December 2024 - Linux-stable-mirror

FAILED: patch "[PATCH] clocksource: Make negative motion detection more robust" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 76031d9536a076bf023bedbdb1b4317fc801dd67 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024121205-could-retype-331c@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 76031d9536a076bf023bedbdb1b4317fc801dd67 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner <tglx(a)linutronix.de> Date: Tue, 3 Dec 2024 11:16:30 +0100 Subject: [PATCH] clocksource: Make negative motion detection more robust Guenter reported boot stalls on a emulated ARM 32-bit platform, which has a 24-bit wide clocksource. It turns out that the calculated maximal idle time, which limits idle sleeps to prevent clocksource wrap arounds, is close to the point where the negative motion detection triggers. max_idle_ns: 597268854 ns negative motion tripping point: 671088640 ns If the idle wakeup is delayed beyond that point, the clocksource advances far enough to trigger the negative motion detection. This prevents the clock to advance and in the worst case the system stalls completely if the consecutive sleeps based on the stale clock are delayed as well. Cure this by calculating a more robust cut-off value for negative motion, which covers 87.5% of the actual clocksource counter width. Compare the delta against this value to catch negative motion. This is specifically for clock sources with a small counter width as their wrap around time is close to the half counter width. For clock sources with wide counters this is not a problem because the maximum idle time is far from the half counter width due to the math overflow protection constraints. For the case at hand this results in a tripping point of 1174405120ns. Note, that this cannot prevent issues when the delay exceeds the 87.5% margin, but that's not different from the previous unchecked version which allowed arbitrary time jumps. Systems with small counter width are prone to invalid results, but this problem is unlikely to be seen on real hardware. If such a system completely stalls for more than half a second, then there are other more urgent problems than the counter wrapping around. Fixes: c163e40af9b2 ("timekeeping: Always check for negative motion") Reported-by: Guenter Roeck <linux(a)roeck-us.net> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Tested-by: Guenter Roeck <linux(a)roeck-us.net> Link: https://lore.kernel.org/all/8734j5ul4x.ffs@tglx Closes: https://lore.kernel.org/all/387b120b-d68a-45e8-b6ab-768cd95d11c2@roeck-us.n… diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index ef1b16da6ad5..65b7c41471c3 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -49,6 +49,7 @@ struct module; * @archdata: Optional arch-specific data * @max_cycles: Maximum safe cycle value which won't overflow on * multiplication + * @max_raw_delta: Maximum safe delta value for negative motion detection * @name: Pointer to clocksource name * @list: List head for registration (internal) * @freq_khz: Clocksource frequency in khz. @@ -109,6 +110,7 @@ struct clocksource { struct arch_clocksource_data archdata; #endif u64 max_cycles; + u64 max_raw_delta; const char *name; struct list_head list; u32 freq_khz; diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index aab6472853fa..7304d7cf47f2 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -24,7 +24,7 @@ static void clocksource_enqueue(struct clocksource *cs); static noinline u64 cycles_to_nsec_safe(struct clocksource *cs, u64 start, u64 end) { - u64 delta = clocksource_delta(end, start, cs->mask); + u64 delta = clocksource_delta(end, start, cs->mask, cs->max_raw_delta); if (likely(delta < cs->max_cycles)) return clocksource_cyc2ns(delta, cs->mult, cs->shift); @@ -993,6 +993,15 @@ static inline void clocksource_update_max_deferment(struct clocksource *cs) cs->max_idle_ns = clocks_calc_max_nsecs(cs->mult, cs->shift, cs->maxadj, cs->mask, &cs->max_cycles); + + /* + * Threshold for detecting negative motion in clocksource_delta(). + * + * Allow for 0.875 of the counter width so that overly long idle + * sleeps, which go slightly over mask/2, do not trigger the + * negative motion detection. + */ + cs->max_raw_delta = (cs->mask >> 1) + (cs->mask >> 2) + (cs->mask >> 3); } static struct clocksource *clocksource_find_best(bool oneshot, bool skipcur) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 0ca85ff4fbb4..3d128825d343 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -755,7 +755,8 @@ static void timekeeping_forward_now(struct timekeeper *tk) u64 cycle_now, delta; cycle_now = tk_clock_read(&tk->tkr_mono); - delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask); + delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask, + tk->tkr_mono.clock->max_raw_delta); tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; @@ -2230,7 +2231,8 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode) return false; offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), - tk->tkr_mono.cycle_last, tk->tkr_mono.mask); + tk->tkr_mono.cycle_last, tk->tkr_mono.mask, + tk->tkr_mono.clock->max_raw_delta); /* Check if there's really nothing to do */ if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK) diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h index 63e600e943a7..8c9079108ffb 100644 --- a/kernel/time/timekeeping_internal.h +++ b/kernel/time/timekeeping_internal.h @@ -30,15 +30,15 @@ static inline void timekeeping_inc_mg_floor_swaps(void) #endif -static inline u64 clocksource_delta(u64 now, u64 last, u64 mask) +static inline u64 clocksource_delta(u64 now, u64 last, u64 mask, u64 max_delta) { u64 ret = (now - last) & mask; /* - * Prevent time going backwards by checking the MSB of mask in - * the result. If set, return 0. + * Prevent time going backwards by checking the result against + * @max_delta. If greater, return 0. */ - return ret & ~(mask >> 1) ? 0 : ret; + return ret > max_delta ? 0 : ret; } /* Semi public for serialization of non timekeeper VDSO updates. */

