emergency_thaw_all(void); extern int thaw_bdev(struct block_device *bdev, struct super_block *sb); extern int fsync_bdev(struct block_device *); +#ifdef CONFIG_FS_DAX +extern bool blkdev_dax_capable(struct block_device *bdev); +#else +static inline bool blkdev_dax_capable(struct block_device *bdev) +{ + return false; +} +#endif extern struct super_block *blockdev_superblock; diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index f15d980249b5..401c409e9239 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -152,6 +152,8 @@ struct inodes_stat_t { #define BLKSECDISCARD _IO(0x12,125) #define BLKROTATIONAL _IO(0x12,126) #define BLKZEROOUT _IO(0x12,127) +#define BLKDAXSET _IO(0x12,128) +#define BLKDAXGET _IO(0x12,129) #define BMAP_IOCTL 1 /* obsolete - kept for compatibility */ #define FIBMAP _IO(0x00,1) /* bmap access */ -- cgit v1.2.3 From 9e0e252a048b0ba5066f0dc15c3b2468ffe5c422 Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Thu, 24 Dec 2015 19:20:32 -0700 Subject: badblocks: Add core badblock management code Take the core badblocks implementation from md, and make it generally available. This follows the same style as kernel implementations of linked lists, rb-trees etc, where you can have a structure that can be embedded anywhere, and accessor functions to manipulate the data. The only changes in this copy of the code are ones to generalize function/variable names from md-specific ones. Also add init and free functions. Signed-off-by: Vishal Verma Signed-off-by: Dan Williams --- block/Makefile | 2 +- block/badblocks.c | 561 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/badblocks.h | 53 +++++ 3 files changed, 615 insertions(+), 1 deletion(-) create mode 100644 block/badblocks.c create mode 100644 include/linux/badblocks.h (limited to 'include') diff --git a/block/Makefile b/block/Makefile index 00ecc97629db..db5f622c9d67 100644 --- a/block/Makefile +++ b/block/Makefile @@ -8,7 +8,7 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \ blk-iopoll.o blk-lib.o blk-mq.o blk-mq-tag.o \ blk-mq-sysfs.o blk-mq-cpu.o blk-mq-cpumap.o ioctl.o \ genhd.o scsi_ioctl.o partition-generic.o ioprio.o \ - partitions/ + badblocks.o partitions/ obj-$(CONFIG_BOUNCE) += bounce.o obj-$(CONFIG_BLK_DEV_BSG) += bsg.o diff --git a/block/badblocks.c b/block/badblocks.c new file mode 100644 index 000000000000..96aeb9194a2e --- /dev/null +++ b/block/badblocks.c @@ -0,0 +1,561 @@ +/* + * Bad block management + * + * - Heavily based on MD badblocks code from Neil Brown + * + * Copyright (c) 2015, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include +#include +#include +#include +#include +#include +#include + +/** + * badblocks_check() - check a given range for bad sectors + * @bb: the badblocks structure that holds all badblock information + * @s: sector (start) at which to check for badblocks + * @sectors: number of sectors to check for badblocks + * @first_bad: pointer to store location of the first badblock + * @bad_sectors: pointer to store number of badblocks after @first_bad + * + * We can record which blocks on each device are 'bad' and so just + * fail those blocks, or that stripe, rather than the whole device. + * Entries in the bad-block table are 64bits wide. This comprises: + * Length of bad-range, in sectors: 0-511 for lengths 1-512 + * Start of bad-range, sector offset, 54 bits (allows 8 exbibytes) + * A 'shift' can be set so that larger blocks are tracked and + * consequently larger devices can be covered. + * 'Acknowledged' flag - 1 bit. - the most significant bit. + * + * Locking of the bad-block table uses a seqlock so badblocks_check + * might need to retry if it is very unlucky. + * We will sometimes want to check for bad blocks in a bi_end_io function, + * so we use the write_seqlock_irq variant. + * + * When looking for a bad block we specify a range and want to + * know if any block in the range is bad. So we binary-search + * to the last range that starts at-or-before the given endpoint, + * (or "before the sector after the target range") + * then see if it ends after the given start. + * + * Return: + * 0: there are no known bad blocks in the range + * 1: there are known bad block which are all acknowledged + * -1: there are bad blocks which have not yet been acknowledged in metadata. + * plus the start/length of the first bad section we overlap. + */ +int badblocks_check(struct badblocks *bb, sector_t s, int sectors, + sector_t *first_bad, int *bad_sectors) +{ + int hi; + int lo; + u64 *p = bb->page; + int rv; + sector_t target = s + sectors; + unsigned seq; + + if (bb->shift > 0) { + /* round the start down, and the end up */ + s >>= bb->shift; + target += (1<shift) - 1; + target >>= bb->shift; + sectors = target - s; + } + /* 'target' is now the first block after the bad range */ + +retry: + seq = read_seqbegin(&bb->lock); + lo = 0; + rv = 0; + hi = bb->count; + + /* Binary search between lo and hi for 'target' + * i.e. for the last range that starts before 'target' + */ + /* INVARIANT: ranges before 'lo' and at-or-after 'hi' + * are known not to be the last range before target. + * VARIANT: hi-lo is the number of possible + * ranges, and decreases until it reaches 1 + */ + while (hi - lo > 1) { + int mid = (lo + hi) / 2; + sector_t a = BB_OFFSET(p[mid]); + + if (a < target) + /* This could still be the one, earlier ranges + * could not. + */ + lo = mid; + else + /* This and later ranges are definitely out. */ + hi = mid; + } + /* 'lo' might be the last that started before target, but 'hi' isn't */ + if (hi > lo) { + /* need to check all range that end after 's' to see if + * any are unacknowledged. + */ + while (lo >= 0 && + BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > s) { + if (BB_OFFSET(p[lo]) < target) { + /* starts before the end, and finishes after + * the start, so they must overlap + */ + if (rv != -1 && BB_ACK(p[lo])) + rv = 1; + else + rv = -1; + *first_bad = BB_OFFSET(p[lo]); + *bad_sectors = BB_LEN(p[lo]); + } + lo--; + } + } + + if (read_seqretry(&bb->lock, seq)) + goto retry; + + return rv; +} +EXPORT_SYMBOL_GPL(badblocks_check); + +/** + * badblocks_set() - Add a range of bad blocks to the table. + * @bb: the badblocks structure that holds all badblock information + * @s: first sector to mark as bad + * @sectors: number of sectors to mark as bad + * @acknowledged: weather to mark the bad sectors as acknowledged + * + * This might extend the table, or might contract it if two adjacent ranges + * can be merged. We binary-search to find the 'insertion' point, then + * decide how best to handle it. + * + * Return: + * 0: success + * 1: failed to set badblocks (out of space) + */ +int badblocks_set(struct badblocks *bb, sector_t s, int sectors, + int acknowledged) +{ + u64 *p; + int lo, hi; + int rv = 0; + unsigned long flags; + + if (bb->shift < 0) + /* badblocks are disabled */ + return 0; + + if (bb->shift) { + /* round the start down, and the end up */ + sector_t next = s + sectors; + + s >>= bb->shift; + next += (1<shift) - 1; + next >>= bb->shift; + sectors = next - s; + } + + write_seqlock_irqsave(&bb->lock, flags); + + p = bb->page; + lo = 0; + hi = bb->count; + /* Find the last range that starts at-or-before 's' */ + while (hi - lo > 1) { + int mid = (lo + hi) / 2; + sector_t a = BB_OFFSET(p[mid]); + + if (a <= s) + lo = mid; + else + hi = mid; + } + if (hi > lo && BB_OFFSET(p[lo]) > s) + hi = lo; + + if (hi > lo) { + /* we found a range that might merge with the start + * of our new range + */ + sector_t a = BB_OFFSET(p[lo]); + sector_t e = a + BB_LEN(p[lo]); + int ack = BB_ACK(p[lo]); + + if (e >= s) { + /* Yes, we can merge with a previous range */ + if (s == a && s + sectors >= e) + /* new range covers old */ + ack = acknowledged; + else + ack = ack && acknowledged; + + if (e < s + sectors) + e = s + sectors; + if (e - a <= BB_MAX_LEN) { + p[lo] = BB_MAKE(a, e-a, ack); + s = e; + } else { + /* does not all fit in one range, + * make p[lo] maximal + */ + if (BB_LEN(p[lo]) != BB_MAX_LEN) + p[lo] = BB_MAKE(a, BB_MAX_LEN, ack); + s = a + BB_MAX_LEN; + } + sectors = e - s; + } + } + if (sectors && hi < bb->count) { + /* 'hi' points to the first range that starts after 's'. + * Maybe we can merge with the start of that range + */ + sector_t a = BB_OFFSET(p[hi]); + sector_t e = a + BB_LEN(p[hi]); + int ack = BB_ACK(p[hi]); + + if (a <= s + sectors) { + /* merging is possible */ + if (e <= s + sectors) { + /* full overlap */ + e = s + sectors; + ack = acknowledged; + } else + ack = ack && acknowledged; + + a = s; + if (e - a <= BB_MAX_LEN) { + p[hi] = BB_MAKE(a, e-a, ack); + s = e; + } else { + p[hi] = BB_MAKE(a, BB_MAX_LEN, ack); + s = a + BB_MAX_LEN; + } + sectors = e - s; + lo = hi; + hi++; + } + } + if (sectors == 0 && hi < bb->count) { + /* we might be able to combine lo and hi */ + /* Note: 's' is at the end of 'lo' */ + sector_t a = BB_OFFSET(p[hi]); + int lolen = BB_LEN(p[lo]); + int hilen = BB_LEN(p[hi]); + int newlen = lolen + hilen - (s - a); + + if (s >= a && newlen < BB_MAX_LEN) { + /* yes, we can combine them */ + int ack = BB_ACK(p[lo]) && BB_ACK(p[hi]); + + p[lo] = BB_MAKE(BB_OFFSET(p[lo]), newlen, ack); + memmove(p + hi, p + hi + 1, + (bb->count - hi - 1) * 8); + bb->count--; + } + } + while (sectors) { + /* didn't merge (it all). + * Need to add a range just before 'hi' + */ + if (bb->count >= MAX_BADBLOCKS) { + /* No room for more */ + rv = 1; + break; + } else { + int this_sectors = sectors; + + memmove(p + hi + 1, p + hi, + (bb->count - hi) * 8); + bb->count++; + + if (this_sectors > BB_MAX_LEN) + this_sectors = BB_MAX_LEN; + p[hi] = BB_MAKE(s, this_sectors, acknowledged); + sectors -= this_sectors; + s += this_sectors; + } + } + + bb->changed = 1; + if (!acknowledged) + bb->unacked_exist = 1; + write_sequnlock_irqrestore(&bb->lock, flags); + + return rv; +} +EXPORT_SYMBOL_GPL(badblocks_set); + +/** + * badblocks_clear() - Remove a range of bad blocks to the table. + * @bb: the badblocks structure that holds all badblock information + * @s: first sector to mark as bad + * @sectors: number of sectors to mark as bad + * + * This may involve extending the table if we spilt a region, + * but it must not fail. So if the table becomes full, we just + * drop the remove request. + * + * Return: + * 0: success + * 1: failed to clear badblocks + */ +int badblocks_clear(struct badblocks *bb, sector_t s, int sectors) +{ + u64 *p; + int lo, hi; + sector_t target = s + sectors; + int rv = 0; + + if (bb->shift > 0) { + /* When clearing we round the start up and the end down. + * This should not matter as the shift should align with + * the block size and no rounding should ever be needed. + * However it is better the think a block is bad when it + * isn't than to think a block is not bad when it is. + */ + s += (1<shift) - 1; + s >>= bb->shift; + target >>= bb->shift; + sectors = target - s; + } + + write_seqlock_irq(&bb->lock); + + p = bb->page; + lo = 0; + hi = bb->count; + /* Find the last range that starts before 'target' */ + while (hi - lo > 1) { + int mid = (lo + hi) / 2; + sector_t a = BB_OFFSET(p[mid]); + + if (a < target) + lo = mid; + else + hi = mid; + } + if (hi > lo) { + /* p[lo] is the last range that could overlap the + * current range. Earlier ranges could also overlap, + * but only this one can overlap the end of the range. + */ + if (BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > target) { + /* Partial overlap, leave the tail of this range */ + int ack = BB_ACK(p[lo]); + sector_t a = BB_OFFSET(p[lo]); + sector_t end = a + BB_LEN(p[lo]); + + if (a < s) { + /* we need to split this range */ + if (bb->count >= MAX_BADBLOCKS) { + rv = -ENOSPC; + goto out; + } + memmove(p+lo+1, p+lo, (bb->count - lo) * 