summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2017-05-10 11:29:23 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2017-05-10 11:29:23 -0700
commit5ccd414080822d5257c3569f4aeca74f63f4a257 (patch)
tree4b567bfc0a8b29dbac9712821062b28337eb3408
parent29250d301b0c75ef142b51eebee6b7403cc79624 (diff)
parent36c344f3f1ffc0b1b20abd237b7401dc6687ee8f (diff)
downloadlinux-5ccd414080822d5257c3569f4aeca74f63f4a257.tar.bz2
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull more KVM updates from Paolo Bonzini: "ARM: - bugfixes - moved shared 32-bit/64-bit files to virt/kvm/arm - support for saving/restoring virtual ITS state to userspace PPC: - XIVE (eXternal Interrupt Virtualization Engine) support x86: - nVMX improvements, including emulated page modification logging (PML) which brings nice performance improvements on some workloads" * tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (45 commits) KVM: arm/arm64: vgic-its: Cleanup after failed ITT restore KVM: arm/arm64: Don't call map_resources when restoring ITS tables KVM: arm/arm64: Register ITS iodev when setting base address KVM: arm/arm64: Get rid of its->initialized field KVM: arm/arm64: Register iodevs when setting redist base and creating VCPUs KVM: arm/arm64: Slightly rework kvm_vgic_addr KVM: arm/arm64: Make vgic_v3_check_base more broadly usable KVM: arm/arm64: Refactor vgic_register_redist_iodevs KVM: Add kvm_vcpu_get_idx to get vcpu index in kvm->vcpus nVMX: Advertise PML to L1 hypervisor nVMX: Implement emulated Page Modification Logging kvm: x86: Add a hook for arch specific dirty logging emulation kvm: nVMX: Validate CR3 target count on nested VM-entry KVM: set no_llseek in stat_fops_per_vm KVM: arm/arm64: vgic: Rename kvm_vgic_vcpu_init to kvm_vgic_vcpu_enable KVM: arm/arm64: Clarification and relaxation to ITS save/restore ABI KVM: arm64: vgic-v3: KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES KVM: arm64: vgic-its: Fix pending table sync KVM: arm64: vgic-its: ITT save and restore KVM: arm64: vgic-its: Device table save/restore ...
-rw-r--r--Documentation/virtual/kvm/devices/arm-vgic-its.txt121
-rw-r--r--Documentation/virtual/kvm/devices/arm-vgic-v3.txt6
-rw-r--r--arch/arm/include/uapi/asm/kvm.h6
-rw-r--r--arch/arm/kvm/Makefile7
-rw-r--r--arch/arm/kvm/trace.h247
-rw-r--r--arch/arm64/include/asm/kvm_emulate.h6
-rw-r--r--arch/arm64/include/uapi/asm/kvm.h6
-rw-r--r--arch/arm64/kvm/Makefile5
-rw-r--r--arch/arm64/kvm/sys_regs.c8
-rw-r--r--arch/powerpc/include/asm/kvm_book3s_asm.h2
-rw-r--r--arch/powerpc/include/asm/kvm_host.h28
-rw-r--r--arch/powerpc/include/asm/kvm_ppc.h74
-rw-r--r--arch/powerpc/include/asm/xive.h9
-rw-r--r--arch/powerpc/kernel/asm-offsets.c10
-rw-r--r--arch/powerpc/kvm/Kconfig5
-rw-r--r--arch/powerpc/kvm/Makefile4
-rw-r--r--arch/powerpc/kvm/book3s.c75
-rw-r--r--arch/powerpc/kvm/book3s_hv.c51
-rw-r--r--arch/powerpc/kvm/book3s_hv_builtin.c103
-rw-r--r--arch/powerpc/kvm/book3s_hv_rm_xics.c10
-rw-r--r--arch/powerpc/kvm/book3s_hv_rm_xive.c47
-rw-r--r--arch/powerpc/kvm/book3s_hv_rmhandlers.S62
-rw-r--r--arch/powerpc/kvm/book3s_rtas.c21
-rw-r--r--arch/powerpc/kvm/book3s_xics.c35
-rw-r--r--arch/powerpc/kvm/book3s_xics.h7
-rw-r--r--arch/powerpc/kvm/book3s_xive.c1894
-rw-r--r--arch/powerpc/kvm/book3s_xive.h256
-rw-r--r--arch/powerpc/kvm/book3s_xive_template.c503
-rw-r--r--arch/powerpc/kvm/irq.h1
-rw-r--r--arch/powerpc/kvm/powerpc.c17
-rw-r--r--arch/powerpc/platforms/powernv/opal.c1
-rw-r--r--arch/powerpc/sysdev/xive/common.c142
-rw-r--r--arch/powerpc/sysdev/xive/native.c86
-rw-r--r--arch/x86/include/asm/kvm_host.h2
-rw-r--r--arch/x86/kvm/mmu.c15
-rw-r--r--arch/x86/kvm/mmu.h1
-rw-r--r--arch/x86/kvm/paging_tmpl.h4
-rw-r--r--arch/x86/kvm/vmx.c105
-rw-r--r--include/kvm/arm_vgic.h5
-rw-r--r--include/linux/irqchip/arm-gic-v3.h14
-rw-r--r--include/linux/kvm_host.h12
-rw-r--r--virt/kvm/arm/arm.c (renamed from arch/arm/kvm/arm.c)2
-rw-r--r--virt/kvm/arm/mmio.c (renamed from arch/arm/kvm/mmio.c)0
-rw-r--r--virt/kvm/arm/mmu.c (renamed from arch/arm/kvm/mmu.c)0
-rw-r--r--virt/kvm/arm/perf.c (renamed from arch/arm/kvm/perf.c)0
-rw-r--r--virt/kvm/arm/psci.c (renamed from arch/arm/kvm/psci.c)0
-rw-r--r--virt/kvm/arm/trace.h246
-rw-r--r--virt/kvm/arm/vgic/trace.h37
-rw-r--r--virt/kvm/arm/vgic/vgic-init.c25
-rw-r--r--virt/kvm/arm/vgic/vgic-its.c1234
-rw-r--r--virt/kvm/arm/vgic/vgic-kvm-device.c53
-rw-r--r--virt/kvm/arm/vgic/vgic-mmio-v3.c147
-rw-r--r--virt/kvm/arm/vgic/vgic-mmio.c11
-rw-r--r--virt/kvm/arm/vgic/vgic-mmio.h14
-rw-r--r--virt/kvm/arm/vgic/vgic-v3.c128
-rw-r--r--virt/kvm/arm/vgic/vgic.c2
-rw-r--r--virt/kvm/arm/vgic/vgic.h33
-rw-r--r--virt/kvm/kvm_main.c8
58 files changed, 5318 insertions, 635 deletions
diff --git a/Documentation/virtual/kvm/devices/arm-vgic-its.txt b/Documentation/virtual/kvm/devices/arm-vgic-its.txt
index 6081a5b7fc1e..eb06beb75960 100644
--- a/Documentation/virtual/kvm/devices/arm-vgic-its.txt
+++ b/Documentation/virtual/kvm/devices/arm-vgic-its.txt
@@ -32,7 +32,128 @@ Groups:
KVM_DEV_ARM_VGIC_CTRL_INIT
request the initialization of the ITS, no additional parameter in
kvm_device_attr.addr.
+
+ KVM_DEV_ARM_ITS_SAVE_TABLES
+ save the ITS table data into guest RAM, at the location provisioned
+ by the guest in corresponding registers/table entries.
+
+ The layout of the tables in guest memory defines an ABI. The entries
+ are laid out in little endian format as described in the last paragraph.
+
+ KVM_DEV_ARM_ITS_RESTORE_TABLES
+ restore the ITS tables from guest RAM to ITS internal structures.
+
+ The GICV3 must be restored before the ITS and all ITS registers but
+ the GITS_CTLR must be restored before restoring the ITS tables.
+
+ The GITS_IIDR read-only register must also be restored before
+ calling KVM_DEV_ARM_ITS_RESTORE_TABLES as the IIDR revision field
+ encodes the ABI revision.
+
+ The expected ordering when restoring the GICv3/ITS is described in section
+ "ITS Restore Sequence".
+
Errors:
-ENXIO: ITS not properly configured as required prior to setting
this attribute
-ENOMEM: Memory shortage when allocating ITS internal data
+ -EINVAL: Inconsistent restored data
+ -EFAULT: Invalid guest ram access
+ -EBUSY: One or more VCPUS are running
+
+ KVM_DEV_ARM_VGIC_GRP_ITS_REGS
+ Attributes:
+ The attr field of kvm_device_attr encodes the offset of the
+ ITS register, relative to the ITS control frame base address
+ (ITS_base).
+
+ kvm_device_attr.addr points to a __u64 value whatever the width
+ of the addressed register (32/64 bits). 64 bit registers can only
+ be accessed with full length.
+
+ Writes to read-only registers are ignored by the kernel except for:
+ - GITS_CREADR. It must be restored otherwise commands in the queue
+ will be re-executed after restoring CWRITER. GITS_CREADR must be
+ restored before restoring the GITS_CTLR which is likely to enable the
+ ITS. Also it must be restored after GITS_CBASER since a write to
+ GITS_CBASER resets GITS_CREADR.
+ - GITS_IIDR. The Revision field encodes the table layout ABI revision.
+ In the future we might implement direct injection of virtual LPIs.
+ This will require an upgrade of the table layout and an evolution of
+ the ABI. GITS_IIDR must be restored before calling
+ KVM_DEV_ARM_ITS_RESTORE_TABLES.
+
+ For other registers, getting or setting a register has the same
+ effect as reading/writing the register on real hardware.
+ Errors:
+ -ENXIO: Offset does not correspond to any supported register
+ -EFAULT: Invalid user pointer for attr->addr
+ -EINVAL: Offset is not 64-bit aligned
+ -EBUSY: one or more VCPUS are running
+
+ ITS Restore Sequence:
+ -------------------------
+
+The following ordering must be followed when restoring the GIC and the ITS:
+a) restore all guest memory and create vcpus
+b) restore all redistributors
+c) provide the its base address
+ (KVM_DEV_ARM_VGIC_GRP_ADDR)
+d) restore the ITS in the following order:
+ 1. Restore GITS_CBASER
+ 2. Restore all other GITS_ registers, except GITS_CTLR!
+ 3. Load the ITS table data (KVM_DEV_ARM_ITS_RESTORE_TABLES)
+ 4. Restore GITS_CTLR
+
+Then vcpus can be started.
+
+ ITS Table ABI REV0:
+ -------------------
+
+ Revision 0 of the ABI only supports the features of a virtual GICv3, and does
+ not support a virtual GICv4 with support for direct injection of virtual
+ interrupts for nested hypervisors.
+
+ The device table and ITT are indexed by the DeviceID and EventID,
+ respectively. The collection table is not indexed by CollectionID, and the
+ entries in the collection are listed in no particular order.
+ All entries are 8 bytes.
+
+ Device Table Entry (DTE):
+
+ bits: | 63| 62 ... 49 | 48 ... 5 | 4 ... 0 |
+ values: | V | next | ITT_addr | Size |
+
+ where;
+ - V indicates whether the entry is valid. If not, other fields
+ are not meaningful.
+ - next: equals to 0 if this entry is the last one; otherwise it
+ corresponds to the DeviceID offset to the next DTE, capped by
+ 2^14 -1.
+ - ITT_addr matches bits [51:8] of the ITT address (256 Byte aligned).
+ - Size specifies the supported number of bits for the EventID,
+ minus one
+
+ Collection Table Entry (CTE):
+
+ bits: | 63| 62 .. 52 | 51 ... 16 | 15 ... 0 |
+ values: | V | RES0 | RDBase | ICID |
+
+ where:
+ - V indicates whether the entry is valid. If not, other fields are
+ not meaningful.
+ - RES0: reserved field with Should-Be-Zero-or-Preserved behavior.
+ - RDBase is the PE number (GICR_TYPER.Processor_Number semantic),
+ - ICID is the collection ID
+
+ Interrupt Translation Entry (ITE):
+
+ bits: | 63 ... 48 | 47 ... 16 | 15 ... 0 |
+ values: | next | pINTID | ICID |
+
+ where:
+ - next: equals to 0 if this entry is the last one; otherwise it corresponds
+ to the EventID offset to the next ITE capped by 2^16 -1.
+ - pINTID is the physical LPI ID; if zero, it means the entry is not valid
+ and other fields are not meaningful.
+ - ICID is the collection ID
diff --git a/Documentation/virtual/kvm/devices/arm-vgic-v3.txt b/Documentation/virtual/kvm/devices/arm-vgic-v3.txt
index c1a24612c198..9293b45abdb9 100644
--- a/Documentation/virtual/kvm/devices/arm-vgic-v3.txt
+++ b/Documentation/virtual/kvm/devices/arm-vgic-v3.txt
@@ -167,11 +167,17 @@ Groups:
KVM_DEV_ARM_VGIC_CTRL_INIT
request the initialization of the VGIC, no additional parameter in
kvm_device_attr.addr.
+ KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES
+ save all LPI pending bits into guest RAM pending tables.
+
+ The first kB of the pending table is not altered by this operation.
Errors:
-ENXIO: VGIC not properly configured as required prior to calling
this attribute
-ENODEV: no online VCPU
-ENOMEM: memory shortage when allocating vgic internal data
+ -EFAULT: Invalid guest ram access
+ -EBUSY: One or more VCPUS are running
KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO
diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h
index a88726359e5f..5e3c673fa3f4 100644
--- a/arch/arm/include/uapi/asm/kvm.h
+++ b/arch/arm/include/uapi/asm/kvm.h
@@ -196,13 +196,17 @@ struct kvm_arch_memory_slot {
#define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5
#define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6
#define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO 7
+#define KVM_DEV_ARM_VGIC_GRP_ITS_REGS 8
#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT 10
#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \
(0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT)
#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff
#define VGIC_LEVEL_INFO_LINE_LEVEL 0
-#define KVM_DEV_ARM_VGIC_CTRL_INIT 0
+#define KVM_DEV_ARM_VGIC_CTRL_INIT 0
+#define KVM_DEV_ARM_ITS_SAVE_TABLES 1
+#define KVM_DEV_ARM_ITS_RESTORE_TABLES 2
+#define KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES 3
/* KVM_IRQ_LINE irq field index values */
#define KVM_ARM_IRQ_TYPE_SHIFT 24
diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile
index 7b3670c2ae7b..d9beee652d36 100644
--- a/arch/arm/kvm/Makefile
+++ b/arch/arm/kvm/Makefile
@@ -18,9 +18,12 @@ KVM := ../../../virt/kvm
kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o
obj-$(CONFIG_KVM_ARM_HOST) += hyp/
+
obj-y += kvm-arm.o init.o interrupts.o
-obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o
-obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o vgic-v3-coproc.o
+obj-y += handle_exit.o guest.o emulate.o reset.o
+obj-y += coproc.o coproc_a15.o coproc_a7.o vgic-v3-coproc.o
+obj-y += $(KVM)/arm/arm.o $(KVM)/arm/mmu.o $(KVM)/arm/mmio.o
+obj-y += $(KVM)/arm/psci.o $(KVM)/arm/perf.o
obj-y += $(KVM)/arm/aarch32.o
obj-y += $(KVM)/arm/vgic/vgic.o
diff --git a/arch/arm/kvm/trace.h b/arch/arm/kvm/trace.h
index c25a88598eb0..fc0943776db2 100644
--- a/arch/arm/kvm/trace.h
+++ b/arch/arm/kvm/trace.h
@@ -6,133 +6,6 @@
#undef TRACE_SYSTEM
#define TRACE_SYSTEM kvm
-/*
- * Tracepoints for entry/exit to guest
- */
-TRACE_EVENT(kvm_entry,
- TP_PROTO(unsigned long vcpu_pc),
- TP_ARGS(vcpu_pc),
-
- TP_STRUCT__entry(
- __field( unsigned long, vcpu_pc )
- ),
-
- TP_fast_assign(
- __entry->vcpu_pc = vcpu_pc;
- ),
-
- TP_printk("PC: 0x%08lx", __entry->vcpu_pc)
-);
-
-TRACE_EVENT(kvm_exit,
- 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("%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)
-);
-
-TRACE_EVENT(kvm_guest_fault,
- TP_PROTO(unsigned long vcpu_pc, unsigned long hsr,
- unsigned long hxfar,
- unsigned long long ipa),
- TP_ARGS(vcpu_pc, hsr, hxfar, ipa),
-
- TP_STRUCT__entry(
- __field( unsigned long, vcpu_pc )
- __field( unsigned long, hsr )
- __field( unsigned long, hxfar )
- __field( unsigned long long, ipa )
- ),
-
- TP_fast_assign(
- __entry->vcpu_pc = vcpu_pc;
- __entry->hsr = hsr;
- __entry->hxfar = hxfar;
- __entry->ipa = ipa;
- ),
-
- TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#08lx",
- __entry->ipa, __entry->hsr,
- __entry->hxfar, __entry->vcpu_pc)
-);
-
-TRACE_EVENT(kvm_access_fault,
- TP_PROTO(unsigned long ipa),
- TP_ARGS(ipa),
-
- TP_STRUCT__entry(
- __field( unsigned long, ipa )
- ),
-
- TP_fast_assign(
- __entry->ipa = ipa;
- ),
-
- TP_printk("IPA: %lx", __entry->ipa)
-);
-
-TRACE_EVENT(kvm_irq_line,
- TP_PROTO(unsigned int type, int vcpu_idx, int irq_num, int level),
- TP_ARGS(type, vcpu_idx, irq_num, level),
-
- TP_STRUCT__entry(
- __field( unsigned int, type )
- __field( int, vcpu_idx )
- __field( int, irq_num )
- __field( int, level )
- ),
-
- TP_fast_assign(
- __entry->type = type;
- __entry->vcpu_idx = vcpu_idx;
- __entry->irq_num = irq_num;
- __entry->level = level;
- ),
-
- TP_printk("Inject %s interrupt (%d), vcpu->idx: %d, num: %d, level: %d",
- (__entry->type == KVM_ARM_IRQ_TYPE_CPU) ? "CPU" :
- (__entry->type == KVM_ARM_IRQ_TYPE_PPI) ? "VGIC PPI" :
- (__entry->type == KVM_ARM_IRQ_TYPE_SPI) ? "VGIC SPI" : "UNKNOWN",
- __entry->type, __entry->vcpu_idx, __entry->irq_num, __entry->level)
-);
-
-TRACE_EVENT(kvm_mmio_emulate,
- TP_PROTO(unsigned long vcpu_pc, unsigned long instr,
- unsigned long cpsr),
- TP_ARGS(vcpu_pc, instr, cpsr),
-
- TP_STRUCT__entry(
- __field( unsigned long, vcpu_pc )
- __field( unsigned long, instr )
- __field( unsigned long, cpsr )
- ),
-
- TP_fast_assign(
- __entry->vcpu_pc = vcpu_pc;
- __entry->instr = instr;
- __entry->cpsr = cpsr;
- ),
-
- TP_printk("Emulate MMIO at: 0x%08lx (instr: %08lx, cpsr: %08lx)",
- __entry->vcpu_pc, __entry->instr, __entry->cpsr)
-);
-
/* Architecturally implementation defined CP15 register access */
TRACE_EVENT(kvm_emulate_cp15_imp,
TP_PROTO(unsigned long Op1, unsigned long Rt1, unsigned long CRn,
@@ -181,87 +54,6 @@ TRACE_EVENT(kvm_wfx,
__entry->is_wfe ? 'e' : 'i', __entry->vcpu_pc)
);
-TRACE_EVENT(kvm_unmap_hva,
- TP_PROTO(unsigned long hva),
- TP_ARGS(hva),
-
- TP_STRUCT__entry(
- __field( unsigned long, hva )
- ),
-
- TP_fast_assign(
- __entry->hva = hva;
- ),
-
- TP_printk("mmu notifier unmap hva: %#08lx", __entry->hva)
-);
-
-TRACE_EVENT(kvm_unmap_hva_range,
- TP_PROTO(unsigned long start, unsigned long end),
- TP_ARGS(start, end),
-
- TP_STRUCT__entry(
- __field( unsigned long, start )
- __field( unsigned long, end )
- ),
-
- TP_fast_assign(
- __entry->start = start;
- __entry->end = end;
- ),
-
- TP_printk("mmu notifier unmap range: %#08lx -- %#08lx",
- __entry->start, __entry->end)
-);
-
-TRACE_EVENT(kvm_set_spte_hva,
- TP_PROTO(unsigned long hva),
- TP_ARGS(hva),
-
- TP_STRUCT__entry(
- __field( unsigned long, hva )
- ),
-
- TP_fast_assign(
- __entry->hva = hva;
- ),
-
- TP_printk("mmu notifier set pte hva: %#08lx", __entry->hva)
-);
-
-TRACE_EVENT(kvm_age_hva,
- TP_PROTO(unsigned long start, unsigned long end),
- TP_ARGS(start, end),
-
- TP_STRUCT__entry(
- __field( unsigned long, start )
- __field( unsigned long, end )
- ),
-
- TP_fast_assign(
- __entry->start = start;
- __entry->end = end;
- ),
-
- TP_printk("mmu notifier age hva: %#08lx -- %#08lx",
- __entry->start, __entry->end)
-);
-
-TRACE_EVENT(kvm_test_age_hva,
- TP_PROTO(unsigned long hva),
- TP_ARGS(hva),
-
- TP_STRUCT__entry(
- __field( unsigned long, hva )
- ),
-
- TP_fast_assign(
- __entry->hva = hva;
- ),
-
- TP_printk("mmu notifier test age hva: %#08lx", __entry->hva)
-);
-
TRACE_EVENT(kvm_hvc,
TP_PROTO(unsigned long vcpu_pc, unsigned long r0, unsigned long imm),
TP_ARGS(vcpu_pc, r0, imm),
@@ -282,45 +74,6 @@ TRACE_EVENT(kvm_hvc,
__entry->vcpu_pc, __entry->r0, __entry->imm)
);
-TRACE_EVENT(kvm_set_way_flush,
- TP_PROTO(unsigned long vcpu_pc, bool cache),
- TP_ARGS(vcpu_pc, cache),
-
- TP_STRUCT__entry(
- __field( unsigned long, vcpu_pc )
- __field( bool, cache )
- ),
-
- TP_fast_assign(
- __entry->vcpu_pc = vcpu_pc;
- __entry->cache = cache;
- ),
-
- TP_printk("S/W flush at 0x%016lx (cache %s)",
- __entry->vcpu_pc, __entry->cache ? "on" : "off")
-);
-
-TRACE_EVENT(kvm_toggle_cache,
- TP_PROTO(unsigned long vcpu_pc, bool was, bool now),
- TP_ARGS(vcpu_pc, was, now),
-
- TP_STRUCT__entry(
- __field( unsigned long, vcpu_pc )
- __field( bool, was )
- __field( bool, now )
- ),
-
- TP_fast_assign(
- __entry->vcpu_pc = vcpu_pc;
- __entry->was = was;
- __entry->now = now;
- ),
-
- TP_printk("VM op at 0x%016lx (cache was %s, now %s)",
- __entry->vcpu_pc, __entry->was ? "on" : "off",
- __entry->now ? "on" : "off")
-);
-
#endif /* _TRACE_KVM_H */
#undef TRACE_INCLUDE_PATH
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index f5ea0ba70f07..fe39e6841326 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -240,6 +240,12 @@ static inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu)
return kvm_vcpu_get_hsr(vcpu) & ESR_ELx_FSC_TYPE;
}
+static inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)
+{
+ u32 esr = kvm_vcpu_get_hsr(vcpu);
+ return (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+}
+
static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
{
return vcpu_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK;
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index 869ee480deed..70eea2ecc663 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -216,13 +216,17 @@ struct kvm_arch_memory_slot {
#define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5
#define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6
#define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO 7
+#define KVM_DEV_ARM_VGIC_GRP_ITS_REGS 8
#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT 10
#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \
(0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT)
#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff
#define VGIC_LEVEL_INFO_LINE_LEVEL 0
-#define KVM_DEV_ARM_VGIC_CTRL_INIT 0
+#define KVM_DEV_ARM_VGIC_CTRL_INIT 0
+#define KVM_DEV_ARM_ITS_SAVE_TABLES 1
+#define KVM_DEV_ARM_ITS_RESTORE_TABLES 2
+#define KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES 3
/* Device Control API on vcpu fd */
#define KVM_ARM_VCPU_PMU_V3_CTRL 0
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index afd51bebb9c5..5d9810086c25 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -7,14 +7,13 @@ CFLAGS_arm.o := -I.
CFLAGS_mmu.o := -I.
KVM=../../../virt/kvm
-ARM=../../../arch/arm/kvm
obj-$(CONFIG_KVM_ARM_HOST) += kvm.o
obj-$(CONFIG_KVM_ARM_HOST) += hyp/
kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o
-kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/arm.o $(ARM)/mmu.o $(ARM)/mmio.o
-kvm-$(CONFIG_KVM_ARM_HOST) += $(ARM)/psci.o $(ARM)/perf.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/arm.o $(KVM)/arm/mmu.o $(KVM)/arm/mmio.o
+kvm-$(CONFIG_KVM_ARM_HOST) += $(KVM)/arm/psci.o $(KVM)/arm/perf.o
kvm-$(CONFIG_KVM_ARM_HOST) += inject_fault.o regmap.o
kvm-$(CONFIG_KVM_ARM_HOST) += hyp.o hyp-init.o handle_exit.o
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index efbe9e8e7a78..0fe27024a2e1 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1529,8 +1529,8 @@ static int kvm_handle_cp_64(struct kvm_vcpu *vcpu,
{
struct sys_reg_params params;
u32 hsr = kvm_vcpu_get_hsr(vcpu);
- int Rt = (hsr >> 5) & 0xf;
- int Rt2 = (hsr >> 10) & 0xf;
+ int Rt = kvm_vcpu_sys_get_rt(vcpu);
+ int Rt2 = (hsr >> 10) & 0x1f;
params.is_aarch32 = true;
params.is_32bit = false;
@@ -1586,7 +1586,7 @@ static int kvm_handle_cp_32(struct kvm_vcpu *vcpu,
{
struct sys_reg_params params;
u32 hsr = kvm_vcpu_get_hsr(vcpu);
- int Rt = (hsr >> 5) & 0xf;
+ int Rt = kvm_vcpu_sys_get_rt(vcpu);
params.is_aarch32 = true;
params.is_32bit = true;
@@ -1688,7 +1688,7 @@ int kvm_handle_sys_reg(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
struct sys_reg_params params;
unsigned long esr = kvm_vcpu_get_hsr(vcpu);
- int Rt = (esr >> 5) & 0x1f;
+ int Rt = kvm_vcpu_sys_get_rt(vcpu);
int ret;
trace_kvm_handle_sys_reg(esr);
diff --git a/arch/powerpc/include/asm/kvm_book3s_asm.h b/arch/powerpc/include/asm/kvm_book3s_asm.h
index 0593d9479f74..b148496ffe36 100644
--- a/arch/powerpc/include/asm/kvm_book3s_asm.h
+++ b/arch/powerpc/include/asm/kvm_book3s_asm.h
@@ -111,6 +111,8 @@ struct kvmppc_host_state {
struct kvm_vcpu *kvm_vcpu;
struct kvmppc_vcore *kvm_vcore;
void __iomem *xics_phys;
+ void __iomem *xive_tima_phys;
+ void __iomem *xive_tima_virt;
u32 saved_xirr;
u64 dabr;
u64 host_mmcr[7]; /* MMCR 0,1,A, SIAR, SDAR, MMCR2, SIER */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 77c60826d145..9c51ac4b8f36 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -210,6 +210,12 @@ struct kvmppc_spapr_tce_table {
/* XICS components, defined in book3s_xics.c */
struct kvmppc_xics;
struct kvmppc_icp;
+extern struct kvm_device_ops kvm_xics_ops;
+
+/* XIVE components, defined in book3s_xive.c */
+struct kvmppc_xive;
+struct kvmppc_xive_vcpu;
+extern struct kvm_device_ops kvm_xive_ops;
struct kvmppc_passthru_irqmap;
@@ -298,6 +304,7 @@ struct kvm_arch {
#endif
#ifdef CONFIG_KVM_XICS
struct kvmppc_xics *xics;
+ struct kvmppc_xive *xive;
struct kvmppc_passthru_irqmap *pimap;
#endif
struct kvmppc_ops *kvm_ops;
@@ -427,7 +434,7 @@ struct kvmppc_passthru_irqmap {
#define KVMPPC_IRQ_DEFAULT 0
#define KVMPPC_IRQ_MPIC 1
-#define KVMPPC_IRQ_XICS 2
+#define KVMPPC_IRQ_XICS 2 /* Includes a XIVE option */
#define MMIO_HPTE_CACHE_SIZE 4
@@ -454,6 +461,21 @@ struct mmio_hpte_cache {
struct openpic;
+/* W0 and W1 of a XIVE thread management context */
+union xive_tma_w01 {
+ struct {
+ u8 nsr;
+ u8 cppr;
+ u8 ipb;
+ u8 lsmfb;
+ u8 ack;
+ u8 inc;
+ u8 age;
+ u8 pipr;
+ };
+ __be64 w01;
+};
+
struct kvm_vcpu_arch {
ulong host_stack;
u32 host_pid;
@@ -714,6 +736,10 @@ struct kvm_vcpu_arch {
struct openpic *mpic; /* KVM_IRQ_MPIC */
#ifdef CONFIG_KVM_XICS
struct kvmppc_icp *icp; /* XICS presentation controller */
+ struct kvmppc_xive_vcpu *xive_vcpu; /* XIVE virtual CPU data */
+ __be32 xive_cam_word; /* Cooked W2 in proper endian with valid bit */
+ u32 xive_pushed; /* Is the VP pushed on the physical CPU ? */
+ union xive_tma_w01 xive_saved_state; /* W0..1 of XIVE thread state */
#endif
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 76e940a3c145..e0d88c38602b 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -240,6 +240,7 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq);
extern int kvm_vm_ioctl_rtas_define_token(struct kvm *kvm, void __user *argp);
extern int kvmppc_rtas_hcall(struct kvm_vcpu *vcpu);
extern void kvmppc_rtas_tokens_free(struct kvm *kvm);
+
extern int kvmppc_xics_set_xive(struct kvm *kvm, u32 irq, u32 server,
u32 priority);
extern int kvmppc_xics_get_xive(struct kvm *kvm, u32 irq, u32 *server,
@@ -428,6 +429,14 @@ static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
paca[cpu].kvm_hstate.xics_phys = (void __iomem *)addr;
}
+static inline void kvmppc_set_xive_tima(int cpu,
+ unsigned long phys_addr,
+ void __iomem *virt_addr)
+{
+ paca[cpu].kvm_hstate.xive_tima_phys = (void __iomem *)phys_addr;
+ paca[cpu].kvm_hstate.xive_tima_virt = virt_addr;
+}
+
static inline u32 kvmppc_get_xics_latch(void)
{
u32 xirr;
@@ -458,6 +467,11 @@ static inline void __init kvm_cma_reserve(void)
static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
{}
+static inline void kvmppc_set_xive_tima(int cpu,
+ unsigned long phys_addr,
+ void __iomem *virt_addr)
+{}
+
static inline u32 kvmppc_get_xics_latch(void)
{
return 0;
@@ -508,6 +522,10 @@ extern long kvmppc_deliver_irq_passthru(struct kvm_vcpu *vcpu, __be32 xirr,
struct kvmppc_irq_map *irq_map,
struct kvmppc_passthru_irqmap *pimap,
bool *again);
+
+extern int kvmppc_xics_set_irq(struct kvm *kvm, int irq_source_id, u32 irq,
+ int level, bool line_status);
+
extern int h_ipi_redirect;
#else
static inline struct kvmppc_passthru_irqmap *kvmppc_get_passthru_irqmap(
@@ -525,6 +543,60 @@ static inline int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 cmd)
{ return 0; }
#endif
+#ifdef CONFIG_KVM_XIVE
+/*
+ * Below the first "xive" is the "eXternal Interrupt Virtualization Engine"
+ * ie. P9 new interrupt controller, while the second "xive" is the legacy
+ * "eXternal Interrupt Vector Entry" which is the configuration of an
+ * interrupt on the "xics" interrupt controller on P8 and earlier. Those
+ * two function consume or produce a legacy "XIVE" state from the
+ * new "XIVE" interrupt controller.
+ */
+extern int kvmppc_xive_set_xive(struct kvm *kvm, u32 irq, u32 server,
+ u32 priority);
+extern int kvmppc_xive_get_xive(struct kvm *kvm, u32 irq, u32 *server,
+ u32 *priority);
+extern int kvmppc_xive_int_on(struct kvm *kvm, u32 irq);
+extern int kvmppc_xive_int_off(struct kvm *kvm, u32 irq);
+extern void kvmppc_xive_init_module(void);
+extern void kvmppc_xive_exit_module(void);
+
+extern int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
+ struct kvm_vcpu *vcpu, u32 cpu);
+extern void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu);
+extern int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq,
+ struct irq_desc *host_desc);
+extern int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq,
+ struct irq_desc *host_desc);
+extern u64 kvmppc_xive_get_icp(struct kvm_vcpu *vcpu);
+extern int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval);
+
+extern int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq,
+ int level, bool line_status);
+#else
+static inline int kvmppc_xive_set_xive(struct kvm *kvm, u32 irq, u32 server,
+ u32 priority) { return -1; }
+static inline int kvmppc_xive_get_xive(struct kvm *kvm, u32 irq, u32 *server,
+ u32 *priority) { return -1; }
+static inline int kvmppc_xive_int_on(struct kvm *kvm, u32 irq) { return -1; }
+static inline int kvmppc_xive_int_off(struct kvm *kvm, u32 irq) { return -1; }
+static inline void kvmppc_xive_init_module(void) { }
+static inline void kvmppc_xive_exit_module(void) { }
+
+static inline int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
+ struct kvm_vcpu *vcpu, u32 cpu) { return -EBUSY; }
+static inline void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu) { }
+static inline int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq,
+ struct irq_desc *host_desc) { return -ENODEV; }
+static inline int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq,
+ struct irq_desc *host_desc) { return -ENODEV; }
+static inline u64 kvmppc_xive_get_icp(struct kvm_vcpu *vcpu) { return 0; }
+static inline int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval) { return -ENOENT; }
+
+static inline int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq,
+ int level, bool line_status) { return -ENODEV; }
+#endif /* CONFIG_KVM_XIVE */
+
/*
* Prototypes for functions called only from assembler code.
* Having prototypes reduces sparse errors.
