Merge tag 'kvm-arm-for-4.4' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD
KVM/ARM Changes for v4.4-rc1
Includes a number of fixes for the arch-timer, introducing proper
level-triggered semantics for the arch-timers, a series of patches to
synchronously halt a guest (prerequisite for IRQ forwarding), some tracepoint
improvements, a tweak for the EL2 panic handlers, some more VGIC cleanups
getting rid of redundant state, and finally a stylistic change that gets rid of
some ctags warnings.
Conflicts:
arch/x86/include/asm/kvm_host.h
diff --git a/Documentation/virtual/kvm/arm/vgic-mapped-irqs.txt b/Documentation/virtual/kvm/arm/vgic-mapped-irqs.txt
new file mode 100644
index 0000000..38bca28
--- /dev/null
+++ b/Documentation/virtual/kvm/arm/vgic-mapped-irqs.txt
@@ -0,0 +1,187 @@
+KVM/ARM VGIC Forwarded Physical Interrupts
+==========================================
+
+The KVM/ARM code implements software support for the ARM Generic
+Interrupt Controller's (GIC's) hardware support for virtualization by
+allowing software to inject virtual interrupts to a VM, which the guest
+OS sees as regular interrupts. The code is famously known as the VGIC.
+
+Some of these virtual interrupts, however, correspond to physical
+interrupts from real physical devices. One example could be the
+architected timer, which itself supports virtualization, and therefore
+lets a guest OS program the hardware device directly to raise an
+interrupt at some point in time. When such an interrupt is raised, the
+host OS initially handles the interrupt and must somehow signal this
+event as a virtual interrupt to the guest. Another example could be a
+passthrough device, where the physical interrupts are initially handled
+by the host, but the device driver for the device lives in the guest OS
+and KVM must therefore somehow inject a virtual interrupt on behalf of
+the physical one to the guest OS.
+
+These virtual interrupts corresponding to a physical interrupt on the
+host are called forwarded physical interrupts, but are also sometimes
+referred to as 'virtualized physical interrupts' and 'mapped interrupts'.
+
+Forwarded physical interrupts are handled slightly differently compared
+to virtual interrupts generated purely by a software emulated device.
+
+
+The HW bit
+----------
+Virtual interrupts are signalled to the guest by programming the List
+Registers (LRs) on the GIC before running a VCPU. The LR is programmed
+with the virtual IRQ number and the state of the interrupt (Pending,
+Active, or Pending+Active). When the guest ACKs and EOIs a virtual
+interrupt, the LR state moves from Pending to Active, and finally to
+inactive.
+
+The LRs include an extra bit, called the HW bit. When this bit is set,
+KVM must also program an additional field in the LR, the physical IRQ
+number, to link the virtual with the physical IRQ.
+
+When the HW bit is set, KVM must EITHER set the Pending OR the Active
+bit, never both at the same time.
+
+Setting the HW bit causes the hardware to deactivate the physical
+interrupt on the physical distributor when the guest deactivates the
+corresponding virtual interrupt.
+
+
+Forwarded Physical Interrupts Life Cycle
+----------------------------------------
+
+The state of forwarded physical interrupts is managed in the following way:
+
+ - The physical interrupt is acked by the host, and becomes active on
+ the physical distributor (*).
+ - KVM sets the LR.Pending bit, because this is the only way the GICV
+ interface is going to present it to the guest.
+ - LR.Pending will stay set as long as the guest has not acked the interrupt.
+ - LR.Pending transitions to LR.Active on the guest read of the IAR, as
+ expected.
+ - On guest EOI, the *physical distributor* active bit gets cleared,
+ but the LR.Active is left untouched (set).
+ - KVM clears the LR on VM exits when the physical distributor
+ active state has been cleared.
+
+(*): The host handling is slightly more complicated. For some forwarded
+interrupts (shared), KVM directly sets the active state on the physical
+distributor before entering the guest, because the interrupt is never actually
+handled on the host (see details on the timer as an example below). For other
+forwarded interrupts (non-shared) the host does not deactivate the interrupt
+when the host ISR completes, but leaves the interrupt active until the guest
+deactivates it. Leaving the interrupt active is allowed, because Linux
+configures the physical GIC with EOIMode=1, which causes EOI operations to
+perform a priority drop allowing the GIC to receive other interrupts of the
+default priority.
+
+
+Forwarded Edge and Level Triggered PPIs and SPIs
+------------------------------------------------
+Forwarded physical interrupts injected should always be active on the
+physical distributor when injected to a guest.
+
+Level-triggered interrupts will keep the interrupt line to the GIC
+asserted, typically until the guest programs the device to deassert the
+line. This means that the interrupt will remain pending on the physical
+distributor until the guest has reprogrammed the device. Since we
+always run the VM with interrupts enabled on the CPU, a pending
+interrupt will exit the guest as soon as we switch into the guest,
+preventing the guest from ever making progress as the process repeats
+over and over. Therefore, the active state on the physical distributor
+must be set when entering the guest, preventing the GIC from forwarding
+the pending interrupt to the CPU. As soon as the guest deactivates the
+interrupt, the physical line is sampled by the hardware again and the host
+takes a new interrupt if and only if the physical line is still asserted.
+
+Edge-triggered interrupts do not exhibit the same problem with
+preventing guest execution that level-triggered interrupts do. One
+option is to not use HW bit at all, and inject edge-triggered interrupts
+from a physical device as pure virtual interrupts. But that would
+potentially slow down handling of the interrupt in the guest, because a
+physical interrupt occurring in the middle of the guest ISR would
+preempt the guest for the host to handle the interrupt. Additionally,
+if you configure the system to handle interrupts on a separate physical
+core from that running your VCPU, you still have to interrupt the VCPU
+to queue the pending state onto the LR, even though the guest won't use
+this information until the guest ISR completes. Therefore, the HW
+bit should always be set for forwarded edge-triggered interrupts. With
+the HW bit set, the virtual interrupt is injected and additional
+physical interrupts occurring before the guest deactivates the interrupt
+simply mark the state on the physical distributor as Pending+Active. As
+soon as the guest deactivates the interrupt, the host takes another
+interrupt if and only if there was a physical interrupt between injecting
+the forwarded interrupt to the guest and the guest deactivating the
+interrupt.
+
+Consequently, whenever we schedule a VCPU with one or more LRs with the
+HW bit set, the interrupt must also be active on the physical
+distributor.
+
+
+Forwarded LPIs
+--------------
+LPIs, introduced in GICv3, are always edge-triggered and do not have an
+active state. They become pending when a device signal them, and as
+soon as they are acked by the CPU, they are inactive again.
+
+It therefore doesn't make sense, and is not supported, to set the HW bit
+for physical LPIs that are forwarded to a VM as virtual interrupts,
+typically virtual SPIs.
+
+For LPIs, there is no other choice than to preempt the VCPU thread if
+necessary, and queue the pending state onto the LR.
+
+
+Putting It Together: The Architected Timer
+------------------------------------------
+The architected timer is a device that signals interrupts with level
+triggered semantics. The timer hardware is directly accessed by VCPUs
+which program the timer to fire at some point in time. Each VCPU on a
+system programs the timer to fire at different times, and therefore the
+hardware is multiplexed between multiple VCPUs. This is implemented by
+context-switching the timer state along with each VCPU thread.
+
+However, this means that a scenario like the following is entirely
+possible, and in fact, typical:
+
+1. KVM runs the VCPU
+2. The guest programs the time to fire in T+100
+3. The guest is idle and calls WFI (wait-for-interrupts)
+4. The hardware traps to the host
+5. KVM stores the timer state to memory and disables the hardware timer
+6. KVM schedules a soft timer to fire in T+(100 - time since step 2)
+7. KVM puts the VCPU thread to sleep (on a waitqueue)
+8. The soft timer fires, waking up the VCPU thread
+9. KVM reprograms the timer hardware with the VCPU's values
+10. KVM marks the timer interrupt as active on the physical distributor
+11. KVM injects a forwarded physical interrupt to the guest
+12. KVM runs the VCPU
+
+Notice that KVM injects a forwarded physical interrupt in step 11 without
+the corresponding interrupt having actually fired on the host. That is
+exactly why we mark the timer interrupt as active in step 10, because
+the active state on the physical distributor is part of the state
+belonging to the timer hardware, which is context-switched along with
+the VCPU thread.