8 months, 2 weeks

1
0
0 0

FAILED: patch "[PATCH] clocksource: Make negative motion detection more robust" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 76031d9536a076bf023bedbdb1b4317fc801dd67 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024121204-among-product-771b@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 76031d9536a076bf023bedbdb1b4317fc801dd67 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner <tglx(a)linutronix.de> Date: Tue, 3 Dec 2024 11:16:30 +0100 Subject: [PATCH] clocksource: Make negative motion detection more robust Guenter reported boot stalls on a emulated ARM 32-bit platform, which has a 24-bit wide clocksource. It turns out that the calculated maximal idle time, which limits idle sleeps to prevent clocksource wrap arounds, is close to the point where the negative motion detection triggers. max_idle_ns: 597268854 ns negative motion tripping point: 671088640 ns If the idle wakeup is delayed beyond that point, the clocksource advances far enough to trigger the negative motion detection. This prevents the clock to advance and in the worst case the system stalls completely if the consecutive sleeps based on the stale clock are delayed as well. Cure this by calculating a more robust cut-off value for negative motion, which covers 87.5% of the actual clocksource counter width. Compare the delta against this value to catch negative motion. This is specifically for clock sources with a small counter width as their wrap around time is close to the half counter width. For clock sources with wide counters this is not a problem because the maximum idle time is far from the half counter width due to the math overflow protection constraints. For the case at hand this results in a tripping point of 1174405120ns. Note, that this cannot prevent issues when the delay exceeds the 87.5% margin, but that's not different from the previous unchecked version which allowed arbitrary time jumps. Systems with small counter width are prone to invalid results, but this problem is unlikely to be seen on real hardware. If such a system completely stalls for more than half a second, then there are other more urgent problems than the counter wrapping around. Fixes: c163e40af9b2 ("timekeeping: Always check for negative motion") Reported-by: Guenter Roeck <linux(a)roeck-us.net> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Tested-by: Guenter Roeck <linux(a)roeck-us.net> Link: https://lore.kernel.org/all/8734j5ul4x.ffs@tglx Closes: https://lore.kernel.org/all/387b120b-d68a-45e8-b6ab-768cd95d11c2@roeck-us.n… diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index ef1b16da6ad5..65b7c41471c3 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -49,6 +49,7 @@ struct module; * @archdata: Optional arch-specific data * @max_cycles: Maximum safe cycle value which won't overflow on * multiplication + * @max_raw_delta: Maximum safe delta value for negative motion detection * @name: Pointer to clocksource name * @list: List head for registration (internal) * @freq_khz: Clocksource frequency in khz. @@ -109,6 +110,7 @@ struct clocksource { struct arch_clocksource_data archdata; #endif u64 max_cycles; + u64 max_raw_delta; const char *name; struct list_head list; u32 freq_khz; diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index aab6472853fa..7304d7cf47f2 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -24,7 +24,7 @@ static void clocksource_enqueue(struct clocksource *cs); static noinline u64 cycles_to_nsec_safe(struct clocksource *cs, u64 start, u64 end) { - u64 delta = clocksource_delta(end, start, cs->mask); + u64 delta = clocksource_delta(end, start, cs->mask, cs->max_raw_delta); if (likely(delta < cs->max_cycles)) return clocksource_cyc2ns(delta, cs->mult, cs->shift); @@ -993,6 +993,15 @@ static inline void clocksource_update_max_deferment(struct clocksource *cs) cs->max_idle_ns = clocks_calc_max_nsecs(cs->mult, cs->shift, cs->maxadj, cs->mask, &cs->max_cycles); + + /* + * Threshold for detecting negative motion in clocksource_delta(). + * + * Allow for 0.875 of the counter width so that overly long idle + * sleeps, which go slightly over mask/2, do not trigger the + * negative motion detection. + */ + cs->max_raw_delta = (cs->mask >> 1) + (cs->mask >> 2) + (cs->mask >> 3); } static struct clocksource *clocksource_find_best(bool oneshot, bool skipcur) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 0ca85ff4fbb4..3d128825d343 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -755,7 +755,8 @@ static void timekeeping_forward_now(struct timekeeper *tk) u64 cycle_now, delta; cycle_now = tk_clock_read(&tk->tkr_mono); - delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask); + delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask, + tk->tkr_mono.clock->max_raw_delta); tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; @@ -2230,7 +2231,8 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode) return false; offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), - tk->tkr_mono.cycle_last, tk->tkr_mono.mask); + tk->tkr_mono.cycle_last, tk->tkr_mono.mask, + tk->tkr_mono.clock->max_raw_delta); /* Check if there's really nothing to do */ if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK) diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h index 63e600e943a7..8c9079108ffb 100644 --- a/kernel/time/timekeeping_internal.h +++ b/kernel/time/timekeeping_internal.h @@ -30,15 +30,15 @@ static inline void timekeeping_inc_mg_floor_swaps(void) #endif -static inline u64 clocksource_delta(u64 now, u64 last, u64 mask) +static inline u64 clocksource_delta(u64 now, u64 last, u64 mask, u64 max_delta) { u64 ret = (now - last) & mask; /* - * Prevent time going backwards by checking the MSB of mask in - * the result. If set, return 0. + * Prevent time going backwards by checking the result against + * @max_delta. If greater, return 0. */ - return ret & ~(mask >> 1) ? 0 : ret; + return ret > max_delta ? 0 : ret; } /* Semi public for serialization of non timekeeper VDSO updates. */