@@ -562,6 +634,8 @@ long kvmppc_h_clear_mod(struct kvm_vcpu *vcpu, unsigned long flags,
long kvmppc_hpte_hv_fault(struct kvm_vcpu *vcpu, unsigned long addr,
unsigned long slb_v, unsigned int status, bool data);
unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu);
+unsigned long kvmppc_rm_h_xirr_x(struct kvm_vcpu *vcpu);
+unsigned long kvmppc_rm_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server);
int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
unsigned long mfrr);
int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr);
diff --git a/arch/powerpc/include/asm/xive.h b/arch/powerpc/include/asm/xive.h
index 3cdbeaeac397..c8a822acf962 100644
--- a/arch/powerpc/include/asm/xive.h
+++ b/arch/powerpc/include/asm/xive.h
@@ -99,7 +99,6 @@ struct xive_q {
#define XIVE_ESB_SET_PQ_01 0xd00
#define XIVE_ESB_SET_PQ_10 0xe00
#define XIVE_ESB_SET_PQ_11 0xf00
-#define XIVE_ESB_MASK XIVE_ESB_SET_PQ_01
#define XIVE_ESB_VAL_P 0x2
#define XIVE_ESB_VAL_Q 0x1
@@ -136,11 +135,11 @@ extern int xive_native_configure_queue(u32 vp_id, struct xive_q *q, u8 prio,
__be32 *qpage, u32 order, bool can_escalate);
extern void xive_native_disable_queue(u32 vp_id, struct xive_q *q, u8 prio);
-extern bool __xive_irq_trigger(struct xive_irq_data *xd);
-extern bool __xive_irq_retrigger(struct xive_irq_data *xd);
-extern void xive_do_source_eoi(u32 hw_irq, struct xive_irq_data *xd);
-
+extern void xive_native_sync_source(u32 hw_irq);
extern bool is_xive_irq(struct irq_chip *chip);
+extern int xive_native_enable_vp(u32 vp_id);
+extern int xive_native_disable_vp(u32 vp_id);
+extern int xive_native_get_vp_info(u32 vp_id, u32 *out_cam_id, u32 *out_chip_id);
#else
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 439c257dec4a..709e23425317 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -634,6 +634,8 @@ int main(void)
HSTATE_FIELD(HSTATE_KVM_VCPU, kvm_vcpu);
HSTATE_FIELD(HSTATE_KVM_VCORE, kvm_vcore);
HSTATE_FIELD(HSTATE_XICS_PHYS, xics_phys);
+ HSTATE_FIELD(HSTATE_XIVE_TIMA_PHYS, xive_tima_phys);
+ HSTATE_FIELD(HSTATE_XIVE_TIMA_VIRT, xive_tima_virt);
HSTATE_FIELD(HSTATE_SAVED_XIRR, saved_xirr);
HSTATE_FIELD(HSTATE_HOST_IPI, host_ipi);
HSTATE_FIELD(HSTATE_PTID, ptid);
@@ -719,6 +721,14 @@ int main(void)
OFFSET(VCPU_HOST_MAS6, kvm_vcpu, arch.host_mas6);
#endif
+#ifdef CONFIG_KVM_XICS
+ DEFINE(VCPU_XIVE_SAVED_STATE, offsetof(struct kvm_vcpu,
+ arch.xive_saved_state));
+ DEFINE(VCPU_XIVE_CAM_WORD, offsetof(struct kvm_vcpu,
+ arch.xive_cam_word));
+ DEFINE(VCPU_XIVE_PUSHED, offsetof(struct kvm_vcpu, arch.xive_pushed));
+#endif
+
#ifdef CONFIG_KVM_EXIT_TIMING
OFFSET(VCPU_TIMING_EXIT_TBU, kvm_vcpu, arch.timing_exit.tv32.tbu);
OFFSET(VCPU_TIMING_EXIT_TBL, kvm_vcpu, arch.timing_exit.tv32.tbl);
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 65a471de96de..24de532c1736 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -197,6 +197,11 @@ config KVM_XICS
Specification) interrupt controller architecture used on
IBM POWER (pSeries) servers.
+config KVM_XIVE
+ bool
+ default y
+ depends on KVM_XICS && PPC_XIVE_NATIVE && KVM_BOOK3S_HV_POSSIBLE
+
source drivers/vhost/Kconfig
endif # VIRTUALIZATION
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index b87ccde2137a..d91a2604c496 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -74,7 +74,7 @@ kvm-hv-y += \
book3s_64_mmu_radix.o
kvm-book3s_64-builtin-xics-objs-$(CONFIG_KVM_XICS) := \
- book3s_hv_rm_xics.o
+ book3s_hv_rm_xics.o book3s_hv_rm_xive.o
ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
@@ -89,6 +89,8 @@ endif
kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \
book3s_xics.o
+kvm-book3s_64-objs-$(CONFIG_KVM_XIVE) += book3s_xive.o
+
kvm-book3s_64-module-objs := \
$(common-objs-y) \
book3s.o \
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 8c4d7e9d27d2..72d977e30952 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -35,6 +35,7 @@
#include <asm/kvm_book3s.h>
#include <asm/mmu_context.h>
#include <asm/page.h>
+#include <asm/xive.h>
#include "book3s.h"
#include "trace.h"
@@ -596,11 +597,14 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id,
break;
#ifdef CONFIG_KVM_XICS
case KVM_REG_PPC_ICP_STATE:
- if (!vcpu->arch.icp) {
+ if (!vcpu->arch.icp && !vcpu->arch.xive_vcpu) {
r = -ENXIO;
break;
}
- *val = get_reg_val(id, kvmppc_xics_get_icp(vcpu));
+ if (xive_enabled())
+ *val = get_reg_val(id, kvmppc_xive_get_icp(vcpu));
+ else
+ *val = get_reg_val(id, kvmppc_xics_get_icp(vcpu));
break;
#endif /* CONFIG_KVM_XICS */
case KVM_REG_PPC_FSCR:
@@ -666,12 +670,14 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id,
#endif /* CONFIG_VSX */
#ifdef CONFIG_KVM_XICS
case KVM_REG_PPC_ICP_STATE:
- if (!vcpu->arch.icp) {
+ if (!vcpu->arch.icp && !vcpu->arch.xive_vcpu) {
r = -ENXIO;
break;
}
- r = kvmppc_xics_set_icp(vcpu,
- set_reg_val(id, *val));
+ if (xive_enabled())
+ r = kvmppc_xive_set_icp(vcpu, set_reg_val(id, *val));
+ else
+ r = kvmppc_xics_set_icp(vcpu, set_reg_val(id, *val));
break;
#endif /* CONFIG_KVM_XICS */
case KVM_REG_PPC_FSCR:
@@ -942,6 +948,50 @@ int kvmppc_book3s_hcall_implemented(struct kvm *kvm, unsigned long hcall)
return kvm->arch.kvm_ops->hcall_implemented(hcall);
}
+#ifdef CONFIG_KVM_XICS
+int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
+ bool line_status)
+{
+ if (xive_enabled())
+ return kvmppc_xive_set_irq(kvm, irq_source_id, irq, level,
+ line_status);
+ else
+ return kvmppc_xics_set_irq(kvm, irq_source_id, irq, level,
+ line_status);
+}
+
+int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *irq_entry,
+ struct kvm *kvm, int irq_source_id,
+ int level, bool line_status)
+{
+ return kvm_set_irq(kvm, irq_source_id, irq_entry->gsi,
+ level, line_status);
+}
+static int kvmppc_book3s_set_irq(struct kvm_kernel_irq_routing_entry *e,
+ struct kvm *kvm, int irq_source_id, int level,
+ bool line_status)
+{
+ return kvm_set_irq(kvm, irq_source_id, e->gsi, level, line_status);
+}
+
+int kvm_irq_map_gsi(struct kvm *kvm,
+ struct kvm_kernel_irq_routing_entry *entries, int gsi)
+{
+ entries->gsi = gsi;
+ entries->type = KVM_IRQ_ROUTING_IRQCHIP;
+ entries->set = kvmppc_book3s_set_irq;
+ entries->irqchip.irqchip = 0;
+ entries->irqchip.pin = gsi;
+ return 1;
+}
+
+int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin)
+{
+ return pin;
+}
+
+#endif /* CONFIG_KVM_XICS */
+
static int kvmppc_book3s_init(void)
{
int r;
@@ -952,12 +1002,25 @@ static int kvmppc_book3s_init(void)
#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
r = kvmppc_book3s_init_pr();
#endif
- return r;
+#ifdef CONFIG_KVM_XICS
+#ifdef CONFIG_KVM_XIVE
+ if (xive_enabled()) {
+ kvmppc_xive_init_module();
+ kvm_register_device_ops(&kvm_xive_ops, KVM_DEV_TYPE_XICS);
+ } else
+#endif
+ kvm_register_device_ops(&kvm_xics_ops, KVM_DEV_TYPE_XICS);
+#endif
+ return r;
}
static void kvmppc_book3s_exit(void)
{
+#ifdef CONFIG_KVM_XICS
+ if (xive_enabled())
+ kvmppc_xive_exit_module();
+#endif
#ifdef CONFIG_KVM_BOOK3S_32_HANDLER
kvmppc_book3s_exit_pr();
#endif
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 549dd6070dee..42b7a4fd57d9 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -67,6 +67,7 @@
#include <asm/mmu.h>
#include <asm/opal.h>
#include <asm/xics.h>
+#include <asm/xive.h>
#include "book3s.h"
@@ -837,6 +838,10 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
case H_IPOLL:
case H_XIRR_X:
if (kvmppc_xics_enabled(vcpu)) {
+ if (xive_enabled()) {
+ ret = H_NOT_AVAILABLE;
+ return RESUME_GUEST;
+ }
ret = kvmppc_xics_hcall(vcpu, req);
break;
}
@@ -2947,8 +2952,12 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
r = kvmppc_book3s_hv_page_fault(run, vcpu,
vcpu->arch.fault_dar, vcpu->arch.fault_dsisr);
srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
- } else if (r == RESUME_PASSTHROUGH)
- r = kvmppc_xics_rm_complete(vcpu, 0);
+ } else if (r == RESUME_PASSTHROUGH) {
+ if (WARN_ON(xive_enabled()))
+ r = H_SUCCESS;
+ else
+ r = kvmppc_xics_rm_complete(vcpu, 0);
+ }
} while (is_kvmppc_resume_guest(r));
out:
@@ -3400,10 +3409,20 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
/*
* On POWER9, VPM0 bit is reserved (VPM0=1 behaviour is assumed)
* Set HVICE bit to enable hypervisor virtualization interrupts.
+ * Set HEIC to prevent OS interrupts to go to hypervisor (should
+ * be unnecessary but better safe than sorry in case we re-enable
+ * EE in HV mode with this LPCR still set)
*/
if (cpu_has_feature(CPU_FTR_ARCH_300)) {
lpcr &= ~LPCR_VPM0;
- lpcr |= LPCR_HVICE;
+ lpcr |= LPCR_HVICE | LPCR_HEIC;
+
+ /*
+ * If xive is enabled, we route 0x500 interrupts directly
+ * to the guest.
+ */
+ if (xive_enabled())
+ lpcr |= LPCR_LPES;
}
/*
@@ -3533,7 +3552,7 @@ static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
struct kvmppc_irq_map *irq_map;
struct kvmppc_passthru_irqmap *pimap;
struct irq_chip *chip;
- int i;
+ int i, rc = 0;
if (!kvm_irq_bypass)
return 1;
@@ -3558,10 +3577,10 @@ static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
/*
* For now, we only support interrupts for which the EOI operation
* is an OPAL call followed by a write to XIRR, since that's
- * what our real-mode EOI code does.
+ * what our real-mode EOI code does, or a XIVE interrupt
*/
chip = irq_data_get_irq_chip(&desc->irq_data);
- if (!chip || !is_pnv_opal_msi(chip)) {
+ if (!chip || !(is_pnv_opal_msi(chip) || is_xive_irq(chip))) {
pr_warn("kvmppc_set_passthru_irq_hv: Could not assign IRQ map for (%d,%d)\n",
host_irq, guest_gsi);
mutex_unlock(&kvm->lock);
@@ -3603,7 +3622,12 @@ static int kvmppc_set_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
if (i == pimap->n_mapped)
pimap->n_mapped++;
- kvmppc_xics_set_mapped(kvm, guest_gsi, desc->irq_data.hwirq);
+ if (xive_enabled())
+ rc = kvmppc_xive_set_mapped(kvm, guest_gsi, desc);
+ else
+ kvmppc_xics_set_mapped(kvm, guest_gsi, desc->irq_data.hwirq);
+ if (rc)
+ irq_map->r_hwirq = 0;
mutex_unlock(&kvm->lock);
@@ -3614,7 +3638,7 @@ static int kvmppc_clr_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
{
struct irq_desc *desc;
struct kvmppc_passthru_irqmap *pimap;
- int i;
+ int i, rc = 0;
if (!kvm_irq_bypass)
return 0;
@@ -3639,9 +3663,12 @@ static int kvmppc_clr_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
return -ENODEV;
}
- kvmppc_xics_clr_mapped(kvm, guest_gsi, pimap->mapped[i].r_hwirq);
+ if (xive_enabled())
+ rc = kvmppc_xive_clr_mapped(kvm, guest_gsi, pimap->mapped[i].desc);
+ else
+ kvmppc_xics_clr_mapped(kvm, guest_gsi, pimap->mapped[i].r_hwirq);
- /* invalidate the entry */
+ /* invalidate the entry (what do do on error from the above ?) */
pimap->mapped[i].r_hwirq = 0;
/*
@@ -3650,7 +3677,7 @@ static int kvmppc_clr_passthru_irq(struct kvm *kvm, int host_irq, int guest_gsi)
*/
unlock:
mutex_unlock(&kvm->lock);
- return 0;
+ return rc;
}
static int kvmppc_irq_bypass_add_producer_hv(struct irq_bypass_consumer *cons,
@@ -3928,7 +3955,7 @@ static int kvmppc_book3s_init_hv(void)
* indirectly, via OPAL.
*/
#ifdef CONFIG_SMP
- if (!get_paca()->kvm_hstate.xics_phys) {
+ if (!xive_enabled() && !local_paca->kvm_hstate.xics_phys) {
struct device_node *np;
np = of_find_compatible_node(NULL, NULL, "ibm,opal-intc");
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 9c71c72e65ce..88a65923c649 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -32,6 +32,24 @@
#define KVM_CMA_CHUNK_ORDER 18
+#include "book3s_xics.h"
+#include "book3s_xive.h"
+
+/*
+ * The XIVE module will populate these when it loads
+ */
+unsigned long (*__xive_vm_h_xirr)(struct kvm_vcpu *vcpu);
+unsigned long (*__xive_vm_h_ipoll)(struct kvm_vcpu *vcpu, unsigned long server);
+int (*__xive_vm_h_ipi)(struct kvm_vcpu *vcpu, unsigned long server,
+ unsigned long mfrr);
+int (*__xive_vm_h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr);
+int (*__xive_vm_h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr);
+EXPORT_SYMBOL_GPL(__xive_vm_h_xirr);
+EXPORT_SYMBOL_GPL(__xive_vm_h_ipoll);
+EXPORT_SYMBOL_GPL(__xive_vm_h_ipi);
+EXPORT_SYMBOL_GPL(__xive_vm_h_cppr);
+EXPORT_SYMBOL_GPL(__xive_vm_h_eoi);
+
/*
* Hash page table alignment on newer cpus(CPU_FTR_ARCH_206)
* should be power of 2.
@@ -211,6 +229,7 @@ void kvmhv_rm_send_ipi(int cpu)
__asm__ __volatile__ (PPC_MSGSND(%0) : : "r" (msg));
return;
}
+
/* On POWER8 for IPIs to threads in the same core, use msgsnd. */
if (cpu_has_feature(CPU_FTR_ARCH_207S) &&
cpu_first_thread_sibling(cpu) ==
@@ -407,6 +426,9 @@ static long kvmppc_read_one_intr(bool *again)
u8 host_ipi;
int64_t rc;
+ if (xive_enabled())
+ return 1;
+
/* see if a host IPI is pending */
host_ipi = local_paca->kvm_hstate.host_ipi;
if (host_ipi)
@@ -491,3 +513,84 @@ static long kvmppc_read_one_intr(bool *again)
return kvmppc_check_passthru(xisr, xirr, again);
}
+
+#ifdef CONFIG_KVM_XICS
+static inline bool is_rm(void)
+{
+ return !(mfmsr() & MSR_DR);
+}
+
+unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu)
+{
+ if (xive_enabled()) {
+ if (is_rm())
+ return xive_rm_h_xirr(vcpu);
+ if (unlikely(!__xive_vm_h_xirr))
+ return H_NOT_AVAILABLE;
+ return __xive_vm_h_xirr(vcpu);
+ } else
+ return xics_rm_h_xirr(vcpu);
+}
+
+unsigned long kvmppc_rm_h_xirr_x(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.gpr[5] = get_tb();
+ if (xive_enabled()) {
+ if (is_rm())
+ return xive_rm_h_xirr(vcpu);
+ if (unlikely(!__xive_vm_h_xirr))
+ return H_NOT_AVAILABLE;
+ return __xive_vm_h_xirr(vcpu);
+ } else
+ return xics_rm_h_xirr(vcpu);
+}
+
+unsigned long kvmppc_rm_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server)
+{
+ if (xive_enabled()) {
+ if (is_rm())
+ return xive_rm_h_ipoll(vcpu, server);
+ if (unlikely(!__xive_vm_h_ipoll))
+ return H_NOT_AVAILABLE;
+ return __xive_vm_h_ipoll(vcpu, server);
+ } else
+ return H_TOO_HARD;
+}
+
+int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
+ unsigned long mfrr)
+{
+ if (xive_enabled()) {
+ if (is_rm())
+ return xive_rm_h_ipi(vcpu, server, mfrr);
+ if (unlikely(!__xive_vm_h_ipi))
+ return H_NOT_AVAILABLE;
+ return __xive_vm_h_ipi(vcpu, server, mfrr);
+ } else
+ return xics_rm_h_ipi(vcpu, server, mfrr);
+}
+
+int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr)
+{
+ if (xive_enabled()) {
+ if (is_rm())
+ return xive_rm_h_cppr(vcpu, cppr);
+ if (unlikely(!__xive_vm_h_cppr))
+ return H_NOT_AVAILABLE;
+ return __xive_vm_h_cppr(vcpu, cppr);
+ } else
+ return xics_rm_h_cppr(vcpu, cppr);
+}
+
+int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
+{
+ if (xive_enabled()) {
+ if (is_rm())
+ return xive_rm_h_eoi(vcpu, xirr);
+ if (unlikely(!__xive_vm_h_eoi))
+ return H_NOT_AVAILABLE;
+ return __xive_vm_h_eoi(vcpu, xirr);
+ } else
+ return xics_rm_h_eoi(vcpu, xirr);
+}
+#endif /* CONFIG_KVM_XICS */
diff --git a/arch/powerpc/kvm/book3s_hv_rm_xics.c b/arch/powerpc/kvm/book3s_hv_rm_xics.c
index ffde4507ddfd..2a862618f072 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_xics.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_xics.c
@@ -484,7 +484,7 @@ static void icp_rm_down_cppr(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
}
-unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu)
+unsigned long xics_rm_h_xirr(struct kvm_vcpu *vcpu)
{
union kvmppc_icp_state old_state, new_state;
struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
@@ -522,8 +522,8 @@ unsigned long kvmppc_rm_h_xirr(struct kvm_vcpu *vcpu)
return check_too_hard(xics, icp);
}
-int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
- unsigned long mfrr)
+int xics_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
+ unsigned long mfrr)
{
union kvmppc_icp_state old_state, new_state;
struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
@@ -609,7 +609,7 @@ int kvmppc_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
return check_too_hard(xics, this_icp);
}
-int kvmppc_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr)
+int xics_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr)
{
union kvmppc_icp_state old_state, new_state;
struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
@@ -729,7 +729,7 @@ static int ics_rm_eoi(struct kvm_vcpu *vcpu, u32 irq)
return check_too_hard(xics, icp);
}
-int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
+int xics_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
{
struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
struct kvmppc_icp *icp = vcpu->arch.icp;
diff --git a/arch/powerpc/kvm/book3s_hv_rm_xive.c b/arch/powerpc/kvm/book3s_hv_rm_xive.c
new file mode 100644
index 000000000000..abf5f01b6eb1
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_hv_rm_xive.c
@@ -0,0 +1,47 @@
+#include <linux/kernel.h>
+#include <linux/kvm_host.h>
+#include <linux/err.h>
+#include <linux/kernel_stat.h>
+
+#include <asm/kvm_book3s.h>
+#include <asm/kvm_ppc.h>
+#include <asm/hvcall.h>
+#include <asm/xics.h>
+#include <asm/debug.h>
+#include <asm/synch.h>
+#include <asm/cputhreads.h>
+#include <asm/pgtable.h>
+#include <asm/ppc-opcode.h>
+#include <asm/pnv-pci.h>
+#include <asm/opal.h>
+#include <asm/smp.h>
+#include <asm/asm-prototypes.h>
+#include <asm/xive.h>
+#include <asm/xive-regs.h>
+
+#include "book3s_xive.h"
+
+/* XXX */
+#include <asm/udbg.h>
+//#define DBG(fmt...) udbg_printf(fmt)
+#define DBG(fmt...) do { } while(0)
+
+static inline void __iomem *get_tima_phys(void)
+{
+ return local_paca->kvm_hstate.xive_tima_phys;
+}
+
+#undef XIVE_RUNTIME_CHECKS
+#define X_PFX xive_rm_
+#define X_STATIC
+#define X_STAT_PFX stat_rm_
+#define __x_tima get_tima_phys()
+#define __x_eoi_page(xd) ((void __iomem *)((xd)->eoi_page))
+#define __x_trig_page(xd) ((void __iomem *)((xd)->trig_page))
+#define __x_readb __raw_rm_readb
+#define __x_writeb __raw_rm_writeb
+#define __x_readw __raw_rm_readw
+#define __x_readq __raw_rm_readq
+#define __x_writeq __raw_rm_writeq
+
+#include "book3s_xive_template.c"
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 7c6477d1840a..bdb3f76ceb6b 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -30,6 +30,7 @@
#include <asm/book3s/64/mmu-hash.h>
#include <asm/tm.h>
#include <asm/opal.h>
+#include <asm/xive-regs.h>
#define VCPU_GPRS_TM(reg) (((reg) * ULONG_SIZE) + VCPU_GPR_TM)
@@ -970,6 +971,23 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
cmpwi r3, 512 /* 1 microsecond */
blt hdec_soon
+#ifdef CONFIG_KVM_XICS
+ /* We are entering the guest on that thread, push VCPU to XIVE */
+ ld r10, HSTATE_XIVE_TIMA_PHYS(r13)
+ cmpldi cr0, r10, r0
+ beq no_xive
+ ld r11, VCPU_XIVE_SAVED_STATE(r4)
+ li r9, TM_QW1_OS
+ stdcix r11,r9,r10
+ eieio
+ lwz r11, VCPU_XIVE_CAM_WORD(r4)
+ li r9, TM_QW1_OS + TM_WORD2
+ stwcix r11,r9,r10
+ li r9, 1
+ stw r9, VCPU_XIVE_PUSHED(r4)
+no_xive:
+#endif /* CONFIG_KVM_XICS */
+
deliver_guest_interrupt:
ld r6, VCPU_CTR(r4)
ld r7, VCPU_XER(r4)
@@ -1307,6 +1325,42 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
blt deliver_guest_interrupt
guest_exit_cont: /* r9 = vcpu, r12 = trap, r13 = paca */
+#ifdef CONFIG_KVM_XICS
+ /* We are exiting, pull the VP from the XIVE */
+ lwz r0, VCPU_XIVE_PUSHED(r9)
+ cmpwi cr0, r0, 0
+ beq 1f
+ li r7, TM_SPC_PULL_OS_CTX
+ li r6, TM_QW1_OS
+ mfmsr r0
+ andi. r0, r0, MSR_IR /* in real mode? */
+ beq 2f
+ ld r10, HSTATE_XIVE_TIMA_VIRT(r13)
+ cmpldi cr0, r10, 0
+ beq 1f
+ /* First load to pull the context, we ignore the value */
+ lwzx r11, r7, r10
+ eieio
+ /* Second load to recover the context state (Words 0 and 1) */
+ ldx r11, r6, r10
+ b 3f
+2: ld r10, HSTATE_XIVE_TIMA_PHYS(r13)
+ cmpldi cr0, r10, 0
+ beq 1f
+ /* First load to pull the context, we ignore the value */
+ lwzcix r11, r7, r10
+ eieio
+ /* Second load to recover the context state (Words 0 and 1) */
+ ldcix r11, r6, r10
+3: std r11, VCPU_XIVE_SAVED_STATE(r9)
+ /* Fixup some of the state for the next load */
+ li r10, 0
+ li r0, 0xff
+ stw r10, VCPU_XIVE_PUSHED(r9)
+ stb r10, (VCPU_XIVE_SAVED_STATE+3)(r9)
+ stb r0, (VCPU_XIVE_SAVED_STATE+4)(r9)
+1:
+#endif /* CONFIG_KVM_XICS */
/* Save more register state */
mfdar r6
mfdsisr r7
@@ -2011,7 +2065,7 @@ hcall_real_table:
.long DOTSYM(kvmppc_rm_h_eoi) - hcall_real_table
.long DOTSYM(kvmppc_rm_h_cppr) - hcall_real_table
.long DOTSYM(kvmppc_rm_h_ipi) - hcall_real_table
- .long 0 /* 0x70 - H_IPOLL */
+ .long DOTSYM(kvmppc_rm_h_ipoll) - hcall_real_table
.long DOTSYM(kvmppc_rm_h_xirr) - hcall_real_table
#else
.long 0 /* 0x64 - H_EOI */
@@ -2181,7 +2235,11 @@ hcall_real_table:
.long 0 /* 0x2f0 */
.long 0 /* 0x2f4 */
.long 0 /* 0x2f8 */
- .long 0 /* 0x2fc */
+#ifdef CONFIG_KVM_XICS
+ .long DOTSYM(kvmppc_rm_h_xirr_x) - hcall_real_table
+#else
+ .long 0 /* 0x2fc - H_XIRR_X*/
+#endif
.long DOTSYM(kvmppc_h_random) - hcall_real_table
.globl hcall_real_table_end
hcall_real_table_end:
diff --git a/arch/powerpc/kvm/book3s_rtas.c b/arch/powerpc/kvm/book3s_rtas.c
index 20528701835b..2d3b2b1cc272 100644
--- a/arch/powerpc/kvm/book3s_rtas.c
+++ b/arch/powerpc/kvm/book3s_rtas.c
@@ -16,6 +16,7 @@
#include <asm/kvm_ppc.h>
#include <asm/hvcall.h>
#include <asm/rtas.h>
+#include <asm/xive.h>
#ifdef CONFIG_KVM_XICS
static void kvm_rtas_set_xive(struct kvm_vcpu *vcpu, struct rtas_args *args)
@@ -32,7 +33,10 @@ static void kvm_rtas_set_xive(struct kvm_vcpu *vcpu, struct rtas_args *args)
server = be32_to_cpu(args->args[1]);
priority = be32_to_cpu(args->args[2]);
- rc = kvmppc_xics_set_xive(vcpu->kvm, irq, server, priority);
+ if (xive_enabled())
+ rc = kvmppc_xive_set_xive(vcpu->kvm, irq, server, priority);
+ else
+ rc = kvmppc_xics_set_xive(vcpu->kvm, irq, server, priority);
if (rc)
rc = -3;
out:
@@ -52,7 +56,10 @@ static void kvm_rtas_get_xive(struct kvm_vcpu *vcpu, struct rtas_args *args)
irq = be32_to_cpu(args->args[0]);
server = priority = 0;
- rc = kvmppc_xics_get_xive(vcpu->kvm, irq, &server, &priority);
+ if (xive_enabled())
+ rc = kvmppc_xive_get_xive(vcpu->kvm, irq, &server, &priority);
+ else
+ rc = kvmppc_xics_get_xive(vcpu->kvm, irq, &server, &priority);
if (rc) {
rc = -3;
goto out;
@@ -76,7 +83,10 @@ static void kvm_rtas_int_off(struct kvm_vcpu *vcpu, struct rtas_args *args)
irq = be32_to_cpu(args->args[0]);
- rc = kvmppc_xics_int_off(vcpu->kvm, irq);
+ if (xive_enabled())
+ rc = kvmppc_xive_int_off(vcpu->kvm, irq);
+ else
+ rc = kvmppc_xics_int_off(vcpu->kvm, irq);
if (rc)
rc = -3;
out:
@@ -95,7 +105,10 @@ static void kvm_rtas_int_on(struct kvm_vcpu *vcpu, struct rtas_args *args)
irq = be32_to_cpu(args->args[0]);
- rc = kvmppc_xics_int_on(vcpu->kvm, irq);
+ if (xive_enabled())
+ rc = kvmppc_xive_int_on(vcpu->kvm, irq);
+ else
+ rc = kvmppc_xics_int_on(vcpu->kvm, irq);
if (rc)
rc = -3;
out:
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index 459b72cb617a..d329b2add7e2 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -1306,8 +1306,8 @@ static int xics_set_source(struct kvmppc_xics *xics, long irq, u64 addr)
return 0;
}
-int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
- bool line_status)
+int kvmppc_xics_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
+ bool line_status)
{
struct kvmppc_xics *xics = kvm->arch.xics;
@@ -1316,14 +1316,6 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
return ics_deliver_irq(xics, irq, level);
}
-int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *irq_entry,
- struct kvm *kvm, int irq_source_id,
- int level, bool line_status)
-{
- return kvm_set_irq(kvm, irq_source_id, irq_entry->gsi,
- level, line_status);
-}
-
static int xics_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
{
struct kvmppc_xics *xics = dev->private;
@@ -1457,29 +1449,6 @@ void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu)
vcpu->arch.irq_type = KVMPPC_IRQ_DEFAULT;
}
-static int xics_set_irq(struct kvm_kernel_irq_routing_entry *e,
- struct kvm *kvm, int irq_source_id, int level,
- bool line_status)
-{
- return kvm_set_irq(kvm, irq_source_id, e->gsi, level, line_status);
-}
-
-int kvm_irq_map_gsi(struct kvm *kvm,
- struct kvm_kernel_irq_routing_entry *entries, int gsi)
-{
- entries->gsi = gsi;
- entries->type = KVM_IRQ_ROUTING_IRQCHIP;
- entries->set = xics_set_irq;
- entries->irqchip.irqchip = 0;
- entries->irqchip.pin = gsi;
- return 1;
-}
-
-int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin)
-{
- return pin;
-}
-
void kvmppc_xics_set_mapped(struct kvm *kvm, unsigned long irq,
unsigned long host_irq)
{
diff --git a/arch/powerpc/kvm/book3s_xics.h b/arch/powerpc/kvm/book3s_xics.h
index ec5474cf70c6..453c9e518c19 100644
--- a/arch/powerpc/kvm/book3s_xics.h
+++ b/arch/powerpc/kvm/book3s_xics.h
@@ -10,6 +10,7 @@
#ifndef _KVM_PPC_BOOK3S_XICS_H
#define _KVM_PPC_BOOK3S_XICS_H
+#ifdef CONFIG_KVM_XICS
/*
* We use a two-level tree to store interrupt source information.
* There are up to 1024 ICS nodes, each of which can represent
@@ -144,5 +145,11 @@ static inline struct kvmppc_ics *kvmppc_xics_find_ics(struct kvmppc_xics *xics,
return ics;
}
+extern unsigned long xics_rm_h_xirr(struct kvm_vcpu *vcpu);
+extern int xics_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
+ unsigned long mfrr);
+extern int xics_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr);
+extern int xics_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr);
+#endif /* CONFIG_KVM_XICS */
#endif /* _KVM_PPC_BOOK3S_XICS_H */
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
new file mode 100644
index 000000000000..ffe1da95033a
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -0,0 +1,1894 @@
+/*
+ * Copyright 2017 Benjamin Herrenschmidt, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) "xive-kvm: " fmt
+
+#include <linux/kernel.h>
+#include <linux/kvm_host.h>
+#include <linux/err.h>
+#include <linux/gfp.h>
+#include <linux/spinlock.h>
+#include <linux/delay.h>
+#include <linux/percpu.h>
+#include <linux/cpumask.h>
+#include <asm/uaccess.h>
+#include <asm/kvm_book3s.h>
+#include <asm/kvm_ppc.h>
+#include <asm/hvcall.h>
+#include <asm/xics.h>
+#include <asm/xive.h>
+#include <asm/xive-regs.h>
+#include <asm/debug.h>
+#include <asm/debugfs.h>
+#include <asm/time.h>
+#include <asm/opal.h>
+
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#include "book3s_xive.h"
+
+
+/*
+ * Virtual mode variants of the hcalls for use on radix/radix
+ * with AIL. They require the VCPU's VP to be "pushed"
+ *
+ * We still instanciate them here because we use some of the
+ * generated utility functions as well in this file.
+ */
+#define XIVE_RUNTIME_CHECKS
+#define X_PFX xive_vm_
+#define X_STATIC static
+#define X_STAT_PFX stat_vm_
+#define __x_tima xive_tima
+#define __x_eoi_page(xd) ((void __iomem *)((xd)->eoi_mmio))
+#define __x_trig_page(xd) ((void __iomem *)((xd)->trig_mmio))
+#define __x_readb __raw_readb
+#define __x_writeb __raw_writeb
+#define __x_readw __raw_readw
+#define __x_readq __raw_readq
+#define __x_writeq __raw_writeq
+
+#include "book3s_xive_template.c"
+
+/*
+ * We leave a gap of a couple of interrupts in the queue to
+ * account for the IPI and additional safety guard.
