Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull second round of KVM changes from Paolo Bonzini:
 "Here are the PPC and ARM changes for KVM, which I separated because
  they had small conflicts (respectively within KVM documentation, and
  with 3.16-rc changes).  Since they were all within the subsystem, I
  took care of them.

  Stephen Rothwell reported some snags in PPC builds, but they are all
  fixed now; the latest linux-next report was clean.

  New features for ARM include:
   - KVM VGIC v2 emulation on GICv3 hardware
   - Big-Endian support for arm/arm64 (guest and host)
   - Debug Architecture support for arm64 (arm32 is on Christoffer's todo list)

  And for PPC:
   - Book3S: Good number of LE host fixes, enable HV on LE
   - Book3S HV: Add in-guest debug support

  This release drops support for KVM on the PPC440.  As a result, the
  PPC merge removes more lines than it adds.  :)

  I also included an x86 change, since Davidlohr tied it to an
  independent bug report and the reporter quickly provided a Tested-by;
  there was no reason to wait for -rc2"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (122 commits)
  KVM: Move more code under CONFIG_HAVE_KVM_IRQFD
  KVM: nVMX: fix "acknowledge interrupt on exit" when APICv is in use
  KVM: nVMX: Fix nested vmexit ack intr before load vmcs01
  KVM: PPC: Enable IRQFD support for the XICS interrupt controller
  KVM: Give IRQFD its own separate enabling Kconfig option
  KVM: Move irq notifier implementation into eventfd.c
  KVM: Move all accesses to kvm::irq_routing into irqchip.c
  KVM: irqchip: Provide and use accessors for irq routing table
  KVM: Don't keep reference to irq routing table in irqfd struct
  KVM: PPC: drop duplicate tracepoint
  arm64: KVM: fix 64bit CP15 VM access for 32bit guests
  KVM: arm64: GICv3: mandate page-aligned GICV region
  arm64: KVM: GICv3: move system register access to msr_s/mrs_s
  KVM: PPC: PR: Handle FSCR feature deselects
  KVM: PPC: HV: Remove generic instruction emulation
  KVM: PPC: BOOKEHV: rename e500hv_spr to bookehv_spr
  KVM: PPC: Remove DCR handling
  KVM: PPC: Expose helper functions for data/inst faults
  KVM: PPC: Separate loadstore emulation from priv emulation
  KVM: PPC: Handle magic page in kvmppc_ld/st
  ...

Documentation/arm64/booting.txt

@@ -168,6 +168,14 @@ Before jumping into the kernel, the following conditions must be met:
   the kernel image will be entered must be initialised by software at a
   higher exception level to prevent execution in an UNKNOWN state.
 
+  For systems with a GICv3 interrupt controller:
+  - If EL3 is present:
+    ICC_SRE_EL3.Enable (bit 3) must be initialiased to 0b1.
+    ICC_SRE_EL3.SRE (bit 0) must be initialised to 0b1.
+  - If the kernel is entered at EL1:
+    ICC.SRE_EL2.Enable (bit 3) must be initialised to 0b1
+    ICC_SRE_EL2.SRE (bit 0) must be initialised to 0b1.
+
 The requirements described above for CPU mode, caches, MMUs, architected
 timers, coherency and system registers apply to all CPUs.  All CPUs must
 enter the kernel in the same exception level.