8 months, 2 weeks

1
0
0 0

FAILED: patch "[PATCH] clocksource: Make negative motion detection more robust" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x 76031d9536a076bf023bedbdb1b4317fc801dd67 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024121227-undermine-effort-1e7c@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 76031d9536a076bf023bedbdb1b4317fc801dd67 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner <tglx(a)linutronix.de> Date: Tue, 3 Dec 2024 11:16:30 +0100 Subject: [PATCH] clocksource: Make negative motion detection more robust Guenter reported boot stalls on a emulated ARM 32-bit platform, which has a 24-bit wide clocksource. It turns out that the calculated maximal idle time, which limits idle sleeps to prevent clocksource wrap arounds, is close to the point where the negative motion detection triggers. max_idle_ns: 597268854 ns negative motion tripping point: 671088640 ns If the idle wakeup is delayed beyond that point, the clocksource advances far enough to trigger the negative motion detection. This prevents the clock to advance and in the worst case the system stalls completely if the consecutive sleeps based on the stale clock are delayed as well. Cure this by calculating a more robust cut-off value for negative motion, which covers 87.5% of the actual clocksource counter width. Compare the delta against this value to catch negative motion. This is specifically for clock sources with a small counter width as their wrap around time is close to the half counter width. For clock sources with wide counters this is not a problem because the maximum idle time is far from the half counter width due to the math overflow protection constraints. For the case at hand this results in a tripping point of 1174405120ns. Note, that this cannot prevent issues when the delay exceeds the 87.5% margin, but that's not different from the previous unchecked version which allowed arbitrary time jumps. Systems with small counter width are prone to invalid results, but this problem is unlikely to be seen on real hardware. If such a system completely stalls for more than half a second, then there are other more urgent problems than the counter wrapping around. Fixes: c163e40af9b2 ("timekeeping: Always check for negative motion") Reported-by: Guenter Roeck <linux(a)roeck-us.net> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Tested-by: Guenter Roeck <linux(a)roeck-us.net> Link: https://lore.kernel.org/all/8734j5ul4x.ffs@tglx Closes: https://lore.kernel.org/all/387b120b-d68a-45e8-b6ab-768cd95d11c2@roeck-us.n… diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index ef1b16da6ad5..65b7c41471c3 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -49,6 +49,7 @@ struct module; * @archdata: Optional arch-specific data * @max_cycles: Maximum safe cycle value which won't overflow on * multiplication + * @max_raw_delta: Maximum safe delta value for negative motion detection * @name: Pointer to clocksource name * @list: List head for registration (internal) * @freq_khz: Clocksource frequency in khz. @@ -109,6 +110,7 @@ struct clocksource { struct arch_clocksource_data archdata; #endif u64 max_cycles; + u64 max_raw_delta; const char *name; struct list_head list; u32 freq_khz; diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index aab6472853fa..7304d7cf47f2 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -24,7 +24,7 @@ static void clocksource_enqueue(struct clocksource *cs); static noinline u64 cycles_to_nsec_safe(struct clocksource *cs, u64 start, u64 end) { - u64 delta = clocksource_delta(end, start, cs->mask); + u64 delta = clocksource_delta(end, start, cs->mask, cs->max_raw_delta); if (likely(delta < cs->max_cycles)) return clocksource_cyc2ns(delta, cs->mult, cs->shift); @@ -993,6 +993,15 @@ static inline void clocksource_update_max_deferment(struct clocksource *cs) cs->max_idle_ns = clocks_calc_max_nsecs(cs->mult, cs->shift, cs->maxadj, cs->mask, &cs->max_cycles); + + /* + * Threshold for detecting negative motion in clocksource_delta(). + * + * Allow for 0.875 of the counter width so that overly long idle + * sleeps, which go slightly over mask/2, do not trigger the + * negative motion detection. + */ + cs->max_raw_delta = (cs->mask >> 1) + (cs->mask >> 2) + (cs->mask >> 3); } static struct clocksource *clocksource_find_best(bool oneshot, bool skipcur) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 0ca85ff4fbb4..3d128825d343 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -755,7 +755,8 @@ static void timekeeping_forward_now(struct timekeeper *tk) u64 cycle_now, delta; cycle_now = tk_clock_read(&tk->tkr_mono); - delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask); + delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask, + tk->tkr_mono.clock->max_raw_delta); tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; @@ -2230,7 +2231,8 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode) return false; offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), - tk->tkr_mono.cycle_last, tk->tkr_mono.mask); + tk->tkr_mono.cycle_last, tk->tkr_mono.mask, + tk->tkr_mono.clock->max_raw_delta); /* Check if there's really nothing to do */ if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK) diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h index 63e600e943a7..8c9079108ffb 100644 --- a/kernel/time/timekeeping_internal.h +++ b/kernel/time/timekeeping_internal.h @@ -30,15 +30,15 @@ static inline void timekeeping_inc_mg_floor_swaps(void) #endif -static inline u64 clocksource_delta(u64 now, u64 last, u64 mask) +static inline u64 clocksource_delta(u64 now, u64 last, u64 mask, u64 max_delta) { u64 ret = (now - last) & mask; /* - * Prevent time going backwards by checking the MSB of mask in - * the result. If set, return 0. + * Prevent time going backwards by checking the result against + * @max_delta. If greater, return 0. */ - return ret & ~(mask >> 1) ? 0 : ret; + return ret > max_delta ? 0 : ret; } /* Semi public for serialization of non timekeeper VDSO updates. */