+ */
+#define XIVE_Q_GAP 2
+
+/*
+ * This is a simple trigger for a generic XIVE IRQ. This must
+ * only be called for interrupts that support a trigger page
+ */
+static bool xive_irq_trigger(struct xive_irq_data *xd)
+{
+ /* This should be only for MSIs */
+ if (WARN_ON(xd->flags & XIVE_IRQ_FLAG_LSI))
+ return false;
+
+ /* Those interrupts should always have a trigger page */
+ if (WARN_ON(!xd->trig_mmio))
+ return false;
+
+ out_be64(xd->trig_mmio, 0);
+
+ return true;
+}
+
+static irqreturn_t xive_esc_irq(int irq, void *data)
+{
+ struct kvm_vcpu *vcpu = data;
+
+ /* We use the existing H_PROD mechanism to wake up the target */
+ vcpu->arch.prodded = 1;
+ smp_mb();
+ if (vcpu->arch.ceded)
+ kvmppc_fast_vcpu_kick(vcpu);
+
+ return IRQ_HANDLED;
+}
+
+static int xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ struct xive_q *q = &xc->queues[prio];
+ char *name = NULL;
+ int rc;
+
+ /* Already there ? */
+ if (xc->esc_virq[prio])
+ return 0;
+
+ /* Hook up the escalation interrupt */
+ xc->esc_virq[prio] = irq_create_mapping(NULL, q->esc_irq);
+ if (!xc->esc_virq[prio]) {
+ pr_err("Failed to map escalation interrupt for queue %d of VCPU %d\n",
+ prio, xc->server_num);
+ return -EIO;
+ }
+
+ /*
+ * Future improvement: start with them disabled
+ * and handle DD2 and later scheme of merged escalation
+ * interrupts
+ */
+ name = kasprintf(GFP_KERNEL, "kvm-%d-%d-%d",
+ vcpu->kvm->arch.lpid, xc->server_num, prio);
+ if (!name) {
+ pr_err("Failed to allocate escalation irq name for queue %d of VCPU %d\n",
+ prio, xc->server_num);
+ rc = -ENOMEM;
+ goto error;
+ }
+ rc = request_irq(xc->esc_virq[prio], xive_esc_irq,
+ IRQF_NO_THREAD, name, vcpu);
+ if (rc) {
+ pr_err("Failed to request escalation interrupt for queue %d of VCPU %d\n",
+ prio, xc->server_num);
+ goto error;
+ }
+ xc->esc_virq_names[prio] = name;
+ return 0;
+error:
+ irq_dispose_mapping(xc->esc_virq[prio]);
+ xc->esc_virq[prio] = 0;
+ kfree(name);
+ return rc;
+}
+
+static int xive_provision_queue(struct kvm_vcpu *vcpu, u8 prio)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ struct kvmppc_xive *xive = xc->xive;
+ struct xive_q *q = &xc->queues[prio];
+ void *qpage;
+ int rc;
+
+ if (WARN_ON(q->qpage))
+ return 0;
+
+ /* Allocate the queue and retrieve infos on current node for now */
+ qpage = (__be32 *)__get_free_pages(GFP_KERNEL, xive->q_page_order);
+ if (!qpage) {
+ pr_err("Failed to allocate queue %d for VCPU %d\n",
+ prio, xc->server_num);
+ return -ENOMEM;;
+ }
+ memset(qpage, 0, 1 << xive->q_order);
+
+ /*
+ * Reconfigure the queue. This will set q->qpage only once the
+ * queue is fully configured. This is a requirement for prio 0
+ * as we will stop doing EOIs for every IPI as soon as we observe
+ * qpage being non-NULL, and instead will only EOI when we receive
+ * corresponding queue 0 entries
+ */
+ rc = xive_native_configure_queue(xc->vp_id, q, prio, qpage,
+ xive->q_order, true);
+ if (rc)
+ pr_err("Failed to configure queue %d for VCPU %d\n",
+ prio, xc->server_num);
+ return rc;
+}
+
+/* Called with kvm_lock held */
+static int xive_check_provisioning(struct kvm *kvm, u8 prio)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ struct kvm_vcpu *vcpu;
+ int i, rc;
+
+ lockdep_assert_held(&kvm->lock);
+
+ /* Already provisioned ? */
+ if (xive->qmap & (1 << prio))
+ return 0;
+
+ pr_devel("Provisioning prio... %d\n", prio);
+
+ /* Provision each VCPU and enable escalations */
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (!vcpu->arch.xive_vcpu)
+ continue;
+ rc = xive_provision_queue(vcpu, prio);
+ if (rc == 0)
+ xive_attach_escalation(vcpu, prio);
+ if (rc)
+ return rc;
+ }
+
+ /* Order previous stores and mark it as provisioned */
+ mb();
+ xive->qmap |= (1 << prio);
+ return 0;
+}
+
+static void xive_inc_q_pending(struct kvm *kvm, u32 server, u8 prio)
+{
+ struct kvm_vcpu *vcpu;
+ struct kvmppc_xive_vcpu *xc;
+ struct xive_q *q;
+
+ /* Locate target server */
+ vcpu = kvmppc_xive_find_server(kvm, server);
+ if (!vcpu) {
+ pr_warn("%s: Can't find server %d\n", __func__, server);
+ return;
+ }
+ xc = vcpu->arch.xive_vcpu;
+ if (WARN_ON(!xc))
+ return;
+
+ q = &xc->queues[prio];
+ atomic_inc(&q->pending_count);
+}
+
+static int xive_try_pick_queue(struct kvm_vcpu *vcpu, u8 prio)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ struct xive_q *q;
+ u32 max;
+
+ if (WARN_ON(!xc))
+ return -ENXIO;
+ if (!xc->valid)
+ return -ENXIO;
+
+ q = &xc->queues[prio];
+ if (WARN_ON(!q->qpage))
+ return -ENXIO;
+
+ /* Calculate max number of interrupts in that queue. */
+ max = (q->msk + 1) - XIVE_Q_GAP;
+ return atomic_add_unless(&q->count, 1, max) ? 0 : -EBUSY;
+}
+
+static int xive_select_target(struct kvm *kvm, u32 *server, u8 prio)
+{
+ struct kvm_vcpu *vcpu;
+ int i, rc;
+
+ /* Locate target server */
+ vcpu = kvmppc_xive_find_server(kvm, *server);
+ if (!vcpu) {
+ pr_devel("Can't find server %d\n", *server);
+ return -EINVAL;
+ }
+
+ pr_devel("Finding irq target on 0x%x/%d...\n", *server, prio);
+
+ /* Try pick it */
+ rc = xive_try_pick_queue(vcpu, prio);
+ if (rc == 0)
+ return rc;
+
+ pr_devel(" .. failed, looking up candidate...\n");
+
+ /* Failed, pick another VCPU */
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (!vcpu->arch.xive_vcpu)
+ continue;
+ rc = xive_try_pick_queue(vcpu, prio);
+ if (rc == 0) {
+ *server = vcpu->arch.xive_vcpu->server_num;
+ pr_devel(" found on 0x%x/%d\n", *server, prio);
+ return rc;
+ }
+ }
+ pr_devel(" no available target !\n");
+
+ /* No available target ! */
+ return -EBUSY;
+}
+
+static u8 xive_lock_and_mask(struct kvmppc_xive *xive,
+ struct kvmppc_xive_src_block *sb,
+ struct kvmppc_xive_irq_state *state)
+{
+ struct xive_irq_data *xd;
+ u32 hw_num;
+ u8 old_prio;
+ u64 val;
+
+ /*
+ * Take the lock, set masked, try again if racing
+ * with H_EOI
+ */
+ for (;;) {
+ arch_spin_lock(&sb->lock);
+ old_prio = state->guest_priority;
+ state->guest_priority = MASKED;
+ mb();
+ if (!state->in_eoi)
+ break;
+ state->guest_priority = old_prio;
+ arch_spin_unlock(&sb->lock);
+ }
+
+ /* No change ? Bail */
+ if (old_prio == MASKED)
+ return old_prio;
+
+ /* Get the right irq */
+ kvmppc_xive_select_irq(state, &hw_num, &xd);
+
+ /*
+ * If the interrupt is marked as needing masking via
+ * firmware, we do it here. Firmware masking however
+ * is "lossy", it won't return the old p and q bits
+ * and won't set the interrupt to a state where it will
+ * record queued ones. If this is an issue we should do
+ * lazy masking instead.
+ *
+ * For now, we work around this in unmask by forcing
+ * an interrupt whenever we unmask a non-LSI via FW
+ * (if ever).
+ */
+ if (xd->flags & OPAL_XIVE_IRQ_MASK_VIA_FW) {
+ xive_native_configure_irq(hw_num,
+ xive->vp_base + state->act_server,
+ MASKED, state->number);
+ /* set old_p so we can track if an H_EOI was done */
+ state->old_p = true;
+ state->old_q = false;
+ } else {
+ /* Set PQ to 10, return old P and old Q and remember them */
+ val = xive_vm_esb_load(xd, XIVE_ESB_SET_PQ_10);
+ state->old_p = !!(val & 2);
+ state->old_q = !!(val & 1);
+
+ /*
+ * Synchronize hardware to sensure the queues are updated
+ * when masking
+ */
+ xive_native_sync_source(hw_num);
+ }
+
+ return old_prio;
+}
+
+static void xive_lock_for_unmask(struct kvmppc_xive_src_block *sb,
+ struct kvmppc_xive_irq_state *state)
+{
+ /*
+ * Take the lock try again if racing with H_EOI
+ */
+ for (;;) {
+ arch_spin_lock(&sb->lock);
+ if (!state->in_eoi)
+ break;
+ arch_spin_unlock(&sb->lock);
+ }
+}
+
+static void xive_finish_unmask(struct kvmppc_xive *xive,
+ struct kvmppc_xive_src_block *sb,
+ struct kvmppc_xive_irq_state *state,
+ u8 prio)
+{
+ struct xive_irq_data *xd;
+ u32 hw_num;
+
+ /* If we aren't changing a thing, move on */
+ if (state->guest_priority != MASKED)
+ goto bail;
+
+ /* Get the right irq */
+ kvmppc_xive_select_irq(state, &hw_num, &xd);
+
+ /*
+ * See command in xive_lock_and_mask() concerning masking
+ * via firmware.
+ */
+ if (xd->flags & OPAL_XIVE_IRQ_MASK_VIA_FW) {
+ xive_native_configure_irq(hw_num,
+ xive->vp_base + state->act_server,
+ state->act_priority, state->number);
+ /* If an EOI is needed, do it here */
+ if (!state->old_p)
+ xive_vm_source_eoi(hw_num, xd);
+ /* If this is not an LSI, force a trigger */
+ if (!(xd->flags & OPAL_XIVE_IRQ_LSI))
+ xive_irq_trigger(xd);
+ goto bail;
+ }
+
+ /* Old Q set, set PQ to 11 */
+ if (state->old_q)
+ xive_vm_esb_load(xd, XIVE_ESB_SET_PQ_11);
+
+ /*
+ * If not old P, then perform an "effective" EOI,
+ * on the source. This will handle the cases where
+ * FW EOI is needed.
+ */
+ if (!state->old_p)
+ xive_vm_source_eoi(hw_num, xd);
+
+ /* Synchronize ordering and mark unmasked */
+ mb();
+bail:
+ state->guest_priority = prio;
+}
+
+/*
+ * Target an interrupt to a given server/prio, this will fallback
+ * to another server if necessary and perform the HW targetting
+ * updates as needed
+ *
+ * NOTE: Must be called with the state lock held
+ */
+static int xive_target_interrupt(struct kvm *kvm,
+ struct kvmppc_xive_irq_state *state,
+ u32 server, u8 prio)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ u32 hw_num;
+ int rc;
+
+ /*
+ * This will return a tentative server and actual
+ * priority. The count for that new target will have
+ * already been incremented.
+ */
+ rc = xive_select_target(kvm, &server, prio);
+
+ /*
+ * We failed to find a target ? Not much we can do
+ * at least until we support the GIQ.
+ */
+ if (rc)
+ return rc;
+
+ /*
+ * Increment the old queue pending count if there
+ * was one so that the old queue count gets adjusted later
+ * when observed to be empty.
+ */
+ if (state->act_priority != MASKED)
+ xive_inc_q_pending(kvm,
+ state->act_server,
+ state->act_priority);
+ /*
+ * Update state and HW
+ */
+ state->act_priority = prio;
+ state->act_server = server;
+
+ /* Get the right irq */
+ kvmppc_xive_select_irq(state, &hw_num, NULL);
+
+ return xive_native_configure_irq(hw_num,
+ xive->vp_base + server,
+ prio, state->number);
+}
+
+/*
+ * Targetting rules: In order to avoid losing track of
+ * pending interrupts accross mask and unmask, which would
+ * allow queue overflows, we implement the following rules:
+ *
+ * - Unless it was never enabled (or we run out of capacity)
+ * an interrupt is always targetted at a valid server/queue
+ * pair even when "masked" by the guest. This pair tends to
+ * be the last one used but it can be changed under some
+ * circumstances. That allows us to separate targetting
+ * from masking, we only handle accounting during (re)targetting,
+ * this also allows us to let an interrupt drain into its target
+ * queue after masking, avoiding complex schemes to remove
+ * interrupts out of remote processor queues.
+ *
+ * - When masking, we set PQ to 10 and save the previous value
+ * of P and Q.
+ *
+ * - When unmasking, if saved Q was set, we set PQ to 11
+ * otherwise we leave PQ to the HW state which will be either
+ * 10 if nothing happened or 11 if the interrupt fired while
+ * masked. Effectively we are OR'ing the previous Q into the
+ * HW Q.
+ *
+ * Then if saved P is clear, we do an effective EOI (Q->P->Trigger)
+ * which will unmask the interrupt and shoot a new one if Q was
+ * set.
+ *
+ * Otherwise (saved P is set) we leave PQ unchanged (so 10 or 11,
+ * effectively meaning an H_EOI from the guest is still expected
+ * for that interrupt).
+ *
+ * - If H_EOI occurs while masked, we clear the saved P.
+ *
+ * - When changing target, we account on the new target and
+ * increment a separate "pending" counter on the old one.
+ * This pending counter will be used to decrement the old
+ * target's count when its queue has been observed empty.
+ */
+
+int kvmppc_xive_set_xive(struct kvm *kvm, u32 irq, u32 server,
+ u32 priority)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u8 new_act_prio;
+ int rc = 0;
+ u16 idx;
+
+ if (!xive)
+ return -ENODEV;
+
+ pr_devel("set_xive ! irq 0x%x server 0x%x prio %d\n",
+ irq, server, priority);
+
+ /* First, check provisioning of queues */
+ if (priority != MASKED)
+ rc = xive_check_provisioning(xive->kvm,
+ xive_prio_from_guest(priority));
+ if (rc) {
+ pr_devel(" provisioning failure %d !\n", rc);
+ return rc;
+ }
+
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb)
+ return -EINVAL;
+ state = &sb->irq_state[idx];
+
+ /*
+ * We first handle masking/unmasking since the locking
+ * might need to be retried due to EOIs, we'll handle
+ * targetting changes later. These functions will return
+ * with the SB lock held.
+ *
+ * xive_lock_and_mask() will also set state->guest_priority
+ * but won't otherwise change other fields of the state.
+ *
+ * xive_lock_for_unmask will not actually unmask, this will
+ * be done later by xive_finish_unmask() once the targetting
+ * has been done, so we don't try to unmask an interrupt
+ * that hasn't yet been targetted.
+ */
+ if (priority == MASKED)
+ xive_lock_and_mask(xive, sb, state);
+ else
+ xive_lock_for_unmask(sb, state);
+
+
+ /*
+ * Then we handle targetting.
+ *
+ * First calculate a new "actual priority"
+ */
+ new_act_prio = state->act_priority;
+ if (priority != MASKED)
+ new_act_prio = xive_prio_from_guest(priority);
+
+ pr_devel(" new_act_prio=%x act_server=%x act_prio=%x\n",
+ new_act_prio, state->act_server, state->act_priority);
+
+ /*
+ * Then check if we actually need to change anything,
+ *
+ * The condition for re-targetting the interrupt is that
+ * we have a valid new priority (new_act_prio is not 0xff)
+ * and either the server or the priority changed.
+ *
+ * Note: If act_priority was ff and the new priority is
+ * also ff, we don't do anything and leave the interrupt
+ * untargetted. An attempt of doing an int_on on an
+ * untargetted interrupt will fail. If that is a problem
+ * we could initialize interrupts with valid default
+ */
+
+ if (new_act_prio != MASKED &&
+ (state->act_server != server ||
+ state->act_priority != new_act_prio))
+ rc = xive_target_interrupt(kvm, state, server, new_act_prio);
+
+ /*
+ * Perform the final unmasking of the interrupt source
+ * if necessary
+ */
+ if (priority != MASKED)
+ xive_finish_unmask(xive, sb, state, priority);
+
+ /*
+ * Finally Update saved_priority to match. Only int_on/off
+ * set this field to a different value.
+ */
+ state->saved_priority = priority;
+
+ arch_spin_unlock(&sb->lock);
+ return rc;
+}
+
+int kvmppc_xive_get_xive(struct kvm *kvm, u32 irq, u32 *server,
+ u32 *priority)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u16 idx;
+
+ if (!xive)
+ return -ENODEV;
+
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb)
+ return -EINVAL;
+ state = &sb->irq_state[idx];
+ arch_spin_lock(&sb->lock);
+ *server = state->guest_server;
+ *priority = state->guest_priority;
+ arch_spin_unlock(&sb->lock);
+
+ return 0;
+}
+
+int kvmppc_xive_int_on(struct kvm *kvm, u32 irq)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u16 idx;
+
+ if (!xive)
+ return -ENODEV;
+
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb)
+ return -EINVAL;
+ state = &sb->irq_state[idx];
+
+ pr_devel("int_on(irq=0x%x)\n", irq);
+
+ /*
+ * Check if interrupt was not targetted
+ */
+ if (state->act_priority == MASKED) {
+ pr_devel("int_on on untargetted interrupt\n");
+ return -EINVAL;
+ }
+
+ /* If saved_priority is 0xff, do nothing */
+ if (state->saved_priority == MASKED)
+ return 0;
+
+ /*
+ * Lock and unmask it.
+ */
+ xive_lock_for_unmask(sb, state);
+ xive_finish_unmask(xive, sb, state, state->saved_priority);
+ arch_spin_unlock(&sb->lock);
+
+ return 0;
+}
+
+int kvmppc_xive_int_off(struct kvm *kvm, u32 irq)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u16 idx;
+
+ if (!xive)
+ return -ENODEV;
+
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb)
+ return -EINVAL;
+ state = &sb->irq_state[idx];
+
+ pr_devel("int_off(irq=0x%x)\n", irq);
+
+ /*
+ * Lock and mask
+ */
+ state->saved_priority = xive_lock_and_mask(xive, sb, state);
+ arch_spin_unlock(&sb->lock);
+
+ return 0;
+}
+
+static bool xive_restore_pending_irq(struct kvmppc_xive *xive, u32 irq)
+{
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u16 idx;
+
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb)
+ return false;
+ state = &sb->irq_state[idx];
+ if (!state->valid)
+ return false;
+
+ /*
+ * Trigger the IPI. This assumes we never restore a pass-through
+ * interrupt which should be safe enough
+ */
+ xive_irq_trigger(&state->ipi_data);
+
+ return true;
+}
+
+u64 kvmppc_xive_get_icp(struct kvm_vcpu *vcpu)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+
+ if (!xc)
+ return 0;
+
+ /* Return the per-cpu state for state saving/migration */
+ return (u64)xc->cppr << KVM_REG_PPC_ICP_CPPR_SHIFT |
+ (u64)xc->mfrr << KVM_REG_PPC_ICP_MFRR_SHIFT;
+}
+
+int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ struct kvmppc_xive *xive = vcpu->kvm->arch.xive;
+ u8 cppr, mfrr;
+ u32 xisr;
+
+ if (!xc || !xive)
+ return -ENOENT;
+
+ /* Grab individual state fields. We don't use pending_pri */
+ cppr = icpval >> KVM_REG_PPC_ICP_CPPR_SHIFT;
+ xisr = (icpval >> KVM_REG_PPC_ICP_XISR_SHIFT) &
+ KVM_REG_PPC_ICP_XISR_MASK;
+ mfrr = icpval >> KVM_REG_PPC_ICP_MFRR_SHIFT;
+
+ pr_devel("set_icp vcpu %d cppr=0x%x mfrr=0x%x xisr=0x%x\n",
+ xc->server_num, cppr, mfrr, xisr);
+
+ /*
+ * We can't update the state of a "pushed" VCPU, but that
+ * shouldn't happen.
+ */
+ if (WARN_ON(vcpu->arch.xive_pushed))
+ return -EIO;
+
+ /* Update VCPU HW saved state */
+ vcpu->arch.xive_saved_state.cppr = cppr;
+ xc->hw_cppr = xc->cppr = cppr;
+
+ /*
+ * Update MFRR state. If it's not 0xff, we mark the VCPU as
+ * having a pending MFRR change, which will re-evaluate the
+ * target. The VCPU will thus potentially get a spurious
+ * interrupt but that's not a big deal.
+ */
+ xc->mfrr = mfrr;
+ if (mfrr < cppr)
+ xive_irq_trigger(&xc->vp_ipi_data);
+
+ /*
+ * Now saved XIRR is "interesting". It means there's something in
+ * the legacy "1 element" queue... for an IPI we simply ignore it,
+ * as the MFRR restore will handle that. For anything else we need
+ * to force a resend of the source.
+ * However the source may not have been setup yet. If that's the
+ * case, we keep that info and increment a counter in the xive to
+ * tell subsequent xive_set_source() to go look.
+ */
+ if (xisr > XICS_IPI && !xive_restore_pending_irq(xive, xisr)) {
+ xc->delayed_irq = xisr;
+ xive->delayed_irqs++;
+ pr_devel(" xisr restore delayed\n");
+ }
+
+ return 0;
+}
+
+int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq,
+ struct irq_desc *host_desc)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ struct irq_data *host_data = irq_desc_get_irq_data(host_desc);
+ unsigned int host_irq = irq_desc_get_irq(host_desc);
+ unsigned int hw_irq = (unsigned int)irqd_to_hwirq(host_data);
+ u16 idx;
+ u8 prio;
+ int rc;
+
+ if (!xive)
+ return -ENODEV;
+
+ pr_devel("set_mapped girq 0x%lx host HW irq 0x%x...\n",guest_irq, hw_irq);
+
+ sb = kvmppc_xive_find_source(xive, guest_irq, &idx);
+ if (!sb)
+ return -EINVAL;
+ state = &sb->irq_state[idx];
+
+ /*
+ * Mark the passed-through interrupt as going to a VCPU,
+ * this will prevent further EOIs and similar operations
+ * from the XIVE code. It will also mask the interrupt
+ * to either PQ=10 or 11 state, the latter if the interrupt
+ * is pending. This will allow us to unmask or retrigger it
+ * after routing it to the guest with a simple EOI.
+ *
+ * The "state" argument is a "token", all it needs is to be
+ * non-NULL to switch to passed-through or NULL for the
+ * other way around. We may not yet have an actual VCPU
+ * target here and we don't really care.
+ */
+ rc = irq_set_vcpu_affinity(host_irq, state);
+ if (rc) {
+ pr_err("Failed to set VCPU affinity for irq %d\n", host_irq);
+ return rc;
+ }
+
+ /*
+ * Mask and read state of IPI. We need to know if its P bit
+ * is set as that means it's potentially already using a
+ * queue entry in the target
+ */
+ prio = xive_lock_and_mask(xive, sb, state);
+ pr_devel(" old IPI prio %02x P:%d Q:%d\n", prio,
+ state->old_p, state->old_q);
+
+ /* Turn the IPI hard off */
+ xive_vm_esb_load(&state->ipi_data, XIVE_ESB_SET_PQ_01);
+
+ /* Grab info about irq */
+ state->pt_number = hw_irq;
+ state->pt_data = irq_data_get_irq_handler_data(host_data);
+
+ /*
+ * Configure the IRQ to match the existing configuration of
+ * the IPI if it was already targetted. Otherwise this will
+ * mask the interrupt in a lossy way (act_priority is 0xff)
+ * which is fine for a never started interrupt.
+ */
+ xive_native_configure_irq(hw_irq,
+ xive->vp_base + state->act_server,
+ state->act_priority, state->number);
+
+ /*
+ * We do an EOI to enable the interrupt (and retrigger if needed)
+ * if the guest has the interrupt unmasked and the P bit was *not*
+ * set in the IPI. If it was set, we know a slot may still be in
+ * use in the target queue thus we have to wait for a guest
+ * originated EOI
+ */
+ if (prio != MASKED && !state->old_p)
+ xive_vm_source_eoi(hw_irq, state->pt_data);
+
+ /* Clear old_p/old_q as they are no longer relevant */
+ state->old_p = state->old_q = false;
+
+ /* Restore guest prio (unlocks EOI) */
+ mb();
+ state->guest_priority = prio;
+ arch_spin_unlock(&sb->lock);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvmppc_xive_set_mapped);
+
+int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq,
+ struct irq_desc *host_desc)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ unsigned int host_irq = irq_desc_get_irq(host_desc);
+ u16 idx;
+ u8 prio;
+ int rc;
+
+ if (!xive)
+ return -ENODEV;
+
+ pr_devel("clr_mapped girq 0x%lx...\n", guest_irq);
+
+ sb = kvmppc_xive_find_source(xive, guest_irq, &idx);
+ if (!sb)
+ return -EINVAL;
+ state = &sb->irq_state[idx];
+
+ /*
+ * Mask and read state of IRQ. We need to know if its P bit
+ * is set as that means it's potentially already using a
+ * queue entry in the target
+ */
+ prio = xive_lock_and_mask(xive, sb, state);
+ pr_devel(" old IRQ prio %02x P:%d Q:%d\n", prio,
+ state->old_p, state->old_q);
+
+ /*
+ * If old_p is set, the interrupt is pending, we switch it to
+ * PQ=11. This will force a resend in the host so the interrupt
+ * isn't lost to whatver host driver may pick it up
+ */
+ if (state->old_p)
+ xive_vm_esb_load(state->pt_data, XIVE_ESB_SET_PQ_11);
+
+ /* Release the passed-through interrupt to the host */
+ rc = irq_set_vcpu_affinity(host_irq, NULL);
+ if (rc) {
+ pr_err("Failed to clr VCPU affinity for irq %d\n", host_irq);
+ return rc;
+ }
+
+ /* Forget about the IRQ */
+ state->pt_number = 0;
+ state->pt_data = NULL;
+
+ /* Reconfigure the IPI */
+ xive_native_configure_irq(state->ipi_number,
+ xive->vp_base + state->act_server,
+ state->act_priority, state->number);
+
+ /*
+ * If old_p is set (we have a queue entry potentially
+ * occupied) or the interrupt is masked, we set the IPI
+ * to PQ=10 state. Otherwise we just re-enable it (PQ=00).
+ */
+ if (prio == MASKED || state->old_p)
+ xive_vm_esb_load(&state->ipi_data, XIVE_ESB_SET_PQ_10);
+ else
+ xive_vm_esb_load(&state->ipi_data, XIVE_ESB_SET_PQ_00);
+
+ /* Restore guest prio (unlocks EOI) */
+ mb();
+ state->guest_priority = prio;
+ arch_spin_unlock(&sb->lock);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kvmppc_xive_clr_mapped);
+
+static void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ struct kvm *kvm = vcpu->kvm;
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ int i, j;
+
+ for (i = 0; i <= xive->max_sbid; i++) {
+ struct kvmppc_xive_src_block *sb = xive->src_blocks[i];
+
+ if (!sb)
+ continue;
+ for (j = 0; j < KVMPPC_XICS_IRQ_PER_ICS; j++) {
+ struct kvmppc_xive_irq_state *state = &sb->irq_state[j];
+
+ if (!state->valid)
+ continue;
+ if (state->act_priority == MASKED)
+ continue;
+ if (state->act_server != xc->server_num)
+ continue;
+
+ /* Clean it up */
+ arch_spin_lock(&sb->lock);
+ state->act_priority = MASKED;
+ xive_vm_esb_load(&state->ipi_data, XIVE_ESB_SET_PQ_01);
+ xive_native_configure_irq(state->ipi_number, 0, MASKED, 0);
+ if (state->pt_number) {
+ xive_vm_esb_load(state->pt_data, XIVE_ESB_SET_PQ_01);
+ xive_native_configure_irq(state->pt_number, 0, MASKED, 0);
+ }
+ arch_spin_unlock(&sb->lock);
+ }
+ }
+}
+
+void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ struct kvmppc_xive *xive = xc->xive;
+ int i;
+
+ pr_devel("cleanup_vcpu(cpu=%d)\n", xc->server_num);
+
+ /* Ensure no interrupt is still routed to that VP */
+ xc->valid = false;
+ kvmppc_xive_disable_vcpu_interrupts(vcpu);
+
+ /* Mask the VP IPI */
+ xive_vm_esb_load(&xc->vp_ipi_data, XIVE_ESB_SET_PQ_01);
+
+ /* Disable the VP */
+ xive_native_disable_vp(xc->vp_id);
+
+ /* Free the queues & associated interrupts */
+ for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
+ struct xive_q *q = &xc->queues[i];
+
+ /* Free the escalation irq */
+ if (xc->esc_virq[i]) {
+ free_irq(xc->esc_virq[i], vcpu);
+ irq_dispose_mapping(xc->esc_virq[i]);
+ kfree(xc->esc_virq_names[i]);
+ }
+ /* Free the queue */
+ xive_native_disable_queue(xc->vp_id, q, i);
+ if (q->qpage) {
+ free_pages((unsigned long)q->qpage,
+ xive->q_page_order);
+ q->qpage = NULL;
+ }
+ }
+
+ /* Free the IPI */
+ if (xc->vp_ipi) {
+ xive_cleanup_irq_data(&xc->vp_ipi_data);
+ xive_native_free_irq(xc->vp_ipi);
+ }
+ /* Free the VP */
+ kfree(xc);
+}
+
+int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
+ struct kvm_vcpu *vcpu, u32 cpu)
+{
+ struct kvmppc_xive *xive = dev->private;
+ struct kvmppc_xive_vcpu *xc;
+ int i, r = -EBUSY;
+
+ pr_devel("connect_vcpu(cpu=%d)\n", cpu);
+
+ if (dev->ops != &kvm_xive_ops) {
+ pr_devel("Wrong ops !\n");
+ return -EPERM;
+ }
+ if (xive->kvm != vcpu->kvm)
+ return -EPERM;
+ if (vcpu->arch.irq_type)
+ return -EBUSY;
+ if (kvmppc_xive_find_server(vcpu->kvm, cpu)) {
+ pr_devel("Duplicate !\n");
+ return -EEXIST;
+ }
+ if (cpu >= KVM_MAX_VCPUS) {
+ pr_devel("Out of bounds !\n");
+ return -EINVAL;
+ }
+ xc = kzalloc(sizeof(*xc), GFP_KERNEL);
+ if (!xc)
+ return -ENOMEM;
+
+ /* We need to synchronize with queue provisioning */
+ mutex_lock(&vcpu->kvm->lock);
+ vcpu->arch.xive_vcpu = xc;
+ xc->xive = xive;
+ xc->vcpu = vcpu;
+ xc->server_num = cpu;
+ xc->vp_id = xive->vp_base + cpu;
+ xc->mfrr = 0xff;
+ xc->valid = true;
+
+ r = xive_native_get_vp_info(xc->vp_id, &xc->vp_cam, &xc->vp_chip_id);
+ if (r)
+ goto bail;
+
+ /* Configure VCPU fields for use by assembly push/pull */
+ vcpu->arch.xive_saved_state.w01 = cpu_to_be64(0xff000000);
+ vcpu->arch.xive_cam_word = cpu_to_be32(xc->vp_cam | TM_QW1W2_VO);
+
+ /* Allocate IPI */
+ xc->vp_ipi = xive_native_alloc_irq();
+ if (!xc->vp_ipi) {
+ r = -EIO;
+ goto bail;
+ }
+ pr_devel(" IPI=0x%x\n", xc->vp_ipi);
+
+ r = xive_native_populate_irq_data(xc->vp_ipi, &xc->vp_ipi_data);
+ if (r)
+ goto bail;
+
+ /*
+ * Initialize queues. Initially we set them all for no queueing
+ * and we enable escalation for queue 0 only which we'll use for
+ * our mfrr change notifications. If the VCPU is hot-plugged, we
+ * do handle provisioning however.
+ */
+ for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
+ struct xive_q *q = &xc->queues[i];
+
+ /* Is queue already enabled ? Provision it */
+ if (xive->qmap & (1 << i)) {
+ r = xive_provision_queue(vcpu, i);
+ if (r == 0)
+ xive_attach_escalation(vcpu, i);
+ if (r)
+ goto bail;
+ } else {
+ r = xive_native_configure_queue(xc->vp_id,
+ q, i, NULL, 0, true);
+ if (r) {
+ pr_err("Failed to configure queue %d for VCPU %d\n",
+ i, cpu);
+ goto bail;
+ }
+ }
+ }
+
+ /* If not done above, attach priority 0 escalation */
+ r = xive_attach_escalation(vcpu, 0);
+ if (r)
+ goto bail;
+
+ /* Enable the VP */
+ r = xive_native_enable_vp(xc->vp_id);
+ if (r)
+ goto bail;
+
+ /* Route the IPI */
+ r = xive_native_configure_irq(xc->vp_ipi, xc->vp_id, 0, XICS_IPI);
+ if (!r)
+ xive_vm_esb_load(&xc->vp_ipi_data, XIVE_ESB_SET_PQ_00);
+
+bail:
+ mutex_unlock(&vcpu->kvm->lock);
+ if (r) {
+ kvmppc_xive_cleanup_vcpu(vcpu);
+ return r;
+ }
+
+ vcpu->arch.irq_type = KVMPPC_IRQ_XICS;
+ return 0;
+}
+
+/*
+ * Scanning of queues before/after migration save
+ */
+static void xive_pre_save_set_queued(struct kvmppc_xive *xive, u32 irq)
+{
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u16 idx;
+
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb)
+ return;
+
+ state = &sb->irq_state[idx];
+
+ /* Some sanity checking */
+ if (!state->valid) {
+ pr_err("invalid irq 0x%x in cpu queue!\n", irq);
+ return;
+ }
+
+ /*
+ * If the interrupt is in a queue it should have P set.
+ * We warn so that gets reported. A backtrace isn't useful
+ * so no need to use a WARN_ON.
+ */
+ if (!state->saved_p)
+ pr_err("Interrupt 0x%x is marked in a queue but P not set !\n", irq);
+
+ /* Set flag */
+ state->in_queue = true;
+}
+
+static void xive_pre_save_mask_irq(struct kvmppc_xive *xive,
+ struct kvmppc_xive_src_block *sb,
+ u32 irq)
+{
+ struct kvmppc_xive_irq_state *state = &sb->irq_state[irq];
+
+ if (!state->valid)
+ return;
+
+ /* Mask and save state, this will also sync HW queues */
+ state->saved_scan_prio = xive_lock_and_mask(xive, sb, state);
+
+ /* Transfer P and Q */
+ state->saved_p = state->old_p;
+ state->saved_q = state->old_q;
+
+ /* Unlock */
+ arch_spin_unlock(&sb->lock);
+}
+
+static void xive_pre_save_unmask_irq(struct kvmppc_xive *xive,
+ struct kvmppc_xive_src_block *sb,
+ u32 irq)
+{
+ struct kvmppc_xive_irq_state *state = &sb->irq_state[irq];
+
+ if (!state->valid)
+ return;
+
+ /*
+ * Lock / exclude EOI (not technically necessary if the
+ * guest isn't running concurrently. If this becomes a
+ * performance issue we can probably remove the lock.
+ */
+ xive_lock_for_unmask(sb, state);
+
+ /* Restore mask/prio if it wasn't masked */
+ if (state->saved_scan_prio != MASKED)
+ xive_finish_unmask(xive, sb, state, state->saved_scan_prio);
+
+ /* Unlock */
+ arch_spin_unlock(&sb->lock);
+}
+
+static void xive_pre_save_queue(struct kvmppc_xive *xive, struct xive_q *q)
+{
+ u32 idx = q->idx;
+ u32 toggle = q->toggle;
+ u32 irq;
+
+ do {
+ irq = __xive_read_eq(q->qpage, q->msk, &idx, &toggle);
+ if (irq > XICS_IPI)
+ xive_pre_save_set_queued(xive, irq);
+ } while(irq);
+}
+
+static void xive_pre_save_scan(struct kvmppc_xive *xive)
+{
+ struct kvm_vcpu *vcpu = NULL;
+ int i, j;
+
+ /*
+ * See comment in xive_get_source() about how this
+ * work. Collect a stable state for all interrupts
+ */
+ for (i = 0; i <= xive->max_sbid; i++) {
+ struct kvmppc_xive_src_block *sb = xive->src_blocks[i];
+ if (!sb)
+ continue;
+ for (j = 0; j < KVMPPC_XICS_IRQ_PER_ICS; j++)
+ xive_pre_save_mask_irq(xive, sb, j);
+ }
+
+ /* Then scan the queues and update the "in_queue" flag */
+ kvm_for_each_vcpu(i, vcpu, xive->kvm) {
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ if (!xc)
+ continue;
+ for (j = 0; j < KVMPPC_XIVE_Q_COUNT; j++) {
+ if (xc->queues[i].qpage)
+ xive_pre_save_queue(xive, &xc->queues[i]);
+ }
+ }
+
+ /* Finally restore interrupt states */
+ for (i = 0; i <= xive->max_sbid; i++) {
+ struct kvmppc_xive_src_block *sb = xive->src_blocks[i];
+ if (!sb)
+ continue;
+ for (j = 0; j < KVMPPC_XICS_IRQ_PER_ICS; j++)
+ xive_pre_save_unmask_irq(xive, sb, j);
+ }
+}
+
+static void xive_post_save_scan(struct kvmppc_xive *xive)
+{
+ u32 i, j;
+
+ /* Clear all the in_queue flags */
+ for (i = 0; i <= xive->max_sbid; i++) {
+ struct kvmppc_xive_src_block *sb = xive->src_blocks[i];
+ if (!sb)
+ continue;
+ for (j = 0; j < KVMPPC_XICS_IRQ_PER_ICS; j++)
+ sb->irq_state[j].in_queue = false;
+ }
+
+ /* Next get_source() will do a new scan */
+ xive->saved_src_count = 0;
+}
+
+/*
+ * This returns the source configuration and state to user space.
