new file mode 100644
@@ -0,0 +1,36 @@
+MPIC interrupt controller
+=========================
+
+Device types supported:
+ KVM_DEV_TYPE_FSL_MPIC_20 Freescale MPIC v2.0
+ KVM_DEV_TYPE_FSL_MPIC_42 Freescale MPIC v4.2
+
+Only one MPIC instance, of any type, may be instantiated. The created
+MPIC will act as the system interrupt controller, connecting to each
+vcpu's interrupt inputs.
+
+Groups:
+ KVM_DEV_MPIC_GRP_MISC
+ Attributes:
+ KVM_DEV_MPIC_BASE_ADDR (rw, 64-bit)
+ Base address of the 256 KiB MPIC register space. Must be
+ naturally aligned. A value of zero disables the mapping.
+ Reset value is zero.
+
+ KVM_DEV_MPIC_GRP_REGISTER (rw, 32-bit)
+ Access MPIC register state. "attr" is the byte offset into
+ the MPIC register space. Accesses must be 4-byte aligned.
+
+ MSIs may be signaled by using this attribute group to write
+ to the relevant MSIIR.
+
+ KVM_DEV_MPIC_GRP_IRQ_ACTIVE (rw, 32-bit)
+ IRQ input line for each standard openpic source. 0 is inactive and 1
+ is active, regardless of interrupt sense.
+
+ For edge-triggered interrupts: Writing 1 is considered an activating
+ edge, and writing 0 is ignored. Reading returns 1 if a previously
+ signaled edge has not been acknowledged, and 0 otherwise.
+
+ "attr" is the IRQ number. IRQ numbers for standard sources are the
+ byte offset of the relevant IVPR from EIVPR0, divided by 32.
@@ -256,6 +256,7 @@ struct kvm_arch {
#ifdef CONFIG_PPC_BOOK3S_64
struct list_head spapr_tce_tables;
#endif
+ void *irqchip_priv;
};
/*
@@ -359,6 +360,11 @@ struct kvmppc_slb {
#define KVMPPC_BOOKE_MAX_IAC 4
#define KVMPPC_BOOKE_MAX_DAC 2
+/* KVMPPC_EPR_USER takes precedence over KVMPPC_EPR_KERNEL */
+#define KVMPPC_EPR_NONE 0 /* EPR not supported */
+#define KVMPPC_EPR_USER 1 /* exit to userspace to fill EPR */
+#define KVMPPC_EPR_KERNEL 2 /* in-kernel irqchip */
+
struct kvmppc_booke_debug_reg {
u32 dbcr0;
u32 dbcr1;
@@ -520,7 +526,7 @@ struct kvm_vcpu_arch {
u8 sane;
u8 cpu_type;
u8 hcall_needed;
- u8 epr_enabled;
+ u8 epr_flags; /* KVMPPC_EPR_xxx */
u8 epr_needed;
u32 cpr0_cfgaddr; /* holds the last set cpr0_cfgaddr */
@@ -587,5 +593,6 @@ struct kvm_vcpu_arch {
#define KVM_MMIO_REG_FQPR 0x0060
#define __KVM_HAVE_ARCH_WQP
+#define __KVM_HAVE_CREATE_DEVICE
#endif /* __POWERPC_KVM_HOST_H__ */
@@ -165,6 +165,8 @@ extern int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu);
extern int kvm_vm_ioctl_get_htab_fd(struct kvm *kvm, struct kvm_get_htab_fd *);
+int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq);
+
/*
* Cuts out inst bits with ordering according to spec.
* That means the leftmost bit is zero. All given bits are included.
@@ -271,6 +273,8 @@ static inline void kvmppc_set_epr(struct kvm_vcpu *vcpu, u32 epr)
#endif
}
+void kvmppc_mpic_set_epr(struct kvm_vcpu *vcpu);
+
int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
struct kvm_config_tlb *cfg);
int kvm_vcpu_ioctl_dirty_tlb(struct kvm_vcpu *vcpu,
@@ -151,6 +151,11 @@ config KVM_E500MC
If unsure, say N.
+config KVM_MPIC
+ bool "KVM in-kernel MPIC emulation"
+ depends on KVM
+
+
source drivers/vhost/Kconfig
endif # VIRTUALIZATION
@@ -103,6 +103,8 @@ kvm-book3s_32-objs := \
book3s_32_mmu.o
kvm-objs-$(CONFIG_KVM_BOOK3S_32) := $(kvm-book3s_32-objs)
+kvm-objs-$(CONFIG_KVM_MPIC) += mpic.o
+
kvm-objs := $(kvm-objs-m) $(kvm-objs-y)
obj-$(CONFIG_KVM_440) += kvm.o
@@ -347,7 +347,7 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
keep_irq = true;
}
- if ((priority == BOOKE_IRQPRIO_EXTERNAL) && vcpu->arch.epr_enabled)
+ if ((priority == BOOKE_IRQPRIO_EXTERNAL) && vcpu->arch.epr_flags)
update_epr = true;
switch (priority) {
@@ -428,8 +428,12 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
set_guest_esr(vcpu, vcpu->arch.queued_esr);
if (update_dear == true)
set_guest_dear(vcpu, vcpu->arch.queued_dear);
- if (update_epr == true)
- kvm_make_request(KVM_REQ_EPR_EXIT, vcpu);
+ if (update_epr == true) {
+ if (vcpu->arch.epr_flags & KVMPPC_EPR_USER)
+ kvm_make_request(KVM_REQ_EPR_EXIT, vcpu);
+ else if (vcpu->arch.epr_flags & KVMPPC_EPR_KERNEL)
+ kvmppc_mpic_set_epr(vcpu);
+ }
new_msr &= msr_mask;
#if defined(CONFIG_64BIT)
@@ -23,6 +23,18 @@
* THE SOFTWARE.