+
+If the guest does not idle because it is busy, the flow looks like this
+instead:
+
+1. KVM runs the VCPU
+2. The guest programs the time to fire in T+100
+4. At T+100 the timer fires and a physical IRQ causes the VM to exit
+ (note that this initially only traps to EL2 and does not run the host ISR
+ until KVM has returned to the host).
+5. With interrupts still disabled on the CPU coming back from the guest, KVM
+ stores the virtual timer state to memory and disables the virtual hw timer.
+6. KVM looks at the timer state (in memory) and injects a forwarded physical
+ interrupt because it concludes the timer has expired.
+7. KVM marks the timer interrupt as active on the physical distributor
+7. KVM enables the timer, enables interrupts, and runs the VCPU
+
+Notice that again the forwarded physical interrupt is injected to the
+guest without having actually been handled on the host. In this case it
+is because the physical interrupt is never actually seen by the host because the
+timer is disabled upon guest return, and the virtual forwarded interrupt is
+injected on the KVM guest entry path.
diff --git a/Documentation/virtual/kvm/devices/arm-vgic.txt b/Documentation/virtual/kvm/devices/arm-vgic.txt
index 3fb9054..59541d4 100644
--- a/Documentation/virtual/kvm/devices/arm-vgic.txt
+++ b/Documentation/virtual/kvm/devices/arm-vgic.txt
@@ -44,28 +44,29 @@
Attributes:
The attr field of kvm_device_attr encodes two values:
bits: | 63 .... 40 | 39 .. 32 | 31 .... 0 |
- values: | reserved | cpu id | offset |
+ values: | reserved | vcpu_index | offset |
All distributor regs are (rw, 32-bit)
The offset is relative to the "Distributor base address" as defined in the
GICv2 specs. Getting or setting such a register has the same effect as
- reading or writing the register on the actual hardware from the cpu
- specified with cpu id field. Note that most distributor fields are not
- banked, but return the same value regardless of the cpu id used to access
- the register.
+ reading or writing the register on the actual hardware from the cpu whose
+ index is specified with the vcpu_index field. Note that most distributor
+ fields are not banked, but return the same value regardless of the
+ vcpu_index used to access the register.
Limitations:
- Priorities are not implemented, and registers are RAZ/WI
- Currently only implemented for KVM_DEV_TYPE_ARM_VGIC_V2.
Errors:
- -ENODEV: Getting or setting this register is not yet supported
+ -ENXIO: Getting or setting this register is not yet supported
-EBUSY: One or more VCPUs are running
+ -EINVAL: Invalid vcpu_index supplied
KVM_DEV_ARM_VGIC_GRP_CPU_REGS
Attributes:
The attr field of kvm_device_attr encodes two values:
bits: | 63 .... 40 | 39 .. 32 | 31 .... 0 |
- values: | reserved | cpu id | offset |
+ values: | reserved | vcpu_index | offset |
All CPU interface regs are (rw, 32-bit)
@@ -91,8 +92,9 @@
- Priorities are not implemented, and registers are RAZ/WI
- Currently only implemented for KVM_DEV_TYPE_ARM_VGIC_V2.
Errors:
- -ENODEV: Getting or setting this register is not yet supported
+ -ENXIO: Getting or setting this register is not yet supported
-EBUSY: One or more VCPUs are running
+ -EINVAL: Invalid vcpu_index supplied
KVM_DEV_ARM_VGIC_GRP_NR_IRQS
Attributes:
diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h
index d995821..dc641dd 100644
--- a/arch/arm/include/asm/kvm_arm.h
+++ b/arch/arm/include/asm/kvm_arm.h
@@ -218,4 +218,24 @@
#define HSR_DABT_CM (1U << 8)
#define HSR_DABT_EA (1U << 9)
+#define kvm_arm_exception_type \
+ {0, "RESET" }, \
+ {1, "UNDEFINED" }, \
+ {2, "SOFTWARE" }, \
+ {3, "PREF_ABORT" }, \
+ {4, "DATA_ABORT" }, \
+ {5, "IRQ" }, \
+ {6, "FIQ" }, \
+ {7, "HVC" }
+
+#define HSRECN(x) { HSR_EC_##x, #x }
+
+#define kvm_arm_exception_class \
+ HSRECN(UNKNOWN), HSRECN(WFI), HSRECN(CP15_32), HSRECN(CP15_64), \
+ HSRECN(CP14_MR), HSRECN(CP14_LS), HSRECN(CP_0_13), HSRECN(CP10_ID), \
+ HSRECN(JAZELLE), HSRECN(BXJ), HSRECN(CP14_64), HSRECN(SVC_HYP), \
+ HSRECN(HVC), HSRECN(SMC), HSRECN(IABT), HSRECN(IABT_HYP), \
+ HSRECN(DABT), HSRECN(DABT_HYP)
+
+
#endif /* __ARM_KVM_ARM_H__ */
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index c4072d9..6692982 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -126,7 +126,10 @@
* here.
*/
- /* Don't run the guest on this vcpu */
+ /* vcpu power-off state */
+ bool power_off;
+
+ /* Don't run the guest (internal implementation need) */
bool pause;
/* IO related fields */
diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index 210ecca..95a0005 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -21,6 +21,7 @@
depends on MMU && OF
select PREEMPT_NOTIFIERS
select ANON_INODES
+ select ARM_GIC
select HAVE_KVM_CPU_RELAX_INTERCEPT
select HAVE_KVM_ARCH_TLB_FLUSH_ALL
select KVM_MMIO
@@ -45,4 +46,6 @@
---help---
Provides host support for ARM processors.
+source drivers/vhost/Kconfig
+
endif # VIRTUALIZATION
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index dc017ad..eab83b2 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -271,6 +271,16 @@
return kvm_timer_should_fire(vcpu);
}
+void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
+{
+ kvm_timer_schedule(vcpu);
+}
+
+void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
+{
+ kvm_timer_unschedule(vcpu);
+}
+
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
/* Force users to call KVM_ARM_VCPU_INIT */
@@ -308,7 +318,7 @@
int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
struct kvm_mp_state *mp_state)
{
- if (vcpu->arch.pause)
+ if (vcpu->arch.power_off)
mp_state->mp_state = KVM_MP_STATE_STOPPED;
else
mp_state->mp_state = KVM_MP_STATE_RUNNABLE;
@@ -321,10 +331,10 @@
{
switch (mp_state->mp_state) {
case KVM_MP_STATE_RUNNABLE:
- vcpu->arch.pause = false;
+ vcpu->arch.power_off = false;
break;
case KVM_MP_STATE_STOPPED:
- vcpu->arch.pause = true;
+ vcpu->arch.power_off = true;
break;
default:
return -EINVAL;
@@ -342,7 +352,8 @@
*/
int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
{
- return !!v->arch.irq_lines || kvm_vgic_vcpu_pending_irq(v);
+ return ((!!v->arch.irq_lines || kvm_vgic_vcpu_pending_irq(v))
+ && !v->arch.power_off && !v->arch.pause);
}
/* Just ensure a guest exit from a particular CPU */
@@ -468,11 +479,38 @@
return vgic_initialized(kvm);
}
-static void vcpu_pause(struct kvm_vcpu *vcpu)
+static void kvm_arm_halt_guest(struct kvm *kvm) __maybe_unused;
+static void kvm_arm_resume_guest(struct kvm *kvm) __maybe_unused;
+
+static void kvm_arm_halt_guest(struct kvm *kvm)
+{
+ int i;
+ struct kvm_vcpu *vcpu;
+
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ vcpu->arch.pause = true;
+ force_vm_exit(cpu_all_mask);
+}
+
+static void kvm_arm_resume_guest(struct kvm *kvm)
+{
+ int i;
+ struct kvm_vcpu *vcpu;
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu);
+
+ vcpu->arch.pause = false;
+ wake_up_interruptible(wq);
+ }
+}
+
+static void vcpu_sleep(struct kvm_vcpu *vcpu)
{
wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu);
- wait_event_interruptible(*wq, !vcpu->arch.pause);
+ wait_event_interruptible(*wq, ((!vcpu->arch.power_off) &&
+ (!vcpu->arch.pause)));
}
static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu)
@@ -522,8 +560,8 @@
update_vttbr(vcpu->kvm);
- if (vcpu->arch.pause)
- vcpu_pause(vcpu);
+ if (vcpu->arch.power_off || vcpu->arch.pause)
+ vcpu_sleep(vcpu);
/*
* Disarming the background timer must be done in a
@@ -549,11 +587,12 @@
run->exit_reason = KVM_EXIT_INTR;
}
- if (ret <= 0 || need_new_vmid_gen(vcpu->kvm)) {
+ if (ret <= 0 || need_new_vmid_gen(vcpu->kvm) ||
+ vcpu->arch.power_off || vcpu->arch.pause) {
local_irq_enable();
+ kvm_timer_sync_hwstate(vcpu);
kvm_vgic_sync_hwstate(vcpu);
preempt_enable();
- kvm_timer_sync_hwstate(vcpu);
continue;
}
@@ -596,14 +635,19 @@
* guest time.