+ */
+static int xive_get_source(struct kvmppc_xive *xive, long irq, u64 addr)
+{
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u64 __user *ubufp = (u64 __user *) addr;
+ u64 val, prio;
+ u16 idx;
+
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb)
+ return -ENOENT;
+
+ state = &sb->irq_state[idx];
+
+ if (!state->valid)
+ return -ENOENT;
+
+ pr_devel("get_source(%ld)...\n", irq);
+
+ /*
+ * So to properly save the state into something that looks like a
+ * XICS migration stream we cannot treat interrupts individually.
+ *
+ * We need, instead, mask them all (& save their previous PQ state)
+ * to get a stable state in the HW, then sync them to ensure that
+ * any interrupt that had already fired hits its queue, and finally
+ * scan all the queues to collect which interrupts are still present
+ * in the queues, so we can set the "pending" flag on them and
+ * they can be resent on restore.
+ *
+ * So we do it all when the "first" interrupt gets saved, all the
+ * state is collected at that point, the rest of xive_get_source()
+ * will merely collect and convert that state to the expected
+ * userspace bit mask.
+ */
+ if (xive->saved_src_count == 0)
+ xive_pre_save_scan(xive);
+ xive->saved_src_count++;
+
+ /* Convert saved state into something compatible with xics */
+ val = state->guest_server;
+ prio = state->saved_scan_prio;
+
+ if (prio == MASKED) {
+ val |= KVM_XICS_MASKED;
+ prio = state->saved_priority;
+ }
+ val |= prio << KVM_XICS_PRIORITY_SHIFT;
+ if (state->lsi) {
+ val |= KVM_XICS_LEVEL_SENSITIVE;
+ if (state->saved_p)
+ val |= KVM_XICS_PENDING;
+ } else {
+ if (state->saved_p)
+ val |= KVM_XICS_PRESENTED;
+
+ if (state->saved_q)
+ val |= KVM_XICS_QUEUED;
+
+ /*
+ * We mark it pending (which will attempt a re-delivery)
+ * if we are in a queue *or* we were masked and had
+ * Q set which is equivalent to the XICS "masked pending"
+ * state
+ */
+ if (state->in_queue || (prio == MASKED && state->saved_q))
+ val |= KVM_XICS_PENDING;
+ }
+
+ /*
+ * If that was the last interrupt saved, reset the
+ * in_queue flags
+ */
+ if (xive->saved_src_count == xive->src_count)
+ xive_post_save_scan(xive);
+
+ /* Copy the result to userspace */
+ if (put_user(val, ubufp))
+ return -EFAULT;
+
+ return 0;
+}
+
+static struct kvmppc_xive_src_block *xive_create_src_block(struct kvmppc_xive *xive,
+ int irq)
+{
+ struct kvm *kvm = xive->kvm;
+ struct kvmppc_xive_src_block *sb;
+ int i, bid;
+
+ bid = irq >> KVMPPC_XICS_ICS_SHIFT;
+
+ mutex_lock(&kvm->lock);
+
+ /* block already exists - somebody else got here first */
+ if (xive->src_blocks[bid])
+ goto out;
+
+ /* Create the ICS */
+ sb = kzalloc(sizeof(*sb), GFP_KERNEL);
+ if (!sb)
+ goto out;
+
+ sb->id = bid;
+
+ for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
+ sb->irq_state[i].number = (bid << KVMPPC_XICS_ICS_SHIFT) | i;
+ sb->irq_state[i].guest_priority = MASKED;
+ sb->irq_state[i].saved_priority = MASKED;
+ sb->irq_state[i].act_priority = MASKED;
+ }
+ smp_wmb();
+ xive->src_blocks[bid] = sb;
+
+ if (bid > xive->max_sbid)
+ xive->max_sbid = bid;
+
+out:
+ mutex_unlock(&kvm->lock);
+ return xive->src_blocks[bid];
+}
+
+static bool xive_check_delayed_irq(struct kvmppc_xive *xive, u32 irq)
+{
+ struct kvm *kvm = xive->kvm;
+ struct kvm_vcpu *vcpu = NULL;
+ int i;
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+
+ if (!xc)
+ continue;
+
+ if (xc->delayed_irq == irq) {
+ xc->delayed_irq = 0;
+ xive->delayed_irqs--;
+ return true;
+ }
+ }
+ return false;
+}
+
+static int xive_set_source(struct kvmppc_xive *xive, long irq, u64 addr)
+{
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u64 __user *ubufp = (u64 __user *) addr;
+ u16 idx;
+ u64 val;
+ u8 act_prio, guest_prio;
+ u32 server;
+ int rc = 0;
+
+ if (irq < KVMPPC_XICS_FIRST_IRQ || irq >= KVMPPC_XICS_NR_IRQS)
+ return -ENOENT;
+
+ pr_devel("set_source(irq=0x%lx)\n", irq);
+
+ /* Find the source */
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb) {
+ pr_devel("No source, creating source block...\n");
+ sb = xive_create_src_block(xive, irq);
+ if (!sb) {
+ pr_devel("Failed to create block...\n");
+ return -ENOMEM;
+ }
+ }
+ state = &sb->irq_state[idx];
+
+ /* Read user passed data */
+ if (get_user(val, ubufp)) {
+ pr_devel("fault getting user info !\n");
+ return -EFAULT;
+ }
+
+ server = val & KVM_XICS_DESTINATION_MASK;
+ guest_prio = val >> KVM_XICS_PRIORITY_SHIFT;
+
+ pr_devel(" val=0x016%llx (server=0x%x, guest_prio=%d)\n",
+ val, server, guest_prio);
+ /*
+ * If the source doesn't already have an IPI, allocate
+ * one and get the corresponding data
+ */
+ if (!state->ipi_number) {
+ state->ipi_number = xive_native_alloc_irq();
+ if (state->ipi_number == 0) {
+ pr_devel("Failed to allocate IPI !\n");
+ return -ENOMEM;
+ }
+ xive_native_populate_irq_data(state->ipi_number, &state->ipi_data);
+ pr_devel(" src_ipi=0x%x\n", state->ipi_number);
+ }
+
+ /*
+ * We use lock_and_mask() to set us in the right masked
+ * state. We will override that state from the saved state
+ * further down, but this will handle the cases of interrupts
+ * that need FW masking. We set the initial guest_priority to
+ * 0 before calling it to ensure it actually performs the masking.
+ */
+ state->guest_priority = 0;
+ xive_lock_and_mask(xive, sb, state);
+
+ /*
+ * Now, we select a target if we have one. If we don't we
+ * leave the interrupt untargetted. It means that an interrupt
+ * can become "untargetted" accross migration if it was masked
+ * by set_xive() but there is little we can do about it.
+ */
+
+ /* First convert prio and mark interrupt as untargetted */
+ act_prio = xive_prio_from_guest(guest_prio);
+ state->act_priority = MASKED;
+ state->guest_server = server;
+
+ /*
+ * We need to drop the lock due to the mutex below. Hopefully
+ * nothing is touching that interrupt yet since it hasn't been
+ * advertized to a running guest yet
+ */
+ arch_spin_unlock(&sb->lock);
+
+ /* If we have a priority target the interrupt */
+ if (act_prio != MASKED) {
+ /* First, check provisioning of queues */
+ mutex_lock(&xive->kvm->lock);
+ rc = xive_check_provisioning(xive->kvm, act_prio);
+ mutex_unlock(&xive->kvm->lock);
+
+ /* Target interrupt */
+ if (rc == 0)
+ rc = xive_target_interrupt(xive->kvm, state,
+ server, act_prio);
+ /*
+ * If provisioning or targetting failed, leave it
+ * alone and masked. It will remain disabled until
+ * the guest re-targets it.
+ */
+ }
+
+ /*
+ * Find out if this was a delayed irq stashed in an ICP,
+ * in which case, treat it as pending
+ */
+ if (xive->delayed_irqs && xive_check_delayed_irq(xive, irq)) {
+ val |= KVM_XICS_PENDING;
+ pr_devel(" Found delayed ! forcing PENDING !\n");
+ }
+
+ /* Cleanup the SW state */
+ state->old_p = false;
+ state->old_q = false;
+ state->lsi = false;
+ state->asserted = false;
+
+ /* Restore LSI state */
+ if (val & KVM_XICS_LEVEL_SENSITIVE) {
+ state->lsi = true;
+ if (val & KVM_XICS_PENDING)
+ state->asserted = true;
+ pr_devel(" LSI ! Asserted=%d\n", state->asserted);
+ }
+
+ /*
+ * Restore P and Q. If the interrupt was pending, we
+ * force both P and Q, which will trigger a resend.
+ *
+ * That means that a guest that had both an interrupt
+ * pending (queued) and Q set will restore with only
+ * one instance of that interrupt instead of 2, but that
+ * is perfectly fine as coalescing interrupts that haven't
+ * been presented yet is always allowed.
+ */
+ if (val & KVM_XICS_PRESENTED || val & KVM_XICS_PENDING)
+ state->old_p = true;
+ if (val & KVM_XICS_QUEUED || val & KVM_XICS_PENDING)
+ state->old_q = true;
+
+ pr_devel(" P=%d, Q=%d\n", state->old_p, state->old_q);
+
+ /*
+ * If the interrupt was unmasked, update guest priority and
+ * perform the appropriate state transition and do a
+ * re-trigger if necessary.
+ */
+ if (val & KVM_XICS_MASKED) {
+ pr_devel(" masked, saving prio\n");
+ state->guest_priority = MASKED;
+ state->saved_priority = guest_prio;
+ } else {
+ pr_devel(" unmasked, restoring to prio %d\n", guest_prio);
+ xive_finish_unmask(xive, sb, state, guest_prio);
+ state->saved_priority = guest_prio;
+ }
+
+ /* Increment the number of valid sources and mark this one valid */
+ if (!state->valid)
+ xive->src_count++;
+ state->valid = true;
+
+ return 0;
+}
+
+int kvmppc_xive_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
+ bool line_status)
+{
+ struct kvmppc_xive *xive = kvm->arch.xive;
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ u16 idx;
+
+ if (!xive)
+ return -ENODEV;
+
+ sb = kvmppc_xive_find_source(xive, irq, &idx);
+ if (!sb)
+ return -EINVAL;
+
+ /* Perform locklessly .... (we need to do some RCUisms here...) */
+ state = &sb->irq_state[idx];
+ if (!state->valid)
+ return -EINVAL;
+
+ /* We don't allow a trigger on a passed-through interrupt */
+ if (state->pt_number)
+ return -EINVAL;
+
+ if ((level == 1 && state->lsi) || level == KVM_INTERRUPT_SET_LEVEL)
+ state->asserted = 1;
+ else if (level == 0 || level == KVM_INTERRUPT_UNSET) {
+ state->asserted = 0;
+ return 0;
+ }
+
+ /* Trigger the IPI */
+ xive_irq_trigger(&state->ipi_data);
+
+ return 0;
+}
+
+static int xive_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
+{
+ struct kvmppc_xive *xive = dev->private;
+
+ /* We honor the existing XICS ioctl */
+ switch (attr->group) {
+ case KVM_DEV_XICS_GRP_SOURCES:
+ return xive_set_source(xive, attr->attr, attr->addr);
+ }
+ return -ENXIO;
+}
+
+static int xive_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
+{
+ struct kvmppc_xive *xive = dev->private;
+
+ /* We honor the existing XICS ioctl */
+ switch (attr->group) {
+ case KVM_DEV_XICS_GRP_SOURCES:
+ return xive_get_source(xive, attr->attr, attr->addr);
+ }
+ return -ENXIO;
+}
+
+static int xive_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
+{
+ /* We honor the same limits as XICS, at least for now */
+ switch (attr->group) {
+ case KVM_DEV_XICS_GRP_SOURCES:
+ if (attr->attr >= KVMPPC_XICS_FIRST_IRQ &&
+ attr->attr < KVMPPC_XICS_NR_IRQS)
+ return 0;
+ break;
+ }
+ return -ENXIO;
+}
+
+static void kvmppc_xive_cleanup_irq(u32 hw_num, struct xive_irq_data *xd)
+{
+ xive_vm_esb_load(xd, XIVE_ESB_SET_PQ_01);
+ xive_native_configure_irq(hw_num, 0, MASKED, 0);
+ xive_cleanup_irq_data(xd);
+}
+
+static void kvmppc_xive_free_sources(struct kvmppc_xive_src_block *sb)
+{
+ int i;
+
+ for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
+ struct kvmppc_xive_irq_state *state = &sb->irq_state[i];
+
+ if (!state->valid)
+ continue;
+
+ kvmppc_xive_cleanup_irq(state->ipi_number, &state->ipi_data);
+ xive_native_free_irq(state->ipi_number);
+
+ /* Pass-through, cleanup too */
+ if (state->pt_number)
+ kvmppc_xive_cleanup_irq(state->pt_number, state->pt_data);
+
+ state->valid = false;
+ }
+}
+
+static void kvmppc_xive_free(struct kvm_device *dev)
+{
+ struct kvmppc_xive *xive = dev->private;
+ struct kvm *kvm = xive->kvm;
+ int i;
+
+ debugfs_remove(xive->dentry);
+
+ if (kvm)
+ kvm->arch.xive = NULL;
+
+ /* Mask and free interrupts */
+ for (i = 0; i <= xive->max_sbid; i++) {
+ if (xive->src_blocks[i])
+ kvmppc_xive_free_sources(xive->src_blocks[i]);
+ kfree(xive->src_blocks[i]);
+ xive->src_blocks[i] = NULL;
+ }
+
+ if (xive->vp_base != XIVE_INVALID_VP)
+ xive_native_free_vp_block(xive->vp_base);
+
+
+ kfree(xive);
+ kfree(dev);
+}
+
+static int kvmppc_xive_create(struct kvm_device *dev, u32 type)
+{
+ struct kvmppc_xive *xive;
+ struct kvm *kvm = dev->kvm;
+ int ret = 0;
+
+ pr_devel("Creating xive for partition\n");
+
+ xive = kzalloc(sizeof(*xive), GFP_KERNEL);
+ if (!xive)
+ return -ENOMEM;
+
+ dev->private = xive;
+ xive->dev = dev;
+ xive->kvm = kvm;
+
+ /* Already there ? */
+ if (kvm->arch.xive)
+ ret = -EEXIST;
+ else
+ kvm->arch.xive = xive;
+
+ /* We use the default queue size set by the host */
+ xive->q_order = xive_native_default_eq_shift();
+ if (xive->q_order < PAGE_SHIFT)
+ xive->q_page_order = 0;
+ else
+ xive->q_page_order = xive->q_order - PAGE_SHIFT;
+
+ /* Allocate a bunch of VPs */
+ xive->vp_base = xive_native_alloc_vp_block(KVM_MAX_VCPUS);
+ pr_devel("VP_Base=%x\n", xive->vp_base);
+
+ if (xive->vp_base == XIVE_INVALID_VP)
+ ret = -ENOMEM;
+
+ if (ret) {
+ kfree(xive);
+ return ret;
+ }
+
+ return 0;
+}
+
+
+static int xive_debug_show(struct seq_file *m, void *private)
+{
+ struct kvmppc_xive *xive = m->private;
+ struct kvm *kvm = xive->kvm;
+ struct kvm_vcpu *vcpu;
+ u64 t_rm_h_xirr = 0;
+ u64 t_rm_h_ipoll = 0;
+ u64 t_rm_h_cppr = 0;
+ u64 t_rm_h_eoi = 0;
+ u64 t_rm_h_ipi = 0;
+ u64 t_vm_h_xirr = 0;
+ u64 t_vm_h_ipoll = 0;
+ u64 t_vm_h_cppr = 0;
+ u64 t_vm_h_eoi = 0;
+ u64 t_vm_h_ipi = 0;
+ unsigned int i;
+
+ if (!kvm)
+ return 0;
+
+ seq_printf(m, "=========\nVCPU state\n=========\n");
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+
+ if (!xc)
+ continue;
+
+ seq_printf(m, "cpu server %#x CPPR:%#x HWCPPR:%#x"
+ " MFRR:%#x PEND:%#x h_xirr: R=%lld V=%lld\n",
+ xc->server_num, xc->cppr, xc->hw_cppr,
+ xc->mfrr, xc->pending,
+ xc->stat_rm_h_xirr, xc->stat_vm_h_xirr);
+
+ t_rm_h_xirr += xc->stat_rm_h_xirr;
+ t_rm_h_ipoll += xc->stat_rm_h_ipoll;
+ t_rm_h_cppr += xc->stat_rm_h_cppr;
+ t_rm_h_eoi += xc->stat_rm_h_eoi;
+ t_rm_h_ipi += xc->stat_rm_h_ipi;
+ t_vm_h_xirr += xc->stat_vm_h_xirr;
+ t_vm_h_ipoll += xc->stat_vm_h_ipoll;
+ t_vm_h_cppr += xc->stat_vm_h_cppr;
+ t_vm_h_eoi += xc->stat_vm_h_eoi;
+ t_vm_h_ipi += xc->stat_vm_h_ipi;
+ }
+
+ seq_printf(m, "Hcalls totals\n");
+ seq_printf(m, " H_XIRR R=%10lld V=%10lld\n", t_rm_h_xirr, t_vm_h_xirr);
+ seq_printf(m, " H_IPOLL R=%10lld V=%10lld\n", t_rm_h_ipoll, t_vm_h_ipoll);
+ seq_printf(m, " H_CPPR R=%10lld V=%10lld\n", t_rm_h_cppr, t_vm_h_cppr);
+ seq_printf(m, " H_EOI R=%10lld V=%10lld\n", t_rm_h_eoi, t_vm_h_eoi);
+ seq_printf(m, " H_IPI R=%10lld V=%10lld\n", t_rm_h_ipi, t_vm_h_ipi);
+
+ return 0;
+}
+
+static int xive_debug_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, xive_debug_show, inode->i_private);
+}
+
+static const struct file_operations xive_debug_fops = {
+ .open = xive_debug_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static void xive_debugfs_init(struct kvmppc_xive *xive)
+{
+ char *name;
+
+ name = kasprintf(GFP_KERNEL, "kvm-xive-%p", xive);
+ if (!name) {
+ pr_err("%s: no memory for name\n", __func__);
+ return;
+ }
+
+ xive->dentry = debugfs_create_file(name, S_IRUGO, powerpc_debugfs_root,
+ xive, &xive_debug_fops);
+
+ pr_debug("%s: created %s\n", __func__, name);
+ kfree(name);
+}
+
+static void kvmppc_xive_init(struct kvm_device *dev)
+{
+ struct kvmppc_xive *xive = (struct kvmppc_xive *)dev->private;
+
+ /* Register some debug interfaces */
+ xive_debugfs_init(xive);
+}
+
+struct kvm_device_ops kvm_xive_ops = {
+ .name = "kvm-xive",
+ .create = kvmppc_xive_create,
+ .init = kvmppc_xive_init,
+ .destroy = kvmppc_xive_free,
+ .set_attr = xive_set_attr,
+ .get_attr = xive_get_attr,
+ .has_attr = xive_has_attr,
+};
+
+void kvmppc_xive_init_module(void)
+{
+ __xive_vm_h_xirr = xive_vm_h_xirr;
+ __xive_vm_h_ipoll = xive_vm_h_ipoll;
+ __xive_vm_h_ipi = xive_vm_h_ipi;
+ __xive_vm_h_cppr = xive_vm_h_cppr;
+ __xive_vm_h_eoi = xive_vm_h_eoi;
+}
+
+void kvmppc_xive_exit_module(void)
+{
+ __xive_vm_h_xirr = NULL;
+ __xive_vm_h_ipoll = NULL;
+ __xive_vm_h_ipi = NULL;
+ __xive_vm_h_cppr = NULL;
+ __xive_vm_h_eoi = NULL;
+}
diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h
new file mode 100644
index 000000000000..5938f7644dc1
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_xive.h
@@ -0,0 +1,256 @@
+/*
+ * Copyright 2017 Benjamin Herrenschmidt, IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _KVM_PPC_BOOK3S_XIVE_H
+#define _KVM_PPC_BOOK3S_XIVE_H
+
+#ifdef CONFIG_KVM_XICS
+#include "book3s_xics.h"
+
+/*
+ * State for one guest irq source.
+ *
+ * For each guest source we allocate a HW interrupt in the XIVE
+ * which we use for all SW triggers. It will be unused for
+ * pass-through but it's easier to keep around as the same
+ * guest interrupt can alternatively be emulated or pass-through
+ * if a physical device is hot unplugged and replaced with an
+ * emulated one.
+ *
+ * This state structure is very similar to the XICS one with
+ * additional XIVE specific tracking.
+ */
+struct kvmppc_xive_irq_state {
+ bool valid; /* Interrupt entry is valid */
+
+ u32 number; /* Guest IRQ number */
+ u32 ipi_number; /* XIVE IPI HW number */
+ struct xive_irq_data ipi_data; /* XIVE IPI associated data */
+ u32 pt_number; /* XIVE Pass-through number if any */
+ struct xive_irq_data *pt_data; /* XIVE Pass-through associated data */
+
+ /* Targetting as set by guest */
+ u32 guest_server; /* Current guest selected target */
+ u8 guest_priority; /* Guest set priority */
+ u8 saved_priority; /* Saved priority when masking */
+
+ /* Actual targetting */
+ u32 act_server; /* Actual server */
+ u8 act_priority; /* Actual priority */
+
+ /* Various state bits */
+ bool in_eoi; /* Synchronize with H_EOI */
+ bool old_p; /* P bit state when masking */
+ bool old_q; /* Q bit state when masking */
+ bool lsi; /* level-sensitive interrupt */
+ bool asserted; /* Only for emulated LSI: current state */
+
+ /* Saved for migration state */
+ bool in_queue;
+ bool saved_p;
+ bool saved_q;
+ u8 saved_scan_prio;
+};
+
+/* Select the "right" interrupt (IPI vs. passthrough) */
+static inline void kvmppc_xive_select_irq(struct kvmppc_xive_irq_state *state,
+ u32 *out_hw_irq,
+ struct xive_irq_data **out_xd)
+{
+ if (state->pt_number) {
+ if (out_hw_irq)
+ *out_hw_irq = state->pt_number;
+ if (out_xd)
+ *out_xd = state->pt_data;
+ } else {
+ if (out_hw_irq)
+ *out_hw_irq = state->ipi_number;
+ if (out_xd)
+ *out_xd = &state->ipi_data;
+ }
+}
+
+/*
+ * This corresponds to an "ICS" in XICS terminology, we use it
+ * as a mean to break up source information into multiple structures.
+ */
+struct kvmppc_xive_src_block {
+ arch_spinlock_t lock;
+ u16 id;
+ struct kvmppc_xive_irq_state irq_state[KVMPPC_XICS_IRQ_PER_ICS];
+};
+
+
+struct kvmppc_xive {
+ struct kvm *kvm;
+ struct kvm_device *dev;
+ struct dentry *dentry;
+
+ /* VP block associated with the VM */
+ u32 vp_base;
+
+ /* Blocks of sources */
+ struct kvmppc_xive_src_block *src_blocks[KVMPPC_XICS_MAX_ICS_ID + 1];
+ u32 max_sbid;
+
+ /*
+ * For state save, we lazily scan the queues on the first interrupt
+ * being migrated. We don't have a clean way to reset that flags
+ * so we keep track of the number of valid sources and how many of
+ * them were migrated so we can reset when all of them have been
+ * processed.
+ */
+ u32 src_count;
+ u32 saved_src_count;
+
+ /*
+ * Some irqs are delayed on restore until the source is created,
+ * keep track here of how many of them
+ */
+ u32 delayed_irqs;
+
+ /* Which queues (priorities) are in use by the guest */
+ u8 qmap;
+
+ /* Queue orders */
+ u32 q_order;
+ u32 q_page_order;
+
+};
+
+#define KVMPPC_XIVE_Q_COUNT 8
+
+struct kvmppc_xive_vcpu {
+ struct kvmppc_xive *xive;
+ struct kvm_vcpu *vcpu;
+ bool valid;
+
+ /* Server number. This is the HW CPU ID from a guest perspective */
+ u32 server_num;
+
+ /*
+ * HW VP corresponding to this VCPU. This is the base of the VP
+ * block plus the server number.
+ */
+ u32 vp_id;
+ u32 vp_chip_id;
+ u32 vp_cam;
+
+ /* IPI used for sending ... IPIs */
+ u32 vp_ipi;
+ struct xive_irq_data vp_ipi_data;
+
+ /* Local emulation state */
+ uint8_t cppr; /* guest CPPR */
+ uint8_t hw_cppr;/* Hardware CPPR */
+ uint8_t mfrr;
+ uint8_t pending;
+
+ /* Each VP has 8 queues though we only provision some */
+ struct xive_q queues[KVMPPC_XIVE_Q_COUNT];
+ u32 esc_virq[KVMPPC_XIVE_Q_COUNT];
+ char *esc_virq_names[KVMPPC_XIVE_Q_COUNT];
+
+ /* Stash a delayed irq on restore from migration (see set_icp) */
+ u32 delayed_irq;
+
+ /* Stats */
+ u64 stat_rm_h_xirr;
+ u64 stat_rm_h_ipoll;
+ u64 stat_rm_h_cppr;
+ u64 stat_rm_h_eoi;
+ u64 stat_rm_h_ipi;
+ u64 stat_vm_h_xirr;
+ u64 stat_vm_h_ipoll;
+ u64 stat_vm_h_cppr;
+ u64 stat_vm_h_eoi;
+ u64 stat_vm_h_ipi;
+};
+
+static inline struct kvm_vcpu *kvmppc_xive_find_server(struct kvm *kvm, u32 nr)
+{
+ struct kvm_vcpu *vcpu = NULL;
+ int i;
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (vcpu->arch.xive_vcpu && nr == vcpu->arch.xive_vcpu->server_num)
+ return vcpu;
+ }
+ return NULL;
+}
+
+static inline struct kvmppc_xive_src_block *kvmppc_xive_find_source(struct kvmppc_xive *xive,
+ u32 irq, u16 *source)
+{
+ u32 bid = irq >> KVMPPC_XICS_ICS_SHIFT;
+ u16 src = irq & KVMPPC_XICS_SRC_MASK;
+
+ if (source)
+ *source = src;
+ if (bid > KVMPPC_XICS_MAX_ICS_ID)
+ return NULL;
+ return xive->src_blocks[bid];
+}
+
+/*
+ * Mapping between guest priorities and host priorities
+ * is as follow.
+ *
+ * Guest request for 0...6 are honored. Guest request for anything
+ * higher results in a priority of 7 being applied.
+ *
+ * However, when XIRR is returned via H_XIRR, 7 is translated to 0xb
+ * in order to match AIX expectations
+ *
+ * Similar mapping is done for CPPR values
+ */
+static inline u8 xive_prio_from_guest(u8 prio)
+{
+ if (prio == 0xff || prio < 8)
+ return prio;
+ return 7;
+}
+
+static inline u8 xive_prio_to_guest(u8 prio)
+{
+ if (prio == 0xff || prio < 7)
+ return prio;
+ return 0xb;
+}
+
+static inline u32 __xive_read_eq(__be32 *qpage, u32 msk, u32 *idx, u32 *toggle)
+{
+ u32 cur;
+
+ if (!qpage)
+ return 0;
+ cur = be32_to_cpup(qpage + *idx);
+ if ((cur >> 31) == *toggle)
+ return 0;
+ *idx = (*idx + 1) & msk;
+ if (*idx == 0)
+ (*toggle) ^= 1;
+ return cur & 0x7fffffff;
+}
+
+extern unsigned long xive_rm_h_xirr(struct kvm_vcpu *vcpu);
+extern unsigned long xive_rm_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server);
+extern int xive_rm_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
+ unsigned long mfrr);
+extern int xive_rm_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr);
+extern int xive_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr);
+
+extern unsigned long (*__xive_vm_h_xirr)(struct kvm_vcpu *vcpu);
+extern unsigned long (*__xive_vm_h_ipoll)(struct kvm_vcpu *vcpu, unsigned long server);
+extern int (*__xive_vm_h_ipi)(struct kvm_vcpu *vcpu, unsigned long server,
+ unsigned long mfrr);
+extern int (*__xive_vm_h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr);
+extern int (*__xive_vm_h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr);
+
+#endif /* CONFIG_KVM_XICS */
+#endif /* _KVM_PPC_BOOK3S_XICS_H */
diff --git a/arch/powerpc/kvm/book3s_xive_template.c b/arch/powerpc/kvm/book3s_xive_template.c
new file mode 100644
index 000000000000..023a31133c37
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_xive_template.c
@@ -0,0 +1,503 @@
+/*
+ * Copyright 2017 Benjamin Herrenschmidt, IBM Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+/* File to be included by other .c files */
+
+#define XGLUE(a,b) a##b
+#define GLUE(a,b) XGLUE(a,b)
+
+static void GLUE(X_PFX,ack_pending)(struct kvmppc_xive_vcpu *xc)
+{
+ u8 cppr;
+ u16 ack;
+
+ /* XXX DD1 bug workaround: Check PIPR vs. CPPR first ! */
+
+ /* Perform the acknowledge OS to register cycle. */
+ ack = be16_to_cpu(__x_readw(__x_tima + TM_SPC_ACK_OS_REG));
+
+ /* Synchronize subsequent queue accesses */
+ mb();
+
+ /* XXX Check grouping level */
+
+ /* Anything ? */
+ if (!((ack >> 8) & TM_QW1_NSR_EO))
+ return;
+
+ /* Grab CPPR of the most favored pending interrupt */
+ cppr = ack & 0xff;
+ if (cppr < 8)
+ xc->pending |= 1 << cppr;
+
+#ifdef XIVE_RUNTIME_CHECKS
+ /* Check consistency */
+ if (cppr >= xc->hw_cppr)
+ pr_warn("KVM-XIVE: CPU %d odd ack CPPR, got %d at %d\n",
+ smp_processor_id(), cppr, xc->hw_cppr);
+#endif
+
+ /*
+ * Update our image of the HW CPPR. We don't yet modify
+ * xc->cppr, this will be done as we scan for interrupts
+ * in the queues.
+ */
+ xc->hw_cppr = cppr;
+}
+
+static u8 GLUE(X_PFX,esb_load)(struct xive_irq_data *xd, u32 offset)
+{
+ u64 val;
+
+ if (xd->flags & XIVE_IRQ_FLAG_SHIFT_BUG)
+ offset |= offset << 4;
+
+ val =__x_readq(__x_eoi_page(xd) + offset);
+#ifdef __LITTLE_ENDIAN__
+ val >>= 64-8;
+#endif
+ return (u8)val;
+}
+
+
+static void GLUE(X_PFX,source_eoi)(u32 hw_irq, struct xive_irq_data *xd)
+{
+ /* If the XIVE supports the new "store EOI facility, use it */
+ if (xd->flags & XIVE_IRQ_FLAG_STORE_EOI)
+ __x_writeq(0, __x_eoi_page(xd));
+ else if (hw_irq && xd->flags & XIVE_IRQ_FLAG_EOI_FW) {
+ opal_int_eoi(hw_irq);
+ } else {
+ uint64_t eoi_val;
+
+ /*
+ * Otherwise for EOI, we use the special MMIO that does
+ * a clear of both P and Q and returns the old Q,
+ * except for LSIs where we use the "EOI cycle" special
+ * load.
+ *
+ * This allows us to then do a re-trigger if Q was set
+ * rather than synthetizing an interrupt in software
+ *
+ * For LSIs, using the HW EOI cycle works around a problem
+ * on P9 DD1 PHBs where the other ESB accesses don't work
+ * properly.
+ */
+ if (xd->flags & XIVE_IRQ_FLAG_LSI)
+ __x_readq(__x_eoi_page(xd));
+ else {
+ eoi_val = GLUE(X_PFX,esb_load)(xd, XIVE_ESB_SET_PQ_00);
+
+ /* Re-trigger if needed */
+ if ((eoi_val & 1) && __x_trig_page(xd))
+ __x_writeq(0, __x_trig_page(xd));
+ }
+ }
+}
+
+enum {
+ scan_fetch,
+ scan_poll,
+ scan_eoi,
+};
+
+static u32 GLUE(X_PFX,scan_interrupts)(struct kvmppc_xive_vcpu *xc,
+ u8 pending, int scan_type)
+{
+ u32 hirq = 0;
+ u8 prio = 0xff;
+
+ /* Find highest pending priority */
+ while ((xc->mfrr != 0xff || pending != 0) && hirq == 0) {
+ struct xive_q *q;
+ u32 idx, toggle;
+ __be32 *qpage;
+
+ /*
+ * If pending is 0 this will return 0xff which is what
+ * we want
+ */
+ prio = ffs(pending) - 1;
+
+ /*
+ * If the most favoured prio we found pending is less
+ * favored (or equal) than a pending IPI, we return
+ * the IPI instead.
+ *
+ * Note: If pending was 0 and mfrr is 0xff, we will
+ * not spurriously take an IPI because mfrr cannot
+ * then be smaller than cppr.
+ */
+ if (prio >= xc->mfrr && xc->mfrr < xc->cppr) {
+ prio = xc->mfrr;
+ hirq = XICS_IPI;
+ break;
+ }
+
+ /* Don't scan past the guest cppr */
+ if (prio >= xc->cppr || prio > 7)
+ break;
+
+ /* Grab queue and pointers */
+ q = &xc->queues[prio];
+ idx = q->idx;
+ toggle = q->toggle;
+
+ /*
+ * Snapshot the queue page. The test further down for EOI
+ * must use the same "copy" that was used by __xive_read_eq
+ * since qpage can be set concurrently and we don't want
+ * to miss an EOI.
+ */
+ qpage = READ_ONCE(q->qpage);
+
+skip_ipi:
+ /*
+ * Try to fetch from the queue. Will return 0 for a
+ * non-queueing priority (ie, qpage = 0).
+ */
+ hirq = __xive_read_eq(qpage, q->msk, &idx, &toggle);
+
+ /*
+ * If this was a signal for an MFFR change done by
+ * H_IPI we skip it. Additionally, if we were fetching
+ * we EOI it now, thus re-enabling reception of a new
+ * such signal.
+ *
+ * We also need to do that if prio is 0 and we had no
+ * page for the queue. In this case, we have non-queued
+ * IPI that needs to be EOId.
+ *
+ * This is safe because if we have another pending MFRR
+ * change that wasn't observed above, the Q bit will have
+ * been set and another occurrence of the IPI will trigger.
+ */
+ if (hirq == XICS_IPI || (prio == 0 && !qpage)) {
+ if (scan_type == scan_fetch)
+ GLUE(X_PFX,source_eoi)(xc->vp_ipi,
+ &xc->vp_ipi_data);
+ /* Loop back on same queue with updated idx/toggle */
+#ifdef XIVE_RUNTIME_CHECKS
+ WARN_ON(hirq && hirq != XICS_IPI);
+#endif
+ if (hirq)
+ goto skip_ipi;
+ }
+
+ /* If fetching, update queue pointers */
+ if (scan_type == scan_fetch) {
+ q->idx = idx;
+ q->toggle = toggle;
+ }
+
+ /* Something found, stop searching */
+ if (hirq)
+ break;
+
+ /* Clear the pending bit on the now empty queue */
+ pending &= ~(1 << prio);
+
+ /*
+ * Check if the queue count needs adjusting due to
+ * interrupts being moved away.