8); + bb->count++; + p[lo] = BB_MAKE(a, s-a, ack); + lo++; + } + p[lo] = BB_MAKE(target, end - target, ack); + /* there is no longer an overlap */ + hi = lo; + lo--; + } + while (lo >= 0 && + BB_OFFSET(p[lo]) + BB_LEN(p[lo]) > s) { + /* This range does overlap */ + if (BB_OFFSET(p[lo]) < s) { + /* Keep the early parts of this range. */ + int ack = BB_ACK(p[lo]); + sector_t start = BB_OFFSET(p[lo]); + + p[lo] = BB_MAKE(start, s - start, ack); + /* now low doesn't overlap, so.. */ + break; + } + lo--; + } + /* 'lo' is strictly before, 'hi' is strictly after, + * anything between needs to be discarded + */ + if (hi - lo > 1) { + memmove(p+lo+1, p+hi, (bb->count - hi) * 8); + bb->count -= (hi - lo - 1); + } + } + + bb->changed = 1; +out: + write_sequnlock_irq(&bb->lock); + return rv; +} +EXPORT_SYMBOL_GPL(badblocks_clear); + +/** + * ack_all_badblocks() - Acknowledge all bad blocks in a list. + * @bb: the badblocks structure that holds all badblock information + * + * This only succeeds if ->changed is clear. It is used by + * in-kernel metadata updates + */ +void ack_all_badblocks(struct badblocks *bb) +{ + if (bb->page == NULL || bb->changed) + /* no point even trying */ + return; + write_seqlock_irq(&bb->lock); + + if (bb->changed == 0 && bb->unacked_exist) { + u64 *p = bb->page; + int i; + + for (i = 0; i < bb->count ; i++) { + if (!BB_ACK(p[i])) { + sector_t start = BB_OFFSET(p[i]); + int len = BB_LEN(p[i]); + + p[i] = BB_MAKE(start, len, 1); + } + } + bb->unacked_exist = 0; + } + write_sequnlock_irq(&bb->lock); +} +EXPORT_SYMBOL_GPL(ack_all_badblocks); + +/** + * badblocks_show() - sysfs access to bad-blocks list + * @bb: the badblocks structure that holds all badblock information + * @page: buffer received from sysfs + * @unack: weather to show unacknowledged badblocks + * + * Return: + * Length of returned data + */ +ssize_t badblocks_show(struct badblocks *bb, char *page, int unack) +{ + size_t len; + int i; + u64 *p = bb->page; + unsigned seq; + + if (bb->shift < 0) + return 0; + +retry: + seq = read_seqbegin(&bb->lock); + + len = 0; + i = 0; + + while (len < PAGE_SIZE && i < bb->count) { + sector_t s = BB_OFFSET(p[i]); + unsigned int length = BB_LEN(p[i]); + int ack = BB_ACK(p[i]); + + i++; + + if (unack && ack) + continue; + + len += snprintf(page+len, PAGE_SIZE-len, "%llu %u\n", + (unsigned long long)s << bb->shift, + length << bb->shift); + } + if (unack && len == 0) + bb->unacked_exist = 0; + + if (read_seqretry(&bb->lock, seq)) + goto retry; + + return len; +} +EXPORT_SYMBOL_GPL(badblocks_show); + +/** + * badblocks_store() - sysfs access to bad-blocks list + * @bb: the badblocks structure that holds all badblock information + * @page: buffer received from sysfs + * @len: length of data received from sysfs + * @unack: weather to show unacknowledged badblocks + * + * Return: + * Length of the buffer processed or -ve error. + */ +ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len, + int unack) +{ + unsigned long long sector; + int length; + char newline; + + switch (sscanf(page, "%llu %d%c", §or, &length, &newline)) { + case 3: + if (newline != '\n') + return -EINVAL; + case 2: + if (length <= 0) + return -EINVAL; + break; + default: + return -EINVAL; + } + + if (badblocks_set(bb, sector, length, !unack)) + return -ENOSPC; + else + return len; +} +EXPORT_SYMBOL_GPL(badblocks_store); + +/** + * badblocks_init() - initialize the badblocks structure + * @bb: the badblocks structure that holds all badblock information + * @enable: weather to enable badblocks accounting + * + * Return: + * 0: success + * -ve errno: on error + */ +int badblocks_init(struct badblocks *bb, int enable) +{ + bb->count = 0; + if (enable) + bb->shift = 0; + else + bb->shift = -1; + bb->page = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (bb->page == (u64 *)0) { + bb->shift = -1; + return -ENOMEM; + } + seqlock_init(&bb->lock); + + return 0; +} +EXPORT_SYMBOL_GPL(badblocks_init); + +/** + * badblocks_free() - free the badblocks structure + * @bb: the badblocks structure that holds all badblock information + */ +void badblocks_free(struct badblocks *bb) +{ + kfree(bb->page); + bb->page = NULL; +} +EXPORT_SYMBOL_GPL(badblocks_free); diff --git a/include/linux/badblocks.h b/include/linux/badblocks.h new file mode 100644 index 000000000000..929344630b51 --- /dev/null +++ b/include/linux/badblocks.h @@ -0,0 +1,53 @@ +#ifndef _LINUX_BADBLOCKS_H +#define _LINUX_BADBLOCKS_H + +#include +#include +#include +#include + +#define BB_LEN_MASK (0x00000000000001FFULL) +#define BB_OFFSET_MASK (0x7FFFFFFFFFFFFE00ULL) +#define BB_ACK_MASK (0x8000000000000000ULL) +#define BB_MAX_LEN 512 +#define BB_OFFSET(x) (((x) & BB_OFFSET_MASK) >> 9) +#define BB_LEN(x) (((x) & BB_LEN_MASK) + 1) +#define BB_ACK(x) (!!((x) & BB_ACK_MASK)) +#define BB_MAKE(a, l, ack) (((a)<<9) | ((l)-1) | ((u64)(!!(ack)) << 63)) + +/* Bad block numbers are stored sorted in a single page. + * 64bits is used for each block or extent. + * 54 bits are sector number, 9 bits are extent size, + * 1 bit is an 'acknowledged' flag. + */ +#define MAX_BADBLOCKS (PAGE_SIZE/8) + +struct badblocks { + int count; /* count of bad blocks */ + int unacked_exist; /* there probably are unacknowledged + * bad blocks. This is only cleared + * when a read discovers none + */ + int shift; /* shift from sectors to block size + * a -ve shift means badblocks are + * disabled.