From: Greg Kroah-Hartman Date: Fri, 3 Jan 2025 14:41:11 +0000 (+0100) Subject: 5.15-stable patches X-Git-Tag: v5.4.289~75 X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=ba21b207c14a0b6bacb317b0e793ff16229a36f0;p=thirdparty%2Fkernel%2Fstable-queue.git 5.15-stable patches added patches: x86-hyperv-fix-hv-tsc-page-based-sched_clock-for-hibernation.patch --- diff --git a/queue-5.15/series b/queue-5.15/series index 4f9ec79dcb6..8b7a297234c 100644 --- a/queue-5.15/series +++ b/queue-5.15/series @@ -101,3 +101,4 @@ power-supply-gpio-charger-fix-set-charge-current-limits.patch btrfs-avoid-monopolizing-a-core-when-activating-a-swap-file.patch nfsd-cancel-nfsd_shrinker_work-using-sync-mode-in-nfs4_state_shutdown_net.patch net-dsa-improve-shutdown-sequence.patch +x86-hyperv-fix-hv-tsc-page-based-sched_clock-for-hibernation.patch diff --git a/queue-5.15/x86-hyperv-fix-hv-tsc-page-based-sched_clock-for-hibernation.patch b/queue-5.15/x86-hyperv-fix-hv-tsc-page-based-sched_clock-for-hibernation.patch new file mode 100644 index 00000000000..63ce3cbe1d1 --- /dev/null +++ b/queue-5.15/x86-hyperv-fix-hv-tsc-page-based-sched_clock-for-hibernation.patch @@ -0,0 +1,169 @@ +From bcc80dec91ee745b3d66f3e48f0ec2efdea97149 Mon Sep 17 00:00:00 2001 +From: Naman Jain +Date: Tue, 17 Sep 2024 11:09:17 +0530 +Subject: x86/hyperv: Fix hv tsc page based sched_clock for hibernation + +From: Naman Jain + +commit bcc80dec91ee745b3d66f3e48f0ec2efdea97149 upstream. + +read_hv_sched_clock_tsc() assumes that the Hyper-V clock counter is +bigger than the variable hv_sched_clock_offset, which is cached during +early boot, but depending on the timing this assumption may be false +when a hibernated VM starts again (the clock counter starts from 0 +again) and is resuming back (Note: hv_init_tsc_clocksource() is not +called during hibernation/resume); consequently, +read_hv_sched_clock_tsc() may return a negative integer (which is +interpreted as a huge positive integer since the return type is u64) +and new kernel messages are prefixed with huge timestamps before +read_hv_sched_clock_tsc() grows big enough (which typically takes +several seconds). + +Fix the issue by saving the Hyper-V clock counter just before the +suspend, and using it to correct the hv_sched_clock_offset in +resume. This makes hv tsc page based sched_clock continuous and ensures +that post resume, it starts from where it left off during suspend. +Override x86_platform.save_sched_clock_state and +x86_platform.restore_sched_clock_state routines to correct this as soon +as possible. + +Note: if Invariant TSC is available, the issue doesn't happen because +1) we don't register read_hv_sched_clock_tsc() for sched clock: +See commit e5313f1c5404 ("clocksource/drivers/hyper-v: Rework +clocksource and sched clock setup"); +2) the common x86 code adjusts TSC similarly: see +__restore_processor_state() -> tsc_verify_tsc_adjust(true) and +x86_platform.restore_sched_clock_state(). + +Cc: stable@vger.kernel.org +Fixes: 1349401ff1aa ("clocksource/drivers/hyper-v: Suspend/resume Hyper-V clocksource for hibernation") +Co-developed-by: Dexuan Cui +Signed-off-by: Dexuan Cui +Signed-off-by: Naman Jain +Reviewed-by: Michael Kelley +Link: https://lore.kernel.org/r/20240917053917.76787-1-namjain@linux.microsoft.com +Signed-off-by: Wei Liu +Message-ID: <20240917053917.76787-1-namjain@linux.microsoft.com> +Signed-off-by: Naman Jain +Signed-off-by: Greg Kroah-Hartman +--- + arch/x86/kernel/cpu/mshyperv.c | 58 +++++++++++++++++++++++++++++++++++++ + drivers/clocksource/hyperv_timer.c | 14 ++++++++ + include/clocksource/hyperv_timer.h | 2 + + 3 files changed, 73 insertions(+), 1 deletion(-) + +--- a/arch/x86/kernel/cpu/mshyperv.c ++++ b/arch/x86/kernel/cpu/mshyperv.c +@@ -150,6 +150,63 @@ static void hv_machine_crash_shutdown(st + hyperv_cleanup(); + } + #endif /* CONFIG_KEXEC_CORE */ ++ ++static u64 hv_ref_counter_at_suspend; ++static void (*old_save_sched_clock_state)(void); ++static void (*old_restore_sched_clock_state)(void); ++ ++/* ++ * Hyper-V clock counter resets during hibernation. Save and restore clock ++ * offset during suspend/resume, while also considering the time passed ++ * before suspend. This is to make sure that sched_clock using hv tsc page ++ * based clocksource, proceeds from where it left off during suspend and ++ * it shows correct time for the timestamps of kernel messages after resume. ++ */ ++static void save_hv_clock_tsc_state(void) ++{ ++ hv_ref_counter_at_suspend = hv_read_reference_counter(); ++} ++ ++static void restore_hv_clock_tsc_state(void) ++{ ++ /* ++ * Adjust the offsets used by hv tsc clocksource to ++ * account for the time spent before hibernation. ++ * adjusted value = reference counter (time) at suspend ++ * - reference counter (time) now. ++ */ ++ hv_adj_sched_clock_offset(hv_ref_counter_at_suspend - hv_read_reference_counter()); ++} ++ ++/* ++ * Functions to override save_sched_clock_state and restore_sched_clock_state ++ * functions of x86_platform. The Hyper-V clock counter is reset during ++ * suspend-resume and the offset used to measure time needs to be ++ * corrected, post resume. ++ */ ++static void hv_save_sched_clock_state(void) ++{ ++ old_save_sched_clock_state(); ++ save_hv_clock_tsc_state(); ++} ++ ++static void hv_restore_sched_clock_state(void) ++{ ++ restore_hv_clock_tsc_state(); ++ old_restore_sched_clock_state(); ++} ++ ++static void __init x86_setup_ops_for_tsc_pg_clock(void) ++{ ++ if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE)) ++ return; ++ ++ old_save_sched_clock_state = x86_platform.save_sched_clock_state; ++ x86_platform.save_sched_clock_state = hv_save_sched_clock_state; ++ ++ old_restore_sched_clock_state = x86_platform.restore_sched_clock_state; ++ x86_platform.restore_sched_clock_state = hv_restore_sched_clock_state; ++} + #endif /* CONFIG_HYPERV */ + + static uint32_t __init ms_hyperv_platform(void) +@@ -438,6 +495,7 @@ static void __init ms_hyperv_init_platfo + + /* Register Hyper-V specific clocksource */ + hv_init_clocksource(); ++ x86_setup_ops_for_tsc_pg_clock(); + #endif + /* + * TSC should be marked as unstable only after Hyper-V +--- a/drivers/clocksource/hyperv_timer.c ++++ b/drivers/clocksource/hyperv_timer.c +@@ -26,7 +26,8 @@ + #include + + static struct clock_event_device __percpu *hv_clock_event; +-static u64 hv_sched_clock_offset __ro_after_init; ++/* Note: offset can hold negative values after hibernation. */ ++static u64 hv_sched_clock_offset __read_mostly; + + /* + * If false, we're using the old mechanism for stimer0 interrupts +@@ -416,6 +417,17 @@ static void resume_hv_clock_tsc(struct c + hv_set_register(HV_REGISTER_REFERENCE_TSC, tsc_msr); + } + ++/* ++ * Called during resume from hibernation, from overridden ++ * x86_platform.restore_sched_clock_state routine. This is to adjust offsets ++ * used to calculate time for hv tsc page based sched_clock, to account for ++ * time spent before hibernation. ++ */ ++void hv_adj_sched_clock_offset(u64 offset) ++{ ++ hv_sched_clock_offset -= offset; ++} ++ + #ifdef HAVE_VDSO_CLOCKMODE_HVCLOCK + static int hv_cs_enable(struct clocksource *cs) + { +--- a/include/clocksource/hyperv_timer.h ++++ b/include/clocksource/hyperv_timer.h +@@ -34,6 +34,8 @@ extern void hv_init_clocksource(void); + + extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void); + ++extern void hv_adj_sched_clock_offset(u64 offset); ++ + static inline notrace u64 + hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg, u64 *cur_tsc) + {