+ */
+ if (atomic_read(&q->pending_count)) {
+ int p = atomic_xchg(&q->pending_count, 0);
+ if (p) {
+#ifdef XIVE_RUNTIME_CHECKS
+ WARN_ON(p > atomic_read(&q->count));
+#endif
+ atomic_sub(p, &q->count);
+ }
+ }
+ }
+
+ /* If we are just taking a "peek", do nothing else */
+ if (scan_type == scan_poll)
+ return hirq;
+
+ /* Update the pending bits */
+ xc->pending = pending;
+
+ /*
+ * If this is an EOI that's it, no CPPR adjustment done here,
+ * all we needed was cleanup the stale pending bits and check
+ * if there's anything left.
+ */
+ if (scan_type == scan_eoi)
+ return hirq;
+
+ /*
+ * If we found an interrupt, adjust what the guest CPPR should
+ * be as if we had just fetched that interrupt from HW.
+ */
+ if (hirq)
+ xc->cppr = prio;
+ /*
+ * If it was an IPI the HW CPPR might have been lowered too much
+ * as the HW interrupt we use for IPIs is routed to priority 0.
+ *
+ * We re-sync it here.
+ */
+ if (xc->cppr != xc->hw_cppr) {
+ xc->hw_cppr = xc->cppr;
+ __x_writeb(xc->cppr, __x_tima + TM_QW1_OS + TM_CPPR);
+ }
+
+ return hirq;
+}
+
+X_STATIC unsigned long GLUE(X_PFX,h_xirr)(struct kvm_vcpu *vcpu)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ u8 old_cppr;
+ u32 hirq;
+
+ pr_devel("H_XIRR\n");
+
+ xc->GLUE(X_STAT_PFX,h_xirr)++;
+
+ /* First collect pending bits from HW */
+ GLUE(X_PFX,ack_pending)(xc);
+
+ /*
+ * Cleanup the old-style bits if needed (they may have been
+ * set by pull or an escalation interrupts).
+ */
+ if (test_bit(BOOK3S_IRQPRIO_EXTERNAL, &vcpu->arch.pending_exceptions))
+ clear_bit(BOOK3S_IRQPRIO_EXTERNAL_LEVEL,
+ &vcpu->arch.pending_exceptions);
+
+ pr_devel(" new pending=0x%02x hw_cppr=%d cppr=%d\n",
+ xc->pending, xc->hw_cppr, xc->cppr);
+
+ /* Grab previous CPPR and reverse map it */
+ old_cppr = xive_prio_to_guest(xc->cppr);
+
+ /* Scan for actual interrupts */
+ hirq = GLUE(X_PFX,scan_interrupts)(xc, xc->pending, scan_fetch);
+
+ pr_devel(" got hirq=0x%x hw_cppr=%d cppr=%d\n",
+ hirq, xc->hw_cppr, xc->cppr);
+
+#ifdef XIVE_RUNTIME_CHECKS
+ /* That should never hit */
+ if (hirq & 0xff000000)
+ pr_warn("XIVE: Weird guest interrupt number 0x%08x\n", hirq);
+#endif
+
+ /*
+ * XXX We could check if the interrupt is masked here and
+ * filter it. If we chose to do so, we would need to do:
+ *
+ * if (masked) {
+ * lock();
+ * if (masked) {
+ * old_Q = true;
+ * hirq = 0;
+ * }
+ * unlock();
+ * }
+ */
+
+ /* Return interrupt and old CPPR in GPR4 */
+ vcpu->arch.gpr[4] = hirq | (old_cppr << 24);
+
+ return H_SUCCESS;
+}
+
+X_STATIC unsigned long GLUE(X_PFX,h_ipoll)(struct kvm_vcpu *vcpu, unsigned long server)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ u8 pending = xc->pending;
+ u32 hirq;
+ u8 pipr;
+
+ pr_devel("H_IPOLL(server=%ld)\n", server);
+
+ xc->GLUE(X_STAT_PFX,h_ipoll)++;
+
+ /* Grab the target VCPU if not the current one */
+ if (xc->server_num != server) {
+ vcpu = kvmppc_xive_find_server(vcpu->kvm, server);
+ if (!vcpu)
+ return H_PARAMETER;
+ xc = vcpu->arch.xive_vcpu;
+
+ /* Scan all priorities */
+ pending = 0xff;
+ } else {
+ /* Grab pending interrupt if any */
+ pipr = __x_readb(__x_tima + TM_QW1_OS + TM_PIPR);
+ if (pipr < 8)
+ pending |= 1 << pipr;
+ }
+
+ hirq = GLUE(X_PFX,scan_interrupts)(xc, pending, scan_poll);
+
+ /* Return interrupt and old CPPR in GPR4 */
+ vcpu->arch.gpr[4] = hirq | (xc->cppr << 24);
+
+ return H_SUCCESS;
+}
+
+static void GLUE(X_PFX,push_pending_to_hw)(struct kvmppc_xive_vcpu *xc)
+{
+ u8 pending, prio;
+
+ pending = xc->pending;
+ if (xc->mfrr != 0xff) {
+ if (xc->mfrr < 8)
+ pending |= 1 << xc->mfrr;
+ else
+ pending |= 0x80;
+ }
+ if (!pending)
+ return;
+ prio = ffs(pending) - 1;
+
+ __x_writeb(prio, __x_tima + TM_SPC_SET_OS_PENDING);
+}
+
+X_STATIC int GLUE(X_PFX,h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ u8 old_cppr;
+
+ pr_devel("H_CPPR(cppr=%ld)\n", cppr);
+
+ xc->GLUE(X_STAT_PFX,h_cppr)++;
+
+ /* Map CPPR */
+ cppr = xive_prio_from_guest(cppr);
+
+ /* Remember old and update SW state */
+ old_cppr = xc->cppr;
+ xc->cppr = cppr;
+
+ /*
+ * We are masking less, we need to look for pending things
+ * to deliver and set VP pending bits accordingly to trigger
+ * a new interrupt otherwise we might miss MFRR changes for
+ * which we have optimized out sending an IPI signal.
+ */
+ if (cppr > old_cppr)
+ GLUE(X_PFX,push_pending_to_hw)(xc);
+
+ /* Apply new CPPR */
+ xc->hw_cppr = cppr;
+ __x_writeb(cppr, __x_tima + TM_QW1_OS + TM_CPPR);
+
+ return H_SUCCESS;
+}
+
+X_STATIC int GLUE(X_PFX,h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr)
+{
+ struct kvmppc_xive *xive = vcpu->kvm->arch.xive;
+ struct kvmppc_xive_src_block *sb;
+ struct kvmppc_xive_irq_state *state;
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+ struct xive_irq_data *xd;
+ u8 new_cppr = xirr >> 24;
+ u32 irq = xirr & 0x00ffffff, hw_num;
+ u16 src;
+ int rc = 0;
+
+ pr_devel("H_EOI(xirr=%08lx)\n", xirr);
+
+ xc->GLUE(X_STAT_PFX,h_eoi)++;
+
+ xc->cppr = xive_prio_from_guest(new_cppr);
+
+ /*
+ * IPIs are synthetized from MFRR and thus don't need
+ * any special EOI handling. The underlying interrupt
+ * used to signal MFRR changes is EOId when fetched from
+ * the queue.
+ */
+ if (irq == XICS_IPI || irq == 0)
+ goto bail;
+
+ /* Find interrupt source */
+ sb = kvmppc_xive_find_source(xive, irq, &src);
+ if (!sb) {
+ pr_devel(" source not found !\n");
+ rc = H_PARAMETER;
+ goto bail;
+ }
+ state = &sb->irq_state[src];
+ kvmppc_xive_select_irq(state, &hw_num, &xd);
+
+ state->in_eoi = true;
+ mb();
+
+again:
+ if (state->guest_priority == MASKED) {
+ arch_spin_lock(&sb->lock);
+ if (state->guest_priority != MASKED) {
+ arch_spin_unlock(&sb->lock);
+ goto again;
+ }
+ pr_devel(" EOI on saved P...\n");
+
+ /* Clear old_p, that will cause unmask to perform an EOI */
+ state->old_p = false;
+
+ arch_spin_unlock(&sb->lock);
+ } else {
+ pr_devel(" EOI on source...\n");
+
+ /* Perform EOI on the source */
+ GLUE(X_PFX,source_eoi)(hw_num, xd);
+
+ /* If it's an emulated LSI, check level and resend */
+ if (state->lsi && state->asserted)
+ __x_writeq(0, __x_trig_page(xd));
+
+ }
+
+ mb();
+ state->in_eoi = false;
+bail:
+
+ /* Re-evaluate pending IRQs and update HW */
+ GLUE(X_PFX,scan_interrupts)(xc, xc->pending, scan_eoi);
+ GLUE(X_PFX,push_pending_to_hw)(xc);
+ pr_devel(" after scan pending=%02x\n", xc->pending);
+
+ /* Apply new CPPR */
+ xc->hw_cppr = xc->cppr;
+ __x_writeb(xc->cppr, __x_tima + TM_QW1_OS + TM_CPPR);
+
+ return rc;
+}
+
+X_STATIC int GLUE(X_PFX,h_ipi)(struct kvm_vcpu *vcpu, unsigned long server,
+ unsigned long mfrr)
+{
+ struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+
+ pr_devel("H_IPI(server=%08lx,mfrr=%ld)\n", server, mfrr);
+
+ xc->GLUE(X_STAT_PFX,h_ipi)++;
+
+ /* Find target */
+ vcpu = kvmppc_xive_find_server(vcpu->kvm, server);
+ if (!vcpu)
+ return H_PARAMETER;
+ xc = vcpu->arch.xive_vcpu;
+
+ /* Locklessly write over MFRR */
+ xc->mfrr = mfrr;
+
+ /* Shoot the IPI if most favored than target cppr */
+ if (mfrr < xc->cppr)
+ __x_writeq(0, __x_trig_page(&xc->vp_ipi_data));
+
+ return H_SUCCESS;
+}
diff --git a/arch/powerpc/kvm/irq.h b/arch/powerpc/kvm/irq.h
index 5a9a10b90762..3f1be85a83bc 100644
--- a/arch/powerpc/kvm/irq.h
+++ b/arch/powerpc/kvm/irq.h
@@ -12,6 +12,7 @@ static inline int irqchip_in_kernel(struct kvm *kvm)
#endif
#ifdef CONFIG_KVM_XICS
ret = ret || (kvm->arch.xics != NULL);
+ ret = ret || (kvm->arch.xive != NULL);
#endif
smp_rmb();
return ret;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 1ee22a910074..f7cf2cd564ef 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -38,6 +38,8 @@
#include <asm/irqflags.h>
#include <asm/iommu.h>
#include <asm/switch_to.h>
+#include <asm/xive.h>
+
#include "timing.h"
#include "irq.h"
#include "../mm/mmu_decl.h"
@@ -697,7 +699,10 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
kvmppc_mpic_disconnect_vcpu(vcpu->arch.mpic, vcpu);
break;
case KVMPPC_IRQ_XICS:
- kvmppc_xics_free_icp(vcpu);
+ if (xive_enabled())
+ kvmppc_xive_cleanup_vcpu(vcpu);
+ else
+ kvmppc_xics_free_icp(vcpu);
break;
}
@@ -1522,8 +1527,12 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
r = -EPERM;
dev = kvm_device_from_filp(f.file);
- if (dev)
- r = kvmppc_xics_connect_vcpu(dev, vcpu, cap->args[1]);
+ if (dev) {
+ if (xive_enabled())
+ r = kvmppc_xive_connect_vcpu(dev, vcpu, cap->args[1]);
+ else
+ r = kvmppc_xics_connect_vcpu(dev, vcpu, cap->args[1]);
+ }
fdput(f);
break;
@@ -1547,7 +1556,7 @@ bool kvm_arch_intc_initialized(struct kvm *kvm)
return true;
#endif
#ifdef CONFIG_KVM_XICS
- if (kvm->arch.xics)
+ if (kvm->arch.xics || kvm->arch.xive)
return true;
#endif
return false;
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 7925a9d72cca..59684b4af4d1 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -967,3 +967,4 @@ EXPORT_SYMBOL_GPL(opal_leds_set_ind);
EXPORT_SYMBOL_GPL(opal_write_oppanel_async);
/* Export this for KVM */
EXPORT_SYMBOL_GPL(opal_int_set_mfrr);
+EXPORT_SYMBOL_GPL(opal_int_eoi);
diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c
index 6a98efb14264..913825086b8d 100644
--- a/arch/powerpc/sysdev/xive/common.c
+++ b/arch/powerpc/sysdev/xive/common.c
@@ -46,13 +46,15 @@
#endif
bool __xive_enabled;
+EXPORT_SYMBOL_GPL(__xive_enabled);
bool xive_cmdline_disabled;
/* We use only one priority for now */
static u8 xive_irq_priority;
-/* TIMA */
+/* TIMA exported to KVM */
void __iomem *xive_tima;
+EXPORT_SYMBOL_GPL(xive_tima);
u32 xive_tima_offset;
/* Backend ops */
@@ -345,8 +347,11 @@ static void xive_irq_eoi(struct irq_data *d)
DBG_VERBOSE("eoi_irq: irq=%d [0x%lx] pending=%02x\n",
d->irq, irqd_to_hwirq(d), xc->pending_prio);
- /* EOI the source if it hasn't been disabled */
- if (!irqd_irq_disabled(d))
+ /*
+ * EOI the source if it hasn't been disabled and hasn't
+ * been passed-through to a KVM guest
+ */
+ if (!irqd_irq_disabled(d) && !irqd_is_forwarded_to_vcpu(d))
xive_do_source_eoi(irqd_to_hwirq(d), xd);
/*
@@ -689,9 +694,14 @@ static int xive_irq_set_affinity(struct irq_data *d,
old_target = xd->target;
- rc = xive_ops->configure_irq(hw_irq,
- get_hard_smp_processor_id(target),
- xive_irq_priority, d->irq);
+ /*
+ * Only configure the irq if it's not currently passed-through to
+ * a KVM guest
+ */
+ if (!irqd_is_forwarded_to_vcpu(d))
+ rc = xive_ops->configure_irq(hw_irq,
+ get_hard_smp_processor_id(target),
+ xive_irq_priority, d->irq);
if (rc < 0) {
pr_err("Error %d reconfiguring irq %d\n", rc, d->irq);
return rc;
@@ -771,6 +781,123 @@ static int xive_irq_retrigger(struct irq_data *d)
return 1;
}
+static int xive_irq_set_vcpu_affinity(struct irq_data *d, void *state)
+{
+ struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
+ unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
+ int rc;
+ u8 pq;
+
+ /*
+ * We only support this on interrupts that do not require
+ * firmware calls for masking and unmasking
+ */
+ if (xd->flags & XIVE_IRQ_FLAG_MASK_FW)
+ return -EIO;
+
+ /*
+ * This is called by KVM with state non-NULL for enabling
+ * pass-through or NULL for disabling it
+ */
+ if (state) {
+ irqd_set_forwarded_to_vcpu(d);
+
+ /* Set it to PQ=10 state to prevent further sends */
+ pq = xive_poke_esb(xd, XIVE_ESB_SET_PQ_10);
+
+ /* No target ? nothing to do */
+ if (xd->target == XIVE_INVALID_TARGET) {
+ /*
+ * An untargetted interrupt should have been
+ * also masked at the source
+ */
+ WARN_ON(pq & 2);
+
+ return 0;
+ }
+
+ /*
+ * If P was set, adjust state to PQ=11 to indicate
+ * that a resend is needed for the interrupt to reach
+ * the guest. Also remember the value of P.
+ *
+ * This also tells us that it's in flight to a host queue
+ * or has already been fetched but hasn't been EOIed yet
+ * by the host. This it's potentially using up a host
+ * queue slot. This is important to know because as long
+ * as this is the case, we must not hard-unmask it when
+ * "returning" that interrupt to the host.
+ *
+ * This saved_p is cleared by the host EOI, when we know
+ * for sure the queue slot is no longer in use.
+ */
+ if (pq & 2) {
+ pq = xive_poke_esb(xd, XIVE_ESB_SET_PQ_11);
+ xd->saved_p = true;
+
+ /*
+ * Sync the XIVE source HW to ensure the interrupt
+ * has gone through the EAS before we change its
+ * target to the guest. That should guarantee us
+ * that we *will* eventually get an EOI for it on
+ * the host. Otherwise there would be a small window
+ * for P to be seen here but the interrupt going
+ * to the guest queue.
+ */
+ if (xive_ops->sync_source)
+ xive_ops->sync_source(hw_irq);
+ } else
+ xd->saved_p = false;
+ } else {
+ irqd_clr_forwarded_to_vcpu(d);
+
+ /* No host target ? hard mask and return */
+ if (xd->target == XIVE_INVALID_TARGET) {
+ xive_do_source_set_mask(xd, true);
+ return 0;
+ }
+
+ /*
+ * Sync the XIVE source HW to ensure the interrupt
+ * has gone through the EAS before we change its
+ * target to the host.
+ */
+ if (xive_ops->sync_source)
+ xive_ops->sync_source(hw_irq);
+
+ /*
+ * By convention we are called with the interrupt in
+ * a PQ=10 or PQ=11 state, ie, it won't fire and will
+ * have latched in Q whether there's a pending HW
+ * interrupt or not.
+ *
+ * First reconfigure the target.
+ */
+ rc = xive_ops->configure_irq(hw_irq,
+ get_hard_smp_processor_id(xd->target),
+ xive_irq_priority, d->irq);
+ if (rc)
+ return rc;
+
+ /*
+ * Then if saved_p is not set, effectively re-enable the
+ * interrupt with an EOI. If it is set, we know there is
+ * still a message in a host queue somewhere that will be
+ * EOId eventually.
+ *
+ * Note: We don't check irqd_irq_disabled(). Effectively,
+ * we *will* let the irq get through even if masked if the
+ * HW is still firing it in order to deal with the whole
+ * saved_p business properly. If the interrupt triggers
+ * while masked, the generic code will re-mask it anyway.
+ */
+ if (!xd->saved_p)
+ xive_do_source_eoi(hw_irq, xd);
+
+ }
+ return 0;
+}
+
static struct irq_chip xive_irq_chip = {
.name = "XIVE-IRQ",
.irq_startup = xive_irq_startup,
@@ -781,12 +908,14 @@ static struct irq_chip xive_irq_chip = {
.irq_set_affinity = xive_irq_set_affinity,
.irq_set_type = xive_irq_set_type,
.irq_retrigger = xive_irq_retrigger,
+ .irq_set_vcpu_affinity = xive_irq_set_vcpu_affinity,
};
bool is_xive_irq(struct irq_chip *chip)
{
return chip == &xive_irq_chip;
}
+EXPORT_SYMBOL_GPL(is_xive_irq);
void xive_cleanup_irq_data(struct xive_irq_data *xd)
{
@@ -801,6 +930,7 @@ void xive_cleanup_irq_data(struct xive_irq_data *xd)
xd->trig_mmio = NULL;
}
}
+EXPORT_SYMBOL_GPL(xive_cleanup_irq_data);
static int xive_irq_alloc_data(unsigned int virq, irq_hw_number_t hw)
{
diff --git a/arch/powerpc/sysdev/xive/native.c b/arch/powerpc/sysdev/xive/native.c
index 1a726229a427..ab9ecce61ee5 100644
--- a/arch/powerpc/sysdev/xive/native.c
+++ b/arch/powerpc/sysdev/xive/native.c
@@ -31,6 +31,7 @@
#include <asm/xive.h>
#include <asm/xive-regs.h>
#include <asm/opal.h>
+#include <asm/kvm_ppc.h>
#include "xive-internal.h"
@@ -95,6 +96,7 @@ int xive_native_populate_irq_data(u32 hw_irq, struct xive_irq_data *data)
}
return 0;
}
+EXPORT_SYMBOL_GPL(xive_native_populate_irq_data);
int xive_native_configure_irq(u32 hw_irq, u32 target, u8 prio, u32 sw_irq)
{
@@ -108,6 +110,8 @@ int xive_native_configure_irq(u32 hw_irq, u32 target, u8 prio, u32 sw_irq)
}
return rc == 0 ? 0 : -ENXIO;
}
+EXPORT_SYMBOL_GPL(xive_native_configure_irq);
+
/* This can be called multiple time to change a queue configuration */
int xive_native_configure_queue(u32 vp_id, struct xive_q *q, u8 prio,
@@ -172,6 +176,7 @@ int xive_native_configure_queue(u32 vp_id, struct xive_q *q, u8 prio,
fail:
return rc;
}
+EXPORT_SYMBOL_GPL(xive_native_configure_queue);
static void __xive_native_disable_queue(u32 vp_id, struct xive_q *q, u8 prio)
{
@@ -192,6 +197,7 @@ void xive_native_disable_queue(u32 vp_id, struct xive_q *q, u8 prio)
{
__xive_native_disable_queue(vp_id, q, prio);
}
+EXPORT_SYMBOL_GPL(xive_native_disable_queue);
static int xive_native_setup_queue(unsigned int cpu, struct xive_cpu *xc, u8 prio)
{
@@ -262,6 +268,7 @@ static int xive_native_get_ipi(unsigned int cpu, struct xive_cpu *xc)
}
return 0;
}
+#endif /* CONFIG_SMP */
u32 xive_native_alloc_irq(void)
{
@@ -277,6 +284,7 @@ u32 xive_native_alloc_irq(void)
return 0;
return rc;
}
+EXPORT_SYMBOL_GPL(xive_native_alloc_irq);
void xive_native_free_irq(u32 irq)
{
@@ -287,7 +295,9 @@ void xive_native_free_irq(u32 irq)
msleep(1);
}
}
+EXPORT_SYMBOL_GPL(xive_native_free_irq);
+#ifdef CONFIG_SMP
static void xive_native_put_ipi(unsigned int cpu, struct xive_cpu *xc)
{
s64 rc;
@@ -383,7 +393,7 @@ static void xive_native_setup_cpu(unsigned int cpu, struct xive_cpu *xc)
return;
/* Enable the pool VP */
- vp = xive_pool_vps + get_hard_smp_processor_id(cpu);
+ vp = xive_pool_vps + cpu;
pr_debug("CPU %d setting up pool VP 0x%x\n", cpu, vp);
for (;;) {
rc = opal_xive_set_vp_info(vp, OPAL_XIVE_VP_ENABLED, 0);
@@ -428,7 +438,7 @@ static void xive_native_teardown_cpu(unsigned int cpu, struct xive_cpu *xc)
in_be64(xive_tima + TM_SPC_PULL_POOL_CTX);
/* Disable it */
- vp = xive_pool_vps + get_hard_smp_processor_id(cpu);
+ vp = xive_pool_vps + cpu;
for (;;) {
rc = opal_xive_set_vp_info(vp, 0, 0);
if (rc != OPAL_BUSY)
@@ -437,10 +447,11 @@ static void xive_native_teardown_cpu(unsigned int cpu, struct xive_cpu *xc)
}
}
-static void xive_native_sync_source(u32 hw_irq)
+void xive_native_sync_source(u32 hw_irq)
{
opal_xive_sync(XIVE_SYNC_EAS, hw_irq);
}
+EXPORT_SYMBOL_GPL(xive_native_sync_source);
static const struct xive_ops xive_native_ops = {
.populate_irq_data = xive_native_populate_irq_data,
@@ -501,10 +512,24 @@ static bool xive_parse_provisioning(struct device_node *np)
return true;
}
+static void xive_native_setup_pools(void)
+{
+ /* Allocate a pool big enough */
+ pr_debug("XIVE: Allocating VP block for pool size %d\n", nr_cpu_ids);
+
+ xive_pool_vps = xive_native_alloc_vp_block(nr_cpu_ids);
+ if (WARN_ON(xive_pool_vps == XIVE_INVALID_VP))
+ pr_err("XIVE: Failed to allocate pool VP, KVM might not function\n");
+
+ pr_debug("XIVE: Pool VPs allocated at 0x%x for %d max CPUs\n",
+ xive_pool_vps, nr_cpu_ids);
+}
+
u32 xive_native_default_eq_shift(void)
{
return xive_queue_shift;
}
+EXPORT_SYMBOL_GPL(xive_native_default_eq_shift);
bool xive_native_init(void)
{
@@ -514,7 +539,7 @@ bool xive_native_init(void)
struct property *prop;
u8 max_prio = 7;
const __be32 *p;
- u32 val;
+ u32 val, cpu;
s64 rc;
if (xive_cmdline_disabled)
@@ -550,7 +575,11 @@ bool xive_native_init(void)
break;
}
- /* Grab size of provisioning pages */
+ /* Configure Thread Management areas for KVM */
+ for_each_possible_cpu(cpu)
+ kvmppc_set_xive_tima(cpu, r.start, tima);
+
+ /* Grab size of provisionning pages */
xive_parse_provisioning(np);
/* Switch the XIVE to exploitation mode */
@@ -560,6 +589,9 @@ bool xive_native_init(void)
return false;
}
+ /* Setup some dummy HV pool VPs */
+ xive_native_setup_pools();
+
/* Initialize XIVE core with our backend */
if (!xive_core_init(&xive_native_ops, tima, TM_QW3_HV_PHYS,
max_prio)) {
@@ -638,3 +670,47 @@ void xive_native_free_vp_block(u32 vp_base)
pr_warn("OPAL error %lld freeing VP block\n", rc);
}
EXPORT_SYMBOL_GPL(xive_native_free_vp_block);
+
+int xive_native_enable_vp(u32 vp_id)
+{
+ s64 rc;
+
+ for (;;) {
+ rc = opal_xive_set_vp_info(vp_id, OPAL_XIVE_VP_ENABLED, 0);
+ if (rc != OPAL_BUSY)
+ break;
+ msleep(1);
+ }
+ return rc ? -EIO : 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_enable_vp);
+
+int xive_native_disable_vp(u32 vp_id)
+{
+ s64 rc;
+
+ for (;;) {
+ rc = opal_xive_set_vp_info(vp_id, 0, 0);
+ if (rc != OPAL_BUSY)
+ break;
+ msleep(1);
+ }
+ return rc ? -EIO : 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_disable_vp);
+
+int xive_native_get_vp_info(u32 vp_id, u32 *out_cam_id, u32 *out_chip_id)
+{
+ __be64 vp_cam_be;
+ __be32 vp_chip_id_be;
+ s64 rc;
+
+ rc = opal_xive_get_vp_info(vp_id, NULL, &vp_cam_be, NULL, &vp_chip_id_be);
+ if (rc)
+ return -EIO;
+ *out_cam_id = be64_to_cpu(vp_cam_be) & 0xffffffffu;
+ *out_chip_id = be32_to_cpu(vp_chip_id_be);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(xive_native_get_vp_info);
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f5bddf92faba..9c761fea0c98 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1020,6 +1020,8 @@ struct kvm_x86_ops {
void (*enable_log_dirty_pt_masked)(struct kvm *kvm,
struct kvm_memory_slot *slot,
gfn_t offset, unsigned long mask);
+ int (*write_log_dirty)(struct kvm_vcpu *vcpu);
+
/* pmu operations of sub-arch */
const struct kvm_pmu_ops *pmu_ops;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 558676538fca..5d3376f67794 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1498,6 +1498,21 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
}
+/**
+ * kvm_arch_write_log_dirty - emulate dirty page logging
+ * @vcpu: Guest mode vcpu
+ *
+ * Emulate arch specific page modification logging for the
+ * nested hypervisor
+ */
+int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu)
+{
+ if (kvm_x86_ops->write_log_dirty)
+ return kvm_x86_ops->write_log_dirty(vcpu);
+
+ return 0;
+}
+
bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
struct kvm_memory_slot *slot, u64 gfn)
{
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index d8ccb32f7308..27975807cc64 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -202,4 +202,5 @@ void kvm_mmu_gfn_disallow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
void kvm_mmu_gfn_allow_lpage(struct kvm_memory_slot *slot, gfn_t gfn);
bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
struct kvm_memory_slot *slot, u64 gfn);
+int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu);
#endif
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 314d2071b337..56241746abbd 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -226,6 +226,10 @@ static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
if (level == walker->level && write_fault &&
!(pte & PT_GUEST_DIRTY_MASK)) {
trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
+#if PTTYPE == PTTYPE_EPT
+ if (kvm_arch_write_log_dirty(vcpu))
+ return -EINVAL;
+#endif
pte |= PT_GUEST_DIRTY_MASK;
}
if (pte == orig_pte)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c5fd459c4043..c6f4ad44aa95 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -248,6 +248,7 @@ struct __packed vmcs12 {
u64 xss_exit_bitmap;
u64 guest_physical_address;
u64 vmcs_link_pointer;
+ u64 pml_address;
u64 guest_ia32_debugctl;
u64 guest_ia32_pat;
u64 guest_ia32_efer;
@@ -369,6 +370,7 @@ struct __packed vmcs12 {
u16 guest_ldtr_selector;
u16 guest_tr_selector;
u16 guest_intr_status;
+ u16 guest_pml_index;
u16 host_es_selector;
u16 host_cs_selector;
u16 host_ss_selector;
@@ -407,6 +409,7 @@ struct nested_vmx {
/* Has the level1 guest done vmxon? */
bool vmxon;
gpa_t vmxon_ptr;
+ bool pml_full;
/* The guest-physical address of the current VMCS L1 keeps for L2 */
gpa_t current_vmptr;
@@ -742,6 +745,7 @@ static const unsigned short vmcs_field_to_offset_table[] = {
FIELD(GUEST_LDTR_SELECTOR, guest_ldtr_selector),
FIELD(GUEST_TR_SELECTOR, guest_tr_selector),
FIELD(GUEST_INTR_STATUS, guest_intr_status),
+ FIELD(GUEST_PML_INDEX, guest_pml_index),
FIELD(HOST_ES_SELECTOR, host_es_selector),
FIELD(HOST_CS_SELECTOR, host_cs_selector),
FIELD(HOST_SS_SELECTOR, host_ss_selector),
@@ -767,6 +771,7 @@ static const unsigned short vmcs_field_to_offset_table[] = {
FIELD64(XSS_EXIT_BITMAP, xss_exit_bitmap),
FIELD64(GUEST_PHYSICAL_ADDRESS, guest_physical_address),
FIELD64(VMCS_LINK_POINTER, vmcs_link_pointer),
+ FIELD64(PML_ADDRESS, pml_address),
FIELD64(GUEST_IA32_DEBUGCTL, guest_ia32_debugctl),
FIELD64(GUEST_IA32_PAT, guest_ia32_pat),
FIELD64(GUEST_IA32_EFER, guest_ia32_efer),
@@ -1314,6 +1319,11 @@ static inline bool report_flexpriority(void)
return flexpriority_enabled;
}
+static inline unsigned nested_cpu_vmx_misc_cr3_count(struct kvm_vcpu *vcpu)
+{
+ return vmx_misc_cr3_count(to_vmx(vcpu)->nested.nested_vmx_misc_low);
+}
+
static inline bool nested_cpu_has(struct vmcs12 *vmcs12, u32 bit)
{
return vmcs12->cpu_based_vm_exec_control & bit;
@@ -1348,6 +1358,11 @@ static inline bool nested_cpu_has_xsaves(struct vmcs12 *vmcs12)
vmx_xsaves_supported();
}
+static inline bool nested_cpu_has_pml(struct vmcs12 *vmcs12)
+{
+ return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_PML);
+}
+
static inline bool nested_cpu_has_virt_x2apic_mode(struct vmcs12 *vmcs12)
{
return nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE);
@@ -2751,8 +2766,11 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
vmx->nested.nested_vmx_ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT |
VMX_EPT_EXTENT_CONTEXT_BIT | VMX_EPT_2MB_PAGE_BIT |
VMX_EPT_1GB_PAGE_BIT;
- if (enable_ept_ad_bits)
+ if (enable_ept_ad_bits) {
+ vmx->nested.nested_vmx_secondary_ctls_high |=
+ SECONDARY_EXEC_ENABLE_PML;
vmx->nested.nested_vmx_ept_caps |= VMX_EPT_AD_BIT;
+ }
} else
vmx->nested.nested_vmx_ept_caps = 0;
@@ -8114,7 +8132,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
case EXIT_REASON_PREEMPTION_TIMER:
return false;
case EXIT_REASON_PML_FULL:
- /* We don't expose PML support to L1. */
+ /* We emulate PML support to L1. */
return false;
default:
return true;
@@ -9364,13 +9382,20 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu,
struct x86_exception *fault)
{
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 exit_reason;
+ unsigned long exit_qualification = vcpu->arch.exit_qualification;
- if (fault->error_code & PFERR_RSVD_MASK)
+ if (vmx->nested.pml_full) {
+ exit_reason = EXIT_REASON_PML_FULL;
+ vmx->nested.pml_full = false;
+ exit_qualification &= INTR_INFO_UNBLOCK_NMI;
+ } else if (fault->error_code & PFERR_RSVD_MASK)
exit_reason = EXIT_REASON_EPT_MISCONFIG;
else
exit_reason = EXIT_REASON_EPT_VIOLATION;
- nested_vmx_vmexit(vcpu, exit_reason, 0, vcpu->arch.exit_qualification);
+
+ nested_vmx_vmexit(vcpu, exit_reason, 0, exit_qualification);
vmcs12->guest_physical_address = fault->address;
}
@@ -9713,6 +9738,22 @@ static int nested_vmx_check_msr_switch_controls(struct kvm_vcpu *vcpu,
return 0;
}
+static int nested_vmx_check_pml_controls(struct kvm_vcpu *vcpu,
+ struct vmcs12 *vmcs12)
+{
+ u64 address = vmcs12->pml_address;
+ int maxphyaddr = cpuid_maxphyaddr(vcpu);
+
+ if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_PML)) {
+ if (!nested_cpu_has_ept(vmcs12) ||
+ !IS_ALIGNED(address, 4096) ||
+ address >> maxphyaddr)
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
static int nested_vmx_msr_check_common(struct kvm_vcpu *vcpu,
struct vmx_msr_entry *e)
{
@@ -9886,7 +9927,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
bool from_vmentry, u32 *entry_failure_code)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- u32 exec_control;
+ u32 exec_control, vmcs12_exec_ctrl;
vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
@@ -10017,8 +10058,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
SECONDARY_EXEC_APIC_REGISTER_VIRT);
if (nested_cpu_has(vmcs12,
- CPU_BASED_ACTIVATE_SECONDARY_CONTROLS))
- exec_control |= vmcs12->secondary_vm_exec_control;
+ CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) {
+ vmcs12_exec_ctrl = vmcs12->secondary_vm_exec_control &
+ ~SECONDARY_EXEC_ENABLE_PML;
+ exec_control |= vmcs12_exec_ctrl;
+ }
if (exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) {
vmcs_write64(EOI_EXIT_BITMAP0,
@@ -10248,6 +10292,9 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
if (nested_vmx_check_msr_switch_controls(vcpu, vmcs12))
return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+ if (nested_vmx_check_pml_controls(vcpu, vmcs12))
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
if (!vmx_control_verify(vmcs12->cpu_based_vm_exec_control,
vmx->nested.nested_vmx_procbased_ctls_low,
vmx->nested.nested_vmx_procbased_ctls_high) ||
@@ -10266,6 +10313,9 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
vmx->nested.nested_vmx_entry_ctls_high))
return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+ if (vmcs12->cr3_target_count > nested_cpu_vmx_misc_cr3_count(vcpu))
+ return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
if (!nested_host_cr0_valid(vcpu, vmcs12->host_cr0) ||
!nested_host_cr4_valid(vcpu, vmcs12->host_cr4) ||
!nested_cr3_valid(vcpu, vmcs12->host_cr3))
@@ -11143,6 +11193,46 @@ static void vmx_flush_log_dirty(struct kvm *kvm)
kvm_flush_pml_buffers(kvm);
}
+static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu)
+{
+ struct vmcs12 *vmcs12;
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ gpa_t gpa;
+ struct page *page = NULL;
+ u64 *pml_address;
+
+ if (is_guest_mode(vcpu)) {
+ WARN_ON_ONCE(vmx->nested.pml_full);
+
+ /*
+ * Check if PML is enabled for the nested guest.
