From d7dcf26ff0ffd7b56fe2b09ed7f1867589f3cdf1 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Fri, 1 Mar 2019 23:48:21 +0100 Subject: softirq: Remove tasklet_hrtimer There are no more users of this interface. Remove it. Signed-off-by: Thomas Gleixner Signed-off-by: Anna-Maria Gleixner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Thomas Gleixner Acked-by: David S. Miller Cc: netdev@vger.kernel.org Link: https://lkml.kernel.org/r/20190301224821.29843-4-bigeasy@linutronix.de --- include/linux/interrupt.h | 25 ------------------------- 1 file changed, 25 deletions(-) (limited to 'include/linux') diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 690b238a44d5..c7eef32e7739 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -668,31 +668,6 @@ extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu); extern void tasklet_init(struct tasklet_struct *t, void (*func)(unsigned long), unsigned long data); -struct tasklet_hrtimer { - struct hrtimer timer; - struct tasklet_struct tasklet; - enum hrtimer_restart (*function)(struct hrtimer *); -}; - -extern void -tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer, - enum hrtimer_restart (*function)(struct hrtimer *), - clockid_t which_clock, enum hrtimer_mode mode); - -static inline -void tasklet_hrtimer_start(struct tasklet_hrtimer *ttimer, ktime_t time, - const enum hrtimer_mode mode) -{ - hrtimer_start(&ttimer->timer, time, mode); -} - -static inline -void tasklet_hrtimer_cancel(struct tasklet_hrtimer *ttimer) -{ - hrtimer_cancel(&ttimer->timer); - tasklet_kill(&ttimer->tasklet); -} - /* * Autoprobing for irqs: * -- cgit From 1b72d43237980eab9b6ae6bb8181e51c840377e6 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 21 Mar 2019 16:39:20 +0100 Subject: tick: Remove outgoing CPU from broadcast masks Valentin reported that unplugging a CPU occasionally results in a warning in the tick broadcast code which is triggered when an offline CPU is in the broadcast mask. This happens because the outgoing CPU is not removing itself from the broadcast masks, especially not from the broadcast_force_mask. The removal happens on the control CPU after the outgoing CPU is dead. It's a long standing issue, but the warning is harmless. Rework the hotplug mechanism so that the outgoing CPU removes itself from the broadcast masks after disabling interrupts and removing itself from the online mask. Reported-by: Valentin Schneider Signed-off-by: Thomas Gleixner Tested-by: Valentin Schneider Cc: Frederic Weisbecker Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1903211540180.1784@nanos.tec.linutronix.de --- include/linux/tick.h | 6 ++++++ kernel/cpu.c | 2 ++ kernel/time/clockevents.c | 18 ++++++++++++++++-- kernel/time/tick-broadcast.c | 40 +++++++++++++++++++--------------------- kernel/time/tick-internal.h | 10 ++++++---- 5 files changed, 49 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tick.h b/include/linux/tick.h index 55388ab45fd4..76acb48acdb7 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -68,6 +68,12 @@ extern void tick_broadcast_control(enum tick_broadcast_mode mode); static inline void tick_broadcast_control(enum tick_broadcast_mode mode) { } #endif /* BROADCAST */ +#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_HOTPLUG_CPU) +extern void tick_offline_cpu(unsigned int cpu); +#else +static inline void tick_offline_cpu(unsigned int cpu) { } +#endif + #ifdef CONFIG_GENERIC_CLOCKEVENTS extern int tick_broadcast_oneshot_control(enum tick_broadcast_state state); #else diff --git a/kernel/cpu.c b/kernel/cpu.c index 025f419d16f6..f69ba38573c2 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -844,6 +844,8 @@ static int take_cpu_down(void *_param) /* Give up timekeeping duties */ tick_handover_do_timer(); + /* Remove CPU from timer broadcasting */ + tick_offline_cpu(cpu); /* Park the stopper thread */ stop_machine_park(cpu); return 0; diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 5e77662dd2d9..f5490222e134 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -611,6 +611,22 @@ void clockevents_resume(void) } #ifdef CONFIG_HOTPLUG_CPU + +# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +/** + * tick_offline_cpu - Take CPU out of the broadcast mechanism + * @cpu: The outgoing CPU + * + * Called on the outgoing CPU after it took itself offline. + */ +void tick_offline_cpu(unsigned int cpu) +{ + raw_spin_lock(&clockevents_lock); + tick_broadcast_offline(cpu); + raw_spin_unlock(&clockevents_lock); +} +# endif + /** * tick_cleanup_dead_cpu - Cleanup the tick and clockevents of a dead cpu */ @@ -621,8 +637,6 @@ void tick_cleanup_dead_cpu(int cpu) raw_spin_lock_irqsave(&clockevents_lock, flags); - tick_shutdown_broadcast_oneshot(cpu); - tick_shutdown_broadcast(cpu); tick_shutdown(cpu); /* * Unregister the clock event devices which were diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index ee834d4fb814..0283523de045 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -36,10 +36,12 @@ static __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(tick_broadcast_lock); static void tick_broadcast_setup_oneshot(struct clock_event_device *bc); static void tick_broadcast_clear_oneshot(int cpu); static void tick_resume_broadcast_oneshot(struct clock_event_device *bc); +static void tick_broadcast_oneshot_offline(unsigned int cpu); #else static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { BUG(); } static inline void tick_broadcast_clear_oneshot(int cpu) { } static inline void tick_resume_broadcast_oneshot(struct clock_event_device *bc) { } +static inline void tick_broadcast_oneshot_offline(unsigned int cpu) { } #endif /* @@ -433,27 +435,29 @@ void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast) } #ifdef CONFIG_HOTPLUG_CPU -/* - * Remove a CPU from broadcasting - */ -void tick_shutdown_broadcast(unsigned int cpu) +static void tick_shutdown_broadcast(void) { - struct clock_event_device *bc; - unsigned long flags; - - raw_spin_lock_irqsave(&tick_broadcast_lock, flags); - - bc = tick_broadcast_device.evtdev; - cpumask_clear_cpu(cpu, tick_broadcast_mask); - cpumask_clear_cpu(cpu, tick_broadcast_on); + struct clock_event_device *bc = tick_broadcast_device.evtdev; if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) { if (bc && cpumask_empty(tick_broadcast_mask)) clockevents_shutdown(bc); } +} - raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); +/* + * Remove a CPU from broadcasting + */ +void tick_broadcast_offline(unsigned int cpu) +{ + raw_spin_lock(&tick_broadcast_lock); + cpumask_clear_cpu(cpu, tick_broadcast_mask); + cpumask_clear_cpu(cpu, tick_broadcast_on); + tick_broadcast_oneshot_offline(cpu); + tick_shutdown_broadcast(); + raw_spin_unlock(&tick_broadcast_lock); } + #endif void tick_suspend_broadcast(void) @@ -950,14 +954,10 @@ void hotplug_cpu__broadcast_tick_pull(int deadcpu) } /* - * Remove a dead CPU from broadcasting + * Remove a dying CPU from broadcasting */ -void tick_shutdown_broadcast_oneshot(unsigned int cpu) +static void tick_broadcast_oneshot_offline(unsigned int cpu) { - unsigned long flags; - - raw_spin_lock_irqsave(&tick_broadcast_lock, flags); - /* * Clear the broadcast masks for the dead cpu, but do not stop * the broadcast device! @@ -965,8 +965,6 @@ void tick_shutdown_broadcast_oneshot(unsigned int cpu) cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask); cpumask_clear_cpu(cpu, tick_broadcast_pending_mask); cpumask_clear_cpu(cpu, tick_broadcast_force_mask); - - raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } #endif diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index e277284c2831..7b2496136729 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -64,7 +64,6 @@ extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt); extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu); extern void tick_install_broadcast_device(struct clock_event_device *dev); extern int tick_is_broadcast_device(struct clock_event_device *dev); -extern void tick_shutdown_broadcast(unsigned int cpu); extern void tick_suspend_broadcast(void); extern void tick_resume_broadcast(void); extern bool tick_resume_check_broadcast(void); @@ -78,7 +77,6 @@ static inline void tick_install_broadcast_device(struct clock_event_device *dev) static inline int tick_is_broadcast_device(struct clock_event_device *dev) { return 0; } static inline int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) { return 0; } static inline void tick_do_periodic_broadcast(struct clock_event_device *d) { } -static inline void tick_shutdown_broadcast(unsigned int cpu) { } static inline void tick_suspend_broadcast(void) { } static inline void tick_resume_broadcast(void) { } static inline bool tick_resume_check_broadcast(void) { return false; } @@ -128,19 +126,23 @@ static inline int tick_check_oneshot_change(int allow_nohz) { return 0; } /* Functions related to oneshot broadcasting */ #if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT) extern void tick_broadcast_switch_to_oneshot(void); -extern void tick_shutdown_broadcast_oneshot(unsigned int cpu); extern int tick_broadcast_oneshot_active(void); extern void tick_check_oneshot_broadcast_this_cpu(void); bool tick_broadcast_oneshot_available(void); extern struct cpumask *tick_get_broadcast_oneshot_mask(void); #else /* !(BROADCAST && ONESHOT): */ static inline void tick_broadcast_switch_to_oneshot(void) { } -static inline void tick_shutdown_broadcast_oneshot(unsigned int cpu) { } static inline int tick_broadcast_oneshot_active(void) { return 0; } static inline void tick_check_oneshot_broadcast_this_cpu(void) { } static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_possible(); } #endif /* !(BROADCAST && ONESHOT) */ +#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_HOTPLUG_CPU) +extern void tick_broadcast_offline(unsigned int cpu); +#else +static inline void tick_broadcast_offline(unsigned int cpu) { } +#endif + /* NO_HZ_FULL internal */ #ifdef CONFIG_NO_HZ_FULL extern void tick_nohz_init(void); -- cgit From b699cce1604e828f19c39845252626eb78cdf38a Mon Sep 17 00:00:00 2001 From: Neeraj Upadhyay Date: Mon, 11 Mar 2019 17:28:03 +0530 Subject: rcu: Do a single rhp->func read in rcu_head_after_call_rcu() The rcu_head_after_call_rcu() function reads the rhp->func pointer twice, which can result in a false-positive WARN_ON_ONCE() if the callback were passed to call_rcu() between the two reads. Although racing rcu_head_after_call_rcu() with call_rcu() is to be a dubious use case (the return value is not reliable in that case), intermittent and irreproducible warnings are also quite dubious. This commit therefore uses a single READ_ONCE() to pick up the value of rhp->func once, then tests that value twice, thus guaranteeing consistent processing within rcu_head_after_call_rcu()(). Neverthless, racing rcu_head_after_call_rcu() with call_rcu() is still a dubious use case. Signed-off-by: Neeraj Upadhyay [ paulmck: Add blank line after declaration per checkpatch.pl. ] Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 6cdb1db776cf..922bb6848813 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -878,9 +878,11 @@ static inline void rcu_head_init(struct rcu_head *rhp) static inline bool rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) { - if (READ_ONCE(rhp->func) == f) + rcu_callback_t func = READ_ONCE(rhp->func); + + if (func == f) return true; - WARN_ON_ONCE(READ_ONCE(rhp->func) != (rcu_callback_t)~0L); + WARN_ON_ONCE(func != (rcu_callback_t)~0L); return false; } -- cgit From f5ad3991493c69d203d42b94d32349b54c58a3f1 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 13 Feb 2019 13:54:37 -0800 Subject: srcu: Remove cleanup_srcu_struct_quiesced() The cleanup_srcu_struct_quiesced() function was added because NVME used WQ_MEM_RECLAIM workqueues and SRCU did not, which meant that NVME workqueues waiting on SRCU workqueues could result in deadlocks during low-memory conditions. However, SRCU now also has WQ_MEM_RECLAIM workqueues, so there is no longer a potential for deadlock. Furthermore, it turns out to be extremely hard to use cleanup_srcu_struct_quiesced() correctly due to the fact that SRCU callback invocation accesses the srcu_struct structure's per-CPU data area just after callbacks are invoked. Therefore, the usual practice of using srcu_barrier() to wait for callbacks to be invoked before invoking cleanup_srcu_struct_quiesced() fails because SRCU's callback-invocation workqueue handler might be delayed, which can result in cleanup_srcu_struct_quiesced() being invoked (and thus freeing the per-CPU data) before the SRCU's callback-invocation workqueue handler is finished using that per-CPU data. Nor is this a theoretical problem: KASAN emitted use-after-free warnings because of this problem on actual runs. In short, NVME can now safely invoke cleanup_srcu_struct(), which avoids the use-after-free scenario. And cleanup_srcu_struct_quiesced() is quite difficult to use safely. This commit therefore removes cleanup_srcu_struct_quiesced(), switching its sole user back to cleanup_srcu_struct(). This effectively reverts the following pair of commits: f7194ac32ca2 ("srcu: Add cleanup_srcu_struct_quiesced()") 4317228ad9b8 ("nvme: Avoid flush dependency in delete controller flow") Reported-by: Bart Van Assche Signed-off-by: Paul E. McKenney Reviewed-by: Bart Van Assche Tested-by: Bart Van Assche --- drivers/nvme/host/core.c | 2 +- include/linux/srcu.h | 36 +----------------------------------- kernel/rcu/rcutorture.c | 7 +------ kernel/rcu/srcutiny.c | 9 +++------ kernel/rcu/srcutree.c | 30 ++++++++++++------------------ 5 files changed, 18 insertions(+), 66 deletions(-) (limited to 'include/linux') diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 470601980794..739c5b4830d7 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -388,7 +388,7 @@ static void nvme_free_ns_head(struct kref *ref) nvme_mpath_remove_disk(head); ida_simple_remove(&head->subsys->ns_ida, head->instance); list_del_init(&head->entry); - cleanup_srcu_struct_quiesced(&head->srcu); + cleanup_srcu_struct(&head->srcu); nvme_put_subsystem(head->subsys); kfree(head); } diff --git a/include/linux/srcu.h b/include/linux/srcu.h index c495b2d51569..e432cc92c73d 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -56,45 +56,11 @@ struct srcu_struct { }; void call_srcu(struct srcu_struct *ssp, struct rcu_head *head, void (*func)(struct rcu_head *head)); -void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced); +void cleanup_srcu_struct(struct srcu_struct *ssp); int __srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp); void synchronize_srcu(struct srcu_struct *ssp); -/** - * cleanup_srcu_struct - deconstruct a sleep-RCU structure - * @ssp: structure to clean up. - * - * Must invoke this after you are finished using a given srcu_struct that - * was initialized via init_srcu_struct(), else you leak memory. - */ -static inline void cleanup_srcu_struct(struct srcu_struct *ssp) -{ - _cleanup_srcu_struct(ssp, false); -} - -/** - * cleanup_srcu_struct_quiesced - deconstruct a quiesced sleep-RCU structure - * @ssp: structure to clean up. - * - * Must invoke this after you are finished using a given srcu_struct that - * was initialized via init_srcu_struct(), else you leak memory. Also, - * all grace-period processing must have completed. - * - * "Completed" means that the last synchronize_srcu() and - * synchronize_srcu_expedited() calls must have returned before the call - * to cleanup_srcu_struct_quiesced(). It also means that the callback - * from the last call_srcu() must have been invoked before the call to - * cleanup_srcu_struct_quiesced(), but you can use srcu_barrier() to help - * with this last. Violating these rules will get you a WARN_ON() splat - * (with high probability, anyway), and will also cause the srcu_struct - * to be leaked. - */ -static inline void cleanup_srcu_struct_quiesced(struct srcu_struct *ssp) -{ - _cleanup_srcu_struct(ssp, true); -} - #ifdef CONFIG_DEBUG_LOCK_ALLOC /** diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index f14d1b18a74f..d2b226110835 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -592,12 +592,7 @@ static void srcu_torture_init(void) static void srcu_torture_cleanup(void) { - static DEFINE_TORTURE_RANDOM(rand); - - if (torture_random(&rand) & 0x800) - cleanup_srcu_struct(&srcu_ctld); - else - cleanup_srcu_struct_quiesced(&srcu_ctld); + cleanup_srcu_struct(&srcu_ctld); srcu_ctlp = &srcu_ctl; /* In case of a later rcutorture run. */ } diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c index 5d4a39a6505a..44d6606b8325 100644 --- a/kernel/rcu/srcutiny.c +++ b/kernel/rcu/srcutiny.c @@ -76,19 +76,16 @@ EXPORT_SYMBOL_GPL(init_srcu_struct); * Must invoke this after you are finished using a given srcu_struct that * was initialized via init_srcu_struct(), else you leak memory. */ -void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced) +void cleanup_srcu_struct(struct srcu_struct *ssp) { WARN_ON(ssp->srcu_lock_nesting[0] || ssp->srcu_lock_nesting[1]); - if (quiesced) - WARN_ON(work_pending(&ssp->srcu_work)); - else - flush_work(&ssp->srcu_work); + flush_work(&ssp->srcu_work); WARN_ON(ssp->srcu_gp_running); WARN_ON(ssp->srcu_gp_waiting); WARN_ON(ssp->srcu_cb_head); WARN_ON(&ssp->srcu_cb_head != ssp->srcu_cb_tail); } -EXPORT_SYMBOL_GPL(_cleanup_srcu_struct); +EXPORT_SYMBOL_GPL(cleanup_srcu_struct); /* * Removes the count for the old reader from the appropriate element of diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 4f30f3ecabc1..9b761e546de8 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -360,8 +360,14 @@ static unsigned long srcu_get_delay(struct srcu_struct *ssp) return SRCU_INTERVAL; } -/* Helper for cleanup_srcu_struct() and cleanup_srcu_struct_quiesced(). */ -void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced) +/** + * cleanup_srcu_struct - deconstruct a sleep-RCU structure + * @ssp: structure to clean up. + * + * Must invoke this after you are finished using a given srcu_struct that + * was initialized via init_srcu_struct(), else you leak memory. + */ +void cleanup_srcu_struct(struct srcu_struct *ssp) { int cpu; @@ -369,24 +375,12 @@ void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced) return; /* Just leak it! */ if (WARN_ON(srcu_readers_active(ssp))) return; /* Just leak it! */ - if (quiesced) { - if (WARN_ON(delayed_work_pending(&ssp->work))) - return; /* Just leak it! */ - } else { - flush_delayed_work(&ssp->work); - } + flush_delayed_work(&ssp->work); for_each_possible_cpu(cpu) { struct srcu_data *sdp = per_cpu_ptr(ssp->sda, cpu); - if (quiesced) { - if (WARN_ON(timer_pending(&sdp->delay_work))) - return; /* Just leak it! */ - if (WARN_ON(work_pending(&sdp->work))) - return; /* Just leak it! */ - } else { - del_timer_sync(&sdp->delay_work); - flush_work(&sdp->work); - } + del_timer_sync(&sdp->delay_work); + flush_work(&sdp->work); if (WARN_ON(rcu_segcblist_n_cbs(&sdp->srcu_cblist))) return; /* Forgot srcu_barrier(), so just leak it! */ } @@ -399,7 +393,7 @@ void _cleanup_srcu_struct(struct srcu_struct *ssp, bool quiesced) free_percpu(ssp->sda); ssp->sda = NULL; } -EXPORT_SYMBOL_GPL(_cleanup_srcu_struct); +EXPORT_SYMBOL_GPL(cleanup_srcu_struct); /* * Counts the new reader in the appropriate per-CPU element of the -- cgit From 7f07e5f1f778605e98cf2156d4db1ff3a3a1a74a Mon Sep 17 00:00:00 2001 From: Claudiu Manoil Date: Tue, 26 Mar 2019 11:48:57 +0200 Subject: net: mii: Fix PAUSE cap advertisement from linkmode_adv_to_lcl_adv_t() helper With a recent link mode advertisement code update this helper providing local pause capability translation used for flow control link mode negotiation got broken. For eth drivers using this helper, the issue is apparent only if either PAUSE or ASYM_PAUSE is being advertised. Fixes: 3c1bcc8614db ("net: ethernet: Convert phydev advertize and supported from u32 to link mode") Signed-off-by: Claudiu Manoil Signed-off-by: David S. Miller --- include/linux/mii.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mii.h b/include/linux/mii.h index 6fee8b1a4400..5cd824c1c0ca 100644 --- a/include/linux/mii.h +++ b/include/linux/mii.h @@ -469,7 +469,7 @@ static inline u32 linkmode_adv_to_lcl_adv_t(unsigned long *advertising) if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, advertising)) lcl_adv |= ADVERTISE_PAUSE_CAP; - if (linkmode_test_bit(ETHTOOL_LINK_MODE_Pause_BIT, + if (linkmode_test_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, advertising)) lcl_adv |= ADVERTISE_PAUSE_ASYM; -- cgit From 7a8e61f8478639072d402a26789055a4a4de8f77 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 23 Mar 2019 11:36:19 +0100 Subject: timekeeping: Force upper bound for setting CLOCK_REALTIME Several people reported testing failures after setting CLOCK_REALTIME close to the limits of the kernel internal representation in nanoseconds, i.e. year 2262. The failures are exposed in subsequent operations, i.e. when arming timers or when the advancing CLOCK_MONOTONIC makes the calculation of CLOCK_REALTIME overflow into negative space. Now people start to paper over the underlying problem by clamping calculations to the valid range, but that's just wrong because such workarounds will prevent detection of real issues as well. It is reasonable to force an upper bound for the various methods of setting CLOCK_REALTIME. Year 2262 is the absolute upper bound. Assume a maximum uptime of 30 years which is plenty enough even for esoteric embedded systems. That results in an upper bound of year 2232 for setting the time. Once that limit is reached in reality this limit is only a small part of the problem space. But until then this stops people from trying to paper over the problem at the wrong places. Reported-by: Xiongfeng Wang Reported-by: Hongbo Yao Signed-off-by: Thomas Gleixner Cc: John Stultz Cc: Stephen Boyd Cc: Miroslav Lichvar Cc: Arnd Bergmann Cc: Richard Cochran Cc: Peter Zijlstra Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1903231125480.2157@nanos.tec.linutronix.de --- include/linux/time64.h | 21 +++++++++++++++++++++ kernel/time/time.c | 2 +- kernel/time/timekeeping.c | 6 +++--- 3 files changed, 25 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/time64.h b/include/linux/time64.h index f38d382ffec1..a620ee610b9f 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -33,6 +33,17 @@ struct itimerspec64 { #define KTIME_MAX ((s64)~((u64)1 << 63)) #define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) +/* + * Limits for settimeofday(): + * + * To prevent setting the time close to the wraparound point time setting + * is limited so a reasonable uptime can be accomodated. Uptime of 30 years + * should be really sufficient, which means the cutoff is 2232. At that + * point the cutoff is just a small part of the larger problem. + */ +#define TIME_UPTIME_SEC_MAX (30LL * 365 * 24 *3600) +#define TIME_SETTOD_SEC_MAX (KTIME_SEC_MAX - TIME_UPTIME_SEC_MAX) + static inline int timespec64_equal(const struct timespec64 *a, const struct timespec64 *b) { @@ -100,6 +111,16 @@ static inline bool timespec64_valid_strict(const struct timespec64 *ts) return true; } +static inline bool timespec64_valid_settod(const struct timespec64 *ts) +{ + if (!timespec64_valid(ts)) + return false; + /* Disallow values which cause overflow issues vs. CLOCK_REALTIME */ + if ((unsigned long long)ts->tv_sec >= TIME_SETTOD_SEC_MAX) + return false; + return true; +} + /** * timespec64_to_ns - Convert timespec64 to nanoseconds * @ts: pointer to the timespec64 variable to be converted diff --git a/kernel/time/time.c b/kernel/time/time.c index c3f756f8534b..86656bbac232 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -171,7 +171,7 @@ int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz static int firsttime = 1; int error = 0; - if (tv && !timespec64_valid(tv)) + if (tv && !timespec64_valid_settod(tv)) return -EINVAL; error = security_settime64(tv, tz); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 540145da33da..5716e28bfa3c 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1221,7 +1221,7 @@ int do_settimeofday64(const struct timespec64 *ts) unsigned long flags; int ret = 0; - if (!timespec64_valid_strict(ts)) + if (!timespec64_valid_settod(ts)) return -EINVAL; raw_spin_lock_irqsave(&timekeeper_lock, flags); @@ -1278,7 +1278,7 @@ static int timekeeping_inject_offset(const struct timespec64 *ts) /* Make sure the proposed value is valid */ tmp = timespec64_add(tk_xtime(tk), *ts); if (timespec64_compare(&tk->wall_to_monotonic, ts) > 0 || - !timespec64_valid_strict(&tmp)) { + !timespec64_valid_settod(&tmp)) { ret = -EINVAL; goto error; } @@ -1527,7 +1527,7 @@ void __init timekeeping_init(void) unsigned long flags; read_persistent_wall_and_boot_offset(&wall_time, &boot_offset); - if (timespec64_valid_strict(&wall_time) && + if (timespec64_valid_settod(&wall_time) && timespec64_to_ns(&wall_time) > 0) { persistent_clock_exists = true; } else if (timespec64_to_ns(&wall_time) != 0) { -- cgit From 0fca08122eaf5c956a2cbe12775245d747f8b1ac Mon Sep 17 00:00:00 2001 From: Robert Richter Date: Thu, 28 Mar 2019 20:34:28 +0100 Subject: efi: Unify DMI setup code over the arm/arm64, ia64 and x86 architectures All architectures (arm/arm64, ia64 and x86) do the same here, so unify the code. Note: We do not need to call dump_stack_set_arch_desc() in case of !dmi_available. Both strings, dmi_ids_string and dump_stack_arch_ desc_str are initialized zero and thus nothing would change. Signed-off-by: Robert Richter Signed-off-by: Ard Biesheuvel Reviewed-by: Jean Delvare Cc: Linus Torvalds Cc: Matt Fleming Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Link: http://lkml.kernel.org/r/20190328193429.21373-5-ard.biesheuvel@linaro.org Signed-off-by: Ingo Molnar --- arch/ia64/kernel/setup.c | 4 +--- arch/x86/kernel/setup.c | 6 ++---- drivers/firmware/dmi_scan.c | 28 +++++++++++++++------------- drivers/firmware/efi/arm-runtime.c | 7 ++----- include/linux/dmi.h | 8 ++------ 5 files changed, 22 insertions(+), 31 deletions(-) (limited to 'include/linux') diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index 583a3746d70b..c9cfa760cd57 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -1058,9 +1058,7 @@ check_bugs (void) static int __init run_dmi_scan(void) { - dmi_scan_machine(); - dmi_memdev_walk(); - dmi_set_dump_stack_arch_desc(); + dmi_setup(); return 0; } core_initcall(run_dmi_scan); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 3d872a527cd9..3773905cd2c1 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1005,13 +1005,11 @@ void __init setup_arch(char **cmdline_p) if (efi_enabled(EFI_BOOT)) efi_init(); - dmi_scan_machine(); - dmi_memdev_walk(); - dmi_set_dump_stack_arch_desc(); + dmi_setup(); /* * VMware detection requires dmi to be available, so this - * needs to be done after dmi_scan_machine(), for the boot CPU. + * needs to be done after dmi_setup(), for the boot CPU. */ init_hypervisor_platform(); diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index 099d83e4e910..fae2d5c43314 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -416,11 +416,8 @@ static void __init save_mem_devices(const struct dmi_header *dm, void *v) nr++; } -void __init dmi_memdev_walk(void) +static void __init dmi_memdev_walk(void) { - if (!dmi_available) - return; - if (dmi_walk_early(count_mem_devices) == 0 && dmi_memdev_nr) { dmi_memdev = dmi_alloc(sizeof(*dmi_memdev) * dmi_memdev_nr); if (dmi_memdev) @@ -614,7 +611,7 @@ static int __init dmi_smbios3_present(const u8 *buf) return 1; } -void __init dmi_scan_machine(void) +static void __init dmi_scan_machine(void) { char __iomem *p, *q; char buf[32]; @@ -769,15 +766,20 @@ static int __init dmi_init(void) subsys_initcall(dmi_init); /** - * dmi_set_dump_stack_arch_desc - set arch description for dump_stack() + * dmi_setup - scan and setup DMI system information * - * Invoke dump_stack_set_arch_desc() with DMI system information so that - * DMI identifiers are printed out on task dumps. Arch boot code should - * call this function after dmi_scan_machine() if it wants to print out DMI - * identifiers on task dumps. + * Scan the DMI system information. This setups DMI identifiers + * (dmi_system_id) for printing it out on task dumps and prepares + * DIMM entry information (dmi_memdev_info) from the SMBIOS table + * for using this when reporting memory errors. */ -void __init dmi_set_dump_stack_arch_desc(void) +void __init dmi_setup(void) { + dmi_scan_machine(); + if (!dmi_available) + return; + + dmi_memdev_walk(); dump_stack_set_arch_desc("%s", dmi_ids_string); } @@ -841,7 +843,7 @@ static bool dmi_is_end_of_table(const struct dmi_system_id *dmi) * returns non zero or we hit the end. Callback function is called for * each successful match. Returns the number of matches. * - * dmi_scan_machine must be called before this function is called. + * dmi_setup must be called before this function is called. */ int dmi_check_system(const struct dmi_system_id *list) { @@ -871,7 +873,7 @@ EXPORT_SYMBOL(dmi_check_system); * Walk the blacklist table until the first match is found. Return the * pointer to the matching entry or NULL if there's no match. * - * dmi_scan_machine must be called before this function is called. + * dmi_setup must be called before this function is called. */ const struct dmi_system_id *dmi_first_match(const struct dmi_system_id *list) { diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c index 4a0dfe4ab829..e2ac5fa5531b 100644 --- a/drivers/firmware/efi/arm-runtime.c +++ b/drivers/firmware/efi/arm-runtime.c @@ -162,14 +162,11 @@ void efi_virtmap_unload(void) static int __init arm_dmi_init(void) { /* - * On arm64/ARM, DMI depends on UEFI, and dmi_scan_machine() needs to + * On arm64/ARM, DMI depends on UEFI, and dmi_setup() needs to * be called early because dmi_id_init(), which is an arch_initcall * itself, depends on dmi_scan_machine() having been called already. */ - dmi_scan_machine(); - dmi_memdev_walk(); - if (dmi_available) - dmi_set_dump_stack_arch_desc(); + dmi_setup(); return 0; } core_initcall(arm_dmi_init); diff --git a/include/linux/dmi.h b/include/linux/dmi.h index c46fdb36700b..8de8c4f15163 100644 --- a/include/linux/dmi.h +++ b/include/linux/dmi.h @@ -102,9 +102,7 @@ const struct dmi_system_id *dmi_first_match(const struct dmi_system_id *list); extern const char * dmi_get_system_info(int field); extern const struct dmi_device * dmi_find_device(int type, const char *name, const struct dmi_device *from); -extern void dmi_scan_machine(void); -extern void dmi_memdev_walk(void); -extern void dmi_set_dump_stack_arch_desc(void); +extern void dmi_setup(void); extern bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp); extern int dmi_get_bios_year(void); extern int dmi_name_in_vendors(const char *str); @@ -122,9 +120,7 @@ static inline int dmi_check_system(const struct dmi_system_id *list) { return 0; static inline const char * dmi_get_system_info(int field) { return NULL; } static inline const struct dmi_device * dmi_find_device(int type, const char *name, const struct dmi_device *from) { return NULL; } -static inline void dmi_scan_machine(void) { return; } -static inline void dmi_memdev_walk(void) { } -static inline void dmi_set_dump_stack_arch_desc(void) { } +static inline void dmi_setup(void) { } static inline bool dmi_get_date(int field, int *yearp, int *monthp, int *dayp) { if (yearp) -- cgit From 80a2a9026b24c6bd34b8d58256973e22270bedec Mon Sep 17 00:00:00 2001 From: Yuval Avnery Date: Mon, 11 Mar 2019 06:18:24 +0200 Subject: net/mlx5e: Add a lock on tir list Refresh tirs is looping over a global list of tirs while netdevs are adding and removing tirs from that list. That is why a lock is required. Fixes: 724b2aa15126 ("net/mlx5e: TIRs management refactoring") Signed-off-by: Yuval Avnery Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_common.c | 7 +++++++ include/linux/mlx5/driver.h | 2 ++ 2 files changed, 9 insertions(+) (limited to 'include/linux') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 8100786f6fb5..1539cf3de5dc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -45,7 +45,9 @@ int mlx5e_create_tir(struct mlx5_core_dev *mdev, if (err) return err; + mutex_lock(&mdev->mlx5e_res.td.list_lock); list_add(&tir->list, &mdev->mlx5e_res.td.tirs_list); + mutex_unlock(&mdev->mlx5e_res.td.list_lock); return 0; } @@ -53,8 +55,10 @@ int mlx5e_create_tir(struct mlx5_core_dev *mdev, void mlx5e_destroy_tir(struct mlx5_core_dev *mdev, struct mlx5e_tir *tir) { + mutex_lock(&mdev->mlx5e_res.td.list_lock); mlx5_core_destroy_tir(mdev, tir->tirn); list_del(&tir->list); + mutex_unlock(&mdev->mlx5e_res.td.list_lock); } static int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, @@ -114,6 +118,7 @@ int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev) } INIT_LIST_HEAD(&mdev->mlx5e_res.td.tirs_list); + mutex_init(&mdev->mlx5e_res.td.list_lock); return 0; @@ -159,6 +164,7 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb) MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1); + mutex_lock(&mdev->mlx5e_res.td.list_lock); list_for_each_entry(tir, &mdev->mlx5e_res.td.tirs_list, list) { tirn = tir->tirn; err = mlx5_core_modify_tir(mdev, tirn, in, inlen); @@ -170,6 +176,7 @@ out: kvfree(in); if (err) netdev_err(priv->netdev, "refresh tir(0x%x) failed, %d\n", tirn, err); + mutex_unlock(&mdev->mlx5e_res.td.list_lock); return err; } diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 022541dc5dbf..0d0729648844 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -594,6 +594,8 @@ enum mlx5_pagefault_type_flags { }; struct mlx5_td { + /* protects tirs list changes while tirs refresh */ + struct mutex list_lock; struct list_head tirs_list; u32 tdn; }; -- cgit From 817b4d64da036f5559297a2fdb82b8b14f4ffdcd Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 18 Mar 2019 23:00:54 +0300 Subject: ACPI / utils: Introduce acpi_dev_get_first_match_dev() helper The acpi_dev_get_first_match_name() is missing put_device() call and thus keeping reference counting unbalanced. In order to fix the issue introduce a new helper to convert existing users one-by-one to a better API. Signed-off-by: Andy Shevchenko Reviewed-by: Hans de Goede Reviewed-by: Mika Westerberg Acked-by: Mark Brown Signed-off-by: Rafael J. Wysocki --- drivers/acpi/utils.c | 24 ++++++++++++++++++++++-- include/acpi/acpi_bus.h | 3 +++ include/linux/acpi.h | 6 ++++++ 3 files changed, 31 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c index c4b06cc075f9..5a2bae2b6c3a 100644 --- a/drivers/acpi/utils.c +++ b/drivers/acpi/utils.c @@ -739,6 +739,7 @@ EXPORT_SYMBOL(acpi_dev_found); struct acpi_dev_match_info { const char *dev_name; + struct acpi_device *adev; struct acpi_device_id hid[2]; const char *uid; s64 hrv; @@ -759,6 +760,7 @@ static int acpi_dev_match_cb(struct device *dev, void *data) return 0; match->dev_name = acpi_dev_name(adev); + match->adev = adev; if (match->hrv == -1) return 1; @@ -806,16 +808,34 @@ bool acpi_dev_present(const char *hid, const char *uid, s64 hrv) EXPORT_SYMBOL(acpi_dev_present); /** - * acpi_dev_get_first_match_name - Return name of first match of ACPI device + * acpi_dev_get_first_match_dev - Return the first match of ACPI device * @hid: Hardware ID of the device. * @uid: Unique ID of the device, pass NULL to not check _UID * @hrv: Hardware Revision of the device, pass -1 to not check _HRV * - * Return device name if a matching device was present + * Return the first match of ACPI device if a matching device was present * at the moment of invocation, or NULL otherwise. * + * The caller is responsible to call put_device() on the returned device. + * * See additional information in acpi_dev_present() as well. */ +struct acpi_device * +acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv) +{ + struct acpi_dev_match_info match = {}; + struct device *dev; + + strlcpy(match.hid[0].id, hid, sizeof(match.hid[0].id)); + match.uid = uid; + match.hrv = hrv; + + dev = bus_find_device(&acpi_bus_type, NULL, &match, acpi_dev_match_cb); + return dev ? match.adev : NULL; +} +EXPORT_SYMBOL(acpi_dev_get_first_match_dev); + +/* DEPRECATED, use acpi_dev_get_first_match_dev() instead */ const char * acpi_dev_get_first_match_name(const char *hid, const char *uid, s64 hrv) { diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 0300374101cd..2063e9e2f384 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -91,6 +91,9 @@ acpi_evaluate_dsm_typed(acpi_handle handle, const guid_t *guid, u64 rev, bool acpi_dev_found(const char *hid); bool acpi_dev_present(const char *hid, const char *uid, s64 hrv); +struct acpi_device * +acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv); + const char * acpi_dev_get_first_match_name(const char *hid, const char *uid, s64 hrv); diff --git a/include/linux/acpi.h b/include/linux/acpi.h index d5dcebd7aad3..3e1d16b00513 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -669,6 +669,12 @@ static inline bool acpi_dev_present(const char *hid, const char *uid, s64 hrv) return false; } +static inline struct acpi_device * +acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv) +{ + return NULL; +} + static inline const char * acpi_dev_get_first_match_name(const char *hid, const char *uid, s64 hrv) { -- cgit From 257f9053c0204ea47491aa236004fd1226f75fa8 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 28 Mar 2019 19:17:29 +0200 Subject: ACPI / utils: Remove deprecated function since no user left There is no more user of acpi_dev_get_first_match_name(), which is deprecated and has no user left, so, remove it for good. Signed-off-by: Andy Shevchenko Reviewed-by: Mika Westerberg Signed-off-by: Rafael J. Wysocki --- drivers/acpi/utils.c | 16 ---------------- include/acpi/acpi_bus.h | 3 --- include/linux/acpi.h | 6 ------ 3 files changed, 25 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c index 5a2bae2b6c3a..89363b245489 100644 --- a/drivers/acpi/utils.c +++ b/drivers/acpi/utils.c @@ -835,22 +835,6 @@ acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv) } EXPORT_SYMBOL(acpi_dev_get_first_match_dev); -/* DEPRECATED, use acpi_dev_get_first_match_dev() instead */ -const char * -acpi_dev_get_first_match_name(const char *hid, const char *uid, s64 hrv) -{ - struct acpi_dev_match_info match = {}; - struct device *dev; - - strlcpy(match.hid[0].id, hid, sizeof(match.hid[0].id)); - match.uid = uid; - match.hrv = hrv; - - dev = bus_find_device(&acpi_bus_type, NULL, &match, acpi_dev_match_cb); - return dev ? match.dev_name : NULL; -} -EXPORT_SYMBOL(acpi_dev_get_first_match_name); - /* * acpi_backlight= handling, this is done here rather then in video_detect.c * because __setup cannot be used in modules. diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index 2063e9e2f384..f7981751ac77 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -94,9 +94,6 @@ bool acpi_dev_present(const char *hid, const char *uid, s64 hrv); struct acpi_device * acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv); -const char * -acpi_dev_get_first_match_name(const char *hid, const char *uid, s64 hrv); - #ifdef CONFIG_ACPI #include diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 3e1d16b00513..392413075cc0 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -675,12 +675,6 @@ acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv) return NULL; } -static inline const char * -acpi_dev_get_first_match_name(const char *hid, const char *uid, s64 hrv) -{ - return NULL; -} - static inline bool is_acpi_node(struct fwnode_handle *fwnode) { return false; -- cgit From 5a25e3f7cc538fb49e11267c1e41c54ccf83835e Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 26 Mar 2019 12:15:13 +0100 Subject: cpufreq: intel_pstate: Driver-specific handling of _PPC updates In some cases, the platform firmware disables or enables turbo frequencies for all CPUs globally before triggering a _PPC change notification for one of them. Obviously, that global change affects all CPUs, not just the notified one, and it needs to be acted upon by cpufreq. The intel_pstate driver is able to detect such global changes of the settings, but it also needs to update policy limits for all CPUs if that happens, in particular if turbo frequencies are enabled globally - to allow them to be used. For this reason, introduce a new cpufreq driver callback to be invoked on _PPC notifications, if present, instead of simply calling cpufreq_update_policy() for the notified CPU and make intel_pstate use it to trigger policy updates for all CPUs in the system if global settings change. Link: https://bugzilla.kernel.org/show_bug.cgi?id=200759 Reported-by: Gabriele Mazzotta Tested-by: Gabriele Mazzotta Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar --- drivers/acpi/processor_perflib.c | 2 +- drivers/cpufreq/cpufreq.c | 16 ++++++++++++++++ drivers/cpufreq/intel_pstate.c | 24 ++++++++++++++++++++++++ include/linux/cpufreq.h | 4 ++++ 4 files changed, 45 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c index a303fd0e108c..c73d3a62799a 100644 --- a/drivers/acpi/processor_perflib.c +++ b/drivers/acpi/processor_perflib.c @@ -181,7 +181,7 @@ void acpi_processor_ppc_has_changed(struct acpi_processor *pr, int event_flag) acpi_processor_ppc_ost(pr->handle, 0); } if (ret >= 0) - cpufreq_update_policy(pr->id); + cpufreq_update_limits(pr->id); } int acpi_processor_get_bios_limit(int cpu, unsigned int *limit) diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index e10922709d13..bb63347f6af1 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -2370,6 +2370,22 @@ unlock: } EXPORT_SYMBOL(cpufreq_update_policy); +/** + * cpufreq_update_limits - Update policy limits for a given CPU. + * @cpu: CPU to update the policy limits for. + * + * Invoke the driver's ->update_limits callback if present or call + * cpufreq_update_policy() for @cpu. + */ +void cpufreq_update_limits(unsigned int cpu) +{ + if (cpufreq_driver->update_limits) + cpufreq_driver->update_limits(cpu); + else + cpufreq_update_policy(cpu); +} +EXPORT_SYMBOL_GPL(cpufreq_update_limits); + /********************************************************************* * BOOST * *********************************************************************/ diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index b599c7318aab..e2191a570ade 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -179,6 +179,7 @@ struct vid_data { * based on the MSR_IA32_MISC_ENABLE value and whether or * not the maximum reported turbo P-state is different from * the maximum reported non-turbo one. + * @turbo_disabled_s: Saved @turbo_disabled value. * @min_perf_pct: Minimum capacity limit in percent of the maximum turbo * P-state capacity. * @max_perf_pct: Maximum capacity limit in percent of the maximum turbo @@ -187,6 +188,7 @@ struct vid_data { struct global_params { bool no_turbo; bool turbo_disabled; + bool turbo_disabled_s; int max_perf_pct; int min_perf_pct; }; @@ -897,6 +899,25 @@ static void intel_pstate_update_policies(void) cpufreq_update_policy(cpu); } +static void intel_pstate_update_limits(unsigned int cpu) +{ + mutex_lock(&intel_pstate_driver_lock); + + update_turbo_state(); + /* + * If turbo has been turned on or off globally, policy limits for + * all CPUs need to be updated to reflect that. + */ + if (global.turbo_disabled_s != global.turbo_disabled) { + global.turbo_disabled_s = global.turbo_disabled; + intel_pstate_update_policies(); + } else { + cpufreq_update_policy(cpu); + } + + mutex_unlock(&intel_pstate_driver_lock); +} + /************************** sysfs begin ************************/ #define show_one(file_name, object) \ static ssize_t show_##file_name \ @@ -2138,6 +2159,7 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy) /* cpuinfo and default policy values */ policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling; update_turbo_state(); + global.turbo_disabled_s = global.turbo_disabled; policy->cpuinfo.max_freq = global.turbo_disabled ? cpu->pstate.max_pstate : cpu->pstate.turbo_pstate; policy->cpuinfo.max_freq *= cpu->pstate.scaling; @@ -2182,6 +2204,7 @@ static struct cpufreq_driver intel_pstate = { .init = intel_pstate_cpu_init, .exit = intel_pstate_cpu_exit, .stop_cpu = intel_pstate_stop_cpu, + .update_limits = intel_pstate_update_limits, .name = "intel_pstate", }; @@ -2316,6 +2339,7 @@ static struct cpufreq_driver intel_cpufreq = { .init = intel_cpufreq_cpu_init, .exit = intel_pstate_cpu_exit, .stop_cpu = intel_cpufreq_stop_cpu, + .update_limits = intel_pstate_update_limits, .name = "intel_cpufreq", }; diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index b160e98076e3..5005ea40364f 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -195,6 +195,7 @@ void disable_cpufreq(void); u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy); int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu); void cpufreq_update_policy(unsigned int cpu); +void cpufreq_update_limits(unsigned int cpu); bool have_governor_per_policy(void); struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy); void cpufreq_enable_fast_switch(struct cpufreq_policy *policy); @@ -322,6 +323,9 @@ struct cpufreq_driver { /* should be defined, if possible */ unsigned int (*get)(unsigned int cpu); + /* Called to update policy limits on firmware notifications. */ + void (*update_limits)(unsigned int cpu); + /* optional */ int (*bios_limit)(int cpu, unsigned int *limit); -- cgit From b5dee3130bb4014511f5d0dd46855ed843e3fdc8 Mon Sep 17 00:00:00 2001 From: Harry Pan Date: Mon, 25 Feb 2019 20:36:41 +0800 Subject: PM / sleep: Refactor filesystems sync to reduce duplication Create a common helper to sync filesystems for system suspend and hibernation. Signed-off-by: Harry Pan Acked-by: Pavel Machek [ rjw: Changelog ] Signed-off-by: Rafael J. Wysocki --- include/linux/suspend.h | 3 +++ kernel/power/hibernate.c | 5 +---- kernel/power/main.c | 9 +++++++++ kernel/power/suspend.c | 13 +++++-------- kernel/power/user.c | 5 +---- 5 files changed, 19 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/suspend.h b/include/linux/suspend.h index 3f529ad9a9d2..6b3ea9ea6a9e 100644 --- a/include/linux/suspend.h +++ b/include/linux/suspend.h @@ -425,6 +425,7 @@ void restore_processor_state(void); /* kernel/power/main.c */ extern int register_pm_notifier(struct notifier_block *nb); extern int unregister_pm_notifier(struct notifier_block *nb); +extern void ksys_sync_helper(void); #define pm_notifier(fn, pri) { \ static struct notifier_block fn##_nb = \ @@ -462,6 +463,8 @@ static inline int unregister_pm_notifier(struct notifier_block *nb) return 0; } +static inline void ksys_sync_helper(void) {} + #define pm_notifier(fn, pri) do { (void)(fn); } while (0) static inline bool pm_wakeup_pending(void) { return false; } diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index abef759de7c8..cc105ecd9c07 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -14,7 +14,6 @@ #include #include -#include #include #include #include @@ -709,9 +708,7 @@ int hibernate(void) goto Exit; } - pr_info("Syncing filesystems ... \n"); - ksys_sync(); - pr_info("done.\n"); + ksys_sync_helper(); error = freeze_processes(); if (error) diff --git a/kernel/power/main.c b/kernel/power/main.c index 98e76cad128b..40472a7c5536 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -16,6 +16,7 @@ #include #include #include +#include #include "power.h" @@ -51,6 +52,14 @@ void unlock_system_sleep(void) } EXPORT_SYMBOL_GPL(unlock_system_sleep); +void ksys_sync_helper(void) +{ + pr_info("Syncing filesystems ... "); + ksys_sync(); + pr_cont("done.\n"); +} +EXPORT_SYMBOL_GPL(ksys_sync_helper); + /* Routines for PM-transition notifications */ static BLOCKING_NOTIFIER_HEAD(pm_chain_head); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 0bd595a0b610..e39059dea38b 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -17,7 +17,6 @@ #include #include #include -#include #include #include #include @@ -568,13 +567,11 @@ static int enter_state(suspend_state_t state) if (state == PM_SUSPEND_TO_IDLE) s2idle_begin(); -#ifndef CONFIG_SUSPEND_SKIP_SYNC - trace_suspend_resume(TPS("sync_filesystems"), 0, true); - pr_info("Syncing filesystems ... "); - ksys_sync(); - pr_cont("done.\n"); - trace_suspend_resume(TPS("sync_filesystems"), 0, false); -#endif + if (!IS_ENABLED(CONFIG_SUSPEND_SKIP_SYNC)) { + trace_suspend_resume(TPS("sync_filesystems"), 0, true); + ksys_sync_helper(); + trace_suspend_resume(TPS("sync_filesystems"), 0, false); + } pm_pr_dbg("Preparing system for sleep (%s)\n", mem_sleep_labels[state]); pm_suspend_clear_flags(); diff --git a/kernel/power/user.c b/kernel/power/user.c index 2d8b60a3c86b..cb24e840a3e6 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -10,7 +10,6 @@ */ #include -#include #include #include #include @@ -228,9 +227,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, if (data->frozen) break; - printk("Syncing filesystems ... "); - ksys_sync(); - printk("done.\n"); + ksys_sync_helper(); error = freeze_processes(); if (error) -- cgit From de7b77e5bb9451417ca57f1b6501da654587c048 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Wed, 27 Mar 2019 07:00:29 -0500 Subject: cpu/hotplug: Create SMT sysfs interface for all arches Make the /sys/devices/system/cpu/smt/* files available on all arches, so user space has a consistent way to detect whether SMT is enabled. The 'control' file now shows 'notimplemented' for architectures which don't yet have CONFIG_HOTPLUG_SMT. [ tglx: Make notimplemented a real state ] Signed-off-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner Cc: Andrea Arcangeli Cc: Waiman Long Cc: Peter Zijlstra Cc: Jiri Kosina Link: https://lkml.kernel.org/r/469c2b98055f2c41e75748e06447d592a64080c9.1553635520.git.jpoimboe@redhat.com --- Documentation/ABI/testing/sysfs-devices-system-cpu | 10 ++-- include/linux/cpu.h | 3 +- kernel/cpu.c | 64 +++++++++++++--------- 3 files changed, 47 insertions(+), 30 deletions(-) (limited to 'include/linux') diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index 9605dbd4b5b5..5eea46fefcb2 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -511,10 +511,12 @@ Description: Control Symetric Multi Threading (SMT) control: Read/write interface to control SMT. Possible values: - "on" SMT is enabled - "off" SMT is disabled - "forceoff" SMT is force disabled. Cannot be changed. - "notsupported" SMT is not supported by the CPU + "on" SMT is enabled + "off" SMT is disabled + "forceoff" SMT is force disabled. Cannot be changed. + "notsupported" SMT is not supported by the CPU + "notimplemented" SMT runtime toggling is not + implemented for the architecture If control status is "forceoff" or "notsupported" writes are rejected. diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 5041357d0297..ae99dde02320 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -175,6 +175,7 @@ enum cpuhp_smt_control { CPU_SMT_DISABLED, CPU_SMT_FORCE_DISABLED, CPU_SMT_NOT_SUPPORTED, + CPU_SMT_NOT_IMPLEMENTED, }; #if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT) @@ -182,7 +183,7 @@ extern enum cpuhp_smt_control cpu_smt_control; extern void cpu_smt_disable(bool force); extern void cpu_smt_check_topology(void); #else -# define cpu_smt_control (CPU_SMT_ENABLED) +# define cpu_smt_control (CPU_SMT_NOT_IMPLEMENTED) static inline void cpu_smt_disable(bool force) { } static inline void cpu_smt_check_topology(void) { } #endif diff --git a/kernel/cpu.c b/kernel/cpu.c index 6754f3ecfd94..b8bf3f93e39b 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -2033,19 +2033,6 @@ static const struct attribute_group cpuhp_cpu_root_attr_group = { #ifdef CONFIG_HOTPLUG_SMT -static const char *smt_states[] = { - [CPU_SMT_ENABLED] = "on", - [CPU_SMT_DISABLED] = "off", - [CPU_SMT_FORCE_DISABLED] = "forceoff", - [CPU_SMT_NOT_SUPPORTED] = "notsupported", -}; - -static ssize_t -show_smt_control(struct device *dev, struct device_attribute *attr, char *buf) -{ - return snprintf(buf, PAGE_SIZE - 2, "%s\n", smt_states[cpu_smt_control]); -} - static void cpuhp_offline_cpu_device(unsigned int cpu) { struct device *dev = get_cpu_device(cpu); @@ -2116,9 +2103,10 @@ static int cpuhp_smt_enable(void) return ret; } + static ssize_t -store_smt_control(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +__store_smt_control(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) { int ctrlval, ret; @@ -2156,14 +2144,44 @@ store_smt_control(struct device *dev, struct device_attribute *attr, unlock_device_hotplug(); return ret ? ret : count; } + +#else /* !CONFIG_HOTPLUG_SMT */ +static ssize_t +__store_smt_control(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + return -ENODEV; +} +#endif /* CONFIG_HOTPLUG_SMT */ + +static const char *smt_states[] = { + [CPU_SMT_ENABLED] = "on", + [CPU_SMT_DISABLED] = "off", + [CPU_SMT_FORCE_DISABLED] = "forceoff", + [CPU_SMT_NOT_SUPPORTED] = "notsupported", + [CPU_SMT_NOT_IMPLEMENTED] = "notimplemented", +}; + +static ssize_t +show_smt_control(struct device *dev, struct device_attribute *attr, char *buf) +{ + const char *state = smt_states[cpu_smt_control]; + + return snprintf(buf, PAGE_SIZE - 2, "%s\n", state); +} + +static ssize_t +store_smt_control(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + return __store_smt_control(dev, attr, buf, count); +} static DEVICE_ATTR(control, 0644, show_smt_control, store_smt_control); static ssize_t show_smt_active(struct device *dev, struct device_attribute *attr, char *buf) { - bool active = topology_max_smt_threads() > 1; - - return snprintf(buf, PAGE_SIZE - 2, "%d\n", active); + return snprintf(buf, PAGE_SIZE - 2, "%d\n", sched_smt_active()); } static DEVICE_ATTR(active, 0444, show_smt_active, NULL); @@ -2179,21 +2197,17 @@ static const struct attribute_group cpuhp_smt_attr_group = { NULL }; -static int __init cpu_smt_state_init(void) +static int __init cpu_smt_sysfs_init(void) { return sysfs_create_group(&cpu_subsys.dev_root->kobj, &cpuhp_smt_attr_group); } -#else -static inline int cpu_smt_state_init(void) { return 0; } -#endif - static int __init cpuhp_sysfs_init(void) { int cpu, ret; - ret = cpu_smt_state_init(); + ret = cpu_smt_sysfs_init(); if (ret) return ret; @@ -2214,7 +2228,7 @@ static int __init cpuhp_sysfs_init(void) return 0; } device_initcall(cpuhp_sysfs_init); -#endif +#endif /* CONFIG_SYSFS && CONFIG_HOTPLUG_CPU */ /* * cpu_bit_bitmap[] is a special, "compressed" data structure that -- cgit From fad9fab975cb9fae651854c811cb07a30bc2b98a Mon Sep 17 00:00:00 2001 From: Thor Thayer Date: Tue, 2 Apr 2019 17:40:56 +0200 Subject: EDAC/altera, firmware/intel: Add Stratix10 ECC DBE SMC call Reserve ECC Double Bit Error SMC call to alert U-Boot that a DBE has occurred. Move the call from local EDAC header file to a common header. [ bp: Merge the two patches. ] Signed-off-by: Thor Thayer Signed-off-by: Borislav Petkov Reviewed-by: Richard Gong Reviewed-by: Alan Tull # firmware Cc: Greg KH Cc: James Morse Cc: linux-edac Cc: mchehab@kernel.org Link: https://lkml.kernel.org/r/1553870639-23895-1-git-send-email-thor.thayer@linux.intel.com Signed-off-by: Borislav Petkov --- drivers/edac/altera_edac.c | 1 + drivers/edac/altera_edac.h | 83 ---------------------------- include/linux/firmware/intel/stratix10-smc.h | 19 +++++++ 3 files changed, 20 insertions(+), 83 deletions(-) (limited to 'include/linux') diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c index 761199175c76..8816f74a22b4 100644 --- a/drivers/edac/altera_edac.c +++ b/drivers/edac/altera_edac.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include diff --git a/drivers/edac/altera_edac.h b/drivers/edac/altera_edac.h index 1532ec9c3510..55654cc4bcdf 100644 --- a/drivers/edac/altera_edac.h +++ b/drivers/edac/altera_edac.h @@ -372,87 +372,4 @@ struct altr_arria10_edac { struct notifier_block panic_notifier; }; -/* - * Functions specified by ARM SMC Calling convention: - * - * FAST call executes atomic operations, returns when the requested operation - * has completed. - * STD call starts a operation which can be preempted by a non-secure - * interrupt. The call can return before the requested operation has - * completed. - * - * a0..a7 is used as register names in the descriptions below, on arm32 - * that translates to r0..r7 and on arm64 to w0..w7. - */ - -#define INTEL_SIP_SMC_STD_CALL_VAL(func_num) \ - ARM_SMCCC_CALL_VAL(ARM_SMCCC_STD_CALL, ARM_SMCCC_SMC_64, \ - ARM_SMCCC_OWNER_SIP, (func_num)) - -#define INTEL_SIP_SMC_FAST_CALL_VAL(func_num) \ - ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, ARM_SMCCC_SMC_64, \ - ARM_SMCCC_OWNER_SIP, (func_num)) - -#define INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION 0xFFFFFFFF -#define INTEL_SIP_SMC_STATUS_OK 0x0 -#define INTEL_SIP_SMC_REG_ERROR 0x5 - -/* - * Request INTEL_SIP_SMC_REG_READ - * - * Read a protected register using SMCCC - * - * Call register usage: - * a0: INTEL_SIP_SMC_REG_READ. - * a1: register address. - * a2-7: not used. - * - * Return status: - * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_REG_ERROR, or - * INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION - * a1: Value in the register - * a2-3: not used. - */ -#define INTEL_SIP_SMC_FUNCID_REG_READ 7 -#define INTEL_SIP_SMC_REG_READ \ - INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_REG_READ) - -/* - * Request INTEL_SIP_SMC_REG_WRITE - * - * Write a protected register using SMCCC - * - * Call register usage: - * a0: INTEL_SIP_SMC_REG_WRITE. - * a1: register address - * a2: value to program into register. - * a3-7: not used. - * - * Return status: - * a0: INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_REG_ERROR, or - * INTEL_SIP_SMC_RETURN_UNKNOWN_FUNCTION - * a1-3: not used. - */ -#define INTEL_SIP_SMC_FUNCID_REG_WRITE 8 -#define INTEL_SIP_SMC_REG_WRITE \ - INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_REG_WRITE) - -/* - * Request INTEL_SIP_SMC_ECC_DBE - * - * Sync call used by service driver at EL1 alert EL3 that a Double Bit - * ECC error has occurred. - * - * Call register usage: - * a0 INTEL_SIP_SMC_ECC_DBE - * a1 SysManager Double Bit Error value - * a2-7 not used - * - * Return status - * a0 INTEL_SIP_SMC_STATUS_OK - */ -#define INTEL_SIP_SMC_FUNCID_ECC_DBE 13 -#define INTEL_SIP_SMC_ECC_DBE \ - INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_ECC_DBE) - #endif /* #ifndef _ALTERA_EDAC_H */ diff --git a/include/linux/firmware/intel/stratix10-smc.h b/include/linux/firmware/intel/stratix10-smc.h index 5be5dab50b13..01684d935580 100644 --- a/include/linux/firmware/intel/stratix10-smc.h +++ b/include/linux/firmware/intel/stratix10-smc.h @@ -309,4 +309,23 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE) #define INTEL_SIP_SMC_FUNCID_RSU_UPDATE 12 #define INTEL_SIP_SMC_RSU_UPDATE \ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_RSU_UPDATE) + +/* + * Request INTEL_SIP_SMC_ECC_DBE + * + * Sync call used by service driver at EL1 to alert EL3 that a Double + * Bit ECC error has occurred. + * + * Call register usage: + * a0 INTEL_SIP_SMC_ECC_DBE + * a1 SysManager Double Bit Error value + * a2-7 not used + * + * Return status + * a0 INTEL_SIP_SMC_STATUS_OK + */ +#define INTEL_SIP_SMC_FUNCID_ECC_DBE 13 +#define INTEL_SIP_SMC_ECC_DBE \ + INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_ECC_DBE) + #endif -- cgit From 37686b1353cfc30e127cef811959cdbcd0495d98 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Thu, 7 Mar 2019 11:48:02 -0600 Subject: tracing: Improve "if" macro code generation With CONFIG_PROFILE_ALL_BRANCHES=y, the "if" macro converts the conditional to an array index. This can cause GCC to create horrible code. When there are nested ifs, the generated code uses register values to encode branching decisions. Make it easier for GCC to optimize by keeping the conditional as a conditional rather than converting it to an integer. This shrinks the generated code quite a bit, and also makes the code sane enough for objtool to understand. Reported-by: Peter Zijlstra Signed-off-by: Josh Poimboeuf Signed-off-by: Peter Zijlstra (Intel) Cc: Borislav Petkov Cc: Linus Torvalds Cc: Thomas Gleixner Cc: brgerst@gmail.com Cc: catalin.marinas@arm.com Cc: dvlasenk@redhat.com Cc: dvyukov@google.com Cc: hpa@zytor.com Cc: james.morse@arm.com Cc: julien.thierry@arm.com Cc: luto@amacapital.net Cc: luto@kernel.org Cc: rostedt@goodmis.org Cc: valentin.schneider@arm.com Cc: will.deacon@arm.com Link: https://lkml.kernel.org/r/20190307174802.46fmpysxyo35hh43@treble Signed-off-by: Ingo Molnar --- include/linux/compiler.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 445348facea9..d58aa0db05f9 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -67,7 +67,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, .line = __LINE__, \ }; \ ______r = !!(cond); \ - ______f.miss_hit[______r]++; \ + ______r ? ______f.miss_hit[1]++ : ______f.miss_hit[0]++;\ ______r; \ })) #endif /* CONFIG_PROFILE_ALL_BRANCHES */ -- cgit From e74deb11931ff682b59d5b9d387f7115f689698e Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 3 Apr 2019 09:39:48 +0200 Subject: x86/uaccess: Introduce user_access_{save,restore}() Introduce common helpers for when we need to safely suspend a uaccess section; for instance to generate a {KA,UB}SAN report. Signed-off-by: Peter Zijlstra (Intel) Cc: Borislav Petkov Cc: Josh Poimboeuf Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- arch/x86/include/asm/smap.h | 20 ++++++++++++++++++++ arch/x86/include/asm/uaccess.h | 3 +++ include/linux/uaccess.h | 2 ++ 3 files changed, 25 insertions(+) (limited to 'include/linux') diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h index db333300bd4b..6cfe43171020 100644 --- a/arch/x86/include/asm/smap.h +++ b/arch/x86/include/asm/smap.h @@ -58,6 +58,23 @@ static __always_inline void stac(void) alternative("", __stringify(__ASM_STAC), X86_FEATURE_SMAP); } +static __always_inline unsigned long smap_save(void) +{ + unsigned long flags; + + asm volatile (ALTERNATIVE("", "pushf; pop %0; " __stringify(__ASM_CLAC), + X86_FEATURE_SMAP) + : "=rm" (flags) : : "memory", "cc"); + + return flags; +} + +static __always_inline void smap_restore(unsigned long flags) +{ + asm volatile (ALTERNATIVE("", "push %0; popf", X86_FEATURE_SMAP) + : : "g" (flags) : "memory", "cc"); +} + /* These macros can be used in asm() statements */ #define ASM_CLAC \ ALTERNATIVE("", __stringify(__ASM_CLAC), X86_FEATURE_SMAP) @@ -69,6 +86,9 @@ static __always_inline void stac(void) static inline void clac(void) { } static inline void stac(void) { } +static inline unsigned long smap_save(void) { return 0; } +static inline void smap_restore(unsigned long flags) { } + #define ASM_CLAC #define ASM_STAC diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index ae5783b5fab0..5ca7b91faf67 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -715,6 +715,9 @@ static __must_check __always_inline bool user_access_begin(const void __user *pt #define user_access_begin(a,b) user_access_begin(a,b) #define user_access_end() __uaccess_end() +#define user_access_save() smap_save() +#define user_access_restore(x) smap_restore(x) + #define unsafe_put_user(x, ptr, label) \ __put_user_size((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), label) diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 37b226e8df13..2b70130af585 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -268,6 +268,8 @@ extern long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count); #define user_access_end() do { } while (0) #define unsafe_get_user(x, ptr, err) do { if (unlikely(__get_user(x, ptr))) goto err; } while (0) #define unsafe_put_user(x, ptr, err) do { if (unlikely(__put_user(x, ptr))) goto err; } while (0) +static inline unsigned long user_access_save(void) { return 0UL; } +static inline void user_access_restore(unsigned long flags) { } #endif #ifdef CONFIG_HARDENED_USERCOPY -- cgit From 1279e41d535e28cc3b56fa4a09e71a709641cae6 Mon Sep 17 00:00:00 2001 From: Shaokun Zhang Date: Wed, 3 Apr 2019 14:54:24 +0800 Subject: perf/headers: Fix stale comment for struct perf_addr_filter The @inode field has been removed after: 9511bce9fe8e ("perf/core: Fix bad use of igrab()") Update the description. Signed-off-by: Shaokun Zhang Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Song Liu Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Link: https://lkml.kernel.org/r/1554274464-5739-1-git-send-email-zhangshaokun@hisilicon.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index e47ef764f613..085a95e2582a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -464,7 +464,7 @@ enum perf_addr_filter_action_t { /** * struct perf_addr_filter - address range filter definition * @entry: event's filter list linkage - * @inode: object file's inode for file-based filters + * @path: object file's path for file-based filters * @offset: filter range offset * @size: filter range size (size==0 means single address trigger) * @action: filter/start/stop -- cgit From a0fe2c6479aab5723239b315ef1b552673f434a3 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Fri, 29 Mar 2019 22:46:49 +0100 Subject: linux/kernel.h: Use parentheses around argument in u64_to_user_ptr() Use parentheses around uses of the argument in u64_to_user_ptr() to ensure that the cast doesn't apply to part of the argument. There are existing uses of the macro of the form u64_to_user_ptr(A + B) which expands to (void __user *)(uintptr_t)A + B (the cast applies to the first operand of the addition, the addition is a pointer addition). This happens to still work as intended, the semantic difference doesn't cause a difference in behavior. But I want to use u64_to_user_ptr() with a ternary operator in the argument, like so: u64_to_user_ptr(A ? B : C) This currently doesn't work as intended. Signed-off-by: Jann Horn Signed-off-by: Borislav Petkov Reviewed-by: Mukesh Ojha Cc: Andrei Vagin Cc: Andrew Morton Cc: Dan Carpenter Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jani Nikula Cc: Kees Cook Cc: Masahiro Yamada Cc: NeilBrown Cc: Peter Zijlstra Cc: Qiaowei Ren Cc: Thomas Gleixner Cc: x86-ml Link: https://lkml.kernel.org/r/20190329214652.258477-1-jannh@google.com --- include/linux/kernel.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 34a5036debd3..2d14e21c16c0 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -47,8 +47,8 @@ #define u64_to_user_ptr(x) ( \ { \ - typecheck(u64, x); \ - (void __user *)(uintptr_t)x; \ + typecheck(u64, (x)); \ + (void __user *)(uintptr_t)(x); \ } \ ) -- cgit From 994aeb7a93e43d28f6074195ccb03a384342e1bf Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Wed, 20 Mar 2019 20:34:24 -0400 Subject: sched_domain: Annotate RCU pointers properly The scheduler uses RCU API in various places to access sched_domain pointers. These cause sparse errors as below. Many new errors show up because of an annotation check I added to rcu_assign_pointer(). Let us annotate the pointers correctly which also will help sparse catch any potential future bugs. This fixes the following sparse errors: rt.c:1681:9: error: incompatible types in comparison expression deadline.c:1904:9: error: incompatible types in comparison expression core.c:519:9: error: incompatible types in comparison expression core.c:1634:17: error: incompatible types in comparison expression fair.c:6193:14: error: incompatible types in comparison expression fair.c:9883:22: error: incompatible types in comparison expression fair.c:9897:9: error: incompatible types in comparison expression sched.h:1287:9: error: incompatible types in comparison expression topology.c:612:9: error: incompatible types in comparison expression topology.c:615:9: error: incompatible types in comparison expression sched.h:1300:9: error: incompatible types in comparison expression topology.c:618:9: error: incompatible types in comparison expression sched.h:1287:9: error: incompatible types in comparison expression topology.c:621:9: error: incompatible types in comparison expression sched.h:1300:9: error: incompatible types in comparison expression topology.c:624:9: error: incompatible types in comparison expression topology.c:671:9: error: incompatible types in comparison expression stats.c:45:17: error: incompatible types in comparison expression fair.c:5998:15: error: incompatible types in comparison expression fair.c:5989:15: error: incompatible types in comparison expression fair.c:5998:15: error: incompatible types in comparison expression fair.c:5989:15: error: incompatible types in comparison expression fair.c:6120:19: error: incompatible types in comparison expression fair.c:6506:14: error: incompatible types in comparison expression fair.c:6515:14: error: incompatible types in comparison expression fair.c:6623:9: error: incompatible types in comparison expression fair.c:5970:17: error: incompatible types in comparison expression fair.c:8642:21: error: incompatible types in comparison expression fair.c:9253:9: error: incompatible types in comparison expression fair.c:9331:9: error: incompatible types in comparison expression fair.c:9519:15: error: incompatible types in comparison expression fair.c:9533:14: error: incompatible types in comparison expression fair.c:9542:14: error: incompatible types in comparison expression fair.c:9567:14: error: incompatible types in comparison expression fair.c:9597:14: error: incompatible types in comparison expression fair.c:9421:16: error: incompatible types in comparison expression fair.c:9421:16: error: incompatible types in comparison expression Signed-off-by: Joel Fernandes (Google) Signed-off-by: Peter Zijlstra (Intel) [ From an RCU perspective. ] Reviewed-by: Paul E. McKenney Cc: Josh Triplett Cc: Lai Jiangshan Cc: Linus Torvalds Cc: Luc Van Oostenryck Cc: Mathieu Desnoyers Cc: Mike Galbraith Cc: Morten Rasmussen Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner Cc: keescook@chromium.org Cc: kernel-hardening@lists.openwall.com Cc: kernel-team@android.com Link: https://lkml.kernel.org/r/20190321003426.160260-3-joel@joelfernandes.org Signed-off-by: Ingo Molnar --- include/linux/sched/topology.h | 4 ++-- kernel/sched/sched.h | 14 +++++++------- kernel/sched/topology.c | 10 +++++----- 3 files changed, 14 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 57c7ed3fe465..cfc0a89a7159 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -76,8 +76,8 @@ struct sched_domain_shared { struct sched_domain { /* These fields must be setup */ - struct sched_domain *parent; /* top domain must be null terminated */ - struct sched_domain *child; /* bottom domain must be null terminated */ + struct sched_domain __rcu *parent; /* top domain must be null terminated */ + struct sched_domain __rcu *child; /* bottom domain must be null terminated */ struct sched_group *groups; /* the balancing groups of the domain */ unsigned long min_interval; /* Minimum balance interval ms */ unsigned long max_interval; /* Maximum balance interval ms */ diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 713715dd00cf..2b452d68ab2e 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -869,8 +869,8 @@ struct rq { atomic_t nr_iowait; #ifdef CONFIG_SMP - struct root_domain *rd; - struct sched_domain *sd; + struct root_domain *rd; + struct sched_domain __rcu *sd; unsigned long cpu_capacity; unsigned long cpu_capacity_orig; @@ -1324,13 +1324,13 @@ static inline struct sched_domain *lowest_flag_domain(int cpu, int flag) return sd; } -DECLARE_PER_CPU(struct sched_domain *, sd_llc); +DECLARE_PER_CPU(struct sched_domain __rcu *, sd_llc); DECLARE_PER_CPU(int, sd_llc_size); DECLARE_PER_CPU(int, sd_llc_id); -DECLARE_PER_CPU(struct sched_domain_shared *, sd_llc_shared); -DECLARE_PER_CPU(struct sched_domain *, sd_numa); -DECLARE_PER_CPU(struct sched_domain *, sd_asym_packing); -DECLARE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity); +DECLARE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared); +DECLARE_PER_CPU(struct sched_domain __rcu *, sd_numa); +DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing); +DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity); extern struct static_key_false sched_asym_cpucapacity; struct sched_group_capacity { diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index ab7f371a3a17..64bec54ded3e 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -615,13 +615,13 @@ static void destroy_sched_domains(struct sched_domain *sd) * the cpumask of the domain), this allows us to quickly tell if * two CPUs are in the same cache domain, see cpus_share_cache(). */ -DEFINE_PER_CPU(struct sched_domain *, sd_llc); +DEFINE_PER_CPU(struct sched_domain __rcu *, sd_llc); DEFINE_PER_CPU(int, sd_llc_size); DEFINE_PER_CPU(int, sd_llc_id); -DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared); -DEFINE_PER_CPU(struct sched_domain *, sd_numa); -DEFINE_PER_CPU(struct sched_domain *, sd_asym_packing); -DEFINE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity); +DEFINE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared); +DEFINE_PER_CPU(struct sched_domain __rcu *, sd_numa); +DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing); +DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity); DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity); static void update_top_cache_domain(int cpu) -- cgit From 03f4b48edae7d936c5bf23488c1ce3fbe7fc2733 Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Wed, 20 Mar 2019 20:34:25 -0400 Subject: rcuwait: Annotate task_struct with __rcu This suppresses sparse error generated due to the recently added rcu_assign_pointer sparse check. percpu-rwsem.c:162:9: sparse: error: incompatible types in comparison expression exit.c:316:16: sparse: error: incompatible types in comparison expression Signed-off-by: Joel Fernandes (Google) Signed-off-by: Peter Zijlstra (Intel) [ From an RCU perspective. ] Reviewed-by: Paul E. McKenney Cc: Josh Triplett Cc: Lai Jiangshan Cc: Linus Torvalds Cc: Luc Van Oostenryck Cc: Mathieu Desnoyers Cc: Mike Galbraith Cc: Morten Rasmussen Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner Cc: keescook@chromium.org Cc: kernel-hardening@lists.openwall.com Cc: kernel-team@android.com Link: https://lkml.kernel.org/r/20190321003426.160260-4-joel@joelfernandes.org Signed-off-by: Ingo Molnar --- include/linux/rcuwait.