8 months, 2 weeks

1
0
0 0

FAILED: patch "[PATCH] clocksource: Make negative motion detection more robust" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x 76031d9536a076bf023bedbdb1b4317fc801dd67 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024121226-cathedral-decimeter-88cb@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 76031d9536a076bf023bedbdb1b4317fc801dd67 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner <tglx(a)linutronix.de> Date: Tue, 3 Dec 2024 11:16:30 +0100 Subject: [PATCH] clocksource: Make negative motion detection more robust Guenter reported boot stalls on a emulated ARM 32-bit platform, which has a 24-bit wide clocksource. It turns out that the calculated maximal idle time, which limits idle sleeps to prevent clocksource wrap arounds, is close to the point where the negative motion detection triggers. max_idle_ns: 597268854 ns negative motion tripping point: 671088640 ns If the idle wakeup is delayed beyond that point, the clocksource advances far enough to trigger the negative motion detection. This prevents the clock to advance and in the worst case the system stalls completely if the consecutive sleeps based on the stale clock are delayed as well. Cure this by calculating a more robust cut-off value for negative motion, which covers 87.5% of the actual clocksource counter width. Compare the delta against this value to catch negative motion. This is specifically for clock sources with a small counter width as their wrap around time is close to the half counter width. For clock sources with wide counters this is not a problem because the maximum idle time is far from the half counter width due to the math overflow protection constraints. For the case at hand this results in a tripping point of 1174405120ns. Note, that this cannot prevent issues when the delay exceeds the 87.5% margin, but that's not different from the previous unchecked version which allowed arbitrary time jumps. Systems with small counter width are prone to invalid results, but this problem is unlikely to be seen on real hardware. If such a system completely stalls for more than half a second, then there are other more urgent problems than the counter wrapping around. Fixes: c163e40af9b2 ("timekeeping: Always check for negative motion") Reported-by: Guenter Roeck <linux(a)roeck-us.net> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Tested-by: Guenter Roeck <linux(a)roeck-us.net> Link: https://lore.kernel.org/all/8734j5ul4x.ffs@tglx Closes: https://lore.kernel.org/all/387b120b-d68a-45e8-b6ab-768cd95d11c2@roeck-us.n… diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index ef1b16da6ad5..65b7c41471c3 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -49,6 +49,7 @@ struct module; * @archdata: Optional arch-specific data * @max_cycles: Maximum safe cycle value which won't overflow on * multiplication + * @max_raw_delta: Maximum safe delta value for negative motion detection * @name: Pointer to clocksource name * @list: List head for registration (internal) * @freq_khz: Clocksource frequency in khz. @@ -109,6 +110,7 @@ struct clocksource { struct arch_clocksource_data archdata; #endif u64 max_cycles; + u64 max_raw_delta; const char *name; struct list_head list; u32 freq_khz; diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index aab6472853fa..7304d7cf47f2 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -24,7 +24,7 @@ static void clocksource_enqueue(struct clocksource *cs); static noinline u64 cycles_to_nsec_safe(struct clocksource *cs, u64 start, u64 end) { - u64 delta = clocksource_delta(end, start, cs->mask); + u64 delta = clocksource_delta(end, start, cs->mask, cs->max_raw_delta); if (likely(delta < cs->max_cycles)) return clocksource_cyc2ns(delta, cs->mult, cs->shift); @@ -993,6 +993,15 @@ static inline void clocksource_update_max_deferment(struct clocksource *cs) cs->max_idle_ns = clocks_calc_max_nsecs(cs->mult, cs->shift, cs->maxadj, cs->mask, &cs->max_cycles); + + /* + * Threshold for detecting negative motion in clocksource_delta(). + * + * Allow for 0.875 of the counter width so that overly long idle + * sleeps, which go slightly over mask/2, do not trigger the + * negative motion detection. + */ + cs->max_raw_delta = (cs->mask >> 1) + (cs->mask >> 2) + (cs->mask >> 3); } static struct clocksource *clocksource_find_best(bool oneshot, bool skipcur) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 0ca85ff4fbb4..3d128825d343 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -755,7 +755,8 @@ static void timekeeping_forward_now(struct timekeeper *tk) u64 cycle_now, delta; cycle_now = tk_clock_read(&tk->tkr_mono); - delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask); + delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask, + tk->tkr_mono.clock->max_raw_delta); tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; @@ -2230,7 +2231,8 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode) return false; offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), - tk->tkr_mono.cycle_last, tk->tkr_mono.mask); + tk->tkr_mono.cycle_last, tk->tkr_mono.mask, + tk->tkr_mono.clock->max_raw_delta); /* Check if there's really nothing to do */ if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK) diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h index 63e600e943a7..8c9079108ffb 100644 --- a/kernel/time/timekeeping_internal.h +++ b/kernel/time/timekeeping_internal.h @@ -30,15 +30,15 @@ static inline void timekeeping_inc_mg_floor_swaps(void) #endif -static inline u64 clocksource_delta(u64 now, u64 last, u64 mask) +static inline u64 clocksource_delta(u64 now, u64 last, u64 mask, u64 max_delta) { u64 ret = (now - last) & mask; /* - * Prevent time going backwards by checking the MSB of mask in - * the result. If set, return 0. + * Prevent time going backwards by checking the result against + * @max_delta. If greater, return 0. */ - return ret & ~(mask >> 1) ? 0 : ret; + return ret > max_delta ? 0 : ret; } /* Semi public for serialization of non timekeeper VDSO updates. */