+ * Whether eptp bit 6 is set is already checked
+ * as part of A/D emulation.
+ */
+ vmcs12 = get_vmcs12(vcpu);
+ if (!nested_cpu_has_pml(vmcs12))
+ return 0;
+
+ if (vmcs12->guest_pml_index > PML_ENTITY_NUM) {
+ vmx->nested.pml_full = true;
+ return 1;
+ }
+
+ gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS) & ~0xFFFull;
+
+ page = nested_get_page(vcpu, vmcs12->pml_address);
+ if (!page)
+ return 0;
+
+ pml_address = kmap(page);
+ pml_address[vmcs12->guest_pml_index--] = gpa;
+ kunmap(page);
+ nested_release_page_clean(page);
+ }
+
+ return 0;
+}
+
static void vmx_enable_log_dirty_pt_masked(struct kvm *kvm,
struct kvm_memory_slot *memslot,
gfn_t offset, unsigned long mask)
@@ -11502,6 +11592,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
.slot_disable_log_dirty = vmx_slot_disable_log_dirty,
.flush_log_dirty = vmx_flush_log_dirty,
.enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked,
+ .write_log_dirty = vmx_write_pml_buffer,
.pre_block = vmx_pre_block,
.post_block = vmx_post_block,
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 581a59ea7e34..97b8d3728b31 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -148,7 +148,6 @@ struct vgic_its {
gpa_t vgic_its_base;
bool enabled;
- bool initialized;
struct vgic_io_device iodev;
struct kvm_device *dev;
@@ -162,6 +161,9 @@ struct vgic_its {
u32 creadr;
u32 cwriter;
+ /* migration ABI revision in use */
+ u32 abi_rev;
+
/* Protects the device and collection lists */
struct mutex its_lock;
struct list_head device_list;
@@ -283,6 +285,7 @@ extern struct static_key_false vgic_v2_cpuif_trap;
int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write);
void kvm_vgic_early_init(struct kvm *kvm);
+int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu);
int kvm_vgic_create(struct kvm *kvm, u32 type);
void kvm_vgic_destroy(struct kvm *kvm);
void kvm_vgic_vcpu_early_init(struct kvm_vcpu *vcpu);
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 97cbca19430d..fffb91202bc9 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -132,6 +132,9 @@
#define GIC_BASER_SHAREABILITY(reg, type) \
(GIC_BASER_##type << reg##_SHAREABILITY_SHIFT)
+/* encode a size field of width @w containing @n - 1 units */
+#define GIC_ENCODE_SZ(n, w) (((unsigned long)(n) - 1) & GENMASK_ULL(((w) - 1), 0))
+
#define GICR_PROPBASER_SHAREABILITY_SHIFT (10)
#define GICR_PROPBASER_INNER_CACHEABILITY_SHIFT (7)
#define GICR_PROPBASER_OUTER_CACHEABILITY_SHIFT (56)
@@ -156,6 +159,8 @@
#define GICR_PROPBASER_RaWaWb GIC_BASER_CACHEABILITY(GICR_PROPBASER, INNER, RaWaWb)
#define GICR_PROPBASER_IDBITS_MASK (0x1f)
+#define GICR_PROPBASER_ADDRESS(x) ((x) & GENMASK_ULL(51, 12))
+#define GICR_PENDBASER_ADDRESS(x) ((x) & GENMASK_ULL(51, 16))
#define GICR_PENDBASER_SHAREABILITY_SHIFT (10)
#define GICR_PENDBASER_INNER_CACHEABILITY_SHIFT (7)
@@ -232,12 +237,18 @@
#define GITS_CTLR_QUIESCENT (1U << 31)
#define GITS_TYPER_PLPIS (1UL << 0)
+#define GITS_TYPER_ITT_ENTRY_SIZE_SHIFT 4
#define GITS_TYPER_IDBITS_SHIFT 8
#define GITS_TYPER_DEVBITS_SHIFT 13
#define GITS_TYPER_DEVBITS(r) ((((r) >> GITS_TYPER_DEVBITS_SHIFT) & 0x1f) + 1)
#define GITS_TYPER_PTA (1UL << 19)
#define GITS_TYPER_HWCOLLCNT_SHIFT 24
+#define GITS_IIDR_REV_SHIFT 12
+#define GITS_IIDR_REV_MASK (0xf << GITS_IIDR_REV_SHIFT)
+#define GITS_IIDR_REV(r) (((r) >> GITS_IIDR_REV_SHIFT) & 0xf)
+#define GITS_IIDR_PRODUCTID_SHIFT 24
+
#define GITS_CBASER_VALID (1ULL << 63)
#define GITS_CBASER_SHAREABILITY_SHIFT (10)
#define GITS_CBASER_INNER_CACHEABILITY_SHIFT (59)
@@ -290,6 +301,7 @@
#define GITS_BASER_TYPE(r) (((r) >> GITS_BASER_TYPE_SHIFT) & 7)
#define GITS_BASER_ENTRY_SIZE_SHIFT (48)
#define GITS_BASER_ENTRY_SIZE(r) ((((r) >> GITS_BASER_ENTRY_SIZE_SHIFT) & 0x1f) + 1)
+#define GITS_BASER_ENTRY_SIZE_MASK GENMASK_ULL(52, 48)
#define GITS_BASER_SHAREABILITY_SHIFT (10)
#define GITS_BASER_InnerShareable \
GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable)
@@ -337,9 +349,11 @@
#define E_ITS_INT_UNMAPPED_INTERRUPT 0x010307
#define E_ITS_CLEAR_UNMAPPED_INTERRUPT 0x010507
#define E_ITS_MAPD_DEVICE_OOR 0x010801
+#define E_ITS_MAPD_ITTSIZE_OOR 0x010802
#define E_ITS_MAPC_PROCNUM_OOR 0x010902
#define E_ITS_MAPC_COLLECTION_OOR 0x010903
#define E_ITS_MAPTI_UNMAPPED_DEVICE 0x010a04
+#define E_ITS_MAPTI_ID_OOR 0x010a05
#define E_ITS_MAPTI_PHYSICALID_OOR 0x010a06
#define E_ITS_INV_UNMAPPED_INTERRUPT 0x010c07
#define E_ITS_INVALL_UNMAPPED_COLLECTION 0x010d09
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 2b12b2683359..8c0664309815 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -499,6 +499,17 @@ static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id)
return NULL;
}
+static inline int kvm_vcpu_get_idx(struct kvm_vcpu *vcpu)
+{
+ struct kvm_vcpu *tmp;
+ int idx;
+
+ kvm_for_each_vcpu(idx, tmp, vcpu->kvm)
+ if (tmp == vcpu)
+ return idx;
+ BUG();
+}
+
#define kvm_for_each_memslot(memslot, slots) \
for (memslot = &slots->memslots[0]; \
memslot < slots->memslots + KVM_MEM_SLOTS_NUM && memslot->npages;\
@@ -1167,7 +1178,6 @@ int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type);
void kvm_unregister_device_ops(u32 type);
extern struct kvm_device_ops kvm_mpic_ops;
-extern struct kvm_device_ops kvm_xics_ops;
extern struct kvm_device_ops kvm_arm_vgic_v2_ops;
extern struct kvm_device_ops kvm_arm_vgic_v3_ops;
diff --git a/arch/arm/kvm/arm.c b/virt/kvm/arm/arm.c
index 8a31906bdc9b..3417e184c8e1 100644
--- a/arch/arm/kvm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -332,7 +332,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
kvm_arm_reset_debug_ptr(vcpu);
- return 0;
+ return kvm_vgic_vcpu_init(vcpu);
}
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
diff --git a/arch/arm/kvm/mmio.c b/virt/kvm/arm/mmio.c
index b6e715fd3c90..b6e715fd3c90 100644
--- a/arch/arm/kvm/mmio.c
+++ b/virt/kvm/arm/mmio.c
diff --git a/arch/arm/kvm/mmu.c b/virt/kvm/arm/mmu.c
index 313ee646480f..313ee646480f 100644
--- a/arch/arm/kvm/mmu.c
+++ b/virt/kvm/arm/mmu.c
diff --git a/arch/arm/kvm/perf.c b/virt/kvm/arm/perf.c
index 1a3849da0b4b..1a3849da0b4b 100644
--- a/arch/arm/kvm/perf.c
+++ b/virt/kvm/arm/perf.c
diff --git a/arch/arm/kvm/psci.c b/virt/kvm/arm/psci.c
index a08d7a93aebb..a08d7a93aebb 100644
--- a/arch/arm/kvm/psci.c
+++ b/virt/kvm/arm/psci.c
diff --git a/virt/kvm/arm/trace.h b/virt/kvm/arm/trace.h
index 37d8b98867d5..f7dc5ddd6847 100644
--- a/virt/kvm/arm/trace.h
+++ b/virt/kvm/arm/trace.h
@@ -7,26 +7,250 @@
#define TRACE_SYSTEM kvm
/*
- * Tracepoints for vgic
+ * Tracepoints for entry/exit to guest
*/
-TRACE_EVENT(vgic_update_irq_pending,
- TP_PROTO(unsigned long vcpu_id, __u32 irq, bool level),
- TP_ARGS(vcpu_id, irq, level),
+TRACE_EVENT(kvm_entry,
+ TP_PROTO(unsigned long vcpu_pc),
+ TP_ARGS(vcpu_pc),
TP_STRUCT__entry(
- __field( unsigned long, vcpu_id )
- __field( __u32, irq )
- __field( bool, level )
+ __field( unsigned long, vcpu_pc )
),
TP_fast_assign(
- __entry->vcpu_id = vcpu_id;
- __entry->irq = irq;
+ __entry->vcpu_pc = vcpu_pc;
+ ),
+
+ TP_printk("PC: 0x%08lx", __entry->vcpu_pc)
+);
+
+TRACE_EVENT(kvm_exit,
+ 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("%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)
+);
+
+TRACE_EVENT(kvm_guest_fault,
+ TP_PROTO(unsigned long vcpu_pc, unsigned long hsr,
+ unsigned long hxfar,
+ unsigned long long ipa),
+ TP_ARGS(vcpu_pc, hsr, hxfar, ipa),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, vcpu_pc )
+ __field( unsigned long, hsr )
+ __field( unsigned long, hxfar )
+ __field( unsigned long long, ipa )
+ ),
+
+ TP_fast_assign(
+ __entry->vcpu_pc = vcpu_pc;
+ __entry->hsr = hsr;
+ __entry->hxfar = hxfar;
+ __entry->ipa = ipa;
+ ),
+
+ TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#08lx",
+ __entry->ipa, __entry->hsr,
+ __entry->hxfar, __entry->vcpu_pc)
+);
+
+TRACE_EVENT(kvm_access_fault,
+ TP_PROTO(unsigned long ipa),
+ TP_ARGS(ipa),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, ipa )
+ ),
+
+ TP_fast_assign(
+ __entry->ipa = ipa;
+ ),
+
+ TP_printk("IPA: %lx", __entry->ipa)
+);
+
+TRACE_EVENT(kvm_irq_line,
+ TP_PROTO(unsigned int type, int vcpu_idx, int irq_num, int level),
+ TP_ARGS(type, vcpu_idx, irq_num, level),
+
+ TP_STRUCT__entry(
+ __field( unsigned int, type )
+ __field( int, vcpu_idx )
+ __field( int, irq_num )
+ __field( int, level )
+ ),
+
+ TP_fast_assign(
+ __entry->type = type;
+ __entry->vcpu_idx = vcpu_idx;
+ __entry->irq_num = irq_num;
__entry->level = level;
),
- TP_printk("VCPU: %ld, IRQ %d, level: %d",
- __entry->vcpu_id, __entry->irq, __entry->level)
+ TP_printk("Inject %s interrupt (%d), vcpu->idx: %d, num: %d, level: %d",
+ (__entry->type == KVM_ARM_IRQ_TYPE_CPU) ? "CPU" :
+ (__entry->type == KVM_ARM_IRQ_TYPE_PPI) ? "VGIC PPI" :
+ (__entry->type == KVM_ARM_IRQ_TYPE_SPI) ? "VGIC SPI" : "UNKNOWN",
+ __entry->type, __entry->vcpu_idx, __entry->irq_num, __entry->level)
+);
+
+TRACE_EVENT(kvm_mmio_emulate,
+ TP_PROTO(unsigned long vcpu_pc, unsigned long instr,
+ unsigned long cpsr),
+ TP_ARGS(vcpu_pc, instr, cpsr),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, vcpu_pc )
+ __field( unsigned long, instr )
+ __field( unsigned long, cpsr )
+ ),
+
+ TP_fast_assign(
+ __entry->vcpu_pc = vcpu_pc;
+ __entry->instr = instr;
+ __entry->cpsr = cpsr;
+ ),
+
+ TP_printk("Emulate MMIO at: 0x%08lx (instr: %08lx, cpsr: %08lx)",
+ __entry->vcpu_pc, __entry->instr, __entry->cpsr)
+);
+
+TRACE_EVENT(kvm_unmap_hva,
+ TP_PROTO(unsigned long hva),
+ TP_ARGS(hva),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, hva )
+ ),
+
+ TP_fast_assign(
+ __entry->hva = hva;
+ ),
+
+ TP_printk("mmu notifier unmap hva: %#08lx", __entry->hva)
+);
+
+TRACE_EVENT(kvm_unmap_hva_range,
+ TP_PROTO(unsigned long start, unsigned long end),
+ TP_ARGS(start, end),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, start )
+ __field( unsigned long, end )
+ ),
+
+ TP_fast_assign(
+ __entry->start = start;
+ __entry->end = end;
+ ),
+
+ TP_printk("mmu notifier unmap range: %#08lx -- %#08lx",
+ __entry->start, __entry->end)
+);
+
+TRACE_EVENT(kvm_set_spte_hva,
+ TP_PROTO(unsigned long hva),
+ TP_ARGS(hva),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, hva )
+ ),
+
+ TP_fast_assign(
+ __entry->hva = hva;
+ ),
+
+ TP_printk("mmu notifier set pte hva: %#08lx", __entry->hva)
+);
+
+TRACE_EVENT(kvm_age_hva,
+ TP_PROTO(unsigned long start, unsigned long end),
+ TP_ARGS(start, end),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, start )
+ __field( unsigned long, end )
+ ),
+
+ TP_fast_assign(
+ __entry->start = start;
+ __entry->end = end;
+ ),
+
+ TP_printk("mmu notifier age hva: %#08lx -- %#08lx",
+ __entry->start, __entry->end)
+);
+
+TRACE_EVENT(kvm_test_age_hva,
+ TP_PROTO(unsigned long hva),
+ TP_ARGS(hva),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, hva )
+ ),
+
+ TP_fast_assign(
+ __entry->hva = hva;
+ ),
+
+ TP_printk("mmu notifier test age hva: %#08lx", __entry->hva)
+);
+
+TRACE_EVENT(kvm_set_way_flush,
+ TP_PROTO(unsigned long vcpu_pc, bool cache),
+ TP_ARGS(vcpu_pc, cache),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, vcpu_pc )
+ __field( bool, cache )
+ ),
+
+ TP_fast_assign(
+ __entry->vcpu_pc = vcpu_pc;
+ __entry->cache = cache;
+ ),
+
+ TP_printk("S/W flush at 0x%016lx (cache %s)",
+ __entry->vcpu_pc, __entry->cache ? "on" : "off")
+);
+
+TRACE_EVENT(kvm_toggle_cache,
+ TP_PROTO(unsigned long vcpu_pc, bool was, bool now),
+ TP_ARGS(vcpu_pc, was, now),
+
+ TP_STRUCT__entry(
+ __field( unsigned long, vcpu_pc )
+ __field( bool, was )
+ __field( bool, now )
+ ),
+
+ TP_fast_assign(
+ __entry->vcpu_pc = vcpu_pc;
+ __entry->was = was;
+ __entry->now = now;
+ ),
+
+ TP_printk("VM op at 0x%016lx (cache was %s, now %s)",
+ __entry->vcpu_pc, __entry->was ? "on" : "off",
+ __entry->now ? "on" : "off")
);
/*
diff --git a/virt/kvm/arm/vgic/trace.h b/virt/kvm/arm/vgic/trace.h
new file mode 100644
index 000000000000..ed3229282888
--- /dev/null
+++ b/virt/kvm/arm/vgic/trace.h
@@ -0,0 +1,37 @@
+#if !defined(_TRACE_VGIC_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_VGIC_H
+
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kvm
+
+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)
+);
+
+#endif /* _TRACE_VGIC_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH ../../../virt/kvm/arm/vgic
+#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/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c
index 25fd1b942c11..dc68e2e424ab 100644
--- a/virt/kvm/arm/vgic/vgic-init.c
+++ b/virt/kvm/arm/vgic/vgic-init.c
@@ -227,10 +227,27 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis)
}
/**
- * kvm_vgic_vcpu_init() - Enable the VCPU interface
- * @vcpu: the VCPU which's VGIC should be enabled
+ * kvm_vgic_vcpu_init() - Register VCPU-specific KVM iodevs
+ * @vcpu: pointer to the VCPU being created and initialized
*/
-static void kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
+int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
+{
+ int ret = 0;
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
+
+ if (!irqchip_in_kernel(vcpu->kvm))
+ return 0;
+
+ /*
+ * If we are creating a VCPU with a GICv3 we must also register the
+ * KVM io device for the redistributor that belongs to this VCPU.
+ */
+ if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3)
+ ret = vgic_register_redist_iodev(vcpu);
+ return ret;
+}
+
+static void kvm_vgic_vcpu_enable(struct kvm_vcpu *vcpu)
{
if (kvm_vgic_global_state.type == VGIC_V2)
vgic_v2_enable(vcpu);
@@ -269,7 +286,7 @@ int vgic_init(struct kvm *kvm)
dist->msis_require_devid = true;
kvm_for_each_vcpu(i, vcpu, kvm)
- kvm_vgic_vcpu_init(vcpu);
+ kvm_vgic_vcpu_enable(vcpu);
ret = kvm_vgic_setup_default_irq_routing(kvm);
if (ret)
diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c
index 8d1da1af4b09..2dff288b3a66 100644
--- a/virt/kvm/arm/vgic/vgic-its.c
+++ b/virt/kvm/arm/vgic/vgic-its.c
@@ -23,6 +23,7 @@
#include <linux/interrupt.h>
#include <linux/list.h>
#include <linux/uaccess.h>
+#include <linux/list_sort.h>
#include <linux/irqchip/arm-gic-v3.h>
@@ -33,6 +34,12 @@
#include "vgic.h"
#include "vgic-mmio.h"
+static int vgic_its_save_tables_v0(struct vgic_its *its);
+static int vgic_its_restore_tables_v0(struct vgic_its *its);
+static int vgic_its_commit_v0(struct vgic_its *its);
+static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq,
+ struct kvm_vcpu *filter_vcpu);
+
/*
* Creates a new (reference to a) struct vgic_irq for a given LPI.
* If this LPI is already mapped on another ITS, we increase its refcount
@@ -40,10 +47,12 @@
* If this is a "new" LPI, we allocate and initialize a new struct vgic_irq.
* This function returns a pointer to the _unlocked_ structure.
*/
-static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid)
+static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid,
+ struct kvm_vcpu *vcpu)
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct vgic_irq *irq = vgic_get_irq(kvm, NULL, intid), *oldirq;
+ int ret;
/* In this case there is no put, since we keep the reference. */
if (irq)
@@ -60,6 +69,7 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid)
irq->config = VGIC_CONFIG_EDGE;
kref_init(&irq->refcount);
irq->intid = intid;
+ irq->target_vcpu = vcpu;
spin_lock(&dist->lpi_list_lock);
@@ -91,6 +101,19 @@ static struct vgic_irq *vgic_add_lpi(struct kvm *kvm, u32 intid)
out_unlock:
spin_unlock(&dist->lpi_list_lock);
+ /*
+ * We "cache" the configuration table entries in our struct vgic_irq's.
+ * However we only have those structs for mapped IRQs, so we read in
+ * the respective config data from memory here upon mapping the LPI.
+ */
+ ret = update_lpi_config(kvm, irq, NULL);
+ if (ret)
+ return ERR_PTR(ret);
+
+ ret = vgic_v3_lpi_sync_pending_status(kvm, irq);
+ if (ret)
+ return ERR_PTR(ret);
+
return irq;
}
@@ -99,6 +122,8 @@ struct its_device {
/* the head for the list of ITTEs */
struct list_head itt_head;
+ u32 num_eventid_bits;
+ gpa_t itt_addr;
u32 device_id;
};
@@ -114,8 +139,8 @@ struct its_collection {
#define its_is_collection_mapped(coll) ((coll) && \
((coll)->target_addr != COLLECTION_NOT_MAPPED))
-struct its_itte {
- struct list_head itte_list;
+struct its_ite {
+ struct list_head ite_list;
struct vgic_irq *irq;
struct its_collection *collection;
@@ -123,6 +148,50 @@ struct its_itte {
u32 event_id;
};
+/**
+ * struct vgic_its_abi - ITS abi ops and settings
+ * @cte_esz: collection table entry size
+ * @dte_esz: device table entry size
+ * @ite_esz: interrupt translation table entry size
+ * @save tables: save the ITS tables into guest RAM
+ * @restore_tables: restore the ITS internal structs from tables
+ * stored in guest RAM
+ * @commit: initialize the registers which expose the ABI settings,
+ * especially the entry sizes
+ */
+struct vgic_its_abi {
+ int cte_esz;
+ int dte_esz;
+ int ite_esz;
+ int (*save_tables)(struct vgic_its *its);
+ int (*restore_tables)(struct vgic_its *its);
+ int (*commit)(struct vgic_its *its);
+};
+
+static const struct vgic_its_abi its_table_abi_versions[] = {
+ [0] = {.cte_esz = 8, .dte_esz = 8, .ite_esz = 8,
+ .save_tables = vgic_its_save_tables_v0,
+ .restore_tables = vgic_its_restore_tables_v0,
+ .commit = vgic_its_commit_v0,
+ },
+};
+
+#define NR_ITS_ABIS ARRAY_SIZE(its_table_abi_versions)
+
+inline const struct vgic_its_abi *vgic_its_get_abi(struct vgic_its *its)
+{
+ return &its_table_abi_versions[its->abi_rev];
+}
+
+int vgic_its_set_abi(struct vgic_its *its, int rev)
+{
+ const struct vgic_its_abi *abi;
+
+ its->abi_rev = rev;
+ abi = vgic_its_get_abi(its);
+ return abi->commit(its);
+}
+
/*
* Find and returns a device in the device table for an ITS.
* Must be called with the its_lock mutex held.
@@ -143,27 +212,27 @@ static struct its_device *find_its_device(struct vgic_its *its, u32 device_id)
* Device ID/Event ID pair on an ITS.
* Must be called with the its_lock mutex held.
*/
-static struct its_itte *find_itte(struct vgic_its *its, u32 device_id,
+static struct its_ite *find_ite(struct vgic_its *its, u32 device_id,
u32 event_id)
{
struct its_device *device;
- struct its_itte *itte;
+ struct its_ite *ite;
device = find_its_device(its, device_id);
if (device == NULL)
return NULL;
- list_for_each_entry(itte, &device->itt_head, itte_list)
- if (itte->event_id == event_id)
- return itte;
+ list_for_each_entry(ite, &device->itt_head, ite_list)
+ if (ite->event_id == event_id)
+ return ite;
return NULL;
}
/* To be used as an iterator this macro misses the enclosing parentheses */
-#define for_each_lpi_its(dev, itte, its) \
+#define for_each_lpi_its(dev, ite, its) \
list_for_each_entry(dev, &(its)->device_list, dev_list) \
- list_for_each_entry(itte, &(dev)->itt_head, itte_list)
+ list_for_each_entry(ite, &(dev)->itt_head, ite_list)
/*
* We only implement 48 bits of PA at the moment, although the ITS
@@ -171,11 +240,14 @@ static struct its_itte *find_itte(struct vgic_its *its, u32 device_id,
*/
#define BASER_ADDRESS(x) ((x) & GENMASK_ULL(47, 16))
#define CBASER_ADDRESS(x) ((x) & GENMASK_ULL(47, 12))
-#define PENDBASER_ADDRESS(x) ((x) & GENMASK_ULL(47, 16))
-#define PROPBASER_ADDRESS(x) ((x) & GENMASK_ULL(47, 12))
#define GIC_LPI_OFFSET 8192
+#define VITS_TYPER_IDBITS 16
+#define VITS_TYPER_DEVBITS 16
+#define VITS_DTE_MAX_DEVID_OFFSET (BIT(14) - 1)
+#define VITS_ITE_MAX_EVENTID_OFFSET (BIT(16) - 1)
+
/*
* Finds and returns a collection in the ITS collection table.
* Must be called with the its_lock mutex held.
@@ -204,7 +276,7 @@ static struct its_collection *find_collection(struct vgic_its *its, int coll_id)
static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq,
struct kvm_vcpu *filter_vcpu)
{
- u64 propbase = PROPBASER_ADDRESS(kvm->arch.vgic.propbaser);
+ u64 propbase = GICR_PROPBASER_ADDRESS(kvm->arch.vgic.propbaser);
u8 prop;
int ret;
@@ -229,13 +301,13 @@ static int update_lpi_config(struct kvm *kvm, struct vgic_irq *irq,
}
/*
- * Create a snapshot of the current LPI list, so that we can enumerate all
- * LPIs without holding any lock.
- * Returns the array length and puts the kmalloc'ed array into intid_ptr.
+ * Create a snapshot of the current LPIs targeting @vcpu, so that we can
+ * enumerate those LPIs without holding any lock.
+ * Returns their number and puts the kmalloc'ed array into intid_ptr.
*/
-static int vgic_copy_lpi_list(struct kvm *kvm, u32 **intid_ptr)
+static int vgic_copy_lpi_list(struct kvm_vcpu *vcpu, u32 **intid_ptr)
{
- struct vgic_dist *dist = &kvm->arch.vgic;
+ struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
struct vgic_irq *irq;
u32 *intids;
int irq_count = dist->lpi_list_count, i = 0;
@@ -254,14 +326,14 @@ static int vgic_copy_lpi_list(struct kvm *kvm, u32 **intid_ptr)
spin_lock(&dist->lpi_list_lock);
list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
/* We don't need to "get" the IRQ, as we hold the list lock. */
- intids[i] = irq->intid;
- if (++i == irq_count)
- break;
+ if (irq->target_vcpu != vcpu)
+ continue;
+ intids[i++] = irq->intid;
}
spin_unlock(&dist->lpi_list_lock);
*intid_ptr = intids;
- return irq_count;
+ return i;
}
/*
@@ -270,18 +342,18 @@ static int vgic_copy_lpi_list(struct kvm *kvm, u32 **intid_ptr)
* Needs to be called whenever either the collection for a LPIs has
* changed or the collection itself got retargeted.
*/
-static void update_affinity_itte(struct kvm *kvm, struct its_itte *itte)
+static void update_affinity_ite(struct kvm *kvm, struct its_ite *ite)
{
struct kvm_vcpu *vcpu;
- if (!its_is_collection_mapped(itte->collection))
+ if (!its_is_collection_mapped(ite->collection))
return;
- vcpu = kvm_get_vcpu(kvm, itte->collection->target_addr);
+ vcpu = kvm_get_vcpu(kvm, ite->collection->target_addr);
- spin_lock(&itte->irq->irq_lock);
- itte->irq->target_vcpu = vcpu;
- spin_unlock(&itte->irq->irq_lock);
+ spin_lock(&ite->irq->irq_lock);
+ ite->irq->target_vcpu = vcpu;
+ spin_unlock(&ite->irq->irq_lock);
}
/*
@@ -292,13 +364,13 @@ static void update_affinity_collection(struct kvm *kvm, struct vgic_its *its,
struct its_collection *coll)
{
struct its_device *device;
- struct its_itte *itte;
+ struct its_ite *ite;
- for_each_lpi_its(device, itte, its) {
- if (!itte->collection || coll != itte->collection)
+ for_each_lpi_its(device, ite, its) {
+ if (!ite->collection || coll != ite->collection)
continue;
- update_affinity_itte(kvm, itte);
+ update_affinity_ite(kvm, ite);
}
}
@@ -310,20 +382,20 @@ static u32 max_lpis_propbaser(u64 propbaser)
}
/*
- * Scan the whole LPI pending table and sync the pending bit in there
+ * Sync the pending table pending bit of LPIs targeting @vcpu
* with our own data structures. This relies on the LPI being
* mapped before.
*/
static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu)
{
- gpa_t pendbase = PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser);
+ gpa_t pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser);
struct vgic_irq *irq;
int last_byte_offset = -1;
int ret = 0;
u32 *intids;
int nr_irqs, i;
- nr_irqs = vgic_copy_lpi_list(vcpu->kvm, &intids);
+ nr_irqs = vgic_copy_lpi_list(vcpu, &intids);
if (nr_irqs < 0)
return nr_irqs;
@@ -364,6 +436,7 @@ static unsigned long vgic_mmio_read_its_typer(struct kvm *kvm,
struct vgic_its *its,
gpa_t addr, unsigned int len)
{
+ const struct vgic_its_abi *abi = vgic_its_get_abi(its);
u64 reg = GITS_TYPER_PLPIS;
/*
@@ -374,8 +447,9 @@ static unsigned long vgic_mmio_read_its_typer(struct kvm *kvm,
* To avoid memory waste in the guest, we keep the number of IDBits and
* DevBits low - as least for the time being.
*/
- reg |= 0x0f << GITS_TYPER_DEVBITS_SHIFT;
- reg |= 0x0f << GITS_TYPER_IDBITS_SHIFT;
+ reg |= GIC_ENCODE_SZ(VITS_TYPER_DEVBITS, 5) << GITS_TYPER_DEVBITS_SHIFT;
+ reg |= GIC_ENCODE_SZ(VITS_TYPER_IDBITS, 5) << GITS_TYPER_IDBITS_SHIFT;
+ reg |= GIC_ENCODE_SZ(abi->ite_esz, 4) << GITS_TYPER_ITT_ENTRY_SIZE_SHIFT;
return extract_bytes(reg, addr & 7, len);
}
@@ -384,7 +458,23 @@ static unsigned long vgic_mmio_read_its_iidr(struct kvm *kvm,
struct vgic_its *its,
gpa_t addr, unsigned int len)
{
- return (PRODUCT_ID_KVM << 24) | (IMPLEMENTER_ARM << 0);
+ u32 val;
+
+ val = (its->abi_rev << GITS_IIDR_REV_SHIFT) & GITS_IIDR_REV_MASK;
+ val |= (PRODUCT_ID_KVM << GITS_IIDR_PRODUCTID_SHIFT) | IMPLEMENTER_ARM;
+ return val;
+}
+
+static int vgic_mmio_uaccess_write_its_iidr(struct kvm *kvm,
+ struct vgic_its *its,
+ gpa_t addr, unsigned int len,
+ unsigned long val)
+{
+ u32 rev = GITS_IIDR_REV(val);
+
+ if (rev >= NR_ITS_ABIS)
+ return -EINVAL;
+ return vgic_its_set_abi(its, rev);
}
static unsigned long vgic_mmio_read_its_idregs(struct kvm *kvm,
@@ -425,25 +515,25 @@ static int vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its,
u32 devid, u32 eventid)
{
struct kvm_vcpu *vcpu;
- struct its_itte *itte;
+ struct its_ite *ite;
if (!its->enabled)
return -EBUSY;
- itte = find_itte(its, devid, eventid);
- if (!itte || !its_is_collection_mapped(itte->collection))
+ ite = find_ite(its, devid, eventid);
+ if (!ite || !its_is_collection_mapped(ite->collection))
return E_ITS_INT_UNMAPPED_INTERRUPT;
- vcpu = kvm_get_vcpu(kvm, itte->collection->target_addr);
+ vcpu = kvm_get_vcpu(kvm, ite->collection->target_addr);
if (!vcpu)
return E_ITS_INT_UNMAPPED_INTERRUPT;
if (!vcpu->arch.vgic_cpu.lpis_enabled)
return -EBUSY;
- spin_lock(&itte->irq->irq_lock);
- itte->irq->pending_latch = true;
- vgic_queue_irq_unlock(kvm, itte->irq);
+ spin_lock(&ite->irq->irq_lock);
+ ite->irq->pending_latch = true;
+ vgic_queue_irq_unlock(kvm, ite->irq);
return 0;
}
@@ -511,15 +601,15 @@ int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi)
}
/* Requires the its_lock to be held. */
-static void its_free_itte(struct kvm *kvm, struct its_itte *itte)
+static void its_free_ite(struct kvm *kvm, struct its_ite *ite)
{
- list_del(&itte->itte_list);
+ list_del(&ite->ite_list);
/* This put matches the get in vgic_add_lpi. */
- if (itte->irq)
- vgic_put_irq(kvm, itte->irq);
+ if (ite->irq)
+ vgic_put_irq(kvm, ite->irq);
- kfree(itte);
+ kfree(ite);
}
static u64 its_cmd_mask_field(u64 *its_cmd, int word, int shift, int size)
@@ -529,9 +619,11 @@ static u64 its_cmd_mask_field(u64 *its_cmd, int word, int shift, int size)
#define its_cmd_get_command(cmd) its_cmd_mask_field(cmd, 0, 0, 8)
#define its_cmd_get_deviceid(cmd) its_cmd_mask_field(cmd, 0, 32, 32)
+#define its_cmd_get_size(cmd) (its_cmd_mask_field(cmd, 1, 0, 5) + 1)
#define its_cmd_get_id(cmd) its_cmd_mask_field(cmd, 1, 0, 32)
#define its_cmd_get_physical_id(cmd) its_cmd_mask_field(cmd, 1, 32, 32)
#define its_cmd_get_collection(cmd) its_cmd_mask_field(cmd, 2, 0, 16)
+#define its_cmd_get_ittaddr(cmd) (its_cmd_mask_field(cmd, 2, 8, 44) << 8)
#define its_cmd_get_target_addr(cmd) its_cmd_mask_field(cmd, 2, 16, 32)
#define its_cmd_get_validbit(cmd) its_cmd_mask_field(cmd, 2, 63, 1)
@@ -544,17 +636,17 @@ static int vgic_its_cmd_handle_discard(struct kvm *kvm, struct vgic_its *its,
{
u32 device_id = its_cmd_get_deviceid(its_cmd);
u32 event_id = its_cmd_get_id(its_cmd);
- struct its_itte *itte;
+ struct its_ite *ite;
- itte = find_itte(its, device_id, event_id);
- if (itte && itte->collection) {
+ ite = find_ite(its, device_id, event_id);
+ if (ite && ite->collection) {
/*
* Though the spec talks about removing the pending state, we
* don't bother here since we clear the ITTE anyway and the
* pending state is a property of the ITTE struct.