*/
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/kvm_host.h>
+#include <linux/errno.h>
+#include <linux/notifier.h>
+#include <asm/uaccess.h>
+#include <asm/mpic.h>
+#include <asm/kvm_para.h>
+#include <asm/kvm_host.h>
+#include <asm/kvm_ppc.h>
+#include "iodev.h"
+
#define MAX_CPU 32
#define MAX_SRC 256
#define MAX_TMR 4
@@ -89,6 +101,7 @@ static struct fsl_mpic_info fsl_mpic_42 = {
#define ILR_INTTGT_INT 0x00
#define ILR_INTTGT_CINT 0x01 /* critical */
#define ILR_INTTGT_MCP 0x02 /* machine check */
+#define NUM_OUTPUTS 3
#define MSIIR_OFFSET 0x140
#define MSIIR_SRS_SHIFT 29
@@ -98,18 +111,14 @@ static struct fsl_mpic_info fsl_mpic_42 = {
static int get_current_cpu(void)
{
- CPUState *cpu_single_cpu;
-
- if (!cpu_single_env)
- return -1;
-
- cpu_single_cpu = ENV_GET_CPU(cpu_single_env);
- return cpu_single_cpu->cpu_index;
+ struct kvm_vcpu *vcpu = current->thread.kvm_vcpu;
+ return vcpu ? vcpu->vcpu_id : -1;
}
-static uint32_t openpic_cpu_read_internal(void *opaque, gpa_t addr, int idx);
-static void openpic_cpu_write_internal(void *opaque, gpa_t addr,
- uint32_t val, int idx);
+static int openpic_cpu_write_internal(struct kvm_io_device *this, gpa_t addr,
+ u32 val, int idx);
+static int openpic_cpu_read_internal(struct kvm_io_device *this, gpa_t addr,
+ u32 *ptr, int idx);
enum irq_type {
IRQ_TYPE_NORMAL = 0,
@@ -131,7 +140,7 @@ struct irq_source {
uint32_t idr; /* IRQ destination register */
uint32_t destmask; /* bitmap of CPU destinations */
int last_cpu;
- int output; /* IRQ level, e.g. OPENPIC_OUTPUT_INT */
+ int output; /* IRQ level, e.g. ILR_INTTGT_INT */
int pending; /* TRUE if IRQ is pending */
enum irq_type type;
bool level:1; /* level-triggered */
@@ -158,16 +167,35 @@ struct irq_source {
#define IDR_CI 0x40000000 /* critical interrupt */
struct irq_dest {
+ struct kvm_vcpu *vcpu;
+
int32_t ctpr; /* CPU current task priority */
struct irq_queue raised;
struct irq_queue servicing;
- qemu_irq *irqs;
/* Count of IRQ sources asserting on non-INT outputs */
- uint32_t outputs_active[OPENPIC_OUTPUT_NB];
+ uint32_t outputs_active[NUM_OUTPUTS];
+};
+
+struct openpic;
+
+struct sub_region {
+ struct kvm_io_device iodev;
+ struct openpic *opp;
+ gpa_t base;
+ int size;
};
struct openpic {
+ struct kvm_device dev;
+ struct kvm *kvm;
+ gpa_t reg_base;
+ spinlock_t lock;
+ struct notifier_block vcpu_notifier;
+
+ struct sub_region sub_io_mem[6];
+ int sub_count;
+
/* Behavior control */
struct fsl_mpic_info *fsl;
uint32_t model;
@@ -208,6 +236,51 @@ struct openpic {
uint32_t irq_msi;
};
+
+static void mpic_irq_raise(struct openpic *opp, struct irq_dest *dst,
+ int output)
+{
+ struct kvm_interrupt irq = {
+ .irq = KVM_INTERRUPT_SET_LEVEL,
+ };
+
+ if (!dst->vcpu) {
+ pr_debug("%s: destination cpu %d does not exist\n",
+ __func__, dst - &opp->dst[0]);
+ return;
+ }
+
+ pr_debug("%s: cpu %d output %d\n", __func__, dst->vcpu->vcpu_id,
+ output);
+
+ if (output != ILR_INTTGT_INT) /* TODO */
+ return;
+
+ kvm_vcpu_ioctl_interrupt(dst->vcpu, &irq);
+}
+
+static void mpic_irq_lower(struct openpic *opp, struct irq_dest *dst,
+ int output)
+{
+ struct kvm_interrupt irq = {
+ .irq = KVM_INTERRUPT_UNSET,
+ };
+
+ if (!dst->vcpu) {
+ pr_debug("%s: destination cpu %d does not exist\n",
+ __func__, dst - &opp->dst[0]);
+ return;
+ }
+
+ pr_debug("%s: cpu %d output %d\n", __func__, dst->vcpu->vcpu_id,
+ output);
+
+ if (output != ILR_INTTGT_INT) /* TODO */
+ return;
+
+ kvmppc_core_dequeue_external(dst->vcpu, &irq);
+}
+
static inline void IRQ_setbit(struct irq_queue *q, int n_IRQ)
{
set_bit(n_IRQ, q->queue);
@@ -268,7 +341,7 @@ static void IRQ_local_pipe(struct openpic *opp, int n_CPU, int n_IRQ,
pr_debug("%s: IRQ %d active %d was %d\n",
__func__, n_IRQ, active, was_active);
- if (src->output != OPENPIC_OUTPUT_INT) {
+ if (src->output != ILR_INTTGT_INT) {
pr_debug("%s: output %d irq %d active %d was %d count %d\n",
__func__, src->output, n_IRQ, active, was_active,
dst->outputs_active[src->output]);
@@ -282,14 +355,14 @@ static void IRQ_local_pipe(struct openpic *opp, int n_CPU, int n_IRQ,
dst->outputs_active[src->output]++ == 0) {
pr_debug("%s: Raise OpenPIC output %d cpu %d irq %d\n",
__func__, src->output, n_CPU, n_IRQ);
- qemu_irq_raise(dst->irqs[src->output]);
+ mpic_irq_raise(opp, dst, src->output);
}
} else {
if (was_active &&
--dst->outputs_active[src->output] == 0) {
pr_debug("%s: Lower OpenPIC output %d cpu %d irq %d\n",
__func__, src->output, n_CPU, n_IRQ);
- qemu_irq_lower(dst->irqs[src->output]);
+ mpic_irq_lower(opp, dst, src->output);
}
}
@@ -322,8 +395,7 @@ static void IRQ_local_pipe(struct openpic *opp, int n_CPU, int n_IRQ,
} else {
pr_debug("%s: Raise OpenPIC INT output cpu %d irq %d/%d\n",
__func__, n_CPU, n_IRQ, dst->raised.next);
- qemu_irq_raise(opp->dst[n_CPU].
- irqs[OPENPIC_OUTPUT_INT]);
+ mpic_irq_raise(opp, dst, ILR_INTTGT_INT);
}
} else {
IRQ_get_next(opp, &dst->servicing);
@@ -338,8 +410,7 @@ static void IRQ_local_pipe(struct openpic *opp, int n_CPU, int n_IRQ,
pr_debug("%s: IRQ %d inactive, current prio %d/%d, CPU %d\n",
__func__, n_IRQ, dst->ctpr,
dst->servicing.priority, n_CPU);
- qemu_irq_lower(opp->dst[n_CPU].