8 months, 2 weeks

1
0
0 0

FAILED: patch "[PATCH] drm/amd/display: Revert commit Update Interface to Check UCLK" failed to apply to 6.12-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.12-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.12.y git checkout FETCH_HEAD git cherry-pick -x 0e93b76cf92f229409e8da85c2a143868835fec3 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2024121247-pantomime-moonlight-81f0@gregkh' --subject-prefix 'PATCH 6.12.y' HEAD^.. Possible dependencies: thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 0e93b76cf92f229409e8da85c2a143868835fec3 Mon Sep 17 00:00:00 2001 From: Austin Zheng <Austin.Zheng(a)amd.com> Date: Mon, 23 Sep 2024 10:07:32 -0400 Subject: [PATCH] drm/amd/display: Revert commit Update Interface to Check UCLK DPM This reverts commit b8d046985c2dc41a0e264a391da4606099f8d44f. Reverting as regression discovered on certain systems and golden values need to updated. Reviewed-by: Alvin Lee <alvin.lee2(a)amd.com> Signed-off-by: Austin Zheng <Austin.Zheng(a)amd.com> Signed-off-by: Rodrigo Siqueira <rodrigo.siqueira(a)amd.com> Tested-by: Daniel Wheeler <daniel.wheeler(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 48057ac22cbd..57ad6ce88f3f 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -6038,15 +6038,8 @@ void dc_set_edp_power(const struct dc *dc, struct dc_link *edp_link, struct dc_power_profile dc_get_power_profile_for_dc_state(const struct dc_state *context) { struct dc_power_profile profile = { 0 }; - struct dc *dc = NULL; - if (!context || !context->clk_mgr || !context->clk_mgr->ctx || !context->clk_mgr->ctx->dc) - return profile; - - dc = context->clk_mgr->ctx->dc; - - if (dc->res_pool->funcs->get_power_profile) - profile.power_level = dc->res_pool->funcs->get_power_profile(context); + profile.power_level += !context->bw_ctx.bw.dcn.clk.p_state_change_support; return profile; } diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c index 2e9c59e9e0c1..1cf9015e854a 100644 --- a/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c +++ b/drivers/gpu/drm/amd/display/dc/dml2/dml21/src/dml2_pmo/dml2_pmo_dcn4_fams2.c @@ -1798,7 +1798,6 @@ bool pmo_dcn4_fams2_init_for_pstate_support(struct dml2_pmo_init_for_pstate_supp } if (s->pmo_dcn4.num_pstate_candidates > 0) { - s->pmo_dcn4.pstate_strategy_candidates[s->pmo_dcn4.num_pstate_candidates-1].allow_state_increase = true; s->pmo_dcn4.cur_pstate_candidate = -1; return true; } else { diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h index 8597e866bfe6..bfb8b8502d20 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h +++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h @@ -215,10 +215,6 @@ struct resource_funcs { void (*get_panel_config_defaults)(struct dc_panel_config *panel_config); void (*build_pipe_pix_clk_params)(struct pipe_ctx *pipe_ctx); - /* - * Get indicator of power from a context that went through full validation - */ - int (*get_power_profile)(const struct dc_state *context); }; struct audio_support{ diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c index f6b840f046a5..3f4b9dba4112 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c @@ -1812,11 +1812,6 @@ static void dcn315_get_panel_config_defaults(struct dc_panel_config *panel_confi *panel_config = panel_config_defaults; } -static int dcn315_get_power_profile(const struct dc_state *context) -{ - return !context->bw_ctx.bw.dcn.clk.p_state_change_support; -} - static struct dc_cap_funcs