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. Override x86_platform.save_sched_clock_state and
x86_platform.restore_sched_clock_state.
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(a)vger.kernel.org
Fixes: 1349401ff1aa ("clocksource/drivers/hyper-v: Suspend/resume Hyper-V clocksource for hibernation")
Co-developed-by: Dexuan Cui <decui(a)microsoft.com>
Signed-off-by: Dexuan Cui <decui(a)microsoft.com>
Signed-off-by: Naman Jain <namjain(a)linux.microsoft.com>
---
Changes from v1:
https://lore.kernel.org/all/20240909053923.8512-1-namjain@linux.microsoft.c…
* Reorganized code as per Michael's comment, and moved the logic to x86
specific files, to keep hyperv_timer.c arch independent.
---
arch/x86/kernel/cpu/mshyperv.c | 70 ++++++++++++++++++++++++++++++
drivers/clocksource/hyperv_timer.c | 8 +++-
include/clocksource/hyperv_timer.h | 8 ++++
3 files changed, 85 insertions(+), 1 deletion(-)
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index e0fd57a8ba84..d83a694e387c 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -224,6 +224,75 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs)
hyperv_cleanup();
}
#endif /* CONFIG_CRASH_DUMP */
+
+static u64 hv_sched_clock_offset_saved;
+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_sched_clock_offset_saved = hv_read_reference_counter();
+}
+
+static void restore_hv_clock_tsc_state(void)
+{
+ /*
+ * hv_sched_clock_offset = offset that is used by hyperv_timer clocksource driver
+ * to get time.
+ * Time passed before suspend = hv_sched_clock_offset_saved
+ * - hv_sched_clock_offset (old)
+ *
+ * After Hyper-V clock counter resets, hv_sched_clock_offset needs a correction.
+ *
+ * New time = hv_read_reference_counter() (future) - hv_sched_clock_offset (new)
+ * New time = Time passed before suspend + hv_read_reference_counter() (future)
+ * - hv_read_reference_counter() (now)
+ *
+ * Solving the above two equations gives:
+ *
+ * hv_sched_clock_offset (new) = hv_sched_clock_offset (old)
+ * - hv_sched_clock_offset_saved
+ * + hv_read_reference_counter() (now))
+ */
+ hv_adj_sched_clock_offset(hv_sched_clock_offset_saved - 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)
@@ -575,6 +644,7 @@ static void __init ms_hyperv_init_platform(void)
/* Register Hyper-V specific clocksource */
hv_init_clocksource();
+ x86_setup_ops_for_tsc_pg_clock();
hv_vtl_init_platform();
#endif
/*
diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c
index b2a080647e41..e424892444ed 100644
--- a/drivers/clocksource/hyperv_timer.c
+++ b/drivers/clocksource/hyperv_timer.c
@@ -27,7 +27,8 @@
#include <asm/mshyperv.h>
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
@@ -456,6 +457,11 @@ static void resume_hv_clock_tsc(struct clocksource *arg)
hv_set_msr(HV_MSR_REFERENCE_TSC, tsc_msr.as_uint64);
}
+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)
{
diff --git a/include/clocksource/hyperv_timer.h b/include/clocksource/hyperv_timer.h
index 6cdc873ac907..62e2bad754c0 100644
--- a/include/clocksource/hyperv_timer.h
+++ b/include/clocksource/hyperv_timer.h
@@ -38,6 +38,14 @@ extern void hv_remap_tsc_clocksource(void);
extern unsigned long hv_get_tsc_pfn(void);
extern struct ms_hyperv_tsc_page *hv_get_tsc_page(void);
+/*
+ * 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.
+ */
+extern void hv_adj_sched_clock_offset(u64 offset);
+
static __always_inline bool
hv_read_tsc_page_tsc(const struct ms_hyperv_tsc_page *tsc_pg,
u64 *cur_tsc, u64 *time)
base-commit: da3ea35007d0af457a0afc87e84fddaebc4e0b63
--
2.25.1
From: Willem de Bruijn <willemb(a)google.com>
The referenced commit drops bad input, but has false positives.
Tighten the check to avoid these.
The check detects illegal checksum offload requests, which produce
csum_start/csum_off beyond end of packet after segmentation.
But it is based on two incorrect assumptions:
1. virtio_net_hdr_to_skb with VIRTIO_NET_HDR_GSO_TCP[46] implies GSO.
True in callers that inject into the tx path, such as tap.
But false in callers that inject into rx, like virtio-net.
Here, the flags indicate GRO, and CHECKSUM_UNNECESSARY or
CHECKSUM_NONE without VIRTIO_NET_HDR_F_NEEDS_CSUM is normal.
2. TSO requires checksum offload, i.e., ip_summed == CHECKSUM_PARTIAL.
False, as tcp[46]_gso_segment will fix up csum_start and offset for
all other ip_summed by calling __tcp_v4_send_check.