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rcuwait.h b/include/linux/rcuwait.h index 90bfa3279a01..563290fc194f 100644 --- a/include/linux/rcuwait.h +++ b/include/linux/rcuwait.h @@ -18,7 +18,7 @@ * awoken. */ struct rcuwait { - struct task_struct *task; + struct task_struct __rcu *task; }; #define __RCUWAIT_INITIALIZER(name) \ -- cgit From 46ad0840b1584b92b5ff2cc3ed0b011dd6b8e0f1 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Fri, 22 Mar 2019 10:30:06 -0400 Subject: locking/rwsem: Remove arch specific rwsem files As the generic rwsem-xadd code is using the appropriate acquire and release versions of the atomic operations, the arch specific rwsem.h files will not be that much faster than the generic code as long as the atomic functions are properly implemented. So we can remove those arch specific rwsem.h and stop building asm/rwsem.h to reduce maintenance effort. Currently, only x86, alpha and ia64 have implemented architecture specific fast paths. I don't have access to alpha and ia64 systems for testing, but they are legacy systems that are not likely to be updated to the latest kernel anyway. By using a rwsem microbenchmark, the total locking rates on a 4-socket 56-core 112-thread x86-64 system before and after the patch were as follows (mixed means equal # of read and write locks): Before Patch After Patch # of Threads wlock rlock mixed wlock rlock mixed ------------ ----- ----- ----- ----- ----- ----- 1 29,201 30,143 29,458 28,615 30,172 29,201 2 6,807 13,299 1,171 7,725 15,025 1,804 4 6,504 12,755 1,520 7,127 14,286 1,345 8 6,762 13,412 764 6,826 13,652 726 16 6,693 15,408 662 6,599 15,938 626 32 6,145 15,286 496 5,549 15,487 511 64 5,812 15,495 60 5,858 15,572 60 There were some run-to-run variations for the multi-thread tests. For x86-64, using the generic C code fast path seems to be a little bit faster than the assembly version with low lock contention. Looking at the assembly version of the fast paths, there are assembly to/from C code wrappers that save and restore all the callee-clobbered registers (7 registers on x86-64). The assembly generated from the generic C code doesn't need to do that. That may explain the slight performance gain here. The generic asm rwsem.h can also be merged into kernel/locking/rwsem.h with no code change as no other code other than those under kernel/locking needs to access the internal rwsem macros and functions. Signed-off-by: Waiman Long Signed-off-by: Peter Zijlstra (Intel) Acked-by: Linus Torvalds Cc: Andrew Morton Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Davidlohr Bueso Cc: H. Peter Anvin Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Tim Chen Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: linux-c6x-dev@linux-c6x.org Cc: linux-m68k@lists.linux-m68k.org Cc: linux-riscv@lists.infradead.org Cc: linux-um@lists.infradead.org Cc: linux-xtensa@linux-xtensa.org Cc: linuxppc-dev@lists.ozlabs.org Cc: nios2-dev@lists.rocketboards.org Cc: openrisc@lists.librecores.org Cc: uclinux-h8-devel@lists.sourceforge.jp Link: https://lkml.kernel.org/r/20190322143008.21313-2-longman@redhat.com Signed-off-by: Ingo Molnar --- MAINTAINERS | 1 - arch/alpha/include/asm/rwsem.h | 211 ----------------------------------- arch/arm/include/asm/Kbuild | 1 - arch/arm64/include/asm/Kbuild | 1 - arch/hexagon/include/asm/Kbuild | 1 - arch/ia64/include/asm/rwsem.h | 172 ----------------------------- arch/powerpc/include/asm/Kbuild | 1 - arch/s390/include/asm/Kbuild | 1 - arch/sh/include/asm/Kbuild | 1 - arch/sparc/include/asm/Kbuild | 1 - arch/x86/include/asm/rwsem.h | 237 ---------------------------------------- arch/x86/lib/Makefile | 1 - arch/x86/lib/rwsem.S | 156 -------------------------- arch/x86/um/Makefile | 4 +- arch/xtensa/include/asm/Kbuild | 1 - include/asm-generic/rwsem.h | 140 ------------------------ include/linux/rwsem.h | 4 +- kernel/locking/percpu-rwsem.c | 2 + kernel/locking/rwsem.h | 130 ++++++++++++++++++++++ 19 files changed, 134 insertions(+), 932 deletions(-) delete mode 100644 arch/alpha/include/asm/rwsem.h delete mode 100644 arch/ia64/include/asm/rwsem.h delete mode 100644 arch/x86/include/asm/rwsem.h delete mode 100644 arch/x86/lib/rwsem.S delete mode 100644 include/asm-generic/rwsem.h (limited to 'include/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 43b36dbed48e..8876f5de7738 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -9098,7 +9098,6 @@ F: arch/*/include/asm/spinlock*.h F: include/linux/rwlock*.h F: include/linux/mutex*.h F: include/linux/rwsem*.h -F: arch/*/include/asm/rwsem.h F: include/linux/seqlock.h F: lib/locking*.[ch] F: kernel/locking/ diff --git a/arch/alpha/include/asm/rwsem.h b/arch/alpha/include/asm/rwsem.h deleted file mode 100644 index cf8fc8f9a2ed..000000000000 --- a/arch/alpha/include/asm/rwsem.h +++ /dev/null @@ -1,211 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ALPHA_RWSEM_H -#define _ALPHA_RWSEM_H - -/* - * Written by Ivan Kokshaysky , 2001. - * Based on asm-alpha/semaphore.h and asm-i386/rwsem.h - */ - -#ifndef _LINUX_RWSEM_H -#error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead" -#endif - -#ifdef __KERNEL__ - -#include - -#define RWSEM_UNLOCKED_VALUE 0x0000000000000000L -#define RWSEM_ACTIVE_BIAS 0x0000000000000001L -#define RWSEM_ACTIVE_MASK 0x00000000ffffffffL -#define RWSEM_WAITING_BIAS (-0x0000000100000000L) -#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS -#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) - -static inline int ___down_read(struct rw_semaphore *sem) -{ - long oldcount; -#ifndef CONFIG_SMP - oldcount = sem->count.counter; - sem->count.counter += RWSEM_ACTIVE_READ_BIAS; -#else - long temp; - __asm__ __volatile__( - "1: ldq_l %0,%1\n" - " addq %0,%3,%2\n" - " stq_c %2,%1\n" - " beq %2,2f\n" - " mb\n" - ".subsection 2\n" - "2: br 1b\n" - ".previous" - :"=&r" (oldcount), "=m" (sem->count), "=&r" (temp) - :"Ir" (RWSEM_ACTIVE_READ_BIAS), "m" (sem->count) : "memory"); -#endif - return (oldcount < 0); -} - -static inline void __down_read(struct rw_semaphore *sem) -{ - if (unlikely(___down_read(sem))) - rwsem_down_read_failed(sem); -} - -static inline int __down_read_killable(struct rw_semaphore *sem) -{ - if (unlikely(___down_read(sem))) - if (IS_ERR(rwsem_down_read_failed_killable(sem))) - return -EINTR; - - return 0; -} - -/* - * trylock for reading -- returns 1 if successful, 0 if contention - */ -static inline int __down_read_trylock(struct rw_semaphore *sem) -{ - long old, new, res; - - res = atomic_long_read(&sem->count); - do { - new = res + RWSEM_ACTIVE_READ_BIAS; - if (new <= 0) - break; - old = res; - res = atomic_long_cmpxchg(&sem->count, old, new); - } while (res != old); - return res >= 0 ? 1 : 0; -} - -static inline long ___down_write(struct rw_semaphore *sem) -{ - long oldcount; -#ifndef CONFIG_SMP - oldcount = sem->count.counter; - sem->count.counter += RWSEM_ACTIVE_WRITE_BIAS; -#else - long temp; - __asm__ __volatile__( - "1: ldq_l %0,%1\n" - " addq %0,%3,%2\n" - " stq_c %2,%1\n" - " beq %2,2f\n" - " mb\n" - ".subsection 2\n" - "2: br 1b\n" - ".previous" - :"=&r" (oldcount), "=m" (sem->count), "=&r" (temp) - :"Ir" (RWSEM_ACTIVE_WRITE_BIAS), "m" (sem->count) : "memory"); -#endif - return oldcount; -} - -static inline void __down_write(struct rw_semaphore *sem) -{ - if (unlikely(___down_write(sem))) - rwsem_down_write_failed(sem); -} - -static inline int __down_write_killable(struct rw_semaphore *sem) -{ - if (unlikely(___down_write(sem))) { - if (IS_ERR(rwsem_down_write_failed_killable(sem))) - return -EINTR; - } - - return 0; -} - -/* - * trylock for writing -- returns 1 if successful, 0 if contention - */ -static inline int __down_write_trylock(struct rw_semaphore *sem) -{ - long ret = atomic_long_cmpxchg(&sem->count, RWSEM_UNLOCKED_VALUE, - RWSEM_ACTIVE_WRITE_BIAS); - if (ret == RWSEM_UNLOCKED_VALUE) - return 1; - return 0; -} - -static inline void __up_read(struct rw_semaphore *sem) -{ - long oldcount; -#ifndef CONFIG_SMP - oldcount = sem->count.counter; - sem->count.counter -= RWSEM_ACTIVE_READ_BIAS; -#else - long temp; - __asm__ __volatile__( - " mb\n" - "1: ldq_l %0,%1\n" - " subq %0,%3,%2\n" - " stq_c %2,%1\n" - " beq %2,2f\n" - ".subsection 2\n" - "2: br 1b\n" - ".previous" - :"=&r" (oldcount), "=m" (sem->count), "=&r" (temp) - :"Ir" (RWSEM_ACTIVE_READ_BIAS), "m" (sem->count) : "memory"); -#endif - if (unlikely(oldcount < 0)) - if ((int)oldcount - RWSEM_ACTIVE_READ_BIAS == 0) - rwsem_wake(sem); -} - -static inline void __up_write(struct rw_semaphore *sem) -{ - long count; -#ifndef CONFIG_SMP - sem->count.counter -= RWSEM_ACTIVE_WRITE_BIAS; - count = sem->count.counter; -#else - long temp; - __asm__ __volatile__( - " mb\n" - "1: ldq_l %0,%1\n" - " subq %0,%3,%2\n" - " stq_c %2,%1\n" - " beq %2,2f\n" - " subq %0,%3,%0\n" - ".subsection 2\n" - "2: br 1b\n" - ".previous" - :"=&r" (count), "=m" (sem->count), "=&r" (temp) - :"Ir" (RWSEM_ACTIVE_WRITE_BIAS), "m" (sem->count) : "memory"); -#endif - if (unlikely(count)) - if ((int)count == 0) - rwsem_wake(sem); -} - -/* - * downgrade write lock to read lock - */ -static inline void __downgrade_write(struct rw_semaphore *sem) -{ - long oldcount; -#ifndef CONFIG_SMP - oldcount = sem->count.counter; - sem->count.counter -= RWSEM_WAITING_BIAS; -#else - long temp; - __asm__ __volatile__( - "1: ldq_l %0,%1\n" - " addq %0,%3,%2\n" - " stq_c %2,%1\n" - " beq %2,2f\n" - " mb\n" - ".subsection 2\n" - "2: br 1b\n" - ".previous" - :"=&r" (oldcount), "=m" (sem->count), "=&r" (temp) - :"Ir" (-RWSEM_WAITING_BIAS), "m" (sem->count) : "memory"); -#endif - if (unlikely(oldcount < 0)) - rwsem_downgrade_wake(sem); -} - -#endif /* __KERNEL__ */ -#endif /* _ALPHA_RWSEM_H */ diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild index a8a4eb7f6dae..8fb51b7bf1d5 100644 --- a/arch/arm/include/asm/Kbuild +++ b/arch/arm/include/asm/Kbuild @@ -12,7 +12,6 @@ generic-y += mm-arch-hooks.h generic-y += msi.h generic-y += parport.h generic-y += preempt.h -generic-y += rwsem.h generic-y += seccomp.h generic-y += segment.h generic-y += serial.h diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild index 1e17ea5c372b..60a933b07001 100644 --- a/arch/arm64/include/asm/Kbuild +++ b/arch/arm64/include/asm/Kbuild @@ -16,7 +16,6 @@ generic-y += mm-arch-hooks.h generic-y += msi.h generic-y += qrwlock.h generic-y += qspinlock.h -generic-y += rwsem.h generic-y += segment.h generic-y += serial.h generic-y += set_memory.h diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild index d046e8ccdf78..3ff5f297acda 100644 --- a/arch/hexagon/include/asm/Kbuild +++ b/arch/hexagon/include/asm/Kbuild @@ -27,7 +27,6 @@ generic-y += mm-arch-hooks.h generic-y += pci.h generic-y += percpu.h generic-y += preempt.h -generic-y += rwsem.h generic-y += sections.h generic-y += segment.h generic-y += serial.h diff --git a/arch/ia64/include/asm/rwsem.h b/arch/ia64/include/asm/rwsem.h deleted file mode 100644 index 917910607e0e..000000000000 --- a/arch/ia64/include/asm/rwsem.h +++ /dev/null @@ -1,172 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * R/W semaphores for ia64 - * - * Copyright (C) 2003 Ken Chen - * Copyright (C) 2003 Asit Mallick - * Copyright (C) 2005 Christoph Lameter - * - * Based on asm-i386/rwsem.h and other architecture implementation. - * - * The MSW of the count is the negated number of active writers and - * waiting lockers, and the LSW is the total number of active locks. - * - * The lock count is initialized to 0 (no active and no waiting lockers). - * - * When a writer subtracts WRITE_BIAS, it'll get 0xffffffff00000001 for - * the case of an uncontended lock. Readers increment by 1 and see a positive - * value when uncontended, negative if there are writers (and maybe) readers - * waiting (in which case it goes to sleep). - */ - -#ifndef _ASM_IA64_RWSEM_H -#define _ASM_IA64_RWSEM_H - -#ifndef _LINUX_RWSEM_H -#error "Please don't include directly, use instead." -#endif - -#include - -#define RWSEM_UNLOCKED_VALUE __IA64_UL_CONST(0x0000000000000000) -#define RWSEM_ACTIVE_BIAS (1L) -#define RWSEM_ACTIVE_MASK (0xffffffffL) -#define RWSEM_WAITING_BIAS (-0x100000000L) -#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS -#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) - -/* - * lock for reading - */ -static inline int -___down_read (struct rw_semaphore *sem) -{ - long result = ia64_fetchadd8_acq((unsigned long *)&sem->count.counter, 1); - - return (result < 0); -} - -static inline void -__down_read (struct rw_semaphore *sem) -{ - if (___down_read(sem)) - rwsem_down_read_failed(sem); -} - -static inline int -__down_read_killable (struct rw_semaphore *sem) -{ - if (___down_read(sem)) - if (IS_ERR(rwsem_down_read_failed_killable(sem))) - return -EINTR; - - return 0; -} - -/* - * lock for writing - */ -static inline long -___down_write (struct rw_semaphore *sem) -{ - long old, new; - - do { - old = atomic_long_read(&sem->count); - new = old + RWSEM_ACTIVE_WRITE_BIAS; - } while (atomic_long_cmpxchg_acquire(&sem->count, old, new) != old); - - return old; -} - -static inline void -__down_write (struct rw_semaphore *sem) -{ - if (___down_write(sem)) - rwsem_down_write_failed(sem); -} - -static inline int -__down_write_killable (struct rw_semaphore *sem) -{ - if (___down_write(sem)) { - if (IS_ERR(rwsem_down_write_failed_killable(sem))) - return -EINTR; - } - - return 0; -} - -/* - * unlock after reading - */ -static inline void -__up_read (struct rw_semaphore *sem) -{ - long result = ia64_fetchadd8_rel((unsigned long *)&sem->count.counter, -1); - - if (result < 0 && (--result & RWSEM_ACTIVE_MASK) == 0) - rwsem_wake(sem); -} - -/* - * unlock after writing - */ -static inline void -__up_write (struct rw_semaphore *sem) -{ - long old, new; - - do { - old = atomic_long_read(&sem->count); - new = old - RWSEM_ACTIVE_WRITE_BIAS; - } while (atomic_long_cmpxchg_release(&sem->count, old, new) != old); - - if (new < 0 && (new & RWSEM_ACTIVE_MASK) == 0) - rwsem_wake(sem); -} - -/* - * trylock for reading -- returns 1 if successful, 0 if contention - */ -static inline int -__down_read_trylock (struct rw_semaphore *sem) -{ - long tmp; - while ((tmp = atomic_long_read(&sem->count)) >= 0) { - if (tmp == atomic_long_cmpxchg_acquire(&sem->count, tmp, tmp+1)) { - return 1; - } - } - return 0; -} - -/* - * trylock for writing -- returns 1 if successful, 0 if contention - */ -static inline int -__down_write_trylock (struct rw_semaphore *sem) -{ - long tmp = atomic_long_cmpxchg_acquire(&sem->count, - RWSEM_UNLOCKED_VALUE, RWSEM_ACTIVE_WRITE_BIAS); - return tmp == RWSEM_UNLOCKED_VALUE; -} - -/* - * downgrade write lock to read lock - */ -static inline void -__downgrade_write (struct rw_semaphore *sem) -{ - long old, new; - - do { - old = atomic_long_read(&sem->count); - new = old - RWSEM_WAITING_BIAS; - } while (atomic_long_cmpxchg_release(&sem->count, old, new) != old); - - if (old < 0) - rwsem_downgrade_wake(sem); -} - -#endif /* _ASM_IA64_RWSEM_H */ diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild index a0c132bedfae..36bda391e549 100644 --- a/arch/powerpc/include/asm/Kbuild +++ b/arch/powerpc/include/asm/Kbuild @@ -8,6 +8,5 @@ generic-y += irq_regs.h generic-y += local64.h generic-y += mcs_spinlock.h generic-y += preempt.h -generic-y += rwsem.h generic-y += vtime.h generic-y += msi.h diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild index 12d77cb11fe5..d5fadefea33c 100644 --- a/arch/s390/include/asm/Kbuild +++ b/arch/s390/include/asm/Kbuild @@ -20,7 +20,6 @@ generic-y += local.h generic-y += local64.h generic-y += mcs_spinlock.h generic-y += mm-arch-hooks.h -generic-y += rwsem.h generic-y += trace_clock.h generic-y += unaligned.h generic-y += word-at-a-time.h diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild index 7bf2cb680d32..73fff39a0122 100644 --- a/arch/sh/include/asm/Kbuild +++ b/arch/sh/include/asm/Kbuild @@ -17,7 +17,6 @@ generic-y += mm-arch-hooks.h generic-y += parport.h generic-y += percpu.h generic-y += preempt.h -generic-y += rwsem.h generic-y += serial.h generic-y += sizes.h generic-y += trace_clock.h diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild index a22cfd5c0ee8..2ca3200d3616 100644 --- a/arch/sparc/include/asm/Kbuild +++ b/arch/sparc/include/asm/Kbuild @@ -18,7 +18,6 @@ generic-y += mm-arch-hooks.h generic-y += module.h generic-y += msi.h generic-y += preempt.h -generic-y += rwsem.h generic-y += serial.h generic-y += trace_clock.h generic-y += word-at-a-time.h diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h deleted file mode 100644 index 4c25cf6caefa..000000000000 --- a/arch/x86/include/asm/rwsem.h +++ /dev/null @@ -1,237 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* rwsem.h: R/W semaphores implemented using XADD/CMPXCHG for i486+ - * - * Written by David Howells (dhowells@redhat.com). - * - * Derived from asm-x86/semaphore.h - * - * - * The MSW of the count is the negated number of active writers and waiting - * lockers, and the LSW is the total number of active locks - * - * The lock count is initialized to 0 (no active and no waiting lockers). - * - * When a writer subtracts WRITE_BIAS, it'll get 0xffff0001 for the case of an - * uncontended lock. This can be determined because XADD returns the old value. - * Readers increment by 1 and see a positive value when uncontended, negative - * if there are writers (and maybe) readers waiting (in which case it goes to - * sleep). - * - * The value of WAITING_BIAS supports up to 32766 waiting processes. This can - * be extended to 65534 by manually checking the whole MSW rather than relying - * on the S flag. - * - * The value of ACTIVE_BIAS supports up to 65535 active processes. - * - * This should be totally fair - if anything is waiting, a process that wants a - * lock will go to the back of the queue. When the currently active lock is - * released, if there's a writer at the front of the queue, then that and only - * that will be woken up; if there's a bunch of consecutive readers at the - * front, then they'll all be woken up, but no other readers will be. - */ - -#ifndef _ASM_X86_RWSEM_H -#define _ASM_X86_RWSEM_H - -#ifndef _LINUX_RWSEM_H -#error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead" -#endif - -#ifdef __KERNEL__ -#include - -/* - * The bias values and the counter type limits the number of - * potential readers/writers to 32767 for 32 bits and 2147483647 - * for 64 bits. - */ - -#ifdef CONFIG_X86_64 -# define RWSEM_ACTIVE_MASK 0xffffffffL -#else -# define RWSEM_ACTIVE_MASK 0x0000ffffL -#endif - -#define RWSEM_UNLOCKED_VALUE 0x00000000L -#define RWSEM_ACTIVE_BIAS 0x00000001L -#define RWSEM_WAITING_BIAS (-RWSEM_ACTIVE_MASK-1) -#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS -#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) - -/* - * lock for reading - */ -#define ____down_read(sem, slow_path) \ -({ \ - struct rw_semaphore* ret; \ - asm volatile("# beginning down_read\n\t" \ - LOCK_PREFIX _ASM_INC "(%[sem])\n\t" \ - /* adds 0x00000001 */ \ - " jns 1f\n" \ - " call " slow_path "\n" \ - "1:\n\t" \ - "# ending down_read\n\t" \ - : "+m" (sem->count), "=a" (ret), \ - ASM_CALL_CONSTRAINT \ - : [sem] "a" (sem) \ - : "memory", "cc"); \ - ret; \ -}) - -static inline void __down_read(struct rw_semaphore *sem) -{ - ____down_read(sem, "call_rwsem_down_read_failed"); -} - -static inline int __down_read_killable(struct rw_semaphore *sem) -{ - if (IS_ERR(____down_read(sem, "call_rwsem_down_read_failed_killable"))) - return -EINTR; - return 0; -} - -/* - * trylock for reading -- returns 1 if successful, 0 if contention - */ -static inline bool __down_read_trylock(struct rw_semaphore *sem) -{ - long result, tmp; - asm volatile("# beginning __down_read_trylock\n\t" - " mov %[count],%[result]\n\t" - "1:\n\t" - " mov %[result],%[tmp]\n\t" - " add %[inc],%[tmp]\n\t" - " jle 2f\n\t" - LOCK_PREFIX " cmpxchg %[tmp],%[count]\n\t" - " jnz 1b\n\t" - "2:\n\t" - "# ending __down_read_trylock\n\t" - : [count] "+m" (sem->count), [result] "=&a" (result), - [tmp] "=&r" (tmp) - : [inc] "i" (RWSEM_ACTIVE_READ_BIAS) - : "memory", "cc"); - return result >= 0; -} - -/* - * lock for writing - */ -#define ____down_write(sem, slow_path) \ -({ \ - long tmp; \ - struct rw_semaphore* ret; \ - \ - asm volatile("# beginning down_write\n\t" \ - LOCK_PREFIX " xadd %[tmp],(%[sem])\n\t" \ - /* adds 0xffff0001, returns the old value */ \ - " test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t" \ - /* was the active mask 0 before? */\ - " jz 1f\n" \ - " call " slow_path "\n" \ - "1:\n" \ - "# ending down_write" \ - : "+m" (sem->count), [tmp] "=d" (tmp), \ - "=a" (ret), ASM_CALL_CONSTRAINT \ - : [sem] "a" (sem), "[tmp]" (RWSEM_ACTIVE_WRITE_BIAS) \ - : "memory", "cc"); \ - ret; \ -}) - -static inline void __down_write(struct rw_semaphore *sem) -{ - ____down_write(sem, "call_rwsem_down_write_failed"); -} - -static inline int __down_write_killable(struct rw_semaphore *sem) -{ - if (IS_ERR(____down_write(sem, "call_rwsem_down_write_failed_killable"))) - return -EINTR; - - return 0; -} - -/* - * trylock for writing -- returns 1 if successful, 0 if contention - */ -static inline bool __down_write_trylock(struct rw_semaphore *sem) -{ - bool result; - long tmp0, tmp1; - asm volatile("# beginning __down_write_trylock\n\t" - " mov %[count],%[tmp0]\n\t" - "1:\n\t" - " test " __ASM_SEL(%w1,%k1) "," __ASM_SEL(%w1,%k1) "\n\t" - /* was the active mask 0 before? */ - " jnz 2f\n\t" - " mov %[tmp0],%[tmp1]\n\t" - " add %[inc],%[tmp1]\n\t" - LOCK_PREFIX " cmpxchg %[tmp1],%[count]\n\t" - " jnz 1b\n\t" - "2:\n\t" - CC_SET(e) - "# ending __down_write_trylock\n\t" - : [count] "+m" (sem->count), [tmp0] "=&a" (tmp0), - [tmp1] "=&r" (tmp1), CC_OUT(e) (result) - : [inc] "er" (RWSEM_ACTIVE_WRITE_BIAS) - : "memory"); - return result; -} - -/* - * unlock after reading - */ -static inline void __up_read(struct rw_semaphore *sem) -{ - long tmp; - asm volatile("# beginning __up_read\n\t" - LOCK_PREFIX " xadd %[tmp],(%[sem])\n\t" - /* subtracts 1, returns the old value */ - " jns 1f\n\t" - " call call_rwsem_wake\n" /* expects old value in %edx */ - "1:\n" - "# ending __up_read\n" - : "+m" (sem->count), [tmp] "=d" (tmp) - : [sem] "a" (sem), "[tmp]" (-RWSEM_ACTIVE_READ_BIAS) - : "memory", "cc"); -} - -/* - * unlock after writing - */ -static inline void __up_write(struct rw_semaphore *sem) -{ - long tmp; - asm volatile("# beginning __up_write\n\t" - LOCK_PREFIX " xadd %[tmp],(%[sem])\n\t" - /* subtracts 0xffff0001, returns the old value */ - " jns 1f\n\t" - " call call_rwsem_wake\n" /* expects old value in %edx */ - "1:\n\t" - "# ending __up_write\n" - : "+m" (sem->count), [tmp] "=d" (tmp) - : [sem] "a" (sem), "[tmp]" (-RWSEM_ACTIVE_WRITE_BIAS) - : "memory", "cc"); -} - -/* - * downgrade write lock to read lock - */ -static inline void __downgrade_write(struct rw_semaphore *sem) -{ - asm volatile("# beginning __downgrade_write\n\t" - LOCK_PREFIX _ASM_ADD "%[inc],(%[sem])\n\t" - /* - * transitions 0xZZZZ0001 -> 0xYYYY0001 (i386) - * 0xZZZZZZZZ00000001 -> 0xYYYYYYYY00000001 (x86_64) - */ - " jns 1f\n\t" - " call call_rwsem_downgrade_wake\n" - "1:\n\t" - "# ending __downgrade_write\n" - : "+m" (sem->count) - : [sem] "a" (sem), [inc] "er" (-RWSEM_WAITING_BIAS) - : "memory", "cc"); -} - -#endif /* __KERNEL__ */ -#endif /* _ASM_X86_RWSEM_H */ diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 140e61843a07..986652064b15 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -23,7 +23,6 @@ obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o lib-y := delay.o misc.o cmdline.o cpu.o lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o lib-y += memcpy_$(BITS).o -lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o lib-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o diff --git a/arch/x86/lib/rwsem.S b/arch/x86/lib/rwsem.S deleted file mode 100644 index dc2ab6ea6768..000000000000 --- a/arch/x86/lib/rwsem.S +++ /dev/null @@ -1,156 +0,0 @@ -/* - * x86 semaphore implementation. - * - * (C) Copyright 1999 Linus Torvalds - * - * Portions Copyright 1999 Red Hat, Inc. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - * - * rw semaphores implemented November 1999 by Benjamin LaHaise - */ - -#include -#include -#include - -#define __ASM_HALF_REG(reg) __ASM_SEL(reg, e##reg) -#define __ASM_HALF_SIZE(inst) __ASM_SEL(inst##w, inst##l) - -#ifdef CONFIG_X86_32 - -/* - * The semaphore operations have a special calling sequence that - * allow us to do a simpler in-line version of them. These routines - * need to convert that sequence back into the C sequence when - * there is contention on the semaphore. - * - * %eax contains the semaphore pointer on entry. Save the C-clobbered - * registers (%eax, %edx and %ecx) except %eax which is either a return - * value or just gets clobbered. Same is true for %edx so make sure GCC - * reloads it after the slow path, by making it hold a temporary, for - * example see ____down_write(). - */ - -#define save_common_regs \ - pushl %ecx - -#define restore_common_regs \ - popl %ecx - - /* Avoid uglifying the argument copying x86-64 needs to do. */ - .macro movq src, dst - .endm - -#else - -/* - * x86-64 rwsem wrappers - * - * This interfaces the inline asm code to the slow-path - * C routines. We need to save the call-clobbered regs - * that the asm does not mark as clobbered, and move the - * argument from %rax to %rdi. - * - * NOTE! We don't need to save %rax, because the functions - * will always return the semaphore pointer in %rax (which - * is also the input argument to these helpers) - * - * The following can clobber %rdx because the asm clobbers it: - * call_rwsem_down_write_failed - * call_rwsem_wake - * but %rdi, %rsi, %rcx, %r8-r11 always need saving. - */ - -#define save_common_regs \ - pushq %rdi; \ - pushq %rsi; \ - pushq %rcx; \ - pushq %r8; \ - pushq %r9; \ - pushq %r10; \ - pushq %r11 - -#define restore_common_regs \ - popq %r11; \ - popq %r10; \ - popq %r9; \ - popq %r8; \ - popq %rcx; \ - popq %rsi; \ - popq %rdi - -#endif - -/* Fix up special calling conventions */ -ENTRY(call_rwsem_down_read_failed) - FRAME_BEGIN - save_common_regs - __ASM_SIZE(push,) %__ASM_REG(dx) - movq %rax,%rdi - call rwsem_down_read_failed - __ASM_SIZE(pop,) %__ASM_REG(dx) - restore_common_regs - FRAME_END - ret -ENDPROC(call_rwsem_down_read_failed) - -ENTRY(call_rwsem_down_read_failed_killable) - FRAME_BEGIN - save_common_regs - __ASM_SIZE(push,) %__ASM_REG(dx) - movq %rax,%rdi - call rwsem_down_read_failed_killable - __ASM_SIZE(pop,) %__ASM_REG(dx) - restore_common_regs - FRAME_END - ret -ENDPROC(call_rwsem_down_read_failed_killable) - -ENTRY(call_rwsem_down_write_failed) - FRAME_BEGIN - save_common_regs - movq %rax,%rdi - call rwsem_down_write_failed - restore_common_regs - FRAME_END - ret -ENDPROC(call_rwsem_down_write_failed) - -ENTRY(call_rwsem_down_write_failed_killable) - FRAME_BEGIN - save_common_regs - movq %rax,%rdi - call rwsem_down_write_failed_killable - restore_common_regs - FRAME_END - ret -ENDPROC(call_rwsem_down_write_failed_killable) - -ENTRY(call_rwsem_wake) - FRAME_BEGIN - /* do nothing if still outstanding active readers */ - __ASM_HALF_SIZE(dec) %__ASM_HALF_REG(dx) - jnz 1f - save_common_regs - movq %rax,%rdi - call rwsem_wake - restore_common_regs -1: FRAME_END - ret -ENDPROC(call_rwsem_wake) - -ENTRY(call_rwsem_downgrade_wake) - FRAME_BEGIN - save_common_regs - __ASM_SIZE(push,) %__ASM_REG(dx) - movq %rax,%rdi - call rwsem_downgrade_wake - __ASM_SIZE(pop,) %__ASM_REG(dx) - restore_common_regs - FRAME_END - ret -ENDPROC(call_rwsem_downgrade_wake) diff --git a/arch/x86/um/Makefile b/arch/x86/um/Makefile index 2d686ae54681..33c51c064c77 100644 --- a/arch/x86/um/Makefile +++ b/arch/x86/um/Makefile @@ -21,14 +21,12 @@ obj-y += checksum_32.o syscalls_32.o obj-$(CONFIG_ELF_CORE) += elfcore.o subarch-y = ../lib/string_32.o ../lib/atomic64_32.o ../lib/atomic64_cx8_32.o -subarch-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += ../lib/rwsem.o else obj-y += syscalls_64.o vdso/ -subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../entry/thunk_64.o \ - ../lib/rwsem.o +subarch-y = ../lib/csum-partial_64.o ../lib/memcpy_64.o ../entry/thunk_64.o endif diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild index 3843198e03d4..4148090cafb0 100644 --- a/arch/xtensa/include/asm/Kbuild +++ b/arch/xtensa/include/asm/Kbuild @@ -25,7 +25,6 @@ generic-y += percpu.h generic-y += preempt.h generic-y += qrwlock.h generic-y += qspinlock.h -generic-y += rwsem.h generic-y += sections.h generic-y += socket.h generic-y += topology.h diff --git a/include/asm-generic/rwsem.h b/include/asm-generic/rwsem.h deleted file mode 100644 index 93e67a055a4d..000000000000 --- a/include/asm-generic/rwsem.h +++ /dev/null @@ -1,140 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_GENERIC_RWSEM_H -#define _ASM_GENERIC_RWSEM_H - -#ifndef _LINUX_RWSEM_H -#error "Please don't include directly, use instead." -#endif - -#ifdef __KERNEL__ - -/* - * R/W semaphores originally for PPC using the stuff in lib/rwsem.c. - * Adapted largely from include/asm-i386/rwsem.h - * by Paul Mackerras . - */ - -/* - * the semaphore definition - */ -#ifdef CONFIG_64BIT -# define RWSEM_ACTIVE_MASK 0xffffffffL -#else -# define RWSEM_ACTIVE_MASK 0x0000ffffL -#endif - -#define RWSEM_UNLOCKED_VALUE 0x00000000L -#define RWSEM_ACTIVE_BIAS 0x00000001L -#define RWSEM_WAITING_BIAS (-RWSEM_ACTIVE_MASK-1) -#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS -#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) - -/* - * lock for reading - */ -static inline void __down_read(struct rw_semaphore *sem) -{ - if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0)) - rwsem_down_read_failed(sem); -} - -static inline int __down_read_killable(struct rw_semaphore *sem) -{ - if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0)) { - if (IS_ERR(rwsem_down_read_failed_killable(sem))) - return -EINTR; - } - - return 0; -} - -static inline int __down_read_trylock(struct rw_semaphore *sem) -{ - long tmp; - - while ((tmp = atomic_long_read(&sem->count)) >= 0) { - if (tmp == atomic_long_cmpxchg_acquire(&sem->count, tmp, - tmp + RWSEM_ACTIVE_READ_BIAS)) { - return 1; - } - } - return 0; -} - -/* - * lock for writing - */ -static inline void __down_write(struct rw_semaphore *sem) -{ - long tmp; - - tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS, - &sem->count); - if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS)) - rwsem_down_write_failed(sem); -} - -static inline int __down_write_killable(struct rw_semaphore *sem) -{ - long tmp; - - tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS, - &sem->count); - if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS)) - if (IS_ERR(rwsem_down_write_failed_killable(sem))) - return -EINTR; - return 0; -} - -static inline int __down_write_trylock(struct rw_semaphore *sem) -{ - long tmp; - - tmp = atomic_long_cmpxchg_acquire(&sem->count, RWSEM_UNLOCKED_VALUE, - RWSEM_ACTIVE_WRITE_BIAS); - return tmp == RWSEM_UNLOCKED_VALUE; -} - -/* - * unlock after reading - */ -static inline void __up_read(struct rw_semaphore *sem) -{ - long tmp; - - tmp = atomic_long_dec_return_release(&sem->count); - if (unlikely(tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0)) - rwsem_wake(sem); -} - -/* - * unlock after writing - */ -static inline void __up_write(struct rw_semaphore *sem) -{ - if (unlikely(atomic_long_sub_return_release(RWSEM_ACTIVE_WRITE_BIAS, - &sem->count) < 0)) - rwsem_wake(sem); -} - -/* - * downgrade write lock to read lock - */ -static inline void __downgrade_write(struct rw_semaphore *sem) -{ - long tmp; - - /* - * When downgrading from exclusive to shared ownership, - * anything inside the write-locked region cannot leak - * into the read side. In contrast, anything in the - * read-locked region is ok to be re-ordered into the - * write side. As such, rely on RELEASE semantics. - */ - tmp = atomic_long_add_return_release(-RWSEM_WAITING_BIAS, &sem->count); - if (tmp < 0) - rwsem_downgrade_wake(sem); -} - -#endif /* __KERNEL__ */ -#endif /* _ASM_GENERIC_RWSEM_H */ diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 67dbb57508b1..6e56006b2cb6 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -57,15 +57,13 @@ extern struct rw_semaphore *rwsem_down_write_failed_killable(struct rw_semaphore extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *); extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem); -/* Include the arch specific part */ -#include - /* In all implementations count != 0 means locked */ static inline int rwsem_is_locked(struct rw_semaphore *sem) { return atomic_long_read(&sem->count) != 0; } +#define RWSEM_UNLOCKED_VALUE 0L #define __RWSEM_INIT_COUNT(name) .count = ATOMIC_LONG_INIT(RWSEM_UNLOCKED_VALUE) #endif diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c index 883cf1b92d90..f17dad99eec8 100644 --- a/kernel/locking/percpu-rwsem.c +++ b/kernel/locking/percpu-rwsem.c @@ -7,6 +7,8 @@ #include #include +#include "rwsem.h" + int __percpu_init_rwsem(struct percpu_rw_semaphore *sem, const char *name, struct lock_class_key *rwsem_key) { diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h index bad2bca0268b..067e265fa5c1 100644 --- a/kernel/locking/rwsem.h +++ b/kernel/locking/rwsem.h @@ -32,6 +32,26 @@ # define DEBUG_RWSEMS_WARN_ON(c) #endif +/* + * R/W semaphores originally for PPC using the stuff in lib/rwsem.c. + * Adapted largely from include/asm-i386/rwsem.h + * by Paul Mackerras . + */ + +/* + * the semaphore definition + */ +#ifdef CONFIG_64BIT +# define RWSEM_ACTIVE_MASK 0xffffffffL +#else +# define RWSEM_ACTIVE_MASK 0x0000ffffL +#endif + +#define RWSEM_ACTIVE_BIAS 0x00000001L +#define RWSEM_WAITING_BIAS (-RWSEM_ACTIVE_MASK-1) +#define RWSEM_ACTIVE_READ_BIAS RWSEM_ACTIVE_BIAS +#define RWSEM_ACTIVE_WRITE_BIAS (RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS) + #ifdef CONFIG_RWSEM_SPIN_ON_OWNER /* * All writes to owner are protected by WRITE_ONCE() to make sure that @@ -132,3 +152,113 @@ static inline void rwsem_clear_reader_owned(struct rw_semaphore *sem) { } #endif + +#ifdef CONFIG_RWSEM_XCHGADD_ALGORITHM +/* + * lock for reading + */ +static inline void __down_read(struct rw_semaphore *sem) +{ + if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0)) + rwsem_down_read_failed(sem); +} + +static inline int __down_read_killable(struct rw_semaphore *sem) +{ + if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0)) { + if (IS_ERR(rwsem_down_read_failed_killable(sem))) + return -EINTR; + } + + return 0; +} + +static inline int __down_read_trylock(struct rw_semaphore *sem) +{ + long tmp; + + while ((tmp = atomic_long_read(&sem->count)) >= 0) { + if (tmp == atomic_long_cmpxchg_acquire(&sem->count, tmp, + tmp + RWSEM_ACTIVE_READ_BIAS)) { + return 1; + } + } + return 0; +} + +/* + * lock for writing + */ +static inline void __down_write(struct rw_semaphore *sem) +{ + long tmp; + + tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS, + &sem->count); + if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS)) + rwsem_down_write_failed(sem); +} + +static inline int __down_write_killable(struct rw_semaphore *sem) +{ + long tmp; + + tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS, + &sem->count); + if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS)) + if (IS_ERR(rwsem_down_write_failed_killable(sem))) + return -EINTR; + return 0; +} + +static inline int __down_write_trylock(struct rw_semaphore *sem) +{ + long tmp; + + tmp = atomic_long_cmpxchg_acquire(&sem->count, RWSEM_UNLOCKED_VALUE, + RWSEM_ACTIVE_WRITE_BIAS); + return tmp == RWSEM_UNLOCKED_VALUE; +} + +/* + * unlock after reading + */ +static inline void __up_read(struct rw_semaphore *sem) +{ + long tmp; + + tmp = atomic_long_dec_return_release(&sem->count); + if (unlikely(tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0)) + rwsem_wake(sem); +} + +/* + * unlock after writing + */ +static inline void __up_write(struct rw_semaphore *sem) +{ + if (unlikely(atomic_long_sub_return_release(RWSEM_ACTIVE_WRITE_BIAS, + &sem->count) < 0)) + rwsem_wake(sem); +} + +/* + * downgrade write lock to read lock + */ +static inline void __downgrade_write(struct rw_semaphore *sem) +{ + long tmp; + + /* + * When downgrading from exclusive to shared ownership, + * anything inside the write-locked region cannot leak + * into the read side. In contrast, anything in the + * read-locked region is ok to be re-ordered into the + * write side. As such, rely on RELEASE semantics. + */ + tmp = atomic_long_add_return_release(-RWSEM_WAITING_BIAS, &sem->count); + if (tmp < 0) + rwsem_downgrade_wake(sem); +} + +#endif /* CONFIG_RWSEM_XCHGADD_ALGORITHM */ -- cgit From 390a0c62c23cb026cd4664a66f6f45fed3a215f6 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Fri, 22 Mar 2019 10:30:07 -0400 Subject: locking/rwsem: Remove rwsem-spinlock.c & use rwsem-xadd.c for all archs Currently, we have two different implementation of rwsem: 1) CONFIG_RWSEM_GENERIC_SPINLOCK (rwsem-spinlock.c) 2) CONFIG_RWSEM_XCHGADD_ALGORITHM (rwsem-xadd.c) As we are going to use a single generic implementation for rwsem-xadd.c and no architecture-specific code will be needed, there is no point in keeping two different implementations of rwsem. In most cases, the performance of rwsem-spinlock.c will be worse. It also doesn't get all the performance tuning and optimizations that had been implemented in rwsem-xadd.c over the years. For simplication, we are going to remove rwsem-spinlock.c and make all architectures use a single implementation of rwsem - rwsem-xadd.c. All references to RWSEM_GENERIC_SPINLOCK and RWSEM_XCHGADD_ALGORITHM in the code are removed. Suggested-by: Peter Zijlstra Signed-off-by: Waiman Long Signed-off-by: Peter Zijlstra (Intel) Acked-by: Linus Torvalds Cc: Andrew Morton Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Davidlohr Bueso Cc: H. Peter Anvin Cc: Paul E. McKenney Cc: Thomas Gleixner Cc: Tim Chen Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: linux-c6x-dev@linux-c6x.org Cc: linux-m68k@lists.linux-m68k.org Cc: linux-riscv@lists.infradead.org Cc: linux-um@lists.infradead.org Cc: linux-xtensa@linux-xtensa.org Cc: linuxppc-dev@lists.ozlabs.org Cc: nios2-dev@lists.rocketboards.org Cc: openrisc@lists.librecores.org Cc: uclinux-h8-devel@lists.sourceforge.jp Link: https://lkml.kernel.org/r/20190322143008.21313-3-longman@redhat.com Signed-off-by: Ingo Molnar --- arch/alpha/Kconfig | 7 - arch/arc/Kconfig | 3 - arch/arm/Kconfig | 4 - arch/arm64/Kconfig | 3 - arch/c6x/Kconfig | 3 - arch/csky/Kconfig | 3 - arch/h8300/Kconfig | 3 - arch/hexagon/Kconfig | 6 - arch/ia64/Kconfig | 4 - arch/m68k/Kconfig | 7 - arch/microblaze/Kconfig | 6 - arch/mips/Kconfig | 7 - arch/nds32/Kconfig | 3 - arch/nios2/Kconfig | 3 - arch/openrisc/Kconfig | 6 - arch/parisc/Kconfig | 6 - arch/powerpc/Kconfig | 7 - arch/riscv/Kconfig | 3 - arch/s390/Kconfig | 6 - arch/sh/Kconfig | 6 - arch/sparc/Kconfig | 8 - arch/unicore32/Kconfig | 6 - arch/x86/Kconfig | 3 - arch/x86/um/Kconfig | 6 - arch/xtensa/Kconfig | 3 - include/linux/rwsem-spinlock.h | 47 ------ include/linux/rwsem.h | 5 - kernel/Kconfig.locks | 2 +- kernel/locking/Makefile | 4 +- kernel/locking/rwsem-spinlock.c | 339 ---------------------------------------- kernel/locking/rwsem.h | 3 - 31 files changed, 2 insertions(+), 520 deletions(-) delete mode 100644 include/linux/rwsem-spinlock.h delete mode 100644 kernel/locking/rwsem-spinlock.c (limited to 'include/linux') diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 584a6e114853..27c871227eee 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -49,13 +49,6 @@ config MMU bool default y -config RWSEM_GENERIC_SPINLOCK - bool - -config RWSEM_XCHGADD_ALGORITHM - bool - default y - config ARCH_HAS_ILOG2_U32 bool default n diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index c781e45d1d99..23e063df5d2c 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -63,9 +63,6 @@ config SCHED_OMIT_FRAME_POINTER config GENERIC_CSUM def_bool y -config RWSEM_GENERIC_SPINLOCK - def_bool y - config ARCH_DISCONTIGMEM_ENABLE def_bool n diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 850b4805e2d1..c8b03e1c6c2a 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -178,10 +178,6 @@ config TRACE_IRQFLAGS_SUPPORT bool default !CPU_V7M -config RWSEM_XCHGADD_ALGORITHM - bool - default y - config ARCH_HAS_ILOG2_U32 bool diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 7e34b9eba5de..c62b9db2b5e8 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -237,9 +237,6 @@ config LOCKDEP_SUPPORT config TRACE_IRQFLAGS_SUPPORT def_bool y -config RWSEM_XCHGADD_ALGORITHM - def_bool y - config GENERIC_BUG def_bool y depends on BUG diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig index e5cd3c5f8399..ed92b5840c0a 100644 --- a/arch/c6x/Kconfig +++ b/arch/c6x/Kconfig @@ -27,9 +27,6 @@ config MMU config FPU def_bool n -config RWSEM_GENERIC_SPINLOCK - def_bool y - config GENERIC_CALIBRATE_DELAY def_bool y diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig index 725a115759c9..6555d1781132 100644 --- a/arch/csky/Kconfig +++ b/arch/csky/Kconfig @@ -92,9 +92,6 @@ config GENERIC_HWEIGHT config MMU def_bool y -config RWSEM_GENERIC_SPINLOCK - def_bool y - config STACKTRACE_SUPPORT def_bool y diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig index c071da34e081..61c01db6c292 100644 --- a/arch/h8300/Kconfig +++ b/arch/h8300/Kconfig @@ -27,9 +27,6 @@ config H8300 config CPU_BIG_ENDIAN def_bool y -config RWSEM_GENERIC_SPINLOCK - def_bool y - config GENERIC_HWEIGHT def_bool y diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig index ac441680dcc0..3e54a53208d5 100644 --- a/arch/hexagon/Kconfig +++ b/arch/hexagon/Kconfig @@ -65,12 +65,6 @@ config GENERIC_CSUM config GENERIC_IRQ_PROBE def_bool y -config RWSEM_GENERIC_SPINLOCK - def_bool n - -config RWSEM_XCHGADD_ALGORITHM - def_bool y - config GENERIC_HWEIGHT def_bool y diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 8d7396bd1790..73a26f04644e 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -83,10 +83,6 @@ config STACKTRACE_SUPPORT config GENERIC_LOCKBREAK def_bool n -config RWSEM_XCHGADD_ALGORITHM - bool - default y - config HUGETLB_PAGE_SIZE_VARIABLE bool depends on HUGETLB_PAGE diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index b54206408f91..f5661f48019c 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -32,13 +32,6 @@ config M68K config CPU_BIG_ENDIAN def_bool y -config RWSEM_GENERIC_SPINLOCK - bool - default y - -config RWSEM_XCHGADD_ALGORITHM - bool - config ARCH_HAS_ILOG2_U32 bool diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index a51b965b3b82..a7a9a9d59f65 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -58,15 +58,9 @@ config CPU_LITTLE_ENDIAN endchoice -config RWSEM_GENERIC_SPINLOCK - def_bool y - config ZONE_DMA def_bool y -config RWSEM_XCHGADD_ALGORITHM - bool - config ARCH_HAS_ILOG2_U32 def_bool n diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 4a5f5b0ee9a9..b9c48b27162d 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -1037,13 +1037,6 @@ source "arch/mips/paravirt/Kconfig" endmenu -config RWSEM_GENERIC_SPINLOCK - bool - default y - -config RWSEM_XCHGADD_ALGORITHM - bool - config GENERIC_HWEIGHT bool default y diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig index addb7f5f5264..55559ca0efe4 100644 --- a/arch/nds32/Kconfig +++ b/arch/nds32/Kconfig @@ -60,9 +60,6 @@ config GENERIC_LOCKBREAK def_bool y depends on PREEMPT -config RWSEM_GENERIC_SPINLOCK - def_bool y - config TRACE_IRQFLAGS_SUPPORT def_bool y diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig index 4ef15a61b7bc..56685fd45ed0 100644 --- a/arch/nios2/Kconfig +++ b/arch/nios2/Kconfig @@ -40,9 +40,6 @@ config NO_IOPORT_MAP config FPU def_bool n -config RWSEM_GENERIC_SPINLOCK - def_bool y - config TRACE_IRQFLAGS_SUPPORT def_bool n diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig index a5e361fbb75a..683511b8c9df 100644 --- a/arch/openrisc/Kconfig +++ b/arch/openrisc/Kconfig @@ -43,12 +43,6 @@ config CPU_BIG_ENDIAN config MMU def_bool y -config RWSEM_GENERIC_SPINLOCK - def_bool y - -config RWSEM_XCHGADD_ALGORITHM - def_bool n - config GENERIC_HWEIGHT def_bool y diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index c8e621296092..f1ed8ddfe486 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -75,12 +75,6 @@ config GENERIC_LOCKBREAK default y depends on SMP && PREEMPT -config RWSEM_GENERIC_SPINLOCK - def_bool y - -config RWSEM_XCHGADD_ALGORITHM - bool - config ARCH_HAS_ILOG2_U32 bool default n diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 2d0be82c3061..e5dd6aafaf68 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -103,13 +103,6 @@ config LOCKDEP_SUPPORT bool default y -config RWSEM_GENERIC_SPINLOCK - bool - -config RWSEM_XCHGADD_ALGORITHM - bool - default y - config GENERIC_LOCKBREAK bool default y diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index eb56c82d8aa1..0582260fb6c2 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -69,9 +69,6 @@ config STACKTRACE_SUPPORT config TRACE_IRQFLAGS_SUPPORT def_bool y -config RWSEM_GENERIC_SPINLOCK - def_bool y - config GENERIC_BUG def_bool y depends on BUG diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index b6e3d0653002..c9300b437195 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -14,12 +14,6 @@ config LOCKDEP_SUPPORT config STACKTRACE_SUPPORT def_bool y -config RWSEM_GENERIC_SPINLOCK - bool - -config RWSEM_XCHGADD_ALGORITHM - def_bool y - config ARCH_HAS_ILOG2_U32 def_bool n diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index b1c91ea9a958..0be08d586d40 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -90,12 +90,6 @@ config ARCH_DEFCONFIG default "arch/sh/configs/shx3_defconfig" if SUPERH32 default "arch/sh/configs/cayman_defconfig" if SUPERH64 -config RWSEM_GENERIC_SPINLOCK - def_bool y - -config RWSEM_XCHGADD_ALGORITHM - bool - config GENERIC_BUG def_bool y depends on BUG && SUPERH32 diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 40f8f4f73fe8..16b620237816 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -191,14 +191,6 @@ config NR_CPUS source "kernel/Kconfig.hz" -config RWSEM_GENERIC_SPINLOCK - bool - default y if SPARC32 - -config RWSEM_XCHGADD_ALGORITHM - bool - default y if SPARC64 - config GENERIC_HWEIGHT bool default y diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig index 817d82608712..0d5869c9bf03 100644 --- a/arch/unicore32/Kconfig +++ b/arch/unicore32/Kconfig @@ -38,12 +38,6 @@ config STACKTRACE_SUPPORT config LOCKDEP_SUPPORT def_bool y -config RWSEM_GENERIC_SPINLOCK - def_bool y - -config RWSEM_XCHGADD_ALGORITHM - bool - config ARCH_HAS_ILOG2_U32 bool diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 5ad92419be19..84b184e016cd 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -268,9 +268,6 @@ config ARCH_MAY_HAVE_PC_FDC def_bool y depends on ISA_DMA_API -config RWSEM_XCHGADD_ALGORITHM - def_bool y - config GENERIC_CALIBRATE_DELAY def_bool y diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig index a9e80e44178c..a8985e1f7432 100644 --- a/arch/x86/um/Kconfig +++ b/arch/x86/um/Kconfig @@ -32,12 +32,6 @@ config ARCH_DEFCONFIG default "arch/um/configs/i386_defconfig" if X86_32 default "arch/um/configs/x86_64_defconfig" if X86_64 -config RWSEM_XCHGADD_ALGORITHM - def_bool 64BIT - -config RWSEM_GENERIC_SPINLOCK - def_bool !RWSEM_XCHGADD_ALGORITHM - config 3_LEVEL_PGTABLES bool "Three-level pagetables" if !64BIT default 64BIT diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index 4b9aafe766c5..35c8d91e6106 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -46,9 +46,6 @@ config XTENSA with reasonable minimum requirements. The Xtensa Linux project has a home page at . -config RWSEM_XCHGADD_ALGORITHM - def_bool y - config GENERIC_HWEIGHT def_bool y diff --git a/include/linux/rwsem-spinlock.h b/include/linux/rwsem-spinlock.h deleted file mode 100644 index e47568363e5e..000000000000 --- a/include/linux/rwsem-spinlock.h +++ /dev/null @@ -1,47 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* rwsem-spinlock.h: fallback C implementation - * - * Copyright (c) 2001 David Howells (dhowells@redhat.com). - * - Derived partially from ideas by Andrea Arcangeli - * - Derived also from comments by Linus - */ - -#ifndef _LINUX_RWSEM_SPINLOCK_H -#define _LINUX_RWSEM_SPINLOCK_H - -#ifndef _LINUX_RWSEM_H -#error "please don't include linux/rwsem-spinlock.h directly, use linux/rwsem.h instead" -#endif - -#ifdef __KERNEL__ -/* - * the rw-semaphore definition - * - if count is 0 then there are no active readers or writers - * - if count is +ve then that is the number of active readers - * - if count is -1 then there is one active writer - * - if wait_list is not empty, then there are processes waiting for the semaphore - */ -struct rw_semaphore { - __s32 count; - raw_spinlock_t wait_lock; - struct list_head wait_list; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map dep_map; -#endif -}; - -#define RWSEM_UNLOCKED_VALUE 0x00000000 - -extern void __down_read(struct rw_semaphore *sem); -extern int __must_check __down_read_killable(struct rw_semaphore *sem); -extern int __down_read_trylock(struct rw_semaphore *sem); -extern void __down_write(struct rw_semaphore *sem); -extern int __must_check __down_write_killable(struct rw_semaphore *sem); -extern int __down_write_trylock(struct rw_semaphore *sem); -extern void __up_read(struct rw_semaphore *sem); -extern void __up_write(struct rw_semaphore *sem); -extern void __downgrade_write(struct rw_semaphore *sem); -extern int rwsem_is_locked(struct rw_semaphore *sem); - -#endif /* __KERNEL__ */ -#endif /* _LINUX_RWSEM_SPINLOCK_H */ diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 6e56006b2cb6..0fc41062c649 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -22,10 +22,6 @@ struct rw_semaphore; -#ifdef CONFIG_RWSEM_GENERIC_SPINLOCK -#include /* use a generic implementation */ -#define __RWSEM_INIT_COUNT(name) .count = RWSEM_UNLOCKED_VALUE -#else /* All arch specific implementations share the same struct */ struct rw_semaphore { atomic_long_t count; @@ -65,7 +61,6 @@ static inline int rwsem_is_locked(struct rw_semaphore *sem) #define RWSEM_UNLOCKED_VALUE 0L #define __RWSEM_INIT_COUNT(name) .count = ATOMIC_LONG_INIT(RWSEM_UNLOCKED_VALUE) -#endif /* Common initializer macros and functions */ diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks index fbba478ae522..e335953fa704 100644 --- a/kernel/Kconfig.locks +++ b/kernel/Kconfig.locks @@ -229,7 +229,7 @@ config MUTEX_SPIN_ON_OWNER config RWSEM_SPIN_ON_OWNER def_bool y - depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW + depends on SMP && ARCH_SUPPORTS_ATOMIC_RMW config LOCK_SPIN_ON_OWNER def_bool y diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile index 392c7f23af76..1af83e9ce57d 100644 --- a/kernel/locking/Makefile +++ b/kernel/locking/Makefile @@ -3,7 +3,7 @@ # and is generally not a function of system call inputs. KCOV_INSTRUMENT := n -obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o +obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o rwsem-xadd.o ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE) @@ -25,8 +25,6 @@ obj-$(CONFIG_RT_MUTEXES) += rtmutex.o obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o -obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o -obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o obj-$(CONFIG_WW_MUTEX_SELFTEST) += test-ww_mutex.o diff --git a/kernel/locking/rwsem-spinlock.c b/kernel/locking/rwsem-spinlock.c deleted file mode 100644 index a7ffb2a96ede..000000000000 --- a/kernel/locking/rwsem-spinlock.c +++ /dev/null @@ -1,339 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* rwsem-spinlock.c: R/W semaphores: contention handling functions for - * generic spinlock implementation - * - * Copyright (c) 2001 David Howells (dhowells@redhat.com). - * - Derived partially from idea by Andrea Arcangeli - * - Derived also from comments by Linus - */ -#include -#include -#include -#include - -enum rwsem_waiter_type { - RWSEM_WAITING_FOR_WRITE, - RWSEM_WAITING_FOR_READ -}; - -struct rwsem_waiter { - struct list_head list; - struct task_struct *task; - enum rwsem_waiter_type type; -}; - -int rwsem_is_locked(struct rw_semaphore *sem) -{ - int ret = 1; - unsigned long flags; - - if (raw_spin_trylock_irqsave(&sem->wait_lock, flags)) { - ret = (sem->count != 0); - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); - } - return ret; -} -EXPORT_SYMBOL(rwsem_is_locked); - -/* - * initialise the semaphore - */ -void __init_rwsem(struct rw_semaphore *sem, const char *name, - struct lock_class_key *key) -{ -#ifdef CONFIG_DEBUG_LOCK_ALLOC - /* - * Make sure we are not reinitializing a held semaphore: - */ - debug_check_no_locks_freed((void *)sem, sizeof(*sem)); - lockdep_init_map(&sem->dep_map, name, key, 0); -#endif - sem->count = 0; - raw_spin_lock_init(&sem->wait_lock); - INIT_LIST_HEAD(&sem->wait_list); -} -EXPORT_SYMBOL(__init_rwsem); - -/* - * handle the lock release when processes blocked on it that can now run - * - if we come here, then: - * - the 'active count' _reached_ zero - * - the 'waiting count' is non-zero - * - the spinlock must be held by the caller - * - woken process blocks are discarded from the list after having task zeroed - * - writers are only woken if wakewrite is non-zero - */ -static inline struct rw_semaphore * -__rwsem_do_wake(struct rw_semaphore *sem, int wakewrite) -{ - struct rwsem_waiter *waiter; - struct task_struct *tsk; - int woken; - - waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list); - - if (waiter->type == RWSEM_WAITING_FOR_WRITE) { - if (wakewrite) - /* Wake up a writer. Note that we do not grant it the - * lock - it will have to acquire it when it runs. */ - wake_up_process(waiter->task); - goto out; - } - - /* grant an infinite number of read locks to the front of the queue */ - woken = 0; - do { - struct list_head *next = waiter->list.next; - - list_del(&waiter->list); - tsk = waiter->task; - /* - * Make sure we do not wakeup the next reader before - * setting the nil condition to grant the next reader; - * otherwise we could miss the wakeup on the other - * side and end up sleeping again. See the pairing - * in rwsem_down_read_failed(). - */ - smp_mb(); - waiter->task = NULL; - wake_up_process(tsk); - put_task_struct(tsk); - woken++; - if (next == &sem->wait_list) - break; - waiter = list_entry(next, struct rwsem_waiter, list); - } while (waiter->type != RWSEM_WAITING_FOR_WRITE); - - sem->count += woken; - - out: - return sem; -} - -/* - * wake a single writer - */ -static inline struct rw_semaphore * -__rwsem_wake_one_writer(struct rw_semaphore *sem) -{ - struct rwsem_waiter *waiter; - - waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list); - wake_up_process(waiter->task); - - return sem; -} - -/* - * get a read lock on the semaphore - */ -int __sched __down_read_common(struct rw_semaphore *sem, int state) -{ - struct rwsem_waiter waiter; - unsigned long flags; - - raw_spin_lock_irqsave(&sem->wait_lock, flags); - - if (sem->count >= 0 && list_empty(&sem->wait_list)) { - /* granted */ - sem->count++; - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); - goto out; - } - - /* set up my own style of waitqueue */ - waiter.task = current; - waiter.type = RWSEM_WAITING_FOR_READ; - get_task_struct(current); - - list_add_tail(&waiter.list, &sem->wait_list); - - /* wait to be given the lock */ - for (;;) { - if (!waiter.task) - break; - if (signal_pending_state(state, current)) - goto out_nolock; - set_current_state(state); - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); - schedule(); - raw_spin_lock_irqsave(&sem->wait_lock, flags); - } - - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); - out: - return 0; - -out_nolock: - /* - * We didn't take the lock, so that there is a writer, which - * is owner or the first waiter of the sem. If it's a waiter, - * it will be woken by current owner. Not need to wake anybody. - */ - list_del(&waiter.list); - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); - return -EINTR; -} - -void __sched __down_read(struct rw_semaphore *sem) -{ - __down_read_common(sem, TASK_UNINTERRUPTIBLE); -} - -int __sched __down_read_killable(struct rw_semaphore *sem) -{ - return __down_read_common(sem, TASK_KILLABLE); -} - -/* - * trylock for reading -- returns 1 if successful, 0 if contention - */ -int __down_read_trylock(struct rw_semaphore *sem) -{ - unsigned long flags; - int ret = 0; - - - raw_spin_lock_irqsave(&sem->wait_lock, flags); - - if (sem->count >= 0 && list_empty(&sem->wait_list)) { - /* granted */ - sem->count++; - ret = 1; - } - - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); - - return ret; -} - -/* - * get a write lock on the semaphore - */ -int __sched __down_write_common(struct rw_semaphore *sem, int state) -{ - struct rwsem_waiter waiter; - unsigned long flags; - int ret = 0; - - raw_spin_lock_irqsave(&sem->wait_lock, flags); - - /* set up my own style of waitqueue */ - waiter.task = current; - waiter.type = RWSEM_WAITING_FOR_WRITE; - list_add_tail(&waiter.list, &sem->wait_list); - - /* wait for someone to release the lock */ - for (;;) { - /* - * That is the key to support write lock stealing: allows the - * task already on CPU to get the lock soon rather than put - * itself into sleep and waiting for system woke it or someone - * else in the head of the wait list up. - */ - if (sem->count == 0) - break; - if (signal_pending_state(state, current)) - goto out_nolock; - - set_current_state(state); - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); - schedule(); - raw_spin_lock_irqsave(&sem->wait_lock, flags); - } - /* got the lock */ - sem->count = -1; - list_del(&waiter.list); - - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); - - return ret; - -out_nolock: - list_del(&waiter.list); - if (!list_empty(&sem->wait_list) && sem->count >= 0) - __rwsem_do_wake(sem, 0); - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); - - return -EINTR; -} - -void __sched __down_write(struct rw_semaphore *sem) -{ - __down_write_common(sem, TASK_UNINTERRUPTIBLE); -} - -int __sched __down_write_killable(struct rw_semaphore *sem) -{ - return __down_write_common(sem, TASK_KILLABLE); -} - -/* - * trylock for writing -- returns 1 if successful, 0 if contention - */ -int __down_write_trylock(struct rw_semaphore *sem) -{ - unsigned long flags; - int ret = 0; - - raw_spin_lock_irqsave(&sem->wait_lock, flags); - - if (sem->count == 0) { - /* got the lock */ - sem->count = -1; - ret = 1; - } - - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); - - return ret; -} - -/* - * release a read lock on the semaphore - */ -void __up_read(struct rw_semaphore *sem) -{ - unsigned long flags; - - raw_spin_lock_irqsave(&sem->wait_lock, flags); - - if (--sem->count == 0 && !list_empty(&sem->wait_list)) - sem = __rwsem_wake_one_writer(sem); - - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); -} - -/* - * release a write lock on the semaphore - */ -void __up_write(struct rw_semaphore *sem) -{ - unsigned long flags; - - raw_spin_lock_irqsave(&sem->wait_lock, flags); - - sem->count = 0; - if (!list_empty(&sem->wait_list)) - sem = __rwsem_do_wake(sem, 1); - - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); -} - -/* - * downgrade a write lock into a read lock - * - just wake up any readers at the front of the queue - */ -void __downgrade_write(struct rw_semaphore *sem) -{ - unsigned long flags; - - raw_spin_lock_irqsave(&sem->wait_lock, flags); - - sem->count = 1; - if (!list_empty(&sem->wait_list)) - sem = __rwsem_do_wake(sem, 0); - - raw_spin_unlock_irqrestore(&sem->wait_lock, flags); -} - diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h index 067e265fa5c1..45ee00236e03 100644 --- a/kernel/locking/rwsem.h +++ b/kernel/locking/rwsem.h @@ -153,7 +153,6 @@ static inline void rwsem_clear_reader_owned(struct rw_semaphore *sem) } #endif -#ifdef CONFIG_RWSEM_XCHGADD_ALGORITHM /* * lock for reading */ @@ -260,5 +259,3 @@ static inline void __downgrade_write(struct rw_semaphore *sem) if (tmp < 0) rwsem_downgrade_wake(sem); } - -#endif /* CONFIG_RWSEM_XCHGADD_ALGORITHM */ -- cgit From 24e516049360eda85cf3fe9903221d43886c2689 Mon Sep 17 00:00:00 2001 From: Neil Leeder Date: Tue, 26 Mar 2019 15:17:50 +0000 Subject: ACPI/IORT: Add support for PMCG Add support for the SMMU Performance Monitor Counter Group information from ACPI. This is in preparation for its use in the SMMUv3 PMU driver. Signed-off-by: Neil Leeder Signed-off-by: Hanjun Guo Signed-off-by: Shameer Kolothum Reviewed-by: Robin Murphy Acked-by: Lorenzo Pieralisi Signed-off-by: Will Deacon --- drivers/acpi/arm64/iort.c | 117 ++++++++++++++++++++++++++++++++++++---------- include/linux/acpi_iort.h | 7 +++ 2 files changed, 100 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index e48894e002ba..e2c9b26bbee6 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -356,7 +356,8 @@ static struct acpi_iort_node *iort_node_get_id(struct acpi_iort_node *node, if (map->flags & ACPI_IORT_ID_SINGLE_MAPPING) { if (node->type == ACPI_IORT_NODE_NAMED_COMPONENT || node->type == ACPI_IORT_NODE_PCI_ROOT_COMPLEX || - node->type == ACPI_IORT_NODE_SMMU_V3) { + node->type == ACPI_IORT_NODE_SMMU_V3 || + node->type == ACPI_IORT_NODE_PMCG) { *id_out = map->output_base; return parent; } @@ -394,6 +395,8 @@ static int iort_get_id_mapping_index(struct acpi_iort_node *node) } return smmu->id_mapping_index; + case ACPI_IORT_NODE_PMCG: + return 0; default: return -EINVAL; } @@ -1218,14 +1221,23 @@ static void __init arm_smmu_v3_init_resources(struct resource *res, } } -static bool __init arm_smmu_v3_is_coherent(struct acpi_iort_node *node) +static void __init arm_smmu_v3_dma_configure(struct device *dev, + struct acpi_iort_node *node) { struct acpi_iort_smmu_v3 *smmu; + enum dev_dma_attr attr; /* Retrieve SMMUv3 specific data */ smmu = (struct acpi_iort_smmu_v3 *)node->node_data; - return smmu->flags & ACPI_IORT_SMMU_V3_COHACC_OVERRIDE; + attr = (smmu->flags & ACPI_IORT_SMMU_V3_COHACC_OVERRIDE) ? + DEV_DMA_COHERENT : DEV_DMA_NON_COHERENT; + + /* We expect the dma masks to be equivalent for all SMMUv3 set-ups */ + dev->dma_mask = &dev->coherent_dma_mask; + + /* Configure DMA for the page table walker */ + acpi_dma_configure(dev, attr); } #if defined(CONFIG_ACPI_NUMA) @@ -1301,30 +1313,82 @@ static void __init arm_smmu_init_resources(struct resource *res, } } -static bool __init arm_smmu_is_coherent(struct acpi_iort_node *node) +static void __init arm_smmu_dma_configure(struct device *dev, + struct acpi_iort_node *node) { struct acpi_iort_smmu *smmu; + enum dev_dma_attr attr; /* Retrieve SMMU specific data */ smmu = (struct acpi_iort_smmu *)node->node_data; - return smmu->flags & ACPI_IORT_SMMU_COHERENT_WALK; + attr = (smmu->flags & ACPI_IORT_SMMU_COHERENT_WALK) ? + DEV_DMA_COHERENT : DEV_DMA_NON_COHERENT; + + /* We expect the dma masks to be equivalent for SMMU set-ups */ + dev->dma_mask = &dev->coherent_dma_mask; + + /* Configure DMA for the page table walker */ + acpi_dma_configure(dev, attr); +} + +static int __init arm_smmu_v3_pmcg_count_resources(struct acpi_iort_node *node) +{ + struct acpi_iort_pmcg *pmcg; + + /* Retrieve PMCG specific data */ + pmcg = (struct acpi_iort_pmcg *)node->node_data; + + /* + * There are always 2 memory resources. + * If the overflow_gsiv is present then add that for a total of 3. + */ + return pmcg->overflow_gsiv ? 