*/
kvm_guest_exit();
- trace_kvm_exit(kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
+ trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));
+
+ /*
+ * We must sync the timer state before the vgic state so that
+ * the vgic can properly sample the updated state of the
+ * interrupt line.
+ */
+ kvm_timer_sync_hwstate(vcpu);
kvm_vgic_sync_hwstate(vcpu);
preempt_enable();
- kvm_timer_sync_hwstate(vcpu);
-
ret = handle_exit(vcpu, run, ret);
}
@@ -765,12 +809,12 @@
vcpu_reset_hcr(vcpu);
/*
- * Handle the "start in power-off" case by marking the VCPU as paused.
+ * Handle the "start in power-off" case.
*/
if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features))
- vcpu->arch.pause = true;
+ vcpu->arch.power_off = true;
else
- vcpu->arch.pause = false;
+ vcpu->arch.power_off = false;
return 0;
}
@@ -1080,7 +1124,7 @@
*/
err = kvm_timer_hyp_init();
if (err)
- goto out_free_mappings;
+ goto out_free_context;
#ifndef CONFIG_HOTPLUG_CPU
free_boot_hyp_pgd();
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index ad6f642..0b55696 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -63,7 +63,7 @@
static void kvm_psci_vcpu_off(struct kvm_vcpu *vcpu)
{
- vcpu->arch.pause = true;
+ vcpu->arch.power_off = true;
}
static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
@@ -87,7 +87,7 @@
*/
if (!vcpu)
return PSCI_RET_INVALID_PARAMS;
- if (!vcpu->arch.pause) {
+ if (!vcpu->arch.power_off) {
if (kvm_psci_version(source_vcpu) != KVM_ARM_PSCI_0_1)
return PSCI_RET_ALREADY_ON;
else
@@ -115,7 +115,7 @@
* the general puspose registers are undefined upon CPU_ON.
*/
*vcpu_reg(vcpu, 0) = context_id;
- vcpu->arch.pause = false;
+ vcpu->arch.power_off = false;
smp_mb(); /* Make sure the above is visible */
wq = kvm_arch_vcpu_wq(vcpu);
@@ -153,7 +153,7 @@
mpidr = kvm_vcpu_get_mpidr_aff(tmp);
if ((mpidr & target_affinity_mask) == target_affinity) {
matching_cpus++;
- if (!tmp->arch.pause)
+ if (!tmp->arch.power_off)
return PSCI_0_2_AFFINITY_LEVEL_ON;
}
}
@@ -179,7 +179,7 @@
* re-initialized.
*/
kvm_for_each_vcpu(i, tmp, vcpu->kvm) {
- tmp->arch.pause = true;
+ tmp->arch.power_off = true;
kvm_vcpu_kick(tmp);
}
diff --git a/arch/arm/kvm/trace.h b/arch/arm/kvm/trace.h
index 0ec3539..c25a885 100644
--- a/arch/arm/kvm/trace.h
+++ b/arch/arm/kvm/trace.h
@@ -25,21 +25,25 @@
);
TRACE_EVENT(kvm_exit,
- TP_PROTO(unsigned int exit_reason, unsigned long vcpu_pc),
- TP_ARGS(exit_reason, vcpu_pc),
+ TP_PROTO(int idx, unsigned int exit_reason, unsigned long vcpu_pc),
+ TP_ARGS(idx, exit_reason, vcpu_pc),
TP_STRUCT__entry(
+ __field( int, idx )
__field( unsigned int, exit_reason )
__field( unsigned long, vcpu_pc )
),
TP_fast_assign(
+ __entry->idx = idx;
__entry->exit_reason = exit_reason;
__entry->vcpu_pc = vcpu_pc;
),
- TP_printk("HSR_EC: 0x%04x, PC: 0x%08lx",
+ TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%08lx",
+ __print_symbolic(__entry->idx, kvm_arm_exception_type),
__entry->exit_reason,
+ __print_symbolic(__entry->exit_reason, kvm_arm_exception_class),
__entry->vcpu_pc)
);
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 9694f26..5e6857b 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -200,4 +200,20 @@
/* Hyp Prefetch Fault Address Register (HPFAR/HDFAR) */
#define HPFAR_MASK (~UL(0xf))
+#define kvm_arm_exception_type \
+ {0, "IRQ" }, \
+ {1, "TRAP" }
+
+#define ECN(x) { ESR_ELx_EC_##x, #x }
+
+#define kvm_arm_exception_class \
+ ECN(UNKNOWN), ECN(WFx), ECN(CP15_32), ECN(CP15_64), ECN(CP14_MR), \
+ ECN(CP14_LS), ECN(FP_ASIMD), ECN(CP10_ID), ECN(CP14_64), ECN(SVC64), \
+ ECN(HVC64), ECN(SMC64), ECN(SYS64), ECN(IMP_DEF), ECN(IABT_LOW), \
+ ECN(IABT_CUR), ECN(PC_ALIGN), ECN(DABT_LOW), ECN(DABT_CUR), \
+ ECN(SP_ALIGN), ECN(FP_EXC32), ECN(FP_EXC64), ECN(SERROR), \
+ ECN(BREAKPT_LOW), ECN(BREAKPT_CUR), ECN(SOFTSTP_LOW), \
+ ECN(SOFTSTP_CUR), ECN(WATCHPT_LOW), ECN(WATCHPT_CUR), \
+ ECN(BKPT32), ECN(VECTOR32), ECN(BRK64)
+
#endif /* __ARM64_KVM_ARM_H__ */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index ed03968..a35ce72 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -149,7 +149,10 @@
u32 mdscr_el1;
} guest_debug_preserved;
- /* Don't run the guest */
+ /* vcpu power-off state */
+ bool power_off;
+
+ /* Don't run the guest (internal implementation need) */
bool pause;
/* IO related fields */
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 5c7e920e..38102f5 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -41,4 +41,6 @@
---help---
Provides host support for ARM processors.
+source drivers/vhost/Kconfig
+
endif # VIRTUALIZATION
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index e583613..1599701 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -880,6 +880,14 @@
bl __restore_sysregs
+ /*
+ * Make sure we have a valid host stack, and don't leave junk in the
+ * frame pointer that will give us a misleading host stack unwinding.