- irqs[OPENPIC_OUTPUT_INT]);
+ mpic_irq_lower(opp, dst, ILR_INTTGT_INT);
}
}
}
@@ -415,8 +486,8 @@ static void openpic_set_irq(void *opaque, int n_IRQ, int level)
struct irq_source *src;
if (n_IRQ >= MAX_IRQ) {
- pr_err("%s: IRQ %d out of range\n", __func__, n_IRQ);
- abort();
+ WARN_ONCE(1, "%s: IRQ %d out of range\n", __func__, n_IRQ);
+ return;
}
src = &opp->src[n_IRQ];
@@ -433,7 +504,7 @@ static void openpic_set_irq(void *opaque, int n_IRQ, int level)
openpic_update_irq(opp, n_IRQ);
}
- if (src->output != OPENPIC_OUTPUT_INT) {
+ if (src->output != ILR_INTTGT_INT) {
/* Edge-triggered interrupts shouldn't be used
* with non-INT delivery, but just in case,
* try to make it do something sane rather than
@@ -446,15 +517,14 @@ static void openpic_set_irq(void *opaque, int n_IRQ, int level)
}
}
-static void openpic_reset(DeviceState *d)
+static void openpic_reset(struct openpic *opp)
{
- struct openpic *opp = FROM_SYSBUS(typeof(*opp), SYS_BUS_DEVICE(d));
int i;
opp->gcr = GCR_RESET;
+
/* Initialise controller registers */
opp->frr = ((opp->nb_irqs - 1) << FRR_NIRQ_SHIFT) |
- ((opp->nb_cpus - 1) << FRR_NCPU_SHIFT) |
(opp->vid << FRR_VID_SHIFT);
opp->pir = 0;
@@ -504,7 +574,7 @@ static inline uint32_t read_IRQreg_idr(struct openpic *opp, int n_IRQ)
static inline uint32_t read_IRQreg_ilr(struct openpic *opp, int n_IRQ)
{
if (opp->flags & OPENPIC_FLAG_ILR)
- return output_to_inttgt(opp->src[n_IRQ].output);
+ return opp->src[n_IRQ].output;
return 0xffffffff;
}
@@ -539,7 +609,7 @@ static inline void write_IRQreg_idr(struct openpic *opp, int n_IRQ,
__func__);
}
- src->output = OPENPIC_OUTPUT_CINT;
+ src->output = ILR_INTTGT_CINT;
src->nomask = true;
src->destmask = 0;
@@ -550,7 +620,7 @@ static inline void write_IRQreg_idr(struct openpic *opp, int n_IRQ,
src->destmask |= 1UL << i;
}
} else {
- src->output = OPENPIC_OUTPUT_INT;
+ src->output = ILR_INTTGT_INT;
src->nomask = false;
src->destmask = src->idr & normal_mask;
}
@@ -565,7 +635,7 @@ static inline void write_IRQreg_ilr(struct openpic *opp, int n_IRQ,
if (opp->flags & OPENPIC_FLAG_ILR) {
struct irq_source *src = &opp->src[n_IRQ];
- src->output = inttgt_to_output(val & ILR_INTTGT_MASK);
+ src->output = val & ILR_INTTGT_MASK;
pr_debug("Set ILR %d to 0x%08x, output %d\n", n_IRQ, src->idr,
src->output);
@@ -614,34 +684,77 @@ static inline void write_IRQreg_ivpr(struct openpic *opp, int n_IRQ,
static void openpic_gcr_write(struct openpic *opp, uint64_t val)
{
+#if 0
bool mpic_proxy = false;
+#endif
if (val & GCR_RESET) {
- openpic_reset(&opp->busdev.qdev);
+ openpic_reset(opp);
return;
}
opp->gcr &= ~opp->mpic_mode_mask;
opp->gcr |= val & opp->mpic_mode_mask;
-
+#if 0
/* Set external proxy mode */
if ((val & opp->mpic_mode_mask) == GCR_MODE_PROXY)
mpic_proxy = true;
ppce500_set_mpic_proxy(mpic_proxy);
+#endif
}
-static void openpic_gbl_write(void *opaque, gpa_t addr, uint64_t val,
- unsigned len)
+static int openpic_get_val32(int len, const void *ptr, u32 *val)
{
- struct openpic *opp = opaque;
+ if (len != 4) {
+ pr_debug("%s: bad length %d\n", __func__, len);
+ return -EINVAL;
+ }
+
+ memcpy(val, ptr, min(len, 4));
+ return 0;
+}
+
+static int openpic_put_val32(int len, void *ptr, u32 val)
+{
+ /*
+ * Technically only 32-bit accesses are allowed, but be nice
+ * to people dumping registers -- it works in real hardware
+ * (reads only, not writes).
+ */
+ if (len > 4) {
+ pr_debug("%s: bad length %d\n", __func__, len);
+ return -EINVAL;
+ }
+
+ memcpy(ptr, &val, min(len, 4));
+ return 0;
+}
+
+static int openpic_gbl_write(struct kvm_io_device *this, gpa_t addr,
+ int len, const void *ptr)
+{
+ struct sub_region *sub = container_of(this, struct sub_region, iodev);
+ struct openpic *opp = sub->opp;
+#if 0
struct irq_dest *dst;
- int idx;
+#endif
+ u32 val;
+ int ret, idx;
+
+ addr -= sub->base;
+ if (addr > sub->size)
+ return 1;
- pr_debug("%s: addr %#" HWADDR_PRIx " <= %08" PRIx64 "\n",
- __func__, addr, val);
+ ret = openpic_get_val32(len, ptr, &val);
+ if (ret < 0)
+ return 1;
+
+ pr_debug("%s: addr %#llx <= %08x\n", __func__, addr, val);
if (addr & 0xF)
- return;
+ return 0;
+
+ spin_lock_irq(&opp->lock);
switch (addr) {
case 0x00: /* Block Revision Register1 (BRR1) is Readonly */
@@ -654,7 +767,7 @@ static void openpic_gbl_write(void *opaque, gpa_t addr, uint64_t val,
case 0x90:
case 0xA0:
case 0xB0:
- openpic_cpu_write_internal(opp, addr, val, get_current_cpu());
+ openpic_cpu_write_internal(this, addr, val, get_current_cpu());
break;
case 0x1000: /* FRR */
break;
@@ -668,14 +781,18 @@ static void openpic_gbl_write(void *opaque, gpa_t addr, uint64_t val,
if ((val & (1 << idx)) && !(opp->pir & (1 << idx))) {
pr_debug("Raise OpenPIC RESET output for CPU %d\n",
idx);
+#if 0
dst = &opp->dst[idx];
- qemu_irq_raise(dst->irqs[OPENPIC_OUTPUT_RESET]);
+ mpic_irq_raise(opp, dst, OPENPIC_OUTPUT_RESET);
+#endif
} else if (!(val & (1 << idx)) &&
(opp->pir & (1 << idx))) {
pr_debug("Lower OpenPIC RESET output for CPU %d\n",
idx);
+#if 0
dst = &opp->dst[idx];
- qemu_irq_lower(dst->irqs[OPENPIC_OUTPUT_RESET]);
+ mpic_irq_lower(opp, dst, OPENPIC_OUTPUT_RESET);
+#endif
}
}
opp->pir = val;
@@ -695,21 +812,34 @@ static void openpic_gbl_write(void *opaque, gpa_t addr, uint64_t val,
