On LoongArch system, ipi hw uses iocsr registers, there is one iocsr
register access on ipi sender and two iocsr access on ipi receiver
which is ipi interrupt handler. On VM mode all iocsr registers
accessing will trap into hypervisor. So with one ipi hw notification
there will be three times of trap.
This patch adds pv ipi support for VM, hypercall instruction is used
to ipi sender, and hypervisor will inject SWI on the VM. During SWI
interrupt handler, only estat CSR register is written to clear irq.
Estat CSR register access will not trap into hypervisor. So with pv ipi
supported, pv ipi sender will trap into hypervsor one time, pv ipi
revicer will not trap, there is only one time of trap.
Also this patch adds ipi multicast support, the method is similar with
x86. With ipi multicast support, ipi notification can be sent to at most
128 vcpus at one time. It reduces trap into hypervisor greatly.
Signed-off-by: Bibo Mao <maobibo@xxxxxxxxxxx>
---
arch/loongarch/include/asm/hardirq.h | 1 +
arch/loongarch/include/asm/kvm_host.h | 1 +
arch/loongarch/include/asm/kvm_para.h | 124 +++++++++++++++++++++++++
arch/loongarch/include/asm/loongarch.h | 1 +
arch/loongarch/kernel/irq.c | 2 +-
arch/loongarch/kernel/paravirt.c | 113 ++++++++++++++++++++++
arch/loongarch/kernel/smp.c | 2 +-
arch/loongarch/kvm/exit.c | 73 ++++++++++++++-
arch/loongarch/kvm/vcpu.c | 1 +
9 files changed, 314 insertions(+), 4 deletions(-)
diff --git a/arch/loongarch/include/asm/hardirq.h b/arch/loongarch/include/asm/hardirq.h
index 9f0038e19c7f..8a611843c1f0 100644
--- a/arch/loongarch/include/asm/hardirq.h
+++ b/arch/loongarch/include/asm/hardirq.h
@@ -21,6 +21,7 @@ enum ipi_msg_type {
typedef struct {
unsigned int ipi_irqs[NR_IPI];
unsigned int __softirq_pending;
+ atomic_t messages ____cacheline_aligned_in_smp;
} ____cacheline_aligned irq_cpustat_t;
DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h
index 57399d7cf8b7..1bf927e2bfac 100644
--- a/arch/loongarch/include/asm/kvm_host.h
+++ b/arch/loongarch/include/asm/kvm_host.h
@@ -43,6 +43,7 @@ struct kvm_vcpu_stat {
u64 idle_exits;
u64 cpucfg_exits;
u64 signal_exits;
+ u64 hvcl_exits;
};
#define KVM_MEM_HUGEPAGE_CAPABLE (1UL << 0)
diff --git a/arch/loongarch/include/asm/kvm_para.h b/arch/loongarch/include/asm/kvm_para.h
index 41200e922a82..a25a84e372b9 100644
--- a/arch/loongarch/include/asm/kvm_para.h
+++ b/arch/loongarch/include/asm/kvm_para.h
@@ -9,6 +9,10 @@
#define HYPERVISOR_VENDOR_SHIFT 8
#define HYPERCALL_CODE(vendor, code) ((vendor << HYPERVISOR_VENDOR_SHIFT) + code)
+#define KVM_HC_CODE_SERVICE 0
+#define KVM_HC_SERVICE HYPERCALL_CODE(HYPERVISOR_KVM, KVM_HC_CODE_SERVICE)
+#define KVM_HC_FUNC_IPI 1
+
/*
* LoongArch hypcall return code
*/
@@ -16,6 +20,126 @@
#define KVM_HC_INVALID_CODE -1UL
#define KVM_HC_INVALID_PARAMETER -2UL
+/*
+ * Hypercalls interface for KVM hypervisor
+ *
+ * a0: function identifier
+ * a1-a6: args
+ * Return value will be placed in v0.
+ * Up to 6 arguments are passed in a1, a2, a3, a4, a5, a6.