*/ + u64 *page; /* badblock list */ + int changed; + seqlock_t lock; + sector_t sector; + sector_t size; /* in sectors */ +}; + +int badblocks_check(struct badblocks *bb, sector_t s, int sectors, + sector_t *first_bad, int *bad_sectors); +int badblocks_set(struct badblocks *bb, sector_t s, int sectors, + int acknowledged); +int badblocks_clear(struct badblocks *bb, sector_t s, int sectors); +void ack_all_badblocks(struct badblocks *bb); +ssize_t badblocks_show(struct badblocks *bb, char *page, int unack); +ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len, + int unack); +int badblocks_init(struct badblocks *bb, int enable); +void badblocks_free(struct badblocks *bb); + +#endif -- cgit v1.2.3 From 99e6608c9e7414ae4f2168df8bf8fae3eb49e41f Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Sat, 9 Jan 2016 08:36:51 -0800 Subject: block: Add badblock management for gendisks NVDIMM devices, which can behave more like DRAM rather than block devices, may develop bad cache lines, or 'poison'. A block device exposed by the pmem driver can then consume poison via a read (or write), and cause a machine check. On platforms without machine check recovery features, this would mean a crash. The block device maintaining a runtime list of all known sectors that have poison can directly avoid this, and also provide a path forward to enable proper handling/recovery for DAX faults on such a device. Use the new badblock management interfaces to add a badblocks list to gendisks. Signed-off-by: Vishal Verma Signed-off-by: Dan Williams --- block/genhd.c | 76 +++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/genhd.h | 7 +++++ 2 files changed, 83 insertions(+) (limited to 'include') diff --git a/block/genhd.c b/block/genhd.c index 1a971bebbbfe..88579cf373b8 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -20,6 +20,7 @@ #include #include #include +#include #include "blk.h" @@ -505,6 +506,16 @@ static int exact_lock(dev_t devt, void *data) return 0; } +int disk_alloc_badblocks(struct gendisk *disk) +{ + disk->bb = kzalloc(sizeof(*(disk->bb)), GFP_KERNEL); + if (!disk->bb) + return -ENOMEM; + + return badblocks_init(disk->bb, 1); +} +EXPORT_SYMBOL(disk_alloc_badblocks); + static void register_disk(struct gendisk *disk) { struct device *ddev = disk_to_dev(disk); @@ -659,6 +670,11 @@ void del_gendisk(struct gendisk *disk) blk_unregister_queue(disk); blk_unregister_region(disk_devt(disk), disk->minors); + if (disk->bb) { + badblocks_free(disk->bb); + kfree(disk->bb); + } + part_stat_set_all(&disk->part0, 0); disk->part0.stamp = 0; @@ -671,6 +687,63 @@ void del_gendisk(struct gendisk *disk) } EXPORT_SYMBOL(del_gendisk); +/* + * The gendisk usage of badblocks does not track acknowledgements for + * badblocks. We always assume they are acknowledged. + */ +int disk_check_badblocks(struct gendisk *disk, sector_t s, int sectors, + sector_t *first_bad, int *bad_sectors) +{ + if (!disk->bb) + return 0; + + return badblocks_check(disk->bb, s, sectors, first_bad, bad_sectors); +} +EXPORT_SYMBOL(disk_check_badblocks); + +int disk_set_badblocks(struct gendisk *disk, sector_t s, int sectors) +{ + if (!disk->bb) + return 0; + + return badblocks_set(disk->bb, s, sectors, 1); +} +EXPORT_SYMBOL(disk_set_badblocks); + +int disk_clear_badblocks(struct gendisk *disk, sector_t s, int sectors) +{ + if (!disk->bb) + return 0; + + return badblocks_clear(disk->bb, s, sectors); +} +EXPORT_SYMBOL(disk_clear_badblocks); + +/* sysfs access to bad-blocks list. */ +static ssize_t disk_badblocks_show(struct device *dev, + struct device_attribute *attr, + char *page) +{ + struct gendisk *disk = dev_to_disk(dev); + + if (!disk->bb) + return sprintf(page, "\n"); + + return badblocks_show(disk->bb, page, 0); +} + +static ssize_t disk_badblocks_store(struct device *dev, + struct device_attribute *attr, + const char *page, size_t len) +{ + struct gendisk *disk = dev_to_disk(dev); + + if (!disk->bb) + return -ENXIO; + + return badblocks_store(disk->bb, page, len, 0); +} + /** * get_gendisk - get partitioning information for a given device * @devt: device to get partitioning information for @@ -989,6 +1062,8 @@ static DEVICE_ATTR(discard_alignment, S_IRUGO, disk_discard_alignment_show, static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL); static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL); static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL); +static DEVICE_ATTR(badblocks, S_IRUGO | S_IWUSR, disk_badblocks_show, + disk_badblocks_store); #ifdef CONFIG_FAIL_MAKE_REQUEST static struct device_attribute dev_attr_fail = __ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store); @@ -1010,6 +1085,7 @@ static struct attribute *disk_attrs[] = { &dev_attr_capability.attr, &dev_attr_stat.attr, &dev_attr_inflight.attr, + &dev_attr_badblocks.attr, #ifdef CONFIG_FAIL_MAKE_REQUEST &dev_attr_fail.attr, #endif diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 847cc1d91634..0bbec6880051 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -162,6 +162,7 @@ struct disk_part_tbl { }; struct disk_events; +struct badblocks; #if defined(CONFIG_BLK_DEV_INTEGRITY) @@ -213,6 +214,7 @@ struct gendisk { struct kobject integrity_kobj; #endif /* CONFIG_BLK_DEV_INTEGRITY */ int node_id; + struct badblocks *bb; }; static inline struct gendisk *part_to_disk(struct hd_struct *part) @@ -433,6 +435,11 @@ extern void add_disk(struct gendisk *disk); extern void del_gendisk(struct gendisk *gp); extern struct gendisk *get_gendisk(dev_t dev, int *partno); extern struct block_device *bdget_disk(struct gendisk *disk, int partno); +int disk_alloc_badblocks(struct gendisk *disk); +extern int disk_check_badblocks(struct gendisk *disk, sector_t s, int sectors, + sector_t *first_bad, int *bad_sectors); +extern int disk_set_badblocks(struct gendisk *disk, sector_t s, int sectors); +extern int disk_clear_badblocks(struct gendisk *disk, sector_t s, int sectors); extern void set_device_ro(struct block_device *bdev, int flag); extern void set_disk_ro(struct gendisk *disk, int flag); -- cgit v1.2.3 From 0caeef63e6d2f866d85bb507bf63e0ce8ec91cef Mon Sep 17 00:00:00 2001 From: Vishal Verma Date: Thu, 24 Dec 2015 19:21:43 -0700 Subject: libnvdimm: Add a poison list and export badblocks During region creation, perform Address Range Scrubs (ARS) for the SPA (System Physical