default:
break;
}
+
+ spin_unlock_irq(&opp->lock);
+ return 0;
}
-static uint64_t openpic_gbl_read(void *opaque, gpa_t addr, unsigned len)
+static int openpic_gbl_read(struct kvm_io_device *this, gpa_t addr,
+ int len, void *ptr)
{
- struct openpic *opp = opaque;
- uint32_t retval;
+ struct sub_region *sub = container_of(this, struct sub_region, iodev);
+ struct openpic *opp = sub->opp;
+ u32 retval;
+ int ret;
+
+ addr -= sub->base;
+ if (addr > sub->size)
+ return 1;
- pr_debug("%s: addr %#" HWADDR_PRIx "\n", __func__, addr);
+ pr_debug("%s: addr %#llx\n", __func__, addr);
retval = 0xFFFFFFFF;
if (addr & 0xF)
- return retval;
+ goto out;
+
+ spin_lock_irq(&opp->lock);
switch (addr) {
case 0x1000: /* FRR */
retval = opp->frr;
+ retval |= (opp->nb_cpus - 1) << FRR_NCPU_SHIFT;
break;
case 0x1020: /* GCR */
retval = opp->gcr;
@@ -731,8 +861,8 @@ static uint64_t openpic_gbl_read(void *opaque, gpa_t addr, unsigned len)
case 0x90:
case 0xA0:
case 0xB0:
- retval =
- openpic_cpu_read_internal(opp, addr, get_current_cpu());
+ retval = openpic_cpu_read_internal(this, addr,
+ &retval, get_current_cpu());
break;
case 0x10A0: /* IPI_IVPR */
case 0x10B0:
@@ -750,33 +880,51 @@ static uint64_t openpic_gbl_read(void *opaque, gpa_t addr, unsigned len)
default:
break;
}
+
+ spin_unlock_irq(&opp->lock);
+out:
pr_debug("%s: => 0x%08x\n", __func__, retval);
- return retval;
+ ret = openpic_put_val32(len, ptr, retval);
+ if (ret < 0)
+ return 1;
+
+ return 0;
}
-static void openpic_tmr_write(void *opaque, gpa_t addr, uint64_t val,
- unsigned len)
+static int openpic_tmr_write(struct kvm_io_device *this, gpa_t addr,
+ int len, const void *ptr)
{
- struct openpic *opp = opaque;
- int idx;
+ struct sub_region *sub = container_of(this, struct sub_region, iodev);
+ struct openpic *opp = sub->opp;
+ u32 val;
+ int ret, idx;
+
+ addr -= sub->base;
+ if (addr > sub->size)
+ return 1;
+
+ ret = openpic_get_val32(len, ptr, &val);
+ if (ret < 0)
+ return 1;
addr += 0x10f0;
- pr_debug("%s: addr %#" HWADDR_PRIx " <= %08" PRIx64 "\n",
- __func__, addr, val);
+ pr_debug("%s: addr %#llx <= %08x\n", __func__, addr, val);
if (addr & 0xF)
- return;
+ return 0;
if (addr == 0x10f0) {
/* TFRR */
opp->tfrr = val;
- return;
+ return 0;
}
idx = (addr >> 6) & 0x3;
addr = addr & 0x30;
+ spin_lock_irq(&opp->lock);
+
switch (addr & 0x30) {
case 0x00: /* TCCR */
break;
@@ -795,15 +943,25 @@ static void openpic_tmr_write(void *opaque, gpa_t addr, uint64_t val,
write_IRQreg_idr(opp, opp->irq_tim0 + idx, val);
break;
}
+
+ spin_unlock_irq(&opp->lock);
+
+ return 0;
}
-static uint64_t openpic_tmr_read(void *opaque, gpa_t addr, unsigned len)
+static int openpic_tmr_read(struct kvm_io_device *this, gpa_t addr,
+ int len, void *ptr)
{
- struct openpic *opp = opaque;
+ struct sub_region *sub = container_of(this, struct sub_region, iodev);
+ struct openpic *opp = sub->opp;
uint32_t retval = -1;
- int idx;
+ int ret, idx;
+
+ addr -= sub->base;
+ if (addr > sub->size)
+ return 1;
- pr_debug("%s: addr %#" HWADDR_PRIx "\n", __func__, addr);
+ pr_debug("%s: addr %#llx\n", __func__, addr);
if (addr & 0xF)
goto out;
@@ -813,6 +971,9 @@ static uint64_t openpic_tmr_read(void *opaque, gpa_t addr, unsigned len)
retval = opp->tfrr;
goto out;
}
+
+ spin_lock_irq(&opp->lock);
+
switch (addr & 0x30) {
case 0x00: /* TCCR */
retval = opp->timers[idx].tccr;
@@ -828,24 +989,40 @@ static uint64_t openpic_tmr_read(void *opaque, gpa_t addr, unsigned len)
break;
}
+ spin_unlock_irq(&opp->lock);
out:
pr_debug("%s: => 0x%08x\n", __func__, retval);
- return retval;
+ ret = openpic_put_val32(len, ptr, retval);
+ if (ret < 0)
+ return 1;
+
+ return 0;
}
-static void openpic_src_write(void *opaque, gpa_t addr, uint64_t val,
- unsigned len)
+static int openpic_src_write(struct kvm_io_device *this, gpa_t addr,
+ int len, const void *ptr)
{
- struct openpic *opp = opaque;
- int idx;
+ struct sub_region *sub = container_of(this, struct sub_region, iodev);
+ struct openpic *opp = sub->opp;
+ u32 val;
+ int ret, idx;
- pr_debug("%s: addr %#" HWADDR_PRIx " <= %08" PRIx64 "\n",
- __func__, addr, val);
+ addr -= sub->base;
+ if (addr > sub->size)
+ return 1;
+
+ ret = openpic_get_val32(len, ptr, &val);
+ if (ret < 0)
+ return 1;
+
+ pr_debug("%s: addr %#llx <= %08x\n", __func__, addr, val);
addr = addr & 0xffff;
idx = addr >> 5;
+ spin_lock_irq(&opp->lock);
+
switch (addr & 0x1f) {
case 0x00:
write_IRQreg_ivpr(opp, idx, val);
@@ -857,20 +1034,32 @@ static void openpic_src_write(void *opaque, gpa_t addr, uint64_t val,
write_IRQreg_ilr(opp, idx, val);
break;
}
+
+
+ spin_unlock_irq(&opp->lock);
+ return 0;
}
-static uint64_t openpic_src_read(void *opaque, uint64_t addr, unsigned len)
+static int openpic_src_read(struct kvm_io_device *this, uint64_t addr,
+ int len, void *ptr)
{
- struct openpic *opp = opaque;
+ struct sub_region *sub = container_of(this, struct sub_region, iodev);
+ struct openpic *opp = sub->opp;
uint32_t retval;
- int idx;
+ int ret, idx;
+
+ addr -= sub->base;
+ if (addr > sub->size)
+ return 1;
- pr_debug("%s: addr %#" HWADDR_PRIx "\n", __func__, addr);
+ pr_debug("%s: addr %#llx\n", __func__, addr);
retval = 0xFFFFFFFF;
addr = addr & 0xffff;
idx = addr >> 5;