+ */
+static __always_inline long kvm_hypercall(u64 fid)
+{
+ register long ret asm("v0");
+ register unsigned long fun asm("a0") = fid;
+
+ __asm__ __volatile__(
+ "hvcl "__stringify(KVM_HC_SERVICE)
+ : "=r" (ret)
+ : "r" (fun)
+ : "memory"
+ );
+
+ return ret;
+}
+
+static __always_inline long kvm_hypercall1(u64 fid, unsigned long arg0)
+{
+ register long ret asm("v0");
+ register unsigned long fun asm("a0") = fid;
+ register unsigned long a1 asm("a1") = arg0;
+
+ __asm__ __volatile__(
+ "hvcl "__stringify(KVM_HC_SERVICE)
+ : "=r" (ret)
+ : "r" (fun), "r" (a1)
+ : "memory"
+ );
+
+ return ret;
+}
+
+static __always_inline long kvm_hypercall2(u64 fid,
+ unsigned long arg0, unsigned long arg1)
+{
+ register long ret asm("v0");
+ register unsigned long fun asm("a0") = fid;
+ register unsigned long a1 asm("a1") = arg0;
+ register unsigned long a2 asm("a2") = arg1;
+
+ __asm__ __volatile__(
+ "hvcl "__stringify(KVM_HC_SERVICE)
+ : "=r" (ret)
+ : "r" (fun), "r" (a1), "r" (a2)
+ : "memory"
+ );
+
+ return ret;
+}
+
+static __always_inline long kvm_hypercall3(u64 fid,
+ unsigned long arg0, unsigned long arg1, unsigned long arg2)
+{
+ register long ret asm("v0");
+ register unsigned long fun asm("a0") = fid;
+ register unsigned long a1 asm("a1") = arg0;
+ register unsigned long a2 asm("a2") = arg1;
+ register unsigned long a3 asm("a3") = arg2;
+
+ __asm__ __volatile__(
+ "hvcl "__stringify(KVM_HC_SERVICE)
+ : "=r" (ret)
+ : "r" (fun), "r" (a1), "r" (a2), "r" (a3)
+ : "memory"
+ );
+
+ return ret;
+}
+
+static __always_inline long kvm_hypercall4(u64 fid,
+ unsigned long arg0, unsigned long arg1, unsigned long arg2,
+ unsigned long arg3)
+{
+ register long ret asm("v0");
+ register unsigned long fun asm("a0") = fid;
+ register unsigned long a1 asm("a1") = arg0;
+ register unsigned long a2 asm("a2") = arg1;
+ register unsigned long a3 asm("a3") = arg2;
+ register unsigned long a4 asm("a4") = arg3;
+
+ __asm__ __volatile__(
+ "hvcl "__stringify(KVM_HC_SERVICE)
+ : "=r" (ret)
+ : "r"(fun), "r" (a1), "r" (a2), "r" (a3), "r" (a4)
+ : "memory"
+ );
+
+ return ret;
+}
+
+static __always_inline long kvm_hypercall5(u64 fid,
+ unsigned long arg0, unsigned long arg1, unsigned long arg2,
+ unsigned long arg3, unsigned long arg4)
+{
+ register long ret asm("v0");
+ register unsigned long fun asm("a0") = fid;
+ register unsigned long a1 asm("a1") = arg0;
+ register unsigned long a2 asm("a2") = arg1;
+ register unsigned long a3 asm("a3") = arg2;
+ register unsigned long a4 asm("a4") = arg3;
+ register unsigned long a5 asm("a5") = arg4;
+
+ __asm__ __volatile__(
+ "hvcl "__stringify(KVM_HC_SERVICE)
+ : "=r" (ret)
+ : "r"(fun), "r" (a1), "r" (a2), "r" (a3), "r" (a4), "r" (a5)
+ : "memory"
+ );
+
+ return ret;
+}
+
+
static inline unsigned int kvm_arch_para_features(void)
{
return 0;
diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h
index a1d22e8b6f94..0ad36704cb4b 100644
--- a/arch/loongarch/include/asm/loongarch.h
+++ b/arch/loongarch/include/asm/loongarch.h
@@ -167,6 +167,7 @@
#define CPUCFG_KVM_SIG CPUCFG_KVM_BASE
#define KVM_SIGNATURE "KVM\0"
#define CPUCFG_KVM_FEATURE (CPUCFG_KVM_BASE + 4)
+#define KVM_FEATURE_PV_IPI BIT(1)
#ifndef __ASSEMBLY__
diff --git a/arch/loongarch/kernel/irq.c b/arch/loongarch/kernel/irq.c
index 1b58f7c3eed9..b5bd298c981f 100644
--- a/arch/loongarch/kernel/irq.c
+++ b/arch/loongarch/kernel/irq.c
@@ -113,5 +113,5 @@ void __init init_IRQ(void)
per_cpu(irq_stack, i), per_cpu(irq_stack, i) + IRQ_STACK_SIZE);
}
