* [PATCH 1/2] ptp_kvm: fix an infinite loop in ptp_kvm_get_time_fn when vm has more than 64 vcpus
2021-05-25 8:44 [PATCH 0/2] Fix ptp_kvm_get_time_fn infinite loop and remove redundant EXPORT_SYMBOL_GPL Chao Wu
@ 2021-05-25 8:44 ` Chao Wu
2021-05-25 8:44 ` [PATCH 2/2] pvclock: remove EXPORT_SYMBOL_GPL for pvclock_get_pvti_cpu0_va Chao Wu
2021-08-09 13:05 ` [PATCH 0/2] Fix ptp_kvm_get_time_fn infinite loop and remove redundant EXPORT_SYMBOL_GPL Chao Wu
2 siblings, 0 replies; 4+ messages in thread
From: Chao Wu @ 2021-05-25 8:44 UTC (permalink / raw)
To: Thomas Gleixner, Ingo Molnar, Borislav Petkov, Richard Cochran
Cc: x86, kvm, Chao Wu, Jiang Liu, Zha Bin
Commit 95a3d4454bb1 ("x86/kvmclock: Switch kvmclock data to a PER_CPU
variable") removes the static data array sized 64bytes * CONFIG_NR_CPUS
and uses a static page sized array to store pvclock data.
For the 64bytes * CONFIG_NR_CPUS size design, the address is consecutive
for all vcpus.
But for the static page sized array design, if page size is 4kB and
struct pvclock_vsyscall_time_info size is 64Byte (cache line aligned),
the maximum length of hv_clock_boot is 64.
For vcpus after 64, kernel will dynamically allocate pages for their
pvclock data in kvmclock_init_mem. So the address is not consecutive for
all vcpus.
Commit 95a3d4454bb1 ("x86/kvmclock: Switch kvmclock data to a PER_CPU
variable") uses per-cpu variable to store the pvclock_vsyscall_time_info
struct pointer to avoid the use of inconsecutive memory address. But
ptp_kvm_get_time_fn in ptp_kvm initiate hv_clock as the cpu0’s
pvclock_vsyscall_time_info virtual address and uses &hv_clock[cpu].pvti
to get specified cpu’s pvclock date. When the vcpu number is beyond 63,
&hv_clock[cpu].pvti will point to an incorrect virtual address and will
cause infinite loop in the following do while code area.
Commit 95a3d4454bb1 ("x86/kvmclock: Switch kvmclock data to a PER_CPU
variable") has removed all &hv_clock[cpu].pvti usage with per-cpu in kvmclock
but the revelant code in ptp_kvm was ignored.
We use this_cpu_pvti() to get pvclock data in ptp_kvm and put per-cpu
related declaration in kvmclock.c to kvmclock.h for ptp_kvm to use.
Signed-off-by: Chao Wu <chaowu@linux.alibaba.com>
Signed-off-by: Jiang Liu <gerry@linux.alibaba.com>
Signed-off-by: Zha Bin <zhabin@linux.alibaba.com>
---
arch/x86/include/asm/kvmclock.h | 16 ++++++++++++++++
arch/x86/kernel/kvmclock.c | 12 ++----------
drivers/ptp/ptp_kvm.c | 6 ++----
3 files changed, 20 insertions(+), 14 deletions(-)
diff --git a/arch/x86/include/asm/kvmclock.h b/arch/x86/include/asm/kvmclock.h
index eceea9299097..69b09839e199 100644
--- a/arch/x86/include/asm/kvmclock.h
+++ b/arch/x86/include/asm/kvmclock.h
@@ -2,6 +2,22 @@
#ifndef _ASM_X86_KVM_CLOCK_H
#define _ASM_X86_KVM_CLOCK_H
+#include <asm/pvclock.h>
+
extern struct clocksource kvm_clock;
+#ifdef CONFIG_KVM_GUEST
+DECLARE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
+
+static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void)
+{
+ return &this_cpu_read(hv_clock_per_cpu)->pvti;
+}
+
+static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void)
+{
+ return this_cpu_read(hv_clock_per_cpu);
+}
+
+#endif /* CONFIG_KVM_GUEST */
#endif /* _ASM_X86_KVM_CLOCK_H */
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 2ec202cb9dfd..006551cccdac 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -64,18 +64,10 @@ early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall);
static struct pvclock_vsyscall_time_info
hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __bss_decrypted __aligned(PAGE_SIZE);
static struct pvclock_wall_clock wall_clock __bss_decrypted;
-static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
static struct pvclock_vsyscall_time_info *hvclock_mem;
-static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void)
-{
- return &this_cpu_read(hv_clock_per_cpu)->pvti;
-}
-
-static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void)
-{
- return this_cpu_read(hv_clock_per_cpu);
-}
+DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
+EXPORT_PER_CPU_SYMBOL_GPL(hv_clock_per_cpu);
/*
* The wallclock is the time of day when we booted. Since then, some time may
diff --git a/drivers/ptp/ptp_kvm.c b/drivers/ptp/ptp_kvm.c
index c67dd11e08b1..985e3728016b 100644
--- a/drivers/ptp/ptp_kvm.c
+++ b/drivers/ptp/ptp_kvm.c
@@ -34,7 +34,6 @@ struct kvm_ptp_clock {
DEFINE_SPINLOCK(kvm_ptp_lock);
-static struct pvclock_vsyscall_time_info *hv_clock;
static struct kvm_clock_pairing clock_pair;
static phys_addr_t clock_pair_gpa;
@@ -53,7 +52,7 @@ static int ptp_kvm_get_time_fn(ktime_t *device_time,
preempt_disable_notrace();
cpu = smp_processor_id();
- src = &hv_clock[cpu].pvti;
+ src = this_cpu_pvti();
do {
/*
@@ -182,9 +181,8 @@ static int __init ptp_kvm_init(void)
return -ENODEV;
clock_pair_gpa = slow_virt_to_phys(&clock_pair);
- hv_clock = pvclock_get_pvti_cpu0_va();
- if (!hv_clock)
+ if (!this_cpu_pvti())
return -ENODEV;
ret = kvm_hypercall2(KVM_HC_CLOCK_PAIRING, clock_pair_gpa,
--
2.24.3 (Apple Git-128)
^ permalink raw reply related [flat|nested] 4+ messages in thread