Address) ranges to retrieve known poison locations from firmware. Add a new data structure 'nd_poison' which is used as a list in nvdimm_bus to store these poison locations. When creating a pmem namespace, if there is any known poison associated with its physical address space, convert the poison ranges to bad sectors that are exposed using the badblocks interface. Signed-off-by: Vishal Verma Signed-off-by: Dan Williams --- drivers/acpi/nfit.c | 203 ++++++++++++++++++++++++++++++++++++++++++++++ drivers/nvdimm/core.c | 187 ++++++++++++++++++++++++++++++++++++++++++ drivers/nvdimm/nd-core.h | 3 + drivers/nvdimm/nd.h | 6 ++ drivers/nvdimm/pmem.c | 6 ++ include/linux/libnvdimm.h | 1 + 6 files changed, 406 insertions(+) (limited to 'include') diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c index e7ed39bab97d..e1dbc8da09b7 100644 --- a/drivers/acpi/nfit.c +++ b/drivers/acpi/nfit.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -1473,6 +1474,201 @@ static void acpi_nfit_blk_region_disable(struct nvdimm_bus *nvdimm_bus, /* devm will free nfit_blk */ } +static int ars_get_cap(struct nvdimm_bus_descriptor *nd_desc, + struct nd_cmd_ars_cap *cmd, u64 addr, u64 length) +{ + cmd->address = addr; + cmd->length = length; + + return nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_CAP, cmd, + sizeof(*cmd)); +} + +static int ars_do_start(struct nvdimm_bus_descriptor *nd_desc, + struct nd_cmd_ars_start *cmd, u64 addr, u64 length) +{ + int rc; + + cmd->address = addr; + cmd->length = length; + cmd->type = ND_ARS_PERSISTENT; + + while (1) { + rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_START, cmd, + sizeof(*cmd)); + if (rc) + return rc; + switch (cmd->status) { + case 0: + return 0; + case 1: + /* ARS unsupported, but we should never get here */ + return 0; + case 2: + return -EINVAL; + case 3: + /* ARS is in progress */ + msleep(1000); + break; + default: + return -ENXIO; + } + } +} + +static int ars_get_status(struct nvdimm_bus_descriptor *nd_desc, + struct nd_cmd_ars_status *cmd) +{ + int rc; + + while (1) { + rc = nd_desc->ndctl(nd_desc, NULL, ND_CMD_ARS_STATUS, cmd, + sizeof(*cmd)); + if (rc || cmd->status & 0xffff) + return -ENXIO; + + /* Check extended status (Upper two bytes) */ + switch (cmd->status >> 16) { + case 0: + return 0; + case 1: + /* ARS is in progress */ + msleep(1000); + break; + case 2: + /* No ARS performed for the current boot */ + return 0; + default: + return -ENXIO; + } + } +} + +static int ars_status_process_records(struct nvdimm_bus *nvdimm_bus, + struct nd_cmd_ars_status *ars_status, u64 start) +{ + int rc; + u32 i; + + /* + * The address field returned by ars_status should be either + * less than or equal to the address we last started ARS for. + * The (start, length) returned by ars_status should also have + * non-zero overlap with the range we started ARS for. + * If this is not the case, bail. + */ + if (ars_status->address > start || + (ars_status->address + ars_status->length < start)) + return -ENXIO; + + for (i = 0; i < ars_status->num_records; i++) { + rc = nvdimm_bus_add_poison(nvdimm_bus, + ars_status->records[i].err_address, + ars_status->records[i].length); + if (rc) + return rc; + } + + return 0; +} + +static int acpi_nfit_find_poison(struct acpi_nfit_desc *acpi_desc, + struct nd_region_desc *ndr_desc) +{ + struct nvdimm_bus_descriptor *nd_desc = &acpi_desc->nd_desc; + struct nvdimm_bus *nvdimm_bus = acpi_desc->nvdimm_bus; + struct nd_cmd_ars_status *ars_status = NULL; + struct nd_cmd_ars_start *ars_start = NULL; + struct nd_cmd_ars_cap *ars_cap = NULL; + u64 start, len, cur, remaining; + int rc; + + ars_cap = kzalloc(sizeof(*ars_cap), GFP_KERNEL); + if (!ars_cap) + return -ENOMEM; + + start = ndr_desc->res->start; + len = ndr_desc->res->end - ndr_desc->res->start + 1; + + rc = ars_get_cap(nd_desc, ars_cap, start, len); + if (rc) + goto out; + + /* + * If ARS is unsupported, or if the 'Persistent Memory Scrub' flag in + * extended status is not set, skip this but continue initialization + */ + if ((ars_cap->status & 0xffff) || + !(ars_cap->status >> 16 & ND_ARS_PERSISTENT)) { + dev_warn(acpi_desc->dev, + "ARS unsupported (status: 0x%x), won't create an error list\n", + ars_cap->status); + goto out; + } + + /* + * Check if a full-range ARS has been run. If so, use those results + * without having to start a new ARS. + */ + ars_status = kzalloc(ars_cap->max_ars_out + sizeof(*ars_status), + GFP_KERNEL); + if (!ars_status) { + rc = -ENOMEM; + goto out; + } + + rc = ars_get_status(nd_desc, ars_status); + if (rc) + goto out; + + if (ars_status->address <= start && + (ars_status->address + ars_status->length >= start + len)) { + rc = ars_status_process_records(nvdimm_bus, ars_status, start); + goto out; + } + + /* + * ARS_STATUS can overflow if the number of poison entries found is + * greater than the maximum buffer size (ars_cap->max_ars_out) + * To detect overflow, check if the length field of ars_status + * is less than the length we supplied. If so, process the + * error entries we got, adjust the start point, and start again + */ + ars_start = kzalloc(sizeof(*ars_start), GFP_KERNEL); + if (!ars_start) + return -ENOMEM; + + cur = start; + remaining = len; + do { + u64 done, end; + + rc = ars_do_start(nd_desc, ars_start, cur, remaining); + if (rc) + goto out; + + rc = ars_get_status(nd_desc, ars_status); + if (rc) + goto out; + + rc = ars_status_process_records(nvdimm_bus, ars_status, cur); + if (rc) + goto out; + + end = min(cur + remaining, + ars_status->address + ars_status->length); + done = end - cur; + cur += done; + remaining -= done; + } while (remaining); + + out: + kfree(ars_cap); + kfree(ars_start); + kfree(ars_status); + return rc; +} + static int acpi_nfit_init_mapping(struct acpi_nfit_desc *acpi_desc, struct nd_mapping *nd_mapping, struct nd_region_desc *ndr_desc, struct acpi_nfit_memory_map *memdev, @@ -1585,6 +1781,13 @@ static int acpi_nfit_register_region(struct acpi_nfit_desc *acpi_desc, nvdimm_bus = acpi_desc->nvdimm_bus; if (nfit_spa_type(spa) == NFIT_SPA_PM) { + rc = acpi_nfit_find_poison(acpi_desc, ndr_desc); + if (rc) { + dev_err(acpi_desc->dev, + "error while performing ARS to find poison: %d\n", + rc); + return rc; + } if (!nvdimm_pmem_region_create(nvdimm_bus, ndr_desc)) return -ENOMEM; } else if (nfit_spa_type(spa) == NFIT_SPA_VOLATILE) { diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c index 82c49bb87055..21003b7f0b38 100644 --- a/drivers/nvdimm/core.c +++ b/drivers/nvdimm/core.c @@ -325,6 +325,7 @@ struct nvdimm_bus *__nvdimm_bus_register(struct device *parent, if (!nvdimm_bus) return NULL; INIT_LIST_HEAD(&nvdimm_bus->list); + INIT_LIST_HEAD(&nvdimm_bus->poison_list); init_waitqueue_head(&nvdimm_bus->probe_wait); nvdimm_bus->id = ida_simple_get(&nd_ida, 0, 0, GFP_KERNEL); mutex_init(&nvdimm_bus->reconfig_mutex); @@ -359,6 +360,191 @@ struct nvdimm_bus *__nvdimm_bus_register(struct device *parent, } EXPORT_SYMBOL_GPL(__nvdimm_bus_register); +/** + * __add_badblock_range() - Convert a physical address range to bad sectors + * @disk: the disk associated with the namespace + * @ns_offset: namespace offset where the error range begins (in bytes) + * @len: number of bytes of poison to be added + * + * This assumes that the range provided with (ns_offset, len) is within + * the bounds of physical addresses for this namespace, i.e. lies in the + * interval [ns_start, ns_start + ns_size) + */ +static int __add_badblock_range(struct gendisk *disk, u64 ns_offset, u64 len) +{ + unsigned int sector_size = queue_logical_block_size(disk->queue); + sector_t start_sector; + u64 num_sectors; + u32 rem; + int rc; + + start_sector = div_u64(ns_offset, sector_size); + num_sectors = div_u64_rem(len, sector_size, &rem); + if (rem) + num_sectors++; + + if (!disk->bb) { + rc = disk_alloc_badblocks(disk); + if (rc) + return rc; + } + + if (unlikely(num_sectors > (u64)INT_MAX)) { + u64 remaining = num_sectors; + sector_t s = start_sector; + + while (remaining) { + int done = min_t(u64, remaining, INT_MAX); + + rc = disk_set_badblocks(disk, s, done); + if (rc) + return rc; + remaining -= done; + s += done; + } + return 0; + } else + return disk_set_badblocks(disk, start_sector, num_sectors); +} + +/** + * nvdimm_namespace_add_poison() - Convert a list of poison ranges to badblocks + * @disk: the gendisk associated with the namespace where badblocks + * will be stored + * @offset: offset at the start of the namespace before 'sector 0' + * @ndns: the namespace containing poison ranges + * + * The poison list generated during NFIT initialization may contain multiple, + * possibly overlapping ranges in the SPA (System Physical Address) space. + * Compare each of these ranges to the namespace currently being initialized, + * and add badblocks to the gendisk for all matching sub-ranges + * + * Return: + * 0 - Success + */ +int nvdimm_namespace_add_poison(struct gendisk *disk, resource_size_t offset, + struct nd_namespace_common *ndns) +{ + struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev); + struct nd_region *nd_region = to_nd_region(ndns->dev.parent); + struct nvdimm_bus *nvdimm_bus; + struct list_head *poison_list; + u64 ns_start, ns_end, ns_size; + struct nd_poison *pl; + int rc; + + ns_size = nvdimm_namespace_capacity(ndns) - offset; + ns_start = nsio->res.start + offset; + ns_end = nsio->res.end; + + nvdimm_bus = to_nvdimm_bus(nd_region->dev.parent); + poison_list = &nvdimm_bus->poison_list; + if (list_empty(poison_list)) + return 0; + + list_for_each_entry(pl, poison_list, list) { + u64 pl_end = pl->start + pl->length - 1; + + /* Discard intervals with no intersection */ + if (pl_end < ns_start) + continue; + if (pl->start > ns_end) + continue; + /* Deal with any overlap after start of the namespace */ + if (pl->start >= ns_start) { + u64 start = pl->start; + u64 len; + + if (pl_end <= ns_end) + len = pl->length; + else + len = ns_start + ns_size - pl->start; + + rc = __add_badblock_range(disk, start - ns_start, len); + if (rc) + return rc; + dev_info(&nvdimm_bus->dev, + "Found a poison range (0x%llx, 0x%llx)\n", + start, len); + continue; + } + /* Deal with overlap for poison starting before the namespace */ + if (pl->start < ns_start) { + u64 len; + + if (pl_end < ns_end) + len = pl->start + pl->length - ns_start; + else + len = ns_size; + + rc = __add_badblock_range(disk, 0, len); + if (rc) + return rc; + dev_info(&nvdimm_bus->dev, + "Found a poison range (0x%llx, 0x%llx)\n", + pl->start, len); + } + } + + return 0; +} +EXPORT_SYMBOL_GPL(nvdimm_namespace_add_poison); + +static int __add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length) +{ + struct nd_poison *pl; + + pl = kzalloc(sizeof(*pl), GFP_KERNEL); + if (!pl) + return -ENOMEM; + + pl->start = addr; + pl->length = length; + list_add_tail(&pl->list, &nvdimm_bus->poison_list); + + return 0; +} + +int nvdimm_bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length) +{ + struct nd_poison *pl; + + if (list_empty(&nvdimm_bus->poison_list)) + return __add_poison(nvdimm_bus, addr, length); + + /* + * There is a chance this is a duplicate, check for those first. + * This will be the common case as ARS_STATUS returns all known + * errors in the SPA space, and we can't query it per region + */ + list_for_each_entry(pl, &nvdimm_bus->poison_list, list) + if (pl->start == addr) { + /* If length has changed, update this list entry */ + if (pl->length != length) + pl->length = length; + return 0; + } + + /* + * If not a duplicate or a simple length update, add the entry as is, + * as any overlapping ranges will get resolved when the list is consumed + * and converted to badblocks + */ + return __add_poison(nvdimm_bus, addr, length); +} +EXPORT_SYMBOL_GPL(nvdimm_bus_add_poison); + +static