+ spin_lock_irq(&opp->lock);
+
switch (addr & 0x1f) {
case 0x00:
retval = read_IRQreg_ivpr(opp, idx);
@@ -883,21 +1072,38 @@ static uint64_t openpic_src_read(void *opaque, uint64_t addr, unsigned len)
break;
}
+ spin_unlock_irq(&opp->lock);
pr_debug("%s: => 0x%08x\n", __func__, retval);
- return retval;
+
+ ret = openpic_put_val32(len, ptr, retval);
+ if (ret < 0)
+ return 1;
+
+ return 0;
}
-static void openpic_msi_write(void *opaque, gpa_t addr, uint64_t val,
- unsigned size)
+static int openpic_msi_write(struct kvm_io_device *this, gpa_t addr,
+ int len, const void *ptr)
{
- struct openpic *opp = opaque;
+ struct sub_region *sub = container_of(this, struct sub_region, iodev);
+ struct openpic *opp = sub->opp;
+ u32 val;
int idx = opp->irq_msi;
- int srs, ibs;
+ int srs, ibs, ret;
+
+ addr -= sub->base;
+ if (addr > sub->size)
+ return 1;
+
+ ret = openpic_get_val32(len, ptr, &val);
+ if (ret < 0)
+ return 1;
- pr_debug("%s: addr %#" HWADDR_PRIx " <= 0x%08" PRIx64 "\n",
- __func__, addr, val);
+ pr_debug("%s: addr %#llx <= 0x%08x\n", __func__, addr, val);
if (addr & 0xF)
- return;
+ return 0;
+
+ spin_lock_irq(&opp->lock);
switch (addr) {
case MSIIR_OFFSET:
@@ -911,20 +1117,31 @@ static void openpic_msi_write(void *opaque, gpa_t addr, uint64_t val,
/* most registers are read-only, thus ignored */
break;
}
+
+ spin_unlock_irq(&opp->lock);
+ return 0;
}
-static uint64_t openpic_msi_read(void *opaque, gpa_t addr, unsigned size)
+static int openpic_msi_read(struct kvm_io_device *this, gpa_t addr,
+ int len, void *ptr)
{
- struct openpic *opp = opaque;
- uint64_t r = 0;
- int i, srs;
+ struct sub_region *sub = container_of(this, struct sub_region, iodev);
+ struct openpic *opp = sub->opp;
+ uint32_t r = 0;
+ int i, srs, ret;
+
+ addr -= sub->base;
+ if (addr > sub->size)
+ return 1;
- pr_debug("%s: addr %#" HWADDR_PRIx "\n", __func__, addr);
+ pr_debug("%s: addr %#llx\n", __func__, addr);
if (addr & 0xF)
- return -1;
+ return 1;
srs = addr >> 4;
+ spin_lock_irq(&opp->lock);
+
switch (addr) {
case 0x00:
case 0x10:
@@ -945,45 +1162,76 @@ static uint64_t openpic_msi_read(void *opaque, gpa_t addr, unsigned size)
break;
}
- return r;
+ spin_unlock_irq(&opp->lock);
+ pr_debug("%s: => 0x%08x\n", __func__, r);
+
+ ret = openpic_put_val32(len, ptr, r);
+ if (ret < 0)
+ return 1;
+
+ return 0;
}
-static uint64_t openpic_summary_read(void *opaque, gpa_t addr, unsigned size)
+static int openpic_summary_read(struct kvm_io_device *this, gpa_t addr,
+ int len, void *ptr)
{
- uint64_t r = 0;
+ struct sub_region *sub = container_of(this, struct sub_region, iodev);
+ uint32_t r = 0;
+ int ret;
- pr_debug("%s: addr %#" HWADDR_PRIx "\n", __func__, addr);
+ addr -= sub->base;
+ if (addr > sub->size)
+ return 1;
+
+ pr_debug("%s: addr %#llx\n", __func__, addr);
/* TODO: EISR/EIMR */
- return r;
+ ret = openpic_put_val32(len, ptr, r);
+ if (ret < 0)
+ return 1;
+
+ return 0;
}
-static void openpic_summary_write(void *opaque, gpa_t addr, uint64_t val,
- unsigned size)
+static int openpic_summary_write(struct kvm_io_device *this, gpa_t addr,
+ int len, const void *ptr)
{
- pr_debug("%s: addr %#" HWADDR_PRIx " <= 0x%08" PRIx64 "\n",
- __func__, addr, val);
+ struct sub_region *sub = container_of(this, struct sub_region, iodev);
+ int ret;
+ uint32_t val;
+
+ addr -= sub->base;
+ if (addr > sub->size)
+ return 1;
+
+ ret = openpic_get_val32(len, ptr, &val);
+ if (ret < 0)
+ return 1;
+
+ pr_debug("%s: addr %#llx <= 0x%08x\n", __func__, addr, val);
/* TODO: EISR/EIMR */
+ return 0;
}
-static void openpic_cpu_write_internal(void *opaque, gpa_t addr,
- uint32_t val, int idx)
+static int openpic_cpu_write_internal(struct kvm_io_device *this, gpa_t addr,
+ u32 val, int idx)
{
- struct openpic *opp = opaque;
+ struct sub_region *sub = container_of(this, struct sub_region, iodev);
+ struct openpic *opp = sub->opp;
struct irq_source *src;
struct irq_dest *dst;
int s_IRQ, n_IRQ;
- pr_debug("%s: cpu %d addr %#" HWADDR_PRIx " <= 0x%08x\n", __func__, idx,
+ pr_debug("%s: cpu %d addr %#llx <= 0x%08x\n", __func__, idx,
addr, val);
if (idx < 0)
- return;
+ return 0;
if (addr & 0xF)
- return;
+ return 0;
dst = &opp->dst[idx];
addr &= 0xFF0;
@@ -1008,11 +1256,11 @@ static void openpic_cpu_write_internal(void *opaque, gpa_t addr,
if (dst->raised.priority <= dst->ctpr) {
pr_debug("%s: Lower OpenPIC INT output cpu %d due to ctpr\n",
__func__, idx);
- qemu_irq_lower(dst->irqs[OPENPIC_OUTPUT_INT]);
+ mpic_irq_lower(opp, dst, ILR_INTTGT_INT);
} else if (dst->raised.priority > dst->servicing.priority) {
pr_debug("%s: Raise OpenPIC INT output cpu %d irq %d\n",
__func__, idx, dst->raised.next);
- qemu_irq_raise(dst->irqs[OPENPIC_OUTPUT_INT]);
+ mpic_irq_raise(opp, dst, ILR_INTTGT_INT);
}
break;
@@ -1043,18 +1291,38 @@ static void openpic_cpu_write_internal(void *opaque, gpa_t addr,
IVPR_PRIORITY(src->ivpr) > dst->servicing.priority)) {
pr_debug("Raise OpenPIC INT output cpu %d irq %d\n",
idx, n_IRQ);
- qemu_irq_raise(opp->dst[idx].irqs[OPENPIC_OUTPUT_INT]);
+ mpic_irq_raise(opp, dst, ILR_INTTGT_INT);
}
break;
default:
break;
}
+
+ return 0;
}
-static void openpic_cpu_write(void *opaque, gpa_t addr, uint64_t val,
- unsigned len)
+static int openpic_cpu_write(struct kvm_io_device *this, gpa_t addr,