3 : 2; +} + +static void __init arm_smmu_v3_pmcg_init_resources(struct resource *res, + struct acpi_iort_node *node) +{ + struct acpi_iort_pmcg *pmcg; + + /* Retrieve PMCG specific data */ + pmcg = (struct acpi_iort_pmcg *)node->node_data; + + res[0].start = pmcg->page0_base_address; + res[0].end = pmcg->page0_base_address + SZ_4K - 1; + res[0].flags = IORESOURCE_MEM; + res[1].start = pmcg->page1_base_address; + res[1].end = pmcg->page1_base_address + SZ_4K - 1; + res[1].flags = IORESOURCE_MEM; + + if (pmcg->overflow_gsiv) + acpi_iort_register_irq(pmcg->overflow_gsiv, "overflow", + ACPI_EDGE_SENSITIVE, &res[2]); +} + +static int __init arm_smmu_v3_pmcg_add_platdata(struct platform_device *pdev) +{ + u32 model = IORT_SMMU_V3_PMCG_GENERIC; + + return platform_device_add_data(pdev, &model, sizeof(model)); } struct iort_dev_config { const char *name; int (*dev_init)(struct acpi_iort_node *node); - bool (*dev_is_coherent)(struct acpi_iort_node *node); + void (*dev_dma_configure)(struct device *dev, + struct acpi_iort_node *node); int (*dev_count_resources)(struct acpi_iort_node *node); void (*dev_init_resources)(struct resource *res, struct acpi_iort_node *node); void (*dev_set_proximity)(struct device *dev, struct acpi_iort_node *node); + int (*dev_add_platdata)(struct platform_device *pdev); }; static const struct iort_dev_config iort_arm_smmu_v3_cfg __initconst = { .name = "arm-smmu-v3", - .dev_is_coherent = arm_smmu_v3_is_coherent, + .dev_dma_configure = arm_smmu_v3_dma_configure, .dev_count_resources = arm_smmu_v3_count_resources, .dev_init_resources = arm_smmu_v3_init_resources, .dev_set_proximity = arm_smmu_v3_set_proximity, @@ -1332,9 +1396,16 @@ static const struct iort_dev_config iort_arm_smmu_v3_cfg __initconst = { static const struct iort_dev_config iort_arm_smmu_cfg __initconst = { .name = "arm-smmu", - .dev_is_coherent = arm_smmu_is_coherent, + .dev_dma_configure = arm_smmu_dma_configure, .dev_count_resources = arm_smmu_count_resources, - .dev_init_resources = arm_smmu_init_resources + .dev_init_resources = arm_smmu_init_resources, +}; + +static const struct iort_dev_config iort_arm_smmu_v3_pmcg_cfg __initconst = { + .name = "arm-smmu-v3-pmcg", + .dev_count_resources = arm_smmu_v3_pmcg_count_resources, + .dev_init_resources = arm_smmu_v3_pmcg_init_resources, + .dev_add_platdata = arm_smmu_v3_pmcg_add_platdata, }; static __init const struct iort_dev_config *iort_get_dev_cfg( @@ -1345,6 +1416,8 @@ static __init const struct iort_dev_config *iort_get_dev_cfg( return &iort_arm_smmu_v3_cfg; case ACPI_IORT_NODE_SMMU: return &iort_arm_smmu_cfg; + case ACPI_IORT_NODE_PMCG: + return &iort_arm_smmu_v3_pmcg_cfg; default: return NULL; } @@ -1362,7 +1435,6 @@ static int __init iort_add_platform_device(struct acpi_iort_node *node, struct fwnode_handle *fwnode; struct platform_device *pdev; struct resource *r; - enum dev_dma_attr attr; int ret, count; pdev = platform_device_alloc(ops->name, PLATFORM_DEVID_AUTO); @@ -1393,19 +1465,19 @@ static int __init iort_add_platform_device(struct acpi_iort_node *node, goto dev_put; /* - * Add a copy of IORT node pointer to platform_data to - * be used to retrieve IORT data information. + * Platform devices based on PMCG nodes uses platform_data to + * pass the hardware model info to the driver. For others, add + * a copy of IORT node pointer to platform_data to be used to + * retrieve IORT data information. */ - ret = platform_device_add_data(pdev, &node, sizeof(node)); + if (ops->dev_add_platdata) + ret = ops->dev_add_platdata(pdev); + else + ret = platform_device_add_data(pdev, &node, sizeof(node)); + if (ret) goto dev_put; - /* - * We expect the dma masks to be equivalent for - * all SMMUs set-ups - */ - pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask; - fwnode = iort_get_fwnode(node); if (!fwnode) { @@ -1415,11 +1487,8 @@ static int __init iort_add_platform_device(struct acpi_iort_node *node, pdev->dev.fwnode = fwnode; - attr = ops->dev_is_coherent && ops->dev_is_coherent(node) ? - DEV_DMA_COHERENT : DEV_DMA_NON_COHERENT; - - /* Configure DMA for the page table walker */ - acpi_dma_configure(&pdev->dev, attr); + if (ops->dev_dma_configure) + ops->dev_dma_configure(&pdev->dev, node); iort_set_device_domain(&pdev->dev, node); diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index 38cd77b39a64..052ef7b9f985 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -26,6 +26,13 @@ #define IORT_IRQ_MASK(irq) (irq & 0xffffffffULL) #define IORT_IRQ_TRIGGER_MASK(irq) ((irq >> 32) & 0xffffffffULL) +/* + * PMCG model identifiers for use in smmu pmu driver. Please note + * that this is purely for the use of software and has nothing to + * do with hardware or with IORT specification. + */ +#define IORT_SMMU_V3_PMCG_GENERIC 0x00000000 /* Generic SMMUv3 PMCG */ + int iort_register_domain_token(int trans_id, phys_addr_t base, struct fwnode_handle *fw_node); void iort_deregister_domain_token(int trans_id); -- cgit From 631b7abacd02b88f4b0795c08b54ad4fc3e7c7c0 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Mon, 7 Nov 2016 16:26:35 -0500 Subject: ptrace: Remove maxargs from task_current_syscall() task_current_syscall() has a single user that passes in 6 for maxargs, which is the maximum arguments that can be used to get system calls from syscall_get_arguments(). Instead of passing in a number of arguments to grab, just get 6 arguments. The args argument even specifies that it's an array of 6 items. This will also allow changing syscall_get_arguments() to not get a variable number of arguments, but always grab 6. Linus also suggested not passing in a bunch of arguments to task_current_syscall() but to instead pass in a pointer to a structure, and just fill the structure. struct seccomp_data has almost all the parameters that is needed except for the stack pointer (sp). As seccomp_data is part of uapi, and I'm afraid to change it, a new structure was created "syscall_info", which includes seccomp_data and adds the "sp" field. Link: http://lkml.kernel.org/r/20161107213233.466776454@goodmis.org Cc: Andy Lutomirski Cc: Alexey Dobriyan Cc: Oleg Nesterov Cc: Kees Cook Cc: Al Viro Cc: linux-fsdevel@vger.kernel.org Reviewed-by: Thomas Gleixner Signed-off-by: Steven Rostedt (VMware) --- fs/proc/base.c | 17 ++++++++------- include/linux/ptrace.h | 11 +++++++--- lib/syscall.c | 57 ++++++++++++++++++++++---------------------------- 3 files changed, 42 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/base.c b/fs/proc/base.c index ddef482f1334..6a803a0b75df 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -616,24 +616,25 @@ static int proc_pid_limits(struct seq_file *m, struct pid_namespace *ns, static int proc_pid_syscall(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { - long nr; - unsigned long args[6], sp, pc; + struct syscall_info info; + u64 *args = &info.data.args[0]; int res; res = lock_trace(task); if (res) return res; - if (task_current_syscall(task, &nr, args, 6, &sp, &pc)) + if (task_current_syscall(task, &info)) seq_puts(m, "running\n"); - else if (nr < 0) - seq_printf(m, "%ld 0x%lx 0x%lx\n", nr, sp, pc); + else if (info.data.nr < 0) + seq_printf(m, "%d 0x%llx 0x%llx\n", + info.data.nr, info.sp, info.data.instruction_pointer); else seq_printf(m, - "%ld 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx\n", - nr, + "%d 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx 0x%llx\n", + info.data.nr, args[0], args[1], args[2], args[3], args[4], args[5], - sp, pc); + info.sp, info.data.instruction_pointer); unlock_trace(task); return 0; diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index edb9b040c94c..d5084ebd9f03 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -9,6 +9,13 @@ #include /* For BUG_ON. */ #include /* For task_active_pid_ns. */ #include +#include + +/* Add sp to seccomp_data, as seccomp is user API, we don't want to modify it */ +struct syscall_info { + __u64 sp; + struct seccomp_data data; +}; extern int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, unsigned int gup_flags); @@ -407,9 +414,7 @@ static inline void user_single_step_report(struct pt_regs *regs) #define current_user_stack_pointer() user_stack_pointer(current_pt_regs()) #endif -extern int task_current_syscall(struct task_struct *target, long *callno, - unsigned long args[6], unsigned int maxargs, - unsigned long *sp, unsigned long *pc); +extern int task_current_syscall(struct task_struct *target, struct syscall_info *info); extern void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact); #endif diff --git a/lib/syscall.c b/lib/syscall.c index 1a7077f20eae..e8467e17b9a2 100644 --- a/lib/syscall.c +++ b/lib/syscall.c @@ -5,16 +5,14 @@ #include #include -static int collect_syscall(struct task_struct *target, long *callno, - unsigned long args[6], unsigned int maxargs, - unsigned long *sp, unsigned long *pc) +static int collect_syscall(struct task_struct *target, struct syscall_info *info) { struct pt_regs *regs; if (!try_get_task_stack(target)) { /* Task has no stack, so the task isn't in a syscall. */ - *sp = *pc = 0; - *callno = -1; + memset(info, 0, sizeof(*info)); + info->data.nr = -1; return 0; } @@ -24,12 +22,13 @@ static int collect_syscall(struct task_struct *target, long *callno, return -EAGAIN; } - *sp = user_stack_pointer(regs); - *pc = instruction_pointer(regs); + info->sp = user_stack_pointer(regs); + info->data.instruction_pointer = instruction_pointer(regs); - *callno = syscall_get_nr(target, regs); - if (*callno != -1L && maxargs > 0) - syscall_get_arguments(target, regs, 0, maxargs, args); + info->data.nr = syscall_get_nr(target, regs); + if (info->data.nr != -1L) + syscall_get_arguments(target, regs, 0, 6, + (unsigned long *)&info->data.args[0]); put_task_stack(target); return 0; @@ -38,41 +37,35 @@ static int collect_syscall(struct task_struct *target, long *callno, /** * task_current_syscall - Discover what a blocked task is doing. * @target: thread to examine - * @callno: filled with system call number or -1 - * @args: filled with @maxargs system call arguments - * @maxargs: number of elements in @args to fill - * @sp: filled with user stack pointer - * @pc: filled with user PC + * @info: structure with the following fields: + * .sp - filled with user stack pointer + * .data.nr - filled with system call number or -1 + * .data.args - filled with @maxargs system call arguments + * .data.instruction_pointer - filled with user PC * - * If @target is blocked in a system call, returns zero with *@callno - * set to the the call's number and @args filled in with its arguments. - * Registers not used for system call arguments may not be available and - * it is not kosher to use &struct user_regset calls while the system + * If @target is blocked in a system call, returns zero with @info.data.nr + * set to the the call's number and @info.data.args filled in with its + * arguments. Registers not used for system call arguments may not be available + * and it is not kosher to use &struct user_regset calls while the system * call is still in progress. Note we may get this result if @target * has finished its system call but not yet returned to user mode, such * as when it's stopped for signal handling or syscall exit tracing. * * If @target is blocked in the kernel during a fault or exception, - * returns zero with *@callno set to -1 and does not fill in @args. - * If so, it's now safe to examine @target using &struct user_regset - * get() calls as long as we're sure @target won't return to user mode. + * returns zero with *@info.data.nr set to -1 and does not fill in + * @info.data.args. If so, it's now safe to examine @target using + * &struct user_regset get() calls as long as we're sure @target won't return + * to user mode. * * Returns -%EAGAIN if @target does not remain blocked. - * - * Returns -%EINVAL if @maxargs is too large (maximum is six). */ -int task_current_syscall(struct task_struct *target, long *callno, - unsigned long args[6], unsigned int maxargs, - unsigned long *sp, unsigned long *pc) +int task_current_syscall(struct task_struct *target, struct syscall_info *info) { long state; unsigned long ncsw; - if (unlikely(maxargs > 6)) - return -EINVAL; - if (target == current) - return collect_syscall(target, callno, args, maxargs, sp, pc); + return collect_syscall(target, info); state = target->state; if (unlikely(!state)) @@ -80,7 +73,7 @@ int task_current_syscall(struct task_struct *target, long *callno, ncsw = wait_task_inactive(target, state); if (unlikely(!ncsw) || - unlikely(collect_syscall(target, callno, args, maxargs, sp, pc)) || + unlikely(collect_syscall(target, info)) || unlikely(wait_task_inactive(target, state) != ncsw)) return -EAGAIN; -- cgit From 24062fe85860debfdae0eeaa495f27c9971ec163 Mon Sep 17 00:00:00 2001 From: Shameer Kolothum Date: Tue, 26 Mar 2019 15:17:53 +0000 Subject: perf/smmuv3: Enable HiSilicon Erratum 162001800 quirk HiSilicon erratum 162001800 describes the limitation of SMMUv3 PMCG implementation on HiSilicon Hip08 platforms. On these platforms, the PMCG event counter registers (SMMU_PMCG_EVCNTRn) are read only and as a result it is not possible to set the initial counter period value on event monitor start. To work around this, the current value of the counter is read and used for delta calculations. OEM information from ACPI header is used to identify the affected hardware platforms. Signed-off-by: Shameer Kolothum Reviewed-by: Hanjun Guo Reviewed-by: Robin Murphy Acked-by: Lorenzo Pieralisi [will: update silicon-errata.txt and add reason string to acpi match] Signed-off-by: Will Deacon --- Documentation/arm64/silicon-errata.txt | 1 + drivers/acpi/arm64/iort.c | 16 +++++++++++- drivers/perf/arm_smmuv3_pmu.c | 48 +++++++++++++++++++++++++++++----- include/linux/acpi_iort.h | 1 + 4 files changed, 58 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt index d1e2bb801e1b..c00efb639e46 100644 --- a/Documentation/arm64/silicon-errata.txt +++ b/Documentation/arm64/silicon-errata.txt @@ -77,6 +77,7 @@ stable kernels. | Hisilicon | Hip0{5,6,7} | #161010101 | HISILICON_ERRATUM_161010101 | | Hisilicon | Hip0{6,7} | #161010701 | N/A | | Hisilicon | Hip07 | #161600802 | HISILICON_ERRATUM_161600802 | +| Hisilicon | Hip08 SMMU PMCG | #162001800 | N/A | | | | | | | Qualcomm Tech. | Kryo/Falkor v1 | E1003 | QCOM_FALKOR_ERRATUM_1003 | | Qualcomm Tech. | Falkor v1 | E1009 | QCOM_FALKOR_ERRATUM_1009 | diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index e2c9b26bbee6..2d70b349bd6c 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -1366,9 +1366,23 @@ static void __init arm_smmu_v3_pmcg_init_resources(struct resource *res, ACPI_EDGE_SENSITIVE, &res[2]); } +static struct acpi_platform_list pmcg_plat_info[] __initdata = { + /* HiSilicon Hip08 Platform */ + {"HISI ", "HIP08 ", 0, ACPI_SIG_IORT, greater_than_or_equal, + "Erratum #162001800", IORT_SMMU_V3_PMCG_HISI_HIP08}, + { } +}; + static int __init arm_smmu_v3_pmcg_add_platdata(struct platform_device *pdev) { - u32 model = IORT_SMMU_V3_PMCG_GENERIC; + u32 model; + int idx; + + idx = acpi_match_platform_list(pmcg_plat_info); + if (idx >= 0) + model = pmcg_plat_info[idx].data; + else + model = IORT_SMMU_V3_PMCG_GENERIC; return platform_device_add_data(pdev, &model, sizeof(model)); } diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c index a4f4b488a2de..da71c741cb46 100644 --- a/drivers/perf/arm_smmuv3_pmu.c +++ b/drivers/perf/arm_smmuv3_pmu.c @@ -35,6 +35,7 @@ */ #include +#include #include #include #include @@ -93,6 +94,8 @@ #define SMMU_PMCG_PA_SHIFT 12 +#define SMMU_PMCG_EVCNTR_RDONLY BIT(0) + static int cpuhp_state_num; struct smmu_pmu { @@ -108,6 +111,7 @@ struct smmu_pmu { void __iomem *reg_base; void __iomem *reloc_base; u64 counter_mask; + u32 options; bool global_filter; u32 global_filter_span; u32 global_filter_sid; @@ -222,15 +226,27 @@ static void smmu_pmu_set_period(struct smmu_pmu *smmu_pmu, u32 idx = hwc->idx; u64 new; - /* - * We limit the max period to half the max counter value of the counter - * size, so that even in the case of extreme interrupt latency the - * counter will (hopefully) not wrap past its initial value. - */ - new = smmu_pmu->counter_mask >> 1; + if (smmu_pmu->options & SMMU_PMCG_EVCNTR_RDONLY) { + /* + * On platforms that require this quirk, if the counter starts + * at < half_counter value and wraps, the current logic of + * handling the overflow may not work. It is expected that, + * those platforms will have full 64 counter bits implemented + * so that such a possibility is remote(eg: HiSilicon HIP08). + */ + new = smmu_pmu_counter_get_value(smmu_pmu, idx); + } else { + /* + * We limit the max period to half the max counter value + * of the counter size, so that even in the case of extreme + * interrupt latency the counter will (hopefully) not wrap + * past its initial value. + */ + new = smmu_pmu->counter_mask >> 1; + smmu_pmu_counter_set_value(smmu_pmu, idx, new); + } local64_set(&hwc->prev_count, new); - smmu_pmu_counter_set_value(smmu_pmu, idx, new); } static void smmu_pmu_set_event_filter(struct perf_event *event, @@ -665,6 +681,22 @@ static void smmu_pmu_reset(struct smmu_pmu *smmu_pmu) smmu_pmu->reloc_base + SMMU_PMCG_OVSCLR0); } +static void smmu_pmu_get_acpi_options(struct smmu_pmu *smmu_pmu) +{ + u32 model; + + model = *(u32 *)dev_get_platdata(smmu_pmu->dev); + + switch (model) { + case IORT_SMMU_V3_PMCG_HISI_HIP08: + /* HiSilicon Erratum 162001800 */ + smmu_pmu->options |= SMMU_PMCG_EVCNTR_RDONLY; + break; + } + + dev_notice(smmu_pmu->dev, "option mask 0x%x\n", smmu_pmu->options); +} + static int smmu_pmu_probe(struct platform_device *pdev) { struct smmu_pmu *smmu_pmu; @@ -744,6 +776,8 @@ static int smmu_pmu_probe(struct platform_device *pdev) return -EINVAL; } + smmu_pmu_get_acpi_options(smmu_pmu); + /* Pick one CPU to be the preferred one to use */ smmu_pmu->on_cpu = raw_smp_processor_id(); WARN_ON(irq_set_affinity_hint(smmu_pmu->irq, diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h index 052ef7b9f985..723e4dfa1c14 100644 --- a/include/linux/acpi_iort.h +++ b/include/linux/acpi_iort.h @@ -32,6 +32,7 @@ * do with hardware or with IORT specification. */ #define IORT_SMMU_V3_PMCG_GENERIC 0x00000000 /* Generic SMMUv3 PMCG */ +#define IORT_SMMU_V3_PMCG_HISI_HIP08 0x00000001 /* HiSilicon HIP08 PMCG */ int iort_register_domain_token(int trans_id, phys_addr_t base, struct fwnode_handle *fw_node); -- cgit From 5f074f3e192f10c9fade898b9b3b8812e3d83342 Mon Sep 17 00:00:00 2001 From: Nick Desaulniers Date: Fri, 5 Apr 2019 18:38:45 -0700 Subject: lib/string.c: implement a basic bcmp A recent optimization in Clang (r355672) lowers comparisons of the return value of memcmp against zero to comparisons of the return value of bcmp against zero. This helps some platforms that implement bcmp more efficiently than memcmp. glibc simply aliases bcmp to memcmp, but an optimized implementation is in the works. This results in linkage failures for all targets with Clang due to the undefined symbol. For now, just implement bcmp as a tailcail to memcmp to unbreak the build. This routine can be further optimized in the future. Other ideas discussed: * A weak alias was discussed, but breaks for architectures that define their own implementations of memcmp since aliases to declarations are not permitted (only definitions). Arch-specific memcmp implementations typically declare memcmp in C headers, but implement them in assembly. * -ffreestanding also is used sporadically throughout the kernel. * -fno-builtin-bcmp doesn't work when doing LTO. Link: https://bugs.llvm.org/show_bug.cgi?id=41035 Link: https://code.woboq.org/userspace/glibc/string/memcmp.c.html#bcmp Link: https://github.com/llvm/llvm-project/commit/8e16d73346f8091461319a7dfc4ddd18eedcff13 Link: https://github.com/ClangBuiltLinux/linux/issues/416 Link: http://lkml.kernel.org/r/20190313211335.165605-1-ndesaulniers@google.com Signed-off-by: Nick Desaulniers Reported-by: Nathan Chancellor Reported-by: Adhemerval Zanella Suggested-by: Arnd Bergmann Suggested-by: James Y Knight Suggested-by: Masahiro Yamada Suggested-by: Nathan Chancellor Suggested-by: Rasmus Villemoes Acked-by: Steven Rostedt (VMware) Reviewed-by: Nathan Chancellor Tested-by: Nathan Chancellor Reviewed-by: Masahiro Yamada Reviewed-by: Andy Shevchenko Cc: David Laight Cc: Rasmus Villemoes Cc: Namhyung Kim Cc: Greg Kroah-Hartman Cc: Alexander Shishkin Cc: Dan Williams Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/string.h | 3 +++ lib/string.c | 20 ++++++++++++++++++++ 2 files changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/string.h b/include/linux/string.h index 7927b875f80c..6ab0a6fa512e 100644 --- a/include/linux/string.h +++ b/include/linux/string.h @@ -150,6 +150,9 @@ extern void * memscan(void *,int,__kernel_size_t); #ifndef __HAVE_ARCH_MEMCMP extern int memcmp(const void *,const void *,__kernel_size_t); #endif +#ifndef __HAVE_ARCH_BCMP +extern int bcmp(const void *,const void *,__kernel_size_t); +#endif #ifndef __HAVE_ARCH_MEMCHR extern void * memchr(const void *,int,__kernel_size_t); #endif diff --git a/lib/string.c b/lib/string.c index 38e4ca08e757..3ab861c1a857 100644 --- a/lib/string.c +++ b/lib/string.c @@ -866,6 +866,26 @@ __visible int memcmp(const void *cs, const void *ct, size_t count) EXPORT_SYMBOL(memcmp); #endif +#ifndef __HAVE_ARCH_BCMP +/** + * bcmp - returns 0 if and only if the buffers have identical contents. + * @a: pointer to first buffer. + * @b: pointer to second buffer. + * @len: size of buffers. + * + * The sign or magnitude of a non-zero return value has no particular + * meaning, and architectures may implement their own more efficient bcmp(). So + * while this particular implementation is a simple (tail) call to memcmp, do + * not rely on anything but whether the return value is zero or non-zero. + */ +#undef bcmp +int bcmp(const void *a, const void *b, size_t len) +{ + return memcmp(a, b, len); +} +EXPORT_SYMBOL(bcmp); +#endif + #ifndef __HAVE_ARCH_MEMSCAN /** * memscan - Find a character in an area of memory. -- cgit From 6147e136ff5071609b54f18982dea87706288e21 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Fri, 5 Apr 2019 18:38:53 -0700 Subject: include/linux/bitrev.h: fix constant bitrev clang points out with hundreds of warnings that the bitrev macros have a problem with constant input: drivers/hwmon/sht15.c:187:11: error: variable '__x' is uninitialized when used within its own initialization [-Werror,-Wuninitialized] u8 crc = bitrev8(data->val_status & 0x0F); ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ include/linux/bitrev.h:102:21: note: expanded from macro 'bitrev8' __constant_bitrev8(__x) : \ ~~~~~~~~~~~~~~~~~~~^~~~ include/linux/bitrev.h:67:11: note: expanded from macro '__constant_bitrev8' u8 __x = x; \ ~~~ ^ Both the bitrev and the __constant_bitrev macros use an internal variable named __x, which goes horribly wrong when passing one to the other. The obvious fix is to rename one of the variables, so this adds an extra '_'. It seems we got away with this because - there are only a few drivers using bitrev macros - usually there are no constant arguments to those - when they are constant, they tend to be either 0 or (unsigned)-1 (drivers/isdn/i4l/isdnhdlc.o, drivers/iio/amplifiers/ad8366.c) and give the correct result by pure chance. In fact, the only driver that I could find that gets different results with this is drivers/net/wan/slic_ds26522.c, which in turn is a driver for fairly rare hardware (adding the maintainer to Cc for testing). Link: http://lkml.kernel.org/r/20190322140503.123580-1-arnd@arndb.de Fixes: 556d2f055bf6 ("ARM: 8187/1: add CONFIG_HAVE_ARCH_BITREVERSE to support rbit instruction") Signed-off-by: Arnd Bergmann Reviewed-by: Nick Desaulniers Cc: Zhao Qiang Cc: Yalin Wang Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitrev.h | 46 +++++++++++++++++++++++----------------------- 1 file changed, 23 insertions(+), 23 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bitrev.h b/include/linux/bitrev.h index 50fb0dee23e8..d35b8ec1c485 100644 --- a/include/linux/bitrev.h +++ b/include/linux/bitrev.h @@ -34,41 +34,41 @@ static inline u32 __bitrev32(u32 x) #define __constant_bitrev32(x) \ ({ \ - u32 __x = x; \ - __x = (__x >> 16) | (__x << 16); \ - __x = ((__x & (u32)0xFF00FF00UL) >> 8) | ((__x & (u32)0x00FF00FFUL) << 8); \ - __x = ((__x & (u32)0xF0F0F0F0UL) >> 4) | ((__x & (u32)0x0F0F0F0FUL) << 4); \ - __x = ((__x & (u32)0xCCCCCCCCUL) >> 2) | ((__x & (u32)0x33333333UL) << 2); \ - __x = ((__x & (u32)0xAAAAAAAAUL) >> 1) | ((__x & (u32)0x55555555UL) << 1); \ - __x; \ + u32 ___x = x; \ + ___x = (___x >> 16) | (___x << 16); \ + ___x = ((___x & (u32)0xFF00FF00UL) >> 8) | ((___x & (u32)0x00FF00FFUL) << 8); \ + ___x = ((___x & (u32)0xF0F0F0F0UL) >> 4) | ((___x & (u32)0x0F0F0F0FUL) << 4); \ + ___x = ((___x & (u32)0xCCCCCCCCUL) >> 2) | ((___x & (u32)0x33333333UL) << 2); \ + ___x = ((___x & (u32)0xAAAAAAAAUL) >> 1) | ((___x & (u32)0x55555555UL) << 1); \ + ___x; \ }) #define __constant_bitrev16(x) \ ({ \ - u16 __x = x; \ - __x = (__x >> 8) | (__x << 8); \ - __x = ((__x & (u16)0xF0F0U) >> 4) | ((__x & (u16)0x0F0FU) << 4); \ - __x = ((__x & (u16)0xCCCCU) >> 2) | ((__x & (u16)0x3333U) << 2); \ - __x = ((__x & (u16)0xAAAAU) >> 1) | ((__x & (u16)0x5555U) << 1); \ - __x; \ + u16 ___x = x; \ + ___x = (___x >> 8) | (___x << 8); \ + ___x = ((___x & (u16)0xF0F0U) >> 4) | ((___x & (u16)0x0F0FU) << 4); \ + ___x = ((___x & (u16)0xCCCCU) >> 2) | ((___x & (u16)0x3333U) << 2); \ + ___x = ((___x & (u16)0xAAAAU) >> 1) | ((___x & (u16)0x5555U) << 1); \ + ___x; \ }) #define __constant_bitrev8x4(x) \ ({ \ - u32 __x = x; \ - __x = ((__x & (u32)0xF0F0F0F0UL) >> 4) | ((__x & (u32)0x0F0F0F0FUL) << 4); \ - __x = ((__x & (u32)0xCCCCCCCCUL) >> 2) | ((__x & (u32)0x33333333UL) << 2); \ - __x = ((__x & (u32)0xAAAAAAAAUL) >> 1) | ((__x & (u32)0x55555555UL) << 1); \ - __x; \ + u32 ___x = x; \ + ___x = ((___x & (u32)0xF0F0F0F0UL) >> 4) | ((___x & (u32)0x0F0F0F0FUL) << 4); \ + ___x = ((___x & (u32)0xCCCCCCCCUL) >> 2) | ((___x & (u32)0x33333333UL) << 2); \ + ___x = ((___x & (u32)0xAAAAAAAAUL) >> 1) | ((___x & (u32)0x55555555UL) << 1); \ + ___x; \ }) #define __constant_bitrev8(x) \ ({ \ - u8 __x = x; \ - __x = (__x >> 4) | (__x << 4); \ - __x = ((__x & (u8)0xCCU) >> 2) | ((__x & (u8)0x33U) << 2); \ - __x = ((__x & (u8)0xAAU) >> 1) | ((__x & (u8)0x55U) << 1); \ - __x; \ + u8 ___x = x; \ + ___x = (___x >> 4) | (___x << 4); \ + ___x = ((___x & (u8)0xCCU) >> 2) | ((___x & (u8)0x33U) << 2); \ + ___x = ((___x & (u8)0xAAU) >> 1) | ((___x & (u8)0x55U) << 1); \ + ___x; \ }) #define bitrev32(x) \ -- cgit From fcae96ff96538f66e7acd5d4e0f2e7516ff8cbd0 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Fri, 5 Apr 2019 18:39:01 -0700 Subject: mm: fix vm_fault_t cast in VM_FAULT_GET_HINDEX() Symmetrically to VM_FAULT_SET_HINDEX(), we need a force-cast in VM_FAULT_GET_HINDEX() to tell sparse that this is intentional. Sparse complains about the current code when building a kernel with CONFIG_MEMORY_FAILURE: arch/x86/mm/fault.c:1058:53: warning: restricted vm_fault_t degrades to integer Link: http://lkml.kernel.org/r/20190327204117.35215-1-jannh@google.com Fixes: 3d3539018d2c ("mm: create the new vm_fault_t type") Signed-off-by: Jann Horn Reviewed-by: Andrew Morton Cc: Souptick Joarder Cc: Matthew Wilcox Cc: Vlastimil Babka Cc: "Kirill A. Shutemov" Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 7eade9132f02..4ef4bbe78a1d 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -671,7 +671,7 @@ enum vm_fault_reason { /* Encode hstate index for a hwpoisoned large page */ #define VM_FAULT_SET_HINDEX(x) ((__force vm_fault_t)((x) << 16)) -#define VM_FAULT_GET_HINDEX(x) (((x) >> 16) & 0xf) +#define VM_FAULT_GET_HINDEX(x) (((__force unsigned int)(x) >> 16) & 0xf) #define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | \ VM_FAULT_SIGSEGV | VM_FAULT_HWPOISON | \ -- cgit From 0b3d6e6f2dd0a7b697b1aa8c167265908940624b Mon Sep 17 00:00:00 2001 From: Greg Thelen Date: Fri, 5 Apr 2019 18:39:18 -0700 Subject: mm: writeback: use exact memcg dirty counts Since commit a983b5ebee57 ("mm: memcontrol: fix excessive complexity in memory.stat reporting") memcg dirty and writeback counters are managed as: 1) per-memcg per-cpu values in range of [-32..32] 2) per-memcg atomic counter When a per-cpu counter cannot fit in [-32..32] it's flushed to the atomic. Stat readers only check the atomic. Thus readers such as balance_dirty_pages() may see a nontrivial error margin: 32 pages per cpu. Assuming 100 cpus: 4k x86 page_size: 13 MiB error per memcg 64k ppc page_size: 200 MiB error per memcg Considering that dirty+writeback are used together for some decisions the errors double. This inaccuracy can lead to undeserved oom kills. One nasty case is when all per-cpu counters hold positive values offsetting an atomic negative value (i.e. per_cpu[*]=32, atomic=n_cpu*-32). balance_dirty_pages() only consults the atomic and does not consider throttling the next n_cpu*32 dirty pages. If the file_lru is in the 13..200 MiB range then there's absolutely no dirty throttling, which burdens vmscan with only dirty+writeback pages thus resorting to oom kill. It could be argued that tiny containers are not supported, but it's more subtle. It's the amount the space available for file lru that matters. If a container has memory.max-200MiB of non reclaimable memory, then it will also suffer such oom kills on a 100 cpu machine. The following test reliably ooms without this patch. This patch avoids oom kills. $ cat test mount -t cgroup2 none /dev/cgroup cd /dev/cgroup echo +io +memory > cgroup.subtree_control mkdir test cd test echo 10M > memory.max (echo $BASHPID > cgroup.procs && exec /memcg-writeback-stress /foo) (echo $BASHPID > cgroup.procs && exec dd if=/dev/zero of=/foo bs=2M count=100) $ cat memcg-writeback-stress.c /* * Dirty pages from all but one cpu. * Clean pages from the non dirtying cpu. * This is to stress per cpu counter imbalance. * On a 100 cpu machine: * - per memcg per cpu dirty count is 32 pages for each of 99 cpus * - per memcg atomic is -99*32 pages * - thus the complete dirty limit: sum of all counters 0 * - balance_dirty_pages() only sees atomic count -99*32 pages, which * it max()s to 0. * - So a workload can dirty -99*32 pages before balance_dirty_pages() * cares. */ #define _GNU_SOURCE #include #include #include #include #include #include #include #include #include static char *buf; static int bufSize; static void set_affinity(int cpu) { cpu_set_t affinity; CPU_ZERO(&affinity); CPU_SET(cpu, &affinity); if (sched_setaffinity(0, sizeof(affinity), &affinity)) err(1, "sched_setaffinity"); } static void dirty_on(int output_fd, int cpu) { int i, wrote; set_affinity(cpu); for (i = 0; i < 32; i++) { for (wrote = 0; wrote < bufSize; ) { int ret = write(output_fd, buf+wrote, bufSize-wrote); if (ret == -1) err(1, "write"); wrote += ret; } } } int main(int argc, char **argv) { int cpu, flush_cpu = 1, output_fd; const char *output; if (argc != 2) errx(1, "usage: output_file"); output = argv[1]; bufSize = getpagesize(); buf = malloc(getpagesize()); if (buf == NULL) errx(1, "malloc failed"); output_fd = open(output, O_CREAT|O_RDWR); if (output_fd == -1) err(1, "open(%s)", output); for (cpu = 0; cpu < get_nprocs(); cpu++) { if (cpu != flush_cpu) dirty_on(output_fd, cpu); } set_affinity(flush_cpu); if (fsync(output_fd)) err(1, "fsync(%s)", output); if (close(output_fd)) err(1, "close(%s)", output); free(buf); } Make balance_dirty_pages() and wb_over_bg_thresh() work harder to collect exact per memcg counters. This avoids the aforementioned oom kills. This does not affect the overhead of memory.stat, which still reads the single atomic counter. Why not use percpu_counter? memcg already handles cpus going offline, so no need for that overhead from percpu_counter. And the percpu_counter spinlocks are more heavyweight than is required. It probably also makes sense to use exact dirty and writeback counters in memcg oom reports. But that is saved for later. Link: http://lkml.kernel.org/r/20190329174609.164344-1-gthelen@google.com Signed-off-by: Greg Thelen Reviewed-by: Roman Gushchin Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Vladimir Davydov Cc: Tejun Heo Cc: [4.16+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 ++++- mm/memcontrol.c | 20 ++++++++++++++++++-- 2 files changed, 22 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 1f3d880b7ca1..dbb6118370c1 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -566,7 +566,10 @@ struct mem_cgroup *lock_page_memcg(struct page *page); void __unlock_page_memcg(struct mem_cgroup *memcg); void unlock_page_memcg(struct page *page); -/* idx can be of type enum memcg_stat_item or node_stat_item */ +/* + * idx can be of type enum memcg_stat_item or node_stat_item. + * Keep in sync with memcg_exact_page_state(). + */ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 532e0e2a4817..81a0d3914ec9 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3882,6 +3882,22 @@ struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb) return &memcg->cgwb_domain; } +/* + * idx can be of type enum memcg_stat_item or node_stat_item. + * Keep in sync with memcg_exact_page(). + */ +static unsigned long memcg_exact_page_state(struct mem_cgroup *memcg, int idx) +{ + long x = atomic_long_read(&memcg->stat[idx]); + int cpu; + + for_each_online_cpu(cpu) + x += per_cpu_ptr(memcg->stat_cpu, cpu)->count[idx]; + if (x < 0) + x = 0; + return x; +} + /** * mem_cgroup_wb_stats - retrieve writeback related stats from its memcg * @wb: bdi_writeback in question @@ -3907,10 +3923,10 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css); struct mem_cgroup *parent; - *pdirty = memcg_page_state(memcg, NR_FILE_DIRTY); + *pdirty = memcg_exact_page_state(memcg, NR_FILE_DIRTY); /* this should eventually include NR_UNSTABLE_NFS */ - *pwriteback = memcg_page_state(memcg, NR_WRITEBACK); + *pwriteback = memcg_exact_page_state(memcg, NR_WRITEBACK); *pfilepages = mem_cgroup_nr_lru_pages(memcg, (1 << LRU_INACTIVE_FILE) | (1 << LRU_ACTIVE_FILE)); *pheadroom = PAGE_COUNTER_MAX; -- cgit From 10dce8af34226d90fa56746a934f8da5dcdba3df Mon Sep 17 00:00:00 2001 From: Kirill Smelkov Date: Tue, 26 Mar 2019 22:20:43 +0000 Subject: fs: stream_open - opener for stream-like files so that read and write can run simultaneously without deadlock Commit 9c225f2655e3 ("vfs: atomic f_pos accesses as per POSIX") added locking for file.f_pos access and in particular made concurrent read and write not possible - now both those functions take f_pos lock for the whole run, and so if e.g. a read is blocked waiting for data, write will deadlock waiting for that read to complete. This caused regression for stream-like files where previously read and write could run simultaneously, but after that patch could not do so anymore. See e.g. commit 581d21a2d02a ("xenbus: fix deadlock on writes to /proc/xen/xenbus") which fixes such regression for particular case of /proc/xen/xenbus. The patch that added f_pos lock in 2014 did so to guarantee POSIX thread safety for read/write/lseek and added the locking to file descriptors of all regular files. In 2014 that thread-safety problem was not new as it was already discussed earlier in 2006. However even though 2006'th version of Linus's patch was adding f_pos locking "only for files that are marked seekable with FMODE_LSEEK (thus avoiding the stream-like objects like pipes and sockets)", the 2014 version - the one that actually made it into the tree as 9c225f2655e3 - is doing so irregardless of whether a file is seekable or not. See https://lore.kernel.org/lkml/53022DB1.4070805@gmail.com/ https://lwn.net/Articles/180387 https://lwn.net/Articles/180396 for historic context. The reason that it did so is, probably, that there are many files that are marked non-seekable, but e.g. their read implementation actually depends on knowing current position to correctly handle the read. Some examples: kernel/power/user.c snapshot_read fs/debugfs/file.c u32_array_read fs/fuse/control.c fuse_conn_waiting_read + ... drivers/hwmon/asus_atk0110.c atk_debugfs_ggrp_read arch/s390/hypfs/inode.c hypfs_read_iter ... Despite that, many nonseekable_open users implement read and write with pure stream semantics - they don't depend on passed ppos at all. And for those cases where read could wait for something inside, it creates a situation similar to xenbus - the write could be never made to go until read is done, and read is waiting for some, potentially external, event, for potentially unbounded time -> deadlock. Besides xenbus, there are 14 such places in the kernel that I've found with semantic patch (see below): drivers/xen/evtchn.c:667:8-24: ERROR: evtchn_fops: .read() can deadlock .write() drivers/isdn/capi/capi.c:963:8-24: ERROR: capi_fops: .read() can deadlock .write() drivers/input/evdev.c:527:1-17: ERROR: evdev_fops: .read() can deadlock .write() drivers/char/pcmcia/cm4000_cs.c:1685:7-23: ERROR: cm4000_fops: .read() can deadlock .write() net/rfkill/core.c:1146:8-24: ERROR: rfkill_fops: .read() can deadlock .write() drivers/s390/char/fs3270.c:488:1-17: ERROR: fs3270_fops: .read() can deadlock .write() drivers/usb/misc/ldusb.c:310:1-17: ERROR: ld_usb_fops: .read() can deadlock .write() drivers/hid/uhid.c:635:1-17: ERROR: uhid_fops: .read() can deadlock .write() net/batman-adv/icmp_socket.c:80:1-17: ERROR: batadv_fops: .read() can deadlock .write() drivers/media/rc/lirc_dev.c:198:1-17: ERROR: lirc_fops: .read() can deadlock .write() drivers/leds/uleds.c:77:1-17: ERROR: uleds_fops: .read() can deadlock .write() drivers/input/misc/uinput.c:400:1-17: ERROR: uinput_fops: .read() can deadlock .write() drivers/infiniband/core/user_mad.c:985:7-23: ERROR: umad_fops: .read() can deadlock .write() drivers/gnss/core.c:45:1-17: ERROR: gnss_fops: .read() can deadlock .write() In addition to the cases above another regression caused by f_pos locking is that now FUSE filesystems that implement open with FOPEN_NONSEEKABLE flag, can no longer implement bidirectional stream-like files - for the same reason as above e.g. read can deadlock write locking on file.f_pos in the kernel. FUSE's FOPEN_NONSEEKABLE was added in 2008 in a7c1b990f715 ("fuse: implement nonseekable open") to support OSSPD. OSSPD implements /dev/dsp in userspace with FOPEN_NONSEEKABLE flag, with corresponding read and write routines not depending on current position at all, and with both read and write being potentially blocking operations: See https://github.com/libfuse/osspd https://lwn.net/Articles/308445 https://github.com/libfuse/osspd/blob/14a9cff0/osspd.c#L1406 https://github.com/libfuse/osspd/blob/14a9cff0/osspd.c#L1438-L1477 https://github.com/libfuse/osspd/blob/14a9cff0/osspd.c#L1479-L1510 Corresponding libfuse example/test also describes FOPEN_NONSEEKABLE as "somewhat pipe-like files ..." with read handler not using offset. However that test implements only read without write and cannot exercise the deadlock scenario: https://github.com/libfuse/libfuse/blob/fuse-3.4.2-3-ga1bff7d/example/poll.c#L124-L131 https://github.com/libfuse/libfuse/blob/fuse-3.4.2-3-ga1bff7d/example/poll.c#L146-L163 https://github.com/libfuse/libfuse/blob/fuse-3.4.2-3-ga1bff7d/example/poll.c#L209-L216 I've actually hit the read vs write deadlock for real while implementing my FUSE filesystem where there is /head/watch file, for which open creates separate bidirectional socket-like stream in between filesystem and its user with both read and write being later performed simultaneously. And there it is semantically not easy to split the stream into two separate read-only and write-only channels: https://lab.nexedi.com/kirr/wendelin.core/blob/f13aa600/wcfs/wcfs.go#L88-169 Let's fix this regression. The plan is: 1. We can't change nonseekable_open to include &~FMODE_ATOMIC_POS - doing so would break many in-kernel nonseekable_open users which actually use ppos in read/write handlers. 2. Add stream_open() to kernel to open stream-like non-seekable file descriptors. Read and write on such file descriptors would never use nor change ppos. And with that property on stream-like files read and write will be running without taking f_pos lock - i.e. read and write could be running simultaneously. 3. With semantic patch search and convert to stream_open all in-kernel nonseekable_open users for which read and write actually do not depend on ppos and where there is no other methods in file_operations which assume @offset access. 4. Add FOPEN_STREAM to fs/fuse/ and open in-kernel file-descriptors via steam_open if that bit is present in filesystem open reply. It was tempting to change fs/fuse/ open handler to use stream_open instead of nonseekable_open on just FOPEN_NONSEEKABLE flags, but grepping through Debian codesearch shows users of FOPEN_NONSEEKABLE, and in particular GVFS which actually uses offset in its read and write handlers https://codesearch.debian.net/search?q=-%3Enonseekable+%3D https://gitlab.gnome.org/GNOME/gvfs/blob/1.40.0-6-gcbc54396/client/gvfsfusedaemon.c#L1080 https://gitlab.gnome.org/GNOME/gvfs/blob/1.40.0-6-gcbc54396/client/gvfsfusedaemon.c#L1247-1346 https://gitlab.gnome.org/GNOME/gvfs/blob/1.40.0-6-gcbc54396/client/gvfsfusedaemon.c#L1399-1481 so if we would do such a change it will break a real user. 5. Add stream_open and FOPEN_STREAM handling to stable kernels starting from v3.14+ (the kernel where 9c225f2655 first appeared). This will allow to patch OSSPD and other FUSE filesystems that provide stream-like files to return FOPEN_STREAM | FOPEN_NONSEEKABLE in their open handler and this way avoid the deadlock on all kernel versions. This should work because fs/fuse/ ignores unknown open flags returned from a filesystem and so passing FOPEN_STREAM to a kernel that is not aware of this flag cannot hurt. In turn the kernel that is not aware of FOPEN_STREAM will be < v3.14 where just FOPEN_NONSEEKABLE is sufficient to implement streams without read vs write deadlock. This patch adds stream_open, converts /proc/xen/xenbus to it and adds semantic patch to automatically locate in-kernel places that are either required to be converted due to read vs write deadlock, or that are just safe to be converted because read and write do not use ppos and there are no other funky methods in file_operations. Regarding semantic patch I've verified each generated change manually - that it is correct to convert - and each other nonseekable_open instance left - that it is either not correct to convert there, or that it is not converted due to current stream_open.cocci limitations. The script also does not convert files that should be valid to convert, but that currently have .llseek = noop_llseek or generic_file_llseek for unknown reason despite file being opened with nonseekable_open (e.g. drivers/input/mousedev.c) Cc: Michael Kerrisk Cc: Yongzhi Pan Cc: Jonathan Corbet Cc: David Vrabel Cc: Juergen Gross Cc: Miklos Szeredi Cc: Tejun Heo Cc: Kirill Tkhai Cc: Arnd Bergmann Cc: Christoph Hellwig Cc: Greg Kroah-Hartman Cc: Julia Lawall Cc: Nikolaus Rath Cc: Han-Wen Nienhuys Signed-off-by: Kirill Smelkov Signed-off-by: Linus Torvalds --- drivers/xen/xenbus/xenbus_dev_frontend.c | 4 +- fs/open.c | 18 ++ fs/read_write.c | 5 +- include/linux/fs.h | 4 + scripts/coccinelle/api/stream_open.cocci | 363 +++++++++++++++++++++++++++++++ 5 files changed, 389 insertions(+), 5 deletions(-) create mode 100644 scripts/coccinelle/api/stream_open.cocci (limited to 'include/linux') diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index c3e201025ef0..0782ff3c2273 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -622,9 +622,7 @@ static int xenbus_file_open(struct inode *inode, struct file *filp) if (xen_store_evtchn == 0) return -ENOENT; - nonseekable_open(inode, filp); - - filp->f_mode &= ~FMODE_ATOMIC_POS; /* cdev-style semantics */ + stream_open(inode, filp); u = kzalloc(sizeof(*u), GFP_KERNEL); if (u == NULL) diff --git a/fs/open.c b/fs/open.c index f1c2f855fd43..a00350018a47 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1215,3 +1215,21 @@ int nonseekable_open(struct inode *inode, struct file *filp) } EXPORT_SYMBOL(nonseekable_open); + +/* + * stream_open is used by subsystems that want stream-like file descriptors. + * Such file descriptors are not seekable and don't have notion of position + * (file.f_pos is always 0). Contrary to file descriptors of other regular + * files, .read() and .write() can run simultaneously. + * + * stream_open never fails and is marked to return int so that it could be + * directly used as file_operations.open . + */ +int stream_open(struct inode *inode, struct file *filp) +{ + filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE | FMODE_ATOMIC_POS); + filp->f_mode |= FMODE_STREAM; + return 0; +} + +EXPORT_SYMBOL(stream_open); diff --git a/fs/read_write.c b/fs/read_write.c index 177ccc3d405a..61b43ad7608e 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -560,12 +560,13 @@ ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_ static inline loff_t file_pos_read(struct file *file) { - return file->f_pos; + return file->f_mode & FMODE_STREAM ? 0 : file->f_pos; } static inline void file_pos_write(struct file *file, loff_t pos) { - file->f_pos = pos; + if ((file->f_mode & FMODE_STREAM) == 0) + file->f_pos = pos; } ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count) diff --git a/include/linux/fs.h b/include/linux/fs.h index 8b42df09b04c..dd28e7679089 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -158,6 +158,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, #define FMODE_OPENED ((__force fmode_t)0x80000) #define FMODE_CREATED ((__force fmode_t)0x100000) +/* File is stream-like */ +#define FMODE_STREAM ((__force fmode_t)0x200000) + /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) @@ -3074,6 +3077,7 @@ extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t); extern loff_t no_seek_end_llseek(struct file *, loff_t, int); extern int generic_file_open(struct inode * inode, struct file * filp); extern int nonseekable_open(struct inode * inode, struct file * filp); +extern int stream_open(struct inode * inode, struct file * filp); #ifdef CONFIG_BLOCK typedef void (dio_submit_t)(struct bio *bio, struct inode *inode, diff --git a/scripts/coccinelle/api/stream_open.cocci b/scripts/coccinelle/api/stream_open.cocci new file mode 100644 index 000000000000..350145da7669 --- /dev/null +++ b/scripts/coccinelle/api/stream_open.cocci @@ -0,0 +1,363 @@ +// SPDX-License-Identifier: GPL-2.0 +// Author: Kirill Smelkov (kirr@nexedi.com) +// +// Search for stream-like files that are using nonseekable_open and convert +// them to stream_open. A stream-like file is a file that does not use ppos in +// its read and write. Rationale for the conversion is to avoid deadlock in +// between read and write. + +virtual report +virtual patch +virtual explain // explain decisions in the patch (SPFLAGS="-D explain") + +// stream-like reader & writer - ones that do not depend on f_pos. +@ stream_reader @ +identifier readstream, ppos; +identifier f, buf, len; +type loff_t; +@@ + ssize_t readstream(struct file *f, char *buf, size_t len, loff_t *ppos) + { + ... when != ppos + } + +@ stream_writer @ +identifier writestream, ppos; +identifier f, buf, len; +type loff_t; +@@ + ssize_t writestream(struct file *f, const char *buf, size_t len, loff_t *ppos) + { + ... when != ppos + } + + +// a function that blocks +@ blocks @ +identifier block_f; +identifier wait_event =~ "^wait_event_.*"; +@@ + block_f(...) { + ... when exists + wait_event(...) + ... when exists + } + +// stream_reader that can block inside. +// +// XXX wait_* can be called not directly from current function (e.g. func -> f -> g -> wait()) +// XXX currently reader_blocks supports only direct and 1-level indirect cases. +@ reader_blocks_direct @ +identifier stream_reader.readstream; +identifier wait_event =~ "^wait_event_.*"; +@@ + readstream(...) + { + ... when exists + wait_event(...) + ... when exists + } + +@ reader_blocks_1 @ +identifier stream_reader.readstream; +identifier blocks.block_f; +@@ + readstream(...) + { + ... when exists + block_f(...) + ... when exists + } + +@ reader_blocks depends on reader_blocks_direct || reader_blocks_1 @ +identifier stream_reader.readstream; +@@ + readstream(...) { + ... + } + + +// file_operations + whether they have _any_ .read, .write, .llseek ... at all. +// +// XXX add support for file_operations xxx[N] = ... (sound/core/pcm_native.c) +@ fops0 @ +identifier fops; +@@ + struct file_operations fops = { + ... + }; + +@ has_read @ +identifier fops0.fops; +identifier read_f; +@@ + struct file_operations fops = { + .read = read_f, + }; + +@ has_read_iter @ +identifier fops0.fops; +identifier read_iter_f; +@@ + struct file_operations fops = { + .read_iter = read_iter_f, + }; + +@ has_write @ +identifier fops0.fops; +identifier write_f; +@@ + struct file_operations fops = { + .write = write_f, + }; + +@ has_write_iter @ +identifier fops0.fops; +identifier write_iter_f; +@@ + struct file_operations fops = { + .write_iter = write_iter_f, + }; + +@ has_llseek @ +identifier fops0.fops; +identifier llseek_f; +@@ + struct file_operations fops = { + .llseek = llseek_f, + }; + +@ has_no_llseek @ +identifier fops0.fops; +@@ + struct file_operations fops = { + .llseek = no_llseek, + }; + +@ has_mmap @ +identifier fops0.fops; +identifier mmap_f; +@@ + struct file_operations fops = { + .mmap = mmap_f, + }; + +@ has_copy_file_range @ +identifier fops0.fops; +identifier copy_file_range_f; +@@ + struct file_operations fops = { + .copy_file_range = copy_file_range_f, + }; + +@ has_remap_file_range @ +identifier fops0.fops; +identifier remap_file_range_f; +@@ + struct file_operations fops = { + .remap_file_range = remap_file_range_f, + }; + +@ has_splice_read @ +identifier fops0.fops; +identifier splice_read_f; +@@ + struct file_operations fops = { + .splice_read = splice_read_f, + }; + +@ has_splice_write @ +identifier fops0.fops; +identifier splice_write_f; +@@ + struct file_operations fops = { + .splice_write = splice_write_f, + }; + + +// file_operations that is candidate for stream_open conversion - it does not +// use mmap and other methods that assume @offset access to file. +// +// XXX for simplicity require no .{read/write}_iter and no .splice_{read/write} for now. +// XXX maybe_steam.fops cannot be used in other rules - it gives "bad rule maybe_stream or bad variable fops". +@ maybe_stream depends on (!has_llseek || has_no_llseek) && !has_mmap && !has_copy_file_range && !has_remap_file_range && !has_read_iter && !has_write_iter && !has_splice_read && !has_splice_write @ +identifier fops0.fops; +@@ + struct file_operations fops = { + }; + + +// ---- conversions ---- + +// XXX .open = nonseekable_open -> .open = stream_open +// XXX .open = func -> openfunc -> nonseekable_open + +// read & write +// +// if both are used in the same file_operations together with an opener - +// under that conditions we can use stream_open instead of nonseekable_open. +@ fops_rw depends on maybe_stream @ +identifier fops0.fops, openfunc; +identifier stream_reader.readstream; +identifier stream_writer.writestream; +@@ + struct file_operations fops = { + .open = openfunc, + .read = readstream, + .write = writestream, + }; + +@ report_rw depends on report @ +identifier fops_rw.openfunc; +position p1; +@@ + openfunc(...) { + <... + nonseekable_open@p1 + ...> + } + +@ script:python depends on report && reader_blocks @ +fops << fops0.fops; +p << report_rw.p1; +@@ +coccilib.report.print_report(p[0], + "ERROR: %s: .read() can deadlock .write(); change nonseekable_open -> stream_open to fix." % (fops,)) + +@ script:python depends on report && !reader_blocks @ +fops << fops0.fops; +p << report_rw.p1; +@@ +coccilib.report.print_report(p[0], + "WARNING: %s: .read() and .write() have stream semantic; safe to change nonseekable_open -> stream_open." % (fops,)) + + +@ explain_rw_deadlocked depends on explain && reader_blocks @ +identifier fops_rw.openfunc; +@@ + openfunc(...) { + <... +- nonseekable_open ++ nonseekable_open /* read & write (was deadlock) */ + ...> + } + + +@ explain_rw_nodeadlock depends on explain && !reader_blocks @ +identifier fops_rw.openfunc; +@@ + openfunc(...) { + <... +- nonseekable_open ++ nonseekable_open /* read & write (no direct deadlock) */ + ...> + } + +@ patch_rw depends on patch @ +identifier fops_rw.openfunc; +@@ + openfunc(...) { + <... +- nonseekable_open ++ stream_open + ...> + } + + +// read, but not write +@ fops_r depends on maybe_stream && !has_write @ +identifier fops0.fops, openfunc; +identifier stream_reader.readstream; +@@ + struct file_operations fops = { + .open = openfunc, + .read = readstream, + }; + +@ report_r depends on report @ +identifier fops_r.openfunc; +position p1; +@@ + openfunc(...) { + <... + nonseekable_open@p1 + ...> + } + +@ script:python depends on report @ +fops << fops0.fops; +p << report_r.p1; +@@ +coccilib.report.print_report(p[0], + "WARNING: %s: .read() has stream semantic; safe to change nonseekable_open -> stream_open." % (fops,)) + +@ explain_r depends on explain @ +identifier fops_r.openfunc; +@@ + openfunc(...) { + <... +- nonseekable_open ++ nonseekable_open /* read only */ + ...> + } + +@ patch_r depends on patch @ +identifier fops_r.openfunc; +@@ + openfunc(...) { + <... +- nonseekable_open ++ stream_open + ...> + } + + +// write, but not read +@ fops_w depends on maybe_stream && !has_read @ +identifier fops0.fops, openfunc; +identifier stream_writer.writestream; +@@ + struct file_operations fops = { + .open = openfunc, + .write = writestream, + }; + +@ report_w depends on report @ +identifier fops_w.openfunc; +position p1; +@@ + openfunc(...) { + <... + nonseekable_open@p1 + ...> + } + +@ script:python depends on report @ +fops << fops0.fops; +p << report_w.p1; +@@ +coccilib.report.print_report(p[0], + "WARNING: %s: .write() has stream semantic; safe to change nonseekable_open -> stream_open." % (fops,)) + +@ explain_w depends on explain @ +identifier fops_w.openfunc; +@@ + openfunc(...) { + <... +- nonseekable_open ++ nonseekable_open /* write only */ + ...> + } + +@ patch_w depends on patch @ +identifier fops_w.openfunc; +@@ + openfunc(...) { + <... +- nonseekable_open ++ stream_open + ...> + } + + +// no read, no write - don't change anything -- cgit From 5861381d486601430cccf64849bd0a226154bc0d Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Thu, 21 Mar 2019 23:18:01 +0100 Subject: PM / arch: x86: Rework the MSR_IA32_ENERGY_PERF_BIAS handling The current handling of MSR_IA32_ENERGY_PERF_BIAS in the kernel is problematic, because it may cause changes made by user space to that MSR (with the help of the x86_energy_perf_policy tool, for example) to be lost every time a CPU goes offline and then back online as well as during system-wide power management transitions into sleep states and back into the working state. The first problem is that if the current EPB value for a CPU going online is 0 ('performance'), the kernel will change it to 6 ('normal') regardless of whether or not this is the first bring-up of that CPU. That also happens during system-wide resume from sleep states (including, but not limited to, hibernation). However, the EPB may have been adjusted by user space this way and the kernel should not blindly override that setting. The second problem is that if the platform firmware resets the EPB values for any CPUs during system-wide resume from a sleep state, the kernel will not restore their previous EPB values that may have been set by user space before the preceding system-wide suspend transition. Again, that behavior may at least be confusing from the user space perspective. In order to address these issues, rework the handling of MSR_IA32_ENERGY_PERF_BIAS so that the EPB value is saved on CPU offline and restored on CPU online as well as (for the boot CPU) during the syscore stages of system-wide suspend and resume transitions, respectively. However, retain the policy by which the EPB is set to 6 ('normal') on the first bring-up of each CPU if its initial value is 0, based on the observation that 0 may mean 'not initialized' just as well as 'performance' in that case. While at it, move the MSR_IA32_ENERGY_PERF_BIAS handling code into a separate file and document it in Documentation/admin-guide. Fixes: abe48b108247 (x86, intel, power: Initialize MSR_IA32_ENERGY_PERF_BIAS) Fixes: b51ef52df71c (x86/cpu: Restore MSR_IA32_ENERGY_PERF_BIAS after resume) Reported-by: Thomas Renninger Signed-off-by: Rafael J. Wysocki Reviewed-by: Hannes Reinecke Acked-by: Borislav Petkov Acked-by: Thomas Gleixner --- Documentation/admin-guide/pm/intel_epb.rst | 6 ++ Documentation/admin-guide/pm/working-state.rst | 1 + arch/x86/kernel/cpu/Makefile | 2 +- arch/x86/kernel/cpu/common.c | 17 ---- arch/x86/kernel/cpu/cpu.h | 1 - arch/x86/kernel/cpu/intel.c | 34 ------- arch/x86/kernel/cpu/intel_epb.c | 131 +++++++++++++++++++++++++ include/linux/cpuhotplug.h | 1 + 8 files changed, 140 insertions(+), 53 deletions(-) create mode 100644 Documentation/admin-guide/pm/intel_epb.rst create mode 100644 arch/x86/kernel/cpu/intel_epb.c (limited to 'include/linux') diff --git a/Documentation/admin-guide/pm/intel_epb.rst b/Documentation/admin-guide/pm/intel_epb.rst new file mode 100644 index 000000000000..e9cfa7ec5420 --- /dev/null +++ b/Documentation/admin-guide/pm/intel_epb.rst @@ -0,0 +1,6 @@ +====================================== +Intel Performance and Energy Bias Hint +====================================== + +.. kernel-doc:: arch/x86/kernel/cpu/intel_epb.c + :doc: overview diff --git a/Documentation/admin-guide/pm/working-state.rst b/Documentation/admin-guide/pm/working-state.rst index b6cef9b5e961..beb004d3632b 100644 --- a/Documentation/admin-guide/pm/working-state.rst +++ b/Documentation/admin-guide/pm/working-state.rst @@ -8,3 +8,4 @@ Working-State Power Management cpuidle cpufreq intel_pstate + intel_epb diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index cfd24f9f7614..1796d2bdcaaa 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -28,7 +28,7 @@ obj-y += cpuid-deps.o obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o -obj-$(CONFIG_CPU_SUP_INTEL) += intel.o intel_pconfig.o +obj-$(CONFIG_CPU_SUP_INTEL) += intel.o intel_pconfig.o intel_epb.o obj-$(CONFIG_CPU_SUP_AMD) += amd.o obj-$(CONFIG_CPU_SUP_HYGON) += hygon.o obj-$(CONFIG_CPU_SUP_CYRIX_32) += cyrix.o diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index cb28e98a0659..5e37dfa4d9df 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1864,23 +1864,6 @@ void cpu_init(void) } #endif -static void bsp_resume(void) -{ - if (this_cpu->c_bsp_resume) - this_cpu->c_bsp_resume(&boot_cpu_data); -} - -static struct syscore_ops cpu_syscore_ops = { - .resume = bsp_resume, -}; - -static int __init init_cpu_syscore(void) -{ - register_syscore_ops(&cpu_syscore_ops); - return 0; -} -core_initcall(init_cpu_syscore); - /* * The microcode loader calls this upon late microcode load to recheck features, * only when microcode has been updated. Caller holds microcode_mutex and CPU diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 5eb946b9a9f3..c0e2407abdd6 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -14,7 +14,6 @@ struct cpu_dev { void (*c_init)(struct cpuinfo_x86 *); void (*c_identify)(struct cpuinfo_x86 *); void (*c_detect_tlb)(struct cpuinfo_x86 *); - void (*c_bsp_resume)(struct cpuinfo_x86 *); int c_x86_vendor; #ifdef CONFIG_X86_32 /* Optional vendor specific routine to obtain the cache size. */ diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index fc3c07fe7df5..f17c1a714779 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -596,36 +596,6 @@ detect_keyid_bits: c->x86_phys_bits -= keyid_bits; } -static void init_intel_energy_perf(struct cpuinfo_x86 *c) -{ - u64 epb; - - /* - * Initialize MSR_IA32_ENERGY_PERF_BIAS if not already initialized. - * (x86_energy_perf_policy(8) is available to change it at run-time.) - */ - if (!cpu_has(c, X86_FEATURE_EPB)) - return; - - rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb); - if ((epb & 0xF) != ENERGY_PERF_BIAS_PERFORMANCE) - return; - - pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n"); - pr_warn_once("ENERGY_PERF_BIAS: View and update with x86_energy_perf_policy(8)\n"); - epb = (epb & ~0xF) | ENERGY_PERF_BIAS_NORMAL; - wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb); -} - -static void intel_bsp_resume(struct cpuinfo_x86 *c) -{ - /* - * MSR_IA32_ENERGY_PERF_BIAS is lost across suspend/resume, - * so reinitialize it properly like during bootup: - */ - init_intel_energy_perf(c); -} - static void init_cpuid_fault(struct cpuinfo_x86 *c) { u64 msr; @@ -763,8 +733,6 @@ static void init_intel(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_TME)) detect_tme(c); - init_intel_energy_perf(c); - init_intel_misc_features(c); } @@ -1023,9 +991,7 @@ static const struct cpu_dev intel_cpu_dev = { .c_detect_tlb = intel_detect_tlb, .c_early_init = early_init_intel, .c_init = init_intel, - .c_bsp_resume = intel_bsp_resume, .c_x86_vendor = X86_VENDOR_INTEL, }; cpu_dev_register(intel_cpu_dev); - diff --git a/arch/x86/kernel/cpu/intel_epb.c b/arch/x86/kernel/cpu/intel_epb.c new file mode 100644 index 000000000000..8d53cc88bd22 --- /dev/null +++ b/arch/x86/kernel/cpu/intel_epb.c @@ -0,0 +1,131 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel Performance and Energy Bias Hint support. + * + * Copyright (C) 2019 Intel Corporation + * + * Author: + * Rafael J. Wysocki + */ + +#include +#include +#include + +#include +#include + +/** + * DOC: overview + * + * The Performance and Energy Bias Hint (EPB) allows software to specify its + * preference with respect to the power-performance tradeoffs present in the + * processor. Generally, the EPB is expected to be set by user space through + * the generic MSR interface (with the help of the x86_energy_perf_policy tool), + * but there are two reasons for the kernel to touch it. + * + * First, there are systems where the platform firmware resets the EPB during + * system-wide transitions from sleep states back into the working state + * effectively causing the previous EPB updates by user space to be lost. + * Thus the kernel needs to save the current EPB values for all CPUs during + * system-wide transitions to sleep states and restore them on the way back to + * the working state. That can be achieved by saving EPB for secondary CPUs + * when they are taken offline during transitions into system sleep states and + * for the boot CPU in a syscore suspend operation, so that it can be restored + * for the boot CPU in a syscore resume operation and for the other CPUs when + * they are brought back online. However, CPUs that are already offline when + * a system-wide PM transition is started are not taken offline again, but their + * EPB values may still be reset by the platform firmware during the transition, + * so in fact it is necessary to save the EPB of any CPU taken offline and to + * restore it when the given CPU goes back online at all times. + * + * Second, on many systems the initial EPB value coming from the platform + * firmware is 0 ('performance') and at least on some of them that is because + * the platform firmware does not initialize EPB at all with the assumption that + * the OS will do that anyway. That sometimes is problematic, as it may cause + * the system battery to drain too fast, for example, so it is better to adjust + * it on CPU bring-up and if the initial EPB value for a given CPU is 0, the + * kernel changes it to 6 ('normal'). + */ + +static DEFINE_PER_CPU(u8, saved_epb); + +#define EPB_MASK 0x0fULL +#define EPB_SAVED 0x10ULL + +static int intel_epb_save(void) +{ + u64 epb; + + rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb); + /* + * Ensure that saved_epb will always be nonzero after this write even if + * the EPB value read from the MSR is 0. + */ + this_cpu_write(saved_epb, (epb & EPB_MASK) | EPB_SAVED); + + return 0; +} + +static void intel_epb_restore(void) +{ + u64 val = this_cpu_read(saved_epb); + u64 epb; + + rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb); + if (val) { + val &= EPB_MASK; + } else { + /* + * Because intel_epb_save() has not run for the current CPU yet, + * it is going online for the first time, so if its EPB value is + * 0 ('performance') at this point, assume that it has not been + * initialized by the platform firmware and set it to 6 + * ('normal'). + */ + val = epb & EPB_MASK; + if (val == ENERGY_PERF_BIAS_PERFORMANCE) { + val = ENERGY_PERF_BIAS_NORMAL; + pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n"); + } + } + wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, (epb & ~EPB_MASK) | val); +} + +static struct syscore_ops intel_epb_syscore_ops = { + .suspend = intel_epb_save, + .resume = intel_epb_restore, +}; + +static int intel_epb_online(unsigned int cpu) +{ + intel_epb_restore(); + return 0; +} + +static int intel_epb_offline(unsigned int cpu) +{ + return intel_epb_save(); +} + +static __init int intel_epb_init(void) +{ + int ret; + + if (!boot_cpu_has(X86_FEATURE_EPB)) + return -ENODEV; + + ret = cpuhp_setup_state(CPUHP_AP_X86_INTEL_EPB_ONLINE, + "x86/intel/epb:online", intel_epb_online, + intel_epb_offline); + if (ret < 0) + goto err_out_online; + + register_syscore_ops(&intel_epb_syscore_ops); + return 0; + +err_out_online: + cpuhp_remove_state(CPUHP_AP_X86_INTEL_EPB_ONLINE); + return ret; +} +subsys_initcall(intel_epb_init); diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index e78281d07b70..dbfdd0fadbef 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -147,6 +147,7 @@ enum cpuhp_state { CPUHP_AP_X86_VDSO_VMA_ONLINE, CPUHP_AP_IRQ_AFFINITY_ONLINE, CPUHP_AP_ARM_MVEBU_SYNC_CLOCKS, + CPUHP_AP_X86_INTEL_EPB_ONLINE, CPUHP_AP_PERF_ONLINE, CPUHP_AP_PERF_X86_ONLINE, CPUHP_AP_PERF_X86_UNCORE_ONLINE, -- cgit From 9083e4986124389e2a7c0ffca95630a4983887f0 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Tue, 26 Mar 2019 12:19:52 +0100 Subject: cpufreq: intel_pstate: Update max frequency on global turbo changes While the cpuinfo.max_freq value doesn't really matter for intel_pstate in the active mode, in the passive mode it is used by governors as the maximum physical frequency of the CPU and the results of governor computations generally depend on it. Also it is made available to user space via sysfs and it should match the current HW configuration. For this reason, make intel_pstate update cpuinfo.max_freq for all CPUs if it detects a global change of turbo frequency settings from "disable" to "enable" or the other way associated with a _PPC change notification from the platform firmware. Note that policy_is_inactive(), cpufreq_cpu_acquire(), cpufreq_cpu_release(), and cpufreq_set_policy() need to be made available to it for this purpose. Link: https://bugzilla.kernel.org/show_bug.cgi?id=200759 Reported-by: Gabriele Mazzotta Tested-by: Gabriele Mazzotta Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar --- drivers/cpufreq/cpufreq.c | 16 ++++------------ drivers/cpufreq/intel_pstate.c | 35 +++++++++++++++++++++++++++++------ include/linux/cpufreq.h | 10 ++++++++++ 3 files changed, 43 insertions(+), 18 deletions(-) (limited to 'include/linux') diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index d8fc395af773..f3f79266ab48 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -34,11 +34,6 @@ static LIST_HEAD(cpufreq_policy_list); -static inline bool policy_is_inactive(struct cpufreq_policy *policy) -{ - return cpumask_empty(policy->cpus); -} - /* Macros to iterate over CPU policies */ #define for_each_suitable_policy(__policy, __active) \ list_for_each_entry(__policy, &cpufreq_policy_list, policy_list) \ @@ -254,7 +249,7 @@ EXPORT_SYMBOL_GPL(cpufreq_cpu_put); * cpufreq_cpu_release - Unlock a policy and decrement its usage counter. * @policy: cpufreq policy returned by cpufreq_cpu_acquire(). */ -static void cpufreq_cpu_release(struct cpufreq_policy *policy) +void cpufreq_cpu_release(struct cpufreq_policy *policy) { if (WARN_ON(!policy)) return; @@ -278,7 +273,7 @@ static void cpufreq_cpu_release(struct cpufreq_policy *policy) * cpufreq_cpu_release() in order to release its rwsem and balance its usage * counter properly. */ -static struct cpufreq_policy *cpufreq_cpu_acquire(unsigned int cpu) +struct cpufreq_policy *cpufreq_cpu_acquire(unsigned int cpu) { struct cpufreq_policy *policy = cpufreq_cpu_get(cpu); @@ -714,9 +709,6 @@ static ssize_t show_scaling_cur_freq(struct cpufreq_policy *policy, char *buf) return ret; } -static int cpufreq_set_policy(struct cpufreq_policy *policy, - struct cpufreq_policy *new_policy); - /** * cpufreq_per_cpu_attr_write() / store_##file_name() - sysfs write access */ @@ -2274,8 +2266,8 @@ EXPORT_SYMBOL(cpufreq_get_policy); * * The cpuinfo part of @policy is not updated by this function. */ -static int cpufreq_set_policy(struct cpufreq_policy *policy, - struct cpufreq_policy *new_policy) +int cpufreq_set_policy(struct cpufreq_policy *policy, + struct cpufreq_policy *new_policy) { struct cpufreq_governor *old_gov; int ret; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index e2191a570ade..08d1a1e845aa 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -179,7 +179,7 @@ struct vid_data { * based on the MSR_IA32_MISC_ENABLE value and whether or * not the maximum reported turbo P-state is different from * the maximum reported non-turbo one. - * @turbo_disabled_s: Saved @turbo_disabled value. + * @turbo_disabled_mf: The @turbo_disabled value reflected by cpuinfo.max_freq. * @min_perf_pct: Minimum capacity limit in percent of the maximum turbo * P-state capacity. * @max_perf_pct: Maximum capacity limit in percent of the maximum turbo @@ -188,7 +188,7 @@ struct vid_data { struct global_params { bool no_turbo; bool turbo_disabled; - bool turbo_disabled_s; + bool turbo_disabled_mf; int max_perf_pct; int min_perf_pct; }; @@ -899,6 +899,28 @@ static void intel_pstate_update_policies(void) cpufreq_update_policy(cpu); } +static void intel_pstate_update_max_freq(unsigned int cpu) +{ + struct cpufreq_policy *policy = cpufreq_cpu_acquire(cpu); + struct cpufreq_policy new_policy; + struct cpudata *cpudata; + + if (!policy) + return; + + cpudata = all_cpu_data[cpu]; + policy->cpuinfo.max_freq = global.turbo_disabled_mf ? + cpudata->pstate.max_freq : cpudata->pstate.turbo_freq; + + memcpy(&new_policy, policy, sizeof(*policy)); + new_policy.max = min(policy->user_policy.max, policy->cpuinfo.max_freq); + new_policy.min = min(policy->user_policy.min, new_policy.max); + + cpufreq_set_policy(policy, &new_policy); + + cpufreq_cpu_release(policy); +} + static void intel_pstate_update_limits(unsigned int cpu) { mutex_lock(&intel_pstate_driver_lock); @@ -908,9 +930,10 @@ static void intel_pstate_update_limits(unsigned int cpu) * If turbo has been turned on or off globally, policy limits for * all CPUs need to be updated to reflect that. */ - if (global.turbo_disabled_s != global.turbo_disabled) { - global.turbo_disabled_s = global.turbo_disabled; - intel_pstate_update_policies(); + if (global.turbo_disabled_mf != global.turbo_disabled) { + global.turbo_disabled_mf = global.turbo_disabled; + for_each_possible_cpu(cpu) + intel_pstate_update_max_freq(cpu); } else { cpufreq_update_policy(cpu); } @@ -2159,7 +2182,7 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy) /* cpuinfo and default policy values */ policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling; update_turbo_state(); - global.turbo_disabled_s = global.turbo_disabled; + global.turbo_disabled_mf = global.turbo_disabled; policy->cpuinfo.max_freq = global.turbo_disabled ? cpu->pstate.max_pstate : cpu->pstate.turbo_pstate; policy->cpuinfo.max_freq *= cpu->pstate.scaling; diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 5005ea40364f..684caf067003 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -178,6 +178,11 @@ static inline struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu) static inline void cpufreq_cpu_put(struct cpufreq_policy *policy) { } #endif +static inline bool policy_is_inactive(struct cpufreq_policy *policy) +{ + return cpumask_empty(policy->cpus); +} + static inline bool policy_is_shared(struct cpufreq_policy *policy) { return cpumask_weight(policy->cpus) > 1; @@ -193,7 +198,12 @@ unsigned int cpufreq_quick_get_max(unsigned int cpu); void disable_cpufreq(void); u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy); + +struct cpufreq_policy *cpufreq_cpu_acquire(unsigned int cpu); +void cpufreq_cpu_release(struct cpufreq_policy *policy); int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu); +int cpufreq_set_policy(struct cpufreq_policy *policy, + struct cpufreq_policy *new_policy); void cpufreq_update_policy(unsigned int cpu); void cpufreq_update_limits(unsigned int cpu); bool have_governor_per_policy(void); -- cgit From 60ca1e5a200cd294a12907fa36dece4241db4ab8 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 22 Feb 2019 12:59:59 +0000 Subject: mmiowb: Hook up mmiowb helpers to spinlocks and generic I/O accessors Removing explicit calls to mmiowb() from driver code means that we must now call into the generic mmiowb_spin_{lock,unlock}() functions