+ */
+ ldr x22, [x2, #CPU_GP_REG_OFFSET(CPU_SP_EL1)]
+ msr sp_el1, x22
+ mov x29, xzr
+
1: adr x0, __hyp_panic_str
adr x1, 2f
ldp x2, x3, [x1]
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index 5a1a882..6ded8d3 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -847,5 +847,7 @@
struct kvm_memory_slot *slot) {}
static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
+static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
#endif /* __MIPS_KVM_HOST_H__ */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 827a38d..c9f122d 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -718,5 +718,7 @@
static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {}
static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
static inline void kvm_arch_exit(void) {}
+static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
#endif /* __POWERPC_KVM_HOST_H__ */
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 8ced426..72a614c 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -644,5 +644,7 @@
static inline void kvm_arch_flush_shadow_all(struct kvm *kvm) {}
static inline void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
struct kvm_memory_slot *slot) {}
+static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
#endif
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 53deb27..9265196 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1261,4 +1261,8 @@
void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e,
struct kvm_lapic_irq *irq);
+
+static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
+
#endif /* _ASM_X86_KVM_HOST_H */
diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index e1e4d7c..1800227 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -51,7 +51,7 @@
bool armed;
/* Timer IRQ */
- const struct kvm_irq_level *irq;
+ struct kvm_irq_level irq;
/* VGIC mapping */
struct irq_phys_map *map;
@@ -71,5 +71,7 @@
int kvm_arm_timer_set_reg(struct kvm_vcpu *, u64 regid, u64 value);
bool kvm_timer_should_fire(struct kvm_vcpu *vcpu);
+void kvm_timer_schedule(struct kvm_vcpu *vcpu);
+void kvm_timer_unschedule(struct kvm_vcpu *vcpu);
#endif
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 4e14dac..f62addc 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -112,7 +112,6 @@
struct vgic_ops {
struct vgic_lr (*get_lr)(const struct kvm_vcpu *, int);
void (*set_lr)(struct kvm_vcpu *, int, struct vgic_lr);
- void (*sync_lr_elrsr)(struct kvm_vcpu *, int, struct vgic_lr);
u64 (*get_elrsr)(const struct kvm_vcpu *vcpu);
u64 (*get_eisr)(const struct kvm_vcpu *vcpu);
void (*clear_eisr)(struct kvm_vcpu *vcpu);
@@ -159,7 +158,6 @@
u32 virt_irq;
u32 phys_irq;
u32 irq;
- bool active;
};
struct irq_phys_map_entry {
@@ -296,22 +294,16 @@
};
struct vgic_cpu {
- /* per IRQ to LR mapping */
- u8 *vgic_irq_lr_map;
-
/* Pending/active/both interrupts on this VCPU */
- DECLARE_BITMAP( pending_percpu, VGIC_NR_PRIVATE_IRQS);
- DECLARE_BITMAP( active_percpu, VGIC_NR_PRIVATE_IRQS);
- DECLARE_BITMAP( pend_act_percpu, VGIC_NR_PRIVATE_IRQS);
+ DECLARE_BITMAP(pending_percpu, VGIC_NR_PRIVATE_IRQS);
+ DECLARE_BITMAP(active_percpu, VGIC_NR_PRIVATE_IRQS);
+ DECLARE_BITMAP(pend_act_percpu, VGIC_NR_PRIVATE_IRQS);
/* Pending/active/both shared interrupts, dynamically sized */
unsigned long *pending_shared;
unsigned long *active_shared;
unsigned long *pend_act_shared;
- /* Bitmap of used/free list registers */
- DECLARE_BITMAP( lr_used, VGIC_V2_MAX_LRS);
-
/* Number of list registers on this CPU */
int nr_lr;
@@ -354,8 +346,6 @@
struct irq_phys_map *kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu,
int virt_irq, int irq);
int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, struct irq_phys_map *map);
-bool kvm_vgic_get_phys_irq_active(struct irq_phys_map *map);
-void kvm_vgic_set_phys_irq_active(struct irq_phys_map *map, bool active);
#define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel))
#define vgic_initialized(k) (!!((k)->arch.vgic.nr_cpus))
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index eba9cae..87189a4 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -647,6 +647,8 @@
void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn);
void kvm_vcpu_block(struct kvm_vcpu *vcpu);
+void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu);
+void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu);
void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
int kvm_vcpu_yield_to(struct kvm_vcpu *target);
void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu);
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 48c6e1a..21a0ab2 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -28,6 +28,8 @@
#include <kvm/arm_vgic.h>
#include <kvm/arm_arch_timer.h>
+#include "trace.h"
+
static struct timecounter *timecounter;
static struct workqueue_struct *wqueue;
static unsigned int host_vtimer_irq;
@@ -59,18 +61,6 @@
}
}
-static void kvm_timer_inject_irq(struct kvm_vcpu *vcpu)
-{
- int ret;
- struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
-
- kvm_vgic_set_phys_irq_active(timer->map, true);
- ret = kvm_vgic_inject_mapped_irq(vcpu->kvm, vcpu->vcpu_id,
- timer->map,
- timer->irq->level);
- WARN_ON(ret);
-}
-
static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id)
{
struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)dev_id;
@@ -111,14 +101,20 @@
return HRTIMER_NORESTART;
}
+static bool kvm_timer_irq_can_fire(struct kvm_vcpu *vcpu)
+{
+ struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+
+ return !(timer->cntv_ctl & ARCH_TIMER_CTRL_IT_MASK) &&
+ (timer->cntv_ctl & ARCH_TIMER_CTRL_ENABLE);
+}
+
bool kvm_timer_should_fire(struct kvm_vcpu *vcpu)
{
struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
cycle_t cval, now;
- if ((timer->cntv_ctl & ARCH_TIMER_CTRL_IT_MASK) ||
- !(timer->cntv_ctl & ARCH_TIMER_CTRL_ENABLE) ||
- kvm_vgic_get_phys_irq_active(timer->map))
+ if (!kvm_timer_irq_can_fire(vcpu))
return false;
cval = timer->cntv_cval;
@@ -127,62 +123,143 @@
return cval <= now;
}
-/**
- * kvm_timer_flush_hwstate - prepare to move the virt timer to the cpu
- * @vcpu: The vcpu pointer
- *
- * Disarm any pending soft timers, since the world-switch code will write the
- * virtual timer state back to the physical CPU.
+static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level)
+{
+ int ret;
+ struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+
+ BUG_ON(!vgic_initialized(vcpu->kvm));
+
+ timer->irq.level = new_level;
+ trace_kvm_timer_update_irq(vcpu->vcpu_id, timer->map->virt_irq,
+ timer->irq.level);
+ ret = kvm_vgic_inject_mapped_irq(vcpu->kvm, vcpu->vcpu_id,
+ timer->map,
+ timer->irq.level);
+ WARN_ON(ret);
+}
+
+/*
+ * Check if there was a change in the timer state (should we raise or lower
+ * the line level to the GIC).
*/
-void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu)
+static void kvm_timer_update_state(struct kvm_vcpu *vcpu)
{
struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
/*
- * We're about to run this vcpu again, so there is no need to
- * keep the background timer running, as we're about to
- * populate the CPU timer again.
+ * If userspace modified the timer registers via SET_ONE_REG before
+ * the vgic was initialized, we mustn't set the timer->irq.level value
+ * because the guest would never see the interrupt. Instead wait
+ * until we call this function from kvm_timer_flush_hwstate.
*/
- timer_disarm(timer);
+ if (!vgic_initialized(vcpu->kvm))
+ return;
+
+ if (kvm_timer_should_fire(vcpu) != timer->irq.level)
+ kvm_timer_update_irq(vcpu, !timer->irq.level);
+}
+
+/*
+ * Schedule the background timer before calling kvm_vcpu_block, so that this
+ * thread is removed from its waitqueue and made runnable when there's a timer
+ * interrupt to handle.
+ */
+void kvm_timer_schedule(struct kvm_vcpu *vcpu)
+{
+ struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+ u64 ns;
+ cycle_t cval, now;
+
+ BUG_ON(timer_is_armed(timer));
/*
- * If the timer expired while we were not scheduled, now is the time
- * to inject it.