cap_funcs = { .get_dcc_compression_cap = dcn20_get_dcc_compression_cap }; @@ -1845,7 +1840,6 @@ static struct resource_funcs dcn315_res_pool_funcs = { .update_bw_bounding_box = dcn315_update_bw_bounding_box, .patch_unknown_plane_state = dcn20_patch_unknown_plane_state, .get_panel_config_defaults = dcn315_get_panel_config_defaults, - .get_power_profile = dcn315_get_power_profile, }; static bool dcn315_resource_construct( diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c index 59184abab1a7..f2653a86d3e7 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn401/dcn401_resource.c @@ -1688,22 +1688,6 @@ static void dcn401_build_pipe_pix_clk_params(struct pipe_ctx *pipe_ctx) } } -static int dcn401_get_power_profile(const struct dc_state *context) -{ - int uclk_mhz = context->bw_ctx.bw.dcn.clk.dramclk_khz / 1000; - int dpm_level = 0; - - for (int i = 0; i < context->clk_mgr->bw_params->clk_table.num_entries_per_clk.num_memclk_levels; i++) { - if (context->clk_mgr->bw_params->clk_table.entries[i].memclk_mhz == 0 || - uclk_mhz < context->clk_mgr->bw_params->clk_table.entries[i].memclk_mhz) - break; - if (uclk_mhz > context->clk_mgr->bw_params->clk_table.entries[i].memclk_mhz) - dpm_level++; - } - - return dpm_level; -} - static struct resource_funcs dcn401_res_pool_funcs = { .destroy = dcn401_destroy_resource_pool, .link_enc_create = dcn401_link_encoder_create, @@ -1730,7 +1714,6 @@ static struct resource_funcs dcn401_res_pool_funcs = { .prepare_mcache_programming = dcn401_prepare_mcache_programming, .build_pipe_pix_clk_params = dcn401_build_pipe_pix_clk_params, .calculate_mall_ways_from_bytes = dcn32_calculate_mall_ways_from_bytes, - .get_power_profile = dcn401_get_power_profile, }; static uint32_t read_pipe_fuses(struct dc_context *ctx)

8 months, 2 weeks

1
0
0 0

[PATCH] ocfs2: Revert "ocfs2: fix the la space leak when unmounting an ocfs2 volume"

by Heming Zhao

This reverts commit dfe6c5692fb5 ("ocfs2: fix the la space leak when unmounting an ocfs2 volume"). In commit dfe6c5692fb5, the commit log "This bug has existed since the initial OCFS2 code." is wrong. The correct introduction commit is 30dd3478c3cd ("ocfs2: correctly use ocfs2_find_next_zero_bit()"). The influence of commit dfe6c5692fb5 is that it provides a correct fix for the latest kernel. however, it shouldn't be pushed to stable branches. Let's use this commit to revert all branches that include dfe6c5692fb5 and use a new fix method to fix commit 30dd3478c3cd. Fixes: dfe6c5692fb5 ("ocfs2: fix the la space leak when unmounting an ocfs2 volume") Signed-off-by: Heming Zhao <heming.zhao(a)suse.com> Cc: <stable(a)vger.kernel.org> --- fs/ocfs2/localalloc.c | 19 ------------------- 1 file changed, 19 deletions(-) diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c index 8ac42ea81a17..5df34561c551 100644 --- a/fs/ocfs2/localalloc.c +++ b/fs/ocfs2/localalloc.c @@ -1002,25 +1002,6 @@ static int ocfs2_sync_local_to_main(struct ocfs2_super *osb, start = bit_off + 1; } - /* clear the contiguous bits until the end boundary */ - if (count) { - blkno = la_start_blk + - ocfs2_clusters_to_blocks(osb->sb, - start - count); - - trace_ocfs2_sync_local_to_main_free( - count, start - count, - (unsigned long long)la_start_blk, - (unsigned long long)blkno); - - status = ocfs2_release_clusters(handle, - main_bm_inode, - main_bm_bh, blkno, - count); - if (status < 0) - mlog_errno(status); - } - bail: if (status) mlog_errno(status); -- 2.43.0