from the core spinlock code. In order to elide barriers following critical sections without any I/O writes, we also hook into the asm-generic I/O routines. Acked-by: Linus Torvalds Signed-off-by: Will Deacon --- include/asm-generic/io.h | 3 ++- include/linux/spinlock.h | 11 ++++++++++- kernel/locking/spinlock_debug.c | 6 +++++- 3 files changed, 17 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index 303871651f8a..bc490a746602 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -19,6 +19,7 @@ #include #endif +#include #include #ifndef mmiowb @@ -49,7 +50,7 @@ /* serialize device access against a spin_unlock, usually handled there. */ #ifndef __io_aw -#define __io_aw() barrier() +#define __io_aw() mmiowb_set_pending() #endif #ifndef __io_pbw diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index e089157dcf97..ed7c4d6b8235 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -57,6 +57,7 @@ #include #include #include +#include /* @@ -178,6 +179,7 @@ static inline void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock) { __acquire(lock); arch_spin_lock(&lock->raw_lock); + mmiowb_spin_lock(); } #ifndef arch_spin_lock_flags @@ -189,15 +191,22 @@ do_raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long *flags) __acquires(lo { __acquire(lock); arch_spin_lock_flags(&lock->raw_lock, *flags); + mmiowb_spin_lock(); } static inline int do_raw_spin_trylock(raw_spinlock_t *lock) { - return arch_spin_trylock(&(lock)->raw_lock); + int ret = arch_spin_trylock(&(lock)->raw_lock); + + if (ret) + mmiowb_spin_lock(); + + return ret; } static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) { + mmiowb_spin_unlock(); arch_spin_unlock(&lock->raw_lock); __release(lock); } diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c index 9aa0fccd5d43..399669f7eba8 100644 --- a/kernel/locking/spinlock_debug.c +++ b/kernel/locking/spinlock_debug.c @@ -111,6 +111,7 @@ void do_raw_spin_lock(raw_spinlock_t *lock) { debug_spin_lock_before(lock); arch_spin_lock(&lock->raw_lock); + mmiowb_spin_lock(); debug_spin_lock_after(lock); } @@ -118,8 +119,10 @@ int do_raw_spin_trylock(raw_spinlock_t *lock) { int ret = arch_spin_trylock(&lock->raw_lock); - if (ret) + if (ret) { + mmiowb_spin_lock(); debug_spin_lock_after(lock); + } #ifndef CONFIG_SMP /* * Must not happen on UP: @@ -131,6 +134,7 @@ int do_raw_spin_trylock(raw_spinlock_t *lock) void do_raw_spin_unlock(raw_spinlock_t *lock) { + mmiowb_spin_unlock(); debug_spin_unlock(lock); arch_spin_unlock(&lock->raw_lock); } -- cgit From fb24ea52f78e0d595852e09e3a55697c8f442189 Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Fri, 22 Feb 2019 17:14:59 +0000 Subject: drivers: Remove explicit invocations of mmiowb() mmiowb() is now implied by spin_unlock() on architectures that require it, so there is no reason to call it from driver code. This patch was generated using coccinelle: @mmiowb@ @@ - mmiowb(); and invoked as: $ for d in drivers include/linux/qed sound; do \ spatch --include-headers --sp-file mmiowb.cocci --dir $d --in-place; done NOTE: mmiowb() has only ever guaranteed ordering in conjunction with spin_unlock(). However, pairing each mmiowb() removal in this patch with the corresponding call to spin_unlock() is not at all trivial, so there is a small chance that this change may regress any drivers incorrectly relying on mmiowb() to order MMIO writes between CPUs using lock-free synchronisation. If you've ended up bisecting to this commit, you can reintroduce the mmiowb() calls using wmb() instead, which should restore the old behaviour on all architectures other than some esoteric ia64 systems. Acked-by: Linus Torvalds Signed-off-by: Will Deacon --- drivers/crypto/cavium/nitrox/nitrox_reqmgr.c | 4 --- drivers/dma/txx9dmac.c | 3 --- drivers/firewire/ohci.c | 1 - drivers/gpu/drm/i915/intel_hdmi.c | 10 -------- drivers/ide/tx4939ide.c | 2 -- drivers/infiniband/hw/hfi1/chip.c | 3 --- drivers/infiniband/hw/hfi1/pio.c | 1 - drivers/infiniband/hw/hns/hns_roce_hw_v1.c | 2 -- drivers/infiniband/hw/mlx4/qp.c | 6 ----- drivers/infiniband/hw/mlx5/qp.c | 1 - drivers/infiniband/hw/mthca/mthca_cmd.c | 6 ----- drivers/infiniband/hw/mthca/mthca_cq.c | 5 ---- drivers/infiniband/hw/mthca/mthca_qp.c | 17 ------------- drivers/infiniband/hw/mthca/mthca_srq.c | 6 ----- drivers/infiniband/hw/qedr/verbs.c | 12 --------- drivers/infiniband/hw/qib/qib_iba6120.c | 4 --- drivers/infiniband/hw/qib/qib_iba7220.c | 3 --- drivers/infiniband/hw/qib/qib_iba7322.c | 3 --- drivers/infiniband/hw/qib/qib_sd7220.c | 4 --- drivers/media/pci/dt3155/dt3155.c | 8 ------ drivers/memstick/host/jmb38x_ms.c | 4 --- drivers/misc/ioc4.c | 2 -- drivers/misc/mei/hw-me.c | 3 --- drivers/misc/tifm_7xx1.c | 1 - drivers/mmc/host/alcor.c | 1 - drivers/mmc/host/sdhci.c | 13 ---------- drivers/mmc/host/tifm_sd.c | 3 --- drivers/mmc/host/via-sdmmc.c | 10 -------- drivers/mtd/nand/raw/r852.c | 2 -- drivers/mtd/nand/raw/txx9ndfmc.c | 1 - drivers/net/ethernet/aeroflex/greth.c | 1 - drivers/net/ethernet/alacritech/slicoss.c | 4 --- drivers/net/ethernet/amazon/ena/ena_com.c | 1 - drivers/net/ethernet/atheros/atlx/atl1.c | 1 - drivers/net/ethernet/atheros/atlx/atl2.c | 1 - drivers/net/ethernet/broadcom/bnx2.c | 4 --- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 2 -- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h | 4 --- .../net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c | 1 - drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 29 ---------------------- drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c | 1 - drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c | 2 -- drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c | 4 --- drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 --- drivers/net/ethernet/broadcom/tg3.c | 6 ----- .../net/ethernet/cavium/liquidio/cn66xx_device.c | 10 -------- .../net/ethernet/cavium/liquidio/octeon_device.c | 1 - drivers/net/ethernet/cavium/liquidio/octeon_droq.c | 4 --- .../net/ethernet/cavium/liquidio/request_manager.c | 1 - drivers/net/ethernet/intel/e1000/e1000_main.c | 5 ---- drivers/net/ethernet/intel/e1000e/netdev.c | 7 ------ drivers/net/ethernet/intel/fm10k/fm10k_iov.c | 2 -- drivers/net/ethernet/intel/fm10k/fm10k_main.c | 5 ---- drivers/net/ethernet/intel/i40e/i40e_txrx.c | 5 ---- drivers/net/ethernet/intel/iavf/iavf_txrx.c | 5 ---- drivers/net/ethernet/intel/ice/ice_txrx.c | 5 ---- drivers/net/ethernet/intel/igb/igb_main.c | 5 ---- drivers/net/ethernet/intel/igbvf/netdev.c | 4 --- drivers/net/ethernet/intel/igc/igc_main.c | 5 ---- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 5 ---- drivers/net/ethernet/marvell/sky2.c | 4 --- drivers/net/ethernet/mellanox/mlx4/catas.c | 4 --- drivers/net/ethernet/mellanox/mlx4/cmd.c | 13 ---------- drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 1 - drivers/net/ethernet/myricom/myri10ge/myri10ge.c | 2 -- drivers/net/ethernet/neterion/s2io.c | 2 -- drivers/net/ethernet/neterion/vxge/vxge-main.c | 5 ---- drivers/net/ethernet/neterion/vxge/vxge-traffic.c | 4 --- drivers/net/ethernet/qlogic/qed/qed_int.c | 13 ---------- drivers/net/ethernet/qlogic/qed/qed_spq.c | 3 --- drivers/net/ethernet/qlogic/qede/qede_ethtool.c | 8 ------ drivers/net/ethernet/qlogic/qede/qede_fp.c | 8 ------ drivers/net/ethernet/qlogic/qla3xxx.c | 1 - drivers/net/ethernet/qlogic/qlge/qlge.h | 1 - drivers/net/ethernet/qlogic/qlge/qlge_main.c | 1 - drivers/net/ethernet/renesas/ravb_main.c | 9 ------- drivers/net/ethernet/renesas/ravb_ptp.c | 3 --- drivers/net/ethernet/renesas/sh_eth.c | 1 - drivers/net/ethernet/sfc/falcon/io.h | 2 -- drivers/net/ethernet/sfc/io.h | 2 -- drivers/net/ethernet/silan/sc92031.c | 14 ----------- drivers/net/ethernet/via/via-rhine.c | 3 --- drivers/net/ethernet/wiznet/w5100.c | 6 ----- drivers/net/ethernet/wiznet/w5300.c | 15 ----------- drivers/net/wireless/ath/ath5k/base.c | 4 --- drivers/net/wireless/ath/ath5k/mac80211-ops.c | 2 -- drivers/net/wireless/broadcom/b43/main.c | 7 ------ drivers/net/wireless/broadcom/b43/sysfs.c | 1 - drivers/net/wireless/broadcom/b43legacy/ilt.c | 2 -- drivers/net/wireless/broadcom/b43legacy/main.c | 20 --------------- drivers/net/wireless/broadcom/b43legacy/phy.c | 1 - drivers/net/wireless/broadcom/b43legacy/pio.h | 1 - drivers/net/wireless/broadcom/b43legacy/radio.c | 4 --- drivers/net/wireless/broadcom/b43legacy/sysfs.c | 1 - drivers/net/wireless/intel/iwlegacy/common.h | 7 ------ drivers/net/wireless/intel/iwlwifi/pcie/trans.c | 1 - drivers/ntb/hw/idt/ntb_hw_idt.c | 7 ------ drivers/ntb/test/ntb_perf.c | 3 --- drivers/scsi/bfa/bfa.h | 3 +-- drivers/scsi/bfa/bfa_hw_cb.c | 2 -- drivers/scsi/bfa/bfa_hw_ct.c | 2 -- drivers/scsi/bnx2fc/bnx2fc_hwi.c | 2 -- drivers/scsi/bnx2i/bnx2i_hwi.c | 3 --- drivers/scsi/megaraid/megaraid_sas_base.c | 1 - drivers/scsi/megaraid/megaraid_sas_fusion.c | 1 - drivers/scsi/mpt3sas/mpt3sas_base.c | 1 - drivers/scsi/qedf/qedf_io.c | 1 - drivers/scsi/qedi/qedi_fw.c | 1 - drivers/scsi/qla1280.c | 5 ---- drivers/ssb/pci.c | 1 - drivers/ssb/pcmcia.c | 4 --- drivers/staging/comedi/drivers/mite.c | 3 --- drivers/staging/comedi/drivers/ni_660x.c | 2 -- drivers/staging/comedi/drivers/ni_mio_common.c | 1 - drivers/staging/comedi/drivers/ni_pcidio.c | 2 -- drivers/staging/comedi/drivers/ni_tio.c | 1 - drivers/staging/comedi/drivers/s626.c | 2 -- drivers/tty/serial/men_z135_uart.c | 1 - drivers/tty/serial/serial_txx9.c | 1 - drivers/usb/early/xhci-dbc.c | 4 --- drivers/usb/host/xhci-dbgcap.c | 2 -- include/linux/qed/qed_if.h | 2 -- sound/soc/txx9/txx9aclc-ac97.c | 1 - 123 files changed, 1 insertion(+), 508 deletions(-) (limited to 'include/linux') diff --git a/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c b/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c index 4c97478d44bd..5826c2c98a50 100644 --- a/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c +++ b/drivers/crypto/cavium/nitrox/nitrox_reqmgr.c @@ -303,8 +303,6 @@ static void post_se_instr(struct nitrox_softreq *sr, /* Ring doorbell with count 1 */ writeq(1, cmdq->dbell_csr_addr); - /* orders the doorbell rings */ - mmiowb(); cmdq->write_idx = incr_index(idx, 1, ndev->qlen); @@ -599,8 +597,6 @@ void pkt_slc_resp_tasklet(unsigned long data) * MSI-X interrupt generates if Completion count > Threshold */ writeq(slc_cnts.value, cmdq->compl_cnt_csr_addr); - /* order the writes */ - mmiowb(); if (atomic_read(&cmdq->backlog_count)) schedule_work(&cmdq->backlog_qflush); diff --git a/drivers/dma/txx9dmac.c b/drivers/dma/txx9dmac.c index eb45af71d3a3..e8d0881b64d8 100644 --- a/drivers/dma/txx9dmac.c +++ b/drivers/dma/txx9dmac.c @@ -327,7 +327,6 @@ static void txx9dmac_reset_chan(struct txx9dmac_chan *dc) channel_writel(dc, SAIR, 0); channel_writel(dc, DAIR, 0); channel_writel(dc, CCR, 0); - mmiowb(); } /* Called with dc->lock held and bh disabled */ @@ -954,7 +953,6 @@ static void txx9dmac_chain_dynamic(struct txx9dmac_chan *dc, dma_sync_single_for_device(chan2parent(&dc->chan), prev->txd.phys, ddev->descsize, DMA_TO_DEVICE); - mmiowb(); if (!(channel_readl(dc, CSR) & TXX9_DMA_CSR_CHNEN) && channel_read_CHAR(dc) == prev->txd.phys) /* Restart chain DMA */ @@ -1080,7 +1078,6 @@ static void txx9dmac_free_chan_resources(struct dma_chan *chan) static void txx9dmac_off(struct txx9dmac_dev *ddev) { dma_writel(ddev, MCR, 0); - mmiowb(); } static int __init txx9dmac_chan_probe(struct platform_device *pdev) diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c index 45c048751f3b..7183ab34269e 100644 --- a/drivers/firewire/ohci.c +++ b/drivers/firewire/ohci.c @@ -2939,7 +2939,6 @@ static void set_multichannel_mask(struct fw_ohci *ohci, u64 channels) reg_write(ohci, OHCI1394_IRMultiChanMaskLoClear, ~lo); reg_write(ohci, OHCI1394_IRMultiChanMaskHiSet, hi); reg_write(ohci, OHCI1394_IRMultiChanMaskLoSet, lo); - mmiowb(); ohci->mc_channels = channels; } diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c index f125a62eba8c..a46bffe2b288 100644 --- a/drivers/gpu/drm/i915/intel_hdmi.c +++ b/drivers/gpu/drm/i915/intel_hdmi.c @@ -182,7 +182,6 @@ static void g4x_write_infoframe(struct intel_encoder *encoder, I915_WRITE(VIDEO_DIP_CTL, val); - mmiowb(); for (i = 0; i < len; i += 4) { I915_WRITE(VIDEO_DIP_DATA, *data); data++; @@ -190,7 +189,6 @@ static void g4x_write_infoframe(struct intel_encoder *encoder, /* Write every possible data byte to force correct ECC calculation. */ for (; i < VIDEO_DIP_DATA_SIZE; i += 4) I915_WRITE(VIDEO_DIP_DATA, 0); - mmiowb(); val |= g4x_infoframe_enable(type); val &= ~VIDEO_DIP_FREQ_MASK; @@ -237,7 +235,6 @@ static void ibx_write_infoframe(struct intel_encoder *encoder, I915_WRITE(reg, val); - mmiowb(); for (i = 0; i < len; i += 4) { I915_WRITE(TVIDEO_DIP_DATA(intel_crtc->pipe), *data); data++; @@ -245,7 +242,6 @@ static void ibx_write_infoframe(struct intel_encoder *encoder, /* Write every possible data byte to force correct ECC calculation. */ for (; i < VIDEO_DIP_DATA_SIZE; i += 4) I915_WRITE(TVIDEO_DIP_DATA(intel_crtc->pipe), 0); - mmiowb(); val |= g4x_infoframe_enable(type); val &= ~VIDEO_DIP_FREQ_MASK; @@ -298,7 +294,6 @@ static void cpt_write_infoframe(struct intel_encoder *encoder, I915_WRITE(reg, val); - mmiowb(); for (i = 0; i < len; i += 4) { I915_WRITE(TVIDEO_DIP_DATA(intel_crtc->pipe), *data); data++; @@ -306,7 +301,6 @@ static void cpt_write_infoframe(struct intel_encoder *encoder, /* Write every possible data byte to force correct ECC calculation. */ for (; i < VIDEO_DIP_DATA_SIZE; i += 4) I915_WRITE(TVIDEO_DIP_DATA(intel_crtc->pipe), 0); - mmiowb(); val |= g4x_infoframe_enable(type); val &= ~VIDEO_DIP_FREQ_MASK; @@ -352,7 +346,6 @@ static void vlv_write_infoframe(struct intel_encoder *encoder, I915_WRITE(reg, val); - mmiowb(); for (i = 0; i < len; i += 4) { I915_WRITE(VLV_TVIDEO_DIP_DATA(intel_crtc->pipe), *data); data++; @@ -360,7 +353,6 @@ static void vlv_write_infoframe(struct intel_encoder *encoder, /* Write every possible data byte to force correct ECC calculation. */ for (; i < VIDEO_DIP_DATA_SIZE; i += 4) I915_WRITE(VLV_TVIDEO_DIP_DATA(intel_crtc->pipe), 0); - mmiowb(); val |= g4x_infoframe_enable(type); val &= ~VIDEO_DIP_FREQ_MASK; @@ -406,7 +398,6 @@ static void hsw_write_infoframe(struct intel_encoder *encoder, val &= ~hsw_infoframe_enable(type); I915_WRITE(ctl_reg, val); - mmiowb(); for (i = 0; i < len; i += 4) { I915_WRITE(hsw_dip_data_reg(dev_priv, cpu_transcoder, type, i >> 2), *data); @@ -416,7 +407,6 @@ static void hsw_write_infoframe(struct intel_encoder *encoder, for (; i < data_size; i += 4) I915_WRITE(hsw_dip_data_reg(dev_priv, cpu_transcoder, type, i >> 2), 0); - mmiowb(); val |= hsw_infoframe_enable(type); I915_WRITE(ctl_reg, val); diff --git a/drivers/ide/tx4939ide.c b/drivers/ide/tx4939ide.c index 67d4a7d4acc8..88d132edc4e3 100644 --- a/drivers/ide/tx4939ide.c +++ b/drivers/ide/tx4939ide.c @@ -156,7 +156,6 @@ static u16 tx4939ide_check_error_ints(ide_hwif_t *hwif) u16 sysctl = tx4939ide_readw(base, TX4939IDE_Sys_Ctl); tx4939ide_writew(sysctl | 0x4000, base, TX4939IDE_Sys_Ctl); - mmiowb(); /* wait 12GBUSCLK (typ. 60ns @ GBUS200MHz, max 270ns) */ ndelay(270); tx4939ide_writew(sysctl, base, TX4939IDE_Sys_Ctl); @@ -396,7 +395,6 @@ static void tx4939ide_init_hwif(ide_hwif_t *hwif) /* Soft Reset */ tx4939ide_writew(0x8000, base, TX4939IDE_Sys_Ctl); - mmiowb(); /* at least 20 GBUSCLK (typ. 100ns @ GBUS200MHz, max 450ns) */ ndelay(450); tx4939ide_writew(0x0000, base, TX4939IDE_Sys_Ctl); diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 12e67a91e578..8f270459b63e 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -8365,7 +8365,6 @@ static inline void clear_recv_intr(struct hfi1_ctxtdata *rcd) struct hfi1_devdata *dd = rcd->dd; u32 addr = CCE_INT_CLEAR + (8 * rcd->ireg); - mmiowb(); write_csr(dd, addr, rcd->imask); /* force the above write on the chip and get a value back */ (void)read_csr(dd, addr); @@ -11803,12 +11802,10 @@ void update_usrhead(struct hfi1_ctxtdata *rcd, u32 hd, u32 updegr, u32 egrhd, << RCV_EGR_INDEX_HEAD_HEAD_SHIFT; write_uctxt_csr(dd, ctxt, RCV_EGR_INDEX_HEAD, reg); } - mmiowb(); reg = ((u64)rcv_intr_count << RCV_HDR_HEAD_COUNTER_SHIFT) | (((u64)hd & RCV_HDR_HEAD_HEAD_MASK) << RCV_HDR_HEAD_HEAD_SHIFT); write_uctxt_csr(dd, ctxt, RCV_HDR_HEAD, reg); - mmiowb(); } u32 hdrqempty(struct hfi1_ctxtdata *rcd) diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c index a1de566fe95e..16ba9d52e1b9 100644 --- a/drivers/infiniband/hw/hfi1/pio.c +++ b/drivers/infiniband/hw/hfi1/pio.c @@ -1578,7 +1578,6 @@ void hfi1_sc_wantpiobuf_intr(struct send_context *sc, u32 needint) sc_del_credit_return_intr(sc); trace_hfi1_wantpiointr(sc, needint, sc->credit_ctrl); if (needint) { - mmiowb(); sc_return_credits(sc); } } diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c index 97515c340134..c8555f7704d8 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c @@ -1750,8 +1750,6 @@ static int hns_roce_v1_post_mbox(struct hns_roce_dev *hr_dev, u64 in_param, writel(val, hcr + 5); - mmiowb(); - return 0; } diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index 429a59c5801c..9426936460f8 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -3744,12 +3744,6 @@ out: writel_relaxed(qp->doorbell_qpn, to_mdev(ibqp->device)->uar_map + MLX4_SEND_DOORBELL); - /* - * Make sure doorbells don't leak out of SQ spinlock - * and reach the HCA out of order. - */ - mmiowb(); - stamp_send_wqe(qp, ind + qp->sq_spare_wqes - 1); qp->sq_next_wqe = ind; diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index 7cd006da1dae..b680be1f3f47 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -5123,7 +5123,6 @@ out: /* Make sure doorbells don't leak out of SQ spinlock * and reach the HCA out of order. */ - mmiowb(); bf->offset ^= bf->buf_size; } diff --git a/drivers/infiniband/hw/mthca/mthca_cmd.c b/drivers/infiniband/hw/mthca/mthca_cmd.c index 83aa47eb81a9..bdf5ed38de22 100644 --- a/drivers/infiniband/hw/mthca/mthca_cmd.c +++ b/drivers/infiniband/hw/mthca/mthca_cmd.c @@ -292,12 +292,6 @@ static int mthca_cmd_post(struct mthca_dev *dev, err = mthca_cmd_post_hcr(dev, in_param, out_param, in_modifier, op_modifier, op, token, event); - /* - * Make sure that our HCR writes don't get mixed in with - * writes from another CPU starting a FW command. - */ - mmiowb(); - mutex_unlock(&dev->cmd.hcr_mutex); return err; } diff --git a/drivers/infiniband/hw/mthca/mthca_cq.c b/drivers/infiniband/hw/mthca/mthca_cq.c index a6531ffe29a6..877a6daffa98 100644 --- a/drivers/infiniband/hw/mthca/mthca_cq.c +++ b/drivers/infiniband/hw/mthca/mthca_cq.c @@ -211,11 +211,6 @@ static inline void update_cons_index(struct mthca_dev *dev, struct mthca_cq *cq, mthca_write64(MTHCA_TAVOR_CQ_DB_INC_CI | cq->cqn, incr - 1, dev->kar + MTHCA_CQ_DOORBELL, MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock)); - /* - * Make sure doorbells don't leak out of CQ spinlock - * and reach the HCA out of order: - */ - mmiowb(); } } diff --git a/drivers/infiniband/hw/mthca/mthca_qp.c b/drivers/infiniband/hw/mthca/mthca_qp.c index 7a5b25d13faa..d65b189f20ea 100644 --- a/drivers/infiniband/hw/mthca/mthca_qp.c +++ b/drivers/infiniband/hw/mthca/mthca_qp.c @@ -1809,11 +1809,6 @@ out: (qp->qpn << 8) | size0, dev->kar + MTHCA_SEND_DOORBELL, MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock)); - /* - * Make sure doorbells don't leak out of SQ spinlock - * and reach the HCA out of order: - */ - mmiowb(); } qp->sq.next_ind = ind; @@ -1924,12 +1919,6 @@ out: qp->rq.next_ind = ind; qp->rq.head += nreq; - /* - * Make sure doorbells don't leak out of RQ spinlock and reach - * the HCA out of order: - */ - mmiowb(); - spin_unlock_irqrestore(&qp->rq.lock, flags); return err; } @@ -2164,12 +2153,6 @@ out: MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock)); } - /* - * Make sure doorbells don't leak out of SQ spinlock and reach - * the HCA out of order: - */ - mmiowb(); - spin_unlock_irqrestore(&qp->sq.lock, flags); return err; } diff --git a/drivers/infiniband/hw/mthca/mthca_srq.c b/drivers/infiniband/hw/mthca/mthca_srq.c index 06b920385512..a85935ccce88 100644 --- a/drivers/infiniband/hw/mthca/mthca_srq.c +++ b/drivers/infiniband/hw/mthca/mthca_srq.c @@ -570,12 +570,6 @@ int mthca_tavor_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr, MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock)); } - /* - * Make sure doorbells don't leak out of SRQ spinlock and - * reach the HCA out of order: - */ - mmiowb(); - spin_unlock_irqrestore(&srq->lock, flags); return err; } diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index 4dab2b5ffb0e..8686a98e113d 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -773,9 +773,6 @@ static void doorbell_cq(struct qedr_cq *cq, u32 cons, u8 flags) cq->db.data.agg_flags = flags; cq->db.data.value = cpu_to_le32(cons); writeq(cq->db.raw, cq->db_addr); - - /* Make sure write would stick */ - mmiowb(); } int qedr_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags) @@ -2084,8 +2081,6 @@ static int qedr_update_qp_state(struct qedr_dev *dev, if (rdma_protocol_roce(&dev->ibdev, 1)) { writel(qp->rq.db_data.raw, qp->rq.db); - /* Make sure write takes effect */ - mmiowb(); } break; case QED_ROCE_QP_STATE_ERR: @@ -3502,9 +3497,6 @@ int qedr_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr, smp_wmb(); writel(qp->sq.db_data.raw, qp->sq.db); - /* Make sure write sticks */ - mmiowb(); - spin_unlock_irqrestore(&qp->q_lock, flags); return rc; @@ -3695,12 +3687,8 @@ int qedr_post_recv(struct ib_qp *ibqp, const struct ib_recv_wr *wr, writel(qp->rq.db_data.raw, qp->rq.db); - /* Make sure write sticks */ - mmiowb(); - if (rdma_protocol_iwarp(&dev->ibdev, 1)) { writel(qp->rq.iwarp_db2_data.raw, qp->rq.iwarp_db2); - mmiowb(); } wr = wr->next; diff --git a/drivers/infiniband/hw/qib/qib_iba6120.c b/drivers/infiniband/hw/qib/qib_iba6120.c index cdbf707fa267..531d8a1db2c3 100644 --- a/drivers/infiniband/hw/qib/qib_iba6120.c +++ b/drivers/infiniband/hw/qib/qib_iba6120.c @@ -1884,7 +1884,6 @@ static void qib_6120_put_tid(struct qib_devdata *dd, u64 __iomem *tidptr, qib_write_kreg(dd, kr_scratch, 0xfeeddeaf); writel(pa, tidp32); qib_write_kreg(dd, kr_scratch, 0xdeadbeef); - mmiowb(); spin_unlock_irqrestore(tidlockp, flags); } @@ -1928,7 +1927,6 @@ static void qib_6120_put_tid_2(struct qib_devdata *dd, u64 __iomem *tidptr, pa |= 2 << 29; } writel(pa, tidp32); - mmiowb(); } @@ -2053,9 +2051,7 @@ static void qib_update_6120_usrhead(struct qib_ctxtdata *rcd, u64 hd, { if (updegr) qib_write_ureg(rcd->dd, ur_rcvegrindexhead, egrhd, rcd->ctxt); - mmiowb(); qib_write_ureg(rcd->dd, ur_rcvhdrhead, hd, rcd->ctxt); - mmiowb(); } static u32 qib_6120_hdrqempty(struct qib_ctxtdata *rcd) diff --git a/drivers/infiniband/hw/qib/qib_iba7220.c b/drivers/infiniband/hw/qib/qib_iba7220.c index 9fde45538f6e..ea3ddb05cbad 100644 --- a/drivers/infiniband/hw/qib/qib_iba7220.c +++ b/drivers/infiniband/hw/qib/qib_iba7220.c @@ -2175,7 +2175,6 @@ static void qib_7220_put_tid(struct qib_devdata *dd, u64 __iomem *tidptr, pa = chippa; } writeq(pa, tidptr); - mmiowb(); } /** @@ -2704,9 +2703,7 @@ static void qib_update_7220_usrhead(struct qib_ctxtdata *rcd, u64 hd, { if (updegr) qib_write_ureg(rcd->dd, ur_rcvegrindexhead, egrhd, rcd->ctxt); - mmiowb(); qib_write_ureg(rcd->dd, ur_rcvhdrhead, hd, rcd->ctxt); - mmiowb(); } static u32 qib_7220_hdrqempty(struct qib_ctxtdata *rcd) diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c index 17d6b24b3473..ac6a84f11ad0 100644 --- a/drivers/infiniband/hw/qib/qib_iba7322.c +++ b/drivers/infiniband/hw/qib/qib_iba7322.c @@ -3793,7 +3793,6 @@ static void qib_7322_put_tid(struct qib_devdata *dd, u64 __iomem *tidptr, pa = chippa; } writeq(pa, tidptr); - mmiowb(); } /** @@ -4440,10 +4439,8 @@ static void qib_update_7322_usrhead(struct qib_ctxtdata *rcd, u64 hd, adjust_rcv_timeout(rcd, npkts); if (updegr) qib_write_ureg(rcd->dd, ur_rcvegrindexhead, egrhd, rcd->ctxt); - mmiowb(); qib_write_ureg(rcd->dd, ur_rcvhdrhead, hd, rcd->ctxt); qib_write_ureg(rcd->dd, ur_rcvhdrhead, hd, rcd->ctxt); - mmiowb(); } static u32 qib_7322_hdrqempty(struct qib_ctxtdata *rcd) diff --git a/drivers/infiniband/hw/qib/qib_sd7220.c b/drivers/infiniband/hw/qib/qib_sd7220.c index 12caf3db8c34..4f4a09c2dbcd 100644 --- a/drivers/infiniband/hw/qib/qib_sd7220.c +++ b/drivers/infiniband/hw/qib/qib_sd7220.c @@ -1068,7 +1068,6 @@ static int qib_sd_setvals(struct qib_devdata *dd) for (idx = 0; idx < NUM_DDS_REGS; ++idx) { data = ((dds_reg_map & 0xF) << 4) | TX_FAST_ELT; writeq(data, iaddr + idx); - mmiowb(); qib_read_kreg32(dd, kr_scratch); dds_reg_map >>= 4; for (midx = 0; midx < DDS_ROWS; ++midx) { @@ -1076,7 +1075,6 @@ static int qib_sd_setvals(struct qib_devdata *dd) data = dds_init_vals[midx].reg_vals[idx]; writeq(data, daddr); - mmiowb(); qib_read_kreg32(dd, kr_scratch); } /* End inner for (vals for this reg, each row) */ } /* end outer for (regs to be stored) */ @@ -1098,13 +1096,11 @@ static int qib_sd_setvals(struct qib_devdata *dd) didx = idx + min_idx; /* Store the next RXEQ register address */ writeq(rxeq_init_vals[idx].rdesc, iaddr + didx); - mmiowb(); qib_read_kreg32(dd, kr_scratch); /* Iterate through RXEQ values */ for (vidx = 0; vidx < 4; vidx++) { data = rxeq_init_vals[idx].rdata[vidx]; writeq(data, taddr + (vidx << 6) + idx); - mmiowb(); qib_read_kreg32(dd, kr_scratch); } } /* end outer for (Reg-writes for RXEQ) */ diff --git a/drivers/media/pci/dt3155/dt3155.c b/drivers/media/pci/dt3155/dt3155.c index 17d69bd5d7f1..49677ee889e3 100644 --- a/drivers/media/pci/dt3155/dt3155.c +++ b/drivers/media/pci/dt3155/dt3155.c @@ -46,7 +46,6 @@ static int read_i2c_reg(void __iomem *addr, u8 index, u8 *data) u32 tmp = index; iowrite32((tmp << 17) | IIC_READ, addr + IIC_CSR2); - mmiowb(); udelay(45); /* wait at least 43 usec for NEW_CYCLE to clear */ if (ioread32(addr + IIC_CSR2) & NEW_CYCLE) return -EIO; /* error: NEW_CYCLE not cleared */ @@ -77,7 +76,6 @@ static int write_i2c_reg(void __iomem *addr, u8 index, u8 data) u32 tmp = index; iowrite32((tmp << 17) | IIC_WRITE | data, addr + IIC_CSR2); - mmiowb(); udelay(65); /* wait at least 63 usec for NEW_CYCLE to clear */ if (ioread32(addr + IIC_CSR2) & NEW_CYCLE) return -EIO; /* error: NEW_CYCLE not cleared */ @@ -104,7 +102,6 @@ static void write_i2c_reg_nowait(void __iomem *addr, u8 index, u8 data) u32 tmp = index; iowrite32((tmp << 17) | IIC_WRITE | data, addr + IIC_CSR2); - mmiowb(); } /** @@ -264,7 +261,6 @@ static irqreturn_t dt3155_irq_handler_even(int irq, void *dev_id) FLD_DN_ODD | FLD_DN_EVEN | CAP_CONT_EVEN | CAP_CONT_ODD, ipd->regs + CSR1); - mmiowb(); } spin_lock(&ipd->lock); @@ -282,7 +278,6 @@ static irqreturn_t dt3155_irq_handler_even(int irq, void *dev_id) iowrite32(dma_addr + ipd->width, ipd->regs + ODD_DMA_START); iowrite32(ipd->width, ipd->regs + EVEN_DMA_STRIDE); iowrite32(ipd->width, ipd->regs + ODD_DMA_STRIDE); - mmiowb(); } /* enable interrupts, clear all irq flags */ @@ -437,12 +432,10 @@ static int dt3155_init_board(struct dt3155_priv *pd) /* resetting the adapter */ iowrite32(ADDR_ERR_ODD | ADDR_ERR_EVEN | FLD_CRPT_ODD | FLD_CRPT_EVEN | FLD_DN_ODD | FLD_DN_EVEN, pd->regs + CSR1); - mmiowb(); msleep(20); /* initializing adapter registers */ iowrite32(FIFO_EN | SRST, pd->regs + CSR1); - mmiowb(); iowrite32(0xEEEEEE01, pd->regs + EVEN_PIXEL_FMT); iowrite32(0xEEEEEE01, pd->regs + ODD_PIXEL_FMT); iowrite32(0x00000020, pd->regs + FIFO_TRIGER); @@ -454,7 +447,6 @@ static int dt3155_init_board(struct dt3155_priv *pd) iowrite32(0, pd->regs + MASK_LENGTH); iowrite32(0x0005007C, pd->regs + FIFO_FLAG_CNT); iowrite32(0x01010101, pd->regs + IIC_CLK_DUR); - mmiowb(); /* verifying that we have a DT3155 board (not just a SAA7116 chip) */ read_i2c_reg(pd->regs, DT_ID, &tmp); diff --git a/drivers/memstick/host/jmb38x_ms.c b/drivers/memstick/host/jmb38x_ms.c index bcdca9fbef51..e3a5af65dbce 100644 --- a/drivers/memstick/host/jmb38x_ms.c +++ b/drivers/memstick/host/jmb38x_ms.c @@ -644,7 +644,6 @@ static int jmb38x_ms_reset(struct jmb38x_ms_host *host) writel(HOST_CONTROL_RESET_REQ | HOST_CONTROL_CLOCK_EN | readl(host->addr + HOST_CONTROL), host->addr + HOST_CONTROL); - mmiowb(); for (cnt = 0; cnt < 20; ++cnt) { if (!(HOST_CONTROL_RESET_REQ @@ -659,7 +658,6 @@ reset_next: writel(HOST_CONTROL_RESET | HOST_CONTROL_CLOCK_EN | readl(host->addr + HOST_CONTROL), host->addr + HOST_CONTROL); - mmiowb(); for (cnt = 0; cnt < 20; ++cnt) { if (!(HOST_CONTROL_RESET @@ -672,7 +670,6 @@ reset_next: return -EIO; reset_ok: - mmiowb(); writel(INT_STATUS_ALL, host->addr + INT_SIGNAL_ENABLE); writel(INT_STATUS_ALL, host->addr + INT_STATUS_ENABLE); return 0; @@ -1009,7 +1006,6 @@ static void jmb38x_ms_remove(struct pci_dev *dev) tasklet_kill(&host->notify); writel(0, host->addr + INT_SIGNAL_ENABLE); writel(0, host->addr + INT_STATUS_ENABLE); - mmiowb(); dev_dbg(&jm->pdev->dev, "interrupts off\n"); spin_lock_irqsave(&host->lock, flags); if (host->req) { diff --git a/drivers/misc/ioc4.c b/drivers/misc/ioc4.c index ec0832278170..9d0445a567db 100644 --- a/drivers/misc/ioc4.c +++ b/drivers/misc/ioc4.c @@ -156,7 +156,6 @@ ioc4_clock_calibrate(struct ioc4_driver_data *idd) /* Reset to power-on state */ writel(0, &idd->idd_misc_regs->int_out.raw); - mmiowb(); /* Set up square wave */ int_out.raw = 0; @@ -164,7 +163,6 @@ ioc4_clock_calibrate(struct ioc4_driver_data *idd) int_out.fields.mode = IOC4_INT_OUT_MODE_TOGGLE; int_out.fields.diag = 0; writel(int_out.raw, &idd->idd_misc_regs->int_out.raw); - mmiowb(); /* Check square wave period averaged over some number of cycles */ start = ktime_get_ns(); diff --git a/drivers/misc/mei/hw-me.c b/drivers/misc/mei/hw-me.c index 3fbbadfa2ae1..8a47a6fc3fc7 100644 --- a/drivers/misc/mei/hw-me.c +++ b/drivers/misc/mei/hw-me.c @@ -350,9 +350,6 @@ static void mei_me_hw_reset_release(struct mei_device *dev) hcsr |= H_IG; hcsr &= ~H_RST; mei_hcsr_set(dev, hcsr); - - /* complete this write before we set host ready on another CPU */ - mmiowb(); } /** diff --git a/drivers/misc/tifm_7xx1.c b/drivers/misc/tifm_7xx1.c index 9ac95b48ef92..cc729f7ab32e 100644 --- a/drivers/misc/tifm_7xx1.c +++ b/drivers/misc/tifm_7xx1.c @@ -403,7 +403,6 @@ static void tifm_7xx1_remove(struct pci_dev *dev) fm->eject = tifm_7xx1_dummy_eject; fm->has_ms_pif = tifm_7xx1_dummy_has_ms_pif; writel(TIFM_IRQ_SETALL, fm->addr + FM_CLEAR_INTERRUPT_ENABLE); - mmiowb(); free_irq(dev->irq, fm); tifm_remove_adapter(fm); diff --git a/drivers/mmc/host/alcor.c b/drivers/mmc/host/alcor.c index 82a97866e0cf..546b1fc30e7d 100644 --- a/drivers/mmc/host/alcor.c +++ b/drivers/mmc/host/alcor.c @@ -967,7 +967,6 @@ static void alcor_timeout_timer(struct work_struct *work) alcor_request_complete(host, 0); } - mmiowb(); mutex_unlock(&host->cmd_mutex); } diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index a8141ff9be03..42e1bad024f4 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -1807,7 +1807,6 @@ void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq) sdhci_send_command(host, mrq->cmd); } - mmiowb(); spin_unlock_irqrestore(&host->lock, flags); } EXPORT_SYMBOL_GPL(sdhci_request); @@ -2010,8 +2009,6 @@ void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) */ if (host->quirks & SDHCI_QUIRK_RESET_CMD_DATA_ON_IOS) sdhci_do_reset(host, SDHCI_RESET_CMD | SDHCI_RESET_DATA); - - mmiowb(); } EXPORT_SYMBOL_GPL(sdhci_set_ios); @@ -2105,7 +2102,6 @@ static void sdhci_enable_sdio_irq_nolock(struct sdhci_host *host, int enable) sdhci_writel(host, host->ier, SDHCI_INT_ENABLE); sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE); - mmiowb(); } } @@ -2353,7 +2349,6 @@ void sdhci_send_tuning(struct sdhci_host *host, u32 opcode) host->tuning_done = 0; - mmiowb(); spin_unlock_irqrestore(&host->lock, flags); /* Wait for Buffer Read Ready interrupt */ @@ -2705,7 +2700,6 @@ static bool sdhci_request_done(struct sdhci_host *host) host->mrqs_done[i] = NULL; - mmiowb(); spin_unlock_irqrestore(&host->lock, flags); mmc_request_done(host->mmc, mrq); @@ -2739,7 +2733,6 @@ static void sdhci_timeout_timer(struct timer_list *t) sdhci_finish_mrq(host, host->cmd->mrq); } - mmiowb(); spin_unlock_irqrestore(&host->lock, flags); } @@ -2770,7 +2763,6 @@ static void sdhci_timeout_data_timer(struct timer_list *t) } } - mmiowb(); spin_unlock_irqrestore(&host->lock, flags); } @@ -3251,7 +3243,6 @@ int sdhci_resume_host(struct sdhci_host *host) mmc->ops->set_ios(mmc, &mmc->ios); } else { sdhci_init(host, (host->mmc->pm_flags & MMC_PM_KEEP_POWER)); - mmiowb(); } if (host->irq_wake_enabled) { @@ -3391,7 +3382,6 @@ void sdhci_cqe_enable(struct mmc_host *mmc) mmc_hostname(mmc), host->ier, sdhci_readl(host, SDHCI_INT_STATUS)); - mmiowb(); spin_unlock_irqrestore(&host->lock, flags); } EXPORT_SYMBOL_GPL(sdhci_cqe_enable); @@ -3416,7 +3406,6 @@ void sdhci_cqe_disable(struct mmc_host *mmc, bool recovery) mmc_hostname(mmc), host->ier, sdhci_readl(host, SDHCI_INT_STATUS)); - mmiowb(); spin_unlock_irqrestore(&host->lock, flags); } EXPORT_SYMBOL_GPL(sdhci_cqe_disable); @@ -4255,8 +4244,6 @@ int __sdhci_add_host(struct sdhci_host *host) goto unirq; } - mmiowb(); - ret = mmc_add_host(mmc); if (ret) goto unled; diff --git a/drivers/mmc/host/tifm_sd.c b/drivers/mmc/host/tifm_sd.c index b6644ce296b2..35dd34b82a4d 100644 --- a/drivers/mmc/host/tifm_sd.c +++ b/drivers/mmc/host/tifm_sd.c @@ -889,7 +889,6 @@ static int tifm_sd_initialize_host(struct tifm_sd *host) struct tifm_dev *sock = host->dev; writel(0, sock->addr + SOCK_MMCSD_INT_ENABLE); - mmiowb(); host->clk_div = 61; host->clk_freq = 20000000; writel(TIFM_MMCSD_RESET, sock->addr + SOCK_MMCSD_SYSTEM_CONTROL); @@ -940,7 +939,6 @@ static int tifm_sd_initialize_host(struct tifm_sd *host) writel(TIFM_MMCSD_CERR | TIFM_MMCSD_BRS | TIFM_MMCSD_EOC | TIFM_MMCSD_ERRMASK, sock->addr + SOCK_MMCSD_INT_ENABLE); - mmiowb(); return 0; } @@ -1005,7 +1003,6 @@ static void tifm_sd_remove(struct tifm_dev *sock) spin_lock_irqsave(&sock->lock, flags); host->eject = 1; writel(0, sock->addr + SOCK_MMCSD_INT_ENABLE); - mmiowb(); spin_unlock_irqrestore(&sock->lock, flags); tasklet_kill(&host->finish_tasklet); diff --git a/drivers/mmc/host/via-sdmmc.c b/drivers/mmc/host/via-sdmmc.c index 32c4211506fc..412395ac2935 100644 --- a/drivers/mmc/host/via-sdmmc.c +++ b/drivers/mmc/host/via-sdmmc.c @@ -686,7 +686,6 @@ static void via_sdc_request(struct mmc_host *mmc, struct mmc_request *mrq) via_sdc_send_command(host, mrq->cmd); } - mmiowb(); spin_unlock_irqrestore(&host->lock, flags); } @@ -711,7 +710,6 @@ static void via_sdc_set_power(struct via_crdr_mmc_host *host, gatt &= ~VIA_CRDR_PCICLKGATT_PAD_PWRON; writeb(gatt, host->pcictrl_mmiobase + VIA_CRDR_PCICLKGATT); - mmiowb(); spin_unlock_irqrestore(&host->lock, flags); via_pwron_sleep(host); @@ -770,7 +768,6 @@ static void via_sdc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) if (readb(addrbase + VIA_CRDR_PCISDCCLK) != clock) writeb(clock, addrbase + VIA_CRDR_PCISDCCLK); - mmiowb(); spin_unlock_irqrestore(&host->lock, flags); if (ios->power_mode != MMC_POWER_OFF) @@ -830,7 +827,6 @@ static void via_reset_pcictrl(struct via_crdr_mmc_host *host) via_restore_pcictrlreg(host); via_restore_sdcreg(host); - mmiowb(); spin_unlock_irqrestore(&host->lock, flags); } @@ -925,7 +921,6 @@ static irqreturn_t via_sdc_isr(int irq, void *dev_id) result = IRQ_HANDLED; - mmiowb(); out: spin_unlock(&sdhost->lock); @@ -960,7 +955,6 @@ static void via_sdc_timeout(struct timer_list *t) } } - mmiowb(); spin_unlock_irqrestore(&sdhost->lock, flags); } @@ -1012,7 +1006,6 @@ static void via_sdc_card_detect(struct work_struct *work) tasklet_schedule(&host->finish_tasklet); } - mmiowb(); spin_unlock_irqrestore(&host->lock, flags); via_reset_pcictrl(host); @@ -1020,7 +1013,6 @@ static void via_sdc_card_detect(struct work_struct *work) spin_lock_irqsave(&host->lock, flags); } - mmiowb(); spin_unlock_irqrestore(&host->lock, flags); via_print_pcictrl(host); @@ -1188,7 +1180,6 @@ static void via_sd_remove(struct pci_dev *pcidev) /* Disable generating further interrupts */ writeb(0x0, sdhost->pcictrl_mmiobase + VIA_CRDR_PCIINTCTRL); - mmiowb(); if (sdhost->mrq) { pr_err("%s: Controller removed during " @@ -1197,7 +1188,6 @@ static void via_sd_remove(struct pci_dev *pcidev) /* make sure all DMA is stopped */ writel(VIA_CRDR_DMACTRL_SFTRST, sdhost->ddma_mmiobase + VIA_CRDR_DMACTRL); - mmiowb(); sdhost->mrq->cmd->error = -ENOMEDIUM; if (sdhost->mrq->stop) sdhost->mrq->stop->error = -ENOMEDIUM; diff --git a/drivers/mtd/nand/raw/r852.c b/drivers/mtd/nand/raw/r852.c index 86456216fb93..7b99831aa046 100644 --- a/drivers/mtd/nand/raw/r852.c +++ b/drivers/mtd/nand/raw/r852.c @@ -45,7 +45,6 @@ static inline void r852_write_reg(struct r852_device *dev, int address, uint8_t value) { writeb(value, dev->mmio + address); - mmiowb(); } @@ -61,7 +60,6 @@ static inline void r852_write_reg_dword(struct r852_device *dev, int address, uint32_t value) { writel(cpu_to_le32(value), dev->mmio + address); - mmiowb(); } /* returns pointer to our private structure */ diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c index ddf0420c0997..97978227aa55 100644 --- a/drivers/mtd/nand/raw/txx9ndfmc.c +++ b/drivers/mtd/nand/raw/txx9ndfmc.c @@ -159,7 +159,6 @@ static void txx9ndfmc_cmd_ctrl(struct nand_chip *chip, int cmd, if ((ctrl & NAND_CTRL_CHANGE) && cmd == NAND_CMD_NONE) txx9ndfmc_write(dev, 0, TXX9_NDFDTR); } - mmiowb(); } static int txx9ndfmc_dev_ready(struct nand_chip *chip) diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c index 47e5984f16fb..3155f7fa83eb 100644 --- a/drivers/net/ethernet/aeroflex/greth.c +++ b/drivers/net/ethernet/aeroflex/greth.c @@ -613,7 +613,6 @@ static irqreturn_t greth_interrupt(int irq, void *dev_id) napi_schedule(&greth->napi); } - mmiowb(); spin_unlock(&greth->devlock); return retval; diff --git a/drivers/net/ethernet/alacritech/slicoss.c b/drivers/net/ethernet/alacritech/slicoss.c index 16477aa6d61f..4f7e792e50e9 100644 --- a/drivers/net/ethernet/alacritech/slicoss.c +++ b/drivers/net/ethernet/alacritech/slicoss.c @@ -345,8 +345,6 @@ static void slic_set_rx_mode(struct net_device *dev) if (sdev->promisc != set_promisc) { sdev->promisc = set_promisc; slic_configure_rcv(sdev); - /* make sure writes to receiver cant leak out of the lock */ - mmiowb(); } spin_unlock_bh(&sdev->link_lock); } @@ -1461,8 +1459,6 @@ static netdev_tx_t slic_xmit(struct sk_buff *skb, struct net_device *dev) if (slic_get_free_tx_descs(txq) < SLIC_MAX_REQ_TX_DESCS) netif_stop_queue(dev); - /* make sure writes to io-memory cant leak out of tx queue lock */ - mmiowb(); return NETDEV_TX_OK; drop_skb: diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index b17d435de09f..05798aa5bb73 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -2016,7 +2016,6 @@ void ena_com_aenq_intr_handler(struct ena_com_dev *dev, void *data) mb(); writel_relaxed((u32)aenq->head, dev->reg_bar + ENA_REGS_AENQ_HEAD_DB_OFF); - mmiowb(); } int ena_com_dev_reset(struct ena_com_dev *ena_dev, diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c index 9e07b469066a..f7583c5d9509 100644 --- a/drivers/net/ethernet/atheros/atlx/atl1.c +++ b/drivers/net/ethernet/atheros/atlx/atl1.c @@ -2439,7 +2439,6 @@ static netdev_tx_t atl1_xmit_frame(struct sk_buff *skb, atl1_tx_map(adapter, skb, ptpd); atl1_tx_queue(adapter, count, ptpd); atl1_update_mailbox(adapter); - mmiowb(); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c index d99317b3d891..1474cac7e892 100644 --- a/drivers/net/ethernet/atheros/atlx/atl2.c +++ b/drivers/net/ethernet/atheros/atlx/atl2.c @@ -908,7 +908,6 @@ static netdev_tx_t atl2_xmit_frame(struct sk_buff *skb, ATL2_WRITE_REGW(&adapter->hw, REG_MB_TXD_WR_IDX, (adapter->txd_write_ptr >> 2)); - mmiowb(); dev_consume_skb_any(skb); return NETDEV_TX_OK; } diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index d63371d70bce..dfdd14eadd57 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -3305,8 +3305,6 @@ next_rx: BNX2_WR(bp, rxr->rx_bseq_addr, rxr->rx_prod_bseq); - mmiowb(); - return rx_pkt; } @@ -6723,8 +6721,6 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev) BNX2_WR16(bp, txr->tx_bidx_addr, prod); BNX2_WR(bp, txr->tx_bseq_addr, txr->tx_prod_bseq); - mmiowb(); - txr->tx_prod = prod; if (unlikely(bnx2_tx_avail(bp, txr) <= MAX_SKB_FRAGS)) { diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index ecb1bd7eb508..0c8f5b546c6f 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -4166,8 +4166,6 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev) DOORBELL_RELAXED(bp, txdata->cid, txdata->tx_db.raw); - mmiowb(); - txdata->tx_bd_prod += nbd; if (unlikely(bnx2x_tx_avail(bp, txdata) < MAX_DESC_PER_TX_PKT)) { diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index 1ed068509337..2d57af9c061c 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -527,8 +527,6 @@ static inline void bnx2x_update_rx_prod(struct bnx2x *bp, REG_WR_RELAXED(bp, fp->ustorm_rx_prods_offset + i * 4, ((u32 *)&rx_prods)[i]); - mmiowb(); - DP(NETIF_MSG_RX_STATUS, "queue[%d]: wrote bd_prod %u cqe_prod %u sge_prod %u\n", fp->index, bd_prod, rx_comp_prod, rx_sge_prod); @@ -653,7 +651,6 @@ static inline void bnx2x_igu_ack_sb_gen(struct bnx2x *bp, u8 igu_sb_id, REG_WR(bp, igu_addr, cmd_data.sb_id_and_flags); /* Make sure that ACK is written */ - mmiowb(); barrier(); } @@ -674,7 +671,6 @@ static inline void bnx2x_hc_ack_sb(struct bnx2x *bp, u8 sb_id, REG_WR(bp, hc_addr, (*(u32 *)&igu_ack)); /* Make sure that ACK is written */ - mmiowb(); barrier(); } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index 749d0ef44371..0745cccd416d 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -2623,7 +2623,6 @@ static int bnx2x_run_loopback(struct bnx2x *bp, int loopback_mode) wmb(); DOORBELL_RELAXED(bp, txdata->cid, txdata->tx_db.raw); - mmiowb(); barrier(); num_pkts++; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index e46786a56b0c..3716c828ff5d 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -869,9 +869,6 @@ static void bnx2x_hc_int_disable(struct bnx2x *bp) "write %x to HC %d (addr 0x%x)\n", val, port, addr); - /* flush all outstanding writes */ - mmiowb(); - REG_WR(bp, addr, val); if (REG_RD(bp, addr) != val) BNX2X_ERR("BUG! Proper val not read from IGU!\n"); @@ -887,9 +884,6 @@ static void bnx2x_igu_int_disable(struct bnx2x *bp) DP(NETIF_MSG_IFDOWN, "write %x to IGU\n", val); - /* flush all outstanding writes */ - mmiowb(); - REG_WR(bp, IGU_REG_PF_CONFIGURATION, val); if (REG_RD(bp, IGU_REG_PF_CONFIGURATION) != val) BNX2X_ERR("BUG! Proper val not read from IGU!\n"); @@ -1595,7 +1589,6 @@ static void bnx2x_hc_int_enable(struct bnx2x *bp) /* * Ensure that HC_CONFIG is written before leading/trailing edge config */ - mmiowb(); barrier(); if (!CHIP_IS_E1(bp)) { @@ -1611,9 +1604,6 @@ static void bnx2x_hc_int_enable(struct bnx2x *bp) REG_WR(bp, HC_REG_TRAILING_EDGE_0 + port*8, val); REG_WR(bp, HC_REG_LEADING_EDGE_0 + port*8, val); } - - /* Make sure that interrupts are indeed enabled from here on */ - mmiowb(); } static void bnx2x_igu_int_enable(struct bnx2x *bp) @@ -1674,9 +1664,6 @@ static void bnx2x_igu_int_enable(struct bnx2x *bp) REG_WR(bp, IGU_REG_TRAILING_EDGE_LATCH, val); REG_WR(bp, IGU_REG_LEADING_EDGE_LATCH, val); - - /* Make sure that interrupts are indeed enabled from here on */ - mmiowb(); } void bnx2x_int_enable(struct bnx2x *bp) @@ -3833,7 +3820,6 @@ static void bnx2x_sp_prod_update(struct bnx2x *bp) REG_WR16_RELAXED(bp, BAR_XSTRORM_INTMEM + XSTORM_SPQ_PROD_OFFSET(func), bp->spq_prod_idx); - mmiowb(); } /** @@ -5244,7 +5230,6 @@ static void bnx2x_update_eq_prod(struct bnx2x *bp, u16 prod) { /* No memory barriers */ storm_memset_eq_prod(bp, prod, BP_FUNC(bp)); - mmiowb(); } static int bnx2x_cnic_handle_cfc_del(struct bnx2x *bp, u32 cid, @@ -6513,7 +6498,6 @@ void bnx2x_nic_init_cnic(struct bnx2x *bp) /* flush all */ mb(); - mmiowb(); } void bnx2x_pre_irq_nic_init(struct bnx2x *bp) @@ -6553,7 +6537,6 @@ void bnx2x_post_irq_nic_init(struct bnx2x *bp, u32 load_code) /* flush all before enabling interrupts */ mb(); - mmiowb(); bnx2x_int_enable(bp); @@ -7775,12 +7758,10 @@ void bnx2x_igu_clear_sb_gen(struct bnx2x *bp, u8 func, u8 idu_sb_id, bool is_pf) DP(NETIF_MSG_HW, "write 0x%08x to IGU(via GRC) addr 0x%x\n", data, igu_addr_data); REG_WR(bp, igu_addr_data, data); - mmiowb(); barrier(); DP(NETIF_MSG_HW, "write 0x%08x to IGU(via GRC) addr 0x%x\n", ctl, igu_addr_ctl); REG_WR(bp, igu_addr_ctl, ctl); - mmiowb(); barrier(); /* wait for clean up to finish */ @@ -9550,7 +9531,6 @@ static void bnx2x_set_234_gates(struct bnx2x *bp, bool close) DP(NETIF_MSG_HW | NETIF_MSG_IFUP, "%s gates #2, #3 and #4\n", close ? "closing" : "opening"); - mmiowb(); } #define SHARED_MF_CLP_MAGIC 0x80000000 /* `magic' bit */ @@ -9674,7 +9654,6 @@ static void bnx2x_pxp_prep(struct bnx2x *bp) if (!CHIP_IS_E1(bp)) { REG_WR(bp, PXP2_REG_RD_START_INIT, 0); REG_WR(bp, PXP2_REG_RQ_RBC_DONE, 0); - mmiowb(); } } @@ -9774,16 +9753,13 @@ static void bnx2x_process_kill_chip_reset(struct bnx2x *bp, bool global) reset_mask1 & (~not_reset_mask1)); barrier(); - mmiowb(); REG_WR(bp, GRCBASE_MISC + MISC_REGISTERS_RESET_REG_2_SET, reset_mask2 & (~stay_reset2)); barrier(); - mmiowb(); REG_WR(bp, GRCBASE_MISC + MISC_REGISTERS_RESET_REG_1_SET, reset_mask1); - mmiowb(); } /** @@ -9867,9 +9843,6 @@ static int bnx2x_process_kill(struct bnx2x *bp, bool global) REG_WR(bp, MISC_REG_UNPREPARED, 0); barrier(); - /* Make sure all is written to the chip before the reset */ - mmiowb(); - /* Wait for 1ms to empty GLUE and PCI-E core queues, * PSWHST, GRC and PSWRD Tetris buffer. */ @@ -14828,7 +14801,6 @@ static int bnx2x_drv_ctl(struct net_device *dev, struct drv_ctl_info *ctl) if (rc) break; - mmiowb(); barrier(); /* Start accepting on iSCSI L2 ring */ @@ -14863,7 +14835,6 @@ static int bnx2x_drv_ctl(struct net_device *dev, struct drv_ctl_info *ctl) if (!bnx2x_wait_sp_comp(bp, sp_bits)) BNX2X_ERR("rx_mode completion timed out!\n"); - mmiowb(); barrier(); /* Unset iSCSI L2 MAC */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c index 7b22a6d8514c..80d250a6d048 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c @@ -5039,7 +5039,6 @@ static inline int bnx2x_q_init(struct bnx2x *bp, /* As no ramrod is sent, complete the command immediately */ o->complete_cmd(bp, o, BNX2X_Q_CMD_INIT); - mmiowb(); smp_mb(); return 0; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index c97b642e6537..0edbb0a76847 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -100,13 +100,11 @@ static void bnx2x_vf_igu_ack_sb(struct bnx2x *bp, struct bnx2x_virtf *vf, DP(NETIF_MSG_HW, "write 0x%08x to IGU(via GRC) addr 0x%x\n", cmd_data.sb_id_and_flags, igu_addr_data); REG_WR(bp, igu_addr_data, cmd_data.sb_id_and_flags); - mmiowb(); barrier(); DP(NETIF_MSG_HW, "write 0x%08x to IGU(via GRC) addr 0x%x\n", ctl, igu_addr_ctl); REG_WR(bp, igu_addr_ctl, ctl); - mmiowb(); barrier(); } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c index a9bdc21873d3..672b57f0b84d 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c @@ -172,8 +172,6 @@ static int bnx2x_send_msg2pf(struct bnx2x *bp, u8 *done, dma_addr_t msg_mapping) /* Trigger the PF FW */ writeb_relaxed(1, &zone_data->trigger.vf_pf_channel.addr_valid); - mmiowb(); - /* Wait for PF to complete */ while ((tout >= 0) && (!*done)) { msleep(interval); @@ -1179,7 +1177,6 @@ static void bnx2x_vf_mbx_resp_send_msg(struct bnx2x *bp, /* ack the FW */ storm_memset_vf_mbx_ack(bp, vf->abs_vfid); - mmiowb(); /* copy the response header including status-done field, * must be last dmae, must be after FW is acked @@ -2174,7 +2171,6 @@ static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf, */ storm_memset_vf_mbx_ack(bp, vf->abs_vfid); /* Firmware ack should be written before unlocking channel */ - mmiowb(); bnx2x_unlock_vf_pf_channel(bp, vf, mbx->first_tlv.tl.type); } } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 0bb9d7b3a2b6..b8b68d408ad0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -556,8 +556,6 @@ normal_tx: tx_done: - mmiowb(); - if (unlikely(bnxt_tx_avail(bp, txr) <= MAX_SKB_FRAGS + 1)) { if (skb->xmit_more && !tx_buf->is_push) bnxt_db_write(bp, &txr->tx_db, prod); @@ -2123,7 +2121,6 @@ static int bnxt_poll(struct napi_struct *napi, int budget) &dim_sample); net_dim(&cpr->dim, dim_sample); } - mmiowb(); return work_done; } diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 328373e0578f..821bccc0915c 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -1073,7 +1073,6 @@ static void tg3_int_reenable(struct tg3_napi *tnapi) struct tg3 *tp = tnapi->tp; tw32_mailbox(tnapi->int_mbox, tnapi->last_tag << 24); - mmiowb(); /* When doing tagged status, this work check is unnecessary. * The last_tag we write above tells the chip which piece of @@ -6999,7 +6998,6 @@ next_pkt_nopost: tw32_rx_mbox(TG3_RX_JMB_PROD_IDX_REG, tpr->rx_jmb_prod_idx); } - mmiowb(); } else if (work_mask) { /* rx_std_buffers[] and rx_jmb_buffers[] entries must be * updated before the producer indices can be updated. @@ -7210,8 +7208,6 @@ static int tg3_poll_work(struct tg3_napi *tnapi, int work_done, int budget) tw32_rx_mbox(TG3_RX_JMB_PROD_IDX_REG, dpr->rx_jmb_prod_idx); - mmiowb(); - if (err) tw32_f(HOSTCC_MODE, tp->coal_now); } @@ -7278,7 +7274,6 @@ static int tg3_poll_msix(struct napi_struct *napi, int budget) HOSTCC_MODE_ENABLE | tnapi->coal_now); } - mmiowb(); break; } } @@ -8159,7 +8154,6 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev) if (!skb->xmit_more || netif_xmit_stopped(txq)) { /* Packets are ready, update Tx producer idx on card. */ tw32_tx_mbox(tnapi->prodmbox, entry); - mmiowb(); } return NETDEV_TX_OK; diff --git a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c index 2df7440f58df..39643be8c30a 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c +++ b/drivers/net/ethernet/cavium/liquidio/cn66xx_device.c @@ -38,9 +38,6 @@ int lio_cn6xxx_soft_reset(struct octeon_device *oct) lio_pci_readq(oct, CN6XXX_CIU_SOFT_RST); lio_pci_writeq(oct, 1, CN6XXX_CIU_SOFT_RST); - /* make sure that the reset is written before starting timer */ - mmiowb(); - /* Wait for 10ms as Octeon resets. */ mdelay(100); @@ -487,9 +484,6 @@ void lio_cn6xxx_disable_interrupt(struct octeon_device *oct, /* Disable Interrupts */ writeq(0, cn6xxx->intr_enb_reg64); - - /* make sure interrupts are really disabled */ - mmiowb(); } static void lio_cn6xxx_get_pcie_qlmport(struct octeon_device *oct) @@ -555,10 +549,6 @@ static int lio_cn6xxx_process_droq_intr_regs(struct octeon_device *oct) value &= ~(1 << oq_no); octeon_write_csr(oct, reg, value); - /* Ensure that the enable register is written. - */ - mmiowb(); - spin_unlock(&cn6xxx->lock_for_droq_int_enb_reg); } } diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c index ce8c3f818666..934115d18488 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c @@ -1449,7 +1449,6 @@ void lio_enable_irq(struct octeon_droq *droq, struct octeon_instr_queue *iq) iq->pkt_in_done -= iq->pkts_processed; iq->pkts_processed = 0; /* this write needs to be flushed before we release the lock */ - mmiowb(); spin_unlock_bh(&iq->lock); oct = iq->oct_dev; } diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c index a0c099f71524..017169023cca 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_droq.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_droq.c @@ -513,8 +513,6 @@ int octeon_retry_droq_refill(struct octeon_droq *droq) */ wmb(); writel(desc_refilled, droq->pkts_credit_reg); - /* make sure mmio write completes */ - mmiowb(); if (pkts_credit + desc_refilled >= CN23XX_SLI_DEF_BP) reschedule = 0; @@ -712,8 +710,6 @@ octeon_droq_fast_process_packets(struct octeon_device *oct, */ wmb(); writel(desc_refilled, droq->pkts_credit_reg); - /* make sure mmio write completes */ - mmiowb(); } } } /* for (each packet)... */ diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c index c6f4cbda040f..fcf20a8f92d9 100644 --- a/drivers/net/ethernet/cavium/liquidio/request_manager.c +++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c @@ -278,7 +278,6 @@ ring_doorbell(struct octeon_device *oct, struct octeon_instr_queue *iq) if (atomic_read(&oct->status) == OCT_DEV_RUNNING) { writel(iq->fill_cnt, iq->doorbell_reg); /* make sure doorbell write goes through */ - mmiowb(); iq->fill_cnt = 0; iq->last_db_time = jiffies; return; diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 8fe9af0e2ab7..466bf1ea186d 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -3270,11 +3270,6 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb, if (!skb->xmit_more || netif_xmit_stopped(netdev_get_tx_queue(netdev, 0))) { writel(tx_ring->next_to_use, hw->hw_addr + tx_ring->tdt); - /* we need this if more than one processor can write to - * our tail at a time, it synchronizes IO on IA64/Altix - * systems - */ - mmiowb(); } } else { dev_kfree_skb_any(skb); diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 7acc61e4f645..022c3ac0e40f 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -3816,7 +3816,6 @@ static void e1000_flush_tx_ring(struct e1000_adapter *adapter) if (tx_ring->next_to_use == tx_ring->count) tx_ring->next_to_use = 0; ew32(TDT(0), tx_ring->next_to_use); - mmiowb(); usleep_range(200, 250); } @@ -5904,12 +5903,6 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb, tx_ring->next_to_use); else writel(tx_ring->next_to_use, tx_ring->tail); - - /* we need this if more than one processor can write - * to our tail at a time, it synchronizes IO on - *IA64/Altix systems - */ - mmiowb(); } } else { dev_kfree_skb_any(skb); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c index 5d4f1761dc0c..8de77155f2e7 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c @@ -321,8 +321,6 @@ static void fm10k_mask_aer_comp_abort(struct pci_dev *pdev) pci_read_config_dword(pdev, pos + PCI_ERR_UNCOR_MASK, &err_mask); err_mask |= PCI_ERR_UNC_COMP_ABORT; pci_write_config_dword(pdev, pos + PCI_ERR_UNCOR_MASK, err_mask); - - mmiowb(); } int fm10k_iov_resume(struct pci_dev *pdev) diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 5a0419421511..1f48298f01e6 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -1037,11 +1037,6 @@ static void fm10k_tx_map(struct fm10k_ring *tx_ring, /* notify HW of packet */ if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { writel(i, tx_ring->tail); - - /* we need this if more than one processor can write to our tail - * at a time, it synchronizes IO on IA64/Altix systems - */ - mmiowb(); } return; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 6c97667d20ef..ffb611bbedfa 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -3471,11 +3471,6 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, /* notify HW of packet */ if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { writel(i, tx_ring->tail); - - /* we need this if more than one processor can write to our tail - * at a time, it synchronizes IO on IA64/Altix systems - */ - mmiowb(); } return 0; diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index 9b4d7cec2e18..6bfef82e7607 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -2360,11 +2360,6 @@ static inline void iavf_tx_map(struct iavf_ring *tx_ring, struct sk_buff *skb, /* notify HW of packet */ if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { writel(i, tx_ring->tail); - - /* we need this if more than one processor can write to our tail - * at a time, it synchronizes IO on IA64/Altix systems - */ - mmiowb(); } return; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index c289d97f477d..1af21bbe180e 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -1356,11 +1356,6 @@ ice_tx_map(struct ice_ring *tx_ring, struct ice_tx_buf *first, /* notify HW of packet */ if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { writel(i, tx_ring->tail); - - /* we need this if more than one processor can write to our tail - * at a time, it synchronizes IO on IA64/Altix systems - */ - mmiowb(); } return; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 69b230c53fed..09ba94496742 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -6028,11 +6028,6 @@ static int igb_tx_map(struct igb_ring *tx_ring, if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { writel(i, tx_ring->tail); - - /* we need this if more than one processor can write to our tail - * at a time, it synchronizes IO on IA64/Altix systems - */ - mmiowb(); } return 0; diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 4eab83faec62..34cd30d7162f 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -2279,10 +2279,6 @@ static inline void igbvf_tx_queue_adv(struct igbvf_adapter *adapter, tx_ring->buffer_info[first].next_to_watch = tx_desc; tx_ring->next_to_use = i; writel(i, adapter->hw.hw_addr + tx_ring->tail); - /* we need this if more than one processor can write to our tail - * at a time, it synchronizes IO on IA64/Altix systems - */ - mmiowb(); } static netdev_tx_t igbvf_xmit_frame_ring_adv(struct sk_buff *skb, diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 87a11879bf2d..f8d692f6aa4f 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -892,11 +892,6 @@ static int igc_tx_map(struct igc_ring *tx_ring, if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { writel(i, tx_ring->tail); - - /* we need this if more than one processor can write to our tail - * at a time, it synchronizes IO on IA64/Altix systems - */ - mmiowb(); } return 0; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index e100054a3765..99e23cf6a73a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -8299,11 +8299,6 @@ static int ixgbe_tx_map(struct ixgbe_ring *tx_ring, if (netif_xmit_stopped(txring_txq(tx_ring)) || !skb->xmit_more) { writel(i, tx_ring->tail); - - /* we need this if more than one processor can write to our tail - * at a time, it synchronizes IO on IA64/Altix systems - */ - mmiowb(); } return 0; diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index 8b3495ee2b6e..49486c10ef81 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -1139,9 +1139,6 @@ static inline void sky2_put_idx(struct sky2_hw *hw, unsigned q, u16 idx) /* Make sure write' to descriptors are complete before we tell hardware */ wmb(); sky2_write16(hw, Y2_QADDR(q, PREF_UNIT_PUT_IDX), idx); - - /* Synchronize I/O on since next processor may write to tail */ - mmiowb(); } @@ -1354,7 +1351,6 @@ stopped: /* reset the Rx prefetch unit */ sky2_write32(hw, Y2_QADDR(rxq, PREF_UNIT_CTRL), PREF_UNIT_RST_SET); - mmiowb(); } /* Clean out receive buffer area, assumes receiver hardware stopped */ diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c index c81d15bf259c..87e90b5d4d7d 100644 --- a/drivers/net/ethernet/mellanox/mlx4/catas.c +++ b/drivers/net/ethernet/mellanox/mlx4/catas.c @@ -129,10 +129,6 @@ static int mlx4_reset_slave(struct mlx4_dev *dev) comm_flags = rst_req << COM_CHAN_RST_REQ_OFFSET; __raw_writel((__force u32)cpu_to_be32(comm_flags), (__iomem char *)priv->mfunc.comm + MLX4_COMM_CHAN_FLAGS); - /* Make sure that our comm channel write doesn't - * get mixed in with writes from another CPU. - */ - mmiowb(); end = msecs_to_jiffies(MLX4_COMM_TIME) + jiffies; while (time_before(jiffies, end)) { diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index a5d5d6fc1da0..c678344d22a2 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -281,7 +281,6 @@ static int mlx4_comm_cmd_post(struct mlx4_dev *dev, u8 cmd, u16 param) val = param | (cmd << 16) | (priv->cmd.comm_toggle << 31); __raw_writel((__force u32) cpu_to_be32(val), &priv->mfunc.comm->slave_write); - mmiowb(); mutex_unlock(&dev->persist->device_state_mutex); return 0; } @@ -496,12 +495,6 @@ static int mlx4_cmd_post(struct mlx4_dev *dev, u64 in_param, u64 out_param, (op_modifier << HCR_OPMOD_SHIFT) | op), hcr + 6); - /* - * Make sure that our HCR writes don't get mixed in with - * writes from another CPU starting a FW command. - */ - mmiowb(); - cmd->toggle = cmd->toggle ^ 1; ret = 0; @@ -2206,7 +2199,6 @@ static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd, } __raw_writel((__force u32) cpu_to_be32(reply), &priv->mfunc.comm[slave].slave_read); - mmiowb(); return; @@ -2410,7 +2402,6 @@ int mlx4_multi_func_init(struct mlx4_dev *dev) &priv->mfunc.comm[i].slave_write); __raw_writel((__force u32) 0, &priv->mfunc.comm[i].slave_read); - mmiowb(); for (port = 1; port <= MLX4_MAX_PORTS; port++) { struct mlx4_vport_state *admin_vport; struct mlx4_vport_state *oper_vport; @@ -2576,10 +2567,6 @@ void mlx4_report_internal_err_comm_event(struct mlx4_dev *dev) slave_read |= (u32)COMM_CHAN_EVENT_INTERNAL_ERR; __raw_writel((__force u32)cpu_to_be32(slave_read), &priv->mfunc.comm[slave].slave_read); - /* Make sure that our comm channel write doesn't - * get mixed in with writes from another CPU. - */ - mmiowb(); } } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index be48c6440251..c087d1014b09 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -917,7 +917,6 @@ static void cmd_work_handler(struct work_struct *work) mlx5_core_dbg(dev, "writing 0x%x to command doorbell\n", 1 << ent->idx); wmb(); iowrite32be(1 << ent->idx, &dev->iseg->cmd_dbell); - mmiowb(); /* if not in polling don't use ent after this point */ if (cmd_mode == CMD_MODE_POLLING || poll_cmd) { poll_timeout(ent); diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index e0340f778d8f..d8b7fba96d58 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -1439,7 +1439,6 @@ myri10ge_tx_done(struct myri10ge_slice_state *ss, int mcp_index) tx->queue_active = 0; put_be32(htonl(1), tx->send_stop); mb(); - mmiowb(); } __netif_tx_unlock(dev_queue); } @@ -2861,7 +2860,6 @@ again: tx->queue_active = 1; put_be32(htonl(1), tx->send_go); mb(); - mmiowb(); } tx->pkt_start++; if ((avail - count) < MXGEFW_MAX_SEND_DESC) { diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c index feda9644289d..3b2ae1a21678 100644 --- a/drivers/net/ethernet/neterion/s2io.c +++ b/drivers/net/ethernet/neterion/s2io.c @@ -4153,8 +4153,6 @@ static netdev_tx_t s2io_xmit(struct sk_buff *skb, struct net_device *dev) writeq(val64, &tx_fifo->List_Control); - mmiowb(); - put_off++; if (put_off == fifo->tx_curr_put_info.fifo_len + 1) put_off = 0; diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c index b877acec5cde..1d334f2e0a56 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-main.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c @@ -1826,7 +1826,6 @@ static int vxge_poll_msix(struct napi_struct *napi, int budget) vxge_hw_channel_msix_unmask( (struct __vxge_hw_channel *)ring->handle, ring->rx_vector_no); - mmiowb(); } /* We are copying and returning the local variable, in case if after @@ -2234,8 +2233,6 @@ static irqreturn_t vxge_tx_msix_handle(int irq, void *dev_id) vxge_hw_channel_msix_unmask((struct __vxge_hw_channel *)fifo->handle, fifo->tx_vector_no); - mmiowb(); - return IRQ_HANDLED; } @@ -2272,14 +2269,12 @@ vxge_alarm_msix_handle(int irq, void *dev_id) */ vxge_hw_vpath_msix_mask(vdev->vpaths[i].handle, msix_id); vxge_hw_vpath_msix_clear(vdev->vpaths[i].handle, msix_id); - mmiowb(); status = vxge_hw_vpath_alarm_process(vdev->vpaths[i].handle, vdev->exec_mode); if (status == VXGE_HW_OK) { vxge_hw_vpath_msix_unmask(vdev->vpaths[i].handle, msix_id); - mmiowb(); continue; } vxge_debug_intr(VXGE_ERR, diff --git a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c index 59e77e3086bb..709d20d9938f 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-traffic.