+ int len, const void *ptr)
{
- openpic_cpu_write_internal(opaque, addr, val, (addr & 0x1f000) >> 12);
+ struct sub_region *sub = container_of(this, struct sub_region, iodev);
+ struct openpic *opp = sub->opp;
+ u32 val;
+ int ret;
+
+ addr -= sub->base;
+ if (addr > sub->size)
+ return 1;
+
+ ret = openpic_get_val32(len, ptr, &val);
+ if (ret < 0)
+ return 1;
+
+ spin_lock_irq(&opp->lock);
+ ret = openpic_cpu_write_internal(this, addr, val,
+ (addr & 0x1f000) >> 12);
+
+ spin_unlock_irq(&opp->lock);
+ return ret;
}
static uint32_t openpic_iack(struct openpic *opp, struct irq_dest *dst,
@@ -1064,7 +1332,7 @@ static uint32_t openpic_iack(struct openpic *opp, struct irq_dest *dst,
int retval, irq;
pr_debug("Lower OpenPIC INT output\n");
- qemu_irq_lower(dst->irqs[OPENPIC_OUTPUT_INT]);
+ mpic_irq_lower(opp, dst, ILR_INTTGT_INT);
irq = IRQ_get_next(opp, &dst->raised);
pr_debug("IACK: irq=%d\n", irq);
@@ -1107,20 +1375,37 @@ static uint32_t openpic_iack(struct openpic *opp, struct irq_dest *dst,
return retval;
}
-static uint32_t openpic_cpu_read_internal(void *opaque, gpa_t addr, int idx)
+void kvmppc_mpic_set_epr(struct kvm_vcpu *vcpu)
{
- struct openpic *opp = opaque;
+ struct kvm *kvm = vcpu->kvm;
+ struct openpic *opp = kvm->arch.irqchip_priv;
+ int cpu = vcpu->vcpu_id;
+ unsigned long flags;
+
+ spin_lock_irqsave(&opp->lock, flags);
+
+ if ((opp->gcr & opp->mpic_mode_mask) == GCR_MODE_PROXY)
+ kvmppc_set_epr(vcpu, openpic_iack(opp, &opp->dst[cpu], cpu));
+
+ spin_unlock_irqrestore(&opp->lock, flags);
+}
+
+static int openpic_cpu_read_internal(struct kvm_io_device *this, gpa_t addr,
+ u32 *ptr, int idx)
+{
+ struct sub_region *sub = container_of(this, struct sub_region, iodev);
+ struct openpic *opp = sub->opp;
struct irq_dest *dst;
uint32_t retval;
- pr_debug("%s: cpu %d addr %#" HWADDR_PRIx "\n", __func__, idx, addr);
+ pr_debug("%s: cpu %d addr %#llx\n", __func__, idx, addr);
retval = 0xFFFFFFFF;
if (idx < 0)
- return retval;
+ goto out;
if (addr & 0xF)
- return retval;
+ goto out;
dst = &opp->dst[idx];
addr &= 0xFF0;
@@ -1142,12 +1427,35 @@ static uint32_t openpic_cpu_read_internal(void *opaque, gpa_t addr, int idx)
}
pr_debug("%s: => 0x%08x\n", __func__, retval);
- return retval;
+out:
+ *ptr = retval;
+ return 0;
}
-static uint64_t openpic_cpu_read(void *opaque, gpa_t addr, unsigned len)
+static int openpic_cpu_read(struct kvm_io_device *this, gpa_t addr,
+ int len, void *ptr)
{
- return openpic_cpu_read_internal(opaque, addr, (addr & 0x1f000) >> 12);
+ struct sub_region *sub = container_of(this, struct sub_region, iodev);
+ struct openpic *opp = sub->opp;
+ int ret;
+ u32 val;
+
+ addr -= sub->base;
+ if (addr > sub->size)
+ return 1;
+
+ spin_lock_irq(&opp->lock);
+ ret = openpic_cpu_read_internal(this, addr, &val,
+ (addr & 0x1f000) >> 12);
+ spin_unlock_irq(&opp->lock);
+ if (ret < 0)
+ return 1;
+
+ ret = openpic_put_val32(len, ptr, val);
+ if (ret < 0)
+ return 1;
+
+ return 0;
}
static const struct kvm_io_device_ops openpic_glb_ops_be = {
@@ -1205,11 +1513,10 @@ static void fsl_common_init(struct openpic *opp)
opp->irq_tim0 = virq;
virq += MAX_TMR;
- assert(virq <= MAX_IRQ);
+ BUG_ON(virq > MAX_IRQ);
opp->irq_msi = 224;
- msi_supported = true;
for (i = 0; i < opp->fsl->max_ext; i++)
opp->src[i].level = false;
@@ -1226,39 +1533,55 @@ static void fsl_common_init(struct openpic *opp)
}
}
-static void map_list(struct openpic *opp, const struct mem_reg *list,
- int *count)
+static void map_list(struct openpic *opp, const struct mem_reg *list)
{
+ mutex_lock(&opp->kvm->slots_lock);
+
while (list->name) {
- assert(*count < ARRAY_SIZE(opp->sub_io_mem));
+ struct sub_region *sub;
+
+ BUG_ON(opp->sub_count >= ARRAY_SIZE(opp->sub_io_mem));
- memory_region_init_io(&opp->sub_io_mem[*count], list->ops, opp,
- list->name, list->size);
+ sub = &opp->sub_io_mem[opp->sub_count];
+ sub->opp = opp;
+ sub->base = opp->reg_base + list->start_addr;
+ sub->size = list->size;
- memory_region_add_subregion(&opp->mem, list->start_addr,
- &opp->sub_io_mem[*count]);
+ kvm_iodevice_init(&sub->iodev, list->ops);
- (*count)++;
+ kvm_io_bus_register_dev(opp->kvm, KVM_MMIO_BUS,
+ opp->reg_base + list->start_addr, list->size,
+ &sub->iodev);
+
+ opp->sub_count++;
list++;
}
+
+ mutex_unlock(&opp->kvm->slots_lock);
+}
+
+static void unmap_all(struct openpic *opp)
+{
+ int i;
+
+ mutex_lock(&opp->kvm->slots_lock);
+
+ for (i = 0; i < opp->sub_count; i++) {
+ kvm_io_bus_unregister_dev(opp->kvm, KVM_MMIO_BUS,
+ &opp->sub_io_mem[i].iodev);
+ }
+
+ mutex_unlock(&opp->kvm->slots_lock);
+
+ opp->sub_count = 0;
}
-static int openpic_init(SysBusDevice *dev)
+static int set_base_addr(struct kvm *kvm, struct kvm_device *dev,
+ struct kvm_device_attr *attr)
{
- struct openpic *opp = FROM_SYSBUS(typeof(*opp), dev);
- int i, j;
- int list_count = 0;
- static const struct mem_reg list_le[] = {
- {"glb", &openpic_glb_ops_le,
- OPENPIC_GLB_REG_START, OPENPIC_GLB_REG_SIZE},
- {"tmr", &openpic_tmr_ops_le,
- OPENPIC_TMR_REG_START, OPENPIC_TMR_REG_SIZE},
- {"src", &openpic_src_ops_le,
- OPENPIC_SRC_REG_START, OPENPIC_SRC_REG_SIZE},
- {"cpu", &openpic_cpu_ops_le,
- OPENPIC_CPU_REG_START, OPENPIC_CPU_REG_SIZE},