Because of 2, we can limit the scope of the fix to virtio_net_hdr
that do try to set these fields, with a bogus value.
Link: https://lore.kernel.org/netdev/20240909094527.GA3048202@port70.net/
Fixes: 89add40066f9 ("net: drop bad gso csum_start and offset in virtio_net_hdr")
Signed-off-by: Willem de Bruijn <willemb(a)google.com>
Acked-by: Jason Wang <jasowang(a)redhat.com>
Acked-by: Michael S. Tsirkin <mst(a)redhat.com>
Cc: stable(a)vger.kernel.org
---
Changes v1->v2:
- Fix Cc:
- Add Acks from v1
---
include/linux/virtio_net.h | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 6c395a2600e8d..276ca543ef44d 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -173,7 +173,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
break;
case SKB_GSO_TCPV4:
case SKB_GSO_TCPV6:
- if (skb->csum_offset != offsetof(struct tcphdr, check))
+ if (skb->ip_summed == CHECKSUM_PARTIAL &&
+ skb->csum_offset != offsetof(struct tcphdr, check))
return -EINVAL;
break;
}
--
2.46.0.598.g6f2099f65c-goog
From: Lai Jiangshan <jiangshan.ljs(a)antgroup.com>
Marc Hartmayer reported:
[ 23.133876] Unable to handle kernel pointer dereference in virtual kernel address space
[ 23.133950] Failing address: 0000000000000000 TEID: 0000000000000483
[ 23.133954] Fault in home space mode while using kernel ASCE.
[ 23.133957] AS:000000001b8f0007 R3:0000000056cf4007 S:0000000056cf3800 P:000000000000003d
[ 23.134207] Oops: 0004 ilc:2 [#1] SMP
(snip)
[ 23.134516] Call Trace:
[ 23.134520] [<0000024e326caf28>] worker_thread+0x48/0x430
[ 23.134525] ([<0000024e326caf18>] worker_thread+0x38/0x430)
[ 23.134528] [<0000024e326d3a3e>] kthread+0x11e/0x130
[ 23.134533] [<0000024e3264b0dc>] __ret_from_fork+0x3c/0x60
[ 23.134536] [<0000024e333fb37a>] ret_from_fork+0xa/0x38
[ 23.134552] Last Breaking-Event-Address:
[ 23.134553] [<0000024e333f4c04>] mutex_unlock+0x24/0x30
[ 23.134562] Kernel panic - not syncing: Fatal exception: panic_on_oops
With debuging and analysis, worker_thread() accesses to the nullified
worker->pool when the newly created worker is destroyed before being
waken-up, in which case worker_thread() can see the result detach_worker()
reseting worker->pool to NULL at the begining.
Move the code "worker->pool = NULL;" out from detach_worker() to fix the
problem.
worker->pool had been designed to be constant for regular workers and
changeable for rescuer. To share attaching/detaching code for regular
and rescuer workers and to avoid worker->pool being accessed inadvertently
when the worker has been detached, worker->pool is reset to NULL when
detached no matter the worker is rescuer or not.
To maintain worker->pool being reset after detached, move the code
"worker->pool = NULL;" in the worker thread context after detached.
It is either be in the regular worker thread context after PF_WQ_WORKER
is cleared or in rescuer worker thread context with wq_pool_attach_mutex
held. So it is safe to do so.
Cc: Marc Hartmayer <mhartmay(a)linux.ibm.com>
Link: https://lore.kernel.org/lkml/87wmjj971b.fsf@linux.ibm.com/
Reported-by: Marc Hartmayer <mhartmay(a)linux.ibm.com>
Fixes: f4b7b53c94af ("workqueue: Detach workers directly in idle_cull_fn()")
Cc: stable(a)vger.kernel.org # v6.11+
Signed-off-by: Lai Jiangshan <jiangshan.ljs(a)antgroup.com>
---
kernel/workqueue.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index e7b005ff3750..6f2545037e57 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2709,7 +2709,6 @@ static void detach_worker(struct worker *worker)
unbind_worker(worker);
list_del(&worker->node);
- worker->pool = NULL;
}
/**
@@ -2729,6 +2728,7 @@ static void worker_detach_from_pool(struct worker *worker)
mutex_lock(&wq_pool_attach_mutex);
detach_worker(worker);
+ worker->pool = NULL;
mutex_unlock(&wq_pool_attach_mutex);
/* clear leftover flags without pool->lock after it is detached */
@@ -3349,7 +3349,11 @@ static int worker_thread(void *__worker)
if (unlikely(worker->flags & WORKER_DIE)) {
raw_spin_unlock_irq(&pool->lock);
set_pf_worker(false);
-
+ /*
+ * The worker is dead and PF_WQ_WORKER is cleared, worker->pool
+ * shouldn't be accessed, reset it to NULL in case otherwise.
+ */
+ worker->pool = NULL;
ida_free(&pool->worker_ida, worker->id);
return 0;
}
--
2.19.1.6.gb485710b