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-traffic.c @@ -1399,11 +1399,7 @@ static void __vxge_hw_non_offload_db_post(struct __vxge_hw_fifo *fifo, VXGE_HW_NODBW_GET_NO_SNOOP(no_snoop), &fifo->nofl_db->control_0); - mmiowb(); - writeq(txdl_ptr, &fifo->nofl_db->txdl_ptr); - - mmiowb(); } /** diff --git a/drivers/net/ethernet/qlogic/qed/qed_int.c b/drivers/net/ethernet/qlogic/qed/qed_int.c index e23980e301b6..69e6a90edf2f 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_int.c +++ b/drivers/net/ethernet/qlogic/qed/qed_int.c @@ -774,18 +774,12 @@ static inline u16 qed_attn_update_idx(struct qed_hwfn *p_hwfn, { u16 rc = 0, index; - /* Make certain HW write took affect */ - mmiowb(); - index = le16_to_cpu(p_sb_desc->sb_attn->sb_index); if (p_sb_desc->index != index) { p_sb_desc->index = index; rc = QED_SB_ATT_IDX; } - /* Make certain we got a consistent view with HW */ - mmiowb(); - return rc; } @@ -1170,7 +1164,6 @@ static void qed_sb_ack_attn(struct qed_hwfn *p_hwfn, /* Both segments (interrupts & acks) are written to same place address; * Need to guarantee all commands will be received (in-order) by HW. */ - mmiowb(); barrier(); } @@ -1805,9 +1798,6 @@ static void qed_int_igu_enable_attn(struct qed_hwfn *p_hwfn, qed_wr(p_hwfn, p_ptt, IGU_REG_TRAILING_EDGE_LATCH, 0xfff); qed_wr(p_hwfn, p_ptt, IGU_REG_ATTENTION_ENABLE, 0xfff); - /* Flush the writes to IGU */ - mmiowb(); - /* Unmask AEU signals toward IGU */ qed_wr(p_hwfn, p_ptt, MISC_REG_AEU_MASK_ATTN_IGU, 0xff); } @@ -1871,9 +1861,6 @@ static void qed_int_igu_cleanup_sb(struct qed_hwfn *p_hwfn, qed_wr(p_hwfn, p_ptt, IGU_REG_COMMAND_REG_CTRL, cmd_ctrl); - /* Flush the write to IGU */ - mmiowb(); - /* calculate where to read the status bit from */ sb_bit = 1 << (igu_sb_id % 32); sb_bit_addr = igu_sb_id / 32 * sizeof(u32); diff --git a/drivers/net/ethernet/qlogic/qed/qed_spq.c b/drivers/net/ethernet/qlogic/qed/qed_spq.c index 79b311b86f66..f5f3c03b9dd2 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_spq.c +++ b/drivers/net/ethernet/qlogic/qed/qed_spq.c @@ -341,9 +341,6 @@ void qed_eq_prod_update(struct qed_hwfn *p_hwfn, u16 prod) USTORM_EQE_CONS_OFFSET(p_hwfn->rel_pf_id); REG_WR16(p_hwfn, addr, prod); - - /* keep prod updates ordered */ - mmiowb(); } int qed_eq_completion(struct qed_hwfn *p_hwfn, void *cookie) diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index b4c8949933f1..4555c0b161ef 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -1526,14 +1526,6 @@ static int qede_selftest_transmit_traffic(struct qede_dev *edev, barrier(); writel(txq->tx_db.raw, txq->doorbell_addr); - /* mmiowb is needed to synchronize doorbell writes from more than one - * processor. It guarantees that the write arrives to the device before - * the queue lock is released and another start_xmit is called (possibly - * on another CPU). Without this barrier, the next doorbell can bypass - * this doorbell. This is applicable to IA64/Altix systems. - */ - mmiowb(); - for (i = 0; i < QEDE_SELFTEST_POLL_COUNT; i++) { if (qede_txq_has_work(txq)) break; diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index 31b046e24565..6f7e3622c6b4 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -580,14 +580,6 @@ void qede_update_rx_prod(struct qede_dev *edev, struct qede_rx_queue *rxq) internal_ram_wr(rxq->hw_rxq_prod_addr, sizeof(rx_prods), (u32 *)&rx_prods); - - /* mmiowb is needed to synchronize doorbell writes from more than one - * processor. It guarantees that the write arrives to the device before - * the napi lock is released and another qede_poll is called (possibly - * on another CPU). Without this barrier, the next doorbell can bypass - * this doorbell. This is applicable to IA64/Altix systems. - */ - mmiowb(); } static void qede_get_rxhash(struct sk_buff *skb, u8 bitfields, __le32 rss_hash) diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c index b61b88cbc0c7..457444894d80 100644 --- a/drivers/net/ethernet/qlogic/qla3xxx.c +++ b/drivers/net/ethernet/qlogic/qla3xxx.c @@ -1858,7 +1858,6 @@ static void ql_update_small_bufq_prod_index(struct ql3_adapter *qdev) wmb(); writel_relaxed(qdev->small_buf_q_producer_index, &port_regs->CommonRegs.rxSmallQProducerIndex); - mmiowb(); } } diff --git a/drivers/net/ethernet/qlogic/qlge/qlge.h b/drivers/net/ethernet/qlogic/qlge/qlge.h index 3e71b65a9546..ad7c5eb8a3b6 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge.h +++ b/drivers/net/ethernet/qlogic/qlge/qlge.h @@ -2181,7 +2181,6 @@ static inline void ql_write32(const struct ql_adapter *qdev, int reg, u32 val) static inline void ql_write_db_reg(u32 val, void __iomem *addr) { writel(val, addr); - mmiowb(); } /* diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c index 07e1c623048e..6cae33072496 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c +++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c @@ -2695,7 +2695,6 @@ static netdev_tx_t qlge_send(struct sk_buff *skb, struct net_device *ndev) wmb(); ql_write_db_reg_relaxed(tx_ring->prod_idx, tx_ring->prod_idx_db_reg); - mmiowb(); netif_printk(qdev, tx_queued, KERN_DEBUG, qdev->ndev, "tx queued, slot %d, len %d\n", tx_ring->prod_idx, skb->len); diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 8154b38c08f7..316b47741d3f 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -728,7 +728,6 @@ static irqreturn_t ravb_emac_interrupt(int irq, void *dev_id) spin_lock(&priv->lock); ravb_emac_interrupt_unlocked(ndev); - mmiowb(); spin_unlock(&priv->lock); return IRQ_HANDLED; } @@ -848,7 +847,6 @@ static irqreturn_t ravb_interrupt(int irq, void *dev_id) result = IRQ_HANDLED; } - mmiowb(); spin_unlock(&priv->lock); return result; } @@ -881,7 +879,6 @@ static irqreturn_t ravb_multi_interrupt(int irq, void *dev_id) result = IRQ_HANDLED; } - mmiowb(); spin_unlock(&priv->lock); return result; } @@ -898,7 +895,6 @@ static irqreturn_t ravb_dma_interrupt(int irq, void *dev_id, int q) if (ravb_queue_interrupt(ndev, q)) result = IRQ_HANDLED; - mmiowb(); spin_unlock(&priv->lock); return result; } @@ -943,7 +939,6 @@ static int ravb_poll(struct napi_struct *napi, int budget) ravb_write(ndev, ~(mask | TIS_RESERVED), TIS); ravb_tx_free(ndev, q, true); netif_wake_subqueue(ndev, q); - mmiowb(); spin_unlock_irqrestore(&priv->lock, flags); } } @@ -959,7 +954,6 @@ static int ravb_poll(struct napi_struct *napi, int budget) ravb_write(ndev, mask, RIE0); ravb_write(ndev, mask, TIE); } - mmiowb(); spin_unlock_irqrestore(&priv->lock, flags); /* Receive error message handling */ @@ -1008,7 +1002,6 @@ static void ravb_adjust_link(struct net_device *ndev) if (priv->no_avb_link && phydev->link) ravb_rcv_snd_enable(ndev); - mmiowb(); spin_unlock_irqrestore(&priv->lock, flags); if (new_state && netif_msg_link(priv)) @@ -1601,7 +1594,6 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev) netif_stop_subqueue(ndev, q); exit: - mmiowb(); spin_unlock_irqrestore(&priv->lock, flags); return NETDEV_TX_OK; @@ -1673,7 +1665,6 @@ static void ravb_set_rx_mode(struct net_device *ndev) spin_lock_irqsave(&priv->lock, flags); ravb_modify(ndev, ECMR, ECMR_PRM, ndev->flags & IFF_PROMISC ? ECMR_PRM : 0); - mmiowb(); spin_unlock_irqrestore(&priv->lock, flags); } diff --git a/drivers/net/ethernet/renesas/ravb_ptp.c b/drivers/net/ethernet/renesas/ravb_ptp.c index dce2a40a31e3..9a42580693cb 100644 --- a/drivers/net/ethernet/renesas/ravb_ptp.c +++ b/drivers/net/ethernet/renesas/ravb_ptp.c @@ -196,7 +196,6 @@ static int ravb_ptp_extts(struct ptp_clock_info *ptp, ravb_write(ndev, GIE_PTCS, GIE); else ravb_write(ndev, GID_PTCD, GID); - mmiowb(); spin_unlock_irqrestore(&priv->lock, flags); return 0; @@ -259,7 +258,6 @@ static int ravb_ptp_perout(struct ptp_clock_info *ptp, else ravb_write(ndev, GID_PTMD0, GID); } - mmiowb(); spin_unlock_irqrestore(&priv->lock, flags); return error; @@ -331,7 +329,6 @@ void ravb_ptp_init(struct net_device *ndev, struct platform_device *pdev) spin_lock_irqsave(&priv->lock, flags); ravb_wait(ndev, GCCR, GCCR_TCR, GCCR_TCR_NOREQ); ravb_modify(ndev, GCCR, GCCR_TCSS, GCCR_TCSS_ADJGPTP); - mmiowb(); spin_unlock_irqrestore(&priv->lock, flags); priv->ptp.clock = ptp_clock_register(&priv->ptp.info, &pdev->dev); diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index e33af371b169..ed30aebdb941 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -2010,7 +2010,6 @@ static void sh_eth_adjust_link(struct net_device *ndev) if ((mdp->cd->no_psr || mdp->no_ether_link) && phydev->link) sh_eth_rcv_snd_enable(ndev); - mmiowb(); spin_unlock_irqrestore(&mdp->lock, flags); if (new_state && netif_msg_link(mdp)) diff --git a/drivers/net/ethernet/sfc/falcon/io.h b/drivers/net/ethernet/sfc/falcon/io.h index 7085ee1d5e2b..c3577643fbda 100644 --- a/drivers/net/ethernet/sfc/falcon/io.h +++ b/drivers/net/ethernet/sfc/falcon/io.h @@ -108,7 +108,6 @@ static inline void ef4_writeo(struct ef4_nic *efx, const ef4_oword_t *value, _ef4_writed(efx, value->u32[2], reg + 8); _ef4_writed(efx, value->u32[3], reg + 12); #endif - mmiowb(); spin_unlock_irqrestore(&efx->biu_lock, flags); } @@ -130,7 +129,6 @@ static inline void ef4_sram_writeq(struct ef4_nic *efx, void __iomem *membase, __raw_writel((__force u32)value->u32[0], membase + addr); __raw_writel((__force u32)value->u32[1], membase + addr + 4); #endif - mmiowb(); spin_unlock_irqrestore(&efx->biu_lock, flags); } diff --git a/drivers/net/ethernet/sfc/io.h b/drivers/net/ethernet/sfc/io.h index 89563170af52..2774a10f44e9 100644 --- a/drivers/net/ethernet/sfc/io.h +++ b/drivers/net/ethernet/sfc/io.h @@ -120,7 +120,6 @@ static inline void efx_writeo(struct efx_nic *efx, const efx_oword_t *value, _efx_writed(efx, value->u32[2], reg + 8); _efx_writed(efx, value->u32[3], reg + 12); #endif - mmiowb(); spin_unlock_irqrestore(&efx->biu_lock, flags); } @@ -142,7 +141,6 @@ static inline void efx_sram_writeq(struct efx_nic *efx, void __iomem *membase, __raw_writel((__force u32)value->u32[0], membase + addr); __raw_writel((__force u32)value->u32[1], membase + addr + 4); #endif - mmiowb(); spin_unlock_irqrestore(&efx->biu_lock, flags); } diff --git a/drivers/net/ethernet/silan/sc92031.c b/drivers/net/ethernet/silan/sc92031.c index c07fd594fe71..db5dc8ce0aff 100644 --- a/drivers/net/ethernet/silan/sc92031.c +++ b/drivers/net/ethernet/silan/sc92031.c @@ -361,7 +361,6 @@ static void sc92031_disable_interrupts(struct net_device *dev) /* stop interrupts */ iowrite32(0, port_base + IntrMask); _sc92031_dummy_read(port_base); - mmiowb(); /* wait for any concurrent interrupt/tasklet to finish */ synchronize_irq(priv->pdev->irq); @@ -379,7 +378,6 @@ static void sc92031_enable_interrupts(struct net_device *dev) wmb(); iowrite32(IntrBits, port_base + IntrMask); - mmiowb(); } static void _sc92031_disable_tx_rx(struct net_device *dev) @@ -867,7 +865,6 @@ out: rmb(); iowrite32(intr_mask, port_base + IntrMask); - mmiowb(); spin_unlock(&priv->lock); } @@ -901,7 +898,6 @@ out_none: rmb(); iowrite32(intr_mask, port_base + IntrMask); - mmiowb(); return IRQ_NONE; } @@ -978,7 +974,6 @@ static netdev_tx_t sc92031_start_xmit(struct sk_buff *skb, iowrite32(priv->tx_bufs_dma_addr + entry * TX_BUF_SIZE, port_base + TxAddr0 + entry * 4); iowrite32(tx_status, port_base + TxStatus0 + entry * 4); - mmiowb(); if (priv->tx_head - priv->tx_tail >= NUM_TX_DESC) netif_stop_queue(dev); @@ -1024,7 +1019,6 @@ static int sc92031_open(struct net_device *dev) spin_lock_bh(&priv->lock); _sc92031_reset(dev); - mmiowb(); spin_unlock_bh(&priv->lock); sc92031_enable_interrupts(dev); @@ -1060,7 +1054,6 @@ static int sc92031_stop(struct net_device *dev) _sc92031_disable_tx_rx(dev); _sc92031_tx_clear(dev); - mmiowb(); spin_unlock_bh(&priv->lock); @@ -1081,7 +1074,6 @@ static void sc92031_set_multicast_list(struct net_device *dev) _sc92031_set_mar(dev); _sc92031_set_rx_config(dev); - mmiowb(); spin_unlock_bh(&priv->lock); } @@ -1098,7 +1090,6 @@ static void sc92031_tx_timeout(struct net_device *dev) priv->tx_timeouts++; _sc92031_reset(dev); - mmiowb(); spin_unlock(&priv->lock); @@ -1140,7 +1131,6 @@ sc92031_ethtool_get_link_ksettings(struct net_device *dev, output_status = _sc92031_mii_read(port_base, MII_OutputStatus); _sc92031_mii_scan(port_base); - mmiowb(); spin_unlock_bh(&priv->lock); @@ -1311,7 +1301,6 @@ static int sc92031_ethtool_set_wol(struct net_device *dev, priv->pm_config = pm_config; iowrite32(pm_config, port_base + PMConfig); - mmiowb(); spin_unlock_bh(&priv->lock); @@ -1337,7 +1326,6 @@ static int sc92031_ethtool_nway_reset(struct net_device *dev) out: _sc92031_mii_scan(port_base); - mmiowb(); spin_unlock_bh(&priv->lock); @@ -1530,7 +1518,6 @@ static int sc92031_suspend(struct pci_dev *pdev, pm_message_t state) _sc92031_disable_tx_rx(dev); _sc92031_tx_clear(dev); - mmiowb(); spin_unlock_bh(&priv->lock); @@ -1555,7 +1542,6 @@ static int sc92031_resume(struct pci_dev *pdev) spin_lock_bh(&priv->lock); _sc92031_reset(dev); - mmiowb(); spin_unlock_bh(&priv->lock); sc92031_enable_interrupts(dev); diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c index 33949248c829..ab55416a10fa 100644 --- a/drivers/net/ethernet/via/via-rhine.c +++ b/drivers/net/ethernet/via/via-rhine.c @@ -571,7 +571,6 @@ static void rhine_ack_events(struct rhine_private *rp, u32 mask) if (rp->quirks & rqStatusWBRace) iowrite8(mask >> 16, ioaddr + IntrStatus2); iowrite16(mask, ioaddr + IntrStatus); - mmiowb(); } /* @@ -863,7 +862,6 @@ static int rhine_napipoll(struct napi_struct *napi, int budget) if (work_done < budget) { napi_complete_done(napi, work_done); iowrite16(enable_mask, ioaddr + IntrEnable); - mmiowb(); } return work_done; } @@ -1893,7 +1891,6 @@ static netdev_tx_t rhine_start_tx(struct sk_buff *skb, static void rhine_irq_disable(struct rhine_private *rp) { iowrite16(0x0000, rp->base + IntrEnable); - mmiowb(); } /* The interrupt handler does all of the Rx thread work and cleans up diff --git a/drivers/net/ethernet/wiznet/w5100.c b/drivers/net/ethernet/wiznet/w5100.c index d8ba512f166a..1713c2d2dccf 100644 --- a/drivers/net/ethernet/wiznet/w5100.c +++ b/drivers/net/ethernet/wiznet/w5100.c @@ -219,7 +219,6 @@ static inline int __w5100_write_direct(struct net_device *ndev, u32 addr, static inline int w5100_write_direct(struct net_device *ndev, u32 addr, u8 data) { __w5100_write_direct(ndev, addr, data); - mmiowb(); return 0; } @@ -236,7 +235,6 @@ static int w5100_write16_direct(struct net_device *ndev, u32 addr, u16 data) { __w5100_write_direct(ndev, addr, data >> 8); __w5100_write_direct(ndev, addr + 1, data); - mmiowb(); return 0; } @@ -260,8 +258,6 @@ static int w5100_writebulk_direct(struct net_device *ndev, u32 addr, for (i = 0; i < len; i++, addr++) __w5100_write_direct(ndev, addr, *buf++); - mmiowb(); - return 0; } @@ -375,7 +371,6 @@ static int w5100_readbulk_indirect(struct net_device *ndev, u32 addr, u8 *buf, for (i = 0; i < len; i++) *buf++ = w5100_read_direct(ndev, W5100_IDM_DR); - mmiowb(); spin_unlock_irqrestore(&mmio_priv->reg_lock, flags); return 0; @@ -394,7 +389,6 @@ static int w5100_writebulk_indirect(struct net_device *ndev, u32 addr, for (i = 0; i < len; i++) __w5100_write_direct(ndev, W5100_IDM_DR, *buf++); - mmiowb(); spin_unlock_irqrestore(&mmio_priv->reg_lock, flags); return 0; diff --git a/drivers/net/ethernet/wiznet/w5300.c b/drivers/net/ethernet/wiznet/w5300.c index f9da5d6172e3..3f03eecc0479 100644 --- a/drivers/net/ethernet/wiznet/w5300.c +++ b/drivers/net/ethernet/wiznet/w5300.c @@ -141,7 +141,6 @@ static u16 w5300_read_indirect(struct w5300_priv *priv, u16 addr) spin_lock_irqsave(&priv->reg_lock, flags); w5300_write_direct(priv, W5300_IDM_AR, addr); - mmiowb(); data = w5300_read_direct(priv, W5300_IDM_DR); spin_unlock_irqrestore(&priv->reg_lock, flags); @@ -154,9 +153,7 @@ static void w5300_write_indirect(struct w5300_priv *priv, u16 addr, u16 data) spin_lock_irqsave(&priv->reg_lock, flags); w5300_write_direct(priv, W5300_IDM_AR, addr); - mmiowb(); w5300_write_direct(priv, W5300_IDM_DR, data); - mmiowb(); spin_unlock_irqrestore(&priv->reg_lock, flags); } @@ -192,7 +189,6 @@ static int w5300_command(struct w5300_priv *priv, u16 cmd) unsigned long timeout = jiffies + msecs_to_jiffies(100); w5300_write(priv, W5300_S0_CR, cmd); - mmiowb(); while (w5300_read(priv, W5300_S0_CR) != 0) { if (time_after(jiffies, timeout)) @@ -241,18 +237,15 @@ static void w5300_write_macaddr(struct w5300_priv *priv) w5300_write(priv, W5300_SHARH, ndev->dev_addr[4] << 8 | ndev->dev_addr[5]); - mmiowb(); } static void w5300_hw_reset(struct w5300_priv *priv) { w5300_write_direct(priv, W5300_MR, MR_RST); - mmiowb(); mdelay(5); w5300_write_direct(priv, W5300_MR, priv->indirect ? MR_WDF(7) | MR_PB | MR_IND : MR_WDF(7) | MR_PB); - mmiowb(); w5300_write(priv, W5300_IMR, 0); w5300_write_macaddr(priv); @@ -264,24 +257,20 @@ static void w5300_hw_reset(struct w5300_priv *priv) w5300_write32(priv, W5300_TMSRL, 64 << 24); w5300_write32(priv, W5300_TMSRH, 0); w5300_write(priv, W5300_MTYPE, 0x00ff); - mmiowb(); } static void w5300_hw_start(struct w5300_priv *priv) { w5300_write(priv, W5300_S0_MR, priv->promisc ? S0_MR_MACRAW : S0_MR_MACRAW_MF); - mmiowb(); w5300_command(priv, S0_CR_OPEN); w5300_write(priv, W5300_S0_IMR, S0_IR_RECV | S0_IR_SENDOK); w5300_write(priv, W5300_IMR, IR_S0); - mmiowb(); } static void w5300_hw_close(struct w5300_priv *priv) { w5300_write(priv, W5300_IMR, 0); - mmiowb(); w5300_command(priv, S0_CR_CLOSE); } @@ -372,7 +361,6 @@ static netdev_tx_t w5300_start_tx(struct sk_buff *skb, struct net_device *ndev) netif_stop_queue(ndev); w5300_write_frame(priv, skb->data, skb->len); - mmiowb(); ndev->stats.tx_packets++; ndev->stats.tx_bytes += skb->len; dev_kfree_skb(skb); @@ -419,7 +407,6 @@ static int w5300_napi_poll(struct napi_struct *napi, int budget) if (rx_count < budget) { napi_complete_done(napi, rx_count); w5300_write(priv, W5300_IMR, IR_S0); - mmiowb(); } return rx_count; @@ -434,7 +421,6 @@ static irqreturn_t w5300_interrupt(int irq, void *ndev_instance) if (!ir) return IRQ_NONE; w5300_write(priv, W5300_S0_IR, ir); - mmiowb(); if (ir & S0_IR_SENDOK) { netif_dbg(priv, tx_done, ndev, "tx done\n"); @@ -444,7 +430,6 @@ static irqreturn_t w5300_interrupt(int irq, void *ndev_instance) if (ir & S0_IR_RECV) { if (napi_schedule_prep(&priv->napi)) { w5300_write(priv, W5300_IMR, 0); - mmiowb(); __napi_schedule(&priv->napi); } } diff --git a/drivers/net/wireless/ath/ath5k/base.c b/drivers/net/wireless/ath/ath5k/base.c index a2351ef45ae0..65a4c142640d 100644 --- a/drivers/net/wireless/ath/ath5k/base.c +++ b/drivers/net/wireless/ath/ath5k/base.c @@ -837,7 +837,6 @@ ath5k_txbuf_setup(struct ath5k_hw *ah, struct ath5k_buf *bf, txq->link = &ds->ds_link; ath5k_hw_start_tx_dma(ah, txq->qnum); - mmiowb(); spin_unlock_bh(&txq->lock); return 0; @@ -2174,7 +2173,6 @@ ath5k_beacon_config(struct ath5k_hw *ah) } ath5k_hw_set_imr(ah, ah->imask); - mmiowb(); spin_unlock_bh(&ah->block); } @@ -2779,7 +2777,6 @@ int ath5k_start(struct ieee80211_hw *hw) ret = 0; done: - mmiowb(); mutex_unlock(&ah->lock); set_bit(ATH_STAT_STARTED, ah->status); @@ -2839,7 +2836,6 @@ void ath5k_stop(struct ieee80211_hw *hw) "putting device to sleep\n"); } - mmiowb(); mutex_unlock(&ah->lock); ath5k_stop_tasklets(ah); diff --git a/drivers/net/wireless/ath/ath5k/mac80211-ops.c b/drivers/net/wireless/ath/ath5k/mac80211-ops.c index 16e052d02c94..5e866a193ed0 100644 --- a/drivers/net/wireless/ath/ath5k/mac80211-ops.c +++ b/drivers/net/wireless/ath/ath5k/mac80211-ops.c @@ -263,7 +263,6 @@ ath5k_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif, memcpy(common->curbssid, bss_conf->bssid, ETH_ALEN); common->curaid = 0; ath5k_hw_set_bssid(ah); - mmiowb(); } if (changes & BSS_CHANGED_BEACON_INT) @@ -528,7 +527,6 @@ ath5k_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, ret = -EINVAL; } - mmiowb(); mutex_unlock(&ah->lock); return ret; } diff --git a/drivers/net/wireless/broadcom/b43/main.c b/drivers/net/wireless/broadcom/b43/main.c index 74be3c809225..4c7980f84591 100644 --- a/drivers/net/wireless/broadcom/b43/main.c +++ b/drivers/net/wireless/broadcom/b43/main.c @@ -485,7 +485,6 @@ static void b43_ram_write(struct b43_wldev *dev, u16 offset, u32 val) val = swab32(val); b43_write32(dev, B43_MMIO_RAM_CONTROL, offset); - mmiowb(); b43_write32(dev, B43_MMIO_RAM_DATA, val); } @@ -656,9 +655,7 @@ static void b43_tsf_write_locked(struct b43_wldev *dev, u64 tsf) /* The hardware guarantees us an atomic write, if we * write the low register first. */ b43_write32(dev, B43_MMIO_REV3PLUS_TSF_LOW, low); - mmiowb(); b43_write32(dev, B43_MMIO_REV3PLUS_TSF_HIGH, high); - mmiowb(); } void b43_tsf_write(struct b43_wldev *dev, u64 tsf) @@ -1822,11 +1819,9 @@ static void b43_beacon_update_trigger_work(struct work_struct *work) if (b43_bus_host_is_sdio(dev->dev)) { /* wl->mutex is enough. */ b43_do_beacon_update_trigger_work(dev); - mmiowb(); } else { spin_lock_irq(&wl->hardirq_lock); b43_do_beacon_update_trigger_work(dev); - mmiowb(); spin_unlock_irq(&wl->hardirq_lock); } } @@ -2078,7 +2073,6 @@ static irqreturn_t b43_interrupt_thread_handler(int irq, void *dev_id) mutex_lock(&dev->wl->mutex); b43_do_interrupt_thread(dev); - mmiowb(); mutex_unlock(&dev->wl->mutex); return IRQ_HANDLED; @@ -2143,7 +2137,6 @@ static irqreturn_t b43_interrupt_handler(int irq, void *dev_id) spin_lock(&dev->wl->hardirq_lock); ret = b43_do_interrupt(dev); - mmiowb(); spin_unlock(&dev->wl->hardirq_lock); return ret; diff --git a/drivers/net/wireless/broadcom/b43/sysfs.c b/drivers/net/wireless/broadcom/b43/sysfs.c index 3190493bd07f..93d03b673670 100644 --- a/drivers/net/wireless/broadcom/b43/sysfs.c +++ b/drivers/net/wireless/broadcom/b43/sysfs.c @@ -129,7 +129,6 @@ static ssize_t b43_attr_interfmode_store(struct device *dev, } else err = -ENOSYS; - mmiowb(); mutex_unlock(&wldev->wl->mutex); return err ? err : count; diff --git a/drivers/net/wireless/broadcom/b43legacy/ilt.c b/drivers/net/wireless/broadcom/b43legacy/ilt.c index ee5682e54204..6d15fb4d30c6 100644 --- a/drivers/net/wireless/broadcom/b43legacy/ilt.c +++ b/drivers/net/wireless/broadcom/b43legacy/ilt.c @@ -315,14 +315,12 @@ const u16 b43legacy_ilt_sigmasqr2[B43legacy_ILT_SIGMASQR_SIZE] = { void b43legacy_ilt_write(struct b43legacy_wldev *dev, u16 offset, u16 val) { b43legacy_phy_write(dev, B43legacy_PHY_ILT_G_CTRL, offset); - mmiowb(); b43legacy_phy_write(dev, B43legacy_PHY_ILT_G_DATA1, val); } void b43legacy_ilt_write32(struct b43legacy_wldev *dev, u16 offset, u32 val) { b43legacy_phy_write(dev, B43legacy_PHY_ILT_G_CTRL, offset); - mmiowb(); b43legacy_phy_write(dev, B43legacy_PHY_ILT_G_DATA2, (val & 0xFFFF0000) >> 16); b43legacy_phy_write(dev, B43legacy_PHY_ILT_G_DATA1, diff --git a/drivers/net/wireless/broadcom/b43legacy/main.c b/drivers/net/wireless/broadcom/b43legacy/main.c index 55f411925960..c777efc6dc13 100644 --- a/drivers/net/wireless/broadcom/b43legacy/main.c +++ b/drivers/net/wireless/broadcom/b43legacy/main.c @@ -264,7 +264,6 @@ static void b43legacy_ram_write(struct b43legacy_wldev *dev, u16 offset, val = swab32(val); b43legacy_write32(dev, B43legacy_MMIO_RAM_CONTROL, offset); - mmiowb(); b43legacy_write32(dev, B43legacy_MMIO_RAM_DATA, val); } @@ -341,14 +340,11 @@ void b43legacy_shm_write32(struct b43legacy_wldev *dev, if (offset & 0x0003) { /* Unaligned access */ b43legacy_shm_control_word(dev, routing, offset >> 2); - mmiowb(); b43legacy_write16(dev, B43legacy_MMIO_SHM_DATA_UNALIGNED, (value >> 16) & 0xffff); - mmiowb(); b43legacy_shm_control_word(dev, routing, (offset >> 2) + 1); - mmiowb(); b43legacy_write16(dev, B43legacy_MMIO_SHM_DATA, value & 0xffff); return; @@ -356,7 +352,6 @@ void b43legacy_shm_write32(struct b43legacy_wldev *dev, offset >>= 2; } b43legacy_shm_control_word(dev, routing, offset); - mmiowb(); b43legacy_write32(dev, B43legacy_MMIO_SHM_DATA, value); } @@ -368,7 +363,6 @@ void b43legacy_shm_write16(struct b43legacy_wldev *dev, u16 routing, u16 offset, if (offset & 0x0003) { /* Unaligned access */ b43legacy_shm_control_word(dev, routing, offset >> 2); - mmiowb(); b43legacy_write16(dev, B43legacy_MMIO_SHM_DATA_UNALIGNED, value); @@ -377,7 +371,6 @@ void b43legacy_shm_write16(struct b43legacy_wldev *dev, u16 routing, u16 offset, offset >>= 2; } b43legacy_shm_control_word(dev, routing, offset); - mmiowb(); b43legacy_write16(dev, B43legacy_MMIO_SHM_DATA, value); } @@ -471,7 +464,6 @@ static void b43legacy_time_lock(struct b43legacy_wldev *dev) status = b43legacy_read32(dev, B43legacy_MMIO_MACCTL); status |= B43legacy_MACCTL_TBTTHOLD; b43legacy_write32(dev, B43legacy_MMIO_MACCTL, status); - mmiowb(); } static void b43legacy_time_unlock(struct b43legacy_wldev *dev) @@ -494,10 +486,8 @@ static void b43legacy_tsf_write_locked(struct b43legacy_wldev *dev, u64 tsf) u32 hi = (tsf & 0xFFFFFFFF00000000ULL) >> 32; b43legacy_write32(dev, B43legacy_MMIO_REV3PLUS_TSF_LOW, 0); - mmiowb(); b43legacy_write32(dev, B43legacy_MMIO_REV3PLUS_TSF_HIGH, hi); - mmiowb(); b43legacy_write32(dev, B43legacy_MMIO_REV3PLUS_TSF_LOW, lo); } else { @@ -507,13 +497,9 @@ static void b43legacy_tsf_write_locked(struct b43legacy_wldev *dev, u64 tsf) u16 v3 = (tsf & 0xFFFF000000000000ULL) >> 48; b43legacy_write16(dev, B43legacy_MMIO_TSF_0, 0); - mmiowb(); b43legacy_write16(dev, B43legacy_MMIO_TSF_3, v3); - mmiowb(); b43legacy_write16(dev, B43legacy_MMIO_TSF_2, v2); - mmiowb(); b43legacy_write16(dev, B43legacy_MMIO_TSF_1, v1); - mmiowb(); b43legacy_write16(dev, B43legacy_MMIO_TSF_0, v0); } } @@ -1250,7 +1236,6 @@ static void b43legacy_beacon_update_trigger_work(struct work_struct *work) /* The handler might have updated the IRQ mask. */ b43legacy_write32(dev, B43legacy_MMIO_GEN_IRQ_MASK, dev->irq_mask); - mmiowb(); spin_unlock_irq(&wl->irq_lock); } mutex_unlock(&wl->mutex); @@ -1346,7 +1331,6 @@ static void b43legacy_interrupt_tasklet(struct b43legacy_wldev *dev) dma_reason[2], dma_reason[3], dma_reason[4], dma_reason[5]); b43legacy_controller_restart(dev, "DMA error"); - mmiowb(); spin_unlock_irqrestore(&dev->wl->irq_lock, flags); return; } @@ -1396,7 +1380,6 @@ static void b43legacy_interrupt_tasklet(struct b43legacy_wldev *dev) handle_irq_transmit_status(dev); b43legacy_write32(dev, B43legacy_MMIO_GEN_IRQ_MASK, dev->irq_mask); - mmiowb(); spin_unlock_irqrestore(&dev->wl->irq_lock, flags); } @@ -1488,7 +1471,6 @@ static irqreturn_t b43legacy_interrupt_handler(int irq, void *dev_id) dev->irq_reason = reason; tasklet_schedule(&dev->isr_tasklet); out: - mmiowb(); spin_unlock(&dev->wl->irq_lock); return ret; @@ -2781,7 +2763,6 @@ static int b43legacy_op_dev_config(struct ieee80211_hw *hw, spin_lock_irqsave(&wl->irq_lock, flags); b43legacy_write32(dev, B43legacy_MMIO_GEN_IRQ_MASK, dev->irq_mask); - mmiowb(); spin_unlock_irqrestore(&wl->irq_lock, flags); out_unlock_mutex: mutex_unlock(&wl->mutex); @@ -2900,7 +2881,6 @@ static void b43legacy_op_bss_info_changed(struct ieee80211_hw *hw, spin_lock_irqsave(&wl->irq_lock, flags); b43legacy_write32(dev, B43legacy_MMIO_GEN_IRQ_MASK, dev->irq_mask); /* XXX: why? */ - mmiowb(); spin_unlock_irqrestore(&wl->irq_lock, flags); out_unlock_mutex: mutex_unlock(&wl->mutex); diff --git a/drivers/net/wireless/broadcom/b43legacy/phy.c b/drivers/net/wireless/broadcom/b43legacy/phy.c index 995c7d0c212a..f949766d27ca 100644 --- a/drivers/net/wireless/broadcom/b43legacy/phy.c +++ b/drivers/net/wireless/broadcom/b43legacy/phy.c @@ -134,7 +134,6 @@ u16 b43legacy_phy_read(struct b43legacy_wldev *dev, u16 offset) void b43legacy_phy_write(struct b43legacy_wldev *dev, u16 offset, u16 val) { b43legacy_write16(dev, B43legacy_MMIO_PHY_CONTROL, offset); - mmiowb(); b43legacy_write16(dev, B43legacy_MMIO_PHY_DATA, val); } diff --git a/drivers/net/wireless/broadcom/b43legacy/pio.h b/drivers/net/wireless/broadcom/b43legacy/pio.h index 1cd1b9ca5e9c..08cd02282beb 100644 --- a/drivers/net/wireless/broadcom/b43legacy/pio.h +++ b/drivers/net/wireless/broadcom/b43legacy/pio.h @@ -92,7 +92,6 @@ void b43legacy_pio_write(struct b43legacy_pioqueue *queue, u16 offset, u16 value) { b43legacy_write16(queue->dev, queue->mmio_base + offset, value); - mmiowb(); } diff --git a/drivers/net/wireless/broadcom/b43legacy/radio.c b/drivers/net/wireless/broadcom/b43legacy/radio.c index eab1c9387846..c6db444ea07e 100644 --- a/drivers/net/wireless/broadcom/b43legacy/radio.c +++ b/drivers/net/wireless/broadcom/b43legacy/radio.c @@ -95,7 +95,6 @@ void b43legacy_radio_lock(struct b43legacy_wldev *dev) B43legacy_WARN_ON(status & B43legacy_MACCTL_RADIOLOCK); status |= B43legacy_MACCTL_RADIOLOCK; b43legacy_write32(dev, B43legacy_MMIO_MACCTL, status); - mmiowb(); udelay(10); } @@ -108,7 +107,6 @@ void b43legacy_radio_unlock(struct b43legacy_wldev *dev) B43legacy_WARN_ON(!(status & B43legacy_MACCTL_RADIOLOCK)); status &= ~B43legacy_MACCTL_RADIOLOCK; b43legacy_write32(dev, B43legacy_MMIO_MACCTL, status); - mmiowb(); } u16 b43legacy_radio_read16(struct b43legacy_wldev *dev, u16 offset) @@ -141,7 +139,6 @@ u16 b43legacy_radio_read16(struct b43legacy_wldev *dev, u16 offset) void b43legacy_radio_write16(struct b43legacy_wldev *dev, u16 offset, u16 val) { b43legacy_write16(dev, B43legacy_MMIO_RADIO_CONTROL, offset); - mmiowb(); b43legacy_write16(dev, B43legacy_MMIO_RADIO_DATA_LOW, val); } @@ -333,7 +330,6 @@ u8 b43legacy_radio_aci_scan(struct b43legacy_wldev *dev) void b43legacy_nrssi_hw_write(struct b43legacy_wldev *dev, u16 offset, s16 val) { b43legacy_phy_write(dev, B43legacy_PHY_NRSSILT_CTRL, offset); - mmiowb(); b43legacy_phy_write(dev, B43legacy_PHY_NRSSILT_DATA, (u16)val); } diff --git a/drivers/net/wireless/broadcom/b43legacy/sysfs.c b/drivers/net/wireless/broadcom/b43legacy/sysfs.c index 2a1da15c913b..2db83eec7a11 100644 --- a/drivers/net/wireless/broadcom/b43legacy/sysfs.c +++ b/drivers/net/wireless/broadcom/b43legacy/sysfs.c @@ -143,7 +143,6 @@ static ssize_t b43legacy_attr_interfmode_store(struct device *dev, if (err) b43legacyerr(wldev->wl, "Interference Mitigation not " "supported by device\n"); - mmiowb(); spin_unlock_irqrestore(&wldev->wl->irq_lock, flags); mutex_unlock(&wldev->wl->mutex); diff --git a/drivers/net/wireless/intel/iwlegacy/common.h b/drivers/net/wireless/intel/iwlegacy/common.h index b079c64ca014..986646af8dfd 100644 --- a/drivers/net/wireless/intel/iwlegacy/common.h +++ b/drivers/net/wireless/intel/iwlegacy/common.h @@ -2030,13 +2030,6 @@ static inline void _il_release_nic_access(struct il_priv *il) { _il_clear_bit(il, CSR_GP_CNTRL, CSR_GP_CNTRL_REG_FLAG_MAC_ACCESS_REQ); - /* - * In above we are reading CSR_GP_CNTRL register, what will flush any - * previous writes, but still want write, which clear MAC_ACCESS_REQ - * bit, be performed on PCI bus before any other writes scheduled on - * different CPUs (after we drop reg_lock). - */ - mmiowb(); } static inline u32 diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c index fe8269d023de..abbfc9cc80fc 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@ -2067,7 +2067,6 @@ static void iwl_trans_pcie_release_nic_access(struct iwl_trans *trans, * MAC_ACCESS_REQ bit to be performed before any other writes * scheduled on different CPUs (after we drop reg_lock). */ - mmiowb(); out: spin_unlock_irqrestore(&trans_pcie->reg_lock, *flags); } diff --git a/drivers/ntb/hw/idt/ntb_hw_idt.c b/drivers/ntb/hw/idt/ntb_hw_idt.c index 1dede87dd54f..dcf234680535 100644 --- a/drivers/ntb/hw/idt/ntb_hw_idt.c +++ b/drivers/ntb/hw/idt/ntb_hw_idt.c @@ -358,8 +358,6 @@ static void idt_sw_write(struct idt_ntb_dev *ndev, iowrite32((u32)reg, ndev->cfgspc + (ptrdiff_t)IDT_NT_GASAADDR); /* Put the new value of the register */ iowrite32(data, ndev->cfgspc + (ptrdiff_t)IDT_NT_GASADATA); - /* Make sure the PCIe transactions are executed */ - mmiowb(); /* Unlock GASA registers operations */ spin_unlock_irqrestore(&ndev->gasa_lock, irqflags); } @@ -750,7 +748,6 @@ static void idt_ntb_local_link_enable(struct idt_ntb_dev *ndev) spin_lock_irqsave(&ndev->mtbl_lock, irqflags); idt_nt_write(ndev, IDT_NT_NTMTBLADDR, ndev->part); idt_nt_write(ndev, IDT_NT_NTMTBLDATA, mtbldata); - mmiowb(); spin_unlock_irqrestore(&ndev->mtbl_lock, irqflags); /* Notify the peers by setting and clearing the global signal bit */ @@ -778,7 +775,6 @@ static void idt_ntb_local_link_disable(struct idt_ntb_dev *ndev) spin_lock_irqsave(&ndev->mtbl_lock, irqflags); idt_nt_write(ndev, IDT_NT_NTMTBLADDR, ndev->part); idt_nt_write(ndev, IDT_NT_NTMTBLDATA, 0); - mmiowb(); spin_unlock_irqrestore(&ndev->mtbl_lock, irqflags); /* Notify the peers by setting and clearing the global signal bit */ @@ -1339,7 +1335,6 @@ static int idt_ntb_peer_mw_set_trans(struct ntb_dev *ntb, int pidx, int widx, idt_nt_write(ndev, IDT_NT_LUTLDATA, (u32)addr); idt_nt_write(ndev, IDT_NT_LUTMDATA, (u32)(addr >> 32)); idt_nt_write(ndev, IDT_NT_LUTUDATA, data); - mmiowb(); spin_unlock_irqrestore(&ndev->lut_lock, irqflags); /* Limit address isn't specified since size is fixed for LUT */ } @@ -1393,7 +1388,6 @@ static int idt_ntb_peer_mw_clear_trans(struct ntb_dev *ntb, int pidx, idt_nt_write(ndev, IDT_NT_LUTLDATA, 0); idt_nt_write(ndev, IDT_NT_LUTMDATA, 0); idt_nt_write(ndev, IDT_NT_LUTUDATA, 0); - mmiowb(); spin_unlock_irqrestore(&ndev->lut_lock, irqflags); } @@ -1812,7 +1806,6 @@ static int idt_ntb_peer_msg_write(struct ntb_dev *ntb, int pidx, int midx, /* Set the route and send the data */ idt_sw_write(ndev, partdata_tbl[ndev->part].msgctl[midx], swpmsgctl); idt_nt_write(ndev, ntdata_tbl.msgs[midx].out, msg); - mmiowb(); /* Unlock the messages routing table */ spin_unlock_irqrestore(&ndev->msg_locks[midx], irqflags); diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c index 2a9d6b0d1f19..11a6cd374004 100644 --- a/drivers/ntb/test/ntb_perf.c +++ b/drivers/ntb/test/ntb_perf.c @@ -284,11 +284,9 @@ static int perf_spad_cmd_send(struct perf_peer *peer, enum perf_cmd cmd, ntb_peer_spad_write(perf->ntb, peer->pidx, PERF_SPAD_HDATA(perf->gidx), upper_32_bits(data)); - mmiowb(); ntb_peer_spad_write(perf->ntb, peer->pidx, PERF_SPAD_CMD(perf->gidx), cmd); - mmiowb(); ntb_peer_db_set(perf->ntb, PERF_SPAD_NOTIFY(peer->gidx)); dev_dbg(&perf->ntb->dev, "DB ring peer %#llx\n", @@ -379,7 +377,6 @@ static int perf_msg_cmd_send(struct perf_peer *peer, enum perf_cmd cmd, ntb_peer_msg_write(perf->ntb, peer->pidx, PERF_MSG_HDATA, upper_32_bits(data)); - mmiowb(); /* This call shall trigger peer message event */ ntb_peer_msg_write(perf->ntb, peer->pidx, PERF_MSG_CMD, cmd); diff --git a/drivers/scsi/bfa/bfa.h b/drivers/scsi/bfa/bfa.h index 0e119d838e1b..762cb77253b9 100644 --- a/drivers/scsi/bfa/bfa.h +++ b/drivers/scsi/bfa/bfa.h @@ -62,8 +62,7 @@ void bfa_isr_unhandled(struct bfa_s *bfa, struct bfi_msg_s *m); ((__bfa)->iocfc.cfg.drvcfg.num_reqq_elems - 1); \ writel((__bfa)->iocfc.req_cq_pi[__reqq], \ (__bfa)->iocfc.bfa_regs.cpe_q_pi[__reqq]); \ - mmiowb(); \ - } while (0) + } while (0) #define bfa_rspq_pi(__bfa, __rspq) \ (*(u32 *)((__bfa)->iocfc.rsp_cq_shadow_pi[__rspq].kva)) diff --git a/drivers/scsi/bfa/bfa_hw_cb.c b/drivers/scsi/bfa/bfa_hw_cb.c index c4a0c0eb88a5..4a0d881b2602 100644 --- a/drivers/scsi/bfa/bfa_hw_cb.c +++ b/drivers/scsi/bfa/bfa_hw_cb.c @@ -61,7 +61,6 @@ bfa_hwcb_rspq_ack_msix(struct bfa_s *bfa, int rspq, u32 ci) bfa_rspq_ci(bfa, rspq) = ci; writel(ci, bfa->iocfc.bfa_regs.rme_q_ci[rspq]); - mmiowb(); } void @@ -72,7 +71,6 @@ bfa_hwcb_rspq_ack(struct bfa_s *bfa, int rspq, u32 ci) bfa_rspq_ci(bfa, rspq) = ci; writel(ci, bfa->iocfc.bfa_regs.rme_q_ci[rspq]); - mmiowb(); } void diff --git a/drivers/scsi/bfa/bfa_hw_ct.c b/drivers/scsi/bfa/bfa_hw_ct.c index b0ff378dece2..b7be5f4f02a5 100644 --- a/drivers/scsi/bfa/bfa_hw_ct.c +++ b/drivers/scsi/bfa/bfa_hw_ct.c @@ -81,7 +81,6 @@ bfa_hwct_rspq_ack(struct bfa_s *bfa, int rspq, u32 ci) bfa_rspq_ci(bfa, rspq) = ci; writel(ci, bfa->iocfc.bfa_regs.rme_q_ci[rspq]); - mmiowb(); } /* @@ -94,7 +93,6 @@ bfa_hwct2_rspq_ack(struct bfa_s *bfa, int rspq, u32 ci) { bfa_rspq_ci(bfa, rspq) = ci; writel(ci, bfa->iocfc.bfa_regs.rme_q_ci[rspq]); - mmiowb(); } void diff --git a/drivers/scsi/bnx2fc/bnx2fc_hwi.c b/drivers/scsi/bnx2fc/bnx2fc_hwi.c index 039328d9ef13..19734ec7f42e 100644 --- a/drivers/scsi/bnx2fc/bnx2fc_hwi.c +++ b/drivers/scsi/bnx2fc/bnx2fc_hwi.c @@ -991,7 +991,6 @@ void bnx2fc_arm_cq(struct bnx2fc_rport *tgt) FCOE_CQE_TOGGLE_BIT_SHIFT); msg = *((u32 *)rx_db); writel(cpu_to_le32(msg), tgt->ctx_base); - mmiowb(); } @@ -1409,7 +1408,6 @@ void bnx2fc_ring_doorbell(struct bnx2fc_rport *tgt) (tgt->sq_curr_toggle_bit << 15); msg = *((u32 *)sq_db); writel(cpu_to_le32(msg), tgt->ctx_base); - mmiowb(); } diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c index d56a78f411cd..12666313b937 100644 --- a/drivers/scsi/bnx2i/bnx2i_hwi.c +++ b/drivers/scsi/bnx2i/bnx2i_hwi.c @@ -253,7 +253,6 @@ void bnx2i_put_rq_buf(struct bnx2i_conn *bnx2i_conn, int count) writew(ep->qp.rq_prod_idx, ep->qp.ctx_base + CNIC_RECV_DOORBELL); } - mmiowb(); } @@ -279,8 +278,6 @@ static void bnx2i_ring_sq_dbell(struct bnx2i_conn *bnx2i_conn, int count) bnx2i_ring_577xx_doorbell(bnx2i_conn); } else writew(count, ep->qp.ctx_base + CNIC_SEND_DOORBELL); - - mmiowb(); } diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c index 293f5cf524d7..59a6546fd602 100644 --- a/drivers/scsi/megaraid/megaraid_sas_base.c +++ b/drivers/scsi/megaraid/megaraid_sas_base.c @@ -815,7 +815,6 @@ megasas_fire_cmd_skinny(struct megasas_instance *instance, &(regs)->inbound_high_queue_port); writel((lower_32_bits(frame_phys_addr) | (frame_count<<1))|1, &(regs)->inbound_low_queue_port); - mmiowb(); spin_unlock_irqrestore(&instance->hba_lock, flags); } diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c index 1d17128030cd..e35c2b64c145 100644 --- a/drivers/scsi/megaraid/megaraid_sas_fusion.c +++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c @@ -242,7 +242,6 @@ megasas_fire_cmd_fusion(struct megasas_instance *instance, &instance->reg_set->inbound_low_queue_port); writel(le32_to_cpu(req_desc->u.high), &instance->reg_set->inbound_high_queue_port); - mmiowb(); spin_unlock_irqrestore(&instance->hba_lock, flags); #endif } diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c index 1d8c584ec1e9..f60b9e0a6ca6 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_base.c +++ b/drivers/scsi/mpt3sas/mpt3sas_base.c @@ -3333,7 +3333,6 @@ _base_mpi_ep_writeq(__u64 b, volatile void __iomem *addr, spin_lock_irqsave(writeq_lock, flags); __raw_writel((u32)(b), addr); __raw_writel((u32)(b >> 32), (addr + 4)); - mmiowb(); spin_unlock_irqrestore(writeq_lock, flags); } diff --git a/drivers/scsi/qedf/qedf_io.c b/drivers/scsi/qedf/qedf_io.c index 6ca583bdde23..53e8221f6816 100644 --- a/drivers/scsi/qedf/qedf_io.c +++ b/drivers/scsi/qedf/qedf_io.c @@ -807,7 +807,6 @@ void qedf_ring_doorbell(struct qedf_rport *fcport) writel(*(u32 *)&dbell, fcport->p_doorbell); /* Make sure SQ index is updated so f/w prcesses requests in order */ wmb(); - mmiowb(); } static void qedf_trace_io(struct qedf_rport *fcport, struct qedf_ioreq *io_req, diff --git a/drivers/scsi/qedi/qedi_fw.c b/drivers/scsi/qedi/qedi_fw.c index e2a995a6e8e7..f8f86774f77f 100644 --- a/drivers/scsi/qedi/qedi_fw.c +++ b/drivers/scsi/qedi/qedi_fw.c @@ -985,7 +985,6 @@ static void qedi_ring_doorbell(struct qedi_conn *qedi_conn) * others they are two different assembly operations. */ wmb(); - mmiowb(); QEDI_INFO(&qedi_conn->qedi->dbg_ctx, QEDI_LOG_MP_REQ, "prod_idx=0x%x, fw_prod_idx=0x%x, cid=0x%x\n", qedi_conn->ep->sq_prod_idx, qedi_conn->ep->fw_sq_prod_idx, diff --git a/drivers/scsi/qla1280.c b/drivers/scsi/qla1280.c index 6856dfdfa473..93acbc5094f0 100644 --- a/drivers/scsi/qla1280.c +++ b/drivers/scsi/qla1280.c @@ -3004,8 +3004,6 @@ qla1280_64bit_start_scsi(struct scsi_qla_host *ha, struct srb * sp) sp->flags |= SRB_SENT; ha->actthreads++; WRT_REG_WORD(®->mailbox4, ha->req_ring_index); - /* Enforce mmio write ordering; see comment in qla1280_isp_cmd(). */ - mmiowb(); out: if (status) @@ -3254,8 +3252,6 @@ qla1280_32bit_start_scsi(struct scsi_qla_host *ha, struct srb * sp) sp->flags |= SRB_SENT; ha->actthreads++; WRT_REG_WORD(®->mailbox4, ha->req_ring_index); - /* Enforce mmio write ordering; see comment in qla1280_isp_cmd(). */ - mmiowb(); out: if (status) @@ -3379,7 +3375,6 @@ qla1280_isp_cmd(struct scsi_qla_host *ha) * See Documentation/driver-api/device-io.rst for more information. */ WRT_REG_WORD(®->mailbox4, ha->req_ring_index); - mmiowb(); LEAVE("qla1280_isp_cmd"); } diff --git a/drivers/ssb/pci.c b/drivers/ssb/pci.c index 84807a9b4b13..da2d2ab8104d 100644 --- a/drivers/ssb/pci.c +++ b/drivers/ssb/pci.c @@ -305,7 +305,6 @@ static int sprom_do_write(struct ssb_bus *bus, const u16 *sprom) else if (i % 2) pr_cont("."); writew(sprom[i], bus->mmio + bus->sprom_offset + (i * 2)); - mmiowb(); msleep(20); } err = pci_read_config_dword(pdev, SSB_SPROMCTL, &spromctl); diff --git a/drivers/ssb/pcmcia.c b/drivers/ssb/pcmcia.c index 567013f8a8be..d7d730c245c5 100644 --- a/drivers/ssb/pcmcia.c +++ b/drivers/ssb/pcmcia.c @@ -338,7 +338,6 @@ static void ssb_pcmcia_write8(struct ssb_device *dev, u16 offset, u8 value) err = select_core_and_segment(dev, &offset); if (likely(!err)) writeb(value, bus->mmio + offset); - mmiowb(); spin_unlock_irqrestore(&bus->bar_lock, flags); } @@ -352,7 +351,6 @@ static void ssb_pcmcia_write16(struct ssb_device *dev, u16 offset, u16 value) err = select_core_and_segment(dev, &offset); if (likely(!err)) writew(value, bus->mmio + offset); - mmiowb(); spin_unlock_irqrestore(&bus->bar_lock, flags); } @@ -368,7 +366,6 @@ static void ssb_pcmcia_write32(struct ssb_device *dev, u16 offset, u32 value) writew((value & 0x0000FFFF), bus->mmio + offset); writew(((value & 0xFFFF0000) >> 16), bus->mmio + offset + 2); } - mmiowb(); spin_unlock_irqrestore(&bus->bar_lock, flags); } @@ -424,7 +421,6 @@ static void ssb_pcmcia_block_write(struct ssb_device *dev, const void *buffer, WARN_ON(1); } unlock: - mmiowb(); spin_unlock_irqrestore(&bus->bar_lock, flags); } #endif /* CONFIG_SSB_BLOCKIO */ diff --git a/drivers/staging/comedi/drivers/mite.c b/drivers/staging/comedi/drivers/mite.c index 61e03ad84123..639ec1586976 100644 --- a/drivers/staging/comedi/drivers/mite.c +++ b/drivers/staging/comedi/drivers/mite.c @@ -371,7 +371,6 @@ static unsigned int mite_get_status(struct mite_channel *mite_chan) writel(CHOR_CLRDONE, mite->mmio + MITE_CHOR(mite_chan->channel)); } - mmiowb(); spin_unlock_irqrestore(&mite->lock, flags); return status; } @@ -451,7 +450,6 @@ void mite_dma_arm(struct mite_channel *mite_chan) mite_chan->done = 0; /* arm */ writel(CHOR_START, mite->mmio + MITE_CHOR(mite_chan->channel)); - mmiowb(); spin_unlock_irqrestore(&mite->lock, flags); } EXPORT_SYMBOL_GPL(mite_dma_arm); @@ -638,7 +636,6 @@ void mite_release_channel(struct mite_channel *mite_chan) CHCR_CLR_LC_IE | CHCR_CLR_CONT_RB_IE, mite->mmio + MITE_CHCR(mite_chan->channel)); mite_chan->ring = NULL; - mmiowb(); } spin_unlock_irqrestore(&mite->lock, flags); } diff --git a/drivers/staging/comedi/drivers/ni_660x.c b/drivers/staging/comedi/drivers/ni_660x.c index 405573e927cf..4ee9b260eab0 100644 --- a/drivers/staging/comedi/drivers/ni_660x.c +++ b/drivers/staging/comedi/drivers/ni_660x.c @@ -320,7 +320,6 @@ static inline void ni_660x_set_dma_channel(struct comedi_device *dev, ni_660x_write(dev, chip, devpriv->dma_cfg[chip] | NI660X_DMA_CFG_RESET(mite_channel), NI660X_DMA_CFG); - mmiowb(); } static inline void ni_660x_unset_dma_channel(struct comedi_device *dev, @@ -333,7 +332,6 @@ static inline void ni_660x_unset_dma_channel(struct comedi_device *dev, devpriv->dma_cfg[chip] &= ~NI660X_DMA_CFG_SEL_MASK(mite_channel); devpriv->dma_cfg[chip] |= NI660X_DMA_CFG_SEL_NONE(mite_channel); ni_660x_write(dev, chip, devpriv->dma_cfg[chip], NI660X_DMA_CFG); - mmiowb(); } static int ni_660x_request_mite_channel(struct comedi_device *dev, diff --git a/drivers/staging/comedi/drivers/ni_mio_common.c b/drivers/staging/comedi/drivers/ni_mio_common.c index b04dad8c7092..668f2aa16baa 100644 --- a/drivers/staging/comedi/drivers/ni_mio_common.c +++ b/drivers/staging/comedi/drivers/ni_mio_common.c @@ -547,7 +547,6 @@ static inline void ni_set_bitfield(struct comedi_device *dev, int reg, reg); break; } - mmiowb(); spin_unlock_irqrestore(&devpriv->soft_reg_copy_lock, flags); } diff --git a/drivers/staging/comedi/drivers/ni_pcidio.c b/drivers/staging/comedi/drivers/ni_pcidio.c index 4bdef87d5dd7..8f3864799c19 100644 --- a/drivers/staging/comedi/drivers/ni_pcidio.c +++ b/drivers/staging/comedi/drivers/ni_pcidio.c @@ -310,7 +310,6 @@ static int ni_pcidio_request_di_mite_channel(struct comedi_device *dev) writeb(primary_DMAChannel_bits(devpriv->di_mite_chan->channel) | secondary_DMAChannel_bits(devpriv->di_mite_chan->channel), dev->mmio + DMA_LINE_CONTROL_GROUP1); - mmiowb(); spin_unlock_irqrestore(&devpriv->mite_channel_lock, flags); return 0; } @@ -327,7 +326,6 @@ static void ni_pcidio_release_di_mite_channel(struct comedi_device *dev) writeb(primary_DMAChannel_bits(0) | secondary_DMAChannel_bits(0), dev->mmio + DMA_LINE_CONTROL_GROUP1); - mmiowb(); } spin_unlock_irqrestore(&devpriv->mite_channel_lock, flags); } diff --git a/drivers/staging/comedi/drivers/ni_tio.c b/drivers/staging/comedi/drivers/ni_tio.c index 048cb35723ad..c1131a1622c0 100644 --- a/drivers/staging/comedi/drivers/ni_tio.c +++ b/drivers/staging/comedi/drivers/ni_tio.c @@ -234,7 +234,6 @@ static void ni_tio_set_bits_transient(struct ni_gpct *counter, regs[reg] &= ~mask; regs[reg] |= (value & mask); ni_tio_write(counter, regs[reg] | transient, reg); - mmiowb(); spin_unlock_irqrestore(&counter_dev->regs_lock, flags); } } diff --git a/drivers/staging/comedi/drivers/s626.c b/drivers/staging/comedi/drivers/s626.c index f5af6f4069dc..39049d3c56d7 100644 --- a/drivers/staging/comedi/drivers/s626.c +++ b/drivers/staging/comedi/drivers/s626.c @@ -108,7 +108,6 @@ static void s626_mc_enable(struct comedi_device *dev, { unsigned int val = (cmd << 16) | cmd; - mmiowb(); writel(val, dev->mmio + reg); } @@ -116,7 +115,6 @@ static void s626_mc_disable(struct comedi_device *dev, unsigned int cmd, unsigned int reg) { writel(cmd << 16, dev->mmio + reg); - mmiowb(); } static bool s626_mc_test(struct comedi_device *dev, diff --git a/drivers/tty/serial/men_z135_uart.c b/drivers/tty/serial/men_z135_uart.c index ef89534dd760..e5d3ebab6dae 100644 --- a/drivers/tty/serial/men_z135_uart.c +++ b/drivers/tty/serial/men_z135_uart.c @@ -353,7 +353,6 @@ static void men_z135_handle_tx(struct men_z135_port *uart) memcpy_toio(port->membase + MEN_Z135_TX_RAM, &xmit->buf[xmit->tail], n); xmit->tail = (xmit->tail + n) & (UART_XMIT_SIZE - 1); - mmiowb(); iowrite32(n & 0x3ff, port->membase + MEN_Z135_TX_CTRL); diff --git a/drivers/tty/serial/serial_txx9.c b/drivers/tty/serial/serial_txx9.c index 1b4008d022bf..d22ccb32aa9b 100644 --- a/drivers/tty/serial/serial_txx9.c +++ b/drivers/tty/serial/serial_txx9.c @@ -248,7 +248,6 @@ static void serial_txx9_initialize(struct uart_port *port) sio_out(up, TXX9_SIFCR, TXX9_SIFCR_SWRST); /* TX4925 BUG WORKAROUND. Accessing SIOC register * immediately after soft reset causes bus error. */ - mmiowb(); udelay(1); while ((sio_in(up, TXX9_SIFCR) & TXX9_SIFCR_SWRST) && --tmout) udelay(1); diff --git a/drivers/usb/early/xhci-dbc.c b/drivers/usb/early/xhci-dbc.c index c9cfb100ecdc..cac991173ac0 100644 --- a/drivers/usb/early/xhci-dbc.c +++ b/drivers/usb/early/xhci-dbc.c @@ -533,8 +533,6 @@ static int xdbc_handle_external_reset(void) xdbc_mem_init(); - mmiowb(); - ret = xdbc_start(); if (ret < 0) goto reset_out; @@ -587,8 +585,6 @@ static int __init xdbc_early_setup(void) xdbc_mem_init(); - mmiowb(); - ret = xdbc_start(); if (ret < 0) { writel(0, &xdbc.xdbc_reg->control); diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c index d932cc31711e..52e32644a4b2 100644 --- a/drivers/usb/host/xhci-dbgcap.c +++ b/drivers/usb/host/xhci-dbgcap.c @@ -421,8 +421,6 @@ static int xhci_dbc_mem_init(struct xhci_hcd *xhci, gfp_t flags) string_length = xhci_dbc_populate_strings(dbc->string); xhci_dbc_init_contexts(xhci, string_length); - mmiowb(); - xhci_dbc_eps_init(xhci); dbc->state = DS_INITIALIZED; diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index f6165d304b4d..48841e5dab90 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -1338,7 +1338,6 @@ static inline u16 qed_sb_update_sb_idx(struct qed_sb_info *sb_info) } /* Let SB update */ - mmiowb(); return rc; } @@ -1374,7 +1373,6 @@ static inline void qed_sb_ack(struct qed_sb_info *sb_info, /* Both segments (interrupts & acks) are written to same place address; * Need to guarantee all commands will be received (in-order) by HW. */ - mmiowb(); barrier(); } diff --git a/sound/soc/txx9/txx9aclc-ac97.c b/sound/soc/txx9/txx9aclc-ac97.c index 1cfca698ae4b..b0fa285c7ba2 100644 --- a/sound/soc/txx9/txx9aclc-ac97.c +++ b/sound/soc/txx9/txx9aclc-ac97.c @@ -102,7 +102,6 @@ static void txx9aclc_ac97_cold_reset(struct snd_ac97 *ac97) u32 ready = ACINT_CODECRDY(ac97->num) | ACINT_REGACCRDY; __raw_writel(ACCTL_ENLINK, base + ACCTLDIS); - mmiowb(); udelay(1); __raw_writel(ACCTL_ENLINK, base + ACCTLEN); /* wait for primary codec ready status */ -- cgit From 1200e07f3ad4b9d976cf2fff3a0c3d9a1faecb3e Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 8 Apr 2019 19:02:38 +0800 Subject: block: don't use for-inside-for in bio_for_each_segment_all Commit 6dc4f100c175 ("block: allow bio_for_each_segment_all() to iterate over multi-page bvec") changes bio_for_each_segment_all() to use for-inside-for. This way breaks all bio_for_each_segment_all() call with error out branch via 'break', since now 'break' can only break from the inner loop. Fixes this issue by implementing bio_for_each_segment_all() via single 'for' loop, and now the logic is very similar with normal bvec iterator. Cc: Qu Wenruo Cc: linux-btrfs@vger.kernel.org Cc: linux-fsdevel@vger.kernel.org Cc: Omar Sandoval Reviewed-by: Johannes Thumshirn Reported-and-Tested-by: Qu Wenruo Fixes: 6dc4f100c175 ("block: allow bio_for_each_segment_all() to iterate over multi-page bvec") Reviewed-by: Christoph Hellwig Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/bio.h | 20 ++++++++++++-------- include/linux/bvec.h | 14 ++++++++++---- 2 files changed, 22 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index bb6090aa165d..e584673c1881 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -120,19 +120,23 @@ static inline bool bio_full(struct bio *bio) return bio->bi_vcnt >= bio->bi_max_vecs; } -#define mp_bvec_for_each_segment(bv, bvl, i, iter_all) \ - for (bv = bvec_init_iter_all(&iter_all); \ - (iter_all.done < (bvl)->bv_len) && \ - (mp_bvec_next_segment((bvl), &iter_all), 1); \ - iter_all.done += bv->bv_len, i += 1) +static inline bool bio_next_segment(const struct bio *bio, + struct bvec_iter_all *iter) +{ + if (iter->idx >= bio->bi_vcnt) + return false; + + bvec_advance(&bio->bi_io_vec[iter->idx], iter); + return true; +} /* * drivers should _never_ use the all version - the bio may have been split * before it got to the driver and the driver won't own all of it */ -#define bio_for_each_segment_all(bvl, bio, i, iter_all) \ - for (i = 0, iter_all.idx = 0; iter_all.idx < (bio)->bi_vcnt; iter_all.idx++) \ - mp_bvec_for_each_segment(bvl, &((bio)->bi_io_vec[iter_all.idx]), i, iter_all) +#define bio_for_each_segment_all(bvl, bio, i, iter) \ + for (i = 0, bvl = bvec_init_iter_all(&iter); \ + bio_next_segment((bio), &iter); i++) static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter, unsigned bytes) diff --git a/include/linux/bvec.h b/include/linux/bvec.h index f6275c4da13a..3bc91879e1e2 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -145,18 +145,18 @@ static inline bool bvec_iter_advance(const struct bio_vec *bv, static inline struct bio_vec *bvec_init_iter_all(struct bvec_iter_all *iter_all) { - iter_all->bv.bv_page = NULL; iter_all->done = 0; + iter_all->idx = 0; return &iter_all->bv; } -static inline void mp_bvec_next_segment(const struct bio_vec *bvec, - struct bvec_iter_all *iter_all) +static inline void bvec_advance(const struct bio_vec *bvec, + struct bvec_iter_all *iter_all) { struct bio_vec *bv = &iter_all->bv; - if (bv->bv_page) { + if (iter_all->done) { bv->bv_page = nth_page(bv->bv_page, 1); bv->bv_offset = 0; } else { @@ -165,6 +165,12 @@ static inline void mp_bvec_next_segment(const struct bio_vec *bvec, } bv->bv_len = min_t(unsigned int, PAGE_SIZE - bv->bv_offset, bvec->bv_len - iter_all->done); + iter_all->done += bv->bv_len; + + if (iter_all->done == bvec->bv_len) { + iter_all->idx++; + iter_all->done = 0; + } } /* -- cgit From cf94db21905333e610e479688add629397a4b384 Mon Sep 17 00:00:00 2001 From: Cornelia Huck Date: Mon, 8 Apr 2019 14:33:22 +0200 Subject: virtio: Honour 'may_reduce_num' in vring_create_virtqueue vring_create_virtqueue() allows the caller to specify via the may_reduce_num parameter whether the vring code is allowed to allocate a smaller ring than specified. However, the split ring allocation code tries to allocate a smaller ring on allocation failure regardless of what the caller specified. This may cause trouble for e.g. virtio-pci in legacy mode, which does not support ring resizing. (The packed ring code does not resize in any case.) Let's fix this by bailing out immediately in the split ring code if the requested size cannot be allocated and may_reduce_num has not been specified. While at it, fix a typo in the usage instructions. Fixes: 2a2d1382fe9d ("virtio: Add improved queue allocation API") Cc: stable@vger.kernel.org # v4.6+ Signed-off-by: Cornelia Huck Signed-off-by: Michael S. Tsirkin Reviewed-by: Halil Pasic Reviewed-by: Jens Freimann --- drivers/virtio/virtio_ring.c | 2 ++ include/linux/virtio_ring.h | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index 18846afb39da..5df92c308286 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -882,6 +882,8 @@ static struct virtqueue *vring_create_virtqueue_split( GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO); if (queue) break; + if (!may_reduce_num) + return NULL; } if (!num) diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h index fab02133a919..3dc70adfe5f5 100644 --- a/include/linux/virtio_ring.h +++ b/include/linux/virtio_ring.h @@ -63,7 +63,7 @@ struct virtqueue; /* * Creates a virtqueue and allocates the descriptor ring. If * may_reduce_num is set, then this may allocate a smaller ring than - * expected. The caller should query virtqueue_get_ring_size to learn + * expected. The caller should query virtqueue_get_vring_size to learn * the actual size of the ring. */ struct virtqueue *vring_create_virtqueue(unsigned int index, -- cgit From 49a27e279052cf71ba931a26b00194ff46510480 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Wed, 27 Mar 2019 15:35:45 +0100 Subject: PM / Domains: Add generic data pointer to struct genpd_power_state Add a data pointer to the genpd_power_state struct, to allow a genpd backend driver to store per-state specific data. To introduce the pointer, change the way genpd deals with freeing of the corresponding allocated data. More precisely, clarify the responsibility of whom that shall free the data, by adding a ->free_states() callback to the generic_pm_domain structure. The one allocating the data will be expected to set the callback, to allow genpd to invoke it from genpd_remove(). Co-developed-by: Lina Iyer Acked-by: Daniel Lezcano Signed-off-by: Ulf Hansson [ rjw: Subject & changelog ] Signed-off-by: Rafael J. Wysocki --- drivers/base/power/domain.c | 12 ++++++++++-- include/linux/pm_domain.h | 4 +++- 2 files changed, 13 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index 96a6dc9d305c..ff6f992f7a1d 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -1686,6 +1686,12 @@ out: } EXPORT_SYMBOL_GPL(pm_genpd_remove_subdomain); +static void genpd_free_default_power_state(struct genpd_power_state *states, + unsigned int state_count) +{ + kfree(states); +} + static int genpd_set_default_power_state(struct generic_pm_domain *genpd) { struct genpd_power_state *state; @@ -1696,7 +1702,7 @@ static int genpd_set_default_power_state(struct generic_pm_domain *genpd) genpd->states = state; genpd->state_count = 1; - genpd->free = state; + genpd->free_states = genpd_free_default_power_state; return 0; } @@ -1812,7 +1818,9 @@ static int genpd_remove(struct generic_pm_domain *genpd) list_del(&genpd->gpd_list_node); genpd_unlock(genpd); cancel_work_sync(&genpd->power_off_work); - kfree(genpd->free); + if (genpd->free_states) + genpd->free_states(genpd->states, genpd->state_count); + pr_debug("%s: removed %s\n", __func__, genpd->name); return 0; diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 1ed5874bcee0..8e1399231753 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -69,6 +69,7 @@ struct genpd_power_state { s64 residency_ns; struct fwnode_handle *fwnode; ktime_t idle_time; + void *data; }; struct genpd_lock_ops; @@ -110,9 +111,10 @@ struct generic_pm_domain { struct device *dev); unsigned int flags; /* Bit field of configs for genpd */ struct genpd_power_state *states; + void (*free_states)(struct genpd_power_state *states, + unsigned int state_count); unsigned int state_count; /* number of states */ unsigned int state_idx; /* state that genpd will go to when off */ - void *free; /* Free the state that was allocated for default */ ktime_t on_time; ktime_t accounting_time; const struct genpd_lock_ops *lock_ops; -- cgit From eb594b7325f61835555140922a4cb715264a325c Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Wed, 27 Mar 2019 15:35:46 +0100 Subject: PM / Domains: Add support for CPU devices to genpd To enable a CPU device to be attached to a PM domain managed by genpd, make a few changes to it for convenience. To be able to quickly find out what CPUs are attached to a genpd, which typically becomes useful from a genpd governor as subsequent changes are about to show, add a cpumask to struct generic_pm_domain to be updated when a CPU device gets attached to the genpd containing that cpumask. Also, propagate the cpumask changes upwards in the domain hierarchy to the master PM domains. This way, the cpumask for a genpd hierarchically reflects all CPUs attached to the topology below it. Finally, make this an opt-in feature, to avoid having to manage CPUs and the cpumask for a genpd that don't need it. To that end, add a new genpd configuration bit, GENPD_FLAG_CPU_DOMAIN. Co-developed-by: Lina Iyer Acked-by: Daniel Lezcano Signed-off-by: Ulf Hansson [ rjw: Changelog ] Signed-off-by: Rafael J. Wysocki --- drivers/base/power/domain.c | 65 ++++++++++++++++++++++++++++++++++++++++++++- include/linux/pm_domain.h | 13 +++++++++ 2 files changed, 77 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index ff6f992f7a1d..ecac03dcc9b2 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -22,6 +22,7 @@ #include #include #include +#include #include "power.h" @@ -128,6 +129,7 @@ static const struct genpd_lock_ops genpd_spin_ops = { #define genpd_is_irq_safe(genpd) (genpd->flags & GENPD_FLAG_IRQ_SAFE) #define genpd_is_always_on(genpd) (genpd->flags & GENPD_FLAG_ALWAYS_ON) #define genpd_is_active_wakeup(genpd) (genpd->flags & GENPD_FLAG_ACTIVE_WAKEUP) +#define genpd_is_cpu_domain(genpd) (genpd->flags & GENPD_FLAG_CPU_DOMAIN) static inline bool irq_safe_dev_in_no_sleep_domain(struct device *dev, const struct generic_pm_domain *genpd) @@ -1454,6 +1456,56 @@ static void genpd_free_dev_data(struct device *dev, dev_pm_put_subsys_data(dev); } +static void __genpd_update_cpumask(struct generic_pm_domain *genpd, + int cpu, bool set, unsigned int depth) +{ + struct gpd_link *link; + + if (!genpd_is_cpu_domain(genpd)) + return; + + list_for_each_entry(link, &genpd->slave_links, slave_node) { + struct generic_pm_domain *master = link->master; + + genpd_lock_nested(master, depth + 1); + __genpd_update_cpumask(master, cpu, set, depth + 1); + genpd_unlock(master); + } + + if (set) + cpumask_set_cpu(cpu, genpd->cpus); + else + cpumask_clear_cpu(cpu, genpd->cpus); +} + +static void genpd_update_cpumask(struct generic_pm_domain *genpd, + struct device *dev, bool set) +{ + int cpu; + + if (!genpd_is_cpu_domain(genpd)) + return; + + for_each_possible_cpu(cpu) { + if (get_cpu_device(cpu) == dev) { + __genpd_update_cpumask(genpd, cpu, set, 0); + return; + } + } +} + +static void genpd_set_cpumask(struct generic_pm_domain *genpd, + struct device *dev) +{ + genpd_update_cpumask(genpd, dev, true); +} + +static void genpd_clear_cpumask(struct generic_pm_domain *genpd, + struct device *dev) +{ + genpd_update_cpumask(genpd, dev, false); +} + static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, struct gpd_timing_data *td) { @@ -1475,6 +1527,7 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, genpd_lock(genpd); + genpd_set_cpumask(genpd, dev); dev_pm_domain_set(dev, &genpd->domain); genpd->device_count++; @@ -1532,6 +1585,7 @@ static int genpd_remove_device(struct generic_pm_domain *genpd, genpd->device_count--; genpd->max_off_time_changed = true; + genpd_clear_cpumask(genpd, dev); dev_pm_domain_set(dev, NULL); list_del_init(&pdd->list_node); @@ -1768,11 +1822,18 @@ int pm_genpd_init(struct generic_pm_domain *genpd, if (genpd_is_always_on(genpd) && !genpd_status_on(genpd)) return -EINVAL; + if (genpd_is_cpu_domain(genpd) && + !zalloc_cpumask_var(&genpd->cpus, GFP_KERNEL)) + return -ENOMEM; + /* Use only one "off" state if there were no states declared */ if (genpd->state_count == 0) { ret = genpd_set_default_power_state(genpd); - if (ret) + if (ret) { + if (genpd_is_cpu_domain(genpd)) + free_cpumask_var(genpd->cpus); return ret; + } } else if (!gov && genpd->state_count > 1) { pr_warn("%s: no governor for states\n", genpd->name); } @@ -1818,6 +1879,8 @@ static int genpd_remove(struct generic_pm_domain *genpd) list_del(&genpd->gpd_list_node); genpd_unlock(genpd); cancel_work_sync(&genpd->power_off_work); + if (genpd_is_cpu_domain(genpd)) + free_cpumask_var(genpd->cpus); if (genpd->free_states) genpd->free_states(genpd->states, genpd->state_count); diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 8e1399231753..a6e251fe9deb 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -16,6 +16,7 @@ #include #include #include +#include /* * Flags to control the behaviour of a genpd. @@ -42,11 +43,22 @@ * GENPD_FLAG_ACTIVE_WAKEUP: Instructs genpd to keep the PM domain powered * on, in case any of its attached devices is used * in the wakeup path to serve system wakeups. + * + * GENPD_FLAG_CPU_DOMAIN: Instructs genpd that it should expect to get + * devices attached, which may belong to CPUs or + * possibly have subdomains with CPUs attached. + * This flag enables the genpd backend driver to + * deploy idle power management support for CPUs + * and groups of CPUs. Note that, the backend + * driver must then comply with the so called, + * last-man-standing algorithm, for the CPUs in the + * PM domain. */ #define GENPD_FLAG_PM_CLK (1U << 0) #define GENPD_FLAG_IRQ_SAFE (1U << 1) #define GENPD_FLAG_ALWAYS_ON (1U << 2) #define GENPD_FLAG_ACTIVE_WAKEUP (1U << 3) +#define GENPD_FLAG_CPU_DOMAIN (1U << 4) enum gpd_status { GPD_STATE_ACTIVE = 0, /* PM domain is active */ @@ -94,6 +106,7 @@ struct generic_pm_domain { unsigned int suspended_count; /* System suspend device counter */ unsigned int prepared_count; /* Suspend counter of prepared devices */ unsigned int performance_state; /* Aggregated max performance state */ + cpumask_var_t cpus; /* A cpumask of the attached CPUs */ int (*power_off)(struct generic_pm_domain *domain); int (*power_on)(struct generic_pm_domain *domain); struct opp_table *opp_table; /* OPP table of the genpd */ -- cgit From 6f9b83ac877fb5558d76b9f78590f3afd1bdf421 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Wed, 27 Mar 2019 15:35:47 +0100 Subject: cpuidle: Export the next timer expiration for CPUs To be able to predict the sleep duration for a CPU entering idle, it is essential to know the expiration time of the next timer. Both the teo and the menu cpuidle governors already use this information for CPU idle state selection. Moving forward, a similar prediction needs to be made for a group of idle CPUs rather than for a single one and the following changes implement a new genpd governor for that purpose. In order to support that feature, add a new function called tick_nohz_get_next_hrtimer() that will return the next hrtimer expiration time of a given CPU to be invoked after deciding whether or not to stop the scheduler tick on that CPU. Make the cpuidle core call tick_nohz_get_next_hrtimer() right before invoking the ->enter() callback provided by the cpuidle driver for the given state and store its return value in the per-CPU struct cpuidle_device, so as to make it available to code outside of cpuidle. Note that at the point when cpuidle calls tick_nohz_get_next_hrtimer(), the governor's ->select() callback has already returned and indicated whether or not the tick should be stopped, so in fact the value returned by tick_nohz_get_next_hrtimer() always is the next hrtimer expiration time for the given CPU, possibly including the tick (if it hasn't been stopped). Co-developed-by: Lina Iyer Co-developed-by: Daniel Lezcano Acked-by: Daniel Lezcano Signed-off-by: Ulf Hansson [ rjw: Subject & changelog ] Signed-off-by: Rafael J. Wysocki --- drivers/cpuidle/cpuidle.c | 19 +++++++++++++++++-- include/linux/cpuidle.h | 1 + include/linux/tick.h | 7 ++++++- kernel/time/tick-sched.c | 12 ++++++++++++ 4 files changed, 36 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 7f108309e871..0f4b7c45df3e 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -328,9 +328,23 @@ int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, int cpuidle_enter(struct cpuidle_driver *drv, struct cpuidle_device *dev, int index) { + int ret = 0; + + /* + * Store the next hrtimer, which becomes either next tick or the next + * timer event, whatever expires first. Additionally, to make this data + * useful for consumers outside cpuidle, we rely on that the governor's + * ->select() callback have decided, whether to stop the tick or not. + */ + WRITE_ONCE(dev->next_hrtimer, tick_nohz_get_next_hrtimer()); + if (cpuidle_state_is_coupled(drv, index)) - return cpuidle_enter_state_coupled(dev, drv, index); - return cpuidle_enter_state(dev, drv, index); + ret = cpuidle_enter_state_coupled(dev, drv, index); + else + ret = cpuidle_enter_state(dev, drv, index); + + WRITE_ONCE(dev->next_hrtimer, 0); + return ret; } /** @@ -511,6 +525,7 @@ static void __cpuidle_device_init(struct cpuidle_device *dev) { memset(dev->states_usage, 0, sizeof(dev->states_usage)); dev->last_residency = 0; + dev->next_hrtimer = 0; } /** diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h index 3b39472324a3..bb9a0db89f1a 100644 --- a/include/linux/cpuidle.h +++ b/include/linux/cpuidle.h @@ -83,6 +83,7 @@ struct cpuidle_device { unsigned int use_deepest_state:1; unsigned int poll_time_limit:1; unsigned int cpu; + ktime_t next_hrtimer; int last_residency; struct cpuidle_state_usage states_usage[CPUIDLE_STATE_MAX]; diff --git a/include/linux/tick.h b/include/linux/tick.h index 55388ab45fd4..8891b5ac3e40 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -122,6 +122,7 @@ extern void tick_nohz_idle_enter(void); extern void tick_nohz_idle_exit(void); extern void tick_nohz_irq_exit(void); extern bool tick_nohz_idle_got_tick(void); +extern ktime_t tick_nohz_get_next_hrtimer(void); extern ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next); extern unsigned long tick_nohz_get_idle_calls(void); extern unsigned long tick_nohz_get_idle_calls_cpu(int cpu); @@ -145,7 +146,11 @@ static inline void tick_nohz_idle_restart_tick(void) { } static inline void tick_nohz_idle_enter(void) { } static inline void tick_nohz_idle_exit(void) { } static inline bool tick_nohz_idle_got_tick(void) { return false; } - +static inline ktime_t tick_nohz_get_next_hrtimer(void) +{ + /* Next wake up is the tick period, assume it starts now */ + return ktime_add(ktime_get(), TICK_NSEC); +} static inline ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next) { *delta_next = TICK_NSEC; diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 6fa52cd6df0b..8d18e03124ff 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -1022,6 +1022,18 @@ bool tick_nohz_idle_got_tick(void) return false; } +/** + * tick_nohz_get_next_hrtimer - return the next expiration time for the hrtimer + * or the tick, whatever that expires first. Note that, if the tick has been + * stopped, it returns the next hrtimer. + * + * Called from power state control code with interrupts disabled + */ +ktime_t tick_nohz_get_next_hrtimer(void) +{ + return __this_cpu_read(tick_cpu_device.evtdev)->next_event; +} + /** * tick_nohz_get_sleep_length - return the expected length of the current sleep * @delta_next: duration until the next event if the tick cannot be stopped -- cgit From 2f36bde0fc8f1ab79d54bd2caa7c1cf874fd2206 Mon Sep 17 00:00:00 2001 From: "Andrew-sh.Cheng" Date: Fri, 29 Mar 2019 14:46:10 +0800 Subject: OPP: Introduce dev_pm_opp_find_freq_ceil_by_volt() This patch introduces a new helper routine in the OPP core, which returns the OPP with the highest frequency which has voltage less than or equal to the target voltage passed to the helper. Signed-off-by: Andrew-sh.Cheng [ Viresh: Massaged the commit log and renamed the helper with some cleanups. ] Signed-off-by: Viresh Kumar --- drivers/opp/core.c | 54 ++++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/pm_opp.h | 8 ++++++++ 2 files changed, 62 insertions(+) (limited to 'include/linux') diff --git a/drivers/opp/core.c b/drivers/opp/core.c index 0420f7e8ad5b..0e7703fe733f 100644 --- a/drivers/opp/core.c +++ b/drivers/opp/core.c @@ -526,6 +526,60 @@ struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, } EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_floor); +/** + * dev_pm_opp_find_freq_ceil_by_volt() - Find OPP with highest frequency for + * target voltage. + * @dev: Device for which we do this operation. + * @u_volt: Target voltage. + * + * Search for OPP with highest (ceil) frequency and has voltage <= u_volt. + * + * Return: matching *opp, else returns ERR_PTR in case of error which should be + * handled using IS_ERR. + * + * Error return values can be: + * EINVAL: bad parameters + * + * The callers are required to call dev_pm_opp_put() for the returned OPP after + * use. + */ +struct dev_pm_opp *dev_pm_opp_find_freq_ceil_by_volt(struct device *dev, + unsigned long u_volt) +{ + struct opp_table *opp_table; + struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ERANGE); + + if (!dev || !u_volt) { + dev_err(dev, "%s: Invalid argument volt=%lu\n", __func__, + u_volt); + return ERR_PTR(-EINVAL); + } + + opp_table = _find_opp_table(dev); + if (IS_ERR(opp_table)) + return ERR_CAST(opp_table); + + mutex_lock(&opp_table->lock); + + list_for_each_entry(temp_opp, &opp_table->opp_list, node) { + if (temp_opp->available) { + if (temp_opp->supplies[0].u_volt > u_volt) + break; + opp = temp_opp; + } + } + + /* Increment the reference count of OPP */ + if (!IS_ERR(opp)) + dev_pm_opp_get(opp); + + mutex_unlock(&opp_table->lock); + dev_pm_opp_put_opp_table(opp_table); + + return opp; +} +EXPORT_SYMBOL_GPL(dev_pm_opp_find_freq_ceil_by_volt); + static int _set_opp_voltage(struct device *dev, struct regulator *reg, struct dev_pm_opp_supply *supply) { diff --git a/include/linux/pm_opp.h b/include/linux/pm_opp.h index 24c757a32a7b..b150fe97ce5a 100644 --- a/include/linux/pm_opp.h +++ b/include/linux/pm_opp.h @@ -102,6 +102,8 @@ struct dev_pm_opp *dev_pm_opp_find_freq_exact(struct device *dev, struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, unsigned long *freq); +struct dev_pm_opp *dev_pm_opp_find_freq_ceil_by_volt(struct device *dev, + unsigned long u_volt); struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev, unsigned long *freq); @@ -207,6 +209,12 @@ static inline struct dev_pm_opp *dev_pm_opp_find_freq_floor(struct device *dev, return ERR_PTR(-ENOTSUPP); } +static inline struct dev_pm_opp *dev_pm_opp_find_freq_ceil_by_volt(struct device *dev, + unsigned long u_volt) +{ + return ERR_PTR(-ENOTSUPP); +} + static inline struct dev_pm_opp *dev_pm_opp_find_freq_ceil(struct device *dev, unsigned long *freq) { -- cgit From 12a30a7fc142a123c61da9623bd824d95d36c12e Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 4 Apr 2019 13:43:12 -0400 Subject: locking/rwsem: Move rwsem internal function declarations to rwsem-xadd.h We don't need to expose rwsem internal functions which are not supposed to be called directly from other kernel code. Signed-off-by: Waiman Long Acked-by: Peter Zijlstra Acked-by: Will Deacon Acked-by: Davidlohr Bueso Cc: Andrew Morton Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Davidlohr Bueso Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Tim Chen Link: http://lkml.kernel.org/r/20190404174320.22416-4-longman@redhat.com Signed-off-by: Ingo Molnar --- include/linux/rwsem.h | 7 ------- kernel/locking/rwsem.h | 7 +++++++ 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index 0fc41062c649..b44e533235c7 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -46,13 +46,6 @@ struct rw_semaphore { */ #define RWSEM_OWNER_UNKNOWN ((struct task_struct *)-2L) -extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_down_read_failed_killable(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_down_write_failed_killable(struct rw_semaphore *sem); -extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *); -extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem); - /* In all implementations count != 0 means locked */ static inline int rwsem_is_locked(struct rw_semaphore *sem) { diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h index ee24c4f257a5..19997c82270b 100644 --- a/kernel/locking/rwsem.h +++ b/kernel/locking/rwsem.h @@ -153,6 +153,13 @@ static inline void rwsem_clear_reader_owned(struct rw_semaphore *sem) } #endif +extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem); +extern struct rw_semaphore *rwsem_down_read_failed_killable(struct rw_semaphore *sem); +extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem); +extern struct rw_semaphore *rwsem_down_write_failed_killable(struct rw_semaphore *sem); +extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem); +extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem); + /* * lock for reading */ -- cgit From 364f784f048c984721986db90c95ca8350213c91 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 4 Apr 2019 13:43:20 -0400 Subject: locking/rwsem: Optimize rwsem structure for uncontended lock acquisition For an uncontended rwsem, count and owner are the only fields a task needs to touch when acquiring the rwsem. So they are put next to each other to increase the chance that they will share the same cacheline. On a ThunderX2 99xx (arm64) system with 32K L1 cache and 256K L2 cache, a rwsem locking microbenchmark with one locking thread was run to write-lock and write-unlock an array of rwsems separated 2 cachelines apart in a 1M byte memory block. The locking rates (kops/s) of the microbenchmark when the rwsems are at various "long" (8-byte) offsets from beginning of the cacheline before and after the patch were as follows: Cacheline Offset Pre-patch Post-patch ---------------- --------- ---------- 0 17,449 16,588 1 17,450 16,465 2 17,450 16,460 3 17,453 16,462 4 14,867 16,471 5 14,867 16,470 6 14,853 16,464 7 14,867 13,172 Before the patch, the count and owner are 4 "long"s apart. After the patch, they are only 1 "long" apart. The rwsem data have to be loaded from the L3 cache for each access. It can be seen that the locking rates are more consistent after the patch than before. Note that for this particular system, the performance drop happens whenever the count and owner are at an odd multiples of "long"s apart. No performance drop was observed when only a single rwsem was used (hot cache). So the drop is likely just an idiosyncrasy of the cache architecture of this chip than an inherent problem with the patch. Suggested-by: Linus Torvalds Signed-off-by: Waiman Long Acked-by: Peter Zijlstra Cc: Andrew Morton Cc: Arnd Bergmann Cc: Borislav Petkov Cc: Davidlohr Bueso Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Tim Chen Cc: Will Deacon Link: http://lkml.kernel.org/r/20190404174320.22416-12-longman@redhat.com Signed-off-by: Ingo Molnar --- include/linux/rwsem.h | 21 +++++++++++++++------ 1 file changed, 15 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h index b44e533235c7..2ea18a3def04 100644 --- a/include/linux/rwsem.h +++ b/include/linux/rwsem.h @@ -20,21 +20,30 @@ #include #endif -struct rw_semaphore; - -/* All arch specific implementations share the same struct */ +/* + * For an uncontended rwsem, count and owner are the only fields a task + * needs to touch when acquiring the rwsem. So they are put next to each + * other to increase the chance that they will share the same cacheline. + * + * In a contended rwsem, the owner is likely the most frequently accessed + * field in the structure as the optimistic waiter that holds the osq lock + * will spin on owner. For an embedded rwsem, other hot fields in the + * containing structure should be moved further away from the rwsem to + * reduce the chance that they will share the same cacheline causing + * cacheline bouncing problem. + */ struct rw_semaphore { atomic_long_t count; - struct list_head wait_list; - raw_spinlock_t wait_lock; #ifdef CONFIG_RWSEM_SPIN_ON_OWNER - struct optimistic_spin_queue osq; /* spinner MCS lock */ /* * Write owner. Used as a speculative check to see * if the owner is running on the