*/
- its_free_itte(kvm, itte);
+ its_free_ite(kvm, ite);
return 0;
}
@@ -572,26 +664,26 @@ static int vgic_its_cmd_handle_movi(struct kvm *kvm, struct vgic_its *its,
u32 event_id = its_cmd_get_id(its_cmd);
u32 coll_id = its_cmd_get_collection(its_cmd);
struct kvm_vcpu *vcpu;
- struct its_itte *itte;
+ struct its_ite *ite;
struct its_collection *collection;
- itte = find_itte(its, device_id, event_id);
- if (!itte)
+ ite = find_ite(its, device_id, event_id);
+ if (!ite)
return E_ITS_MOVI_UNMAPPED_INTERRUPT;
- if (!its_is_collection_mapped(itte->collection))
+ if (!its_is_collection_mapped(ite->collection))
return E_ITS_MOVI_UNMAPPED_COLLECTION;
collection = find_collection(its, coll_id);
if (!its_is_collection_mapped(collection))
return E_ITS_MOVI_UNMAPPED_COLLECTION;
- itte->collection = collection;
+ ite->collection = collection;
vcpu = kvm_get_vcpu(kvm, collection->target_addr);
- spin_lock(&itte->irq->irq_lock);
- itte->irq->target_vcpu = vcpu;
- spin_unlock(&itte->irq->irq_lock);
+ spin_lock(&ite->irq->irq_lock);
+ ite->irq->target_vcpu = vcpu;
+ spin_unlock(&ite->irq->irq_lock);
return 0;
}
@@ -600,16 +692,31 @@ static int vgic_its_cmd_handle_movi(struct kvm *kvm, struct vgic_its *its,
* Check whether an ID can be stored into the corresponding guest table.
* For a direct table this is pretty easy, but gets a bit nasty for
* indirect tables. We check whether the resulting guest physical address
- * is actually valid (covered by a memslot and guest accessbible).
+ * is actually valid (covered by a memslot and guest accessible).
* For this we have to read the respective first level entry.
*/
-static bool vgic_its_check_id(struct vgic_its *its, u64 baser, int id)
+static bool vgic_its_check_id(struct vgic_its *its, u64 baser, u32 id,
+ gpa_t *eaddr)
{
int l1_tbl_size = GITS_BASER_NR_PAGES(baser) * SZ_64K;
+ u64 indirect_ptr, type = GITS_BASER_TYPE(baser);
+ int esz = GITS_BASER_ENTRY_SIZE(baser);
int index;
- u64 indirect_ptr;
gfn_t gfn;
- int esz = GITS_BASER_ENTRY_SIZE(baser);
+
+ switch (type) {
+ case GITS_BASER_TYPE_DEVICE:
+ if (id >= BIT_ULL(VITS_TYPER_DEVBITS))
+ return false;
+ break;
+ case GITS_BASER_TYPE_COLLECTION:
+ /* as GITS_TYPER.CIL == 0, ITS supports 16-bit collection ID */
+ if (id >= BIT_ULL(16))
+ return false;
+ break;
+ default:
+ return false;
+ }
if (!(baser & GITS_BASER_INDIRECT)) {
phys_addr_t addr;
@@ -620,6 +727,8 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, int id)
addr = BASER_ADDRESS(baser) + id * esz;
gfn = addr >> PAGE_SHIFT;
+ if (eaddr)
+ *eaddr = addr;
return kvm_is_visible_gfn(its->dev->kvm, gfn);
}
@@ -652,6 +761,8 @@ static bool vgic_its_check_id(struct vgic_its *its, u64 baser, int id)
indirect_ptr += index * esz;
gfn = indirect_ptr >> PAGE_SHIFT;
+ if (eaddr)
+ *eaddr = indirect_ptr;
return kvm_is_visible_gfn(its->dev->kvm, gfn);
}
@@ -661,7 +772,7 @@ static int vgic_its_alloc_collection(struct vgic_its *its,
{
struct its_collection *collection;
- if (!vgic_its_check_id(its, its->baser_coll_table, coll_id))
+ if (!vgic_its_check_id(its, its->baser_coll_table, coll_id, NULL))
return E_ITS_MAPC_COLLECTION_OOR;
collection = kzalloc(sizeof(*collection), GFP_KERNEL);
@@ -679,7 +790,7 @@ static void vgic_its_free_collection(struct vgic_its *its, u32 coll_id)
{
struct its_collection *collection;
struct its_device *device;
- struct its_itte *itte;
+ struct its_ite *ite;
/*
* Clearing the mapping for that collection ID removes the
@@ -690,15 +801,34 @@ static void vgic_its_free_collection(struct vgic_its *its, u32 coll_id)
if (!collection)
return;
- for_each_lpi_its(device, itte, its)
- if (itte->collection &&
- itte->collection->collection_id == coll_id)
- itte->collection = NULL;
+ for_each_lpi_its(device, ite, its)
+ if (ite->collection &&
+ ite->collection->collection_id == coll_id)
+ ite->collection = NULL;
list_del(&collection->coll_list);
kfree(collection);
}
+/* Must be called with its_lock mutex held */
+static struct its_ite *vgic_its_alloc_ite(struct its_device *device,
+ struct its_collection *collection,
+ u32 lpi_id, u32 event_id)
+{
+ struct its_ite *ite;
+
+ ite = kzalloc(sizeof(*ite), GFP_KERNEL);
+ if (!ite)
+ return ERR_PTR(-ENOMEM);
+
+ ite->event_id = event_id;
+ ite->collection = collection;
+ ite->lpi = lpi_id;
+
+ list_add_tail(&ite->ite_list, &device->itt_head);
+ return ite;
+}
+
/*
* The MAPTI and MAPI commands map LPIs to ITTEs.
* Must be called with its_lock mutex held.
@@ -709,16 +839,20 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its,
u32 device_id = its_cmd_get_deviceid(its_cmd);
u32 event_id = its_cmd_get_id(its_cmd);
u32 coll_id = its_cmd_get_collection(its_cmd);
- struct its_itte *itte;
+ struct its_ite *ite;
+ struct kvm_vcpu *vcpu = NULL;
struct its_device *device;
struct its_collection *collection, *new_coll = NULL;
- int lpi_nr;
struct vgic_irq *irq;
+ int lpi_nr;
device = find_its_device(its, device_id);
if (!device)
return E_ITS_MAPTI_UNMAPPED_DEVICE;
+ if (event_id >= BIT_ULL(device->num_eventid_bits))
+ return E_ITS_MAPTI_ID_OOR;
+
if (its_cmd_get_command(its_cmd) == GITS_CMD_MAPTI)
lpi_nr = its_cmd_get_physical_id(its_cmd);
else
@@ -728,7 +862,7 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its,
return E_ITS_MAPTI_PHYSICALID_OOR;
/* If there is an existing mapping, behavior is UNPREDICTABLE. */
- if (find_itte(its, device_id, event_id))
+ if (find_ite(its, device_id, event_id))
return 0;
collection = find_collection(its, coll_id);
@@ -739,36 +873,24 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its,
new_coll = collection;
}
- itte = kzalloc(sizeof(struct its_itte), GFP_KERNEL);
- if (!itte) {
+ ite = vgic_its_alloc_ite(device, collection, lpi_nr, event_id);
+ if (IS_ERR(ite)) {
if (new_coll)
vgic_its_free_collection(its, coll_id);
- return -ENOMEM;
+ return PTR_ERR(ite);
}
- itte->event_id = event_id;
- list_add_tail(&itte->itte_list, &device->itt_head);
-
- itte->collection = collection;
- itte->lpi = lpi_nr;
+ if (its_is_collection_mapped(collection))
+ vcpu = kvm_get_vcpu(kvm, collection->target_addr);
- irq = vgic_add_lpi(kvm, lpi_nr);
+ irq = vgic_add_lpi(kvm, lpi_nr, vcpu);
if (IS_ERR(irq)) {
if (new_coll)
vgic_its_free_collection(its, coll_id);
- its_free_itte(kvm, itte);
+ its_free_ite(kvm, ite);
return PTR_ERR(irq);
}
- itte->irq = irq;
-
- update_affinity_itte(kvm, itte);
-
- /*
- * We "cache" the configuration table entries in out struct vgic_irq's.
- * However we only have those structs for mapped IRQs, so we read in
- * the respective config data from memory here upon mapping the LPI.
- */
- update_lpi_config(kvm, itte->irq, NULL);
+ ite->irq = irq;
return 0;
}
@@ -776,20 +898,40 @@ static int vgic_its_cmd_handle_mapi(struct kvm *kvm, struct vgic_its *its,
/* Requires the its_lock to be held. */
static void vgic_its_unmap_device(struct kvm *kvm, struct its_device *device)
{
- struct its_itte *itte, *temp;
+ struct its_ite *ite, *temp;
/*
* The spec says that unmapping a device with still valid
* ITTEs associated is UNPREDICTABLE. We remove all ITTEs,
* since we cannot leave the memory unreferenced.
*/
- list_for_each_entry_safe(itte, temp, &device->itt_head, itte_list)
- its_free_itte(kvm, itte);
+ list_for_each_entry_safe(ite, temp, &device->itt_head, ite_list)
+ its_free_ite(kvm, ite);
list_del(&device->dev_list);
kfree(device);
}
+/* Must be called with its_lock mutex held */
+static struct its_device *vgic_its_alloc_device(struct vgic_its *its,
+ u32 device_id, gpa_t itt_addr,
+ u8 num_eventid_bits)
+{
+ struct its_device *device;
+
+ device = kzalloc(sizeof(*device), GFP_KERNEL);
+ if (!device)
+ return ERR_PTR(-ENOMEM);
+
+ device->device_id = device_id;
+ device->itt_addr = itt_addr;
+ device->num_eventid_bits = num_eventid_bits;
+ INIT_LIST_HEAD(&device->itt_head);
+
+ list_add_tail(&device->dev_list, &its->device_list);
+ return device;
+}
+
/*
* MAPD maps or unmaps a device ID to Interrupt Translation Tables (ITTs).
* Must be called with the its_lock mutex held.
@@ -799,11 +941,16 @@ static int vgic_its_cmd_handle_mapd(struct kvm *kvm, struct vgic_its *its,
{
u32 device_id = its_cmd_get_deviceid(its_cmd);
bool valid = its_cmd_get_validbit(its_cmd);
+ u8 num_eventid_bits = its_cmd_get_size(its_cmd);
+ gpa_t itt_addr = its_cmd_get_ittaddr(its_cmd);
struct its_device *device;
- if (!vgic_its_check_id(its, its->baser_device_table, device_id))
+ if (!vgic_its_check_id(its, its->baser_device_table, device_id, NULL))
return E_ITS_MAPD_DEVICE_OOR;
+ if (valid && num_eventid_bits > VITS_TYPER_IDBITS)
+ return E_ITS_MAPD_ITTSIZE_OOR;
+
device = find_its_device(its, device_id);
/*
@@ -821,14 +968,10 @@ static int vgic_its_cmd_handle_mapd(struct kvm *kvm, struct vgic_its *its,
if (!valid)
return 0;
- device = kzalloc(sizeof(struct its_device), GFP_KERNEL);
- if (!device)
- return -ENOMEM;
-
- device->device_id = device_id;
- INIT_LIST_HEAD(&device->itt_head);
-
- list_add_tail(&device->dev_list, &its->device_list);
+ device = vgic_its_alloc_device(its, device_id, itt_addr,
+ num_eventid_bits);
+ if (IS_ERR(device))
+ return PTR_ERR(device);
return 0;
}
@@ -883,14 +1026,14 @@ static int vgic_its_cmd_handle_clear(struct kvm *kvm, struct vgic_its *its,
{
u32 device_id = its_cmd_get_deviceid(its_cmd);
u32 event_id = its_cmd_get_id(its_cmd);
- struct its_itte *itte;
+ struct its_ite *ite;
- itte = find_itte(its, device_id, event_id);
- if (!itte)
+ ite = find_ite(its, device_id, event_id);
+ if (!ite)
return E_ITS_CLEAR_UNMAPPED_INTERRUPT;
- itte->irq->pending_latch = false;
+ ite->irq->pending_latch = false;
return 0;
}
@@ -904,14 +1047,14 @@ static int vgic_its_cmd_handle_inv(struct kvm *kvm, struct vgic_its *its,
{
u32 device_id = its_cmd_get_deviceid(its_cmd);
u32 event_id = its_cmd_get_id(its_cmd);
- struct its_itte *itte;
+ struct its_ite *ite;
- itte = find_itte(its, device_id, event_id);
- if (!itte)
+ ite = find_ite(its, device_id, event_id);
+ if (!ite)
return E_ITS_INV_UNMAPPED_INTERRUPT;
- return update_lpi_config(kvm, itte->irq, NULL);
+ return update_lpi_config(kvm, ite->irq, NULL);
}
/*
@@ -938,7 +1081,7 @@ static int vgic_its_cmd_handle_invall(struct kvm *kvm, struct vgic_its *its,
vcpu = kvm_get_vcpu(kvm, collection->target_addr);
- irq_count = vgic_copy_lpi_list(kvm, &intids);
+ irq_count = vgic_copy_lpi_list(vcpu, &intids);
if (irq_count < 0)
return irq_count;
@@ -1213,6 +1356,33 @@ static unsigned long vgic_mmio_read_its_creadr(struct kvm *kvm,
return extract_bytes(its->creadr, addr & 0x7, len);
}
+static int vgic_mmio_uaccess_write_its_creadr(struct kvm *kvm,
+ struct vgic_its *its,
+ gpa_t addr, unsigned int len,
+ unsigned long val)
+{
+ u32 cmd_offset;
+ int ret = 0;
+
+ mutex_lock(&its->cmd_lock);
+
+ if (its->enabled) {
+ ret = -EBUSY;
+ goto out;
+ }
+
+ cmd_offset = ITS_CMD_OFFSET(val);
+ if (cmd_offset >= ITS_CMD_BUFFER_SIZE(its->cbaser)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ its->creadr = cmd_offset;
+out:
+ mutex_unlock(&its->cmd_lock);
+ return ret;
+}
+
#define BASER_INDEX(addr) (((addr) / sizeof(u64)) & 0x7)
static unsigned long vgic_mmio_read_its_baser(struct kvm *kvm,
struct vgic_its *its,
@@ -1241,6 +1411,7 @@ static void vgic_mmio_write_its_baser(struct kvm *kvm,
gpa_t addr, unsigned int len,
unsigned long val)
{
+ const struct vgic_its_abi *abi = vgic_its_get_abi(its);
u64 entry_size, device_type;
u64 reg, *regptr, clearbits = 0;
@@ -1251,12 +1422,12 @@ static void vgic_mmio_write_its_baser(struct kvm *kvm,
switch (BASER_INDEX(addr)) {
case 0:
regptr = &its->baser_device_table;
- entry_size = 8;
+ entry_size = abi->dte_esz;
device_type = GITS_BASER_TYPE_DEVICE;
break;
case 1:
regptr = &its->baser_coll_table;
- entry_size = 8;
+ entry_size = abi->cte_esz;
device_type = GITS_BASER_TYPE_COLLECTION;
clearbits = GITS_BASER_INDIRECT;
break;
@@ -1317,6 +1488,16 @@ static void vgic_mmio_write_its_ctlr(struct kvm *kvm, struct vgic_its *its,
.its_write = wr, \
}
+#define REGISTER_ITS_DESC_UACCESS(off, rd, wr, uwr, length, acc)\
+{ \
+ .reg_offset = off, \
+ .len = length, \
+ .access_flags = acc, \
+ .its_read = rd, \
+ .its_write = wr, \
+ .uaccess_its_write = uwr, \
+}
+
static void its_mmio_write_wi(struct kvm *kvm, struct vgic_its *its,
gpa_t addr, unsigned int len, unsigned long val)
{
@@ -1327,8 +1508,9 @@ static struct vgic_register_region its_registers[] = {
REGISTER_ITS_DESC(GITS_CTLR,
vgic_mmio_read_its_ctlr, vgic_mmio_write_its_ctlr, 4,
VGIC_ACCESS_32bit),
- REGISTER_ITS_DESC(GITS_IIDR,
- vgic_mmio_read_its_iidr, its_mmio_write_wi, 4,
+ REGISTER_ITS_DESC_UACCESS(GITS_IIDR,
+ vgic_mmio_read_its_iidr, its_mmio_write_wi,
+ vgic_mmio_uaccess_write_its_iidr, 4,
VGIC_ACCESS_32bit),
REGISTER_ITS_DESC(GITS_TYPER,
vgic_mmio_read_its_typer, its_mmio_write_wi, 8,
@@ -1339,8 +1521,9 @@ static struct vgic_register_region its_registers[] = {
REGISTER_ITS_DESC(GITS_CWRITER,
vgic_mmio_read_its_cwriter, vgic_mmio_write_its_cwriter, 8,
VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
- REGISTER_ITS_DESC(GITS_CREADR,
- vgic_mmio_read_its_creadr, its_mmio_write_wi, 8,
+ REGISTER_ITS_DESC_UACCESS(GITS_CREADR,
+ vgic_mmio_read_its_creadr, its_mmio_write_wi,
+ vgic_mmio_uaccess_write_its_creadr, 8,
VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
REGISTER_ITS_DESC(GITS_BASER,
vgic_mmio_read_its_baser, vgic_mmio_write_its_baser, 0x40,
@@ -1357,17 +1540,19 @@ void vgic_enable_lpis(struct kvm_vcpu *vcpu)
its_sync_lpi_pending_table(vcpu);
}
-static int vgic_register_its_iodev(struct kvm *kvm, struct vgic_its *its)
+static int vgic_register_its_iodev(struct kvm *kvm, struct vgic_its *its,
+ u64 addr)
{
struct vgic_io_device *iodev = &its->iodev;
int ret;
- if (!its->initialized)
- return -EBUSY;
-
- if (IS_VGIC_ADDR_UNDEF(its->vgic_its_base))
- return -ENXIO;
+ mutex_lock(&kvm->slots_lock);
+ if (!IS_VGIC_ADDR_UNDEF(its->vgic_its_base)) {
+ ret = -EBUSY;
+ goto out;
+ }
+ its->vgic_its_base = addr;
iodev->regions = its_registers;
iodev->nr_regions = ARRAY_SIZE(its_registers);
kvm_iodevice_init(&iodev->dev, &kvm_io_gic_ops);
@@ -1375,9 +1560,9 @@ static int vgic_register_its_iodev(struct kvm *kvm, struct vgic_its *its)
iodev->base_addr = its->vgic_its_base;
iodev->iodev_type = IODEV_ITS;
iodev->its = its;
- mutex_lock(&kvm->slots_lock);
ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, iodev->base_addr,
KVM_VGIC_V3_ITS_SIZE, &iodev->dev);
+out:
mutex_unlock(&kvm->slots_lock);
return ret;
@@ -1387,7 +1572,6 @@ static int vgic_register_its_iodev(struct kvm *kvm, struct vgic_its *its)
(GIC_BASER_CACHEABILITY(GITS_BASER, INNER, RaWb) | \
GIC_BASER_CACHEABILITY(GITS_BASER, OUTER, SameAsInner) | \
GIC_BASER_SHAREABILITY(GITS_BASER, InnerShareable) | \
- ((8ULL - 1) << GITS_BASER_ENTRY_SIZE_SHIFT) | \
GITS_BASER_PAGE_SIZE_64K)
#define INITIAL_PROPBASER_VALUE \
@@ -1415,7 +1599,6 @@ static int vgic_its_create(struct kvm_device *dev, u32 type)
INIT_LIST_HEAD(&its->collection_list);
dev->kvm->arch.vgic.has_its = true;
- its->initialized = false;
its->enabled = false;
its->dev = dev;
@@ -1427,16 +1610,23 @@ static int vgic_its_create(struct kvm_device *dev, u32 type)
dev->private = its;
- return 0;
+ return vgic_its_set_abi(its, NR_ITS_ABIS - 1);
+}
+
+static void vgic_its_free_device(struct kvm *kvm, struct its_device *dev)
+{
+ struct its_ite *ite, *tmp;
+
+ list_for_each_entry_safe(ite, tmp, &dev->itt_head, ite_list)
+ its_free_ite(kvm, ite);
+ list_del(&dev->dev_list);
+ kfree(dev);
}
static void vgic_its_destroy(struct kvm_device *kvm_dev)
{
struct kvm *kvm = kvm_dev->kvm;
struct vgic_its *its = kvm_dev->private;
- struct its_device *dev;
- struct its_itte *itte;
- struct list_head *dev_cur, *dev_temp;
struct list_head *cur, *temp;
/*
@@ -1447,25 +1637,710 @@ static void vgic_its_destroy(struct kvm_device *kvm_dev)
return;
mutex_lock(&its->its_lock);
- list_for_each_safe(dev_cur, dev_temp, &its->device_list) {
- dev = container_of(dev_cur, struct its_device, dev_list);
- list_for_each_safe(cur, temp, &dev->itt_head) {
- itte = (container_of(cur, struct its_itte, itte_list));
- its_free_itte(kvm, itte);
- }
- list_del(dev_cur);
- kfree(dev);
+ list_for_each_safe(cur, temp, &its->device_list) {
+ struct its_device *dev;
+
+ dev = list_entry(cur, struct its_device, dev_list);
+ vgic_its_free_device(kvm, dev);
}
list_for_each_safe(cur, temp, &its->collection_list) {
+ struct its_collection *coll;
+
+ coll = list_entry(cur, struct its_collection, coll_list);
list_del(cur);
- kfree(container_of(cur, struct its_collection, coll_list));
+ kfree(coll);
}
mutex_unlock(&its->its_lock);
kfree(its);
}
+int vgic_its_has_attr_regs(struct kvm_device *dev,
+ struct kvm_device_attr *attr)
+{
+ const struct vgic_register_region *region;
+ gpa_t offset = attr->attr;
+ int align;
+
+ align = (offset < GITS_TYPER) || (offset >= GITS_PIDR4) ? 0x3 : 0x7;
+
+ if (offset & align)
+ return -EINVAL;
+
+ region = vgic_find_mmio_region(its_registers,
+ ARRAY_SIZE(its_registers),
+ offset);
+ if (!region)
+ return -ENXIO;
+
+ return 0;
+}
+
+int vgic_its_attr_regs_access(struct kvm_device *dev,
+ struct kvm_device_attr *attr,
+ u64 *reg, bool is_write)
+{
+ const struct vgic_register_region *region;
+ struct vgic_its *its;
+ gpa_t addr, offset;
+ unsigned int len;
+ int align, ret = 0;
+
+ its = dev->private;
+ offset = attr->attr;
+
+ /*
+ * Although the spec supports upper/lower 32-bit accesses to
+ * 64-bit ITS registers, the userspace ABI requires 64-bit
+ * accesses to all 64-bit wide registers. We therefore only
+ * support 32-bit accesses to GITS_CTLR, GITS_IIDR and GITS ID
+ * registers
+ */
+ if ((offset < GITS_TYPER) || (offset >= GITS_PIDR4))
+ align = 0x3;
+ else
+ align = 0x7;
+
+ if (offset & align)
+ return -EINVAL;
+
+ mutex_lock(&dev->kvm->lock);
+
+ if (IS_VGIC_ADDR_UNDEF(its->vgic_its_base)) {
+ ret = -ENXIO;
+ goto out;
+ }
+
+ region = vgic_find_mmio_region(its_registers,
+ ARRAY_SIZE(its_registers),
+ offset);
+ if (!region) {
+ ret = -ENXIO;
+ goto out;
+ }
+
+ if (!lock_all_vcpus(dev->kvm)) {
+ ret = -EBUSY;
+ goto out;
+ }
+
+ addr = its->vgic_its_base + offset;
+
+ len = region->access_flags & VGIC_ACCESS_64bit ? 8 : 4;
+
+ if (is_write) {
+ if (region->uaccess_its_write)
+ ret = region->uaccess_its_write(dev->kvm, its, addr,
+ len, *reg);
+ else
+ region->its_write(dev->kvm, its, addr, len, *reg);
+ } else {
+ *reg = region->its_read(dev->kvm, its, addr, len);
+ }
+ unlock_all_vcpus(dev->kvm);
+out:
+ mutex_unlock(&dev->kvm->lock);
+ return ret;
+}
+
+static u32 compute_next_devid_offset(struct list_head *h,
+ struct its_device *dev)
+{
+ struct its_device *next;
+ u32 next_offset;
+
+ if (list_is_last(&dev->dev_list, h))
+ return 0;
+ next = list_next_entry(dev, dev_list);
+ next_offset = next->device_id - dev->device_id;
+
+ return min_t(u32, next_offset, VITS_DTE_MAX_DEVID_OFFSET);
+}
+
+static u32 compute_next_eventid_offset(struct list_head *h, struct its_ite *ite)
+{
+ struct its_ite *next;
+ u32 next_offset;
+
+ if (list_is_last(&ite->ite_list, h))
+ return 0;
+ next = list_next_entry(ite, ite_list);
+ next_offset = next->event_id - ite->event_id;
+
+ return min_t(u32, next_offset, VITS_ITE_MAX_EVENTID_OFFSET);
+}
+
+/**
+ * entry_fn_t - Callback called on a table entry restore path
+ * @its: its handle
+ * @id: id of the entry
+ * @entry: pointer to the entry
+ * @opaque: pointer to an opaque data
+ *
+ * Return: < 0 on error, 0 if last element was identified, id offset to next
+ * element otherwise
+ */
+typedef int (*entry_fn_t)(struct vgic_its *its, u32 id, void *entry,
+ void *opaque);
+
+/**
+ * scan_its_table - Scan a contiguous table in guest RAM and applies a function
+ * to each entry
+ *
+ * @its: its handle
+ * @base: base gpa of the table
+ * @size: size of the table in bytes
+ * @esz: entry size in bytes
+ * @start_id: the ID of the first entry in the table
+ * (non zero for 2d level tables)
+ * @fn: function to apply on each entry
+ *
+ * Return: < 0 on error, 0 if last element was identified, 1 otherwise
+ * (the last element may not be found on second level tables)
+ */
+static int scan_its_table(struct vgic_its *its, gpa_t base, int size, int esz,
+ int start_id, entry_fn_t fn, void *opaque)
+{
+ void *entry = kzalloc(esz, GFP_KERNEL);
+ struct kvm *kvm = its->dev->kvm;
+ unsigned long len = size;
+ int id = start_id;
+ gpa_t gpa = base;
+ int ret;
+
+ while (len > 0) {
+ int next_offset;
+ size_t byte_offset;
+
+ ret = kvm_read_guest(kvm, gpa, entry, esz);
+ if (ret)
+ goto out;
+
+ next_offset = fn(its, id, entry, opaque);
+ if (next_offset <= 0) {
+ ret = next_offset;
+ goto out;
+ }
+
+ byte_offset = next_offset * esz;
+ id += next_offset;
+ gpa += byte_offset;
+ len -= byte_offset;
+ }
+ ret = 1;
+
+out:
+ kfree(entry);
+ return ret;
+}
+
+/**
+ * vgic_its_save_ite - Save an interrupt translation entry at @gpa
+ */
+static int vgic_its_save_ite(struct vgic_its *its, struct its_device *dev,
+ struct its_ite *ite, gpa_t gpa, int ite_esz)
+{
+ struct kvm *kvm = its->dev->kvm;
+ u32 next_offset;
+ u64 val;
+
+ next_offset = compute_next_eventid_offset(&dev->itt_head, ite);
+ val = ((u64)next_offset << KVM_ITS_ITE_NEXT_SHIFT) |
+ ((u64)ite->lpi << KVM_ITS_ITE_PINTID_SHIFT) |
+ ite->collection->collection_id;
+ val = cpu_to_le64(val);
+ return kvm_write_guest(kvm, gpa, &val, ite_esz);
+}
+
+/**
+ * vgic_its_restore_ite - restore an interrupt translation entry
+ * @event_id: id used for indexing
+ * @ptr: pointer to the ITE entry
+ * @opaque: pointer to the its_device
+ */
+static int vgic_its_restore_ite(struct vgic_its *its, u32 event_id,
+ void *ptr, void *opaque)
+{
+ struct its_device *dev = (struct its_device *)opaque;
+ struct its_collection *collection;
+ struct kvm *kvm = its->dev->kvm;
+ struct kvm_vcpu *vcpu = NULL;
+ u64 val;
+ u64 *p = (u64 *)ptr;
+ struct vgic_irq *irq;
+ u32 coll_id, lpi_id;
+ struct its_ite *ite;
+ u32 offset;
+
+ val = *p;
+
+ val = le64_to_cpu(val);
+
+ coll_id = val & KVM_ITS_ITE_ICID_MASK;
+ lpi_id = (val & KVM_ITS_ITE_PINTID_MASK) >> KVM_ITS_ITE_PINTID_SHIFT;
+
+ if (!lpi_id)
+ return 1; /* invalid entry, no choice but to scan next entry */
+
+ if (lpi_id < VGIC_MIN_LPI)
+ return -EINVAL;
+
+ offset = val >> KVM_ITS_ITE_NEXT_SHIFT;
+ if (event_id + offset >= BIT_ULL(dev->num_eventid_bits))
+ return -EINVAL;
+
+ collection = find_collection(its, coll_id);
+ if (!collection)
+ return -EINVAL;
+
+ ite = vgic_its_alloc_ite(dev, collection, lpi_id, event_id);
+ if (IS_ERR(ite))
+ return PTR_ERR(ite);
+
+ if (its_is_collection_mapped(collection))
+ vcpu = kvm_get_vcpu(kvm, collection->target_addr);
+
+ irq = vgic_add_lpi(kvm, lpi_id, vcpu);
+ if (IS_ERR(irq))
+ return PTR_ERR(irq);
+ ite->irq = irq;
+
+ return offset;
+}
+
+static int vgic_its_ite_cmp(void *priv, struct list_head *a,
+ struct list_head *b)
+{
+ struct its_ite *itea = container_of(a, struct its_ite, ite_list);
+ struct its_ite *iteb = container_of(b, struct its_ite, ite_list);
+
+ if (itea->event_id < iteb->event_id)
+ return -1;
+ else
+ return 1;
+}
+
+static int vgic_its_save_itt(struct vgic_its *its, struct its_device *device)
+{
+ const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+ gpa_t base = device->itt_addr;
+ struct its_ite *ite;
+ int ret;
+ int ite_esz = abi->ite_esz;
+
+ list_sort(NULL, &device->itt_head, vgic_its_ite_cmp);
+
+ list_for_each_entry(ite, &device->itt_head, ite_list) {
+ gpa_t gpa = base + ite->event_id * ite_esz;
+
+ ret = vgic_its_save_ite(its, device, ite, gpa, ite_esz);
+ if (ret)
+ return ret;
+ }
+ return 0;
+}
+
+static int vgic_its_restore_itt(struct vgic_its *its, struct its_device *dev)
+{
+ const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+ gpa_t base = dev->itt_addr;
+ int ret;
+ int ite_esz = abi->ite_esz;
+ size_t max_size = BIT_ULL(dev->num_eventid_bits) * ite_esz;
+
+ ret = scan_its_table(its, base, max_size, ite_esz, 0,
+ vgic_its_restore_ite, dev);
+
+ return ret;
+}
+
+/**
+ * vgic_its_save_dte - Save a device table entry at a given GPA
+ *
+ * @its: ITS handle
+ * @dev: ITS device
+ * @ptr: GPA
+ */
+static int vgic_its_save_dte(struct vgic_its *its, struct its_device *dev,
+ gpa_t ptr, int dte_esz)
+{
+ struct kvm *kvm = its->dev->kvm;
+ u64 val, itt_addr_field;
+ u32 next_offset;
+
+ itt_addr_field = dev->itt_addr >> 8;
+ next_offset = compute_next_devid_offset(&its->device_list, dev);
+ val = (1ULL << KVM_ITS_DTE_VALID_SHIFT |
+ ((u64)next_offset << KVM_ITS_DTE_NEXT_SHIFT) |
+ (itt_addr_field << KVM_ITS_DTE_ITTADDR_SHIFT) |
+ (dev->num_eventid_bits - 1));
+ val = cpu_to_le64(val);
+ return kvm_write_guest(kvm, ptr, &val, dte_esz);
+}
+
+/**
+ * vgic_its_restore_dte - restore a device table entry
+ *
+ * @its: its handle
+ * @id: device id the DTE corresponds to
+ * @ptr: kernel VA where the 8 byte DTE is located
+ * @opaque: unused
+ *
+ * Return: < 0 on error, 0 if the dte is the last one, id offset to the
+ * next dte otherwise
+ */
+static int vgic_its_restore_dte(struct vgic_its *its, u32 id,
+ void *ptr, void *opaque)
+{
+ struct its_device *dev;
+ gpa_t itt_addr;
+ u8 num_eventid_bits;
+ u64 entry = *(u64 *)ptr;
+ bool valid;
+ u32 offset;
+ int ret;
+
+ entry = le64_to_cpu(entry);
+
+ valid = entry >> KVM_ITS_DTE_VALID_SHIFT;
+ num_eventid_bits = (entry & KVM_ITS_DTE_SIZE_MASK) + 1;
+ itt_addr = ((entry & KVM_ITS_DTE_ITTADDR_MASK)
+ >> KVM_ITS_DTE_ITTADDR_SHIFT) << 8;
+
+ if (!valid)
+ return 1;
+
+ /* dte entry is valid */
+ offset = (entry & KVM_ITS_DTE_NEXT_MASK) >> KVM_ITS_DTE_NEXT_SHIFT;
+
+ dev = vgic_its_alloc_device(its, id, itt_addr, num_eventid_bits);
+ if (IS_ERR(dev))
+ return PTR_ERR(dev);
+
+ ret = vgic_its_restore_itt(its, dev);
+ if (ret) {
+ vgic_its_free_device(its->dev->kvm, dev);
+ return ret;
+ }
+
+ return offset;
+}
+
+static int vgic_its_device_cmp(void *priv, struct list_head *a,
+ struct list_head *b)
+{
+ struct its_device *deva = container_of(a, struct its_device, dev_list);
+ struct its_device *devb = container_of(b, struct its_device, dev_list);
+
+ if (deva->device_id < devb->device_id)
+ return -1;
+ else
+ return 1;
+}
+
+/**
+ * vgic_its_save_device_tables - Save the device table and all ITT
+ * into guest RAM
+ *
+ * L1/L2 handling is hidden by vgic_its_check_id() helper which directly
+ * returns the GPA of the device entry
+ */
+static int vgic_its_save_device_tables(struct vgic_its *its)
+{
+ const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+ struct its_device *dev;
+ int dte_esz = abi->dte_esz;
+ u64 baser;
+
+ baser = its->baser_device_table;
+
+ list_sort(NULL, &its->device_list, vgic_its_device_cmp);
+
+ list_for_each_entry(dev, &its->device_list, dev_list) {
+ int ret;
+ gpa_t eaddr;
+
+ if (!vgic_its_check_id(its, baser,
+ dev->device_id, &eaddr))
+ return -EINVAL;
+
+ ret = vgic_its_save_itt(its, dev);
+ if (ret)
+ return ret;
+
+ ret = vgic_its_save_dte(its, dev, eaddr, dte_esz);
+ if (ret)
+ return ret;
+ }
+ return 0;
+}
+
+/**
+ * handle_l1_dte - callback used for L1 device table entries (2 stage case)
+ *
+ * @its: its handle
+ * @id: index of the entry in the L1 table
+ * @addr: kernel VA
+ * @opaque: unused
+ *
+ * L1 table entries are scanned by steps of 1 entry
+ * Return < 0 if error, 0 if last dte was found when scanning the L2
+ * table, +1 otherwise (meaning next L1 entry must be scanned)
+ */
+static int handle_l1_dte(struct vgic_its *its, u32 id, void *addr,
+ void *opaque)
+{
+ const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+ int l2_start_id = id * (SZ_64K / abi->dte_esz);
+ u64 entry = *(u64 *)addr;
+ int dte_esz = abi->dte_esz;
+ gpa_t gpa;
+ int ret;
+
+ entry = le64_to_cpu(entry);
+
+ if (!(entry & KVM_ITS_L1E_VALID_MASK))
+ return 1;
+
+ gpa = entry & KVM_ITS_L1E_ADDR_MASK;
+
+ ret = scan_its_table(its, gpa, SZ_64K, dte_esz,
+ l2_start_id, vgic_its_restore_dte, NULL);
+
+ if (ret <= 0)
+ return ret;
+
+ return 1;
+}
+
+/**
+ * vgic_its_restore_device_tables - Restore the device table and all ITT
+ * from guest RAM to internal data structs
+ */
+static int vgic_its_restore_device_tables(struct vgic_its *its)
+{
+ const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+ u64 baser = its->baser_device_table;
+ int l1_esz, ret;
+ int l1_tbl_size = GITS_BASER_NR_PAGES(baser) * SZ_64K;
+ gpa_t l1_gpa;
+
+ if (!(baser & GITS_BASER_VALID))
+ return 0;
+
+ l1_gpa = BASER_ADDRESS(baser);
+
+ if (baser & GITS_BASER_INDIRECT) {
+ l1_esz = GITS_LVL1_ENTRY_SIZE;
+ ret = scan_its_table(its, l1_gpa, l1_tbl_size, l1_esz, 0,
+ handle_l1_dte, NULL);
+ } else {
+ l1_esz = abi->dte_esz;
+ ret = scan_its_table(its, l1_gpa, l1_tbl_size, l1_esz, 0,
+ vgic_its_restore_dte, NULL);
+ }
+
+ if (ret > 0)
+ ret = -EINVAL;
+
+ return ret;
+}
+
+static int vgic_its_save_cte(struct vgic_its *its,
+ struct its_collection *collection,
+ gpa_t gpa, int esz)
+{
+ u64 val;
+
+ val = (1ULL << KVM_ITS_CTE_VALID_SHIFT |
+ ((u64)collection->target_addr << KVM_ITS_CTE_RDBASE_SHIFT) |
+ collection->collection_id);
+ val = cpu_to_le64(val);
+ return kvm_write_guest(its->dev->kvm, gpa, &val, esz);
+}
+
+static int vgic_its_restore_cte(struct vgic_its *its, gpa_t gpa, int esz)
+{
+ struct its_collection *collection;
+ struct kvm *kvm = its->dev->kvm;
+ u32 target_addr, coll_id;
+ u64 val;
+ int ret;
+
+ BUG_ON(esz > sizeof(val));
+ ret = kvm_read_guest(kvm, gpa, &val, esz);
+ if (ret)
+ return ret;
+ val = le64_to_cpu(val);
+ if (!(val & KVM_ITS_CTE_VALID_MASK))
+ return 0;
+
+ target_addr = (u32)(val >> KVM_ITS_CTE_RDBASE_SHIFT);
+ coll_id = val & KVM_ITS_CTE_ICID_MASK;
+
+ if (target_addr >= atomic_read(&kvm->online_vcpus))
+ return -EINVAL;
+
+ collection = find_collection(its, coll_id);
+ if (collection)
+ return -EEXIST;
+ ret = vgic_its_alloc_collection(its, &collection, coll_id);
+ if (ret)
+ return ret;
+ collection->target_addr = target_addr;
+ return 1;
+}
+
+/**
+ * vgic_its_save_collection_table - Save the collection table into
+ * guest RAM
+ */
+static int vgic_its_save_collection_table(struct vgic_its *its)
+{
+ const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+ struct its_collection *collection;
+ u64 val;
+ gpa_t gpa;
+ size_t max_size, filled = 0;
+ int ret, cte_esz = abi->cte_esz;
+
+ gpa = BASER_ADDRESS(its->baser_coll_table);
+ if (!gpa)
+ return 0;
+
+ max_size = GITS_BASER_NR_PAGES(its->baser_coll_table) * SZ_64K;
+
+ list_for_each_entry(collection, &its->collection_list, coll_list) {
+ ret = vgic_its_save_cte(its, collection, gpa, cte_esz);
+ if (ret)
+ return ret;
+ gpa += cte_esz;
+ filled += cte_esz;
+ }
+
+ if (filled == max_size)
+ return 0;
+
+ /*
+ * table is not fully filled, add a last dummy element
+ * with valid bit unset
+ */
+ val = 0;
+ BUG_ON(cte_esz > sizeof(val));
+ ret = kvm_write_guest(its->dev->kvm, gpa, &val, cte_esz);
+ return ret;
+}
+
+/**
+ * vgic_its_restore_collection_table - reads the collection table
+ * in guest memory and restores the ITS internal state. Requires the
+ * BASER registers to be restored before.