+ * No need to schedule a background timer if the guest timer has
+ * already expired, because kvm_vcpu_block will return before putting
+ * the thread to sleep.
*/
if (kvm_timer_should_fire(vcpu))
- kvm_timer_inject_irq(vcpu);
+ return;
+
+ /*
+ * If the timer is not capable of raising interrupts (disabled or
+ * masked), then there's no more work for us to do.
+ */
+ if (!kvm_timer_irq_can_fire(vcpu))
+ return;
+
+ /* The timer has not yet expired, schedule a background timer */
+ cval = timer->cntv_cval;
+ now = kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff;
+
+ ns = cyclecounter_cyc2ns(timecounter->cc,
+ cval - now,
+ timecounter->mask,
+ &timecounter->frac);
+ timer_arm(timer, ns);
+}
+
+void kvm_timer_unschedule(struct kvm_vcpu *vcpu)
+{
+ struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+ timer_disarm(timer);
+}
+
+/**
+ * kvm_timer_flush_hwstate - prepare to move the virt timer to the cpu
+ * @vcpu: The vcpu pointer
+ *
+ * Check if the virtual timer has expired while we were running in the host,
+ * and inject an interrupt if that was the case.
+ */
+void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu)
+{
+ struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
+ bool phys_active;
+ int ret;
+
+ kvm_timer_update_state(vcpu);
+
+ /*
+ * If we enter the guest with the virtual input level to the VGIC
+ * asserted, then we have already told the VGIC what we need to, and
+ * we don't need to exit from the guest until the guest deactivates
+ * the already injected interrupt, so therefore we should set the
+ * hardware active state to prevent unnecessary exits from the guest.
+ *
+ * Conversely, if the virtual input level is deasserted, then always
+ * clear the hardware active state to ensure that hardware interrupts
+ * from the timer triggers a guest exit.
+ */
+ if (timer->irq.level)
+ phys_active = true;
+ else
+ phys_active = false;
+
+ ret = irq_set_irqchip_state(timer->map->irq,
+ IRQCHIP_STATE_ACTIVE,
+ phys_active);
+ WARN_ON(ret);
}
/**
* kvm_timer_sync_hwstate - sync timer state from cpu
* @vcpu: The vcpu pointer
*
- * Check if the virtual timer was armed and either schedule a corresponding
- * soft timer or inject directly if already expired.
+ * Check if the virtual timer has expired while we were running in the guest,
+ * and inject an interrupt if that was the case.
*/
void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu)
{
struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
- cycle_t cval, now;
- u64 ns;
BUG_ON(timer_is_armed(timer));
- if (kvm_timer_should_fire(vcpu)) {
- /*
- * Timer has already expired while we were not
- * looking. Inject the interrupt and carry on.
- */
- kvm_timer_inject_irq(vcpu);
- return;
- }
-
- cval = timer->cntv_cval;
- now = kvm_phys_timer_read() - vcpu->kvm->arch.timer.cntvoff;
-
- ns = cyclecounter_cyc2ns(timecounter->cc, cval - now, timecounter->mask,
- &timecounter->frac);
- timer_arm(timer, ns);
+ /*
+ * The guest could have modified the timer registers or the timer
+ * could have expired, update the timer state.
+ */
+ kvm_timer_update_state(vcpu);
}
int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu,
@@ -197,7 +274,7 @@
* kvm_vcpu_set_target(). To handle this, we determine
* vcpu timer irq number when the vcpu is reset.
*/
- timer->irq = irq;
+ timer->irq.irq = irq->irq;
/*
* The bits in CNTV_CTL are architecturally reset to UNKNOWN for ARMv8
@@ -206,6 +283,7 @@
* the ARMv7 architecture.
*/
timer->cntv_ctl = 0;
+ kvm_timer_update_state(vcpu);
/*
* Tell the VGIC that the virtual interrupt is tied to a
@@ -250,6 +328,8 @@
default:
return -1;
}
+
+ kvm_timer_update_state(vcpu);
return 0;
}
diff --git a/virt/kvm/arm/trace.h b/virt/kvm/arm/trace.h
new file mode 100644
index 0000000..37d8b98
--- /dev/null
+++ b/virt/kvm/arm/trace.h
@@ -0,0 +1,63 @@
+#if !defined(_TRACE_KVM_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_KVM_H
+
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kvm
+
+/*
+ * Tracepoints for vgic
+ */
+TRACE_EVENT(vgic_update_irq_pending,
+ TP_PROTO(unsigned long vcpu_id, __u32 irq, bool level),
+ TP_ARGS(vcpu_id, irq, level),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, vcpu_id )
+ __field( __u32, irq )
+ __field( bool, level )
+ ),
+
+ TP_fast_assign(
+ __entry->vcpu_id = vcpu_id;
+ __entry->irq = irq;
+ __entry->level = level;
+ ),
+
+ TP_printk("VCPU: %ld, IRQ %d, level: %d",
+ __entry->vcpu_id, __entry->irq, __entry->level)
+);
+
+/*
+ * Tracepoints for arch_timer
+ */
+TRACE_EVENT(kvm_timer_update_irq,
+ TP_PROTO(unsigned long vcpu_id, __u32 irq, int level),
+ TP_ARGS(vcpu_id, irq, level),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, vcpu_id )
+ __field( __u32, irq )
+ __field( int, level )
+ ),
+
+ TP_fast_assign(
+ __entry->vcpu_id = vcpu_id;
+ __entry->irq = irq;
+ __entry->level = level;
+ ),
+
+ TP_printk("VCPU: %ld, IRQ %d, level %d",
+ __entry->vcpu_id, __entry->irq, __entry->level)
+);
+
+#endif /* _TRACE_KVM_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH ../../../virt/kvm/arm
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/virt/kvm/arm/vgic-v2.c b/virt/kvm/arm/vgic-v2.c
index 8d7b04d..ff02f08 100644
--- a/virt/kvm/arm/vgic-v2.c
+++ b/virt/kvm/arm/vgic-v2.c
@@ -79,11 +79,7 @@
lr_val |= (lr_desc.source << GICH_LR_PHYSID_CPUID_SHIFT);
vcpu->arch.vgic_cpu.vgic_v2.vgic_lr[lr] = lr_val;
-}
-static void vgic_v2_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr,
- struct vgic_lr lr_desc)
-{
if (!(lr_desc.state & LR_STATE_MASK))
vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr |= (1ULL << lr);
else
@@ -158,6 +154,7 @@
* anyway.
*/
vcpu->arch.vgic_cpu.vgic_v2.vgic_vmcr = 0;
+ vcpu->arch.vgic_cpu.vgic_v2.vgic_elrsr = ~0;
/* Get the show on the road... */
vcpu->arch.vgic_cpu.vgic_v2.vgic_hcr = GICH_HCR_EN;
@@ -166,7 +163,6 @@
static const struct vgic_ops vgic_v2_ops = {
.get_lr = vgic_v2_get_lr,
.set_lr = vgic_v2_set_lr,
- .sync_lr_elrsr = vgic_v2_sync_lr_elrsr,
.get_elrsr = vgic_v2_get_elrsr,
.get_eisr = vgic_v2_get_eisr,
.clear_eisr = vgic_v2_clear_eisr,
diff --git a/virt/kvm/arm/vgic-v3.c b/virt/kvm/arm/vgic-v3.c
index 7dd5d62..487d635 100644
--- a/virt/kvm/arm/vgic-v3.c
+++ b/virt/kvm/arm/vgic-v3.c
@@ -112,11 +112,7 @@
}
vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[LR_INDEX(lr)] = lr_val;
-}
-static void vgic_v3_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr,
- struct vgic_lr lr_desc)
-{
if (!(lr_desc.state & LR_STATE_MASK))
vcpu->arch.vgic_cpu.vgic_v3.vgic_elrsr |= (1U << lr);
else
@@ -193,6 +189,7 @@
* anyway.