- set_csr_ecfg(ECFGF_IP0 | ECFGF_IP1 | ECFGF_IP2 | ECFGF_IPI | ECFGF_PMC);
+ set_csr_ecfg(ECFGF_SIP0 | ECFGF_IP0 | ECFGF_IP1 | ECFGF_IP2 | ECFGF_IPI | ECFGF_PMC);
}
diff --git a/arch/loongarch/kernel/paravirt.c b/arch/loongarch/kernel/paravirt.c
index 21d01d05791a..b840a004995a 100644
--- a/arch/loongarch/kernel/paravirt.c
+++ b/arch/loongarch/kernel/paravirt.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/export.h>
#include <linux/types.h>
+#include <linux/interrupt.h>
#include <linux/jump_label.h>
#include <linux/kvm_para.h>
#include <asm/paravirt.h>
@@ -16,6 +17,104 @@ static u64 native_steal_clock(int cpu)
DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock);
+#ifdef CONFIG_SMP
+static void pv_send_ipi_single(int cpu, unsigned int action)
+{
+ unsigned int min, old;
+ unsigned long bitmap = 0;
+ irq_cpustat_t *info = &per_cpu(irq_stat, cpu);
+
+ action = BIT(action);
+ old = atomic_fetch_or(action, &info->messages);
+ if (old == 0) {
+ min = cpu_logical_map(cpu);
+ bitmap = 1;
+ kvm_hypercall3(KVM_HC_FUNC_IPI, bitmap, 0, min);
+ }
+}
+
+#define KVM_IPI_CLUSTER_SIZE (2 * BITS_PER_LONG)
+static void pv_send_ipi_mask(const struct cpumask *mask, unsigned int action)
+{
+ unsigned int cpu, i, min = 0, max = 0, old;
+ __uint128_t bitmap = 0;
+ irq_cpustat_t *info;
+
+ if (cpumask_empty(mask))
+ return;
+
+ action = BIT(action);
+ for_each_cpu(i, mask) {
+ info = &per_cpu(irq_stat, i);
+ old = atomic_fetch_or(action, &info->messages);
+ if (old)
+ continue;
+
+ cpu = cpu_logical_map(i);
+ if (!bitmap) {
+ min = max = cpu;
+ } else if (cpu > min && cpu < min + KVM_IPI_CLUSTER_SIZE) {
+ max = cpu > max ? cpu : max;
+ } else if (cpu < min && (max - cpu) < KVM_IPI_CLUSTER_SIZE) {
+ bitmap <<= min - cpu;
+ min = cpu;
+ } else {
+ /*
+ * Physical cpuid is sorted in ascending order ascend
+ * for the next mask calculation, send IPI here
+ * directly and skip the remainding cpus
+ */
+ kvm_hypercall3(KVM_HC_FUNC_IPI, (unsigned long)bitmap,
+ (unsigned long)(bitmap >> BITS_PER_LONG), min);
+ min = max = cpu;
+ bitmap = 0;
+ }
+ __set_bit(cpu - min, (unsigned long *)&bitmap);
+ }
+
+ if (bitmap)
+ kvm_hypercall3(KVM_HC_FUNC_IPI, (unsigned long)bitmap,
+ (unsigned long)(bitmap >> BITS_PER_LONG), min);
+}
+
+static irqreturn_t loongson_do_swi(int irq, void *dev)
+{
+ irq_cpustat_t *info;
+ long action;
+
+ clear_csr_estat(1 << INT_SWI0);
+
+ info = this_cpu_ptr(&irq_stat);
+ do {
+ action = atomic_xchg(&info->messages, 0);
+ if (action & SMP_CALL_FUNCTION) {
+ generic_smp_call_function_interrupt();
+ info->ipi_irqs[IPI_CALL_FUNCTION]++;
+ }
+
+ if (action & SMP_RESCHEDULE) {
+ scheduler_ipi();
+ info->ipi_irqs[IPI_RESCHEDULE]++;
+ }
+ } while (action);
+
+ return IRQ_HANDLED;
+}
+
+static void pv_ipi_init(void)
+{
+ int r, swi0;
+
+ swi0 = get_percpu_irq(INT_SWI0);
+ if (swi0 < 0)
+ panic("SWI0 IRQ mapping failed\n");
+ irq_set_percpu_devid(swi0);
+ r = request_percpu_irq(swi0, loongson_do_swi, "SWI0", &irq_stat);
+ if (r < 0)
+ panic("SWI0 IRQ request failed\n");
+}
+#endif
+
static bool kvm_para_available(void)
{
static int hypervisor_type;
@@ -32,10 +131,24 @@ static bool kvm_para_available(void)
int __init pv_guest_init(void)
{
+ int feature;
+
if (!cpu_has_hypervisor)
return 0;
if (!kvm_para_available())
return 0;
+ /*
+ * check whether KVM hypervisor supports pv_ipi or not
+ */
+#ifdef CONFIG_SMP
+ feature = read_cpucfg(CPUCFG_KVM_FEATURE);
+ if (feature & KVM_FEATURE_PV_IPI) {
+ smp_ops.call_func_single_ipi = pv_send_ipi_single;
+ smp_ops.call_func_ipi = pv_send_ipi_mask;