void free_poison_list(struct list_head *poison_list) +{ + struct nd_poison *pl, *next; + + list_for_each_entry_safe(pl, next, poison_list, list) { + list_del(&pl->list); + kfree(pl); + } + list_del_init(poison_list); +} + static int child_unregister(struct device *dev, void *data) { /* @@ -385,6 +571,7 @@ void nvdimm_bus_unregister(struct nvdimm_bus *nvdimm_bus) nd_synchronize(); device_for_each_child(&nvdimm_bus->dev, NULL, child_unregister); + free_poison_list(&nvdimm_bus->poison_list); nvdimm_bus_destroy_ndctl(nvdimm_bus); device_unregister(&nvdimm_bus->dev); diff --git a/drivers/nvdimm/nd-core.h b/drivers/nvdimm/nd-core.h index 159aed532042..d3b7ea78df96 100644 --- a/drivers/nvdimm/nd-core.h +++ b/drivers/nvdimm/nd-core.h @@ -30,6 +30,7 @@ struct nvdimm_bus { struct list_head list; struct device dev; int id, probe_active; + struct list_head poison_list; struct mutex reconfig_mutex; }; @@ -89,4 +90,6 @@ bool __nd_attach_ndns(struct device *dev, struct nd_namespace_common *attach, ssize_t nd_namespace_store(struct device *dev, struct nd_namespace_common **_ndns, const char *buf, size_t len); +int nvdimm_namespace_add_poison(struct gendisk *disk, resource_size_t offset, + struct nd_namespace_common *ndns); #endif /* __ND_CORE_H__ */ diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index 417e521d299c..ba91fcd5818d 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -38,6 +38,12 @@ enum { #endif }; +struct nd_poison { + u64 start; + u64 length; + struct list_head list; +}; + struct nvdimm_drvdata { struct device *dev; int nsindex_size; diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 8ee79893d2f5..5b95043443a3 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -27,6 +27,7 @@ #include #include #include +#include "nd-core.h" #include "pfn.h" #include "nd.h" @@ -168,6 +169,7 @@ static int pmem_attach_disk(struct device *dev, { int nid = dev_to_node(dev); struct gendisk *disk; + int ret; pmem->pmem_queue = blk_alloc_queue_node(GFP_KERNEL, nid); if (!pmem->pmem_queue) @@ -196,6 +198,10 @@ static int pmem_attach_disk(struct device *dev, set_capacity(disk, (pmem->size - pmem->data_offset) / 512); pmem->pmem_disk = disk; + ret = nvdimm_namespace_add_poison(disk, pmem->data_offset, ndns); + if (ret) + return ret; + add_disk(disk); revalidate_disk(disk); diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 3f021dc5da8c..bed40dff0e86 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -116,6 +116,7 @@ static inline struct nd_blk_region_desc *to_blk_region_desc( } +int nvdimm_bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length); struct nvdimm_bus *__nvdimm_bus_register(struct device *parent, struct nvdimm_bus_descriptor *nfit_desc, struct module *module); #define nvdimm_bus_register(parent, desc) \ -- cgit v1.2.3 From d3b407fb3f782bd915db64e266010ea30a2d381e Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 6 Jan 2016 12:19:22 -0800 Subject: badblocks: rename badblocks_free to badblocks_exit For symmetry with badblocks_init() make it clear that this path only destroys incremental allocations of a badblocks instance, and does not free the badblocks instance itself. Signed-off-by: Dan Williams --- block/badblocks.c | 6 +++--- block/genhd.c | 2 +- drivers/md/md.c | 2 +- include/linux/badblocks.h | 2 +- 4 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include') diff --git a/block/badblocks.c b/block/badblocks.c index 96aeb9194a2e..fabf6b64c2d1 100644 --- a/block/badblocks.c +++ b/block/badblocks.c @@ -550,12 +550,12 @@ int badblocks_init(struct badblocks *bb, int enable) EXPORT_SYMBOL_GPL(badblocks_init); /** - * badblocks_free() - free the badblocks structure + * badblocks_exit() - free the badblocks structure * @bb: the badblocks structure that holds all badblock information */ -void badblocks_free(struct badblocks *bb) +void badblocks_exit(struct badblocks *bb) { kfree(bb->page); bb->page = NULL; } -EXPORT_SYMBOL_GPL(badblocks_free); +EXPORT_SYMBOL_GPL(badblocks_exit); diff --git a/block/genhd.c b/block/genhd.c index 88579cf373b8..f463c67e6ba2 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -671,7 +671,7 @@ void del_gendisk(struct gendisk *disk) blk_unregister_region(disk_devt(disk), disk->minors); if (disk->bb) { - badblocks_free(disk->bb); + badblocks_exit(disk->bb); kfree(disk->bb); } diff --git a/drivers/md/md.c b/drivers/md/md.c index 1e48aa9de352..96a991821ae6 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -710,7 +710,7 @@ void md_rdev_clear(struct md_rdev *rdev) put_page(rdev->bb_page); rdev->bb_page = NULL; } - badblocks_free(&rdev->badblocks); + badblocks_exit(&rdev->badblocks); } EXPORT_SYMBOL_GPL(md_rdev_clear); diff --git a/include/linux/badblocks.h b/include/linux/badblocks.h index 929344630b51..2d98c026c57f 100644 --- a/include/linux/badblocks.h +++ b/include/linux/badblocks.h @@ -48,6 +48,6 @@ ssize_t badblocks_show(struct badblocks *bb, char *page, int unack); ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len, int unack); int badblocks_init(struct badblocks *bb, int enable); -void badblocks_free(struct badblocks *bb); +void badblocks_exit(struct badblocks *bb); #endif -- cgit v1.2.3 From 16263ff6c72eb4cc00aa287230144dda12ccad12 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 4 Jan 2016 23:50:23 -0800 Subject: block, badblocks: introduce devm_init_badblocks Provide a devres interface for initializing a badblocks instance. The pmem driver has several scenarios where it will be beneficial to have this structure automatically freed when the device is disabled / fails probe. Signed-off-by: Dan Williams --- block/badblocks.c | 48 ++++++++++++++++++++++++++++++++++------------- include/linux/badblocks.h | 14 +++++++++++++- 2 files changed, 48 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/block/badblocks.c b/block/badblocks.c index 37e5c0a2ef69..7be53cb1cc3c 