*/
vgic_v3->vgic_vmcr = 0;
+ vgic_v3->vgic_elrsr = ~0;
/*
* If we are emulating a GICv3, we do it in an non-GICv2-compatible
@@ -211,7 +208,6 @@
static const struct vgic_ops vgic_v3_ops = {
.get_lr = vgic_v3_get_lr,
.set_lr = vgic_v3_set_lr,
- .sync_lr_elrsr = vgic_v3_sync_lr_elrsr,
.get_elrsr = vgic_v3_get_elrsr,
.get_eisr = vgic_v3_get_eisr,
.clear_eisr = vgic_v3_clear_eisr,
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 6bd1c9b..fe451d4 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -34,6 +34,9 @@
#include <asm/kvm.h>
#include <kvm/iodev.h>
+#define CREATE_TRACE_POINTS
+#include "trace.h"
+
/*
* How the whole thing works (courtesy of Christoffer Dall):
*
@@ -102,11 +105,13 @@
#include "vgic.h"
static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu);
-static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu);
+static void vgic_retire_lr(int lr_nr, struct kvm_vcpu *vcpu);
static struct vgic_lr vgic_get_lr(const struct kvm_vcpu *vcpu, int lr);
static void vgic_set_lr(struct kvm_vcpu *vcpu, int lr, struct vgic_lr lr_desc);
+static u64 vgic_get_elrsr(struct kvm_vcpu *vcpu);
static struct irq_phys_map *vgic_irq_map_search(struct kvm_vcpu *vcpu,
int virt_irq);
+static int compute_pending_for_cpu(struct kvm_vcpu *vcpu);
static const struct vgic_ops *vgic_ops;
static const struct vgic_params *vgic;
@@ -357,6 +362,11 @@
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
vgic_bitmap_set_irq_val(&dist->irq_soft_pend, vcpu->vcpu_id, irq, 0);
+ if (!vgic_dist_irq_get_level(vcpu, irq)) {
+ vgic_dist_irq_clear_pending(vcpu, irq);
+ if (!compute_pending_for_cpu(vcpu))
+ clear_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu);
+ }
}
static int vgic_dist_irq_is_pending(struct kvm_vcpu *vcpu, int irq)
@@ -654,10 +664,9 @@
vgic_reg_access(mmio, &val, offset,
ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
if (mmio->is_write) {
- if (offset < 8) {
- *reg = ~0U; /* Force PPIs/SGIs to 1 */
+ /* Ignore writes to read-only SGI and PPI bits */
+ if (offset < 8)
return false;
- }
val = vgic_cfg_compress(val);
if (offset & 4) {
@@ -683,9 +692,11 @@
void vgic_unqueue_irqs(struct kvm_vcpu *vcpu)
{
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+ u64 elrsr = vgic_get_elrsr(vcpu);
+ unsigned long *elrsr_ptr = u64_to_bitmask(&elrsr);
int i;
- for_each_set_bit(i, vgic_cpu->lr_used, vgic_cpu->nr_lr) {
+ for_each_clear_bit(i, elrsr_ptr, vgic_cpu->nr_lr) {
struct vgic_lr lr = vgic_get_lr(vcpu, i);
/*
@@ -706,30 +717,14 @@
* interrupt then move the active state to the
* distributor tracking bit.
*/
- if (lr.state & LR_STATE_ACTIVE) {
+ if (lr.state & LR_STATE_ACTIVE)
vgic_irq_set_active(vcpu, lr.irq);
- lr.state &= ~LR_STATE_ACTIVE;
- }
/*
* Reestablish the pending state on the distributor and the
- * CPU interface. It may have already been pending, but that
- * is fine, then we are only setting a few bits that were
- * already set.
+ * CPU interface and mark the LR as free for other use.
*/
- if (lr.state & LR_STATE_PENDING) {
- vgic_dist_irq_set_pending(vcpu, lr.irq);
- lr.state &= ~LR_STATE_PENDING;
- }
-
- vgic_set_lr(vcpu, i, lr);
-
- /*
- * Mark the LR as free for other use.
- */
- BUG_ON(lr.state & LR_STATE_MASK);
- vgic_retire_lr(i, lr.irq, vcpu);
- vgic_irq_clear_queued(vcpu, lr.irq);
+ vgic_retire_lr(i, vcpu);
/* Finally update the VGIC state. */
vgic_update_state(vcpu->kvm);
@@ -982,6 +977,12 @@
pend_percpu = vcpu->arch.vgic_cpu.pending_percpu;
pend_shared = vcpu->arch.vgic_cpu.pending_shared;
+ if (!dist->enabled) {
+ bitmap_zero(pend_percpu, VGIC_NR_PRIVATE_IRQS);
+ bitmap_zero(pend_shared, nr_shared);
+ return 0;
+ }
+
pending = vgic_bitmap_get_cpu_map(&dist->irq_pending, vcpu_id);
enabled = vgic_bitmap_get_cpu_map(&dist->irq_enabled, vcpu_id);
bitmap_and(pend_percpu, pending, enabled, VGIC_NR_PRIVATE_IRQS);
@@ -1009,11 +1010,6 @@
struct kvm_vcpu *vcpu;
int c;
- if (!dist->enabled) {
- set_bit(0, dist->irq_pending_on_cpu);
- return;
- }
-
kvm_for_each_vcpu(c, vcpu, kvm) {
if (compute_pending_for_cpu(vcpu))
set_bit(c, dist->irq_pending_on_cpu);
@@ -1036,12 +1032,6 @@
vgic_ops->set_lr(vcpu, lr, vlr);
}
-static void vgic_sync_lr_elrsr(struct kvm_vcpu *vcpu, int lr,
- struct vgic_lr vlr)
-{
- vgic_ops->sync_lr_elrsr(vcpu, lr, vlr);
-}
-
static inline u64 vgic_get_elrsr(struct kvm_vcpu *vcpu)
{
return vgic_ops->get_elrsr(vcpu);
@@ -1087,16 +1077,23 @@
vgic_ops->enable(vcpu);
}
-static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu)
+static void vgic_retire_lr(int lr_nr, struct kvm_vcpu *vcpu)
{
- struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
struct vgic_lr vlr = vgic_get_lr(vcpu, lr_nr);
+ vgic_irq_clear_queued(vcpu, vlr.irq);
+
+ /*
+ * We must transfer the pending state back to the distributor before
+ * retiring the LR, otherwise we may loose edge-triggered interrupts.