cpu. */ struct task_struct *owner; + struct optimistic_spin_queue osq; /* spinner MCS lock */ #endif + raw_spinlock_t wait_lock; + struct list_head wait_list; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif -- cgit From 1b8f21b74c3c9c82fce5a751d7aefb7cc0b8d33d Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 9 Apr 2019 06:31:21 +0800 Subject: blk-mq: introduce blk_mq_complete_request_sync() In NVMe's error handler, follows the typical steps of tearing down hardware for recovering controller: 1) stop blk_mq hw queues 2) stop the real hw queues 3) cancel in-flight requests via blk_mq_tagset_busy_iter(tags, cancel_request, ...) cancel_request(): mark the request as abort blk_mq_complete_request(req); 4) destroy real hw queues However, there may be race between #3 and #4, because blk_mq_complete_request() may run q->mq_ops->complete(rq) remotelly and asynchronously, and ->complete(rq) may be run after #4. This patch introduces blk_mq_complete_request_sync() for fixing the above race. Cc: Sagi Grimberg Cc: Bart Van Assche Cc: James Smart Cc: linux-nvme@lists.infradead.org Reviewed-by: Keith Busch Reviewed-by: Christoph Hellwig Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-mq.c | 7 +++++++ include/linux/blk-mq.h | 1 + 2 files changed, 8 insertions(+) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index a9354835cf51..9516304a38ee 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -654,6 +654,13 @@ bool blk_mq_complete_request(struct request *rq) } EXPORT_SYMBOL(blk_mq_complete_request); +void blk_mq_complete_request_sync(struct request *rq) +{ + WRITE_ONCE(rq->state, MQ_RQ_COMPLETE); + rq->q->mq_ops->complete(rq); +} +EXPORT_SYMBOL_GPL(blk_mq_complete_request_sync); + int blk_mq_request_started(struct request *rq) { return blk_mq_rq_state(rq) != MQ_RQ_IDLE; diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index cb2aa7ecafff..db29928de467 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -302,6 +302,7 @@ void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list); void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs); bool blk_mq_complete_request(struct request *rq); +void blk_mq_complete_request_sync(struct request *rq); bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list, struct bio *bio); bool blk_mq_queue_stopped(struct request_queue *q); -- cgit From 7c2e07130090ae001a97a6b65597830d6815e93e Mon Sep 17 00:00:00 2001 From: David Müller Date: Mon, 8 Apr 2019 15:33:54 +0200 Subject: clk: x86: Add system specific quirk to mark clocks as critical MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Since commit 648e921888ad ("clk: x86: Stop marking clocks as CLK_IS_CRITICAL"), the pmc_plt_clocks of the Bay Trail SoC are unconditionally gated off. Unfortunately this will break systems where these clocks are used for external purposes beyond the kernel's knowledge. Fix it by implementing a system specific quirk to mark the necessary pmc_plt_clks as critical. Fixes: 648e921888ad ("clk: x86: Stop marking clocks as CLK_IS_CRITICAL") Signed-off-by: David Müller Signed-off-by: Hans de Goede Reviewed-by: Andy Shevchenko Signed-off-by: Stephen Boyd --- drivers/clk/x86/clk-pmc-atom.c | 14 +++++++++++--- drivers/platform/x86/pmc_atom.c | 21 +++++++++++++++++++++ include/linux/platform_data/x86/clk-pmc-atom.h | 3 +++ 3 files changed, 35 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/clk/x86/clk-pmc-atom.c b/drivers/clk/x86/clk-pmc-atom.c index d977193842df..19174835693b 100644 --- a/drivers/clk/x86/clk-pmc-atom.c +++ b/drivers/clk/x86/clk-pmc-atom.c @@ -165,7 +165,7 @@ static const struct clk_ops plt_clk_ops = { }; static struct clk_plt *plt_clk_register(struct platform_device *pdev, int id, - void __iomem *base, + const struct pmc_clk_data *pmc_data, const char **parent_names, int num_parents) { @@ -184,9 +184,17 @@ static struct clk_plt *plt_clk_register(struct platform_device *pdev, int id, init.num_parents = num_parents; pclk->hw.init = &init; - pclk->reg = base + PMC_CLK_CTL_OFFSET + id * PMC_CLK_CTL_SIZE; + pclk->reg = pmc_data->base + PMC_CLK_CTL_OFFSET + id * PMC_CLK_CTL_SIZE; spin_lock_init(&pclk->lock); + /* + * On some systems, the pmc_plt_clocks already enabled by the + * firmware are being marked as critical to avoid them being + * gated by the clock framework. + */ + if (pmc_data->critical && plt_clk_is_enabled(&pclk->hw)) + init.flags |= CLK_IS_CRITICAL; + ret = devm_clk_hw_register(&pdev->dev, &pclk->hw); if (ret) { pclk = ERR_PTR(ret); @@ -332,7 +340,7 @@ static int plt_clk_probe(struct platform_device *pdev) return PTR_ERR(parent_names); for (i = 0; i < PMC_CLK_NUM; i++) { - data->clks[i] = plt_clk_register(pdev, i, pmc_data->base, + data->clks[i] = plt_clk_register(pdev, i, pmc_data, parent_names, data->nparents); if (IS_ERR(data->clks[i])) { err = PTR_ERR(data->clks[i]); diff --git a/drivers/platform/x86/pmc_atom.c b/drivers/platform/x86/pmc_atom.c index 8f018b3f3cd4..eaec2d306481 100644 --- a/drivers/platform/x86/pmc_atom.c +++ b/drivers/platform/x86/pmc_atom.c @@ -17,6 +17,7 @@ #include #include +#include #include #include #include @@ -391,11 +392,27 @@ static int pmc_dbgfs_register(struct pmc_dev *pmc) } #endif /* CONFIG_DEBUG_FS */ +/* + * Some systems need one or more of their pmc_plt_clks to be + * marked as critical. + */ +static const struct dmi_system_id critclk_systems[] __initconst = { + { + .ident = "MPL CEC1x", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "MPL AG"), + DMI_MATCH(DMI_PRODUCT_NAME, "CEC10 Family"), + }, + }, + { /*sentinel*/ } +}; + static int pmc_setup_clks(struct pci_dev *pdev, void __iomem *pmc_regmap, const struct pmc_data *pmc_data) { struct platform_device *clkdev; struct pmc_clk_data *clk_data; + const struct dmi_system_id *d = dmi_first_match(critclk_systems); clk_data = kzalloc(sizeof(*clk_data), GFP_KERNEL); if (!clk_data) @@ -403,6 +420,10 @@ static int pmc_setup_clks(struct pci_dev *pdev, void __iomem *pmc_regmap, clk_data->base = pmc_regmap; /* offset is added by client */ clk_data->clks = pmc_data->clks; + if (d) { + clk_data->critical = true; + pr_info("%s critclks quirk enabled\n", d->ident); + } clkdev = platform_device_register_data(&pdev->dev, "clk-pmc-atom", PLATFORM_DEVID_NONE, diff --git a/include/linux/platform_data/x86/clk-pmc-atom.h b/include/linux/platform_data/x86/clk-pmc-atom.h index 3ab892208343..7a37ac27d0fb 100644 --- a/include/linux/platform_data/x86/clk-pmc-atom.h +++ b/include/linux/platform_data/x86/clk-pmc-atom.h @@ -35,10 +35,13 @@ struct pmc_clk { * * @base: PMC clock register base offset * @clks: pointer to set of registered clocks, typically 0..5 + * @critical: flag to indicate if firmware enabled pmc_plt_clks + * should be marked as critial or not */ struct pmc_clk_data { void __iomem *base; const struct pmc_clk *clks; + bool critical; }; #endif /* __PLATFORM_DATA_X86_CLK_PMC_ATOM_H */ -- cgit From 8065a779f17e94536a1c4dcee4f9d88011672f97 Mon Sep 17 00:00:00 2001 From: Si-Wei Liu Date: Mon, 8 Apr 2019 19:45:27 -0400 Subject: failover: allow name change on IFF_UP slave interfaces When a netdev appears through hot plug then gets enslaved by a failover master that is already up and running, the slave will be opened right away after getting enslaved. Today there's a race that userspace (udev) may fail to rename the slave if the kernel (net_failover) opens the slave earlier than when the userspace rename happens. Unlike bond or team, the primary slave of failover can't be renamed by userspace ahead of time, since the kernel initiated auto-enslavement is unable to, or rather, is never meant to be synchronized with the rename request from userspace. As the failover slave interfaces are not designed to be operated directly by userspace apps: IP configuration, filter rules with regard to network traffic passing and etc., should all be done on master interface. In general, userspace apps only care about the name of master interface, while slave names are less important as long as admin users can see reliable names that may carry other information describing the netdev. For e.g., they can infer that "ens3nsby" is a standby slave of "ens3", while for a name like "eth0" they can't tell which master it belongs to. Historically the name of IFF_UP interface can't be changed because there might be admin script or management software that is already relying on such behavior and assumes that the slave name can't be changed once UP. But failover is special: with the in-kernel auto-enslavement mechanism, the userspace expectation for device enumeration and bring-up order is already broken. Previously initramfs and various userspace config tools were modified to bypass failover slaves because of auto-enslavement and duplicate MAC address. Similarly, in case that users care about seeing reliable slave name, the new type of failover slaves needs to be taken care of specifically in userspace anyway. It's less risky to lift up the rename restriction on failover slave which is already UP. Although it's possible this change may potentially break userspace component (most likely configuration scripts or management software) that assumes slave name can't be changed while UP, it's relatively a limited and controllable set among all userspace components, which can be fixed specifically to listen for the rename events on failover slaves. Userspace component interacting with slaves is expected to be changed to operate on failover master interface instead, as the failover slave is dynamic in nature which may come and go at any point. The goal is to make the role of failover slaves less relevant, and userspace components should only deal with failover master in the long run. Fixes: 30c8bd5aa8b2 ("net: Introduce generic failover module") Signed-off-by: Si-Wei Liu Reviewed-by: Liran Alon Acked-by: Sridhar Samudrala Signed-off-by: David S. Miller --- include/linux/netdevice.h | 3 +++ net/core/dev.c | 16 +++++++++++++++- net/core/failover.c | 6 +++--- 3 files changed, 21 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 26f69cf763f4..324e872c91d1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1500,6 +1500,7 @@ struct net_device_ops { * @IFF_FAILOVER: device is a failover master device * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device * @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device + * @IFF_LIVE_RENAME_OK: rename is allowed while device is up and running */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1532,6 +1533,7 @@ enum netdev_priv_flags { IFF_FAILOVER = 1<<27, IFF_FAILOVER_SLAVE = 1<<28, IFF_L3MDEV_RX_HANDLER = 1<<29, + IFF_LIVE_RENAME_OK = 1<<30, }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1563,6 +1565,7 @@ enum netdev_priv_flags { #define IFF_FAILOVER IFF_FAILOVER #define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE #define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER +#define IFF_LIVE_RENAME_OK IFF_LIVE_RENAME_OK /** * struct net_device - The DEVICE structure. diff --git a/net/core/dev.c b/net/core/dev.c index fdcff29df915..f409406254dd 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1184,7 +1184,21 @@ int dev_change_name(struct net_device *dev, const char *newname) BUG_ON(!dev_net(dev)); net = dev_net(dev); - if (dev->flags & IFF_UP) + + /* Some auto-enslaved devices e.g. failover slaves are + * special, as userspace might rename the device after + * the interface had been brought up and running since + * the point kernel initiated auto-enslavement. Allow + * live name change even when these slave devices are + * up and running. + * + * Typically, users of these auto-enslaving devices + * don't actually care about slave name change, as + * they are supposed to operate on master interface + * directly. + */ + if (dev->flags & IFF_UP && + likely(!(dev->priv_flags & IFF_LIVE_RENAME_OK))) return -EBUSY; write_seqcount_begin(&devnet_rename_seq); diff --git a/net/core/failover.c b/net/core/failover.c index 4a92a98ccce9..b5cd3c727285 100644 --- a/net/core/failover.c +++ b/net/core/failover.c @@ -80,14 +80,14 @@ static int failover_slave_register(struct net_device *slave_dev) goto err_upper_link; } - slave_dev->priv_flags |= IFF_FAILOVER_SLAVE; + slave_dev->priv_flags |= (IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK); if (fops && fops->slave_register && !fops->slave_register(slave_dev, failover_dev)) return NOTIFY_OK; netdev_upper_dev_unlink(slave_dev, failover_dev); - slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE; + slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK); err_upper_link: netdev_rx_handler_unregister(slave_dev); done: @@ -121,7 +121,7 @@ int failover_slave_unregister(struct net_device *slave_dev) netdev_rx_handler_unregister(slave_dev); netdev_upper_dev_unlink(slave_dev, failover_dev); - slave_dev->priv_flags &= ~IFF_FAILOVER_SLAVE; + slave_dev->priv_flags &= ~(IFF_FAILOVER_SLAVE | IFF_LIVE_RENAME_OK); if (fops && fops->slave_unregister && !fops->slave_unregister(slave_dev, failover_dev)) -- cgit From d808b7f759b50acf0784ce6230ffa63e12ef465d Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Tue, 9 Apr 2019 10:03:59 -0600 Subject: nvmet: fix discover log page when offsets are used The nvme target hadn't been taking the Get Log Page offset parameter into consideration, and so has been returning corrupted log pages when offsets are used. Since many tools, including nvme-cli, split the log request to 4k, we've been breaking discovery log responses when more than 3 subsystems exist. Fix the returned data by internally generating the entire discovery log page and copying only the requested bytes into the user buffer. The command log page offset type has been modified to a native __le64 to make it easier to extract the value from a command. Signed-off-by: Keith Busch Tested-by: Minwoo Im Reviewed-by: Chaitanya Kulkarni Reviewed-by: Hannes Reinecke Reviewed-by: James Smart Signed-off-by: Christoph Hellwig --- drivers/nvme/target/admin-cmd.c | 5 +++ drivers/nvme/target/discovery.c | 68 +++++++++++++++++++++++++++-------------- drivers/nvme/target/nvmet.h | 1 + include/linux/nvme.h | 9 ++++-- 4 files changed, 58 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 76250181fee0..9f72d515fc4b 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -24,6 +24,11 @@ u32 nvmet_get_log_page_len(struct nvme_command *cmd) return len; } +u64 nvmet_get_log_page_offset(struct nvme_command *cmd) +{ + return le64_to_cpu(cmd->get_log_page.lpo); +} + static void nvmet_execute_get_log_page_noop(struct nvmet_req *req) { nvmet_req_complete(req, nvmet_zero_sgl(req, 0, req->data_len)); diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c index c872b47a88f3..33ed95e72d6b 100644 --- a/drivers/nvme/target/discovery.c +++ b/drivers/nvme/target/discovery.c @@ -131,54 +131,76 @@ static void nvmet_set_disc_traddr(struct nvmet_req *req, struct nvmet_port *port memcpy(traddr, port->disc_addr.traddr, NVMF_TRADDR_SIZE); } +static size_t discovery_log_entries(struct nvmet_req *req) +{ + struct nvmet_ctrl *ctrl = req->sq->ctrl; + struct nvmet_subsys_link *p; + struct nvmet_port *r; + size_t entries = 0; + + list_for_each_entry(p, &req->port->subsystems, entry) { + if (!nvmet_host_allowed(p->subsys, ctrl->hostnqn)) + continue; + entries++; + } + list_for_each_entry(r, &req->port->referrals, entry) + entries++; + return entries; +} + static void nvmet_execute_get_disc_log_page(struct nvmet_req *req) { const int entry_size = sizeof(struct nvmf_disc_rsp_page_entry); struct nvmet_ctrl *ctrl = req->sq->ctrl; struct nvmf_disc_rsp_page_hdr *hdr; + u64 offset = nvmet_get_log_page_offset(req->cmd); size_t data_len = nvmet_get_log_page_len(req->cmd); - size_t alloc_len = max(data_len, sizeof(*hdr)); - int residual_len = data_len - sizeof(*hdr); + size_t alloc_len; struct nvmet_subsys_link *p; struct nvmet_port *r; u32 numrec = 0; u16 status = 0; + void *buffer; + + /* Spec requires dword aligned offsets */ + if (offset & 0x3) { + status = NVME_SC_INVALID_FIELD | NVME_SC_DNR; + goto out; + } /* * Make sure we're passing at least a buffer of response header size. * If host provided data len is less than the header size, only the * number of bytes requested by host will be sent to host. */ - hdr = kzalloc(alloc_len, GFP_KERNEL); - if (!hdr) { + down_read(&nvmet_config_sem); + alloc_len = sizeof(*hdr) + entry_size * discovery_log_entries(req); + buffer = kzalloc(alloc_len, GFP_KERNEL); + if (!buffer) { + up_read(&nvmet_config_sem); status = NVME_SC_INTERNAL; goto out; } - down_read(&nvmet_config_sem); + hdr = buffer; list_for_each_entry(p, &req->port->subsystems, entry) { + char traddr[NVMF_TRADDR_SIZE]; + if (!nvmet_host_allowed(p->subsys, ctrl->hostnqn)) continue; - if (residual_len >= entry_size) { - char traddr[NVMF_TRADDR_SIZE]; - - nvmet_set_disc_traddr(req, req->port, traddr); - nvmet_format_discovery_entry(hdr, req->port, - p->subsys->subsysnqn, traddr, - NVME_NQN_NVME, numrec); - residual_len -= entry_size; - } + + nvmet_set_disc_traddr(req, req->port, traddr); + nvmet_format_discovery_entry(hdr, req->port, + p->subsys->subsysnqn, traddr, + NVME_NQN_NVME, numrec); numrec++; } list_for_each_entry(r, &req->port->referrals, entry) { - if (residual_len >= entry_size) { - nvmet_format_discovery_entry(hdr, r, - NVME_DISC_SUBSYS_NAME, - r->disc_addr.traddr, - NVME_NQN_DISC, numrec); - residual_len -= entry_size; - } + nvmet_format_discovery_entry(hdr, r, + NVME_DISC_SUBSYS_NAME, + r->disc_addr.traddr, + NVME_NQN_DISC, numrec); numrec++; } @@ -190,8 +212,8 @@ static void nvmet_execute_get_disc_log_page(struct nvmet_req *req) up_read(&nvmet_config_sem); - status = nvmet_copy_to_sgl(req, 0, hdr, data_len); - kfree(hdr); + status = nvmet_copy_to_sgl(req, 0, buffer + offset, data_len); + kfree(buffer); out: nvmet_req_complete(req, status); } diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 51e49efd7849..1653d19b187f 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -428,6 +428,7 @@ u16 nvmet_copy_from_sgl(struct nvmet_req *req, off_t off, void *buf, u16 nvmet_zero_sgl(struct nvmet_req *req, off_t off, size_t len); u32 nvmet_get_log_page_len(struct nvme_command *cmd); +u64 nvmet_get_log_page_offset(struct nvme_command *cmd); extern struct list_head *nvmet_ports; void nvmet_port_disc_changed(struct nvmet_port *port, diff --git a/include/linux/nvme.h b/include/linux/nvme.h index baa49e6a23cc..c40720cb59ac 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -967,8 +967,13 @@ struct nvme_get_log_page_command { __le16 numdl; __le16 numdu; __u16 rsvd11; - __le32 lpol; - __le32 lpou; + union { + struct { + __le32 lpol; + __le32 lpou; + }; + __le64 lpo; + }; __u32 rsvd14[2]; }; -- cgit From af6b61d7ef58099c82d854395a0e002be6bd036c Mon Sep 17 00:00:00 2001 From: Trond Myklebust Date: Thu, 11 Apr 2019 15:16:52 -0400 Subject: Revert "SUNRPC: Micro-optimise when the task is known not to be sleeping" This reverts commit 009a82f6437490c262584d65a14094a818bcb747. The ability to optimise here relies on compiler being able to optimise away tail calls to avoid stack overflows. Unfortunately, we are seeing reports of problems, so let's just revert. Reported-by: Daniel Mack Signed-off-by: Trond Myklebust --- include/linux/sunrpc/sched.h | 8 -------- net/sunrpc/clnt.c | 45 ++++++++------------------------------------ 2 files changed, 8 insertions(+), 45 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h index ec861cd0cfe8..52d41d0c1ae1 100644 --- a/include/linux/sunrpc/sched.h +++ b/include/linux/sunrpc/sched.h @@ -304,12 +304,4 @@ rpc_clnt_swap_deactivate(struct rpc_clnt *clnt) } #endif /* CONFIG_SUNRPC_SWAP */ -static inline bool -rpc_task_need_resched(const struct rpc_task *task) -{ - if (RPC_IS_QUEUED(task) || task->tk_callback) - return true; - return false; -} - #endif /* _LINUX_SUNRPC_SCHED_H_ */ diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 187d10443a15..1d0395ef62c9 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1540,7 +1540,6 @@ call_start(struct rpc_task *task) clnt->cl_stats->rpccnt++; task->tk_action = call_reserve; rpc_task_set_transport(task, clnt); - call_reserve(task); } /* @@ -1554,9 +1553,6 @@ call_reserve(struct rpc_task *task) task->tk_status = 0; task->tk_action = call_reserveresult; xprt_reserve(task); - if (rpc_task_need_resched(task)) - return; - call_reserveresult(task); } static void call_retry_reserve(struct rpc_task *task); @@ -1579,7 +1575,6 @@ call_reserveresult(struct rpc_task *task) if (status >= 0) { if (task->tk_rqstp) { task->tk_action = call_refresh; - call_refresh(task); return; } @@ -1605,7 +1600,6 @@ call_reserveresult(struct rpc_task *task) /* fall through */ case -EAGAIN: /* woken up; retry */ task->tk_action = call_retry_reserve; - call_retry_reserve(task); return; case -EIO: /* probably a shutdown */ break; @@ -1628,9 +1622,6 @@ call_retry_reserve(struct rpc_task *task) task->tk_status = 0; task->tk_action = call_reserveresult; xprt_retry_reserve(task); - if (rpc_task_need_resched(task)) - return; - call_reserveresult(task); } /* @@ -1645,9 +1636,6 @@ call_refresh(struct rpc_task *task) task->tk_status = 0; task->tk_client->cl_stats->rpcauthrefresh++; rpcauth_refreshcred(task); - if (rpc_task_need_resched(task)) - return; - call_refreshresult(task); } /* @@ -1666,7 +1654,6 @@ call_refreshresult(struct rpc_task *task) case 0: if (rpcauth_uptodatecred(task)) { task->tk_action = call_allocate; - call_allocate(task); return; } /* Use rate-limiting and a max number of retries if refresh @@ -1685,7 +1672,6 @@ call_refreshresult(struct rpc_task *task) task->tk_cred_retry--; dprintk("RPC: %5u %s: retry refresh creds\n", task->tk_pid, __func__); - call_refresh(task); return; } dprintk("RPC: %5u %s: refresh creds failed with error %d\n", @@ -1711,10 +1697,8 @@ call_allocate(struct rpc_task *task) task->tk_status = 0; task->tk_action = call_encode; - if (req->rq_buffer) { - call_encode(task); + if (req->rq_buffer) return; - } if (proc->p_proc != 0) { BUG_ON(proc->p_arglen == 0); @@ -1740,12 +1724,8 @@ call_allocate(struct rpc_task *task) status = xprt->ops->buf_alloc(task); xprt_inject_disconnect(xprt); - if (status == 0) { - if (rpc_task_need_resched(task)) - return; - call_encode(task); + if (status == 0) return; - } if (status != -ENOMEM) { rpc_exit(task, status); return; @@ -1828,8 +1808,12 @@ call_encode(struct rpc_task *task) xprt_request_enqueue_receive(task); xprt_request_enqueue_transmit(task); out: - task->tk_action = call_bind; - call_bind(task); + task->tk_action = call_transmit; + /* Check that the connection is OK */ + if (!xprt_bound(task->tk_xprt)) + task->tk_action = call_bind; + else if (!xprt_connected(task->tk_xprt)) + task->tk_action = call_connect; } /* @@ -1847,7 +1831,6 @@ rpc_task_handle_transmitted(struct rpc_task *task) { xprt_end_transmit(task); task->tk_action = call_transmit_status; - call_transmit_status(task); } /* @@ -1865,7 +1848,6 @@ call_bind(struct rpc_task *task) if (xprt_bound(xprt)) { task->tk_action = call_connect; - call_connect(task); return; } @@ -1896,7 +1878,6 @@ call_bind_status(struct rpc_task *task) dprint_status(task); task->tk_status = 0; task->tk_action = call_connect; - call_connect(task); return; } @@ -1981,7 +1962,6 @@ call_connect(struct rpc_task *task) if (xprt_connected(xprt)) { task->tk_action = call_transmit; - call_transmit(task); return; } @@ -2051,7 +2031,6 @@ call_connect_status(struct rpc_task *task) case 0: clnt->cl_stats->netreconn++; task->tk_action = call_transmit; - call_transmit(task); return; } rpc_exit(task, status); @@ -2087,9 +2066,6 @@ call_transmit(struct rpc_task *task) xprt_transmit(task); } xprt_end_transmit(task); - if (rpc_task_need_resched(task)) - return; - call_transmit_status(task); } /* @@ -2107,9 +2083,6 @@ call_transmit_status(struct rpc_task *task) if (rpc_task_transmitted(task)) { if (task->tk_status == 0) xprt_request_wait_receive(task); - if (rpc_task_need_resched(task)) - return; - call_status(task); return; } @@ -2170,7 +2143,6 @@ call_bc_encode(struct rpc_task *task) { xprt_request_enqueue_transmit(task); task->tk_action = call_bc_transmit; - call_bc_transmit(task); } /* @@ -2261,7 +2233,6 @@ call_status(struct rpc_task *task) status = task->tk_status; if (status >= 0) { task->tk_action = call_decode; - call_decode(task); return; } -- cgit From e94999688e3aa3c0a8ad5a60352cdc3ca3030434 Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Thu, 11 Apr 2019 20:17:33 +0200 Subject: PM / Domains: Add genpd governor for CPUs After some preceding changes, PM domains managed by genpd may contain CPU devices, so idle state residency values should be taken into account during the state selection process. [The residency value is the minimum amount of time to be spent by a CPU (or a group of CPUs) in an idle state in order to save more energy than could be saved by picking up a shallower idle state.] For this purpose, add a new genpd governor, pm_domain_cpu_gov, to be used for selecting idle states of PM domains with CPU devices attached either directly or through subdomains. The new governor computes the minimum expected idle duration for all online CPUs attached to a PM domain and its subdomains. Next, it finds the deepest idle state whose target residency is within the expected idle duration and selects it as the target idle state of the domain. It should be noted that the minimum expected idle duration computation is based on the closest timer event information stored in the per-CPU variables cpuidle_devices for all of the CPUs in the domain. That needs to be revisited in future, as obviously there are other reasons why a CPU may be woken up from idle. Co-developed-by: Lina Iyer Acked-by: Daniel Lezcano Signed-off-by: Ulf Hansson [ rjw: Changelog ] Signed-off-by: Rafael J. Wysocki --- drivers/base/power/domain_governor.c | 67 +++++++++++++++++++++++++++++++++++- include/linux/pm_domain.h | 4 +++ 2 files changed, 70 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/base/power/domain_governor.c b/drivers/base/power/domain_governor.c index 4d07e38a8247..7912bc957244 100644 --- a/drivers/base/power/domain_governor.c +++ b/drivers/base/power/domain_governor.c @@ -10,6 +10,9 @@ #include #include #include +#include +#include +#include static int dev_update_qos_constraint(struct device *dev, void *data) { @@ -210,8 +213,10 @@ static bool default_power_down_ok(struct dev_pm_domain *pd) struct generic_pm_domain *genpd = pd_to_genpd(pd); struct gpd_link *link; - if (!genpd->max_off_time_changed) + if (!genpd->max_off_time_changed) { + genpd->state_idx = genpd->cached_power_down_state_idx; return genpd->cached_power_down_ok; + } /* * We have to invalidate the cached results for the masters, so @@ -236,6 +241,7 @@ static bool default_power_down_ok(struct dev_pm_domain *pd) genpd->state_idx--; } + genpd->cached_power_down_state_idx = genpd->state_idx; return genpd->cached_power_down_ok; } @@ -244,6 +250,65 @@ static bool always_on_power_down_ok(struct dev_pm_domain *domain) return false; } +#ifdef CONFIG_CPU_IDLE +static bool cpu_power_down_ok(struct dev_pm_domain *pd) +{ + struct generic_pm_domain *genpd = pd_to_genpd(pd); + struct cpuidle_device *dev; + ktime_t domain_wakeup, next_hrtimer; + s64 idle_duration_ns; + int cpu, i; + + /* Validate dev PM QoS constraints. */ + if (!default_power_down_ok(pd)) + return false; + + if (!(genpd->flags & GENPD_FLAG_CPU_DOMAIN)) + return true; + + /* + * Find the next wakeup for any of the online CPUs within the PM domain + * and its subdomains. Note, we only need the genpd->cpus, as it already + * contains a mask of all CPUs from subdomains. + */ + domain_wakeup = ktime_set(KTIME_SEC_MAX, 0); + for_each_cpu_and(cpu, genpd->cpus, cpu_online_mask) { + dev = per_cpu(cpuidle_devices, cpu); + if (dev) { + next_hrtimer = READ_ONCE(dev->next_hrtimer); + if (ktime_before(next_hrtimer, domain_wakeup)) + domain_wakeup = next_hrtimer; + } + } + + /* The minimum idle duration is from now - until the next wakeup. */ + idle_duration_ns = ktime_to_ns(ktime_sub(domain_wakeup, ktime_get())); + if (idle_duration_ns <= 0) + return false; + + /* + * Find the deepest idle state that has its residency value satisfied + * and by also taking into account the power off latency for the state. + * Start at the state picked by the dev PM QoS constraint validation. + */ + i = genpd->state_idx; + do { + if (idle_duration_ns >= (genpd->states[i].residency_ns + + genpd->states[i].power_off_latency_ns)) { + genpd->state_idx = i; + return true; + } + } while (--i >= 0); + + return false; +} + +struct dev_power_governor pm_domain_cpu_gov = { + .suspend_ok = default_suspend_ok, + .power_down_ok = cpu_power_down_ok, +}; +#endif + struct dev_power_governor simple_qos_governor = { .suspend_ok = default_suspend_ok, .power_down_ok = default_power_down_ok, diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index a6e251fe9deb..bc82e74560ee 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -118,6 +118,7 @@ struct generic_pm_domain { s64 max_off_time_ns; /* Maximum allowed "suspended" time. */ bool max_off_time_changed; bool cached_power_down_ok; + bool cached_power_down_state_idx; int (*attach_dev)(struct generic_pm_domain *domain, struct device *dev); void (*detach_dev)(struct generic_pm_domain *domain, @@ -202,6 +203,9 @@ int dev_pm_genpd_set_performance_state(struct device *dev, unsigned int state); extern struct dev_power_governor simple_qos_governor; extern struct dev_power_governor pm_domain_always_on_gov; +#ifdef CONFIG_CPU_IDLE +extern struct dev_power_governor pm_domain_cpu_gov; +#endif #else static inline struct generic_pm_domain_data *dev_gpd_data(struct device *dev) -- cgit From 77f1e0a52d26242b6c2dba019f6ebebfb9ff701e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 18 Jan 2019 10:34:16 -0700 Subject: bfq: update internal depth state when queue depth changes A previous commit moved the shallow depth and BFQ depth map calculations to be done at init time, moving it outside of the hotter IO path. This potentially causes hangs if the users changes the depth of the scheduler map, by writing to the 'nr_requests' sysfs file for that device. Add a blk-mq-sched hook that allows blk-mq to inform the scheduler if the depth changes, so that the scheduler can update its internal state. Tested-by: Kai Krakow Reported-by: Paolo Valente Fixes: f0635b8a416e ("bfq: calculate shallow depths at init time") Signed-off-by: Jens Axboe --- block/bfq-iosched.c | 8 +++++++- block/blk-mq.c | 2 ++ include/linux/elevator.h | 1 + 3 files changed, 10 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index dfb8cb0af13a..5ba1e0d841b4 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -5396,7 +5396,7 @@ static unsigned int bfq_update_depths(struct bfq_data *bfqd, return min_shallow; } -static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index) +static void bfq_depth_updated(struct blk_mq_hw_ctx *hctx) { struct bfq_data *bfqd = hctx->queue->elevator->elevator_data; struct blk_mq_tags *tags = hctx->sched_tags; @@ -5404,6 +5404,11 @@ static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index) min_shallow = bfq_update_depths(bfqd, &tags->bitmap_tags); sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, min_shallow); +} + +static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index) +{ + bfq_depth_updated(hctx); return 0; } @@ -5826,6 +5831,7 @@ static struct elevator_type iosched_bfq_mq = { .requests_merged = bfq_requests_merged, .request_merged = bfq_request_merged, .has_work = bfq_has_work, + .depth_updated = bfq_depth_updated, .init_hctx = bfq_init_hctx, .init_sched = bfq_init_queue, .exit_sched = bfq_exit_queue, diff --git a/block/blk-mq.c b/block/blk-mq.c index 9516304a38ee..fc60ed7e940e 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -3135,6 +3135,8 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr) } if (ret) break; + if (q->elevator && q->elevator->type->ops.depth_updated) + q->elevator->type->ops.depth_updated(hctx); } if (!ret) diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 2e9e2763bf47..6e8bc53740f0 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -31,6 +31,7 @@ struct elevator_mq_ops { void (*exit_sched)(struct elevator_queue *); int (*init_hctx)(struct blk_mq_hw_ctx *, unsigned int); void (*exit_hctx)(struct blk_mq_hw_ctx *, unsigned int); + void (*depth_updated)(struct blk_mq_hw_ctx *); bool (*allow_merge)(struct request_queue *, struct request *, struct bio *); bool (*bio_merge)(struct blk_mq_hw_ctx *, struct bio *); -- cgit From f958d7b528b1b40c44cfda5eabe2d82760d868c3 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 11 Apr 2019 10:06:20 -0700 Subject: mm: make page ref count overflow check tighter and more explicit We have a VM_BUG_ON() to check that the page reference count doesn't underflow (or get close to overflow) by checking the sign of the count. That's all fine, but we actually want to allow people to use a "get page ref unless it's already very high" helper function, and we want that one to use the sign of the page ref (without triggering this VM_BUG_ON). Change the VM_BUG_ON to only check for small underflows (or _very_ close to overflowing), and ignore overflows which have strayed into negative territory. Acked-by: Matthew Wilcox Cc: Jann Horn Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 80bb6408fe73..541d99b86aea 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -965,6 +965,10 @@ static inline bool is_pci_p2pdma_page(const struct page *page) } #endif /* CONFIG_DEV_PAGEMAP_OPS */ +/* 127: arbitrary random number, small enough to assemble well */ +#define page_ref_zero_or_close_to_overflow(page) \ + ((unsigned int) page_ref_count(page) + 127u <= 127u) + static inline void get_page(struct page *page) { page = compound_head(page); @@ -972,7 +976,7 @@ static inline void get_page(struct page *page) * Getting a normal page or the head of a compound page * requires to already have an elevated page->_refcount. */ - VM_BUG_ON_PAGE(page_ref_count(page) <= 0, page); + VM_BUG_ON_PAGE(page_ref_zero_or_close_to_overflow(page), page); page_ref_inc(page); } -- cgit From 88b1a17dfc3ed7728316478fae0f5ad508f50397 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Thu, 11 Apr 2019 10:14:59 -0700 Subject: mm: add 'try_get_page()' helper function This is the same as the traditional 'get_page()' function, but instead of unconditionally incrementing the reference count of the page, it only does so if the count was "safe". It returns whether the reference count was incremented (and is marked __must_check, since the caller obviously has to be aware of it). Also like 'get_page()', you can't use this function unless you already had a reference to the page. The intent is that you can use this exactly like get_page(), but in situations where you want to limit the maximum reference count. The code currently does an unconditional WARN_ON_ONCE() if we ever hit the reference count issues (either zero or negative), as a notification that the conditional non-increment actually happened. NOTE! The count access for the "safety" check is inherently racy, but that doesn't matter since the buffer we use is basically half the range of the reference count (ie we look at the sign of the count). Acked-by: Matthew Wilcox Cc: Jann Horn Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- include/linux/mm.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 541d99b86aea..7000ddd807e0 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -980,6 +980,15 @@ static inline void get_page(struct page *page) page_ref_inc(page); } +static inline __must_check bool try_get_page(struct page *page) +{ + page = compound_head(page); + if (WARN_ON_ONCE(page_ref_count(page) <= 0)) + return false; + page_ref_inc(page); + return true; +} + static inline void put_page(struct page *page) { page = compound_head(page); -- cgit From 15fab63e1e57be9fdb5eec1bbc5916e9825e9acb Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 5 Apr 2019 14:02:10 -0700 Subject: fs: prevent page refcount overflow in pipe_buf_get Change pipe_buf_get() to return a bool indicating whether it succeeded in raising the refcount of the page (if the thing in the pipe is a page). This removes another mechanism for overflowing the page refcount. All callers converted to handle a failure. Reported-by: Jann Horn Signed-off-by: Matthew Wilcox Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- fs/fuse/dev.c | 12 ++++++------ fs/pipe.c | 4 ++-- fs/splice.c | 12 ++++++++++-- include/linux/pipe_fs_i.h | 10 ++++++---- kernel/trace/trace.c | 6 +++++- 5 files changed, 29 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 809c0f2f9942..64f4de983468 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -2034,10 +2034,8 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, rem += pipe->bufs[(pipe->curbuf + idx) & (pipe->buffers - 1)].len; ret = -EINVAL; - if (rem < len) { - pipe_unlock(pipe); - goto out; - } + if (rem < len) + goto out_free; rem = len; while (rem) { @@ -2055,7 +2053,9 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, pipe->curbuf = (pipe->curbuf + 1) & (pipe->buffers - 1); pipe->nrbufs--; } else { - pipe_buf_get(pipe, ibuf); + if (!pipe_buf_get(pipe, ibuf)) + goto out_free; + *obuf = *ibuf; obuf->flags &= ~PIPE_BUF_FLAG_GIFT; obuf->len = rem; @@ -2078,11 +2078,11 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe, ret = fuse_dev_do_write(fud, &cs, len); pipe_lock(pipe); +out_free: for (idx = 0; idx < nbuf; idx++) pipe_buf_release(pipe, &bufs[idx]); pipe_unlock(pipe); -out: kvfree(bufs); return ret; } diff --git a/fs/pipe.c b/fs/pipe.c index bdc5d3c0977d..b1543b85c14a 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -189,9 +189,9 @@ EXPORT_SYMBOL(generic_pipe_buf_steal); * in the tee() system call, when we duplicate the buffers in one * pipe into another. */ -void generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) +bool generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { - get_page(buf->page); + return try_get_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_get); diff --git a/fs/splice.c b/fs/splice.c index de2ede048473..f30af82b850d 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -1588,7 +1588,11 @@ retry: * Get a reference to this pipe buffer, * so we can copy the contents over. */ - pipe_buf_get(ipipe, ibuf); + if (!pipe_buf_get(ipipe, ibuf)) { + if (ret == 0) + ret = -EFAULT; + break; + } *obuf = *ibuf; /* @@ -1660,7 +1664,11 @@ static int link_pipe(struct pipe_inode_info *ipipe, * Get a reference to this pipe buffer, * so we can copy the contents over. */ - pipe_buf_get(ipipe, ibuf); + if (!pipe_buf_get(ipipe, ibuf)) { + if (ret == 0) + ret = -EFAULT; + break; + } obuf = opipe->bufs + nbuf; *obuf = *ibuf; diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 5a3bb3b7c9ad..3f2a42c11e20 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -108,18 +108,20 @@ struct pipe_buf_operations { /* * Get a reference to the pipe buffer. */ - void (*get)(struct pipe_inode_info *, struct pipe_buffer *); + bool (*get)(struct pipe_inode_info *, struct pipe_buffer *); }; /** * pipe_buf_get - get a reference to a pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to get a reference to + * + * Return: %true if the reference was successfully obtained. */ -static inline void pipe_buf_get(struct pipe_inode_info *pipe, +static inline __must_check bool pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { - buf->ops->get(pipe, buf); + return buf->ops->get(pipe, buf); } /** @@ -178,7 +180,7 @@ struct pipe_inode_info *alloc_pipe_info(void); void free_pipe_info(struct pipe_inode_info *); /* Generic pipe buffer ops functions */ -void generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); +bool generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *); void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c4238b441624..0f300d488c9f 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6835,12 +6835,16 @@ static void buffer_pipe_buf_release(struct pipe_inode_info *pipe, buf->private = 0; } -static void buffer_pipe_buf_get(struct pipe_inode_info *pipe, +static bool buffer_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct buffer_ref *ref = (struct buffer_ref *)buf->private; + if (ref->ref > INT_MAX/2) + return false; + ref->ref++; + return true; } /* Pipe buffer operations for a buffer. */ -- cgit From 0082517fa4bce073e7cf542633439f26538a14cc Mon Sep 17 00:00:00 2001 From: Jian-Hong Pan Date: Fri, 12 Apr 2019 16:01:53 +0800 Subject: x86/reboot, efi: Use EFI reboot for Acer TravelMate X514-51T Upon reboot, the Acer TravelMate X514-51T laptop appears to complete the shutdown process, but then it hangs in BIOS POST with a black screen. The problem is intermittent - at some points it has appeared related to Secure Boot settings or different kernel builds, but ultimately we have not been able to identify the exact conditions that trigger the issue to come and go. Besides, the EFI mode cannot be disabled in the BIOS of this model. However, after extensive testing, we observe that using the EFI reboot method reliably avoids the issue in all cases. So add a boot time quirk to use EFI reboot on such systems. Buglink: https://bugzilla.kernel.org/show_bug.cgi?id=203119 Signed-off-by: Jian-Hong Pan Signed-off-by: Daniel Drake Cc: Ard Biesheuvel Cc: Borislav Petkov Cc: Linus Torvalds Cc: Matt Fleming Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-efi@vger.kernel.org Cc: linux@endlessm.com Link: http://lkml.kernel.org/r/20190412080152.3718-1-jian-hong@endlessm.com [ Fix !CONFIG_EFI build failure, clarify the code and the changelog a bit. ] Signed-off-by: Ingo Molnar --- arch/x86/kernel/reboot.c | 21 +++++++++++++++++++++ include/linux/efi.h | 7 ++++++- 2 files changed, 27 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 725624b6c0c0..8fd3cedd9acc 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -81,6 +81,19 @@ static int __init set_bios_reboot(const struct dmi_system_id *d) return 0; } +/* + * Some machines don't handle the default ACPI reboot method and + * require the EFI reboot method: + */ +static int __init set_efi_reboot(const struct dmi_system_id *d) +{ + if (reboot_type != BOOT_EFI && !efi_runtime_disabled()) { + reboot_type = BOOT_EFI; + pr_info("%s series board detected. Selecting EFI-method for reboot.\n", d->ident); + } + return 0; +} + void __noreturn machine_real_restart(unsigned int type) { local_irq_disable(); @@ -166,6 +179,14 @@ static const struct dmi_system_id reboot_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "AOA110"), }, }, + { /* Handle reboot issue on Acer TravelMate X514-51T */ + .callback = set_efi_reboot, + .ident = "Acer TravelMate X514-51T", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Acer"), + DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate X514-51T"), + }, + }, /* Apple */ { /* Handle problems with rebooting on Apple MacBook5 */ diff --git a/include/linux/efi.h b/include/linux/efi.h index 54357a258b35..6ebc2098cfe1 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -1611,7 +1611,12 @@ efi_status_t efi_setup_gop(efi_system_table_t *sys_table_arg, struct screen_info *si, efi_guid_t *proto, unsigned long size); -bool efi_runtime_disabled(void); +#ifdef CONFIG_EFI +extern bool efi_runtime_disabled(void); +#else +static inline bool efi_runtime_disabled(void) { return true; } +#endif + extern void efi_call_virt_check_flags(unsigned long flags, const char *call); extern unsigned long efi_call_virt_save_flags(void); -- cgit From c68d224e5ed15605e651e2482c6ffd95915ddf58 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Mon, 8 Apr 2019 10:32:51 -0700 Subject: perf/core: Add perf_pmu_resched() as global function This patch add perf_pmu_resched() a global function that can be called to force rescheduling of events for a given PMU. The function locks both cpuctx and task_ctx internally. This will be used by a subsequent patch. Signed-off-by: Stephane Eranian [ Simplified the calling convention. ] Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vince Weaver Cc: kan.liang@intel.com Cc: nelson.dsouza@intel.com Cc: tonyj@suse.com Link: https://lkml.kernel.org/r/20190408173252.37932-2-eranian@google.com Signed-off-by: Ingo Molnar --- include/linux/perf_event.h | 3 +++ kernel/events/core.c | 10 ++++++++++ 2 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 085a95e2582a..f3864e1c5569 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -888,6 +888,9 @@ extern void perf_sched_cb_dec(struct pmu *pmu); extern void perf_sched_cb_inc(struct pmu *pmu); extern int perf_event_task_disable(void); extern int perf_event_task_enable(void); + +extern void perf_pmu_resched(struct pmu *pmu); + extern int perf_event_refresh(struct perf_event *event, int refresh); extern void perf_event_update_userpage(struct perf_event *event); extern int perf_event_release_kernel(struct perf_event *event); diff --git a/kernel/events/core.c b/kernel/events/core.c index 30a572e4c6f1..abbd4b3b96c2 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2478,6 +2478,16 @@ static void ctx_resched(struct perf_cpu_context *cpuctx, perf_pmu_enable(cpuctx->ctx.pmu); } +void perf_pmu_resched(struct pmu *pmu) +{ + struct perf_cpu_context *cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); + struct perf_event_context *task_ctx = cpuctx->task_ctx; + + perf_ctx_lock(cpuctx, task_ctx); + ctx_resched(cpuctx, task_ctx, EVENT_ALL|EVENT_CPU); + perf_ctx_unlock(cpuctx, task_ctx); +} + /* * Cross CPU call to install and enable a performance event * -- cgit From 1d487e9bf8ba66a7174c56a0029c54b1eca8f99c Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 11 Apr 2019 11:16:47 +0200 Subject: KVM: fix spectrev1 gadgets These were found with smatch, and then generalized when applicable. Signed-off-by: Paolo Bonzini --- arch/x86/kvm/lapic.c | 4 +++- include/linux/kvm_host.h | 10 ++++++---- virt/kvm/irqchip.c | 5 +++-- virt/kvm/kvm_main.c | 6 ++++-- 4 files changed, 16 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 991fdf7fc17f..9bf70cf84564 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -138,6 +138,7 @@ static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map, if (offset <= max_apic_id) { u8 cluster_size = min(max_apic_id - offset + 1, 16U); + offset = array_index_nospec(offset, map->max_apic_id + 1); *cluster = &map->phys_map[offset]; *mask = dest_id & (0xffff >> (16 - cluster_size)); } else { @@ -901,7 +902,8 @@ static inline bool kvm_apic_map_get_dest_lapic(struct kvm *kvm, if (irq->dest_id > map->max_apic_id) { *bitmap = 0; } else { - *dst = &map->phys_map[irq->dest_id]; + u32 dest_id = array_index_nospec(irq->dest_id, map->max_apic_id + 1); + *dst = &map->phys_map[dest_id]; *bitmap = 1; } return true; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9d55c63db09b..640a03642766 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -28,6 +28,7 @@ #include #include #include +#include #include #include @@ -513,10 +514,10 @@ static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx) static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i) { - /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu, in case - * the caller has read kvm->online_vcpus before (as is the case - * for kvm_for_each_vcpu, for example). - */ + int num_vcpus = atomic_read(&kvm->online_vcpus); + i = array_index_nospec(i, num_vcpus); + + /* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu. */ smp_rmb(); return kvm->vcpus[i]; } @@ -600,6 +601,7 @@ void kvm_put_kvm(struct kvm *kvm); static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id) { + as_id = array_index_nospec(as_id, KVM_ADDRESS_SPACE_NUM); return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu, lockdep_is_held(&kvm->slots_lock) || !refcount_read(&kvm->users_count)); diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c index 3547b0d8c91e..79e59e4fa3dc 100644 --- a/virt/kvm/irqchip.c +++ b/virt/kvm/irqchip.c @@ -144,18 +144,19 @@ static int setup_routing_entry(struct kvm *kvm, { struct kvm_kernel_irq_routing_entry *ei; int r; + u32 gsi = array_index_nospec(ue->gsi, KVM_MAX_IRQ_ROUTES); /* * Do not allow GSI to be mapped to the same irqchip more than once. * Allow only one to one mapping between GSI and non-irqchip routing. */ - hlist_for_each_entry(ei, &rt->map[ue->gsi], link) + hlist_for_each_entry(ei, &rt->map[gsi], link) if (ei->type != KVM_IRQ_ROUTING_IRQCHIP || ue->type != KVM_IRQ_ROUTING_IRQCHIP || ue->u.irqchip.irqchip == ei->irqchip.irqchip) return -EINVAL; - e->gsi = ue->gsi; + e->gsi = gsi; e->type = ue->type; r = kvm_set_routing_entry(kvm, e, ue); if (r) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 55fe8e20d8fd..dc8edc97ba85 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2977,12 +2977,14 @@ static int kvm_ioctl_create_device(struct kvm *kvm, struct kvm_device_ops *ops = NULL; struct kvm_device *dev; bool test = cd->flags & KVM_CREATE_DEVICE_TEST; + int type; int ret; if (cd->type >= ARRAY_SIZE(kvm_device_ops_table)) return -ENODEV; - ops = kvm_device_ops_table[cd->type]; + type = array_index_nospec(cd->type, ARRAY_SIZE(kvm_device_ops_table)); + ops = kvm_device_ops_table[type]; if (ops == NULL) return -ENODEV; @@ -2997,7 +2999,7 @@ static int kvm_ioctl_create_device(struct kvm *kvm, dev->kvm = kvm; mutex_lock(&kvm->lock); - ret = ops->create(dev, cd->type); + ret = ops->create(dev, type); if (ret < 0) { mutex_unlock(&kvm->lock); kfree(dev); -- cgit From 98af8452945c55652de68536afdde3b520fec429 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Fri, 12 Apr 2019 15:39:28 -0500 Subject: cpu/speculation: Add 'mitigations=' cmdline option Keeping track of the number of mitigations for all the CPU speculation bugs has become overwhelming for many users. It's getting more and more complicated to decide which mitigations are needed for a given architecture. Complicating matters is the fact that each arch tends to have its own custom way to mitigate the same vulnerability. Most users fall into a few basic categories: a) they want all mitigations off; b) they want all reasonable mitigations on, with SMT enabled even if it's vulnerable; or c) they want all reasonable mitigations on, with SMT disabled if vulnerable. Define a set of curated, arch-independent options, each of which is an aggregation of existing options: - mitigations=off: Disable all mitigations. - mitigations=auto: [default] Enable all the default mitigations, but leave SMT enabled, even if it's vulnerable. - mitigations=auto,nosmt: Enable all the default mitigations, disabling SMT if needed by a mitigation. Currently, these options are placeholders which don't actually do anything. They will be fleshed out in upcoming patches. Signed-off-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner Tested-by: Jiri Kosina (on x86) Reviewed-by: Jiri Kosina Cc: Borislav Petkov Cc: "H . Peter Anvin" Cc: Andy Lutomirski Cc: Peter Zijlstra Cc: Jiri Kosina Cc: Waiman Long Cc: Andrea Arcangeli Cc: Jon Masters Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: linuxppc-dev@lists.ozlabs.org Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: linux-s390@vger.kernel.org Cc: Catalin Marinas Cc: Will Deacon Cc: linux-arm-kernel@lists.infradead.org Cc: linux-arch@vger.kernel.org Cc: Greg Kroah-Hartman Cc: Tyler Hicks Cc: Linus Torvalds Cc: Randy Dunlap Cc: Steven Price Cc: Phil Auld Link: https://lkml.kernel.org/r/b07a8ef9b7c5055c3a4637c87d07c296d5016fe0.1555085500.git.jpoimboe@redhat.com --- Documentation/admin-guide/kernel-parameters.txt | 24 ++++++++++++++++++++++++ include/linux/cpu.h | 24 ++++++++++++++++++++++++ kernel/cpu.c | 15 +++++++++++++++ 3 files changed, 63 insertions(+) (limited to 'include/linux') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 858b6c0b9a15..720ffa9c4e04 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2513,6 +2513,30 @@ in the "bleeding edge" mini2440 support kernel at http://repo.or.cz/w/linux-2.6/mini2440.git + mitigations= + Control optional mitigations for CPU vulnerabilities. + This is a set of curated, arch-independent options, each + of which is an aggregation of existing arch-specific + options. + + off + Disable all optional CPU mitigations. This + improves system performance, but it may also + expose users to several CPU vulnerabilities. + + auto (default) + Mitigate all CPU vulnerabilities, but leave SMT + enabled, even if it's vulnerable. This is for + users who don't want to be surprised by SMT + getting disabled across kernel upgrades, or who + have other ways of avoiding SMT-based attacks. + This is the default behavior. + + auto,nosmt + Mitigate all CPU vulnerabilities, disabling SMT + if needed. This is for users who always want to + be fully mitigated, even if it means losing SMT. + mminit_loglevel= [KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this parameter allows control of the logging verbosity for diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 5041357d0297..2d9c6f4b78f5 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -187,4 +187,28 @@ static inline void cpu_smt_disable(bool force) { } static inline void cpu_smt_check_topology(void) { } #endif +/* + * These are used for a global "mitigations=" cmdline option for toggling + * optional CPU mitigations. + */ +enum cpu_mitigations { + CPU_MITIGATIONS_OFF, + CPU_MITIGATIONS_AUTO, + CPU_MITIGATIONS_AUTO_NOSMT, +}; + +extern enum cpu_mitigations cpu_mitigations; + +/* mitigations=off */ +static inline bool cpu_mitigations_off(void) +{ + return cpu_mitigations == CPU_MITIGATIONS_OFF; +} + +/* mitigations=auto,nosmt */ +static inline bool cpu_mitigations_auto_nosmt(void) +{ + return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT; +} + #endif /* _LINUX_CPU_H_ */ diff --git a/kernel/cpu.c b/kernel/cpu.c index d1c6d152da89..e70a90634b41 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -2279,3 +2279,18 @@ void __init boot_cpu_hotplug_init(void) #endif this_cpu_write(cpuhp_state.state, CPUHP_ONLINE); } + +enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO; + +static int __init mitigations_parse_cmdline(char *arg) +{ + if (!strcmp(arg, "off")) + cpu_mitigations = CPU_MITIGATIONS_OFF; + else if (!strcmp(arg, "auto")) + cpu_mitigations = CPU_MITIGATIONS_AUTO; + else if (!strcmp(arg, "auto,nosmt")) + cpu_mitigations = CPU_MITIGATIONS_AUTO_NOSMT; + + return 0; +} +early_param("mitigations", mitigations_parse_cmdline); -- cgit From 3771b0fe9dfc3801eac0142d1af6ba94dee83c6c Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 25 Mar 2019 13:57:57 +0100 Subject: locking/lockdep: Avoid bogus Clang warning When lockdep is enabled, and -Wuninitialized warnings are enabled, Clang produces a silly warning for every file we compile: In file included from kernel/sched/fair.c:23: kernel/sched/sched.h:1094:15: error: variable 'cookie' is uninitialized when used here [-Werror,-Wuninitialized] rf->cookie = lockdep_pin_lock(&rq->lock); ^~~~~~~~~~~~~~~~~~~~~~~~~~~ include/linux/lockdep.h:474:60: note: expanded from macro 'lockdep_pin_lock' #define lockdep_pin_lock(l) ({ struct pin_cookie cookie; cookie; }) ^~~~~~ kernel/sched/sched.h:1094:15: note: variable 'cookie' is declared here include/linux/lockdep.h:474:34: note: expanded from macro 'lockdep_pin_lock' #define lockdep_pin_lock(l) ({ struct pin_cookie cookie; cookie; }) ^ As the 'struct pin_cookie' structure is empty in this configuration, there is no need to initialize it for correctness, but it also does not hurt to set it to an empty structure, so do that to avoid the warning. Signed-off-by: Arnd Bergmann Acked-by: Will Deacon Cc: Bart Van Assche Cc: Joel Fernandes (Google) Cc: Linus Torvalds Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Peter Zijlstra Cc: Steven Rostedt (VMware) Cc: Thomas Gleixner Cc: Waiman Long Cc: clang-built-linux@googlegroups.com Link: http://lkml.kernel.org/r/20190325125807.1437049-1-arnd@arndb.de Signed-off-by: Ingo Molnar --- include/linux/lockdep.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 79c3873d58ac..21725a91442b 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -471,7 +471,7 @@ struct pin_cookie { }; #define NIL_COOKIE (struct pin_cookie){ } -#define lockdep_pin_lock(l) ({ struct pin_cookie cookie; cookie; }) +#define lockdep_pin_lock(l) ({ struct pin_cookie cookie = { }; cookie; }) #define lockdep_repin_lock(l, c) do { (void)(l); (void)(c); } while (0) #define lockdep_unpin_lock(l, c) do { (void)(l); (void)(c); } while (0) -- cgit From 0fcc2bdc8aff6e7feb3222930edb78b4b820cd3e Mon Sep 17 00:00:00 2001 From: Sakari Ailus Date: Tue, 2 Apr 2019 13:30:37 +0300 Subject: device property: Add fwnode_graph_get_endpoint_by_id() fwnode_graph_get_endpoint_by_id() is intended for obtaining local endpoints by a given local port. fwnode_graph_get_endpoint_by_id() is slightly different from its OF counterpart, of_graph_get_endpoint_by_regs(): instead of using -1 as a value to indicate that a port or an endpoint number does not matter, it uses flags to look for equal or greater endpoint. The port number is always fixed. It also returns only remote endpoints that belong to an available device, a behaviour that can be turned off with a flag. Signed-off-by: Sakari Ailus [ rjw: Changelog ] Signed-off-by: Rafael J. Wysocki --- drivers/base/property.c | 75 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/property.h | 18 ++++++++++++ 2 files changed, 93 insertions(+) (limited to 'include/linux') diff --git a/drivers/base/property.c b/drivers/base/property.c index 8b91ab380d14..348b37e64944 100644 --- a/drivers/base/property.c +++ b/drivers/base/property.c @@ -983,6 +983,81 @@ fwnode_graph_get_remote_node(const struct fwnode_handle *fwnode, u32 port_id, } EXPORT_SYMBOL_GPL(fwnode_graph_get_remote_node); +/** + * fwnode_graph_get_endpoint_by_id - get endpoint by port and endpoint numbers + * @fwnode: parent fwnode_handle containing the graph + * @port: identifier of the port node + * @endpoint: identifier of the endpoint node under the port node + * @flags: fwnode lookup flags + * + * Return the fwnode handle of the local endpoint corresponding the port and + * endpoint IDs or NULL if not found. + * + * If FWNODE_GRAPH_ENDPOINT_NEXT is passed in @flags and the specified endpoint + * has not been found, look for the closest endpoint ID greater than the + * specified one and return the endpoint that corresponds to it, if present. + * + * Do not return endpoints that belong to disabled devices, unless + * FWNODE_GRAPH_DEVICE_DISABLED is passed in @flags. + * + * The returned endpoint needs to be released by calling fwnode_handle_put() on + * it when it is not needed any more. + */ +struct fwnode_handle * +fwnode_graph_get_endpoint_by_id(const struct fwnode_handle *fwnode, + u32 port, u32 endpoint, unsigned long flags) +{ + struct fwnode_handle *ep = NULL, *best_ep = NULL; + unsigned int best_ep_id = 0; + bool endpoint_next = flags & FWNODE_GRAPH_ENDPOINT_NEXT; + bool enabled_only = !(flags & FWNODE_GRAPH_DEVICE_DISABLED); + + while ((ep = fwnode_graph_get_next_endpoint(fwnode, ep))) { + struct fwnode_endpoint fwnode_ep = { 0 }; + int ret; + + if (enabled_only) { + struct fwnode_handle *dev_node; + bool available; + + dev_node = fwnode_graph_get_remote_port_parent(ep); + available = fwnode_device_is_available(dev_node); + fwnode_handle_put(dev_node); + if (!available) + continue; + } + + ret = fwnode_graph_parse_endpoint(ep, &fwnode_ep); + if (ret < 0) + continue; + + if (fwnode_ep.port != port) + continue; + + if (fwnode_ep.id == endpoint) + return ep; + + if (!endpoint_next) + continue; + + /* + * If the endpoint that has just been found is not the first + * matching one and the ID of the one found previously is closer + * to the requested endpoint ID, skip it. + */ + if (fwnode_ep.id < endpoint || + (best_ep && best_ep_id < fwnode_ep.id)) + continue; + + fwnode_handle_put(best_ep); + best_ep = fwnode_handle_get(ep); + best_ep_id = fwnode_ep.id; + } + + return best_ep; +} +EXPORT_SYMBOL_GPL(fwnode_graph_get_endpoint_by_id); + /** * fwnode_graph_parse_endpoint - parse common endpoint node properties * @fwnode: pointer to endpoint fwnode_handle diff --git a/include/linux/property.h b/include/linux/property.h index 65d3420dd5d1..a29369c89e6e 100644 --- a/include/linux/property.h +++ b/include/linux/property.h @@ -13,6 +13,7 @@ #ifndef _LINUX_PROPERTY_H_ #define _LINUX_PROPERTY_H_ +#include #include #include @@ -304,6 +305,23 @@ struct fwnode_handle * fwnode_graph_get_remote_node(const struct fwnode_handle *fwnode, u32 port, u32 endpoint); +/* + * Fwnode lookup flags + * + * @FWNODE_GRAPH_ENDPOINT_NEXT: In the case of no exact match, look for the + * closest endpoint ID greater than the specified + * one. + * @FWNODE_GRAPH_DEVICE_DISABLED: That the device to which the remote + * endpoint of the given endpoint belongs to, + * may be disabled. + */ +#define FWNODE_GRAPH_ENDPOINT_NEXT BIT(0) +#define FWNODE_GRAPH_DEVICE_DISABLED BIT(1) + +struct fwnode_handle * +fwnode_graph_get_endpoint_by_id(const struct fwnode_handle *fwnode, + u32 port, u32 endpoint, unsigned long flags); + #define fwnode_graph_for_each_endpoint(fwnode, child) \ for (child = NULL; \ (child = fwnode_graph_get_next_endpoint(fwnode, child)); ) -- cgit From 83b0b15bcb0f700e7c1d070aae2e7841170a4c33 Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Tue, 5 Mar 2019 14:47:54 -0500 Subject: rseq: Remove superfluous rseq_len from task_struct The rseq system call, when invoked with flags of "0" or "RSEQ_FLAG_UNREGISTER" values, expects the rseq_len parameter to be equal to sizeof(struct rseq), which is fixed-size and fixed-layout, specified in uapi linux/rseq.h. Expecting a fixed size for rseq_len is a design choice that ensures multiple libraries and application defining __rseq_abi in the same process agree on its exact size. Considering that this size is and will always be the same value, there is no point in saving this value within task_struct rseq_len. Remove this field from task_struct. No change in functionality intended. Signed-off-by: Mathieu Desnoyers Acked-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Andy Lutomirski Cc: Ben Maurer Cc: Boqun Feng Cc: Catalin Marinas Cc: Chris Lameter Cc: Dave Watson Cc: H. Peter Anvin Cc: Joel Fernandes Cc: Josh Triplett Cc: Linus Torvalds Cc: Michael Kerrisk Cc: Paul E. McKenney Cc: Paul Turner Cc: Peter Zijlstra Cc: Russell King Cc: Steven Rostedt Cc: Thomas Gleixner Cc: Will Deacon Cc: linux-api@vger.kernel.org Link: http://lkml.kernel.org/r/20190305194755.2602-3-mathieu.desnoyers@efficios.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ---- kernel/rseq.c | 6 ++---- 2 files changed, 2 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 1549584a1538..50606a6e73d6 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1057,7 +1057,6 @@ struct task_struct { #ifdef CONFIG_RSEQ struct rseq __user *rseq; - u32 rseq_len; u32 rseq_sig; /* * RmW on rseq_event_mask must be performed atomically @@ -1855,12 +1854,10 @@ static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) { if (clone_flags & CLONE_THREAD) { t->rseq = NULL; - t->rseq_len = 0; t->rseq_sig = 0; t->rseq_event_mask = 0; } else { t->rseq = current->rseq; - t->rseq_len = current->rseq_len; t->rseq_sig = current->rseq_sig; t->rseq_event_mask = current->rseq_event_mask; } @@ -1869,7 +1866,6 @@ static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) static inline void rseq_execve(struct task_struct *t) { t->rseq = NULL; - t->rseq_len = 0; t->rseq_sig = 0; t->rseq_event_mask = 0; } diff --git a/kernel/rseq.c b/kernel/rseq.c index 849afe749131..9424ee90589e 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -313,7 +313,7 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, /* Unregister rseq for current thread. */ if (current->rseq != rseq || !current->rseq) return -EINVAL; - if (current->rseq_len != rseq_len) + if (rseq_len != sizeof(*rseq)) return -EINVAL; if (current->rseq_sig != sig) return -EPERM; @@ -321,7 +321,6 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, if (ret) return ret; current->rseq = NULL; - current->rseq_len = 0; current->rseq_sig = 0; return 0; } @@ -335,7 +334,7 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, * the provided address differs from the prior * one. */ - if (current->rseq != rseq || current->rseq_len != rseq_len) + if (current->rseq != rseq || rseq_len != sizeof(*rseq)) return -EINVAL; if (current->rseq_sig != sig) return -EPERM; @@ -353,7 +352,6 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, if (!access_ok(rseq, rseq_len)) return -EFAULT; current->rseq = rseq; - current->rseq_len = rseq_len; current->rseq_sig = sig; /* * If rseq was previously inactive, and has just been -- cgit From 3ff9c075cc767b3060bdac12da72fc94dd7da1b8 Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Sun, 24 Feb 2019 01:49:52 +0900 Subject: x86/kprobes: Verify stack frame on kretprobe Verify the stack frame pointer on kretprobe trampoline handler, If the stack frame pointer does not match, it skips the wrong entry and tries to find correct one. This can happen if user puts the kretprobe on the function which can be used in the path of ftrace user-function call. Such functions should not be probed, so this adds a warning message that reports which function should be blacklisted. Tested-by: Andrea Righi Signed-off-by: Masami Hiramatsu Acked-by: Steven Rostedt Cc: Linus Torvalds Cc: Mathieu Desnoyers Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/155094059185.6137.15527904013362842072.stgit@devbox Signed-off-by: Ingo Molnar --- arch/x86/kernel/kprobes/core.c | 26 ++++++++++++++++++++++++++ include/linux/kprobes.h | 1 + 2 files changed, 27 insertions(+) (limited to 'include/linux') diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index a034cb808e7e..18fbe9be2d68 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -569,6 +569,7 @@ void arch_prepare_kretprobe(struct kretprobe_instance *ri, struct pt_regs *regs) unsigned long *sara = stack_addr(regs); ri->ret_addr = (kprobe_opcode_t *) *sara; + ri->fp = sara; /* Replace the return addr with trampoline addr */ *sara = (unsigned long) &kretprobe_trampoline; @@ -759,15 +760,21 @@ static __used void *trampoline_handler(struct pt_regs *regs) unsigned long flags, orig_ret_address = 0; unsigned long trampoline_address = (unsigned long)&kretprobe_trampoline; kprobe_opcode_t *correct_ret_addr = NULL; + void *frame_pointer; + bool skipped = false; INIT_HLIST_HEAD(&empty_rp); kretprobe_hash_lock(current, &head, &flags); /* fixup registers */ #ifdef CONFIG_X86_64 regs->cs = __KERNEL_CS; + /* On x86-64, we use pt_regs->sp for return address holder. */ + frame_pointer = ®s->sp; #else regs->cs = __KERNEL_CS | get_kernel_rpl(); regs->gs = 0; + /* On x86-32, we use pt_regs->flags for return address holder. */ + frame_pointer = ®s->flags; #endif regs->ip = trampoline_address; regs->orig_ax = ~0UL; @@ -789,8 +796,25 @@ static __used void *trampoline_handler(struct pt_regs *regs) if (ri->task != current) /* another task is sharing our hash bucket */ continue; + /* + * Return probes must be pushed on this hash list correct + * order (same as return order) so that it can be poped + * correctly. However, if we find it is pushed it incorrect + * order, this means we find a function which should not be + * probed, because the wrong order entry is pushed on the + * path of processing other kretprobe itself. + */ + if (ri->fp != frame_pointer) { + if (!skipped) + pr_warn("kretprobe is stacked incorrectly. Trying to fixup.