- {NULL}
- };
+ struct openpic *opp = container_of(dev, struct openpic, dev);
+ u64 base;
+
static const struct mem_reg list_be[] = {
{"glb", &openpic_glb_ops_be,
OPENPIC_GLB_REG_START, OPENPIC_GLB_REG_SIZE},
@@ -1278,11 +1601,239 @@ static int openpic_init(SysBusDevice *dev)
{NULL}
};
- memory_region_init(&opp->mem, "openpic", 0x40000);
+ if (copy_from_user(&base, (u64 __iomem *)(long)attr->addr, sizeof(u64)))
+ return -EFAULT;
+
+ if (base & 0x3ffff) {
+ pr_debug("kvm mpic %s: KVM_DEV_MPIC_BASE_ADDR %08llx not aligned\n",
+ __func__, base);
+ return -EINVAL;
+ }
+
+ if (base == opp->reg_base)
+ return 0;
+
+ unmap_all(opp);
+ opp->reg_base = base;
+
+ pr_debug("kvm mpic %s: KVM_DEV_MPIC_BASE_ADDR %08llx\n",
+ __func__, base);
+
+ if (base == 0)
+ return 0;
switch (opp->model) {
- case OPENPIC_MODEL_FSL_MPIC_20:
+ case KVM_DEV_TYPE_FSL_MPIC_20:
+ map_list(opp, list_be);
+ map_list(opp, list_fsl);
+
+ break;
+
+ case KVM_DEV_TYPE_FSL_MPIC_42:
+ map_list(opp, list_be);
+ map_list(opp, list_fsl);
+
+ break;
+
default:
+ WARN_ON_ONCE(1);
+ }
+
+ return 0;
+}
+
+#define ATTR_SET 0
+#define ATTR_GET 1
+
+static int access_reg(struct openpic *opp, gpa_t addr, u32 *val, int type)
+{
+ int ret;
+
+ if (!opp->sub_count)
+ return -EPERM;
+
+ if (addr & 3)
+ return -ENXIO;
+
+ if (addr > 0x40000)
+ return -ENXIO;
+
+ addr += opp->reg_base;
+
+ mutex_lock(&opp->kvm->slots_lock);
+
+ if (type == ATTR_SET)
+ ret = kvm_io_bus_write(opp->kvm, KVM_MMIO_BUS, addr, 4, val);
+ else
+ ret = kvm_io_bus_read(opp->kvm, KVM_MMIO_BUS, addr, 4, val);
+
+ mutex_unlock(&opp->kvm->slots_lock);
+
+ pr_debug("%s: type %d addr %llx val %x\n", __func__, type, addr, *val);
+
+ return ret;
+}
+
+static int mpic_set_attr(struct kvm *kvm, struct kvm_device *dev,
+ struct kvm_device_attr *attr)
+{
+ struct openpic *opp = container_of(dev, struct openpic, dev);
+ u32 attr32;
+
+ switch (attr->group) {
+ case KVM_DEV_MPIC_GRP_MISC:
+ switch (attr->attr) {
+ case KVM_DEV_MPIC_BASE_ADDR:
+ return set_base_addr(kvm, dev, attr);
+ }
+
+ break;
+
+ case KVM_DEV_MPIC_GRP_REGISTER:
+ if (copy_from_user(&attr32, (u32 __user *)(long)attr->addr,
+ sizeof(u32)))
+ return -EFAULT;
+
+ return access_reg(opp, attr->attr, &attr32, ATTR_SET);
+
+ case KVM_DEV_MPIC_GRP_IRQ_ACTIVE:
+ if (attr->attr > MAX_SRC)
+ return -EINVAL;
+
+ if (copy_from_user(&attr32, (u32 __user *)(long)attr->addr,
+ sizeof(u32)))
+ return -EFAULT;
+
+ if (attr32 != 0 && attr32 != 1)
+ return -EINVAL;
+
+ spin_lock_irq(&opp->lock);
+ openpic_set_irq(opp, attr->attr, attr32);
+ spin_unlock_irq(&opp->lock);
+ return 0;
+ }
+
+ return -ENXIO;
+}
+
+static int mpic_get_attr(struct kvm *kvm, struct kvm_device *dev,
+ struct kvm_device_attr *attr)
+{
+ struct openpic *opp = container_of(dev, struct openpic, dev);
+ u64 attr64;
+ u32 attr32;
+ int ret;
+
+ switch (attr->group) {
+ case KVM_DEV_MPIC_GRP_MISC:
+ switch (attr->attr) {
+ case KVM_DEV_MPIC_BASE_ADDR:
+ attr64 = opp->reg_base;
+
+ if (copy_to_user((u64 __user *)(long)attr->addr,
+ &attr64, sizeof(u64)))
+ return -EFAULT;
+
+ return 0;
+ }
+
+ break;
+
+ case KVM_DEV_MPIC_GRP_REGISTER:
+ ret = access_reg(opp, attr->attr, &attr32, ATTR_GET);
+ if (ret)
+ return ret;
+
+ if (copy_to_user((u32 __user *)(long)attr->addr, &attr32,
+ sizeof(u32)))
+ return -EFAULT;
+
+ return 0;
+
+ case KVM_DEV_MPIC_GRP_IRQ_ACTIVE:
+ if (attr->attr > MAX_SRC)
+ return -EINVAL;
+
+ attr32 = opp->src[attr->attr].pending;
+
+ if (copy_to_user((u32 __user *)(long)attr->addr, &attr32,
+ sizeof(u32)))
+ return -EFAULT;
+
+ return 0;
+ }
+
+ return -ENXIO;
+}
+
+static void mpic_destroy(struct kvm *kvm, struct kvm_device *dev)
+{
+ struct openpic *opp = container_of(dev, struct openpic, dev);
+
+ blocking_notifier_chain_unregister(&kvm->vcpu_notifier,
+ &opp->vcpu_notifier);
+
+ unmap_all(opp);
+ kfree(opp);
+}
+
+static int add_cpu(struct openpic *opp, struct kvm_vcpu *vcpu)
+{
+ u32 id = vcpu->vcpu_id;
+
+ if (id < 0 || id >= MAX_CPU)
+ return -EPERM;
+
+ spin_lock_irq(&opp->lock);
+
+ WARN_ON(opp->dst[id].vcpu);
+ opp->dst[id].vcpu = vcpu;
+ opp->nb_cpus = max(opp->nb_cpus, id + 1);
+
+ spin_unlock_irq(&opp->lock);
+
+ if (opp->mpic_mode_mask == GCR_MODE_PROXY)
+ vcpu->arch.epr_flags |= KVMPPC_EPR_KERNEL;
+
+ return 0;
+}
+
+static int kvm_mpic_vcpu_notifier(struct notifier_block *nb,
+ unsigned long create, void *v)
+{
+ struct openpic *opp = container_of(nb, struct openpic, vcpu_notifier);
+ struct kvm_vcpu *vcpu = v;
+ int ret;
+
+ if (create) {
+ ret = add_cpu(opp, vcpu);
+ if (ret < 0)
+ return notifier_from_errno(ret);
+ }
+
+ return NOTIFY_OK;
+}
+
+int kvm_create_mpic(struct kvm *kvm, u32 type, struct kvm_device **dev)
+{
+ struct openpic *opp;
+ struct kvm_vcpu *vcpu;
+ int ret, i;
+
+ if (kvm->arch.irqchip_priv)
+ return -EEXIST;
+
+ opp = kzalloc(sizeof(struct openpic), GFP_KERNEL);
+ if (!opp)
+ return 0;
+
+ kvm->arch.irqchip_priv = opp;
+ opp->kvm = kvm;
+ opp->model = type;
+ spin_lock_init(&opp->lock);
+
+ switch (opp->model) {
+ case KVM_DEV_TYPE_FSL_MPIC_20:
opp->fsl = &fsl_mpic_20;
opp->brr1 = 0x00400200;
opp->flags |= OPENPIC_FLAG_IDR_CRIT;
@@ -1290,12 +1841,10 @@ static int openpic_init(SysBusDevice *dev)
opp->mpic_mode_mask = GCR_MODE_MIXED;