+ */
+ if (vlr.state & LR_STATE_PENDING) {
+ vgic_dist_irq_set_pending(vcpu, vlr.irq);
+ vlr.hwirq = 0;
+ }
+
vlr.state = 0;
vgic_set_lr(vcpu, lr_nr, vlr);
- clear_bit(lr_nr, vgic_cpu->lr_used);
- vgic_cpu->vgic_irq_lr_map[irq] = LR_EMPTY;
- vgic_sync_lr_elrsr(vcpu, lr_nr, vlr);
}
/*
@@ -1110,17 +1107,15 @@
*/
static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu)
{
- struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
+ u64 elrsr = vgic_get_elrsr(vcpu);
+ unsigned long *elrsr_ptr = u64_to_bitmask(&elrsr);
int lr;
- for_each_set_bit(lr, vgic_cpu->lr_used, vgic->nr_lr) {
+ for_each_clear_bit(lr, elrsr_ptr, vgic->nr_lr) {
struct vgic_lr vlr = vgic_get_lr(vcpu, lr);
- if (!vgic_irq_is_enabled(vcpu, vlr.irq)) {
- vgic_retire_lr(lr, vlr.irq, vcpu);
- if (vgic_irq_is_queued(vcpu, vlr.irq))
- vgic_irq_clear_queued(vcpu, vlr.irq);
- }
+ if (!vgic_irq_is_enabled(vcpu, vlr.irq))
+ vgic_retire_lr(lr, vcpu);
}
}
@@ -1132,7 +1127,8 @@
kvm_debug("Set active, clear distributor: 0x%x\n", vlr.state);
vgic_irq_clear_active(vcpu, irq);
vgic_update_state(vcpu->kvm);
- } else if (vgic_dist_irq_is_pending(vcpu, irq)) {
+ } else {
+ WARN_ON(!vgic_dist_irq_is_pending(vcpu, irq));
vlr.state |= LR_STATE_PENDING;
kvm_debug("Set pending: 0x%x\n", vlr.state);
}
@@ -1159,7 +1155,6 @@
}
vgic_set_lr(vcpu, lr_nr, vlr);
- vgic_sync_lr_elrsr(vcpu, lr_nr, vlr);
}
/*
@@ -1169,8 +1164,9 @@
*/
bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq)
{
- struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+ u64 elrsr = vgic_get_elrsr(vcpu);
+ unsigned long *elrsr_ptr = u64_to_bitmask(&elrsr);
struct vgic_lr vlr;
int lr;
@@ -1181,28 +1177,22 @@
kvm_debug("Queue IRQ%d\n", irq);
- lr = vgic_cpu->vgic_irq_lr_map[irq];
-
/* Do we have an active interrupt for the same CPUID? */
- if (lr != LR_EMPTY) {
+ for_each_clear_bit(lr, elrsr_ptr, vgic->nr_lr) {
vlr = vgic_get_lr(vcpu, lr);
- if (vlr.source == sgi_source_id) {
+ if (vlr.irq == irq && vlr.source == sgi_source_id) {
kvm_debug("LR%d piggyback for IRQ%d\n", lr, vlr.irq);
- BUG_ON(!test_bit(lr, vgic_cpu->lr_used));
vgic_queue_irq_to_lr(vcpu, irq, lr, vlr);
return true;
}
}
/* Try to use another LR for this interrupt */
- lr = find_first_zero_bit((unsigned long *)vgic_cpu->lr_used,
- vgic->nr_lr);
+ lr = find_first_bit(elrsr_ptr, vgic->nr_lr);
if (lr >= vgic->nr_lr)
return false;
kvm_debug("LR%d allocated for IRQ%d %x\n", lr, irq, sgi_source_id);
- vgic_cpu->vgic_irq_lr_map[irq] = lr;
- set_bit(lr, vgic_cpu->lr_used);
vlr.irq = irq;
vlr.source = sgi_source_id;
@@ -1240,7 +1230,7 @@
struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
unsigned long *pa_percpu, *pa_shared;
- int i, vcpu_id, lr, ret;
+ int i, vcpu_id;
int overflow = 0;
int nr_shared = vgic_nr_shared_irqs(dist);
@@ -1295,39 +1285,62 @@
*/
clear_bit(vcpu_id, dist->irq_pending_on_cpu);
}
+}
- for (lr = 0; lr < vgic->nr_lr; lr++) {
- struct vgic_lr vlr;
+static int process_queued_irq(struct kvm_vcpu *vcpu,
+ int lr, struct vgic_lr vlr)
+{
+ int pending = 0;
- if (!test_bit(lr, vgic_cpu->lr_used))
- continue;
+ /*
+ * If the IRQ was EOIed (called from vgic_process_maintenance) or it
+ * went from active to non-active (called from vgic_sync_hwirq) it was
+ * also ACKed and we we therefore assume we can clear the soft pending
+ * state (should it had been set) for this interrupt.
+ *
+ * Note: if the IRQ soft pending state was set after the IRQ was
+ * acked, it actually shouldn't be cleared, but we have no way of
+ * knowing that unless we start trapping ACKs when the soft-pending
+ * state is set.
+ */
+ vgic_dist_irq_clear_soft_pend(vcpu, vlr.irq);
- vlr = vgic_get_lr(vcpu, lr);
+ /*
+ * Tell the gic to start sampling this interrupt again.
+ */
+ vgic_irq_clear_queued(vcpu, vlr.irq);
- /*
- * If we have a mapping, and the virtual interrupt is
- * presented to the guest (as pending or active), then we must
- * set the state to active in the physical world. See
- * Documentation/virtual/kvm/arm/vgic-mapped-irqs.txt.
- */
- if (vlr.state & LR_HW) {
- struct irq_phys_map *map;
- map = vgic_irq_map_search(vcpu, vlr.irq);
-
- ret = irq_set_irqchip_state(map->irq,
- IRQCHIP_STATE_ACTIVE,
- true);
- WARN_ON(ret);
+ /* Any additional pending interrupt? */
+ if (vgic_irq_is_edge(vcpu, vlr.irq)) {
+ BUG_ON(!(vlr.state & LR_HW));
+ pending = vgic_dist_irq_is_pending(vcpu, vlr.irq);
+ } else {
+ if (vgic_dist_irq_get_level(vcpu, vlr.irq)) {
+ vgic_cpu_irq_set(vcpu, vlr.irq);
+ pending = 1;
+ } else {
+ vgic_dist_irq_clear_pending(vcpu, vlr.irq);
+ vgic_cpu_irq_clear(vcpu, vlr.irq);
}
}
+
+ /*
+ * Despite being EOIed, the LR may not have
+ * been marked as empty.
+ */
+ vlr.state = 0;
+ vlr.hwirq = 0;
+ vgic_set_lr(vcpu, lr, vlr);
+
+ return pending;
}
static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
{
u32 status = vgic_get_interrupt_status(vcpu);
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
- bool level_pending = false;
struct kvm *kvm = vcpu->kvm;
+ int level_pending = 0;
kvm_debug("STATUS = %08x\n", status);
@@ -1342,54 +1355,22 @@
for_each_set_bit(lr, eisr_ptr, vgic->nr_lr) {
struct vgic_lr vlr = vgic_get_lr(vcpu, lr);
+
WARN_ON(vgic_irq_is_edge(vcpu, vlr.irq));
-
- spin_lock(&dist->lock);
- vgic_irq_clear_queued(vcpu, vlr.irq);
WARN_ON(vlr.state & LR_STATE_MASK);
- vlr.state = 0;
- vgic_set_lr(vcpu, lr, vlr);
- /*
- * If the IRQ was EOIed it was also ACKed and we we
- * therefore assume we can clear the soft pending
- * state (should it had been set) for this interrupt.
- *
- * Note: if the IRQ soft pending state was set after
- * the IRQ was acked, it actually shouldn't be
- * cleared, but we have no way of knowing that unless
- * we start trapping ACKs when the soft-pending state
- * is set.
- */
- vgic_dist_irq_clear_soft_pend(vcpu, vlr.irq);
/*
* kvm_notify_acked_irq calls kvm_set_irq()
- * to reset the IRQ level. Need to release the
- * lock for kvm_set_irq to grab it.
+ * to reset the IRQ level, which grabs the dist->lock
+ * so we call this before taking the dist->lock.
*/
- spin_unlock(&dist->lock);
-
kvm_notify_acked_irq(kvm, 0,
vlr.irq - VGIC_NR_PRIVATE_IRQS);
+
spin_lock(&dist->lock);
-
- /* Any additional pending interrupt? */
- if (vgic_dist_irq_get_level(vcpu, vlr.irq)) {
- vgic_cpu_irq_set(vcpu, vlr.irq);
- level_pending = true;
- } else {
- vgic_dist_irq_clear_pending(vcpu, vlr.irq);
- vgic_cpu_irq_clear(vcpu, vlr.irq);
- }
-
+ level_pending |= process_queued_irq(vcpu, lr, vlr);
spin_unlock(&dist->lock);
-
- /*
- * Despite being EOIed, the LR may not have
- * been marked as empty.
- */
- vgic_sync_lr_elrsr(vcpu, lr, vlr);
}
}
@@ -1410,40 +1391,40 @@
/*
* Save the physical active state, and reset it to inactive.
*
- * Return 1 if HW interrupt went from active to inactive, and 0 otherwise.
+ * Return true if there's a pending forwarded interrupt to queue.