+ */
+static int vgic_its_restore_collection_table(struct vgic_its *its)
+{
+ const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+ int cte_esz = abi->cte_esz;
+ size_t max_size, read = 0;
+ gpa_t gpa;
+ int ret;
+
+ if (!(its->baser_coll_table & GITS_BASER_VALID))
+ return 0;
+
+ gpa = BASER_ADDRESS(its->baser_coll_table);
+
+ max_size = GITS_BASER_NR_PAGES(its->baser_coll_table) * SZ_64K;
+
+ while (read < max_size) {
+ ret = vgic_its_restore_cte(its, gpa, cte_esz);
+ if (ret <= 0)
+ break;
+ gpa += cte_esz;
+ read += cte_esz;
+ }
+ return ret;
+}
+
+/**
+ * vgic_its_save_tables_v0 - Save the ITS tables into guest ARM
+ * according to v0 ABI
+ */
+static int vgic_its_save_tables_v0(struct vgic_its *its)
+{
+ struct kvm *kvm = its->dev->kvm;
+ int ret;
+
+ mutex_lock(&kvm->lock);
+ mutex_lock(&its->its_lock);
+
+ if (!lock_all_vcpus(kvm)) {
+ mutex_unlock(&its->its_lock);
+ mutex_unlock(&kvm->lock);
+ return -EBUSY;
+ }
+
+ ret = vgic_its_save_device_tables(its);
+ if (ret)
+ goto out;
+
+ ret = vgic_its_save_collection_table(its);
+
+out:
+ unlock_all_vcpus(kvm);
+ mutex_unlock(&its->its_lock);
+ mutex_unlock(&kvm->lock);
+ return ret;
+}
+
+/**
+ * vgic_its_restore_tables_v0 - Restore the ITS tables from guest RAM
+ * to internal data structs according to V0 ABI
+ *
+ */
+static int vgic_its_restore_tables_v0(struct vgic_its *its)
+{
+ struct kvm *kvm = its->dev->kvm;
+ int ret;
+
+ mutex_lock(&kvm->lock);
+ mutex_lock(&its->its_lock);
+
+ if (!lock_all_vcpus(kvm)) {
+ mutex_unlock(&its->its_lock);
+ mutex_unlock(&kvm->lock);
+ return -EBUSY;
+ }
+
+ ret = vgic_its_restore_collection_table(its);
+ if (ret)
+ goto out;
+
+ ret = vgic_its_restore_device_tables(its);
+out:
+ unlock_all_vcpus(kvm);
+ mutex_unlock(&its->its_lock);
+ mutex_unlock(&kvm->lock);
+
+ return ret;
+}
+
+static int vgic_its_commit_v0(struct vgic_its *its)
+{
+ const struct vgic_its_abi *abi;
+
+ abi = vgic_its_get_abi(its);
+ its->baser_coll_table &= ~GITS_BASER_ENTRY_SIZE_MASK;
+ its->baser_device_table &= ~GITS_BASER_ENTRY_SIZE_MASK;
+
+ its->baser_coll_table |= (GIC_ENCODE_SZ(abi->cte_esz, 5)
+ << GITS_BASER_ENTRY_SIZE_SHIFT);
+
+ its->baser_device_table |= (GIC_ENCODE_SZ(abi->dte_esz, 5)
+ << GITS_BASER_ENTRY_SIZE_SHIFT);
+ return 0;
+}
+
static int vgic_its_has_attr(struct kvm_device *dev,
struct kvm_device_attr *attr)
{
@@ -1480,8 +2355,14 @@ static int vgic_its_has_attr(struct kvm_device *dev,
switch (attr->attr) {
case KVM_DEV_ARM_VGIC_CTRL_INIT:
return 0;
+ case KVM_DEV_ARM_ITS_SAVE_TABLES:
+ return 0;
+ case KVM_DEV_ARM_ITS_RESTORE_TABLES:
+ return 0;
}
break;
+ case KVM_DEV_ARM_VGIC_GRP_ITS_REGS:
+ return vgic_its_has_attr_regs(dev, attr);
}
return -ENXIO;
}
@@ -1509,18 +2390,30 @@ static int vgic_its_set_attr(struct kvm_device *dev,
if (ret)
return ret;
- its->vgic_its_base = addr;
-
- return 0;
+ return vgic_register_its_iodev(dev->kvm, its, addr);
}
- case KVM_DEV_ARM_VGIC_GRP_CTRL:
+ case KVM_DEV_ARM_VGIC_GRP_CTRL: {
+ const struct vgic_its_abi *abi = vgic_its_get_abi(its);
+
switch (attr->attr) {
case KVM_DEV_ARM_VGIC_CTRL_INIT:
- its->initialized = true;
-
+ /* Nothing to do */
return 0;
+ case KVM_DEV_ARM_ITS_SAVE_TABLES:
+ return abi->save_tables(its);
+ case KVM_DEV_ARM_ITS_RESTORE_TABLES:
+ return abi->restore_tables(its);
}
- break;
+ }
+ case KVM_DEV_ARM_VGIC_GRP_ITS_REGS: {
+ u64 __user *uaddr = (u64 __user *)(long)attr->addr;
+ u64 reg;
+
+ if (get_user(reg, uaddr))
+ return -EFAULT;
+
+ return vgic_its_attr_regs_access(dev, attr, &reg, true);
+ }
}
return -ENXIO;
}
@@ -1541,10 +2434,20 @@ static int vgic_its_get_attr(struct kvm_device *dev,
if (copy_to_user(uaddr, &addr, sizeof(addr)))
return -EFAULT;
break;
+ }
+ case KVM_DEV_ARM_VGIC_GRP_ITS_REGS: {
+ u64 __user *uaddr = (u64 __user *)(long)attr->addr;
+ u64 reg;
+ int ret;
+
+ ret = vgic_its_attr_regs_access(dev, attr, &reg, false);
+ if (ret)
+ return ret;
+ return put_user(reg, uaddr);
+ }
default:
return -ENXIO;
}
- }
return 0;
}
@@ -1563,30 +2466,3 @@ int kvm_vgic_register_its_device(void)
return kvm_register_device_ops(&kvm_arm_vgic_its_ops,
KVM_DEV_TYPE_ARM_VGIC_ITS);
}
-
-/*
- * Registers all ITSes with the kvm_io_bus framework.
- * To follow the existing VGIC initialization sequence, this has to be
- * done as late as possible, just before the first VCPU runs.
- */
-int vgic_register_its_iodevs(struct kvm *kvm)
-{
- struct kvm_device *dev;
- int ret = 0;
-
- list_for_each_entry(dev, &kvm->devices, vm_node) {
- if (dev->ops != &kvm_arm_vgic_its_ops)
- continue;
-
- ret = vgic_register_its_iodev(kvm, dev->private);
- if (ret)
- return ret;
- /*
- * We don't need to care about tearing down previously
- * registered ITSes, as the kvm_io_bus framework removes
- * them for us if the VM gets destroyed.
- */
- }
-
- return ret;
-}
diff --git a/virt/kvm/arm/vgic/vgic-kvm-device.c b/virt/kvm/arm/vgic/vgic-kvm-device.c
index d181d2baee9c..10ae6f394b71 100644
--- a/virt/kvm/arm/vgic/vgic-kvm-device.c
+++ b/virt/kvm/arm/vgic/vgic-kvm-device.c
@@ -37,6 +37,14 @@ int vgic_check_ioaddr(struct kvm *kvm, phys_addr_t *ioaddr,
return 0;
}
+static int vgic_check_type(struct kvm *kvm, int type_needed)
+{
+ if (kvm->arch.vgic.vgic_model != type_needed)
+ return -ENODEV;
+ else
+ return 0;
+}
+
/**
* kvm_vgic_addr - set or get vgic VM base addresses
* @kvm: pointer to the vm struct
@@ -57,40 +65,41 @@ int kvm_vgic_addr(struct kvm *kvm, unsigned long type, u64 *addr, bool write)
{
int r = 0;
struct vgic_dist *vgic = &kvm->arch.vgic;
- int type_needed;
phys_addr_t *addr_ptr, alignment;
mutex_lock(&kvm->lock);
switch (type) {
case KVM_VGIC_V2_ADDR_TYPE_DIST:
- type_needed = KVM_DEV_TYPE_ARM_VGIC_V2;
+ r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
addr_ptr = &vgic->vgic_dist_base;
alignment = SZ_4K;
break;
case KVM_VGIC_V2_ADDR_TYPE_CPU:
- type_needed = KVM_DEV_TYPE_ARM_VGIC_V2;
+ r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
addr_ptr = &vgic->vgic_cpu_base;
alignment = SZ_4K;
break;
case KVM_VGIC_V3_ADDR_TYPE_DIST:
- type_needed = KVM_DEV_TYPE_ARM_VGIC_V3;
+ r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3);
addr_ptr = &vgic->vgic_dist_base;
alignment = SZ_64K;
break;
case KVM_VGIC_V3_ADDR_TYPE_REDIST:
- type_needed = KVM_DEV_TYPE_ARM_VGIC_V3;
+ r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3);
+ if (r)
+ break;
+ if (write) {
+ r = vgic_v3_set_redist_base(kvm, *addr);
+ goto out;
+ }
addr_ptr = &vgic->vgic_redist_base;
- alignment = SZ_64K;
break;
default:
r = -ENODEV;
- goto out;
}
- if (vgic->vgic_model != type_needed) {
- r = -ENODEV;
+ if (r)
goto out;
- }
if (write) {
r = vgic_check_ioaddr(kvm, addr_ptr, *addr, alignment);
@@ -259,13 +268,13 @@ static void unlock_vcpus(struct kvm *kvm, int vcpu_lock_idx)
}
}
-static void unlock_all_vcpus(struct kvm *kvm)
+void unlock_all_vcpus(struct kvm *kvm)
{
unlock_vcpus(kvm, atomic_read(&kvm->online_vcpus) - 1);
}
/* Returns true if all vcpus were locked, false otherwise */
-static bool lock_all_vcpus(struct kvm *kvm)
+bool lock_all_vcpus(struct kvm *kvm)
{
struct kvm_vcpu *tmp_vcpu;
int c;
@@ -580,6 +589,24 @@ static int vgic_v3_set_attr(struct kvm_device *dev,
reg = tmp32;
return vgic_v3_attr_regs_access(dev, attr, &reg, true);
}
+ case KVM_DEV_ARM_VGIC_GRP_CTRL: {
+ int ret;
+
+ switch (attr->attr) {
+ case KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES:
+ mutex_lock(&dev->kvm->lock);
+
+ if (!lock_all_vcpus(dev->kvm)) {
+ mutex_unlock(&dev->kvm->lock);
+ return -EBUSY;
+ }
+ ret = vgic_v3_save_pending_tables(dev->kvm);
+ unlock_all_vcpus(dev->kvm);
+ mutex_unlock(&dev->kvm->lock);
+ return ret;
+ }
+ break;
+ }
}
return -ENXIO;
}
@@ -658,6 +685,8 @@ static int vgic_v3_has_attr(struct kvm_device *dev,
switch (attr->attr) {
case KVM_DEV_ARM_VGIC_CTRL_INIT:
return 0;
+ case KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES:
+ return 0;
}
}
return -ENXIO;
diff --git a/virt/kvm/arm/vgic/vgic-mmio-v3.c b/virt/kvm/arm/vgic/vgic-mmio-v3.c
index 6afb3b484886..99da1a207c19 100644
--- a/virt/kvm/arm/vgic/vgic-mmio-v3.c
+++ b/virt/kvm/arm/vgic/vgic-mmio-v3.c
@@ -556,67 +556,130 @@ unsigned int vgic_v3_init_dist_iodev(struct vgic_io_device *dev)
return SZ_64K;
}
-int vgic_register_redist_iodevs(struct kvm *kvm, gpa_t redist_base_address)
+/**
+ * vgic_register_redist_iodev - register a single redist iodev
+ * @vcpu: The VCPU to which the redistributor belongs
+ *
+ * Register a KVM iodev for this VCPU's redistributor using the address
+ * provided.
+ *
+ * Return 0 on success, -ERRNO otherwise.
+ */
+int vgic_register_redist_iodev(struct kvm_vcpu *vcpu)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct vgic_dist *vgic = &kvm->arch.vgic;
+ struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev;
+ struct vgic_io_device *sgi_dev = &vcpu->arch.vgic_cpu.sgi_iodev;
+ gpa_t rd_base, sgi_base;
+ int ret;
+
+ /*
+ * We may be creating VCPUs before having set the base address for the
+ * redistributor region, in which case we will come back to this
+ * function for all VCPUs when the base address is set. Just return
+ * without doing any work for now.
+ */
+ if (IS_VGIC_ADDR_UNDEF(vgic->vgic_redist_base))
+ return 0;
+
+ if (!vgic_v3_check_base(kvm))
+ return -EINVAL;
+
+ rd_base = vgic->vgic_redist_base + kvm_vcpu_get_idx(vcpu) * SZ_64K * 2;
+ sgi_base = rd_base + SZ_64K;
+
+ kvm_iodevice_init(&rd_dev->dev, &kvm_io_gic_ops);
+ rd_dev->base_addr = rd_base;
+ rd_dev->iodev_type = IODEV_REDIST;
+ rd_dev->regions = vgic_v3_rdbase_registers;
+ rd_dev->nr_regions = ARRAY_SIZE(vgic_v3_rdbase_registers);
+ rd_dev->redist_vcpu = vcpu;
+
+ mutex_lock(&kvm->slots_lock);
+ ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, rd_base,
+ SZ_64K, &rd_dev->dev);
+ mutex_unlock(&kvm->slots_lock);
+
+ if (ret)
+ return ret;
+
+ kvm_iodevice_init(&sgi_dev->dev, &kvm_io_gic_ops);
+ sgi_dev->base_addr = sgi_base;
+ sgi_dev->iodev_type = IODEV_REDIST;
+ sgi_dev->regions = vgic_v3_sgibase_registers;
+ sgi_dev->nr_regions = ARRAY_SIZE(vgic_v3_sgibase_registers);
+ sgi_dev->redist_vcpu = vcpu;
+
+ mutex_lock(&kvm->slots_lock);
+ ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, sgi_base,
+ SZ_64K, &sgi_dev->dev);
+ mutex_unlock(&kvm->slots_lock);
+ if (ret)
+ kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS,
+ &rd_dev->dev);
+
+ return ret;
+}
+
+static void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu)
+{
+ struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev;
+ struct vgic_io_device *sgi_dev = &vcpu->arch.vgic_cpu.sgi_iodev;
+
+ kvm_io_bus_unregister_dev(vcpu->kvm, KVM_MMIO_BUS, &rd_dev->dev);
+ kvm_io_bus_unregister_dev(vcpu->kvm, KVM_MMIO_BUS, &sgi_dev->dev);
+}
+
+static int vgic_register_all_redist_iodevs(struct kvm *kvm)
{
struct kvm_vcpu *vcpu;
int c, ret = 0;
kvm_for_each_vcpu(c, vcpu, kvm) {
- gpa_t rd_base = redist_base_address + c * SZ_64K * 2;
- gpa_t sgi_base = rd_base + SZ_64K;
- struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev;
- struct vgic_io_device *sgi_dev = &vcpu->arch.vgic_cpu.sgi_iodev;
-
- kvm_iodevice_init(&rd_dev->dev, &kvm_io_gic_ops);
- rd_dev->base_addr = rd_base;
- rd_dev->iodev_type = IODEV_REDIST;
- rd_dev->regions = vgic_v3_rdbase_registers;
- rd_dev->nr_regions = ARRAY_SIZE(vgic_v3_rdbase_registers);
- rd_dev->redist_vcpu = vcpu;
-
- mutex_lock(&kvm->slots_lock);
- ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, rd_base,
- SZ_64K, &rd_dev->dev);
- mutex_unlock(&kvm->slots_lock);
-
+ ret = vgic_register_redist_iodev(vcpu);
if (ret)
break;
-
- kvm_iodevice_init(&sgi_dev->dev, &kvm_io_gic_ops);
- sgi_dev->base_addr = sgi_base;
- sgi_dev->iodev_type = IODEV_REDIST;
- sgi_dev->regions = vgic_v3_sgibase_registers;
- sgi_dev->nr_regions = ARRAY_SIZE(vgic_v3_sgibase_registers);
- sgi_dev->redist_vcpu = vcpu;
-
- mutex_lock(&kvm->slots_lock);
- ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, sgi_base,
- SZ_64K, &sgi_dev->dev);
- mutex_unlock(&kvm->slots_lock);
- if (ret) {
- kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS,
- &rd_dev->dev);
- break;
- }
}
if (ret) {
/* The current c failed, so we start with the previous one. */
for (c--; c >= 0; c--) {
- struct vgic_cpu *vgic_cpu;
-
vcpu = kvm_get_vcpu(kvm, c);
- vgic_cpu = &vcpu->arch.vgic_cpu;
- kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS,
- &vgic_cpu->rd_iodev.dev);
- kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS,
- &vgic_cpu->sgi_iodev.dev);
+ vgic_unregister_redist_iodev(vcpu);
}
}
return ret;
}
+int vgic_v3_set_redist_base(struct kvm *kvm, u64 addr)
+{
+ struct vgic_dist *vgic = &kvm->arch.vgic;
+ int ret;
+
+ /* vgic_check_ioaddr makes sure we don't do this twice */
+ ret = vgic_check_ioaddr(kvm, &vgic->vgic_redist_base, addr, SZ_64K);
+ if (ret)
+ return ret;
+
+ vgic->vgic_redist_base = addr;
+ if (!vgic_v3_check_base(kvm)) {
+ vgic->vgic_redist_base = VGIC_ADDR_UNDEF;
+ return -EINVAL;
+ }
+
+ /*
+ * Register iodevs for each existing VCPU. Adding more VCPUs
+ * afterwards will register the iodevs when needed.
+ */
+ ret = vgic_register_all_redist_iodevs(kvm);
+ if (ret)
+ return ret;
+
+ return 0;
+}
+
int vgic_v3_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr)
{
const struct vgic_register_region *region;
diff --git a/virt/kvm/arm/vgic/vgic-mmio.c b/virt/kvm/arm/vgic/vgic-mmio.c
index 2a5db1352722..1c17b2a2f105 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.c
+++ b/virt/kvm/arm/vgic/vgic-mmio.c
@@ -446,13 +446,12 @@ static int match_region(const void *key, const void *elt)
return 0;
}
-/* Find the proper register handler entry given a certain address offset. */
-static const struct vgic_register_region *
-vgic_find_mmio_region(const struct vgic_register_region *region, int nr_regions,
- unsigned int offset)
+const struct vgic_register_region *
+vgic_find_mmio_region(const struct vgic_register_region *regions,
+ int nr_regions, unsigned int offset)
{
- return bsearch((void *)(uintptr_t)offset, region, nr_regions,
- sizeof(region[0]), match_region);
+ return bsearch((void *)(uintptr_t)offset, regions, nr_regions,
+ sizeof(regions[0]), match_region);
}
void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
diff --git a/virt/kvm/arm/vgic/vgic-mmio.h b/virt/kvm/arm/vgic/vgic-mmio.h
index 98bb566b660a..ea4171acdef3 100644
--- a/virt/kvm/arm/vgic/vgic-mmio.h
+++ b/virt/kvm/arm/vgic/vgic-mmio.h
@@ -36,8 +36,13 @@ struct vgic_register_region {
};
unsigned long (*uaccess_read)(struct kvm_vcpu *vcpu, gpa_t addr,
unsigned int len);
- void (*uaccess_write)(struct kvm_vcpu *vcpu, gpa_t addr,
- unsigned int len, unsigned long val);
+ union {
+ void (*uaccess_write)(struct kvm_vcpu *vcpu, gpa_t addr,
+ unsigned int len, unsigned long val);
+ int (*uaccess_its_write)(struct kvm *kvm, struct vgic_its *its,
+ gpa_t addr, unsigned int len,
+ unsigned long val);
+ };
};
extern struct kvm_io_device_ops kvm_io_gic_ops;
@@ -192,4 +197,9 @@ u64 vgic_sanitise_shareability(u64 reg);
u64 vgic_sanitise_field(u64 reg, u64 field_mask, int field_shift,
u64 (*sanitise_fn)(u64));
+/* Find the proper register handler entry given a certain address offset */
+const struct vgic_register_region *
+vgic_find_mmio_region(const struct vgic_register_region *regions,
+ int nr_regions, unsigned int offset);
+
#endif
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
index df1503650300..8fa737edde6f 100644
--- a/virt/kvm/arm/vgic/vgic-v3.c
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -234,19 +234,125 @@ void vgic_v3_enable(struct kvm_vcpu *vcpu)
vgic_v3->vgic_hcr = ICH_HCR_EN;
}
-/* check for overlapping regions and for regions crossing the end of memory */
-static bool vgic_v3_check_base(struct kvm *kvm)
+int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq)
+{
+ struct kvm_vcpu *vcpu;
+ int byte_offset, bit_nr;
+ gpa_t pendbase, ptr;
+ bool status;
+ u8 val;
+ int ret;
+
+retry:
+ vcpu = irq->target_vcpu;
+ if (!vcpu)
+ return 0;
+
+ pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser);
+
+ byte_offset = irq->intid / BITS_PER_BYTE;
+ bit_nr = irq->intid % BITS_PER_BYTE;
+ ptr = pendbase + byte_offset;
+
+ ret = kvm_read_guest(kvm, ptr, &val, 1);
+ if (ret)
+ return ret;
+
+ status = val & (1 << bit_nr);
+
+ spin_lock(&irq->irq_lock);
+ if (irq->target_vcpu != vcpu) {
+ spin_unlock(&irq->irq_lock);
+ goto retry;
+ }
+ irq->pending_latch = status;
+ vgic_queue_irq_unlock(vcpu->kvm, irq);
+
+ if (status) {
+ /* clear consumed data */
+ val &= ~(1 << bit_nr);
+ ret = kvm_write_guest(kvm, ptr, &val, 1);
+ if (ret)
+ return ret;
+ }
+ return 0;
+}
+
+/**
+ * vgic_its_save_pending_tables - Save the pending tables into guest RAM
+ * kvm lock and all vcpu lock must be held
+ */
+int vgic_v3_save_pending_tables(struct kvm *kvm)
+{
+ struct vgic_dist *dist = &kvm->arch.vgic;
+ int last_byte_offset = -1;
+ struct vgic_irq *irq;
+ int ret;
+
+ list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
+ int byte_offset, bit_nr;
+ struct kvm_vcpu *vcpu;
+ gpa_t pendbase, ptr;
+ bool stored;
+ u8 val;
+
+ vcpu = irq->target_vcpu;
+ if (!vcpu)
+ continue;
+
+ pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser);
+
+ byte_offset = irq->intid / BITS_PER_BYTE;
+ bit_nr = irq->intid % BITS_PER_BYTE;
+ ptr = pendbase + byte_offset;
+
+ if (byte_offset != last_byte_offset) {
+ ret = kvm_read_guest(kvm, ptr, &val, 1);
+ if (ret)
+ return ret;
+ last_byte_offset = byte_offset;
+ }
+
+ stored = val & (1U << bit_nr);
+ if (stored == irq->pending_latch)
+ continue;
+
+ if (irq->pending_latch)
+ val |= 1 << bit_nr;
+ else
+ val &= ~(1 << bit_nr);
+
+ ret = kvm_write_guest(kvm, ptr, &val, 1);
+ if (ret)
+ return ret;
+ }
+ return 0;
+}
+
+/*
+ * Check for overlapping regions and for regions crossing the end of memory
+ * for base addresses which have already been set.
+ */
+bool vgic_v3_check_base(struct kvm *kvm)
{
struct vgic_dist *d = &kvm->arch.vgic;
gpa_t redist_size = KVM_VGIC_V3_REDIST_SIZE;
redist_size *= atomic_read(&kvm->online_vcpus);
- if (d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE < d->vgic_dist_base)
+ if (!IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) &&
+ d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE < d->vgic_dist_base)
return false;
- if (d->vgic_redist_base + redist_size < d->vgic_redist_base)
+
+ if (!IS_VGIC_ADDR_UNDEF(d->vgic_redist_base) &&
+ d->vgic_redist_base + redist_size < d->vgic_redist_base)
return false;
+ /* Both base addresses must be set to check if they overlap */
+ if (IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) ||
+ IS_VGIC_ADDR_UNDEF(d->vgic_redist_base))
+ return true;
+
if (d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE <= d->vgic_redist_base)
return true;
if (d->vgic_redist_base + redist_size <= d->vgic_dist_base)
@@ -291,20 +397,6 @@ int vgic_v3_map_resources(struct kvm *kvm)
goto out;
}
- ret = vgic_register_redist_iodevs(kvm, dist->vgic_redist_base);
- if (ret) {
- kvm_err("Unable to register VGICv3 redist MMIO regions\n");
- goto out;
- }
-
- if (vgic_has_its(kvm)) {
- ret = vgic_register_its_iodevs(kvm);
- if (ret) {
- kvm_err("Unable to register VGIC ITS MMIO regions\n");
- goto out;
- }
- }
-
dist->ready = true;
out:
diff --git a/virt/kvm/arm/vgic/vgic.c b/virt/kvm/arm/vgic/vgic.c
index 4346bc7d08dc..83b24d20ff8f 100644
--- a/virt/kvm/arm/vgic/vgic.c
+++ b/virt/kvm/arm/vgic/vgic.c
@@ -21,7 +21,7 @@
#include "vgic.h"
#define CREATE_TRACE_POINTS
-#include "../trace.h"
+#include "trace.h"
#ifdef CONFIG_DEBUG_SPINLOCK
#define DEBUG_SPINLOCK_BUG_ON(p) BUG_ON(p)
diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h
index 799fd651b260..da83e4caa272 100644
--- a/virt/kvm/arm/vgic/vgic.h
+++ b/virt/kvm/arm/vgic/vgic.h
@@ -73,6 +73,29 @@
KVM_REG_ARM_VGIC_SYSREG_CRM_MASK | \
KVM_REG_ARM_VGIC_SYSREG_OP2_MASK)
+/*
+ * As per Documentation/virtual/kvm/devices/arm-vgic-its.txt,
+ * below macros are defined for ITS table entry encoding.
+ */
+#define KVM_ITS_CTE_VALID_SHIFT 63
+#define KVM_ITS_CTE_VALID_MASK BIT_ULL(63)
+#define KVM_ITS_CTE_RDBASE_SHIFT 16
+#define KVM_ITS_CTE_ICID_MASK GENMASK_ULL(15, 0)
+#define KVM_ITS_ITE_NEXT_SHIFT 48
+#define KVM_ITS_ITE_PINTID_SHIFT 16
+#define KVM_ITS_ITE_PINTID_MASK GENMASK_ULL(47, 16)
+#define KVM_ITS_ITE_ICID_MASK GENMASK_ULL(15, 0)
+#define KVM_ITS_DTE_VALID_SHIFT 63
+#define KVM_ITS_DTE_VALID_MASK BIT_ULL(63)
+#define KVM_ITS_DTE_NEXT_SHIFT 49
+#define KVM_ITS_DTE_NEXT_MASK GENMASK_ULL(62, 49)
+#define KVM_ITS_DTE_ITTADDR_SHIFT 5
+#define KVM_ITS_DTE_ITTADDR_MASK GENMASK_ULL(48, 5)
+#define KVM_ITS_DTE_SIZE_MASK GENMASK_ULL(4, 0)
+#define KVM_ITS_L1E_VALID_MASK BIT_ULL(63)
+/* we only support 64 kB translation table page size */
+#define KVM_ITS_L1E_ADDR_MASK GENMASK_ULL(51, 16)
+
static inline bool irq_is_pending(struct vgic_irq *irq)
{
if (irq->config == VGIC_CONFIG_EDGE)
@@ -157,12 +180,15 @@ void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr);
void vgic_v3_enable(struct kvm_vcpu *vcpu);
int vgic_v3_probe(const struct gic_kvm_info *info);
int vgic_v3_map_resources(struct kvm *kvm);
-int vgic_register_redist_iodevs(struct kvm *kvm, gpa_t dist_base_address);
+int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq);
+int vgic_v3_save_pending_tables(struct kvm *kvm);
+int vgic_v3_set_redist_base(struct kvm *kvm, u64 addr);
+int vgic_register_redist_iodev(struct kvm_vcpu *vcpu);
+bool vgic_v3_check_base(struct kvm *kvm);
void vgic_v3_load(struct kvm_vcpu *vcpu);
void vgic_v3_put(struct kvm_vcpu *vcpu);
-int vgic_register_its_iodevs(struct kvm *kvm);
bool vgic_has_its(struct kvm *kvm);
int kvm_vgic_register_its_device(void);
void vgic_enable_lpis(struct kvm_vcpu *vcpu);
@@ -187,4 +213,7 @@ int vgic_init(struct kvm *kvm);
int vgic_debug_init(struct kvm *kvm);
int vgic_debug_destroy(struct kvm *kvm);
+bool lock_all_vcpus(struct kvm *kvm);
+void unlock_all_vcpus(struct kvm *kvm);
+
#endif
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index b3d151ee2a67..f0fe9d02f6bb 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2836,10 +2836,6 @@ static struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = {
[KVM_DEV_TYPE_FSL_MPIC_20] = &kvm_mpic_ops,
[KVM_DEV_TYPE_FSL_MPIC_42] = &kvm_mpic_ops,
#endif
-
-#ifdef CONFIG_KVM_XICS
- [KVM_DEV_TYPE_XICS] = &kvm_xics_ops,
-#endif
};
int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type)
@@ -3715,7 +3711,7 @@ static const struct file_operations vm_stat_get_per_vm_fops = {
.release = kvm_debugfs_release,
.read = simple_attr_read,
.write = simple_attr_write,
- .llseek = generic_file_llseek,
+ .llseek = no_llseek,
};
static int vcpu_stat_get_per_vm(void *data, u64 *val)
@@ -3760,7 +3756,7 @@ static const struct file_operations vcpu_stat_get_per_vm_fops = {
.release = kvm_debugfs_release,
.read = simple_attr_read,
.write = simple_attr_write,
- .llseek = generic_file_llseek,
+ .llseek = no_llseek,
};
static const struct file_operations *stat_fops_per_vm[] = {