fsl_common_init(opp);
- map_list(opp, list_be, &list_count);
- map_list(opp, list_fsl, &list_count);
break;
- case OPENPIC_MODEL_FSL_MPIC_42:
+ case KVM_DEV_TYPE_FSL_MPIC_42:
opp->fsl = &fsl_mpic_42;
opp->brr1 = 0x00400402;
opp->flags |= OPENPIC_FLAG_ILR;
@@ -1303,11 +1852,39 @@ static int openpic_init(SysBusDevice *dev)
opp->mpic_mode_mask = GCR_MODE_PROXY;
fsl_common_init(opp);
- map_list(opp, list_be, &list_count);
- map_list(opp, list_fsl, &list_count);
break;
+
+ default:
+ ret = -ENODEV;
+ goto err;
}
+ openpic_reset(opp);
+
+ opp->dev.type = type;
+ opp->dev.set_attr = mpic_set_attr;
+ opp->dev.get_attr = mpic_get_attr;
+ opp->dev.destroy = mpic_destroy;
+ *dev = &opp->dev;
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ ret = add_cpu(opp, vcpu);
+ if (ret < 0)
+ goto err;
+ }
+
+ opp->vcpu_notifier.notifier_call = kvm_mpic_vcpu_notifier;
+
+ /* FIXME: register notifier for subsequently created vcpus */
+ ret = blocking_notifier_chain_register(&kvm->vcpu_notifier,
+ &opp->vcpu_notifier);
+ if (ret < 0)
+ goto err;
+
return 0;
+
+err:
+ kfree(opp);
+ return ret;
}
@@ -317,6 +317,7 @@ int kvm_dev_ioctl_check_extension(long ext)
case KVM_CAP_ENABLE_CAP:
case KVM_CAP_ONE_REG:
case KVM_CAP_IOEVENTFD:
+ case KVM_CAP_DEVICE_CTRL:
r = 1;
break;
#ifndef CONFIG_KVM_BOOK3S_64_HV
@@ -781,7 +782,10 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
break;
case KVM_CAP_PPC_EPR:
r = 0;
- vcpu->arch.epr_enabled = cap->args[0];
+ if (cap->args[0])
+ vcpu->arch.epr_flags |= KVMPPC_EPR_USER;
+ else
+ vcpu->arch.epr_flags &= ~KVMPPC_EPR_USER;
break;
#ifdef CONFIG_BOOKE
case KVM_CAP_PPC_BOOKE_WATCHDOG:
@@ -927,6 +931,7 @@ static int kvm_vm_ioctl_get_pvinfo(struct kvm_ppc_pvinfo *pvinfo)
long kvm_arch_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
+ struct kvm *kvm __maybe_unused = filp->private_data;
void __user *argp = (void __user *)arg;
long r;
@@ -945,7 +950,6 @@ long kvm_arch_vm_ioctl(struct file *filp,
#ifdef CONFIG_PPC_BOOK3S_64
case KVM_CREATE_SPAPR_TCE: {
struct kvm_create_spapr_tce create_tce;
- struct kvm *kvm = filp->private_data;
r = -EFAULT;
if (copy_from_user(&create_tce, argp, sizeof(create_tce)))
@@ -957,7 +961,6 @@ long kvm_arch_vm_ioctl(struct file *filp,
#ifdef CONFIG_KVM_BOOK3S_64_HV
case KVM_ALLOCATE_RMA: {
- struct kvm *kvm = filp->private_data;
struct kvm_allocate_rma rma;
r = kvm_vm_ioctl_allocate_rma(kvm, &rma);
@@ -967,7 +970,6 @@ long kvm_arch_vm_ioctl(struct file *filp,
}
case KVM_PPC_ALLOCATE_HTAB: {
- struct kvm *kvm = filp->private_data;
u32 htab_order;
r = -EFAULT;
@@ -984,7 +986,6 @@ long kvm_arch_vm_ioctl(struct file *filp,
}
case KVM_PPC_GET_HTAB_FD: {
- struct kvm *kvm = filp->private_data;
struct kvm_get_htab_fd ghf;
r = -EFAULT;
@@ -997,7 +998,6 @@ long kvm_arch_vm_ioctl(struct file *filp,
#ifdef CONFIG_PPC_BOOK3S_64
case KVM_PPC_GET_SMMU_INFO: {
- struct kvm *kvm = filp->private_data;
struct kvm_ppc_smmu_info info;
memset(&info, 0, sizeof(info));
@@ -1059,5 +1059,7 @@ static inline bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
}
#endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */
-#endif
+int kvm_create_mpic(struct kvm *kvm, u32 type, struct kvm_device **dev);
+
+#endif
@@ -910,10 +910,19 @@ struct kvm_device_attr {
#define KVM_DEV_ATTR_COMMON 0
#define KVM_DEV_ATTR_TYPE 0 /* 32-bit */
-#define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xac, struct kvm_create_device)
-#define KVM_SET_DEVICE_ATTR _IOW(KVMIO, 0xad, struct kvm_device_attr)
-#define KVM_GET_DEVICE_ATTR _IOW(KVMIO, 0xae, struct kvm_device_attr)
-#define KVM_HAS_DEVICE_ATTR _IOW(KVMIO, 0xaf, struct kvm_device_attr)
+#define KVM_DEV_TYPE_FSL_MPIC_20 1
+#define KVM_DEV_TYPE_FSL_MPIC_42 2
+
+#define KVM_DEV_MPIC_GRP_MISC 1
+#define KVM_DEV_MPIC_BASE_ADDR 0 /* 64-bit */
+
+#define KVM_DEV_MPIC_GRP_REGISTER 2 /* 32-bit */
+#define KVM_DEV_MPIC_GRP_IRQ_ACTIVE 3 /* 32-bit */
+
+#define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xab, struct kvm_create_device)
+#define KVM_SET_DEVICE_ATTR _IOW(KVMIO, 0xac, struct kvm_device_attr)
+#define KVM_GET_DEVICE_ATTR _IOW(KVMIO, 0xad, struct kvm_device_attr)
+#define KVM_HAS_DEVICE_ATTR _IOW(KVMIO, 0xae, struct kvm_device_attr)
/*
* ioctls for vcpu fds
@@ -2210,6 +2210,18 @@ static int kvm_ioctl_create_device(struct kvm *kvm,
}
switch (cd->type) {
+#ifdef CONFIG_KVM_MPIC
+ case KVM_DEV_TYPE_FSL_MPIC_20:
+ case KVM_DEV_TYPE_FSL_MPIC_42: {
+ if (test) {
+ r = 0;
+ break;
+ }
+
+ r = kvm_create_mpic(kvm, cd->type, &dev);
+ break;
+ }
+#endif
default:
r = -ENODEV;
goto out;
Hook the MPIC code up to the KVM interfaces, add locking, etc. TODO: irqfd support Signed-off-by: Scott Wood <scottwood@freescale.com> --- Documentation/virtual/kvm/devices/mpic.txt | 36 ++ arch/powerpc/include/asm/kvm_host.h | 9 +- arch/powerpc/include/asm/kvm_ppc.h | 4 + arch/powerpc/kvm/Kconfig | 5 + arch/powerpc/kvm/Makefile | 2 + arch/powerpc/kvm/booke.c | 10 +- arch/powerpc/kvm/mpic.c | 875 +++++++++++++++++++++++----- arch/powerpc/kvm/powerpc.c | 12 +- include/linux/kvm_host.h | 4 +- include/uapi/linux/kvm.h | 17 +- virt/kvm/kvm_main.c | 12 + 11 files changed, 822 insertions(+), 164 deletions(-) create mode 100644 Documentation/virtual/kvm/devices/mpic.txt