8 months, 2 weeks

2
2
0 0

[PATCH v3] vmalloc: Fix accounting with i915

by Matthew Wilcox (Oracle)

If the caller of vmap() specifies VM_MAP_PUT_PAGES (currently only the i915 driver), we will decrement nr_vmalloc_pages and MEMCG_VMALLOC in vfree(). These counters are incremented by vmalloc() but not by vmap() so this will cause an underflow. Check the VM_MAP_PUT_PAGES flag before decrementing either counter. Fixes: b944afc9d64d (mm: add a VM_MAP_PUT_PAGES flag for vmap) Cc: stable(a)vger.kernel.org Signed-off-by: Matthew Wilcox (Oracle) <willy(a)infradead.org> Acked-by: Johannes Weiner <hannes(a)cmpxchg.org> --- mm/vmalloc.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index f009b21705c1..5c88d0e90c20 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3374,7 +3374,8 @@ void vfree(const void *addr) struct page *page = vm->pages[i]; BUG_ON(!page); - mod_memcg_page_state(page, MEMCG_VMALLOC, -1); + if (!(vm->flags & VM_MAP_PUT_PAGES)) + mod_memcg_page_state(page, MEMCG_VMALLOC, -1); /* * High-order allocs for huge vmallocs are split, so * can be freed as an array of order-0 allocations @@ -3382,7 +3383,8 @@ void vfree(const void *addr) __free_page(page); cond_resched(); } - atomic_long_sub(vm->nr_pages, &nr_vmalloc_pages); + if (!(vm->flags & VM_MAP_PUT_PAGES)) + atomic_long_sub(vm->nr_pages, &nr_vmalloc_pages); kvfree(vm->pages); kfree(vm); } -- 2.45.2

8 months, 2 weeks

5
4
0 0

[PATCH 6.1.y] drm/amd/display: Don't refer to dc_sink in is_dsc_need_re_compute

by jianqi.ren.cn＠windriver.com

From: Wayne Lin <wayne.lin(a)amd.com> [ Upstream commit fcf6a49d79923a234844b8efe830a61f3f0584e4 ] [Why] When unplug one of monitors connected after mst hub, encounter null pointer dereference. It's due to dc_sink get released immediately in early_unregister() or detect_ctx(). When commit new state which directly referring to info stored in dc_sink will cause null pointer dereference. [how] Remove redundant checking condition. Relevant condition should already be covered by checking if dsc_aux is null or not. Also reset dsc_aux to NULL when the connector is disconnected. Reviewed-by: Jerry Zuo <jerry.zuo(a)amd.com> Acked-by: Zaeem Mohamed <zaeem.mohamed(a)amd.com> Signed-off-by: Wayne Lin <wayne.lin(a)amd.com> Tested-by: Daniel Wheeler <daniel.wheeler(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> Signed-off-by: Jianqi Ren <jianqi.ren.cn(a)windriver.com> --- drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index 1acef5f3838f..a1619f4569cf 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -183,6 +183,8 @@ amdgpu_dm_mst_connector_early_unregister(struct drm_connector *connector) dc_sink_release(dc_sink); aconnector->dc_sink = NULL; aconnector->edid = NULL; + aconnector->dsc_aux = NULL; + port->passthrough_aux = NULL; } aconnector->mst_status = MST_STATUS_DEFAULT; @@ -487,6 +489,8 @@ dm_dp_mst_detect(struct drm_connector *connector, dc_sink_release(aconnector->dc_sink); aconnector->dc_sink = NULL; aconnector->edid = NULL; + aconnector->dsc_aux = NULL; + port->passthrough_aux = NULL; amdgpu_dm_set_mst_status(&aconnector->mst_status, MST_REMOTE_EDID | MST_ALLOCATE_NEW_PAYLOAD | MST_CLEAR_ALLOCATED_PAYLOAD, -- 2.25.1