100644 --- a/block/badblocks.c +++ b/block/badblocks.c @@ -17,6 +17,7 @@ #include #include +#include #include #include #include @@ -522,24 +523,20 @@ ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len, } EXPORT_SYMBOL_GPL(badblocks_store); -/** - * badblocks_init() - initialize the badblocks structure - * @bb: the badblocks structure that holds all badblock information - * @enable: weather to enable badblocks accounting - * - * Return: - * 0: success - * -ve errno: on error - */ -int badblocks_init(struct badblocks *bb, int enable) +static int __badblocks_init(struct device *dev, struct badblocks *bb, + int enable) { + bb->dev = dev; bb->count = 0; if (enable) bb->shift = 0; else bb->shift = -1; - bb->page = kzalloc(PAGE_SIZE, GFP_KERNEL); - if (bb->page == (u64 *)0) { + if (dev) + bb->page = devm_kzalloc(dev, PAGE_SIZE, GFP_KERNEL); + else + bb->page = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!bb->page) { bb->shift = -1; return -ENOMEM; } @@ -547,8 +544,30 @@ int badblocks_init(struct badblocks *bb, int enable) return 0; } + +/** + * badblocks_init() - initialize the badblocks structure + * @bb: the badblocks structure that holds all badblock information + * @enable: weather to enable badblocks accounting + * + * Return: + * 0: success + * -ve errno: on error + */ +int badblocks_init(struct badblocks *bb, int enable) +{ + return __badblocks_init(NULL, bb, enable); +} EXPORT_SYMBOL_GPL(badblocks_init); +int devm_init_badblocks(struct device *dev, struct badblocks *bb) +{ + if (!bb) + return -EINVAL; + return __badblocks_init(dev, bb, 1); +} +EXPORT_SYMBOL_GPL(devm_init_badblocks); + /** * badblocks_exit() - free the badblocks structure * @bb: the badblocks structure that holds all badblock information @@ -557,7 +576,10 @@ void badblocks_exit(struct badblocks *bb) { if (!bb) return; - kfree(bb->page); + if (bb->dev) + devm_kfree(bb->dev, bb->page); + else + kfree(bb->page); bb->page = NULL; } EXPORT_SYMBOL_GPL(badblocks_exit); diff --git a/include/linux/badblocks.h b/include/linux/badblocks.h index 2d98c026c57f..c3bdf8c59480 100644 --- a/include/linux/badblocks.h +++ b/include/linux/badblocks.h @@ -2,6 +2,7 @@ #define _LINUX_BADBLOCKS_H #include +#include #include #include #include @@ -23,6 +24,7 @@ #define MAX_BADBLOCKS (PAGE_SIZE/8) struct badblocks { + struct device *dev; /* set by devm_init_badblocks */ int count; /* count of bad blocks */ int unacked_exist; /* there probably are unacknowledged * bad blocks. This is only cleared @@ -49,5 +51,15 @@ ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len, int unack); int badblocks_init(struct badblocks *bb, int enable); void badblocks_exit(struct badblocks *bb); - +struct device; +int devm_init_badblocks(struct device *dev, struct badblocks *bb); +static inline void devm_exit_badblocks(struct device *dev, struct badblocks *bb) +{ + if (bb->dev != dev) { + dev_WARN_ONCE(dev, 1, "%s: badblocks instance not associated\n", + __func__); + return; + } + badblocks_exit(bb); +} #endif -- cgit v1.2.3 From 55f5560d8c18fe33fc169f8d244a9247dcac7612 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Tue, 5 Jan 2016 00:28:18 -0800 Subject: block: kill disk_{check|set|clear|alloc}_badblocks These actions are completely managed by a block driver or can use the badblocks api directly. Signed-off-by: Dan Williams --- block/genhd.c | 42 ------------------------------------------ include/linux/genhd.h | 5 ----- 2 files changed, 47 deletions(-) (limited to 'include') diff --git a/block/genhd.c b/block/genhd.c index aa38cd0a66c7..5aaeb2ad0fd3 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -506,16 +506,6 @@ static int exact_lock(dev_t devt, void *data) return 0; } -int disk_alloc_badblocks(struct gendisk *disk) -{ - disk->bb = kzalloc(sizeof(*(disk->bb)), GFP_KERNEL); - if (!disk->bb) - return -ENOMEM; - - return badblocks_init(disk->bb, 1); -} -EXPORT_SYMBOL(disk_alloc_badblocks); - static void register_disk(struct gendisk *disk) { struct device *ddev = disk_to_dev(disk); @@ -682,38 +672,6 @@ void del_gendisk(struct gendisk *disk) } EXPORT_SYMBOL(del_gendisk); -/* - * The gendisk usage of badblocks does not track acknowledgements for - * badblocks. We always assume they are acknowledged. - */ -int disk_check_badblocks(struct gendisk *disk, sector_t s, int sectors, - sector_t *first_bad, int *bad_sectors) -{ - if (!disk->bb) - return 0; - - return badblocks_check(disk->bb, s, sectors, first_bad, bad_sectors); -} -EXPORT_SYMBOL(disk_check_badblocks); - -int disk_set_badblocks(struct gendisk *disk, sector_t s, int sectors) -{ - if (!disk->bb) - return 0; - - return badblocks_set(disk->bb, s, sectors, 1); -} -EXPORT_SYMBOL(disk_set_badblocks); - -int disk_clear_badblocks(struct gendisk *disk, sector_t s, int sectors) -{ - if (!disk->bb) - return 0; - - return badblocks_clear(disk->bb, s, sectors); -} -EXPORT_SYMBOL(disk_clear_badblocks); - /* sysfs access to bad-blocks list. */ static ssize_t disk_badblocks_show(struct device *dev, struct device_attribute *attr, diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 0bbec6880051..5c706765404a 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -435,11 +435,6 @@ extern void add_disk(struct gendisk *disk); extern void del_gendisk(struct gendisk *gp); extern struct gendisk *get_gendisk(dev_t dev, int *partno); extern struct block_device *bdget_disk(struct gendisk *disk, int partno); -int disk_alloc_badblocks(struct gendisk *disk); -extern int disk_check_badblocks(struct gendisk *disk, sector_t s, int sectors, - sector_t *first_bad, int *bad_sectors); -extern int disk_set_badblocks(struct gendisk *disk, sector_t s, int sectors); -extern int disk_clear_badblocks(struct gendisk *disk, sector_t s, int sectors); extern void set_device_ro(struct block_device *bdev, int flag); extern void set_disk_ro(struct gendisk *disk, int flag); -- cgit v1.2.3