\n"); + skipped = true; + continue; + } orig_ret_address = (unsigned long)ri->ret_addr; + if (skipped) + pr_warn("%ps must be blacklisted because of incorrect kretprobe order\n", + ri->rp->kp.addr); if (orig_ret_address != trampoline_address) /* @@ -808,6 +832,8 @@ static __used void *trampoline_handler(struct pt_regs *regs) if (ri->task != current) /* another task is sharing our hash bucket */ continue; + if (ri->fp != frame_pointer) + continue; orig_ret_address = (unsigned long)ri->ret_addr; if (ri->rp && ri->rp->handler) { diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 201f0f2683f2..9a897256e481 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -173,6 +173,7 @@ struct kretprobe_instance { struct kretprobe *rp; kprobe_opcode_t *ret_addr; struct task_struct *task; + void *fp; char data[0]; }; -- cgit From af53d3e9e04024885de5b4fda51e5fa362ae2bd8 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Thu, 18 Apr 2019 17:50:13 -0700 Subject: mm: swapoff: shmem_unuse() stop eviction without igrab() The igrab() in shmem_unuse() looks good, but we forgot that it gives no protection against concurrent unmounting: a point made by Konstantin Khlebnikov eight years ago, and then fixed in 2.6.39 by 778dd893ae78 ("tmpfs: fix race between umount and swapoff"). The current 5.1-rc swapoff is liable to hit "VFS: Busy inodes after unmount of tmpfs. Self-destruct in 5 seconds. Have a nice day..." followed by GPF. Once again, give up on using igrab(); but don't go back to making such heavy-handed use of shmem_swaplist_mutex as last time: that would spoil the new design, and I expect could deadlock inside shmem_swapin_page(). Instead, shmem_unuse() just raise a "stop_eviction" count in the shmem- specific inode, and shmem_evict_inode() wait for that to go down to 0. Call it "stop_eviction" rather than "swapoff_busy" because it can be put to use for others later (huge tmpfs patches expect to use it). That simplifies shmem_unuse(), protecting it from both unlink and unmount; and in practice lets it locate all the swap in its first try. But do not rely on that: there's still a theoretical case, when shmem_writepage() might have been preempted after its get_swap_page(), before making the swap entry visible to swapoff. [hughd@google.com: remove incorrect list_del()] Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1904091133570.1898@eggly.anvils Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1904081259400.1523@eggly.anvils Fixes: b56a2d8af914 ("mm: rid swapoff of quadratic complexity") Signed-off-by: Hugh Dickins Cc: "Alex Xu (Hello71)" Cc: Huang Ying Cc: Kelley Nielsen Cc: Konstantin Khlebnikov Cc: Rik van Riel Cc: Vineeth Pillai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/shmem_fs.h | 1 + mm/shmem.c | 40 ++++++++++++++++++---------------------- mm/swapfile.c | 11 +++++------ 3 files changed, 24 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index f3fb1edb3526..20d815a33145 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -21,6 +21,7 @@ struct shmem_inode_info { struct list_head swaplist; /* chain of maybes on swap */ struct shared_policy policy; /* NUMA memory alloc policy */ struct simple_xattrs xattrs; /* list of xattrs */ + atomic_t stop_eviction; /* hold when working on inode */ struct inode vfs_inode; }; diff --git a/mm/shmem.c b/mm/shmem.c index 859e8628071f..2275a0ff7c30 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1081,9 +1081,14 @@ static void shmem_evict_inode(struct inode *inode) } spin_unlock(&sbinfo->shrinklist_lock); } - if (!list_empty(&info->swaplist)) { + while (!list_empty(&info->swaplist)) { + /* Wait while shmem_unuse() is scanning this inode... */ + wait_var_event(&info->stop_eviction, + !atomic_read(&info->stop_eviction)); mutex_lock(&shmem_swaplist_mutex); - list_del_init(&info->swaplist); + /* ...but beware of the race if we peeked too early */ + if (!atomic_read(&info->stop_eviction)) + list_del_init(&info->swaplist); mutex_unlock(&shmem_swaplist_mutex); } } @@ -1227,36 +1232,27 @@ int shmem_unuse(unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { struct shmem_inode_info *info, *next; - struct inode *inode; - struct inode *prev_inode = NULL; int error = 0; if (list_empty(&shmem_swaplist)) return 0; mutex_lock(&shmem_swaplist_mutex); - - /* - * The extra refcount on the inode is necessary to safely dereference - * p->next after re-acquiring the lock. New shmem inodes with swap - * get added to the end of the list and we will scan them all. - */ list_for_each_entry_safe(info, next, &shmem_swaplist, swaplist) { if (!info->swapped) { list_del_init(&info->swaplist); continue; } - - inode = igrab(&info->vfs_inode); - if (!inode) - continue; - + /* + * Drop the swaplist mutex while searching the inode for swap; + * but before doing so, make sure shmem_evict_inode() will not + * remove placeholder inode from swaplist, nor let it be freed + * (igrab() would protect from unlink, but not from unmount). + */ + atomic_inc(&info->stop_eviction); mutex_unlock(&shmem_swaplist_mutex); - if (prev_inode) - iput(prev_inode); - prev_inode = inode; - error = shmem_unuse_inode(inode, type, frontswap, + error = shmem_unuse_inode(&info->vfs_inode, type, frontswap, fs_pages_to_unuse); cond_resched(); @@ -1264,14 +1260,13 @@ int shmem_unuse(unsigned int type, bool frontswap, next = list_next_entry(info, swaplist); if (!info->swapped) list_del_init(&info->swaplist); + if (atomic_dec_and_test(&info->stop_eviction)) + wake_up_var(&info->stop_eviction); if (error) break; } mutex_unlock(&shmem_swaplist_mutex); - if (prev_inode) - iput(prev_inode); - return error; } @@ -2238,6 +2233,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode info = SHMEM_I(inode); memset(info, 0, (char *)inode - (char *)info); spin_lock_init(&info->lock); + atomic_set(&info->stop_eviction, 0); info->seals = F_SEAL_SEAL; info->flags = flags & VM_NORESERVE; INIT_LIST_HEAD(&info->shrinklist); diff --git a/mm/swapfile.c b/mm/swapfile.c index 71383625a582..cf63b5f01adf 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2116,12 +2116,11 @@ retry: * Under global memory pressure, swap entries can be reinserted back * into process space after the mmlist loop above passes over them. * - * Limit the number of retries? No: when shmem_unuse()'s igrab() fails, - * a shmem inode using swap is being evicted; and when mmget_not_zero() - * above fails, that mm is likely to be freeing swap from exit_mmap(). - * Both proceed at their own independent pace: we could move them to - * separate lists, and wait for those lists to be emptied; but it's - * easier and more robust (though cpu-intensive) just to keep retrying. + * Limit the number of retries? No: when mmget_not_zero() above fails, + * that mm is likely to be freeing swap from exit_mmap(), which proceeds + * at its own independent pace; and even shmem_writepage() could have + * been preempted after get_swap_page(), temporarily hiding that swap. + * It's easy and robust (though cpu-intensive) just to keep retrying. */ if (si->inuse_pages) { if (!signal_pending(current)) -- cgit From 04f5866e41fb70690e28397487d8bd8eea7d712a Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Thu, 18 Apr 2019 17:50:52 -0700 Subject: coredump: fix race condition between mmget_not_zero()/get_task_mm() and core dumping The core dumping code has always run without holding the mmap_sem for writing, despite that is the only way to ensure that the entire vma layout will not change from under it. Only using some signal serialization on the processes belonging to the mm is not nearly enough. This was pointed out earlier. For example in Hugh's post from Jul 2017: https://lkml.kernel.org/r/alpine.LSU.2.11.1707191716030.2055@eggly.anvils "Not strictly relevant here, but a related note: I was very surprised to discover, only quite recently, how handle_mm_fault() may be called without down_read(mmap_sem) - when core dumping. That seems a misguided optimization to me, which would also be nice to correct" In particular because the growsdown and growsup can move the vm_start/vm_end the various loops the core dump does around the vma will not be consistent if page faults can happen concurrently. Pretty much all users calling mmget_not_zero()/get_task_mm() and then taking the mmap_sem had the potential to introduce unexpected side effects in the core dumping code. Adding mmap_sem for writing around the ->core_dump invocation is a viable long term fix, but it requires removing all copy user and page faults and to replace them with get_dump_page() for all binary formats which is not suitable as a short term fix. For the time being this solution manually covers the places that can confuse the core dump either by altering the vma layout or the vma flags while it runs. Once ->core_dump runs under mmap_sem for writing the function mmget_still_valid() can be dropped. Allowing mmap_sem protected sections to run in parallel with the coredump provides some minor parallelism advantage to the swapoff code (which seems to be safe enough by never mangling any vma field and can keep doing swapins in parallel to the core dumping) and to some other corner case. In order to facilitate the backporting I added "Fixes: 86039bd3b4e6" however the side effect of this same race condition in /proc/pid/mem should be reproducible since before 2.6.12-rc2 so I couldn't add any other "Fixes:" because there's no hash beyond the git genesis commit. Because find_extend_vma() is the only location outside of the process context that could modify the "mm" structures under mmap_sem for reading, by adding the mmget_still_valid() check to it, all other cases that take the mmap_sem for reading don't need the new check after mmget_not_zero()/get_task_mm(). The expand_stack() in page fault context also doesn't need the new check, because all tasks under core dumping are frozen. Link: http://lkml.kernel.org/r/20190325224949.11068-1-aarcange@redhat.com Fixes: 86039bd3b4e6 ("userfaultfd: add new syscall to provide memory externalization") Signed-off-by: Andrea Arcangeli Reported-by: Jann Horn Suggested-by: Oleg Nesterov Acked-by: Peter Xu Reviewed-by: Mike Rapoport Reviewed-by: Oleg Nesterov Reviewed-by: Jann Horn Acked-by: Jason Gunthorpe Acked-by: Michal Hocko Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/infiniband/core/uverbs_main.c | 3 +++ fs/proc/task_mmu.c | 18 ++++++++++++++++++ fs/userfaultfd.c | 9 +++++++++ include/linux/sched/mm.h | 21 +++++++++++++++++++++ mm/mmap.c | 7 ++++++- 5 files changed, 57 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 70b7d80431a9..f2e7ffe6fc54 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -993,6 +993,8 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile) * will only be one mm, so no big deal. */ down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto skip_mm; mutex_lock(&ufile->umap_lock); list_for_each_entry_safe (priv, next_priv, &ufile->umaps, list) { @@ -1007,6 +1009,7 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile) vma->vm_flags &= ~(VM_SHARED | VM_MAYSHARE); } mutex_unlock(&ufile->umap_lock); + skip_mm: up_write(&mm->mmap_sem); mmput(mm); } diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 92a91e7816d8..95ca1fe7283c 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1143,6 +1143,24 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, count = -EINTR; goto out_mm; } + /* + * Avoid to modify vma->vm_flags + * without locked ops while the + * coredump reads the vm_flags. + */ + if (!mmget_still_valid(mm)) { + /* + * Silently return "count" + * like if get_task_mm() + * failed. FIXME: should this + * function have returned + * -ESRCH if get_task_mm() + * failed like if + * get_proc_task() fails? + */ + up_write(&mm->mmap_sem); + goto out_mm; + } for (vma = mm->mmap; vma; vma = vma->vm_next) { vma->vm_flags &= ~VM_SOFTDIRTY; vma_set_page_prot(vma); diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 89800fc7dc9d..f5de1e726356 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -629,6 +629,8 @@ static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx, /* the various vma->vm_userfaultfd_ctx still points to it */ down_write(&mm->mmap_sem); + /* no task can run (and in turn coredump) yet */ + VM_WARN_ON(!mmget_still_valid(mm)); for (vma = mm->mmap; vma; vma = vma->vm_next) if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) { vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; @@ -883,6 +885,8 @@ static int userfaultfd_release(struct inode *inode, struct file *file) * taking the mmap_sem for writing. */ down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto skip_mm; prev = NULL; for (vma = mm->mmap; vma; vma = vma->vm_next) { cond_resched(); @@ -905,6 +909,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) vma->vm_flags = new_flags; vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX; } +skip_mm: up_write(&mm->mmap_sem); mmput(mm); wakeup: @@ -1333,6 +1338,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, goto out; down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto out_unlock; vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; @@ -1520,6 +1527,8 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, goto out; down_write(&mm->mmap_sem); + if (!mmget_still_valid(mm)) + goto out_unlock; vma = find_vma_prev(mm, start, &prev); if (!vma) goto out_unlock; diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index 0cd9f10423fb..a3fda9f024c3 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -49,6 +49,27 @@ static inline void mmdrop(struct mm_struct *mm) __mmdrop(mm); } +/* + * This has to be called after a get_task_mm()/mmget_not_zero() + * followed by taking the mmap_sem for writing before modifying the + * vmas or anything the coredump pretends not to change from under it. + * + * NOTE: find_extend_vma() called from GUP context is the only place + * that can modify the "mm" (notably the vm_start/end) under mmap_sem + * for reading and outside the context of the process, so it is also + * the only case that holds the mmap_sem for reading that must call + * this function. Generally if the mmap_sem is hold for reading + * there's no need of this check after get_task_mm()/mmget_not_zero(). + * + * This function can be obsoleted and the check can be removed, after + * the coredump code will hold the mmap_sem for writing before + * invoking the ->core_dump methods. + */ +static inline bool mmget_still_valid(struct mm_struct *mm) +{ + return likely(!mm->core_state); +} + /** * mmget() - Pin the address space associated with a &struct mm_struct. * @mm: The address space to pin. diff --git a/mm/mmap.c b/mm/mmap.c index 41eb48d9b527..bd7b9f293b39 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -45,6 +45,7 @@ #include #include #include +#include #include #include @@ -2525,7 +2526,8 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr) vma = find_vma_prev(mm, addr, &prev); if (vma && (vma->vm_start <= addr)) return vma; - if (!prev || expand_stack(prev, addr)) + /* don't alter vm_end if the coredump is running */ + if (!prev || !mmget_still_valid(mm) || expand_stack(prev, addr)) return NULL; if (prev->vm_flags & VM_LOCKED) populate_vma_page_range(prev, addr, prev->vm_end, NULL); @@ -2551,6 +2553,9 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr) return vma; if (!(vma->vm_flags & VM_GROWSDOWN)) return NULL; + /* don't alter vm_start if the coredump is running */ + if (!mmget_still_valid(mm)) + return NULL; start = vma->vm_start; if (expand_stack(vma, addr)) return NULL; -- cgit From b40fabc05ea047f6af5933d26a5483873340b0d4 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Fri, 19 Apr 2019 10:31:27 +0800 Subject: block: kill all_q_node in request_queue all_q_node has not been used since commit 4b855ad37194 ("blk-mq: Create hctx for each present CPU"), so remove it. Reviewed-by: Chaitanya Kulkarni Reviewed-by: Ming Lei Signed-off-by: Hou Tao Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5c58a3b2bf00..317ab30d2904 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -548,7 +548,6 @@ struct request_queue { struct rcu_head rcu_head; wait_queue_head_t mq_freeze_wq; struct percpu_ref q_usage_counter; - struct list_head all_q_node; struct blk_mq_tag_set *tag_set; struct list_head tag_set_list; -- cgit From 6bedf00e55e5dd0a4ed1ad3f06131edd6fb56ec8 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 17 Apr 2019 09:11:26 +0800 Subject: block: make sure that bvec length can't be overflow bvec->bv_offset may be bigger than PAGE_SIZE sometimes, such as, when one bio is splitted in the middle of one bvec via bio_split(), and bi_iter.bi_bvec_done is used to build offset of the 1st bvec of remained bio. And the remained bio's bvec may be re-submitted to fs layer via ITER_IBVEC, such as loop and nvme-loop. So we have to make sure that every bvec's offset is less than PAGE_SIZE from bio_for_each_segment_all() because some drivers(loop, nvme-loop) passes the splitted bvec to fs layer via ITER_BVEC. This patch fixes this issue reported by Zhang Yi When running nvme/011. Cc: Christoph Hellwig Cc: Yi Zhang Reported-by: Yi Zhang Reviewed-by: Christoph Hellwig Fixes: 6dc4f100c175 ("block: allow bio_for_each_segment_all() to iterate over multi-page bvec") Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/bvec.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 3bc91879e1e2..ff13cbc1887d 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -160,8 +160,9 @@ static inline void bvec_advance(const struct bio_vec *bvec, bv->bv_page = nth_page(bv->bv_page, 1); bv->bv_offset = 0; } else { - bv->bv_page = bvec->bv_page; - bv->bv_offset = bvec->bv_offset; + bv->bv_page = bvec_nth_page(bvec->bv_page, bvec->bv_offset / + PAGE_SIZE); + bv->bv_offset = bvec->bv_offset & ~PAGE_MASK; } bv->bv_len = min_t(unsigned int, PAGE_SIZE - bv->bv_offset, bvec->bv_len - iter_all->done); -- cgit From c2b71462d294cf517a0bc6e4fd6424d7cee5596f Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Fri, 19 Apr 2019 13:52:38 -0400 Subject: USB: core: Fix bug caused by duplicate interface PM usage counter The syzkaller fuzzer reported a bug in the USB hub driver which turned out to be caused by a negative runtime-PM usage counter. This allowed a hub to be runtime suspended at a time when the driver did not expect it. The symptom is a WARNING issued because the hub's status URB is submitted while it is already active: URB 0000000031fb463e submitted while active WARNING: CPU: 0 PID: 2917 at drivers/usb/core/urb.c:363 The negative runtime-PM usage count was caused by an unfortunate design decision made when runtime PM was first implemented for USB. At that time, USB class drivers were allowed to unbind from their interfaces without balancing the usage counter (i.e., leaving it with a positive count). The core code would take care of setting the counter back to 0 before allowing another driver to bind to the interface. Later on when runtime PM was implemented for the entire kernel, the opposite decision was made: Drivers were required to balance their runtime-PM get and put calls. In order to maintain backward compatibility, however, the USB subsystem adapted to the new implementation by keeping an independent usage counter for each interface and using it to automatically adjust the normal usage counter back to 0 whenever a driver was unbound. This approach involves duplicating information, but what is worse, it doesn't work properly in cases where a USB class driver delays decrementing the usage counter until after the driver's disconnect() routine has returned and the counter has been adjusted back to 0. Doing so would cause the usage counter to become negative. There's even a warning about this in the USB power management documentation! As it happens, this is exactly what the hub driver does. The kick_hub_wq() routine increments the runtime-PM usage counter, and the corresponding decrement is carried out by hub_event() in the context of the hub_wq work-queue thread. This work routine may sometimes run after the driver has been unbound from its interface, and when it does it causes the usage counter to go negative. It is not possible for hub_disconnect() to wait for a pending hub_event() call to finish, because hub_disconnect() is called with the device lock held and hub_event() acquires that lock. The only feasible fix is to reverse the original design decision: remove the duplicate interface-specific usage counter and require USB drivers to balance their runtime PM gets and puts. As far as I know, all existing drivers currently do this. Signed-off-by: Alan Stern Reported-and-tested-by: syzbot+7634edaea4d0b341c625@syzkaller.appspotmail.com CC: Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-api/usb/power-management.rst | 14 +++++++++----- drivers/usb/core/driver.c | 13 ------------- drivers/usb/storage/realtek_cr.c | 13 +++++-------- include/linux/usb.h | 2 -- 4 files changed, 14 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/Documentation/driver-api/usb/power-management.rst b/Documentation/driver-api/usb/power-management.rst index 79beb807996b..4a74cf6f2797 100644 --- a/Documentation/driver-api/usb/power-management.rst +++ b/Documentation/driver-api/usb/power-management.rst @@ -370,11 +370,15 @@ autosuspend the interface's device. When the usage counter is = 0 then the interface is considered to be idle, and the kernel may autosuspend the device. -Drivers need not be concerned about balancing changes to the usage -counter; the USB core will undo any remaining "get"s when a driver -is unbound from its interface. As a corollary, drivers must not call -any of the ``usb_autopm_*`` functions after their ``disconnect`` -routine has returned. +Drivers must be careful to balance their overall changes to the usage +counter. Unbalanced "get"s will remain in effect when a driver is +unbound from its interface, preventing the device from going into +runtime suspend should the interface be bound to a driver again. On +the other hand, drivers are allowed to achieve this balance by calling +the ``usb_autopm_*`` functions even after their ``disconnect`` routine +has returned -- say from within a work-queue routine -- provided they +retain an active reference to the interface (via ``usb_get_intf`` and +``usb_put_intf``). Drivers using the async routines are responsible for their own synchronization and mutual exclusion. diff --git a/drivers/usb/core/driver.c b/drivers/usb/core/driver.c index 8987cec9549d..ebcadaad89d1 100644 --- a/drivers/usb/core/driver.c +++ b/drivers/usb/core/driver.c @@ -473,11 +473,6 @@ static int usb_unbind_interface(struct device *dev) pm_runtime_disable(dev); pm_runtime_set_suspended(dev); - /* Undo any residual pm_autopm_get_interface_* calls */ - for (r = atomic_read(&intf->pm_usage_cnt); r > 0; --r) - usb_autopm_put_interface_no_suspend(intf); - atomic_set(&intf->pm_usage_cnt, 0); - if (!error) usb_autosuspend_device(udev); @@ -1633,7 +1628,6 @@ void usb_autopm_put_interface(struct usb_interface *intf) int status; usb_mark_last_busy(udev); - atomic_dec(&intf->pm_usage_cnt); status = pm_runtime_put_sync(&intf->dev); dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n", __func__, atomic_read(&intf->dev.power.usage_count), @@ -1662,7 +1656,6 @@ void usb_autopm_put_interface_async(struct usb_interface *intf) int status; usb_mark_last_busy(udev); - atomic_dec(&intf->pm_usage_cnt); status = pm_runtime_put(&intf->dev); dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n", __func__, atomic_read(&intf->dev.power.usage_count), @@ -1684,7 +1677,6 @@ void usb_autopm_put_interface_no_suspend(struct usb_interface *intf) struct usb_device *udev = interface_to_usbdev(intf); usb_mark_last_busy(udev); - atomic_dec(&intf->pm_usage_cnt); pm_runtime_put_noidle(&intf->dev); } EXPORT_SYMBOL_GPL(usb_autopm_put_interface_no_suspend); @@ -1715,8 +1707,6 @@ int usb_autopm_get_interface(struct usb_interface *intf) status = pm_runtime_get_sync(&intf->dev); if (status < 0) pm_runtime_put_sync(&intf->dev); - else - atomic_inc(&intf->pm_usage_cnt); dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n", __func__, atomic_read(&intf->dev.power.usage_count), status); @@ -1750,8 +1740,6 @@ int usb_autopm_get_interface_async(struct usb_interface *intf) status = pm_runtime_get(&intf->dev); if (status < 0 && status != -EINPROGRESS) pm_runtime_put_noidle(&intf->dev); - else - atomic_inc(&intf->pm_usage_cnt); dev_vdbg(&intf->dev, "%s: cnt %d -> %d\n", __func__, atomic_read(&intf->dev.power.usage_count), status); @@ -1775,7 +1763,6 @@ void usb_autopm_get_interface_no_resume(struct usb_interface *intf) struct usb_device *udev = interface_to_usbdev(intf); usb_mark_last_busy(udev); - atomic_inc(&intf->pm_usage_cnt); pm_runtime_get_noresume(&intf->dev); } EXPORT_SYMBOL_GPL(usb_autopm_get_interface_no_resume); diff --git a/drivers/usb/storage/realtek_cr.c b/drivers/usb/storage/realtek_cr.c index 31b024441938..cc794e25a0b6 100644 --- a/drivers/usb/storage/realtek_cr.c +++ b/drivers/usb/storage/realtek_cr.c @@ -763,18 +763,16 @@ static void rts51x_suspend_timer_fn(struct timer_list *t) break; case RTS51X_STAT_IDLE: case RTS51X_STAT_SS: - usb_stor_dbg(us, "RTS51X_STAT_SS, intf->pm_usage_cnt:%d, power.usage:%d\n", - atomic_read(&us->pusb_intf->pm_usage_cnt), + usb_stor_dbg(us, "RTS51X_STAT_SS, power.usage:%d\n", atomic_read(&us->pusb_intf->dev.power.usage_count)); - if (atomic_read(&us->pusb_intf->pm_usage_cnt) > 0) { + if (atomic_read(&us->pusb_intf->dev.power.usage_count) > 0) { usb_stor_dbg(us, "Ready to enter SS state\n"); rts51x_set_stat(chip, RTS51X_STAT_SS); /* ignore mass storage interface's children */ pm_suspend_ignore_children(&us->pusb_intf->dev, true); usb_autopm_put_interface_async(us->pusb_intf); - usb_stor_dbg(us, "RTS51X_STAT_SS 01, intf->pm_usage_cnt:%d, power.usage:%d\n", - atomic_read(&us->pusb_intf->pm_usage_cnt), + usb_stor_dbg(us, "RTS51X_STAT_SS 01, power.usage:%d\n", atomic_read(&us->pusb_intf->dev.power.usage_count)); } break; @@ -807,11 +805,10 @@ static void rts51x_invoke_transport(struct scsi_cmnd *srb, struct us_data *us) int ret; if (working_scsi(srb)) { - usb_stor_dbg(us, "working scsi, intf->pm_usage_cnt:%d, power.usage:%d\n", - atomic_read(&us->pusb_intf->pm_usage_cnt), + usb_stor_dbg(us, "working scsi, power.usage:%d\n", atomic_read(&us->pusb_intf->dev.power.usage_count)); - if (atomic_read(&us->pusb_intf->pm_usage_cnt) <= 0) { + if (atomic_read(&us->pusb_intf->dev.power.usage_count) <= 0) { ret = usb_autopm_get_interface(us->pusb_intf); usb_stor_dbg(us, "working scsi, ret=%d\n", ret); } diff --git a/include/linux/usb.h b/include/linux/usb.h index 5e49e82c4368..ff010d1fd1c7 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -200,7 +200,6 @@ usb_find_last_int_out_endpoint(struct usb_host_interface *alt, * @dev: driver model's view of this device * @usb_dev: if an interface is bound to the USB major, this will point * to the sysfs representation for that device. - * @pm_usage_cnt: PM usage counter for this interface * @reset_ws: Used for scheduling resets from atomic context. * @resetting_device: USB core reset the device, so use alt setting 0 as * current; needs bandwidth alloc after reset. @@ -257,7 +256,6 @@ struct usb_interface { struct device dev; /* interface specific device info */ struct device *usb_dev; - atomic_t pm_usage_cnt; /* usage counter for autosuspend */ struct work_struct reset_ws; /* for resets in atomic context */ }; #define to_usb_interface(d) container_of(d, struct usb_interface, dev) -- cgit From fe066621c7966fe47fa17c6be6fd81adb3c0509f Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Fri, 12 Apr 2019 23:19:11 +0800 Subject: gpio: merrifield: Fix build err without CONFIG_ACPI When building CONFIG_ACPI is not set gcc warn this: drivers/gpio/gpio-merrifield.c: In function mrfld_gpio_get_pinctrl_dev_name: drivers/gpio/gpio-merrifield.c:388:19: error: dereferencing pointer to incomplete type struct acpi_device put_device(&adev->dev); ^~ Reported-by: Hulk Robot Fixes: d00d2109c367 ("gpio: merrifield: Convert to use acpi_dev_get_first_match_dev()") Suggested-by: Andy Shevchenko Signed-off-by: YueHaibing Reviewed-by: Andy Shevchenko Acked-by: Linus Walleij Signed-off-by: Rafael J. Wysocki --- drivers/gpio/gpio-merrifield.c | 2 +- include/acpi/acpi_bus.h | 4 ++++ include/linux/acpi.h | 2 ++ 3 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/gpio/gpio-merrifield.c b/drivers/gpio/gpio-merrifield.c index 2383dc78b123..3302125e5265 100644 --- a/drivers/gpio/gpio-merrifield.c +++ b/drivers/gpio/gpio-merrifield.c @@ -385,7 +385,7 @@ static const char *mrfld_gpio_get_pinctrl_dev_name(struct mrfld_gpio *priv) adev = acpi_dev_get_first_match_dev("INTC1002", NULL, -1); if (adev) { name = devm_kstrdup(priv->dev, acpi_dev_name(adev), GFP_KERNEL); - put_device(&adev->dev); + acpi_dev_put(adev); } else { name = "pinctrl-merrifield"; } diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h index f7981751ac77..2a462cf4eaa9 100644 --- a/include/acpi/acpi_bus.h +++ b/include/acpi/acpi_bus.h @@ -687,6 +687,10 @@ static inline bool acpi_device_can_poweroff(struct acpi_device *adev) adev->power.states[ACPI_STATE_D3_HOT].flags.explicit_set); } +static inline void acpi_dev_put(struct acpi_device *adev) +{ + put_device(&adev->dev); +} #else /* CONFIG_ACPI */ static inline int register_acpi_bus_type(void *bus) { return 0; } diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 392413075cc0..ca55ae00f8c9 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -675,6 +675,8 @@ acpi_dev_get_first_match_dev(const char *hid, const char *uid, s64 hrv) return NULL; } +static inline void acpi_dev_put(struct acpi_device *adev) {} + static inline bool is_acpi_node(struct fwnode_handle *fwnode) { return false; -- cgit From 1c5c12ee308aacf635c8819cd4baa3bd58f8a8b7 Mon Sep 17 00:00:00 2001 From: Tao Ren Date: Wed, 24 Apr 2019 01:43:32 +0000 Subject: net/ncsi: handle overflow when incrementing mac address Previously BMC's MAC address is calculated by simply adding 1 to the last byte of network controller's MAC address, and it produces incorrect result when network controller's MAC address ends with 0xFF. The problem can be fixed by calling eth_addr_inc() function to increment MAC address; besides, the MAC address is also validated before assigning to BMC. Fixes: cb10c7c0dfd9 ("net/ncsi: Add NCSI Broadcom OEM command") Signed-off-by: Tao Ren Acked-by: Jakub Kicinski Acked-by: Samuel Mendoza-Jonas Signed-off-by: David S. Miller --- include/linux/etherdevice.h | 12 ++++++++++++ net/ncsi/ncsi-rsp.c | 6 +++++- 2 files changed, 17 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h index e2f3b21cd72a..aa8bfd6f738c 100644 --- a/include/linux/etherdevice.h +++ b/include/linux/etherdevice.h @@ -448,6 +448,18 @@ static inline void eth_addr_dec(u8 *addr) u64_to_ether_addr(u, addr); } +/** + * eth_addr_inc() - Increment the given MAC address. + * @addr: Pointer to a six-byte array containing Ethernet address to increment. + */ +static inline void eth_addr_inc(u8 *addr) +{ + u64 u = ether_addr_to_u64(addr); + + u++; + u64_to_ether_addr(u, addr); +} + /** * is_etherdev_addr - Tell if given Ethernet address belongs to the device. * @dev: Pointer to a device structure diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index dc07fcc7938e..802db01e3075 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -667,7 +668,10 @@ static int ncsi_rsp_handler_oem_bcm_gma(struct ncsi_request *nr) ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE; memcpy(saddr.sa_data, &rsp->data[BCM_MAC_ADDR_OFFSET], ETH_ALEN); /* Increase mac address by 1 for BMC's address */ - saddr.sa_data[ETH_ALEN - 1]++; + eth_addr_inc((u8 *)saddr.sa_data); + if (!is_valid_ether_addr((const u8 *)saddr.sa_data)) + return -ENXIO; + ret = ops->ndo_set_mac_address(ndev, &saddr); if (ret < 0) netdev_warn(ndev, "NCSI: 'Writing mac address to device failed\n"); -- cgit From d4645d30b50d1691c26ff0f8fa4e718b08f8d3bb Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Wed, 24 Apr 2019 10:52:53 +0200 Subject: smpboot: Place the __percpu annotation correctly The test robot reported a wrong assignment of a per-CPU variable which it detected by using sparse and sent a report. The assignment itself is correct. The annotation for sparse was wrong and hence the report. The first pointer is a "normal" pointer and points to the per-CPU memory area. That means that the __percpu annotation has to be moved. Move the __percpu annotation to pointer which points to the per-CPU area. This change affects only the sparse tool (and is ignored by the compiler). Reported-by: kbuild test robot Signed-off-by: Sebastian Andrzej Siewior Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: f97f8f06a49fe ("smpboot: Provide infrastructure for percpu hotplug threads") Link: http://lkml.kernel.org/r/20190424085253.12178-1-bigeasy@linutronix.de Signed-off-by: Ingo Molnar --- include/linux/smpboot.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h index d0884b525001..9d1bc65d226c 100644 --- a/include/linux/smpboot.h +++ b/include/linux/smpboot.h @@ -29,7 +29,7 @@ struct smpboot_thread_data; * @thread_comm: The base name of the thread */ struct smp_hotplug_thread { - struct task_struct __percpu **store; + struct task_struct * __percpu *store; struct list_head list; int (*thread_should_run)(unsigned int cpu); void (*thread_fn)(unsigned int cpu); -- cgit From b88c9f4129dcec941e5a26508e991c08051ed1ac Mon Sep 17 00:00:00 2001 From: Dmitry Osipenko Date: Thu, 25 Apr 2019 16:28:37 +0300 Subject: clk: Add missing stubs for a few functions Compilation fails if any of undeclared clk_set_*() functions are in use and CONFIG_HAVE_CLK=n. Reported-by: kbuild test robot Signed-off-by: Dmitry Osipenko Signed-off-by: Stephen Boyd --- include/linux/clk.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/clk.h b/include/linux/clk.h index d8bc1a856b39..f689fc58d7be 100644 --- a/include/linux/clk.h +++ b/include/linux/clk.h @@ -811,6 +811,22 @@ static inline bool clk_has_parent(struct clk *clk, struct clk *parent) return true; } +static inline int clk_set_rate_range(struct clk *clk, unsigned long min, + unsigned long max) +{ + return 0; +} + +static inline int clk_set_min_rate(struct clk *clk, unsigned long rate) +{ + return 0; +} + +static inline int clk_set_max_rate(struct clk *clk, unsigned long rate) +{ + return 0; +} + static inline int clk_set_parent(struct clk *clk, struct clk *parent) { return 0; -- cgit From f9ccd7c3a1d87cea3a6f9ed6c946dee9e7456b2e Mon Sep 17 00:00:00 2001 From: Ulf Hansson Date: Thu, 25 Apr 2019 11:04:13 +0200 Subject: PM / Domains: Allow to attach a CPU via genpd_dev_pm_attach_by_id|name() Attaching a device via genpd_dev_pm_attach_by_id|name() makes genpd allocate a virtual device that it attaches instead. This leads to a problem in case when the base device belongs to a CPU. More precisely, it means genpd_get_cpu() compares against the virtual device, thus it fails to find a matching CPU device. Address this limitation by passing the base device to genpd_get_cpu() rather than the virtual device. Moreover, to deal with detach correctly from genpd_remove_device(), store the CPU number in struct generic_pm_domain_data, so as to be able to clear the corresponding bit in the cpumask for the genpd. Signed-off-by: Ulf Hansson Acked-by: Viresh Kumar Signed-off-by: Rafael J. Wysocki --- drivers/base/power/domain.c | 20 ++++++++++---------- include/linux/pm_domain.h | 1 + 2 files changed, 11 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index da1c99178943..3d899e8abd58 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -1499,10 +1499,11 @@ static int genpd_get_cpu(struct generic_pm_domain *genpd, struct device *dev) return -1; } -static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev) +static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev, + struct device *base_dev) { struct generic_pm_domain_data *gpd_data; - int ret, cpu; + int ret; dev_dbg(dev, "%s()\n", __func__); @@ -1513,7 +1514,7 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev) if (IS_ERR(gpd_data)) return PTR_ERR(gpd_data); - cpu = genpd_get_cpu(genpd, dev); + gpd_data->cpu = genpd_get_cpu(genpd, base_dev); ret = genpd->attach_dev ? genpd->attach_dev(genpd, dev) : 0; if (ret) @@ -1521,7 +1522,7 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev) genpd_lock(genpd); - genpd_set_cpumask(genpd, cpu); + genpd_set_cpumask(genpd, gpd_data->cpu); dev_pm_domain_set(dev, &genpd->domain); genpd->device_count++; @@ -1549,7 +1550,7 @@ int pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev) int ret; mutex_lock(&gpd_list_lock); - ret = genpd_add_device(genpd, dev); + ret = genpd_add_device(genpd, dev, dev); mutex_unlock(&gpd_list_lock); return ret; @@ -1561,14 +1562,13 @@ static int genpd_remove_device(struct generic_pm_domain *genpd, { struct generic_pm_domain_data *gpd_data; struct pm_domain_data *pdd; - int cpu, ret = 0; + int ret = 0; dev_dbg(dev, "%s()\n", __func__); pdd = dev->power.subsys_data->domain_data; gpd_data = to_gpd_data(pdd); dev_pm_qos_remove_notifier(dev, &gpd_data->nb); - cpu = genpd_get_cpu(genpd, dev); genpd_lock(genpd); @@ -1580,7 +1580,7 @@ static int genpd_remove_device(struct generic_pm_domain *genpd, genpd->device_count--; genpd->max_off_time_changed = true; - genpd_clear_cpumask(genpd, cpu); + genpd_clear_cpumask(genpd, gpd_data->cpu); dev_pm_domain_set(dev, NULL); list_del_init(&pdd->list_node); @@ -2256,7 +2256,7 @@ int of_genpd_add_device(struct of_phandle_args *genpdspec, struct device *dev) goto out; } - ret = genpd_add_device(genpd, dev); + ret = genpd_add_device(genpd, dev, dev); out: mutex_unlock(&gpd_list_lock); @@ -2426,7 +2426,7 @@ static int __genpd_dev_pm_attach(struct device *dev, struct device *base_dev, dev_dbg(dev, "adding to PM domain %s\n", pd->name); - ret = genpd_add_device(pd, dev); + ret = genpd_add_device(pd, dev, base_dev); mutex_unlock(&gpd_list_lock); if (ret < 0) { diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index bc82e74560ee..0e8e356bed6a 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -175,6 +175,7 @@ struct generic_pm_domain_data { struct pm_domain_data base; struct gpd_timing_data td; struct notifier_block nb; + int cpu; unsigned int performance_state; void *data; }; -- cgit From 0edd6b64d1939e9e9168ff27947995bb7751db5d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 23 Apr 2019 21:55:59 +0200 Subject: bpf: Fix preempt_enable_no_resched() abuse Unless the very next line is schedule(), or implies it, one must not use preempt_enable_no_resched(). It can cause a preemption to go missing and thereby cause arbitrary delays, breaking the PREEMPT=y invariant. Cc: Roman Gushchin Cc: Alexei Starovoitov Cc: Daniel Borkmann Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f02367faa58d..944ccc310201 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -510,7 +510,7 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, } \ _out: \ rcu_read_unlock(); \ - preempt_enable_no_resched(); \ + preempt_enable(); \ _ret; \ }) -- cgit From b987222654f84f7b4ca95b3a55eca784cb30235b Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Thu, 4 Apr 2019 23:59:25 +0200 Subject: tracing: Fix buffer_ref pipe ops This fixes multiple issues in buffer_pipe_buf_ops: - The ->steal() handler must not return zero unless the pipe buffer has the only reference to the page. But generic_pipe_buf_steal() assumes that every reference to the pipe is tracked by the page's refcount, which isn't true for these buffers - buffer_pipe_buf_get(), which duplicates a buffer, doesn't touch the page's refcount. Fix it by using generic_pipe_buf_nosteal(), which refuses every attempted theft. It should be easy to actually support ->steal, but the only current users of pipe_buf_steal() are the virtio console and FUSE, and they also only use it as an optimization. So it's probably not worth the effort. - The ->get() and ->release() handlers can be invoked concurrently on pipe buffers backed by the same struct buffer_ref. Make them safe against concurrency by using refcount_t. - The pointers stored in ->private were only zeroed out when the last reference to the buffer_ref was dropped. As far as I know, this shouldn't be necessary anyway, but if we do it, let's always do it. Link: http://lkml.kernel.org/r/20190404215925.253531-1-jannh@google.com Cc: Ingo Molnar Cc: Masami Hiramatsu Cc: Al Viro Cc: stable@vger.kernel.org Fixes: 73a757e63114d ("ring-buffer: Return reader page back into existing ring buffer") Signed-off-by: Jann Horn Signed-off-by: Steven Rostedt (VMware) --- fs/splice.c | 4 ++-- include/linux/pipe_fs_i.h | 1 + kernel/trace/trace.c | 28 ++++++++++++++-------------- 3 files changed, 17 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/fs/splice.c b/fs/splice.c index 3ee7e82df48f..e75807380caa 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -330,8 +330,8 @@ const struct pipe_buf_operations default_pipe_buf_ops = { .get = generic_pipe_buf_get, }; -static int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe, - struct pipe_buffer *buf) +int generic_pipe_buf_nosteal(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) { return 1; } diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 787d224ff43e..a830e9a00eb9 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -174,6 +174,7 @@ void free_pipe_info(struct pipe_inode_info *); void generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *); int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *); +int generic_pipe_buf_nosteal(struct pipe_inode_info *, struct pipe_buffer *); void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *); void pipe_buf_mark_unmergeable(struct pipe_buffer *buf); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 21153e64bf1c..0cfa13a60086 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -7025,19 +7025,23 @@ struct buffer_ref { struct ring_buffer *buffer; void *page; int cpu; - int ref; + refcount_t refcount; }; +static void buffer_ref_release(struct buffer_ref *ref) +{ + if (!refcount_dec_and_test(&ref->refcount)) + return; + ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page); + kfree(ref); +} + static void buffer_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct buffer_ref *ref = (struct buffer_ref *)buf->private; - if (--ref->ref) - return; - - ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page); - kfree(ref); + buffer_ref_release(ref); buf->private = 0; } @@ -7046,14 +7050,14 @@ static void buffer_pipe_buf_get(struct pipe_inode_info *pipe, { struct buffer_ref *ref = (struct buffer_ref *)buf->private; - ref->ref++; + refcount_inc(&ref->refcount); } /* Pipe buffer operations for a buffer. */ static const struct pipe_buf_operations buffer_pipe_buf_ops = { .confirm = generic_pipe_buf_confirm, .release = buffer_pipe_buf_release, - .steal = generic_pipe_buf_steal, + .steal = generic_pipe_buf_nosteal, .get = buffer_pipe_buf_get, }; @@ -7066,11 +7070,7 @@ static void buffer_spd_release(struct splice_pipe_desc *spd, unsigned int i) struct buffer_ref *ref = (struct buffer_ref *)spd->partial[i].private; - if (--ref->ref) - return; - - ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page); - kfree(ref); + buffer_ref_release(ref); spd->partial[i].private = 0; } @@ -7125,7 +7125,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, break; } - ref->ref = 1; + refcount_set(&ref->refcount, 1); ref->buffer = iter->trace_buffer->buffer; ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file); if (IS_ERR(ref->page)) { -- cgit From d15d356887e770c5f2dcf963b52c7cb510c9e42d Mon Sep 17 00:00:00 2001 From: Kairui Song Date: Tue, 23 Apr 2019 00:26:52 +0800 Subject: perf/x86: Make perf callchains work without CONFIG_FRAME_POINTER Currently perf callchain doesn't work well with ORC unwinder when sampling from trace point. We'll get useless in kernel callchain like this: perf 6429 [000] 22.498450: kmem:mm_page_alloc: page=0x176a17 pfn=1534487 order=0 migratetype=0 gfp_flags=GFP_KERNEL ffffffffbe23e32e __alloc_pages_nodemask+0x22e (/lib/modules/5.1.0-rc3+/build/vmlinux) 7efdf7f7d3e8 __poll+0x18 (/usr/lib64/libc-2.28.so) 5651468729c1 [unknown] (/usr/bin/perf) 5651467ee82a main+0x69a (/usr/bin/perf) 7efdf7eaf413 __libc_start_main+0xf3 (/usr/lib64/libc-2.28.so) 5541f689495641d7 [unknown] ([unknown]) The root cause is that, for trace point events, it doesn't provide a real snapshot of the hardware registers. Instead perf tries to get required caller's registers and compose a fake register snapshot which suppose to contain enough information for start a unwinding. However without CONFIG_FRAME_POINTER, if failed to get caller's BP as the frame pointer, so current frame pointer is returned instead. We get a invalid register combination which confuse the unwinder, and end the stacktrace early. So in such case just don't try dump BP, and let the unwinder start directly when the register is not a real snapshot. Use SP as the skip mark, unwinder will skip all the frames until it meet the frame of the trace point caller. Tested with frame pointer unwinder and ORC unwinder, this makes perf callchain get the full kernel space stacktrace again like this: perf 6503 [000] 1567.570191: kmem:mm_page_alloc: page=0x16c904 pfn=1493252 order=0 migratetype=0 gfp_flags=GFP_KERNEL ffffffffb523e2ae __alloc_pages_nodemask+0x22e (/lib/modules/5.1.0-rc3+/build/vmlinux) ffffffffb52383bd __get_free_pages+0xd (/lib/modules/5.1.0-rc3+/build/vmlinux) ffffffffb52fd28a __pollwait+0x8a (/lib/modules/5.1.0-rc3+/build/vmlinux) ffffffffb521426f perf_poll+0x2f (/lib/modules/5.1.0-rc3+/build/vmlinux) ffffffffb52fe3e2 do_sys_poll+0x252 (/lib/modules/5.1.0-rc3+/build/vmlinux) ffffffffb52ff027 __x64_sys_poll+0x37 (/lib/modules/5.1.0-rc3+/build/vmlinux) ffffffffb500418b do_syscall_64+0x5b (/lib/modules/5.1.0-rc3+/build/vmlinux) ffffffffb5a0008c entry_SYSCALL_64_after_hwframe+0x44 (/lib/modules/5.1.0-rc3+/build/vmlinux) 7f71e92d03e8 __poll+0x18 (/usr/lib64/libc-2.28.so) 55a22960d9c1 [unknown] (/usr/bin/perf) 55a22958982a main+0x69a (/usr/bin/perf) 7f71e9202413 __libc_start_main+0xf3 (/usr/lib64/libc-2.28.so) 5541f689495641d7 [unknown] ([unknown]) Co-developed-by: Josh Poimboeuf Signed-off-by: Kairui Song Signed-off-by: Peter Zijlstra (Intel) Cc: Alexander Shishkin Cc: Alexei Starovoitov Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: Dave Young Cc: Jiri Olsa Cc: Linus Torvalds Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20190422162652.15483-1-kasong@redhat.com Signed-off-by: Ingo Molnar --- arch/x86/events/core.c | 21 +++++++++++++++++---- arch/x86/include/asm/perf_event.h | 7 +------ arch/x86/include/asm/stacktrace.h | 13 ------------- include/linux/perf_event.h | 14 ++++++++++---- 4 files changed, 28 insertions(+), 27 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index de1a924a4914..f315425d8468 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -2382,6 +2382,15 @@ void arch_perf_update_userpage(struct perf_event *event, cyc2ns_read_end(); } +/* + * Determine whether the regs were taken from an irq/exception handler rather + * than from perf_arch_fetch_caller_regs(). + */ +static bool perf_hw_regs(struct pt_regs *regs) +{ + return regs->flags & X86_EFLAGS_FIXED; +} + void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { @@ -2393,11 +2402,15 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re return; } - if (perf_callchain_store(entry, regs->ip)) - return; + if (perf_hw_regs(regs)) { + if (perf_callchain_store(entry, regs->ip)) + return; + unwind_start(&state, current, regs, NULL); + } else { + unwind_start(&state, current, NULL, (void *)regs->sp); + } - for (unwind_start(&state, current, regs, NULL); !unwind_done(&state); - unwind_next_frame(&state)) { + for (; !unwind_done(&state); unwind_next_frame(&state)) { addr = unwind_get_return_address(&state); if (!addr || perf_callchain_store(entry, addr)) return; diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 04768a3a5454..1392d5e6e8d6 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -308,14 +308,9 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs); */ #define perf_arch_fetch_caller_regs(regs, __ip) { \ (regs)->ip = (__ip); \ - (regs)->bp = caller_frame_pointer(); \ + (regs)->sp = (unsigned long)__builtin_frame_address(0); \ (regs)->cs = __KERNEL_CS; \ regs->flags = 0; \ - asm volatile( \ - _ASM_MOV "%%"_ASM_SP ", %0\n" \ - : "=m" ((regs)->sp) \ - :: "memory" \ - ); \ } struct perf_guest_switch_msr { diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index f335aad404a4..beef7ad9e43a 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -98,19 +98,6 @@ struct stack_frame_ia32 { u32 return_address; }; -static inline unsigned long caller_frame_pointer(void) -{ - struct stack_frame *frame; - - frame = __builtin_frame_address(0); - -#ifdef CONFIG_FRAME_POINTER - frame = frame->next_frame; -#endif - - return (unsigned long)frame; -} - void show_opcodes(struct pt_regs *regs, const char *loglvl); void show_ip(struct pt_regs *regs, const char *loglvl); #endif /* _ASM_X86_STACKTRACE_H */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index f3864e1c5569..cf023db0e8a2 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1058,12 +1058,18 @@ static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned lo #endif /* - * Take a snapshot of the regs. Skip ip and frame pointer to - * the nth caller. We only need a few of the regs: + * When generating a perf sample in-line, instead of from an interrupt / + * exception, we lack a pt_regs. This is typically used from software events + * like: SW_CONTEXT_SWITCHES, SW_MIGRATIONS and the tie-in with tracepoints. + * + * We typically don't need a full set, but (for x86) do require: * - ip for PERF_SAMPLE_IP * - cs for user_mode() tests - * - bp for callchains - * - eflags, for future purposes, just in case + * - sp for PERF_SAMPLE_CALLCHAIN + * - eflags for MISC bits and CALLCHAIN (see: perf_hw_regs()) + * + * NOTE: assumes @regs is otherwise already 0 filled; this is important for + * things like PERF_SAMPLE_REGS_INTR. */ static inline void perf_fetch_caller_regs(struct pt_regs *regs) { -- cgit From ad282a8117d5048398f506f20b092c14b3b3c43f Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 29 Mar 2019 17:08:52 -0700 Subject: locking/static_key: Add support for deferred static branches Add deferred static branches. We can't unfortunately use the nice trick of encapsulating the entire structure in true/false variants, because the inside has to be either struct static_key_true or struct static_key_false. Use defines to pass the appropriate members to the helpers separately. Signed-off-by: Jakub Kicinski Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Simon Horman Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Cc: alexei.starovoitov@gmail.com Cc: ard.biesheuvel@linaro.org Cc: oss-drivers@netronome.com Cc: yamada.masahiro@socionext.com Link: https://lkml.kernel.org/r/20190330000854.30142-2-jakub.kicinski@netronome.com Signed-off-by: Ingo Molnar --- include/linux/jump_label_ratelimit.h | 64 ++++++++++++++++++++++++++++++++++-- kernel/jump_label.c | 17 ++++++---- 2 files changed, 71 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/jump_label_ratelimit.h b/include/linux/jump_label_ratelimit.h index a49f2b45b3f0..42710d5949ba 100644 --- a/include/linux/jump_label_ratelimit.h +++ b/include/linux/jump_label_ratelimit.h @@ -12,21 +12,79 @@ struct static_key_deferred { struct delayed_work work; }; -extern void static_key_slow_dec_deferred(struct static_key_deferred *key); -extern void static_key_deferred_flush(struct static_key_deferred *key); +struct static_key_true_deferred { + struct static_key_true key; + unsigned long timeout; + struct delayed_work work; +}; + +struct static_key_false_deferred { + struct static_key_false key; + unsigned long timeout; + struct delayed_work work; +}; + +#define static_key_slow_dec_deferred(x) \ + __static_key_slow_dec_deferred(&(x)->key, &(x)->work, (x)->timeout) +#define static_branch_slow_dec_deferred(x) \ + __static_key_slow_dec_deferred(&(x)->key.key, &(x)->work, (x)->timeout) + +#define static_key_deferred_flush(x) \ + __static_key_deferred_flush((x), &(x)->work) + +extern void +__static_key_slow_dec_deferred(struct static_key *key, + struct delayed_work *work, + unsigned long timeout); +extern void __static_key_deferred_flush(void *key, struct delayed_work *work); extern void jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl); +extern void jump_label_update_timeout(struct work_struct *work); + +#define DEFINE_STATIC_KEY_DEFERRED_TRUE(name, rl) \ + struct static_key_true_deferred name = { \ + .key = { STATIC_KEY_INIT_TRUE }, \ + .timeout = (rl), \ + .work = __DELAYED_WORK_INITIALIZER((name).work, \ + jump_label_update_timeout, \ + 0), \ + } + +#define DEFINE_STATIC_KEY_DEFERRED_FALSE(name, rl) \ + struct static_key_false_deferred name = { \ + .key = { STATIC_KEY_INIT_FALSE }, \ + .timeout = (rl), \ + .work = __DELAYED_WORK_INITIALIZER((name).work, \ + jump_label_update_timeout, \ + 0), \ + } + +#define static_branch_deferred_inc(x) static_branch_inc(&(x)->key) + #else /* !CONFIG_JUMP_LABEL */ struct static_key_deferred { struct static_key key; }; +struct static_key_true_deferred { + struct static_key_true key; +}; +struct static_key_false_deferred { + struct static_key_false key; +}; +#define DEFINE_STATIC_KEY_DEFERRED_TRUE(name, rl) \ + struct static_key_true_deferred name = { STATIC_KEY_TRUE_INIT } +#define DEFINE_STATIC_KEY_DEFERRED_FALSE(name, rl) \ + struct static_key_false_deferred name = { STATIC_KEY_FALSE_INIT } + +#define static_branch_slow_dec_deferred(x) static_branch_dec(&(x)->key) + static inline void static_key_slow_dec_deferred(struct static_key_deferred *key) { STATIC_KEY_CHECK_USE(key); static_key_slow_dec(&key->key); } -static inline void static_key_deferred_flush(struct static_key_deferred *key) +static inline void static_key_deferred_flush(void *key) { STATIC_KEY_CHECK_USE(key); } diff --git a/kernel/jump_label.c b/kernel/jump_label.c index a799b1ac6b2f..73bbbaddbd9c 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -244,12 +244,13 @@ static void __static_key_slow_dec(struct static_key *key, cpus_read_unlock(); } -static void jump_label_update_timeout(struct work_struct *work) +void jump_label_update_timeout(struct work_struct *work) { struct static_key_deferred *key = container_of(work, struct static_key_deferred, work.work); __static_key_slow_dec(&key->key, 0, NULL); } +EXPORT_SYMBOL_GPL(jump_label_update_timeout); void static_key_slow_dec(struct static_key *key) { @@ -264,19 +265,21 @@ void static_key_slow_dec_cpuslocked(struct static_key *key) __static_key_slow_dec_cpuslocked(key, 0, NULL); } -void static_key_slow_dec_deferred(struct static_key_deferred *key) +void __static_key_slow_dec_deferred(struct static_key *key, + struct delayed_work *work, + unsigned long timeout) { STATIC_KEY_CHECK_USE(key); - __static_key_slow_dec(&key->key, key->timeout, &key->work); + __static_key_slow_dec(key, timeout, work); } -EXPORT_SYMBOL_GPL(static_key_slow_dec_deferred); +EXPORT_SYMBOL_GPL(__static_key_slow_dec_deferred); -void static_key_deferred_flush(struct static_key_deferred *key) +void __static_key_deferred_flush(void *key, struct delayed_work *work) { STATIC_KEY_CHECK_USE(key); - flush_delayed_work(&key->work); + flush_delayed_work(work); } -EXPORT_SYMBOL_GPL(static_key_deferred_flush); +EXPORT_SYMBOL_GPL(__static_key_deferred_flush); void jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl) -- cgit From 268a78404973594d1a7ec3a2b6a2474e0543a435 Mon Sep 17 00:00:00 2001 From: Philipp Rudo Date: Tue, 26 Mar 2019 15:45:53 +0100 Subject: s390/kexec_file: Disable kexec_load when IPLed secure A kernel loaded via kexec_load cannot be verified. Thus disable kexec_load systemcall in kernels which where IPLed securely. Use the IMA mechanism to do so. Signed-off-by: Philipp Rudo Signed-off-by: Martin Schwidefsky --- arch/s390/kernel/Makefile | 2 ++ arch/s390/kernel/ima_arch.c | 14 ++++++++++++++ include/linux/ima.h | 2 +- 3 files changed, 17 insertions(+), 1 deletion(-) create mode 100644 arch/s390/kernel/ima_arch.c (limited to 'include/linux') diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile index 1222db6d4ee9..d28acd7ba81e 100644 --- a/arch/s390/kernel/Makefile +++ b/arch/s390/kernel/Makefile @@ -77,6 +77,8 @@ obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_KEXEC_FILE) += machine_kexec_file.o kexec_image.o obj-$(CONFIG_KEXEC_FILE) += kexec_elf.o +obj-$(CONFIG_IMA) += ima_arch.o + obj-$(CONFIG_PERF_EVENTS) += perf_event.o perf_cpum_cf_common.o obj-$(CONFIG_PERF_EVENTS) += perf_cpum_cf.o perf_cpum_sf.o obj-$(CONFIG_PERF_EVENTS) += perf_cpum_cf_events.o perf_regs.o diff --git a/arch/s390/kernel/ima_arch.c b/arch/s390/kernel/ima_arch.c new file mode 100644 index 000000000000..f3c3e6e1c5d3 --- /dev/null +++ b/arch/s390/kernel/ima_arch.c @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +bool arch_ima_get_secureboot(void) +{ + return ipl_secure_flag; +} + +const char * const *arch_get_ima_policy(void) +{ + return NULL; +} diff --git a/include/linux/ima.h b/include/linux/ima.h index dc12fbcf484c..fd9f7cf4cdf5 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -31,7 +31,7 @@ extern void ima_post_path_mknod(struct dentry *dentry); extern void ima_add_kexec_buffer(struct kimage *image); #endif -#if defined(CONFIG_X86) && defined(CONFIG_EFI) +#if (defined(CONFIG_X86) && defined(CONFIG_EFI)) || defined(CONFIG_S390) extern bool arch_ima_get_secureboot(void); extern const char * const *arch_get_ima_policy(void); #else -- cgit From 3d9a8072915366b5932beeed97f158f8d4955768 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 25 Apr 2019 11:44:54 +0200 Subject: tracing: Cleanup stack trace code - Remove the extra array member of stack_dump_trace[] along with the ARRAY_SIZE - 1 initialization for struct stack_trace :: max_entries. Both are historical leftovers of no value. The stack tracer never exceeds the array and there is no extra storage requirement either. - Make variables which are only used in trace_stack.c static. - Simplify the enable/disable logic. - Rename stack_trace_print() as it's using the stack_trace_ namespace. Free the name up for stack trace related functions. Signed-off-by: Thomas Gleixner Reviewed-by: Steven Rostedt Reviewed-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Alexander Potapenko Cc: Alexey Dobriyan Cc: Andrew Morton Cc: Christoph Lameter Cc: Pekka Enberg Cc: linux-mm@kvack.org Cc: David Rientjes Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Andrey Ryabinin Cc: kasan-dev@googlegroups.com Cc: Mike Rapoport Cc: Akinobu Mita Cc: Christoph Hellwig Cc: iommu@lists.linux-foundation.org Cc: Robin Murphy Cc: Marek Szyprowski Cc: Johannes Thumshirn Cc: David Sterba Cc: Chris Mason Cc: Josef Bacik Cc: linux-btrfs@vger.kernel.org Cc: dm-devel@redhat.com Cc: Mike Snitzer Cc: Alasdair Kergon Cc: Daniel Vetter Cc: intel-gfx@lists.freedesktop.org Cc: Joonas Lahtinen Cc: Maarten Lankhorst Cc: dri-devel@lists.freedesktop.org Cc: David Airlie Cc: Jani Nikula Cc: Rodrigo Vivi Cc: Tom Zanussi Cc: Miroslav Benes Cc: linux-arch@vger.kernel.org Link: https://lkml.kernel.org/r/20190425094801.230654524@linutronix.de --- include/linux/ftrace.h | 18 ++++-------------- kernel/trace/trace_stack.c | 42 +++++++++++++----------------------------- 2 files changed, 17 insertions(+), 43 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 730876187344..20899919ead8 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -241,21 +241,11 @@ static inline void ftrace_free_mem(struct module *mod, void *start, void *end) { #ifdef CONFIG_STACK_TRACER -#define STACK_TRACE_ENTRIES 500 - -struct stack_trace; - -extern unsigned stack_trace_index[]; -extern struct stack_trace stack_trace_max; -extern unsigned long stack_trace_max_size; -extern arch_spinlock_t stack_trace_max_lock; - extern int stack_tracer_enabled; -void stack_trace_print(void); -int -stack_trace_sysctl(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos); + +int stack_trace_sysctl(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos); /* DO NOT MODIFY THIS VARIABLE DIRECTLY! */ DECLARE_PER_CPU(int, disable_stack_tracer); diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index c6e54ff25cae..4efda5f75a0f 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -18,30 +18,26 @@ #include "trace.h" -static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES + 1]; -unsigned stack_trace_index[STACK_TRACE_ENTRIES]; +#define STACK_TRACE_ENTRIES 500 + +static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES]; +static unsigned stack_trace_index[STACK_TRACE_ENTRIES]; -/* - * Reserve one entry for the passed in ip. This will allow - * us to remove most or all of the stack size overhead - * added by the stack tracer itself. - */ struct stack_trace stack_trace_max = { - .max_entries = STACK_TRACE_ENTRIES - 1, + .max_entries = STACK_TRACE_ENTRIES, .entries = &stack_dump_trace[0], }; -unsigned long stack_trace_max_size; -arch_spinlock_t stack_trace_max_lock = +static unsigned long stack_trace_max_size; +static arch_spinlock_t stack_trace_max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; DEFINE_PER_CPU(int, disable_stack_tracer); static DEFINE_MUTEX(stack_sysctl_mutex); int stack_tracer_enabled; -static int last_stack_tracer_enabled; -void stack_trace_print(void) +static void print_max_stack(void) { long i; int size; @@ -61,16 +57,7 @@ void stack_trace_print(void) } } -/* - * When arch-specific code overrides this function, the following - * data should be filled up, assuming stack_trace_max_lock is held to - * prevent concurrent updates. - * stack_trace_index[] - * stack_trace_max - * stack_trace_max_size - */ -void __weak -check_stack(unsigned long ip, unsigned long *stack) +static void check_stack(unsigned long ip, unsigned long *stack) { unsigned long this_size, flags; unsigned long *p, *top, *start; static int tracer_frame; @@ -179,7 +166,7 @@ check_stack(unsigned long ip, unsigned long *stack) stack_trace_max.nr_entries = x; if (task_stack_end_corrupted(current)) { - stack_trace_print(); + print_max_stack(); BUG(); } @@ -412,23 +399,21 @@ stack_trace_sysctl(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + int was_enabled; int ret; mutex_lock(&stack_sysctl_mutex); + was_enabled = !!stack_tracer_enabled; ret = proc_dointvec(table, write, buffer, lenp, ppos); - if (ret || !write || - (last_stack_tracer_enabled == !!stack_tracer_enabled)) + if (ret || !write || (was_enabled == !!stack_tracer_enabled)) goto out; - last_stack_tracer_enabled = !!stack_tracer_enabled; - if (stack_tracer_enabled) register_ftrace_function(&trace_ops); else unregister_ftrace_function(&trace_ops); - out: mutex_unlock(&stack_sysctl_mutex); return ret; @@ -444,7 +429,6 @@ static __init int enable_stacktrace(char *str) strncpy(stack_trace_filter_buf, str + len, COMMAND_LINE_SIZE); stack_tracer_enabled = 1; - last_stack_tracer_enabled = 1; return 1; } __setup("stacktrace", enable_stacktrace); -- cgit From e9b98e162aa53cbea7c8b0d6c9d5dc6e0f822b9c Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 25 Apr 2019 11:44:55 +0200 Subject: stacktrace: Provide helpers for common stack trace operations All operations with stack traces are based on struct stack_trace. That's a horrible construct as the struct is a kitchen sink for input and output. Quite some usage sites embed it into their own data structures which creates weird indirections. There is absolutely no point in doing so. For all use cases a storage array and the number of valid stack trace entries in the array is sufficient. Provide helper functions which avoid the struct stack_trace indirection so the usage sites can be cleaned up. Signed-off-by: Thomas Gleixner Reviewed-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Steven Rostedt Cc: Alexander Potapenko Cc: Alexey Dobriyan Cc: Andrew Morton Cc: Christoph Lameter Cc: Pekka Enberg Cc: linux-mm@kvack.org Cc: David Rientjes Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Andrey Ryabinin Cc: kasan-dev@googlegroups.com Cc: Mike Rapoport Cc: Akinobu Mita Cc: Christoph Hellwig Cc: iommu@lists.linux-foundation.org Cc: Robin Murphy Cc: Marek Szyprowski Cc: Johannes Thumshirn Cc: David Sterba Cc: Chris Mason Cc: Josef Bacik Cc: linux-btrfs@vger.kernel.org Cc: dm-devel@redhat.com Cc: Mike Snitzer Cc: Alasdair Kergon Cc: Daniel Vetter Cc: intel-gfx@lists.freedesktop.org Cc: Joonas Lahtinen Cc: Maarten Lankhorst Cc: dri-devel@lists.freedesktop.org Cc: David Airlie Cc: Jani Nikula Cc: Rodrigo Vivi Cc: Tom Zanussi Cc: Miroslav Benes Cc: linux-arch@vger.kernel.org Link: https://lkml.kernel.org/r/20190425094801.324810708@linutronix.de --- include/linux/stacktrace.h | 27 +++++++ kernel/stacktrace.c | 170 +++++++++++++++++++++++++++++++++++++++++---- 2 files changed, 182 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h index ba29a0613e66..a24340b3e9e1 100644 --- a/include/linux/stacktrace.h +++ b/include/linux/stacktrace.h @@ -3,11 +3,26 @@ #define __LINUX_STACKTRACE_H #include +#include struct task_struct; struct pt_regs; #ifdef CONFIG_STACKTRACE +void stack_trace_print(unsigned long *trace, unsigned int nr_entries, + int spaces); +int stack_trace_snprint(char *buf, size_t size, unsigned long *entries, + unsigned int nr_entries, int spaces); +unsigned int stack_trace_save(unsigned long *store, unsigned int size, + unsigned int skipnr); +unsigned int stack_trace_save_tsk(struct task_struct *task, + unsigned long *store, unsigned int size, + unsigned int skipnr); +unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store, + unsigned int size, unsigned int skipnr); +unsigned int stack_trace_save_user(unsigned long *store, unsigned int size); + +/* Internal interfaces. Do not use in generic code */ struct stack_trace { unsigned int nr_entries, max_entries; unsigned long *entries; @@ -41,4 +56,16 @@ extern void save_stack_trace_user(struct stack_trace *trace); # define save_stack_trace_tsk_reliable(tsk, trace) ({ -ENOSYS; }) #endif /* CONFIG_STACKTRACE */ +#if defined(CONFIG_STACKTRACE) && defined(CONFIG_HAVE_RELIABLE_STACKTRACE) +int stack_trace_save_tsk_reliable(struct task_struct *tsk, unsigned long *store, + unsigned int size); +#else +static inline int stack_trace_save_tsk_reliable(struct task_struct *tsk, + unsigned long *store, + unsigned int size) +{ + return -ENOSYS; +} +#endif + #endif /* __LINUX_STACKTRACE_H */ diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c index f8edee9c792d..b38333b3bc18 100644 --- a/kernel/stacktrace.c +++ b/kernel/stacktrace.c @@ -11,35 +11,54 @@ #include #include -void print_stack_trace(struct stack_trace *trace, int spaces) +/** + * stack_trace_print - Print the entries in the stack trace + * @entries: Pointer to storage array + * @nr_entries: Number of entries in the storage array + * @spaces: Number of leading spaces to print + */ +void stack_trace_print(unsigned long *entries, unsigned int nr_entries, + int spaces) { - int i; + unsigned int i; - if (WARN_ON(!trace->entries)) + if (WARN_ON(!entries)) return; - for (i = 0; i < trace->nr_entries; i++) - printk("%*c%pS\n", 1 + spaces, ' ', (void *)trace->entries[i]); + for (i = 0; i < nr_entries; i++) + printk("%*c%pS\n", 1 + spaces, ' ', (void *)entries[i]); +} +EXPORT_SYMBOL_GPL(stack_trace_print); + +void print_stack_trace(struct stack_trace *trace, int spaces) +{ + stack_trace_print(trace->entries, trace->nr_entries, spaces); } EXPORT_SYMBOL_GPL(print_stack_trace); -int snprint_stack_trace(char *buf, size_t size, - struct stack_trace *trace, int spaces) +/** + * stack_trace_snprint - Print the entries in the stack trace into a buffer + * @buf: Pointer to the print buffer + * @size: Size of the print buffer + * @entries: Pointer to storage array + * @nr_entries: Number of entries in the storage array + * @spaces: Number of leading spaces to print + * + * Return: Number of bytes printed. + */ +int stack_trace_snprint(char *buf, size_t size, unsigned long *entries, + unsigned int nr_entries, int spaces) { - int i; - int generated; - int total = 0; + unsigned int generated, i, total = 0; - if (WARN_ON(!trace->entries)) + if (WARN_ON(!entries)) return 0; - for (i = 0; i < trace->nr_entries; i++) { + for (i = 0; i < nr_entries && size; i++) { generated = snprintf(buf, size, "%*c%pS\n", 1 + spaces, ' ', - (void *)trace->entries[i]); + (void *)entries[i]); total += generated; - - /* Assume that generated isn't a negative number */ if (generated >= size) { buf += size; size = 0; @@ -51,6 +70,14 @@ int snprint_stack_trace(char *buf, size_t size, return total; } +EXPORT_SYMBOL_GPL(stack_trace_snprint); + +int snprint_stack_trace(char *buf, size_t size, + struct stack_trace *trace, int spaces) +{ + return stack_trace_snprint(buf, size, trace->entries, + trace->nr_entries, spaces); +} EXPORT_SYMBOL_GPL(snprint_stack_trace); /* @@ -77,3 +104,116 @@ save_stack_trace_tsk_reliable(struct task_struct *tsk, WARN_ONCE(1, KERN_INFO "save_stack_tsk_reliable() not implemented yet.