8 months, 2 weeks

3
2
0 0

[PATCH 6.1.y] smb: client: fix potential UAF in cifs_dump_full_key()

by jianqi.ren.cn＠windriver.com

From: Paulo Alcantara <pc(a)manguebit.com> [ Upstream commit 58acd1f497162e7d282077f816faa519487be045 ] Skip sessions that are being teared down (status == SES_EXITING) to avoid UAF. Cc: stable(a)vger.kernel.org Signed-off-by: Paulo Alcantara (Red Hat) <pc(a)manguebit.com> Signed-off-by: Steve French <stfrench(a)microsoft.com> Signed-off-by: Jianqi Ren <jianqi.ren.cn(a)windriver.com> --- fs/smb/client/ioctl.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c index ae9905e2b9d4..7402070b7a06 100644 --- a/fs/smb/client/ioctl.c +++ b/fs/smb/client/ioctl.c @@ -246,7 +246,9 @@ static int cifs_dump_full_key(struct cifs_tcon *tcon, struct smb3_full_key_debug spin_lock(&cifs_tcp_ses_lock); list_for_each_entry(server_it, &cifs_tcp_ses_list, tcp_ses_list) { list_for_each_entry(ses_it, &server_it->smb_ses_list, smb_ses_list) { - if (ses_it->Suid == out.session_id) { + spin_lock(&ses_it->ses_lock); + if (ses_it->ses_status != SES_EXITING && + ses_it->Suid == out.session_id) { ses = ses_it; /* * since we are using the session outside the crit @@ -254,9 +256,11 @@ static int cifs_dump_full_key(struct cifs_tcon *tcon, struct smb3_full_key_debug * so increment its refcount */ ses->ses_count++; + spin_unlock(&ses_it->ses_lock); found = true; goto search_end; } + spin_unlock(&ses_it->ses_lock); } } search_end: -- 2.25.1

8 months, 2 weeks

3
2
0 0

[PATCH 5.15 v2] gve: Fixes for napi_poll when budget is 0

by Ziwei Xiao

Netpoll will explicitly pass the polling call with a budget of 0 to indicate it's clearing the Tx path only. For the gve_rx_poll and gve_xdp_poll, they were mistakenly taking the 0 budget as the indication to do all the work. Add check to avoid the rx path and xdp path being called when budget is 0. And also avoid napi_complete_done being called when budget is 0 for netpoll. The original fix was merged here: https://lore.kernel.org/r/20231114004144.2022268-1-ziweixiao@google.com Resend it since the original one was not cleanly applied to 5.15 kernel. commit 278a370c1766 ("gve: Fixes for napi_poll when budget is 0") Fixes: f5cedc84a30d ("gve: Add transmit and receive support") Signed-off-by: Ziwei Xiao <ziweixiao(a)google.com> Reviewed-by: Praveen Kaligineedi <pkaligineedi(a)google.com> Signed-off-by: Praveen Kaligineedi <pkaligineedi(a)google.com> --- Changes in v2: * Add the original git commit id --- drivers/net/ethernet/google/gve/gve_main.c | 7 +++++++ drivers/net/ethernet/google/gve/gve_rx.c | 4 ---- drivers/net/ethernet/google/gve/gve_tx.c | 4 ---- 3 files changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index bf8a4a7c43f7..c3f1959533a8 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -198,6 +198,10 @@ static int gve_napi_poll(struct napi_struct *napi, int budget) if (block->tx) reschedule |= gve_tx_poll(block, budget); + + if (!budget) + return 0; + if (block->rx) reschedule |= gve_rx_poll(block, budget); @@ -246,6 +250,9 @@ static int gve_napi_poll_dqo(struct napi_struct *napi, int budget) if (block->tx) reschedule |= gve_tx_poll_dqo(block, /*do_clean=*/true); + if (!budget) + return 0; + if (block->rx) { work_done = gve_rx_poll_dqo(block, budget); reschedule |= work_done == budget; diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c index 94941d4e4744..368e0e770178 100644 --- a/drivers/net/ethernet/google/gve/gve_rx.c +++ b/drivers/net/ethernet/google/gve/gve_rx.c @@ -599,10 +599,6 @@ bool gve_rx_poll(struct gve_notify_block *block, int budget) feat = block->napi.dev->features; - /* If budget is 0, do all the work */ - if (budget == 0) - budget = INT_MAX; - if (budget > 0) repoll |= gve_clean_rx_done(rx, budget, feat); else diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c index 665ac795a1ad..d56b8356f1f3 100644 --- a/drivers/net/ethernet/google/gve/gve_tx.c +++ b/drivers/net/ethernet/google/gve/gve_tx.c @@ -691,10 +691,6 @@ bool gve_tx_poll(struct gve_notify_block *block, int budget) u32 nic_done; u32 to_do; - /* If budget is 0, do all the work */ - if (budget == 0) - budget = INT_MAX; - /* Find out how much work there is to be done */ tx->last_nic_done = gve_tx_load_event_counter(priv, tx); nic_done = be32_to_cpu(tx->last_nic_done); -- 2.47.0.338.g60cca15819-goog

8 months, 2 weeks

3
2
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror December 2024