*/
-static int vgic_sync_hwirq(struct kvm_vcpu *vcpu, struct vgic_lr vlr)
+static bool vgic_sync_hwirq(struct kvm_vcpu *vcpu, int lr, struct vgic_lr vlr)
{
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
struct irq_phys_map *map;
+ bool phys_active;
+ bool level_pending;
int ret;
if (!(vlr.state & LR_HW))
- return 0;
+ return false;
map = vgic_irq_map_search(vcpu, vlr.irq);
- BUG_ON(!map || !map->active);
+ BUG_ON(!map);
ret = irq_get_irqchip_state(map->irq,
IRQCHIP_STATE_ACTIVE,
- &map->active);
+ &phys_active);
WARN_ON(ret);
- if (map->active) {
- ret = irq_set_irqchip_state(map->irq,
- IRQCHIP_STATE_ACTIVE,
- false);
- WARN_ON(ret);
+ if (phys_active)
return 0;
- }
- return 1;
+ spin_lock(&dist->lock);
+ level_pending = process_queued_irq(vcpu, lr, vlr);
+ spin_unlock(&dist->lock);
+ return level_pending;
}
/* Sync back the VGIC state after a guest run */
static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
{
- struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
u64 elrsr;
unsigned long *elrsr_ptr;
@@ -1451,40 +1432,18 @@
bool level_pending;
level_pending = vgic_process_maintenance(vcpu);
- elrsr = vgic_get_elrsr(vcpu);
- elrsr_ptr = u64_to_bitmask(&elrsr);
/* Deal with HW interrupts, and clear mappings for empty LRs */
for (lr = 0; lr < vgic->nr_lr; lr++) {
- struct vgic_lr vlr;
+ struct vgic_lr vlr = vgic_get_lr(vcpu, lr);
- if (!test_bit(lr, vgic_cpu->lr_used))
- continue;
-
- vlr = vgic_get_lr(vcpu, lr);
- if (vgic_sync_hwirq(vcpu, vlr)) {
- /*
- * So this is a HW interrupt that the guest
- * EOI-ed. Clean the LR state and allow the
- * interrupt to be sampled again.
- */
- vlr.state = 0;
- vlr.hwirq = 0;
- vgic_set_lr(vcpu, lr, vlr);
- vgic_irq_clear_queued(vcpu, vlr.irq);
- set_bit(lr, elrsr_ptr);
- }
-
- if (!test_bit(lr, elrsr_ptr))
- continue;
-
- clear_bit(lr, vgic_cpu->lr_used);
-
+ level_pending |= vgic_sync_hwirq(vcpu, lr, vlr);
BUG_ON(vlr.irq >= dist->nr_irqs);
- vgic_cpu->vgic_irq_lr_map[vlr.irq] = LR_EMPTY;
}
/* Check if we still have something up our sleeve... */
+ elrsr = vgic_get_elrsr(vcpu);
+ elrsr_ptr = u64_to_bitmask(&elrsr);
pending = find_first_zero_bit(elrsr_ptr, vgic->nr_lr);
if (level_pending || pending < vgic->nr_lr)
set_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu);
@@ -1574,6 +1533,8 @@
int enabled;
bool ret = true, can_inject = true;
+ trace_vgic_update_irq_pending(cpuid, irq_num, level);
+
if (irq_num >= min(kvm->arch.vgic.nr_irqs, 1020))
return -EINVAL;
@@ -1607,8 +1568,12 @@
} else {
if (level_triggered) {
vgic_dist_irq_clear_level(vcpu, irq_num);
- if (!vgic_dist_irq_soft_pend(vcpu, irq_num))
+ if (!vgic_dist_irq_soft_pend(vcpu, irq_num)) {
vgic_dist_irq_clear_pending(vcpu, irq_num);
+ vgic_cpu_irq_clear(vcpu, irq_num);
+ if (!compute_pending_for_cpu(vcpu))
+ clear_bit(cpuid, dist->irq_pending_on_cpu);
+ }
}
ret = false;
@@ -1849,30 +1814,6 @@
}
/**
- * kvm_vgic_get_phys_irq_active - Return the active state of a mapped IRQ
- *
- * Return the logical active state of a mapped interrupt. This doesn't
- * necessarily reflects the current HW state.
- */
-bool kvm_vgic_get_phys_irq_active(struct irq_phys_map *map)
-{
- BUG_ON(!map);
- return map->active;
-}
-
-/**
- * kvm_vgic_set_phys_irq_active - Set the active state of a mapped IRQ
- *
- * Set the logical active state of a mapped interrupt. This doesn't
- * immediately affects the HW state.
- */
-void kvm_vgic_set_phys_irq_active(struct irq_phys_map *map, bool active)
-{
- BUG_ON(!map);
- map->active = active;
-}
-
-/**
* kvm_vgic_unmap_phys_irq - Remove a virtual to physical IRQ mapping
* @vcpu: The VCPU pointer
* @map: The pointer to a mapping obtained through kvm_vgic_map_phys_irq
@@ -1927,12 +1868,10 @@
kfree(vgic_cpu->pending_shared);
kfree(vgic_cpu->active_shared);
kfree(vgic_cpu->pend_act_shared);
- kfree(vgic_cpu->vgic_irq_lr_map);
vgic_destroy_irq_phys_map(vcpu->kvm, &vgic_cpu->irq_phys_map_list);
vgic_cpu->pending_shared = NULL;
vgic_cpu->active_shared = NULL;
vgic_cpu->pend_act_shared = NULL;
- vgic_cpu->vgic_irq_lr_map = NULL;
}
static int vgic_vcpu_init_maps(struct kvm_vcpu *vcpu, int nr_irqs)
@@ -1943,18 +1882,14 @@
vgic_cpu->pending_shared = kzalloc(sz, GFP_KERNEL);
vgic_cpu->active_shared = kzalloc(sz, GFP_KERNEL);
vgic_cpu->pend_act_shared = kzalloc(sz, GFP_KERNEL);
- vgic_cpu->vgic_irq_lr_map = kmalloc(nr_irqs, GFP_KERNEL);
if (!vgic_cpu->pending_shared
|| !vgic_cpu->active_shared
- || !vgic_cpu->pend_act_shared
- || !vgic_cpu->vgic_irq_lr_map) {
+ || !vgic_cpu->pend_act_shared) {
kvm_vgic_vcpu_destroy(vcpu);
return -ENOMEM;
}
- memset(vgic_cpu->vgic_irq_lr_map, LR_EMPTY, nr_irqs);
-
/*
* Store the number of LRs per vcpu, so we don't have to go
* all the way to the distributor structure to find out. Only
@@ -2096,14 +2031,24 @@
break;
}
- for (i = 0; i < dist->nr_irqs; i++) {
- if (i < VGIC_NR_PPIS)
+ /*
+ * Enable and configure all SGIs to be edge-triggere and
+ * configure all PPIs as level-triggered.
+ */
+ for (i = 0; i < VGIC_NR_PRIVATE_IRQS; i++) {
+ if (i < VGIC_NR_SGIS) {
+ /* SGIs */
vgic_bitmap_set_irq_val(&dist->irq_enabled,
vcpu->vcpu_id, i, 1);
- if (i < VGIC_NR_PRIVATE_IRQS)
vgic_bitmap_set_irq_val(&dist->irq_cfg,
vcpu->vcpu_id, i,
VGIC_CFG_EDGE);
+ } else if (i < VGIC_NR_PRIVATE_IRQS) {
+ /* PPIs */
+ vgic_bitmap_set_irq_val(&dist->irq_cfg,
+ vcpu->vcpu_id, i,
+ VGIC_CFG_LEVEL);
+ }
}
vgic_enable(vcpu);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index a75502c..484079e 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2021,6 +2021,8 @@
} while (single_task_running() && ktime_before(cur, stop));
}
+ kvm_arch_vcpu_blocking(vcpu);
+
for (;;) {
prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
@@ -2034,6 +2036,7 @@
finish_wait(&vcpu->wq, &wait);
cur = ktime_get();
+ kvm_arch_vcpu_unblocking(vcpu);
out:
block_ns = ktime_to_ns(cur) - ktime_to_ns(start);