| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20211101082556.326799324@linuxfoundation.org>
Date: Mon, 1 Nov 2021 10:18:16 +0100
From: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To: linux-kernel@...r.kernel.org
Cc: Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
stable@...r.kernel.org,
syzbot+b282b65c2c68492df769@...kaller.appspotmail.com,
David Woodhouse <dwmw@...zon.co.uk>,
Paolo Bonzini <pbonzini@...hat.com>
Subject: [PATCH 5.14 123/125] KVM: x86: switch pvclock_gtod_sync_lock to a raw spinlock
From: David Woodhouse <dwmw@...zon.co.uk>
commit 8228c77d8b56e3f735baf71fefb1b548c23691a7 upstream.
On the preemption path when updating a Xen guest's runstate times, this
lock is taken inside the scheduler rq->lock, which is a raw spinlock.
This was shown in a lockdep warning:
[ 89.138354] =============================
[ 89.138356] [ BUG: Invalid wait context ]
[ 89.138358] 5.15.0-rc5+ #834 Tainted: G S I E
[ 89.138360] -----------------------------
[ 89.138361] xen_shinfo_test/2575 is trying to lock:
[ 89.138363] ffffa34a0364efd8 (&kvm->arch.pvclock_gtod_sync_lock){....}-{3:3}, at: get_kvmclock_ns+0x1f/0x130 [kvm]
[ 89.138442] other info that might help us debug this:
[ 89.138444] context-{5:5}
[ 89.138445] 4 locks held by xen_shinfo_test/2575:
[ 89.138447] #0: ffff972bdc3b8108 (&vcpu->mutex){+.+.}-{4:4}, at: kvm_vcpu_ioctl+0x77/0x6f0 [kvm]
[ 89.138483] #1: ffffa34a03662e90 (&kvm->srcu){....}-{0:0}, at: kvm_arch_vcpu_ioctl_run+0xdc/0x8b0 [kvm]
[ 89.138526] #2: ffff97331fdbac98 (&rq->__lock){-.-.}-{2:2}, at: __schedule+0xff/0xbd0
[ 89.138534] #3: ffffa34a03662e90 (&kvm->srcu){....}-{0:0}, at: kvm_arch_vcpu_put+0x26/0x170 [kvm]
...
[ 89.138695] get_kvmclock_ns+0x1f/0x130 [kvm]
[ 89.138734] kvm_xen_update_runstate+0x14/0x90 [kvm]
[ 89.138783] kvm_xen_update_runstate_guest+0x15/0xd0 [kvm]
[ 89.138830] kvm_arch_vcpu_put+0xe6/0x170 [kvm]
[ 89.138870] kvm_sched_out+0x2f/0x40 [kvm]
[ 89.138900] __schedule+0x5de/0xbd0
Cc: stable@...r.kernel.org
Reported-by: syzbot+b282b65c2c68492df769@...kaller.appspotmail.com
Fixes: 30b5c851af79 ("KVM: x86/xen: Add support for vCPU runstate information")
Signed-off-by: David Woodhouse <dwmw@...zon.co.uk>
Message-Id: <1b02a06421c17993df337493a68ba923f3bd5c0f.camel@...radead.org>
Signed-off-by: Paolo Bonzini <pbonzini@...hat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
---
arch/x86/include/asm/kvm_host.h | 2 +-
arch/x86/kvm/x86.c | 28 ++++++++++++++--------------
2 files changed, 15 insertions(+), 15 deletions(-)
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1084,7 +1084,7 @@ struct kvm_arch {
u64 cur_tsc_generation;
int nr_vcpus_matched_tsc;
- spinlock_t pvclock_gtod_sync_lock;
+ raw_spinlock_t pvclock_gtod_sync_lock;
bool use_master_clock;
u64 master_kernel_ns;
u64 master_cycle_now;
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2537,7 +2537,7 @@ static void kvm_synchronize_tsc(struct k
kvm_vcpu_write_tsc_offset(vcpu, offset);
raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
- spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags);
+ raw_spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags);
if (!matched) {
kvm->arch.nr_vcpus_matched_tsc = 0;
} else if (!already_matched) {
@@ -2545,7 +2545,7 @@ static void kvm_synchronize_tsc(struct k
}
kvm_track_tsc_matching(vcpu);
- spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags);
}
static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu,
@@ -2775,9 +2775,9 @@ static void kvm_gen_update_masterclock(s
kvm_make_mclock_inprogress_request(kvm);
/* no guest entries from this point */
- spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
pvclock_update_vm_gtod_copy(kvm);
- spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
kvm_for_each_vcpu(i, vcpu, kvm)
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
@@ -2795,15 +2795,15 @@ u64 get_kvmclock_ns(struct kvm *kvm)
unsigned long flags;
u64 ret;
- spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
if (!ka->use_master_clock) {
- spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
return get_kvmclock_base_ns() + ka->kvmclock_offset;
}
hv_clock.tsc_timestamp = ka->master_cycle_now;
hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset;
- spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
/* both __this_cpu_read() and rdtsc() should be on the same cpu */
get_cpu();
@@ -2897,13 +2897,13 @@ static int kvm_guest_time_update(struct
* If the host uses TSC clock, then passthrough TSC as stable
* to the guest.
*/
- spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
use_master_clock = ka->use_master_clock;
if (use_master_clock) {
host_tsc = ka->master_cycle_now;
kernel_ns = ka->master_kernel_ns;
}
- spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
/* Keep irq disabled to prevent changes to the clock */
local_irq_save(flags);
@@ -6101,13 +6101,13 @@ set_pit2_out:
* is slightly ahead) here we risk going negative on unsigned
* 'system_time' when 'user_ns.clock' is very small.
*/
- spin_lock_irq(&ka->pvclock_gtod_sync_lock);
+ raw_spin_lock_irq(&ka->pvclock_gtod_sync_lock);
if (kvm->arch.use_master_clock)
now_ns = ka->master_kernel_ns;
else
now_ns = get_kvmclock_base_ns();
ka->kvmclock_offset = user_ns.clock - now_ns;
- spin_unlock_irq(&ka->pvclock_gtod_sync_lock);
+ raw_spin_unlock_irq(&ka->pvclock_gtod_sync_lock);
kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE);
break;
@@ -8157,9 +8157,9 @@ static void kvm_hyperv_tsc_notifier(void
list_for_each_entry(kvm, &vm_list, vm_list) {
struct kvm_arch *ka = &kvm->arch;
- spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags);
pvclock_update_vm_gtod_copy(kvm);
- spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
+ raw_spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags);
kvm_for_each_vcpu(cpu, vcpu, kvm)
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
@@ -11148,7 +11148,7 @@ int kvm_arch_init_vm(struct kvm *kvm, un
raw_spin_lock_init(&kvm->arch.tsc_write_lock);
mutex_init(&kvm->arch.apic_map_lock);
- spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock);
+ raw_spin_lock_init(&kvm->arch.pvclock_gtod_sync_lock);
kvm->arch.kvmclock_offset = -get_kvmclock_base_ns();
pvclock_update_vm_gtod_copy(kvm);
Powered by blists - more mailing lists