From 30c66fc30ee7a98c4f3adf5fb7e213b61884474f Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 3 Jul 2020 03:06:57 +0200 Subject: timer: Prevent base->clk from moving backward When a timer is enqueued with a negative delta (ie: expiry is below base->clk), it gets added to the wheel as expiring now (base->clk). Yet the value that gets stored in base->next_expiry, while calling trigger_dyntick_cpu(), is the initial timer->expires value. The resulting state becomes: base->next_expiry < base->clk On the next timer enqueue, forward_timer_base() may accidentally rewind base->clk. As a possible outcome, timers may expire way too early, the worst case being that the highest wheel levels get spuriously processed again. To prevent from that, make sure that base->next_expiry doesn't get below base->clk. Fixes: a683f390b93f ("timers: Forward the wheel clock whenever possible") Signed-off-by: Frederic Weisbecker Signed-off-by: Thomas Gleixner Reviewed-by: Anna-Maria Behnsen Tested-by: Juri Lelli Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20200703010657.2302-1-frederic@kernel.org --- kernel/time/timer.c | 17 ++++++++++++++--- 1 file changed, 14 insertions(+), 3 deletions(-) (limited to 'kernel/time') diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 398e6eadb861..9a838d38dbe6 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -584,7 +584,15 @@ trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer) * Set the next expiry time and kick the CPU so it can reevaluate the * wheel: */ - base->next_expiry = timer->expires; + if (time_before(timer->expires, base->clk)) { + /* + * Prevent from forward_timer_base() moving the base->clk + * backward + */ + base->next_expiry = base->clk; + } else { + base->next_expiry = timer->expires; + } wake_up_nohz_cpu(base->cpu); } @@ -896,10 +904,13 @@ static inline void forward_timer_base(struct timer_base *base) * If the next expiry value is > jiffies, then we fast forward to * jiffies otherwise we forward to the next expiry value. */ - if (time_after(base->next_expiry, jnow)) + if (time_after(base->next_expiry, jnow)) { base->clk = jnow; - else + } else { + if (WARN_ON_ONCE(time_before(base->next_expiry, base->clk))) + return; base->clk = base->next_expiry; + } #endif } -- cgit v1.2.3 From e2a71bdea81690b6ef11f4368261ec6f5b6891aa Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 17 Jul 2020 16:05:40 +0200 Subject: timer: Fix wheel index calculation on last level When an expiration delta falls into the last level of the wheel, that delta has be compared against the maximum possible delay and reduced to fit in if necessary. However instead of comparing the delta against the maximum, the code compares the actual expiry against the maximum. Then instead of fixing the delta to fit in, it sets the maximum delta as the expiry value. This can result in various undesired outcomes, the worst possible one being a timer expiring 15 days ahead to fire immediately. Fixes: 500462a9de65 ("timers: Switch to a non-cascading wheel") Signed-off-by: Frederic Weisbecker Signed-off-by: Thomas Gleixner Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20200717140551.29076-2-frederic@kernel.org --- kernel/time/timer.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/time') diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 9a838d38dbe6..df1ff803acc4 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -521,8 +521,8 @@ static int calc_wheel_index(unsigned long expires, unsigned long clk) * Force expire obscene large timeouts to expire at the * capacity limit of the wheel. */ - if (expires >= WHEEL_TIMEOUT_CUTOFF) - expires = WHEEL_TIMEOUT_MAX; + if (delta >= WHEEL_TIMEOUT_CUTOFF) + expires = clk + WHEEL_TIMEOUT_MAX; idx = calc_index(expires, LVL_DEPTH - 1); } -- cgit v1.2.3 From f227e3ec3b5cad859ad15666874405e8c1bbc1d4 Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Fri, 10 Jul 2020 15:23:19 +0200 Subject: random32: update the net random state on interrupt and activity This modifies the first 32 bits out of the 128 bits of a random CPU's net_rand_state on interrupt or CPU activity to complicate remote observations that could lead to guessing the network RNG's internal state. Note that depending on some network devices' interrupt rate moderation or binding, this re-seeding might happen on every packet or even almost never. In addition, with NOHZ some CPUs might not even get timer interrupts, leaving their local state rarely updated, while they are running networked processes making use of the random state. For this reason, we also perform this update in update_process_times() in order to at least update the state when there is user or system activity, since it's the only case we care about. Reported-by: Amit Klein Suggested-by: Linus Torvalds Cc: Eric Dumazet Cc: "Jason A. Donenfeld" Cc: Andy Lutomirski Cc: Kees Cook Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Signed-off-by: Willy Tarreau Signed-off-by: Linus Torvalds --- kernel/time/timer.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'kernel/time') diff --git a/kernel/time/timer.c b/kernel/time/timer.c index df1ff803acc4..026ac01af9da 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include @@ -1742,6 +1743,13 @@ void update_process_times(int user_tick) scheduler_tick(); if (IS_ENABLED(CONFIG_POSIX_TIMERS)) run_posix_cpu_timers(); + + /* The current CPU might make use of net randoms without receiving IRQs + * to renew them often enough. Let's update the net_rand_state from a + * non-constant value that's not affine to the number of calls to make + * sure it's updated when there's some activity (we don't care in idle). + */ + this_cpu_add(net_rand_state.s1, rol32(jiffies, 24) + user_tick); } /** -- cgit v1.2.3