\n"); return -ENOSYS; } + +/** + * stack_trace_save - Save a stack trace into a storage array + * @store: Pointer to storage array + * @size: Size of the storage array + * @skipnr: Number of entries to skip at the start of the stack trace + * + * Return: Number of trace entries stored + */ +unsigned int stack_trace_save(unsigned long *store, unsigned int size, + unsigned int skipnr) +{ + struct stack_trace trace = { + .entries = store, + .max_entries = size, + .skip = skipnr + 1, + }; + + save_stack_trace(&trace); + return trace.nr_entries; +} +EXPORT_SYMBOL_GPL(stack_trace_save); + +/** + * stack_trace_save_tsk - Save a task stack trace into a storage array + * @task: The task to examine + * @store: Pointer to storage array + * @size: Size of the storage array + * @skipnr: Number of entries to skip at the start of the stack trace + * + * Return: Number of trace entries stored + */ +unsigned int stack_trace_save_tsk(struct task_struct *task, + unsigned long *store, unsigned int size, + unsigned int skipnr) +{ + struct stack_trace trace = { + .entries = store, + .max_entries = size, + .skip = skipnr + 1, + }; + + save_stack_trace_tsk(task, &trace); + return trace.nr_entries; +} + +/** + * stack_trace_save_regs - Save a stack trace based on pt_regs into a storage array + * @regs: Pointer to pt_regs to examine + * @store: Pointer to storage array + * @size: Size of the storage array + * @skipnr: Number of entries to skip at the start of the stack trace + * + * Return: Number of trace entries stored + */ +unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store, + unsigned int size, unsigned int skipnr) +{ + struct stack_trace trace = { + .entries = store, + .max_entries = size, + .skip = skipnr, + }; + + save_stack_trace_regs(regs, &trace); + return trace.nr_entries; +} + +#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE +/** + * stack_trace_save_tsk_reliable - Save task stack with verification + * @tsk: Pointer to the task to examine + * @store: Pointer to storage array + * @size: Size of the storage array + * + * Return: An error if it detects any unreliable features of the + * stack. Otherwise it guarantees that the stack trace is + * reliable and returns the number of entries stored. + * + * If the task is not 'current', the caller *must* ensure the task is inactive. + */ +int stack_trace_save_tsk_reliable(struct task_struct *tsk, unsigned long *store, + unsigned int size) +{ + struct stack_trace trace = { + .entries = store, + .max_entries = size, + }; + int ret = save_stack_trace_tsk_reliable(tsk, &trace); + + return ret ? ret : trace.nr_entries; +} +#endif + +#ifdef CONFIG_USER_STACKTRACE_SUPPORT +/** + * stack_trace_save_user - Save a user space stack trace into a storage array + * @store: Pointer to storage array + * @size: Size of the storage array + * + * Return: Number of trace entries stored + */ +unsigned int stack_trace_save_user(unsigned long *store, unsigned int size) +{ + struct stack_trace trace = { + .entries = store, + .max_entries = size, + }; + + save_stack_trace_user(&trace); + return trace.nr_entries; +} +#endif /* CONFIG_USER_STACKTRACE_SUPPORT */ -- cgit From c0cfc337264c5e02e0bc79de6b62857999588879 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 25 Apr 2019 11:44:56 +0200 Subject: lib/stackdepot: Provide functions which operate on plain storage arrays The struct stack_trace indirection in the stack depot functions is a truly pointless excercise which requires horrible code at the callsites. Provide interfaces based on plain storage arrays. Signed-off-by: Thomas Gleixner Reviewed-by: Josh Poimboeuf Acked-by: Alexander Potapenko Cc: Andy Lutomirski Cc: Steven Rostedt Cc: Alexey Dobriyan Cc: Andrew Morton Cc: Christoph Lameter Cc: Pekka Enberg Cc: linux-mm@kvack.org Cc: David Rientjes Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Andrey Ryabinin Cc: kasan-dev@googlegroups.com Cc: Mike Rapoport Cc: Akinobu Mita Cc: Christoph Hellwig Cc: iommu@lists.linux-foundation.org Cc: Robin Murphy Cc: Marek Szyprowski Cc: Johannes Thumshirn Cc: David Sterba Cc: Chris Mason Cc: Josef Bacik Cc: linux-btrfs@vger.kernel.org Cc: dm-devel@redhat.com Cc: Mike Snitzer Cc: Alasdair Kergon Cc: Daniel Vetter Cc: intel-gfx@lists.freedesktop.org Cc: Joonas Lahtinen Cc: Maarten Lankhorst Cc: dri-devel@lists.freedesktop.org Cc: David Airlie Cc: Jani Nikula Cc: Rodrigo Vivi Cc: Tom Zanussi Cc: Miroslav Benes Cc: linux-arch@vger.kernel.org Link: https://lkml.kernel.org/r/20190425094801.414574828@linutronix.de --- include/linux/stackdepot.h | 4 +++ lib/stackdepot.c | 70 +++++++++++++++++++++++++++++++++------------- 2 files changed, 55 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index 7978b3e2c1e1..4297c6d2991d 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -26,7 +26,11 @@ typedef u32 depot_stack_handle_t; struct stack_trace; depot_stack_handle_t depot_save_stack(struct stack_trace *trace, gfp_t flags); +depot_stack_handle_t stack_depot_save(unsigned long *entries, + unsigned int nr_entries, gfp_t gfp_flags); void depot_fetch_stack(depot_stack_handle_t handle, struct stack_trace *trace); +unsigned int stack_depot_fetch(depot_stack_handle_t handle, + unsigned long **entries); #endif diff --git a/lib/stackdepot.c b/lib/stackdepot.c index e513459a5601..e84f8e58495c 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -194,40 +194,60 @@ static inline struct stack_record *find_stack(struct stack_record *bucket, return NULL; } -void depot_fetch_stack(depot_stack_handle_t handle, struct stack_trace *trace) +/** + * stack_depot_fetch - Fetch stack entries from a depot + * + * @handle: Stack depot handle which was returned from + * stack_depot_save(). + * @entries: Pointer to store the entries address + * + * Return: The number of trace entries for this depot. + */ +unsigned int stack_depot_fetch(depot_stack_handle_t handle, + unsigned long **entries) { union handle_parts parts = { .handle = handle }; void *slab = stack_slabs[parts.slabindex]; size_t offset = parts.offset << STACK_ALLOC_ALIGN; struct stack_record *stack = slab + offset; - trace->nr_entries = trace->max_entries = stack->size; - trace->entries = stack->entries; - trace->skip = 0; + *entries = stack->entries; + return stack->size; +} +EXPORT_SYMBOL_GPL(stack_depot_fetch); + +void depot_fetch_stack(depot_stack_handle_t handle, struct stack_trace *trace) +{ + unsigned int nent = stack_depot_fetch(handle, &trace->entries); + + trace->max_entries = trace->nr_entries = nent; } EXPORT_SYMBOL_GPL(depot_fetch_stack); /** - * depot_save_stack - save stack in a stack depot. - * @trace - the stacktrace to save. - * @alloc_flags - flags for allocating additional memory if required. + * stack_depot_save - Save a stack trace from an array + * + * @entries: Pointer to storage array + * @nr_entries: Size of the storage array + * @alloc_flags: Allocation gfp flags * - * Returns the handle of the stack struct stored in depot. + * Return: The handle of the stack struct stored in depot */ -depot_stack_handle_t depot_save_stack(struct stack_trace *trace, - gfp_t alloc_flags) +depot_stack_handle_t stack_depot_save(unsigned long *entries, + unsigned int nr_entries, + gfp_t alloc_flags) { - u32 hash; - depot_stack_handle_t retval = 0; struct stack_record *found = NULL, **bucket; - unsigned long flags; + depot_stack_handle_t retval = 0; struct page *page = NULL; void *prealloc = NULL; + unsigned long flags; + u32 hash; - if (unlikely(trace->nr_entries == 0)) + if (unlikely(nr_entries == 0)) goto fast_exit; - hash = hash_stack(trace->entries, trace->nr_entries); + hash = hash_stack(entries, nr_entries); bucket = &stack_table[hash & STACK_HASH_MASK]; /* @@ -235,8 +255,8 @@ depot_stack_handle_t depot_save_stack(struct stack_trace *trace, * The smp_load_acquire() here pairs with smp_store_release() to * |bucket| below. */ - found = find_stack(smp_load_acquire(bucket), trace->entries, - trace->nr_entries, hash); + found = find_stack(smp_load_acquire(bucket), entries, + nr_entries, hash); if (found) goto exit; @@ -264,10 +284,10 @@ depot_stack_handle_t depot_save_stack(struct stack_trace *trace, spin_lock_irqsave(&depot_lock, flags); - found = find_stack(*bucket, trace->entries, trace->nr_entries, hash); + found = find_stack(*bucket, entries, nr_entries, hash); if (!found) { struct stack_record *new = - depot_alloc_stack(trace->entries, trace->nr_entries, + depot_alloc_stack(entries, nr_entries, hash, &prealloc, alloc_flags); if (new) { new->next = *bucket; @@ -297,4 +317,16 @@ exit: fast_exit: return retval; } +EXPORT_SYMBOL_GPL(stack_depot_save); + +/** + * depot_save_stack - save stack in a stack depot. + * @trace - the stacktrace to save. + * @alloc_flags - flags for allocating additional memory if required. + */ +depot_stack_handle_t depot_save_stack(struct stack_trace *trace, + gfp_t alloc_flags) +{ + return stack_depot_save(trace->entries, trace->nr_entries, alloc_flags); +} EXPORT_SYMBOL_GPL(depot_save_stack); -- cgit From c120bce78065cbea460a58b1572c215db9c148ba Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 25 Apr 2019 11:45:12 +0200 Subject: lockdep: Simplify stack trace handling Replace the indirection through struct stack_trace by using the storage array based interfaces and storing the information is a small lockdep specific data structure. Signed-off-by: Thomas Gleixner Reviewed-by: Josh Poimboeuf Acked-by: Peter Zijlstra (Intel) Cc: Andy Lutomirski Cc: Steven Rostedt Cc: Alexander Potapenko Cc: Alexey Dobriyan Cc: Andrew Morton Cc: Christoph Lameter Cc: Pekka Enberg Cc: linux-mm@kvack.org Cc: David Rientjes Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Andrey Ryabinin Cc: kasan-dev@googlegroups.com Cc: Mike Rapoport Cc: Akinobu Mita Cc: Christoph Hellwig Cc: iommu@lists.linux-foundation.org Cc: Robin Murphy Cc: Marek Szyprowski Cc: Johannes Thumshirn Cc: David Sterba Cc: Chris Mason Cc: Josef Bacik Cc: linux-btrfs@vger.kernel.org Cc: dm-devel@redhat.com Cc: Mike Snitzer Cc: Alasdair Kergon Cc: Daniel Vetter Cc: intel-gfx@lists.freedesktop.org Cc: Joonas Lahtinen Cc: Maarten Lankhorst Cc: dri-devel@lists.freedesktop.org Cc: David Airlie Cc: Jani Nikula Cc: Rodrigo Vivi Cc: Tom Zanussi Cc: Miroslav Benes Cc: linux-arch@vger.kernel.org Link: https://lkml.kernel.org/r/20190425094802.891724020@linutronix.de --- include/linux/lockdep.h | 9 ++++++-- kernel/locking/lockdep.c | 55 ++++++++++++++++++++++++------------------------ 2 files changed, 35 insertions(+), 29 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 79c3873d58ac..6f165d625320 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -66,6 +66,11 @@ struct lock_class_key { extern struct lock_class_key __lockdep_no_validate__; +struct lock_trace { + unsigned int nr_entries; + unsigned int offset; +}; + #define LOCKSTAT_POINTS 4 /* @@ -100,7 +105,7 @@ struct lock_class { * IRQ/softirq usage tracking bits: */ unsigned long usage_mask; - struct stack_trace usage_traces[XXX_LOCK_USAGE_STATES]; + struct lock_trace usage_traces[XXX_LOCK_USAGE_STATES]; /* * Generation counter, when doing certain classes of graph walking, @@ -188,7 +193,7 @@ struct lock_list { struct list_head entry; struct lock_class *class; struct lock_class *links_to; - struct stack_trace trace; + struct lock_trace trace; int distance; /* diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 3603893d5bbd..45bcaf2e4cb6 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -434,18 +434,14 @@ static void print_lockdep_off(const char *bug_msg) #endif } -static int save_trace(struct stack_trace *trace) +static int save_trace(struct lock_trace *trace) { - trace->nr_entries = 0; - trace->max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries; - trace->entries = stack_trace + nr_stack_trace_entries; - - trace->skip = 3; - - save_stack_trace(trace); - - trace->max_entries = trace->nr_entries; + unsigned long *entries = stack_trace + nr_stack_trace_entries; + unsigned int max_entries; + trace->offset = nr_stack_trace_entries; + max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries; + trace->nr_entries = stack_trace_save(entries, max_entries, 3); nr_stack_trace_entries += trace->nr_entries; if (nr_stack_trace_entries >= MAX_STACK_TRACE_ENTRIES-1) { @@ -1196,7 +1192,7 @@ static struct lock_list *alloc_list_entry(void) static int add_lock_to_list(struct lock_class *this, struct lock_class *links_to, struct list_head *head, unsigned long ip, int distance, - struct stack_trace *trace) + struct lock_trace *trace) { struct lock_list *entry; /* @@ -1415,6 +1411,13 @@ static inline int __bfs_backwards(struct lock_list *src_entry, * checking. */ +static void print_lock_trace(struct lock_trace *trace, unsigned int spaces) +{ + unsigned long *entries = stack_trace + trace->offset; + + stack_trace_print(entries, trace->nr_entries, spaces); +} + /* * Print a dependency chain entry (this is only done when a deadlock * has been detected): @@ -1427,8 +1430,7 @@ print_circular_bug_entry(struct lock_list *target, int depth) printk("\n-> #%u", depth); print_lock_name(target->class); printk(KERN_CONT ":\n"); - print_stack_trace(&target->trace, 6); - + print_lock_trace(&target->trace, 6); return 0; } @@ -1740,7 +1742,7 @@ static void print_lock_class_header(struct lock_class *class, int depth) len += printk("%*s %s", depth, "", usage_str[bit]); len += printk(KERN_CONT " at:\n"); - print_stack_trace(class->usage_traces + bit, len); + print_lock_trace(class->usage_traces + bit, len); } } printk("%*s }\n", depth, ""); @@ -1765,7 +1767,7 @@ print_shortest_lock_dependencies(struct lock_list *leaf, do { print_lock_class_header(entry->class, depth); printk("%*s ... acquired at:\n", depth, ""); - print_stack_trace(&entry->trace, 2); + print_lock_trace(&entry->trace, 2); printk("\n"); if (depth == 0 && (entry != root)) { @@ -1878,14 +1880,14 @@ print_bad_irq_dependency(struct task_struct *curr, print_lock_name(backwards_entry->class); pr_warn("\n... which became %s-irq-safe at:\n", irqclass); - print_stack_trace(backwards_entry->class->usage_traces + bit1, 1); + print_lock_trace(backwards_entry->class->usage_traces + bit1, 1); pr_warn("\nto a %s-irq-unsafe lock:\n", irqclass); print_lock_name(forwards_entry->class); pr_warn("\n... which became %s-irq-unsafe at:\n", irqclass); pr_warn("..."); - print_stack_trace(forwards_entry->class->usage_traces + bit2, 1); + print_lock_trace(forwards_entry->class->usage_traces + bit2, 1); pr_warn("\nother info that might help us debug this:\n\n"); print_irq_lock_scenario(backwards_entry, forwards_entry, @@ -2158,7 +2160,7 @@ check_deadlock(struct task_struct *curr, struct held_lock *next, */ static int check_prev_add(struct task_struct *curr, struct held_lock *prev, - struct held_lock *next, int distance, struct stack_trace *trace) + struct held_lock *next, int distance, struct lock_trace *trace) { struct lock_list *uninitialized_var(target_entry); struct lock_list *entry; @@ -2196,7 +2198,7 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, this.parent = NULL; ret = check_noncircular(&this, hlock_class(prev), &target_entry); if (unlikely(!ret)) { - if (!trace->entries) { + if (!trace->nr_entries) { /* * If save_trace fails here, the printing might * trigger a WARN but because of the !nr_entries it @@ -2252,7 +2254,7 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, return print_bfs_bug(ret); - if (!trace->entries && !save_trace(trace)) + if (!trace->nr_entries && !save_trace(trace)) return 0; /* @@ -2284,14 +2286,9 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, static int check_prevs_add(struct task_struct *curr, struct held_lock *next) { + struct lock_trace trace = { .nr_entries = 0 }; int depth = curr->lockdep_depth; struct held_lock *hlock; - struct stack_trace trace = { - .nr_entries = 0, - .max_entries = 0, - .entries = NULL, - .skip = 0, - }; /* * Debugging checks. @@ -2719,6 +2716,10 @@ static inline int validate_chain(struct task_struct *curr, { return 1; } + +static void print_lock_trace(struct lock_trace *trace, unsigned int spaces) +{ +} #endif /* @@ -2815,7 +2816,7 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this, print_lock(this); pr_warn("{%s} state was registered at:\n", usage_str[prev_bit]); - print_stack_trace(hlock_class(this)->usage_traces + prev_bit, 1); + print_lock_trace(hlock_class(this)->usage_traces + prev_bit, 1); print_irqtrace_events(curr); pr_warn("\nother info that might help us debug this:\n"); -- cgit From 988ec8841ca1e22b2978fce0134d8267e838770e Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 25 Apr 2019 11:45:19 +0200 Subject: stacktrace: Remove obsolete functions No more users of the struct stack_trace based interfaces. Remove them. Remove the macro stubs for !CONFIG_STACKTRACE as well as they are pointless because the storage on the call sites is conditional on CONFIG_STACKTRACE already. No point to be 'smart'. Signed-off-by: Thomas Gleixner Reviewed-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: Steven Rostedt Cc: Alexander Potapenko Cc: Alexey Dobriyan Cc: Andrew Morton Cc: Christoph Lameter Cc: Pekka Enberg Cc: linux-mm@kvack.org Cc: David Rientjes Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Andrey Ryabinin Cc: kasan-dev@googlegroups.com Cc: Mike Rapoport Cc: Akinobu Mita Cc: Christoph Hellwig Cc: iommu@lists.linux-foundation.org Cc: Robin Murphy Cc: Marek Szyprowski Cc: Johannes Thumshirn Cc: David Sterba Cc: Chris Mason Cc: Josef Bacik Cc: linux-btrfs@vger.kernel.org Cc: dm-devel@redhat.com Cc: Mike Snitzer Cc: Alasdair Kergon Cc: Daniel Vetter Cc: intel-gfx@lists.freedesktop.org Cc: Joonas Lahtinen Cc: Maarten Lankhorst Cc: dri-devel@lists.freedesktop.org Cc: David Airlie Cc: Jani Nikula Cc: Rodrigo Vivi Cc: Tom Zanussi Cc: Miroslav Benes Cc: linux-arch@vger.kernel.org Link: https://lkml.kernel.org/r/20190425094803.524796783@linutronix.de --- include/linux/stacktrace.h | 17 ----------------- kernel/stacktrace.c | 14 -------------- 2 files changed, 31 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h index a24340b3e9e1..40decfbb9a24 100644 --- a/include/linux/stacktrace.h +++ b/include/linux/stacktrace.h @@ -36,24 +36,7 @@ extern void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace); extern int save_stack_trace_tsk_reliable(struct task_struct *tsk, struct stack_trace *trace); - -extern void print_stack_trace(struct stack_trace *trace, int spaces); -extern int snprint_stack_trace(char *buf, size_t size, - struct stack_trace *trace, int spaces); - -#ifdef CONFIG_USER_STACKTRACE_SUPPORT extern void save_stack_trace_user(struct stack_trace *trace); -#else -# define save_stack_trace_user(trace) do { } while (0) -#endif - -#else /* !CONFIG_STACKTRACE */ -# define save_stack_trace(trace) do { } while (0) -# define save_stack_trace_tsk(tsk, trace) do { } while (0) -# define save_stack_trace_user(trace) do { } while (0) -# define print_stack_trace(trace, spaces) do { } while (0) -# define snprint_stack_trace(buf, size, trace, spaces) do { } while (0) -# define save_stack_trace_tsk_reliable(tsk, trace) ({ -ENOSYS; }) #endif /* CONFIG_STACKTRACE */ #if defined(CONFIG_STACKTRACE) && defined(CONFIG_HAVE_RELIABLE_STACKTRACE) diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c index b38333b3bc18..dd55312f3fe9 100644 --- a/kernel/stacktrace.c +++ b/kernel/stacktrace.c @@ -30,12 +30,6 @@ void stack_trace_print(unsigned long *entries, unsigned int nr_entries, } EXPORT_SYMBOL_GPL(stack_trace_print); -void print_stack_trace(struct stack_trace *trace, int spaces) -{ - stack_trace_print(trace->entries, trace->nr_entries, spaces); -} -EXPORT_SYMBOL_GPL(print_stack_trace); - /** * stack_trace_snprint - Print the entries in the stack trace into a buffer * @buf: Pointer to the print buffer @@ -72,14 +66,6 @@ int stack_trace_snprint(char *buf, size_t size, unsigned long *entries, } EXPORT_SYMBOL_GPL(stack_trace_snprint); -int snprint_stack_trace(char *buf, size_t size, - struct stack_trace *trace, int spaces) -{ - return stack_trace_snprint(buf, size, trace->entries, - trace->nr_entries, spaces); -} -EXPORT_SYMBOL_GPL(snprint_stack_trace); - /* * Architectures that do not implement save_stack_trace_*() * get these weak aliases and once-per-bootup warnings -- cgit From 56d8f079c51afc8b564b9fb0252d48e7b437c1e5 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 25 Apr 2019 11:45:20 +0200 Subject: lib/stackdepot: Remove obsolete functions No more users of the struct stack_trace based interfaces. Signed-off-by: Thomas Gleixner Reviewed-by: Josh Poimboeuf Acked-by: Alexander Potapenko Cc: Andy Lutomirski Cc: Steven Rostedt Cc: Alexey Dobriyan Cc: Andrew Morton Cc: Christoph Lameter Cc: Pekka Enberg Cc: linux-mm@kvack.org Cc: David Rientjes Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Andrey Ryabinin Cc: kasan-dev@googlegroups.com Cc: Mike Rapoport Cc: Akinobu Mita Cc: Christoph Hellwig Cc: iommu@lists.linux-foundation.org Cc: Robin Murphy Cc: Marek Szyprowski Cc: Johannes Thumshirn Cc: David Sterba Cc: Chris Mason Cc: Josef Bacik Cc: linux-btrfs@vger.kernel.org Cc: dm-devel@redhat.com Cc: Mike Snitzer Cc: Alasdair Kergon Cc: Daniel Vetter Cc: intel-gfx@lists.freedesktop.org Cc: Joonas Lahtinen Cc: Maarten Lankhorst Cc: dri-devel@lists.freedesktop.org Cc: David Airlie Cc: Jani Nikula Cc: Rodrigo Vivi Cc: Tom Zanussi Cc: Miroslav Benes Cc: linux-arch@vger.kernel.org Link: https://lkml.kernel.org/r/20190425094803.617937448@linutronix.de --- include/linux/stackdepot.h | 4 ---- lib/stackdepot.c | 20 -------------------- 2 files changed, 24 deletions(-) (limited to 'include/linux') diff --git a/include/linux/stackdepot.h b/include/linux/stackdepot.h index 4297c6d2991d..0805dee1b6b8 100644 --- a/include/linux/stackdepot.h +++ b/include/linux/stackdepot.h @@ -23,13 +23,9 @@ typedef u32 depot_stack_handle_t; -struct stack_trace; - -depot_stack_handle_t depot_save_stack(struct stack_trace *trace, gfp_t flags); depot_stack_handle_t stack_depot_save(unsigned long *entries, unsigned int nr_entries, gfp_t gfp_flags); -void depot_fetch_stack(depot_stack_handle_t handle, struct stack_trace *trace); unsigned int stack_depot_fetch(depot_stack_handle_t handle, unsigned long **entries); diff --git a/lib/stackdepot.c b/lib/stackdepot.c index e84f8e58495c..605c61f65d94 100644 --- a/lib/stackdepot.c +++ b/lib/stackdepot.c @@ -216,14 +216,6 @@ unsigned int stack_depot_fetch(depot_stack_handle_t handle, } EXPORT_SYMBOL_GPL(stack_depot_fetch); -void depot_fetch_stack(depot_stack_handle_t handle, struct stack_trace *trace) -{ - unsigned int nent = stack_depot_fetch(handle, &trace->entries); - - trace->max_entries = trace->nr_entries = nent; -} -EXPORT_SYMBOL_GPL(depot_fetch_stack); - /** * stack_depot_save - Save a stack trace from an array * @@ -318,15 +310,3 @@ fast_exit: return retval; } EXPORT_SYMBOL_GPL(stack_depot_save); - -/** - * depot_save_stack - save stack in a stack depot. - * @trace - the stacktrace to save. - * @alloc_flags - flags for allocating additional memory if required. - */ -depot_stack_handle_t depot_save_stack(struct stack_trace *trace, - gfp_t alloc_flags) -{ - return stack_depot_save(trace->entries, trace->nr_entries, alloc_flags); -} -EXPORT_SYMBOL_GPL(depot_save_stack); -- cgit From 214d8ca6ee854f696f75e75511fe66b409e656db Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Thu, 25 Apr 2019 11:45:21 +0200 Subject: stacktrace: Provide common infrastructure All architectures which support stacktrace carry duplicated code and do the stack storage and filtering at the architecture side. Provide a consolidated interface with a callback function for consuming the stack entries provided by the architecture specific stack walker. This removes lots of duplicated code and allows to implement better filtering than 'skip number of entries' in the future without touching any architecture specific code. Signed-off-by: Thomas Gleixner Reviewed-by: Josh Poimboeuf Cc: Andy Lutomirski Cc: linux-arch@vger.kernel.org Cc: Steven Rostedt Cc: Alexander Potapenko Cc: Alexey Dobriyan Cc: Andrew Morton Cc: Christoph Lameter Cc: Pekka Enberg Cc: linux-mm@kvack.org Cc: David Rientjes Cc: Catalin Marinas Cc: Dmitry Vyukov Cc: Andrey Ryabinin Cc: kasan-dev@googlegroups.com Cc: Mike Rapoport Cc: Akinobu Mita Cc: Christoph Hellwig Cc: iommu@lists.linux-foundation.org Cc: Robin Murphy Cc: Marek Szyprowski Cc: Johannes Thumshirn Cc: David Sterba Cc: Chris Mason Cc: Josef Bacik Cc: linux-btrfs@vger.kernel.org Cc: dm-devel@redhat.com Cc: Mike Snitzer Cc: Alasdair Kergon Cc: Daniel Vetter Cc: intel-gfx@lists.freedesktop.org Cc: Joonas Lahtinen Cc: Maarten Lankhorst Cc: dri-devel@lists.freedesktop.org Cc: David Airlie Cc: Jani Nikula Cc: Rodrigo Vivi Cc: Tom Zanussi Cc: Miroslav Benes Link: https://lkml.kernel.org/r/20190425094803.713568606@linutronix.de --- include/linux/stacktrace.h | 39 ++++++++++ kernel/stacktrace.c | 173 +++++++++++++++++++++++++++++++++++++++++++++ lib/Kconfig | 4 ++ 3 files changed, 216 insertions(+) (limited to 'include/linux') diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h index 40decfbb9a24..f0cfd12cb45e 100644 --- a/include/linux/stacktrace.h +++ b/include/linux/stacktrace.h @@ -23,6 +23,44 @@ unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store, unsigned int stack_trace_save_user(unsigned long *store, unsigned int size); /* Internal interfaces. Do not use in generic code */ +#ifdef CONFIG_ARCH_STACKWALK + +/** + * stack_trace_consume_fn - Callback for arch_stack_walk() + * @cookie: Caller supplied pointer handed back by arch_stack_walk() + * @addr: The stack entry address to consume + * @reliable: True when the stack entry is reliable. Required by + * some printk based consumers. + * + * Return: True, if the entry was consumed or skipped + * False, if there is no space left to store + */ +typedef bool (*stack_trace_consume_fn)(void *cookie, unsigned long addr, + bool reliable); +/** + * arch_stack_walk - Architecture specific function to walk the stack + * @consume_entry: Callback which is invoked by the architecture code for + * each entry. + * @cookie: Caller supplied pointer which is handed back to + * @consume_entry + * @task: Pointer to a task struct, can be NULL + * @regs: Pointer to registers, can be NULL + * + * ============ ======= ============================================ + * task regs + * ============ ======= ============================================ + * task NULL Stack trace from task (can be current) + * current regs Stack trace starting on regs->stackpointer + * ============ ======= ============================================ + */ +void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, + struct task_struct *task, struct pt_regs *regs); +int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry, void *cookie, + struct task_struct *task); +void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie, + const struct pt_regs *regs); + +#else /* CONFIG_ARCH_STACKWALK */ struct stack_trace { unsigned int nr_entries, max_entries; unsigned long *entries; @@ -37,6 +75,7 @@ extern void save_stack_trace_tsk(struct task_struct *tsk, extern int save_stack_trace_tsk_reliable(struct task_struct *tsk, struct stack_trace *trace); extern void save_stack_trace_user(struct stack_trace *trace); +#endif /* !CONFIG_ARCH_STACKWALK */ #endif /* CONFIG_STACKTRACE */ #if defined(CONFIG_STACKTRACE) && defined(CONFIG_HAVE_RELIABLE_STACKTRACE) diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c index dd55312f3fe9..27bafc1e271e 100644 --- a/kernel/stacktrace.c +++ b/kernel/stacktrace.c @@ -5,6 +5,8 @@ * * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar */ +#include +#include #include #include #include @@ -66,6 +68,175 @@ int stack_trace_snprint(char *buf, size_t size, unsigned long *entries, } EXPORT_SYMBOL_GPL(stack_trace_snprint); +#ifdef CONFIG_ARCH_STACKWALK + +struct stacktrace_cookie { + unsigned long *store; + unsigned int size; + unsigned int skip; + unsigned int len; +}; + +static bool stack_trace_consume_entry(void *cookie, unsigned long addr, + bool reliable) +{ + struct stacktrace_cookie *c = cookie; + + if (c->len >= c->size) + return false; + + if (c->skip > 0) { + c->skip--; + return true; + } + c->store[c->len++] = addr; + return c->len < c->size; +} + +static bool stack_trace_consume_entry_nosched(void *cookie, unsigned long addr, + bool reliable) +{ + if (in_sched_functions(addr)) + return true; + return stack_trace_consume_entry(cookie, addr, reliable); +} + +/** + * stack_trace_save - Save a stack trace into a storage array + * @store: Pointer to storage array + * @size: Size of the storage array + * @skipnr: Number of entries to skip at the start of the stack trace + * + * Return: Number of trace entries stored. + */ +unsigned int stack_trace_save(unsigned long *store, unsigned int size, + unsigned int skipnr) +{ + stack_trace_consume_fn consume_entry = stack_trace_consume_entry; + struct stacktrace_cookie c = { + .store = store, + .size = size, + .skip = skipnr + 1, + }; + + arch_stack_walk(consume_entry, &c, current, NULL); + return c.len; +} +EXPORT_SYMBOL_GPL(stack_trace_save); + +/** + * stack_trace_save_tsk - Save a task stack trace into a storage array + * @task: The task to examine + * @store: Pointer to storage array + * @size: Size of the storage array + * @skipnr: Number of entries to skip at the start of the stack trace + * + * Return: Number of trace entries stored. + */ +unsigned int stack_trace_save_tsk(struct task_struct *tsk, unsigned long *store, + unsigned int size, unsigned int skipnr) +{ + stack_trace_consume_fn consume_entry = stack_trace_consume_entry_nosched; + struct stacktrace_cookie c = { + .store = store, + .size = size, + .skip = skipnr + 1, + }; + + if (!try_get_task_stack(tsk)) + return 0; + + arch_stack_walk(consume_entry, &c, tsk, NULL); + put_task_stack(tsk); + return c.len; +} + +/** + * stack_trace_save_regs - Save a stack trace based on pt_regs into a storage array + * @regs: Pointer to pt_regs to examine + * @store: Pointer to storage array + * @size: Size of the storage array + * @skipnr: Number of entries to skip at the start of the stack trace + * + * Return: Number of trace entries stored. + */ +unsigned int stack_trace_save_regs(struct pt_regs *regs, unsigned long *store, + unsigned int size, unsigned int skipnr) +{ + stack_trace_consume_fn consume_entry = stack_trace_consume_entry; + struct stacktrace_cookie c = { + .store = store, + .size = size, + .skip = skipnr, + }; + + arch_stack_walk(consume_entry, &c, current, regs); + return c.len; +} + +#ifdef CONFIG_HAVE_RELIABLE_STACKTRACE +/** + * stack_trace_save_tsk_reliable - Save task stack with verification + * @tsk: Pointer to the task to examine + * @store: Pointer to storage array + * @size: Size of the storage array + * + * Return: An error if it detects any unreliable features of the + * stack. Otherwise it guarantees that the stack trace is + * reliable and returns the number of entries stored. + * + * If the task is not 'current', the caller *must* ensure the task is inactive. + */ +int stack_trace_save_tsk_reliable(struct task_struct *tsk, unsigned long *store, + unsigned int size) +{ + stack_trace_consume_fn consume_entry = stack_trace_consume_entry; + struct stacktrace_cookie c = { + .store = store, + .size = size, + }; + int ret; + + /* + * If the task doesn't have a stack (e.g., a zombie), the stack is + * "reliably" empty. + */ + if (!try_get_task_stack(tsk)) + return 0; + + ret = arch_stack_walk_reliable(consume_entry, &c, tsk); + put_task_stack(tsk); + return ret; +} +#endif + +#ifdef CONFIG_USER_STACKTRACE_SUPPORT +/** + * stack_trace_save_user - Save a user space stack trace into a storage array + * @store: Pointer to storage array + * @size: Size of the storage array + * + * Return: Number of trace entries stored. + */ +unsigned int stack_trace_save_user(unsigned long *store, unsigned int size) +{ + stack_trace_consume_fn consume_entry = stack_trace_consume_entry; + struct stacktrace_cookie c = { + .store = store, + .size = size, + }; + + /* Trace user stack if not a kernel thread */ + if (!current->mm) + return 0; + + arch_stack_walk_user(consume_entry, &c, task_pt_regs(current)); + return c.len; +} +#endif + +#else /* CONFIG_ARCH_STACKWALK */ + /* * Architectures that do not implement save_stack_trace_*() * get these weak aliases and once-per-bootup warnings @@ -203,3 +374,5 @@ unsigned int stack_trace_save_user(unsigned long *store, unsigned int size) return trace.nr_entries; } #endif /* CONFIG_USER_STACKTRACE_SUPPORT */ + +#endif /* !CONFIG_ARCH_STACKWALK */ diff --git a/lib/Kconfig b/lib/Kconfig index a9e56539bd11..e86975bfca6a 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -597,6 +597,10 @@ config ARCH_HAS_UACCESS_FLUSHCACHE config ARCH_HAS_UACCESS_MCSAFE bool +# Temporary. Goes away when all archs are cleaned up +config ARCH_STACKWALK + bool + config STACKDEPOT bool select STACKTRACE -- cgit From aad42dd44db086c79ca3f470ad563d2ac4ac218d Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Fri, 26 Apr 2019 16:22:44 -0700 Subject: uprobes: Initialize uprobes earlier In order to have a separate address space for text poking, we need to duplicate init_mm early during start_kernel(). This, however, introduces a problem since uprobes functions are called from dup_mmap(), but uprobes is still not initialized in this early stage. Since uprobes initialization is necassary for fork, and since all the dependant initialization has been done when fork is initialized (percpu and vmalloc), move uprobes initialization to fork_init(). It does not seem uprobes introduces any security problem for the poking_mm. Crash and burn if uprobes initialization fails, similarly to other early initializations. Change the init_probes() name to probes_init() to match other early initialization functions name convention. Reported-by: kernel test robot Signed-off-by: Nadav Amit Signed-off-by: Peter Zijlstra (Intel) Cc: Andy Lutomirski Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: Dave Hansen Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Rick Edgecombe Cc: Rik van Riel Cc: Thomas Gleixner Cc: akpm@linux-foundation.org Cc: ard.biesheuvel@linaro.org Cc: deneen.t.dock@intel.com Cc: kernel-hardening@lists.openwall.com Cc: kristen@linux.intel.com Cc: linux_dti@icloud.com Cc: will.deacon@arm.com Link: https://lkml.kernel.org/r/20190426232303.28381-6-nadav.amit@gmail.com Signed-off-by: Ingo Molnar --- include/linux/uprobes.h | 5 +++++ kernel/events/uprobes.c | 8 +++----- kernel/fork.c | 1 + 3 files changed, 9 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h index 103a48a48872..12bf0b68ed92 100644 --- a/include/linux/uprobes.h +++ b/include/linux/uprobes.h @@ -115,6 +115,7 @@ struct uprobes_state { struct xol_area *xol_area; }; +extern void __init uprobes_init(void); extern int set_swbp(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr); extern int set_orig_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long vaddr); extern bool is_swbp_insn(uprobe_opcode_t *insn); @@ -154,6 +155,10 @@ extern void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr, struct uprobes_state { }; +static inline void uprobes_init(void) +{ +} + #define uprobe_get_trap_addr(regs) instruction_pointer(regs) static inline int diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index c5cde87329c7..e6a0d6be87e3 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -2294,16 +2294,14 @@ static struct notifier_block uprobe_exception_nb = { .priority = INT_MAX-1, /* notified after kprobes, kgdb */ }; -static int __init init_uprobes(void) +void __init uprobes_init(void) { int i; for (i = 0; i < UPROBES_HASH_SZ; i++) mutex_init(&uprobes_mmap_mutex[i]); - if (percpu_init_rwsem(&dup_mmap_sem)) - return -ENOMEM; + BUG_ON(percpu_init_rwsem(&dup_mmap_sem)); - return register_die_notifier(&uprobe_exception_nb); + BUG_ON(register_die_notifier(&uprobe_exception_nb)); } -__initcall(init_uprobes); diff --git a/kernel/fork.c b/kernel/fork.c index 9dcd18aa210b..44fba5e5e916 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -815,6 +815,7 @@ void __init fork_init(void) #endif lockdep_init_task(&init_task); + uprobes_init(); } int __weak arch_dup_task_struct(struct task_struct *dst, -- cgit From 13585fa0668c724efab9635aaeef6ec390217415 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Thu, 25 Apr 2019 17:11:25 -0700 Subject: fork: Provide a function for copying init_mm Provide a function for copying init_mm. This function will be later used for setting a temporary mm. Tested-by: Masami Hiramatsu Signed-off-by: Nadav Amit Signed-off-by: Rick Edgecombe Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Masami Hiramatsu Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: H. Peter Anvin Cc: Kees Cook Cc: Linus Torvalds Cc: Rik van Riel Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20190426001143.4983-6-namit@vmware.com Signed-off-by: Ingo Molnar --- include/linux/sched/task.h | 1 + kernel/fork.c | 24 ++++++++++++++++++------ 2 files changed, 19 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h index 2e97a2227045..f1227f2c38a4 100644 --- a/include/linux/sched/task.h +++ b/include/linux/sched/task.h @@ -76,6 +76,7 @@ extern void exit_itimers(struct signal_struct *); extern long _do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *, unsigned long); extern long do_fork(unsigned long, unsigned long, unsigned long, int __user *, int __user *); struct task_struct *fork_idle(int); +struct mm_struct *copy_init_mm(void); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); extern long kernel_wait4(pid_t, int __user *, int, struct rusage *); diff --git a/kernel/fork.c b/kernel/fork.c index 44fba5e5e916..fbe9dfcd8680 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1299,13 +1299,20 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm) complete_vfork_done(tsk); } -/* - * Allocate a new mm structure and copy contents from the - * mm structure of the passed in task structure. +/** + * dup_mm() - duplicates an existing mm structure + * @tsk: the task_struct with which the new mm will be associated. + * @oldmm: the mm to duplicate. + * + * Allocates a new mm structure and duplicates the provided @oldmm structure + * content into it. + * + * Return: the duplicated mm or NULL on failure. */ -static struct mm_struct *dup_mm(struct task_struct *tsk) +static struct mm_struct *dup_mm(struct task_struct *tsk, + struct mm_struct *oldmm) { - struct mm_struct *mm, *oldmm = current->mm; + struct mm_struct *mm; int err; mm = allocate_mm(); @@ -1372,7 +1379,7 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) } retval = -ENOMEM; - mm = dup_mm(tsk); + mm = dup_mm(tsk, current->mm); if (!mm) goto fail_nomem; @@ -2187,6 +2194,11 @@ struct task_struct *fork_idle(int cpu) return task; } +struct mm_struct *copy_init_mm(void) +{ + return dup_mm(NULL, &init_mm); +} + /* * Ok, this is the main fork-routine. * -- cgit From f2c65fb3221adc6b73b0549fc7ba892022db9797 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Thu, 25 Apr 2019 17:11:31 -0700 Subject: x86/modules: Avoid breaking W^X while loading modules When modules and BPF filters are loaded, there is a time window in which some memory is both writable and executable. An attacker that has already found another vulnerability (e.g., a dangling pointer) might be able to exploit this behavior to overwrite kernel code. Prevent having writable executable PTEs in this stage. In addition, avoiding having W+X mappings can also slightly simplify the patching of modules code on initialization (e.g., by alternatives and static-key), as would be done in the next patch. This was actually the main motivation for this patch. To avoid having W+X mappings, set them initially as RW (NX) and after they are set as RO set them as X as well. Setting them as executable is done as a separate step to avoid one core in which the old PTE is cached (hence writable), and another which sees the updated PTE (executable), which would break the W^X protection. Suggested-by: Thomas Gleixner Suggested-by: Andy Lutomirski Signed-off-by: Nadav Amit Signed-off-by: Rick Edgecombe Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: H. Peter Anvin Cc: Jessica Yu Cc: Kees Cook Cc: Linus Torvalds Cc: Masami Hiramatsu Cc: Rik van Riel Link: https://lkml.kernel.org/r/20190426001143.4983-12-namit@vmware.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/alternative.c | 28 +++++++++++++++++++++------- arch/x86/kernel/module.c | 2 +- include/linux/filter.h | 1 + kernel/module.c | 5 +++++ 4 files changed, 28 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 599203876c32..3d2b6b6fb20c 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -668,15 +668,29 @@ void __init alternative_instructions(void) * handlers seeing an inconsistent instruction while you patch. */ void *__init_or_module text_poke_early(void *addr, const void *opcode, - size_t len) + size_t len) { unsigned long flags; - local_irq_save(flags); - memcpy(addr, opcode, len); - local_irq_restore(flags); - sync_core(); - /* Could also do a CLFLUSH here to speed up CPU recovery; but - that causes hangs on some VIA CPUs. */ + + if (boot_cpu_has(X86_FEATURE_NX) && + is_module_text_address((unsigned long)addr)) { + /* + * Modules text is marked initially as non-executable, so the + * code cannot be running and speculative code-fetches are + * prevented. Just change the code. + */ + memcpy(addr, opcode, len); + } else { + local_irq_save(flags); + memcpy(addr, opcode, len); + local_irq_restore(flags); + sync_core(); + + /* + * Could also do a CLFLUSH here to speed up CPU recovery; but + * that causes hangs on some VIA CPUs. + */ + } return addr; } diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index b052e883dd8c..cfa3106faee4 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -87,7 +87,7 @@ void *module_alloc(unsigned long size) p = __vmalloc_node_range(size, MODULE_ALIGN, MODULES_VADDR + get_module_load_offset(), MODULES_END, GFP_KERNEL, - PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE, + PAGE_KERNEL, 0, NUMA_NO_NODE, __builtin_return_address(0)); if (p && (kasan_module_alloc(p, size) < 0)) { vfree(p); diff --git a/include/linux/filter.h b/include/linux/filter.h index 6074aa064b54..14ec3bdad9a9 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -746,6 +746,7 @@ static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { set_memory_ro((unsigned long)hdr, hdr->pages); + set_memory_x((unsigned long)hdr, hdr->pages); } static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr) diff --git a/kernel/module.c b/kernel/module.c index 0b9aa8ab89f0..2b2845ae983e 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1950,8 +1950,13 @@ void module_enable_ro(const struct module *mod, bool after_init) return; frob_text(&mod->core_layout, set_memory_ro); + frob_text(&mod->core_layout, set_memory_x); + frob_rodata(&mod->core_layout, set_memory_ro); + frob_text(&mod->init_layout, set_memory_ro); + frob_text(&mod->init_layout, set_memory_x); + frob_rodata(&mod->init_layout, set_memory_ro); if (after_init) -- cgit From d253ca0c3865a8d9a8c01143cf20425e0be4d0ce Mon Sep 17 00:00:00 2001 From: Rick Edgecombe Date: Thu, 25 Apr 2019 17:11:34 -0700 Subject: x86/mm/cpa: Add set_direct_map_*() functions Add two new functions set_direct_map_default_noflush() and set_direct_map_invalid_noflush() for setting the direct map alias for the page to its default valid permissions and to an invalid state that cannot be cached in a TLB, respectively. These functions do not flush the TLB. Note, __kernel_map_pages() does something similar but flushes the TLB and doesn't reset the permission bits to default on all architectures. Also add an ARCH config ARCH_HAS_SET_DIRECT_MAP for specifying whether these have an actual implementation or a default empty one. Signed-off-by: Rick Edgecombe Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Nadav Amit Cc: Rik van Riel Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20190426001143.4983-15-namit@vmware.com Signed-off-by: Ingo Molnar --- arch/Kconfig | 4 ++++ arch/x86/Kconfig | 1 + arch/x86/include/asm/set_memory.h | 3 +++ arch/x86/mm/pageattr.c | 14 +++++++++++--- include/linux/set_memory.h | 11 +++++++++++ 5 files changed, 30 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/arch/Kconfig b/arch/Kconfig index 33687dddd86a..88e5a92a9e58 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -249,6 +249,10 @@ config ARCH_HAS_FORTIFY_SOURCE config ARCH_HAS_SET_MEMORY bool +# Select if arch has all set_direct_map_invalid/default() functions +config ARCH_HAS_SET_DIRECT_MAP + bool + # Select if arch init_task must go in the __init_task_data section config ARCH_TASK_STRUCT_ON_STACK bool diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index bd6f93ce0633..cee3f22ce8d1 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -65,6 +65,7 @@ config X86 select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64 select ARCH_HAS_UACCESS_MCSAFE if X86_64 && X86_MCE select ARCH_HAS_SET_MEMORY + select ARCH_HAS_SET_DIRECT_MAP select ARCH_HAS_STRICT_KERNEL_RWX select ARCH_HAS_STRICT_MODULE_RWX select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index 07a25753e85c..ae7b909dc242 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -85,6 +85,9 @@ int set_pages_nx(struct page *page, int numpages); int set_pages_ro(struct page *page, int numpages); int set_pages_rw(struct page *page, int numpages); +int set_direct_map_invalid_noflush(struct page *page); +int set_direct_map_default_noflush(struct page *page); + extern int kernel_set_to_readonly; void set_kernel_text_rw(void); void set_kernel_text_ro(void); diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 4c570612e24e..3574550192c6 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -2209,8 +2209,6 @@ int set_pages_rw(struct page *page, int numpages) return set_memory_rw(addr, numpages); } -#ifdef CONFIG_DEBUG_PAGEALLOC - static int __set_pages_p(struct page *page, int numpages) { unsigned long tempaddr = (unsigned long) page_address(page); @@ -2249,6 +2247,17 @@ static int __set_pages_np(struct page *page, int numpages) return __change_page_attr_set_clr(&cpa, 0); } +int set_direct_map_invalid_noflush(struct page *page) +{ + return __set_pages_np(page, 1); +} + +int set_direct_map_default_noflush(struct page *page) +{ + return __set_pages_p(page, 1); +} + +#ifdef CONFIG_DEBUG_PAGEALLOC void __kernel_map_pages(struct page *page, int numpages, int enable) { if (PageHighMem(page)) @@ -2282,7 +2291,6 @@ void __kernel_map_pages(struct page *page, int numpages, int enable) } #ifdef CONFIG_HIBERNATION - bool kernel_page_present(struct page *page) { unsigned int level; diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h index 2a986d282a97..b5071497b8cb 100644 --- a/include/linux/set_memory.h +++ b/include/linux/set_memory.h @@ -17,6 +17,17 @@ static inline int set_memory_x(unsigned long addr, int numpages) { return 0; } static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; } #endif +#ifndef CONFIG_ARCH_HAS_SET_DIRECT_MAP +static inline int set_direct_map_invalid_noflush(struct page *page) +{ + return 0; +} +static inline int set_direct_map_default_noflush(struct page *page) +{ + return 0; +} +#endif + #ifndef set_mce_nospec static inline int set_mce_nospec(unsigned long pfn) { -- cgit From d63326928611600ad65baff54a70f53b02b3cdfe Mon Sep 17 00:00:00 2001 From: Rick Edgecombe Date: Thu, 25 Apr 2019 17:11:35 -0700 Subject: mm/hibernation: Make hibernation handle unmapped pages Make hibernate handle unmapped pages on the direct map when CONFIG_ARCH_HAS_SET_ALIAS=y is set. These functions allow for setting pages to invalid configurations, so now hibernate should check if the pages have valid mappings and handle if they are unmapped when doing a hibernate save operation. Previously this checking was already done when CONFIG_DEBUG_PAGEALLOC=y was configured. It does not appear to have a big hibernating performance impact. The speed of the saving operation before this change was measured as 819.02 MB/s, and after was measured at 813.32 MB/s. Before: [ 4.670938] PM: Wrote 171996 kbytes in 0.21 seconds (819.02 MB/s) After: [ 4.504714] PM: Wrote 178932 kbytes in 0.22 seconds (813.32 MB/s) Signed-off-by: Rick Edgecombe Signed-off-by: Peter Zijlstra (Intel) Acked-by: Pavel Machek Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Nadav Amit Cc: Rafael J. Wysocki Cc: Rik van Riel Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20190426001143.4983-16-namit@vmware.com Signed-off-by: Ingo Molnar --- arch/x86/mm/pageattr.c | 4 ---- include/linux/mm.h | 18 ++++++------------ kernel/power/snapshot.c | 5 +++-- mm/page_alloc.c | 7 +++++-- 4 files changed, 14 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 3574550192c6..daf4d645e537 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -2257,7 +2257,6 @@ int set_direct_map_default_noflush(struct page *page) return __set_pages_p(page, 1); } -#ifdef CONFIG_DEBUG_PAGEALLOC void __kernel_map_pages(struct page *page, int numpages, int enable) { if (PageHighMem(page)) @@ -2302,11 +2301,8 @@ bool kernel_page_present(struct page *page) pte = lookup_address((unsigned long)page_address(page), &level); return (pte_val(*pte) & _PAGE_PRESENT); } - #endif /* CONFIG_HIBERNATION */ -#endif /* CONFIG_DEBUG_PAGEALLOC */ - int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, unsigned numpages, unsigned long page_flags) { diff --git a/include/linux/mm.h b/include/linux/mm.h index 6b10c21630f5..083d7b4863ed 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2610,37 +2610,31 @@ static inline void kernel_poison_pages(struct page *page, int numpages, int enable) { } #endif -#ifdef CONFIG_DEBUG_PAGEALLOC extern bool _debug_pagealloc_enabled; -extern void __kernel_map_pages(struct page *page, int numpages, int enable); static inline bool debug_pagealloc_enabled(void) { - return _debug_pagealloc_enabled; + return IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) && _debug_pagealloc_enabled; } +#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_ARCH_HAS_SET_DIRECT_MAP) +extern void __kernel_map_pages(struct page *page, int numpages, int enable); + static inline void kernel_map_pages(struct page *page, int numpages, int enable) { - if (!debug_pagealloc_enabled()) - return; - __kernel_map_pages(page, numpages, enable); } #ifdef CONFIG_HIBERNATION extern bool kernel_page_present(struct page *page); #endif /* CONFIG_HIBERNATION */ -#else /* CONFIG_DEBUG_PAGEALLOC */ +#else /* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */ static inline void kernel_map_pages(struct page *page, int numpages, int enable) {} #ifdef CONFIG_HIBERNATION static inline bool kernel_page_present(struct page *page) { return true; } #endif /* CONFIG_HIBERNATION */ -static inline bool debug_pagealloc_enabled(void) -{ - return false; -} -#endif /* CONFIG_DEBUG_PAGEALLOC */ +#endif /* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */ #ifdef __HAVE_ARCH_GATE_AREA extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm); diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index f08a1e4ee1d4..bc9558ab1e5b 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1342,8 +1342,9 @@ static inline void do_copy_page(long *dst, long *src) * safe_copy_page - Copy a page in a safe way. * * Check if the page we are going to copy is marked as present in the kernel - * page tables (this always is the case if CONFIG_DEBUG_PAGEALLOC is not set - * and in that case kernel_page_present() always returns 'true'). + * page tables. This always is the case if CONFIG_DEBUG_PAGEALLOC or + * CONFIG_ARCH_HAS_SET_DIRECT_MAP is not set. In that case kernel_page_present() + * always returns 'true'. */ static void safe_copy_page(void *dst, struct page *s_page) { diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c02cff1ed56e..59661106da16 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1144,7 +1144,9 @@ static __always_inline bool free_pages_prepare(struct page *page, } arch_free_page(page, order); kernel_poison_pages(page, 1 << order, 0); - kernel_map_pages(page, 1 << order, 0); + if (debug_pagealloc_enabled()) + kernel_map_pages(page, 1 << order, 0); + kasan_free_nondeferred_pages(page, order); return true; @@ -2014,7 +2016,8 @@ inline void post_alloc_hook(struct page *page, unsigned int order, set_page_refcounted(page); arch_alloc_page(page, order); - kernel_map_pages(page, 1 << order, 1); + if (debug_pagealloc_enabled()) + kernel_map_pages(page, 1 << order, 1); kasan_alloc_pages(page, order); kernel_poison_pages(page, 1 << order, 1); set_page_owner(page, order, gfp_flags); -- cgit From 868b104d7379e28013e9d48bdd2db25e0bdcf751 Mon Sep 17 00:00:00 2001 From: Rick Edgecombe Date: Thu, 25 Apr 2019 17:11:36 -0700 Subject: mm/vmalloc: Add flag for freeing of special permsissions Add a new flag VM_FLUSH_RESET_PERMS, for enabling vfree operations to immediately clear executable TLB entries before freeing pages, and handle resetting permissions on the directmap. This flag is useful for any kind of memory with elevated permissions, or where there can be related permissions changes on the directmap. Today this is RO+X and RO memory. Although this enables directly vfreeing non-writeable memory now, non-writable memory cannot be freed in an interrupt because the allocation itself is used as a node on deferred free list. So when RO memory needs to be freed in an interrupt the code doing the vfree needs to have its own work queue, as was the case before the deferred vfree list was added to vmalloc. For architectures with set_direct_map_ implementations this whole operation can be done with one TLB flush when centralized like this. For others with directmap permissions, currently only arm64, a backup method using set_memory functions is used to reset the directmap. When arm64 adds set_direct_map_ functions, this backup can be removed. When the TLB is flushed to both remove TLB entries for the vmalloc range mapping and the direct map permissions, the lazy purge operation could be done to try to save a TLB flush later. However today vm_unmap_aliases could flush a TLB range that does not include the directmap. So a helper is added with extra parameters that can allow both the vmalloc address and the direct mapping to be flushed during this operation. The behavior of the normal vm_unmap_aliases function is unchanged. Suggested-by: Dave Hansen Suggested-by: Andy Lutomirski Suggested-by: Will Deacon Signed-off-by: Rick Edgecombe Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Cc: Cc: Cc: Cc: Cc: Borislav Petkov Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Nadav Amit Cc: Rik van Riel Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20190426001143.4983-17-namit@vmware.com Signed-off-by: Ingo Molnar --- include/linux/vmalloc.h | 15 +++++++ mm/vmalloc.c | 113 ++++++++++++++++++++++++++++++++++++++++-------- 2 files changed, 109 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 398e9c95cd61..c6eebb839552 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -21,6 +21,11 @@ struct notifier_block; /* in notifier.h */ #define VM_UNINITIALIZED 0x00000020 /* vm_struct is not fully initialized */ #define VM_NO_GUARD 0x00000040 /* don't add guard page */ #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ +/* + * Memory with VM_FLUSH_RESET_PERMS cannot be freed in an interrupt or with + * vfree_atomic(). + */ +#define VM_FLUSH_RESET_PERMS 0x00000100 /* Reset direct map and flush TLB on unmap */ /* bits [20..32] reserved for arch specific ioremap internals */ /* @@ -142,6 +147,13 @@ extern int map_kernel_range_noflush(unsigned long start, unsigned long size, pgprot_t prot, struct page **pages); extern void unmap_kernel_range_noflush(unsigned long addr, unsigned long size); extern void unmap_kernel_range(unsigned long addr, unsigned long size); +static inline void set_vm_flush_reset_perms(void *addr) +{ + struct vm_struct *vm = find_vm_area(addr); + + if (vm) + vm->flags |= VM_FLUSH_RESET_PERMS; +} #else static inline int map_kernel_range_noflush(unsigned long start, unsigned long size, @@ -157,6 +169,9 @@ static inline void unmap_kernel_range(unsigned long addr, unsigned long size) { } +static inline void set_vm_flush_reset_perms(void *addr) +{ +} #endif /* Allocate/destroy a 'vmalloc' VM area. */ diff --git a/mm/vmalloc.c b/mm/vmalloc.c index e86ba6e74b50..e5e9e1fcac01 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -1059,24 +1060,9 @@ static void vb_free(const void *addr, unsigned long size) spin_unlock(&vb->lock); } -/** - * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer - * - * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily - * to amortize TLB flushing overheads. What this means is that any page you - * have now, may, in a former life, have been mapped into kernel virtual - * address by the vmap layer and so there might be some CPUs with TLB entries - * still referencing that page (additional to the regular 1:1 kernel mapping). - * - * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can - * be sure that none of the pages we have control over will have any aliases - * from the vmap layer. - */ -void vm_unmap_aliases(void) +static void _vm_unmap_aliases(unsigned long start, unsigned long end, int flush) { - unsigned long start = ULONG_MAX, end = 0; int cpu; - int flush = 0; if (unlikely(!vmap_initialized)) return; @@ -1113,6 +1099,27 @@ void vm_unmap_aliases(void) flush_tlb_kernel_range(start, end); mutex_unlock(&vmap_purge_lock); } + +/** + * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer + * + * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily + * to amortize TLB flushing overheads. What this means is that any page you + * have now, may, in a former life, have been mapped into kernel virtual + * address by the vmap layer and so there might be some CPUs with TLB entries + * still referencing that page (additional to the regular 1:1 kernel mapping). + * + * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can + * be sure that none of the pages we have control over will have any aliases + * from the vmap layer. + */ +void vm_unmap_aliases(void) +{ + unsigned long start = ULONG_MAX, end = 0; + int flush = 0; + + _vm_unmap_aliases(start, end, flush); +} EXPORT_SYMBOL_GPL(vm_unmap_aliases); /** @@ -1505,6 +1512,72 @@ struct vm_struct *remove_vm_area(const void *addr) return NULL; } +static inline void set_area_direct_map(const struct vm_struct *area, + int (*set_direct_map)(struct page *page)) +{ + int i; + + for (i = 0; i < area->nr_pages; i++) + if (page_address(area->pages[i])) + set_direct_map(area->pages[i]); +} + +/* Handle removing and resetting vm mappings related to the vm_struct. */ +static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages) +{ + unsigned long addr = (unsigned long)area->addr; + unsigned long start = ULONG_MAX, end = 0; + int flush_reset = area->flags & VM_FLUSH_RESET_PERMS; + int i; + + /* + * The below block can be removed when all architectures that have + * direct map permissions also have set_direct_map_() implementations. + * This is concerned with resetting the direct map any an vm alias with + * execute permissions, without leaving a RW+X window. + */ + if (flush_reset && !IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) { + set_memory_nx(addr, area->nr_pages); + set_memory_rw(addr, area->nr_pages); + } + + remove_vm_area(area->addr); + + /* If this is not VM_FLUSH_RESET_PERMS memory, no need for the below. */ + if (!flush_reset) + return; + + /* + * If not deallocating pages, just do the flush of the VM area and + * return. + */ + if (!deallocate_pages) { + vm_unmap_aliases(); + return; + } + + /* + * If execution gets here, flush the vm mapping and reset the direct + * map. Find the start and end range of the direct mappings to make sure + * the vm_unmap_aliases() flush includes the direct map. + */ + for (i = 0; i < area->nr_pages; i++) { + if (page_address(area->pages[i])) { + start = min(addr, start); + end = max(addr, end); + } + } + + /* + * Set direct map to something invalid so that it won't be cached if + * there are any accesses after the TLB flush, then flush the TLB and + * reset the direct map permissions to the default. + */ + set_area_direct_map(area, set_direct_map_invalid_noflush); + _vm_unmap_aliases(start, end, 1); + set_area_direct_map(area, set_direct_map_default_noflush); +} + static void __vunmap(const void *addr, int deallocate_pages) { struct vm_struct *area; @@ -1526,7 +1599,8 @@ static void __vunmap(const void *addr, int deallocate_pages) debug_check_no_locks_freed(area->addr, get_vm_area_size(area)); debug_check_no_obj_freed(area->addr, get_vm_area_size(area)); - remove_vm_area(addr); + vm_remove_mappings(area, deallocate_pages); + if (deallocate_pages) { int i; @@ -1961,8 +2035,9 @@ EXPORT_SYMBOL(vzalloc_node); */ void *vmalloc_exec(unsigned long size) { - return __vmalloc_node(size, 1, GFP_KERNEL, PAGE_KERNEL_EXEC, - NUMA_NO_NODE, __builtin_return_address(0)); + return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END, + GFP_KERNEL, PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS, + NUMA_NO_NODE, __builtin_return_address(0)); } #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32) -- cgit From d53d2f78ceadba081fc7785570798c3c8d50a718 Mon Sep 17 00:00:00 2001 From: Rick Edgecombe Date: Thu, 25 Apr 2019 17:11:38 -0700 Subject: bpf: Use vmalloc special flag Use new flag VM_FLUSH_RESET_PERMS for handling freeing of special permissioned memory in vmalloc and remove places where memory was set RW before freeing which is no longer needed. Don't track if the memory is RO anymore because it is now tracked in vmalloc. Signed-off-by: Rick Edgecombe Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Alexei Starovoitov Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Daniel Borkmann Cc: Dave Hansen Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Nadav Amit Cc: Rik van Riel Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20190426001143.4983-19-namit@vmware.com Signed-off-by: Ingo Molnar --- include/linux/filter.h | 17 +++-------------- kernel/bpf/core.c | 1 - 2 files changed, 3 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 14ec3bdad9a9..7d3abde3f183 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -20,6 +20,7 @@ #include #include #include +#include #include @@ -503,7 +504,6 @@ struct bpf_prog { u16 pages; /* Number of allocated pages */ u16 jited:1, /* Is our filter JIT'ed? */ jit_requested:1,/* archs need to JIT the prog */ - undo_set_mem:1, /* Passed set_memory_ro() checkpoint */ gpl_compatible:1, /* Is filter GPL compatible? */ cb_access:1, /* Is control block accessed? */ dst_needed:1, /* Do we need dst entry? */ @@ -733,27 +733,17 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) static inline void bpf_prog_lock_ro(struct bpf_prog *fp) { - fp->undo_set_mem = 1; + set_vm_flush_reset_perms(fp); set_memory_ro((unsigned long)fp, fp->pages); } -static inline void bpf_prog_unlock_ro(struct bpf_prog *fp) -{ - if (fp->undo_set_mem) - set_memory_rw((unsigned long)fp, fp->pages); -} - static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { + set_vm_flush_reset_perms(hdr); set_memory_ro((unsigned long)hdr, hdr->pages); set_memory_x((unsigned long)hdr, hdr->pages); } -static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr) -{ - set_memory_rw((unsigned long)hdr, hdr->pages); -} - static inline struct bpf_binary_header * bpf_jit_binary_hdr(const struct bpf_prog *fp) { @@ -789,7 +779,6 @@ void __bpf_prog_free(struct bpf_prog *fp); static inline void bpf_prog_unlock_free(struct bpf_prog *fp) { - bpf_prog_unlock_ro(fp); __bpf_prog_free(fp); } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index ff09d32a8a1b..c605397c79f0 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -848,7 +848,6 @@ void __weak bpf_jit_free(struct bpf_prog *fp) if (fp->jited) { struct bpf_binary_header *hdr = bpf_jit_binary_hdr(fp); - bpf_jit_binary_unlock_ro(hdr); bpf_jit_binary_free(hdr); WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(fp)); -- cgit From f5eb4d3b92a6a1096ef3480b54782a9409281300 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 26 Apr 2019 18:45:21 +0800 Subject: iov_iter: fix iov_iter_type Commit 875f1d0769cd ("iov_iter: add ITER_BVEC_FLAG_NO_REF flag") introduces one extra flag of ITER_BVEC_FLAG_NO_REF, and this flag is stored into iter->type. However, iov_iter_type() doesn't consider the new added flag, fix it by masking this flag in iov_iter_type(). Fixes: 875f1d0769cd ("iov_iter: add ITER_BVEC_FLAG_NO_REF flag") Reviewed-by: Christoph Hellwig Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/uio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/uio.h b/include/linux/uio.h index f184af1999a8..2d0131ad4604 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -60,7 +60,7 @@ struct iov_iter { static inline enum iter_type iov_iter_type(const struct iov_iter *i) { - return i->type & ~(READ | WRITE); + return i->type & ~(READ | WRITE | ITER_BVEC_FLAG_NO_REF); } static inline bool iter_is_iovec(const struct iov_iter *i) -- cgit From 72e830f68428ab9ea9eca65d160795f4e02cecfc Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Fri, 3 May 2019 11:55:36 +0300 Subject: perf/x86/intel/pt: Remove software double buffering PMU capability Now that all AUX allocations are high-order by default, the software double buffering PMU capability doesn't make sense any more, get rid of it. In case some PMUs choose to opt out, we can re-introduce it. Signed-off-by: Alexander Shishkin Acked-by: Peter Zijlstra Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Linus Torvalds Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Cc: adrian.hunter@intel.com Link: http://lkml.kernel.org/r/20190503085536.24119-3-alexander.shishkin@linux.intel.com Signed-off-by: Ingo Molnar --- arch/x86/events/intel/pt.c | 3 +-- include/linux/perf_event.h | 1 - 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index fb3a2f13fc70..339d7628080c 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -1525,8 +1525,7 @@ static __init int pt_init(void) } if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries)) - pt_pmu.pmu.capabilities = - PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_AUX_SW_DOUBLEBUF; + pt_pmu.pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG; pt_pmu.pmu.capabilities |= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE; pt_pmu.pmu.attr_groups = pt_attr_groups; diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index e47ef764f613..1f678f023850 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -240,7 +240,6 @@ struct perf_event; #define PERF_PMU_CAP_NO_INTERRUPT 0x01 #define PERF_PMU_CAP_NO_NMI 0x02 #define PERF_PMU_CAP_AUX_NO_SG 0x04 -#define PERF_PMU_CAP_AUX_SW_DOUBLEBUF 0x08 #define PERF_PMU_CAP_EXCLUSIVE 0x10 #define PERF_PMU_CAP_ITRACE 0x20 #define PERF_PMU_CAP_HETEROGENEOUS_CPUS 0x40 -- cgit From 2f1a6fbbef7781382850c3104ecb658f21b5d460 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Thu, 11 Apr 2019 13:34:45 +1000 Subject: power/suspend: Add function to disable secondaries for suspend This adds a function to disable secondary CPUs for suspend that are not necessarily non-zero / non-boot CPUs. Platforms will be able to use this to suspend using non-zero CPUs. Signed-off-by: Nicholas Piggin Signed-off-by: Peter Zijlstra (Intel) Cc: Frederic Weisbecker Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rafael J . Wysocki Cc: Thomas Gleixner Cc: linuxppc-dev@lists.ozlabs.org Link: https://lkml.kernel.org/r/20190411033448.20842-3-npiggin@gmail.com Signed-off-by: Ingo Molnar --- include/linux/cpu.h | 12 ++++++++++++ kernel/kexec_core.c | 4 ++-- kernel/power/hibernate.c | 12 ++++++------ kernel/power/suspend.c | 4 ++-- 4 files changed, 22 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 5041357d0297..7ab2f09c0a14 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -137,9 +137,21 @@ static inline int disable_nonboot_cpus(void) return freeze_secondary_cpus(0); } extern void enable_nonboot_cpus(void); + +static inline int suspend_disable_secondary_cpus(void) +{ + return freeze_secondary_cpus(0); +} +static inline void suspend_enable_secondary_cpus(void) +{ + return enable_nonboot_cpus(); +} + #else /* !CONFIG_PM_SLEEP_SMP */ static inline int disable_nonboot_cpus(void) { return 0; } static inline void enable_nonboot_cpus(void) {} +static inline int suspend_disable_secondary_cpus(void) { return 0; } +static inline void suspend_enable_secondary_cpus(void) { } #endif /* !CONFIG_PM_SLEEP_SMP */ void cpu_startup_entry(enum cpuhp_state state); diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index d7140447be75..fd5c95ff9251 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -1150,7 +1150,7 @@ int kernel_kexec(void) error = dpm_suspend_end(PMSG_FREEZE); if (error) goto Resume_devices; - error = disable_nonboot_cpus(); + error = suspend_disable_secondary_cpus(); if (error) goto Enable_cpus; local_irq_disable(); @@ -1183,7 +1183,7 @@ int kernel_kexec(void) Enable_irqs: local_irq_enable(); Enable_cpus: - enable_nonboot_cpus(); + suspend_enable_secondary_cpus(); dpm_resume_start(PMSG_RESTORE); Resume_devices: dpm_resume_end(PMSG_RESTORE); diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index abef759de7c8..cfc7a57049e4 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -281,7 +281,7 @@ static int create_image(int platform_mode) if (error || hibernation_test(TEST_PLATFORM)) goto Platform_finish; - error = disable_nonboot_cpus(); + error = suspend_disable_secondary_cpus(); if (error || hibernation_test(TEST_CPUS)) goto Enable_cpus; @@ -323,7 +323,7 @@ static int create_image(int platform_mode) local_irq_enable(); Enable_cpus: - enable_nonboot_cpus(); + suspend_enable_secondary_cpus(); Platform_finish: platform_finish(platform_mode); @@ -417,7 +417,7 @@ int hibernation_snapshot(int platform_mode) int __weak hibernate_resume_nonboot_cpu_disable(void) { - return disable_nonboot_cpus(); + return suspend_disable_secondary_cpus(); } /** @@ -486,7 +486,7 @@ static int resume_target_kernel(bool platform_mode) local_irq_enable(); Enable_cpus: - enable_nonboot_cpus(); + suspend_enable_secondary_cpus(); Cleanup: platform_restore_cleanup(platform_mode); @@ -564,7 +564,7 @@ int hibernation_platform_enter(void) if (error) goto Platform_finish; - error = disable_nonboot_cpus(); + error = suspend_disable_secondary_cpus(); if (error) goto Enable_cpus; @@ -586,7 +586,7 @@ int hibernation_platform_enter(void) local_irq_enable(); Enable_cpus: - enable_nonboot_cpus(); + suspend_enable_secondary_cpus(); Platform_finish: hibernation_ops->finish(); diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 0bd595a0b610..59b6def23046 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -428,7 +428,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) if (suspend_test(TEST_PLATFORM)) goto Platform_wake; - error = disable_nonboot_cpus(); + error = suspend_disable_secondary_cpus(); if (error || suspend_test(TEST_CPUS)) goto Enable_cpus; @@ -458,7 +458,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup) BUG_ON(irqs_disabled()); Enable_cpus: - enable_nonboot_cpus(); + suspend_enable_secondary_cpus(); Platform_wake: platform_resume_noirq(state); -- cgit From 9ca12ac04bb7d7cfb28aa549dcd3d15761f15543 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Thu, 11 Apr 2019 13:34:46 +1000 Subject: kernel/cpu: Allow non-zero CPU to be primary for suspend / kexec freeze This patch provides an arch option, ARCH_SUSPEND_NONZERO_CPU, to opt-in to allowing suspend to occur on one of the housekeeping CPUs rather than hardcoded CPU0. This will allow CPU0 to be a nohz_full CPU with a later change. It may be possible for platforms with hardware/firmware restrictions on suspend/wake effectively support this by handing off the final stage to CPU0 when kernel housekeeping is no longer required. Another option is to make housekeeping / nohz_full mask dynamic at runtime, but the complexity could not be justified at this time. Signed-off-by: Nicholas Piggin Signed-off-by: Peter Zijlstra (Intel) Cc: Frederic Weisbecker Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Rafael J . Wysocki Cc: Thomas Gleixner Cc: linuxppc-dev@lists.ozlabs.org Link: https://lkml.kernel.org/r/20190411033448.20842-4-npiggin@gmail.com Signed-off-by: Ingo Molnar --- arch/powerpc/Kconfig | 4 ++++ include/linux/cpu.h | 7 ++++++- kernel/cpu.c | 10 +++++++++- kernel/power/Kconfig | 9 +++++++++ 4 files changed, 28 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 2d0be82c3061..bc98b0e37a10 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -318,6 +318,10 @@ config ARCH_SUSPEND_POSSIBLE (PPC_85xx && !PPC_E500MC) || PPC_86xx || PPC_PSERIES \ || 44x || 40x +config ARCH_SUSPEND_NONZERO_CPU + def_bool y + depends on PPC_POWERNV || PPC_PSERIES + config PPC_DCR_NATIVE bool diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 7ab2f09c0a14..73baab8535c1 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -140,7 +140,12 @@ extern void enable_nonboot_cpus(void); static inline int suspend_disable_secondary_cpus(void) { - return freeze_secondary_cpus(0); + int cpu = 0; + + if (IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU)) + cpu = -1; + + return freeze_secondary_cpus(cpu); } static inline void suspend_enable_secondary_cpus(void) { diff --git a/kernel/cpu.c b/kernel/cpu.c index 6754f3ecfd94..d1bf6e2b4752 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -1199,8 +1200,15 @@ int freeze_secondary_cpus(int primary) int cpu, error = 0; cpu_maps_update_begin(); - if (!cpu_online(primary)) + if (primary == -1) { primary = cpumask_first(cpu_online_mask); + if (!housekeeping_cpu(primary, HK_FLAG_TIMER)) + primary = housekeeping_any_cpu(HK_FLAG_TIMER); + } else { + if (!cpu_online(primary)) + primary = cpumask_first(cpu_online_mask); + } + /* * We take down all of the non-boot CPUs in one shot to avoid races * with the userspace trying to use the CPU hotplug at the same time diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index f8fe57d1022e..9bbaaab14b36 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -114,6 +114,15 @@ config PM_SLEEP_SMP depends on PM_SLEEP select HOTPLUG_CPU +config PM_SLEEP_SMP_NONZERO_CPU + def_bool y + depends on PM_SLEEP_SMP + depends on ARCH_SUSPEND_NONZERO_CPU + ---help--- + If an arch can suspend (for suspend, hibernate, kexec, etc) on a + non-zero numbered CPU, it may define ARCH_SUSPEND_NONZERO_CPU. This + will allow nohz_full mask to include CPU0. + config PM_AUTOSLEEP bool "Opportunistic sleep" depends on PM_SLEEP -- cgit