Documentation/devicetree/bindings/arm/gic-v3.txt

@@ -0,0 +1,79 @@
+* ARM Generic Interrupt Controller, version 3
+
+AArch64 SMP cores are often associated with a GICv3, providing Private
+Peripheral Interrupts (PPI), Shared Peripheral Interrupts (SPI),
+Software Generated Interrupts (SGI), and Locality-specific Peripheral
+Interrupts (LPI).
+
+Main node required properties:
+
+- compatible : should at least contain  "arm,gic-v3".
+- interrupt-controller : Identifies the node as an interrupt controller
+- #interrupt-cells : Specifies the number of cells needed to encode an
+  interrupt source. Must be a single cell with a value of at least 3.
+
+  The 1st cell is the interrupt type; 0 for SPI interrupts, 1 for PPI
+  interrupts. Other values are reserved for future use.
+
+  The 2nd cell contains the interrupt number for the interrupt type.
+  SPI interrupts are in the range [0-987]. PPI interrupts are in the
+  range [0-15].
+
+  The 3rd cell is the flags, encoded as follows:
+	bits[3:0] trigger type and level flags.
+		1 = edge triggered
+		4 = level triggered
+
+  Cells 4 and beyond are reserved for future use. When the 1st cell
+  has a value of 0 or 1, cells 4 and beyond act as padding, and may be
+  ignored. It is recommended that padding cells have a value of 0.
+
+- reg : Specifies base physical address(s) and size of the GIC
+  registers, in the following order:
+  - GIC Distributor interface (GICD)
+  - GIC Redistributors (GICR), one range per redistributor region
+  - GIC CPU interface (GICC)
+  - GIC Hypervisor interface (GICH)
+  - GIC Virtual CPU interface (GICV)
+
+  GICC, GICH and GICV are optional.
+
+- interrupts : Interrupt source of the VGIC maintenance interrupt.
+
+Optional
+
+- redistributor-stride : If using padding pages, specifies the stride
+  of consecutive redistributors. Must be a multiple of 64kB.
+
+- #redistributor-regions: The number of independent contiguous regions
+  occupied by the redistributors. Required if more than one such
+  region is present.
+
+Examples:
+
+	gic: interrupt-controller@2cf00000 {
+		compatible = "arm,gic-v3";
+		#interrupt-cells = <3>;
+		interrupt-controller;
+		reg = <0x0 0x2f000000 0 0x10000>,	// GICD
+		      <0x0 0x2f100000 0 0x200000>,	// GICR
+		      <0x0 0x2c000000 0 0x2000>,	// GICC
+		      <0x0 0x2c010000 0 0x2000>,	// GICH
+		      <0x0 0x2c020000 0 0x2000>;	// GICV
+		interrupts = <1 9 4>;
+	};
+
+	gic: interrupt-controller@2c010000 {
+		compatible = "arm,gic-v3";
+		#interrupt-cells = <3>;
+		interrupt-controller;
+		redistributor-stride = <0x0 0x40000>;	// 256kB stride
+		#redistributor-regions = <2>;
+		reg = <0x0 0x2c010000 0 0x10000>,	// GICD
+		      <0x0 0x2d000000 0 0x800000>,	// GICR 1: CPUs 0-31
+		      <0x0 0x2e000000 0 0x800000>;	// GICR 2: CPUs 32-63
+		      <0x0 0x2c040000 0 0x2000>,	// GICC
+		      <0x0 0x2c060000 0 0x2000>,	// GICH
+		      <0x0 0x2c080000 0 0x2000>;	// GICV
+		interrupts = <1 9 4>;
+	};

Documentation/powerpc/00-INDEX

@@ -17,8 +17,6 @@ firmware-assisted-dump.txt
 	- Documentation on the firmware assisted dump mechanism "fadump".
 hvcs.txt
 	- IBM "Hypervisor Virtual Console Server" Installation Guide
-kvm_440.txt
-	- Various notes on the implementation of KVM for PowerPC 440.
 mpc52xx.txt
 	- Linux 2.6.x on MPC52xx family
 pmu-ebb.txt

Documentation/virtual/kvm/api.txt

@@ -148,9 +148,9 @@ of banks, as set via the KVM_X86_SETUP_MCE ioctl.
 
 4.4 KVM_CHECK_EXTENSION
 
-Capability: basic
+Capability: basic, KVM_CAP_CHECK_EXTENSION_VM for vm ioctl
 Architectures: all
-Type: system ioctl
+Type: system ioctl, vm ioctl
 Parameters: extension identifier (KVM_CAP_*)
 Returns: 0 if unsupported; 1 (or some other positive integer) if supported
 
@@ -160,6 +160,9 @@ receives an integer that describes the extension availability.
 Generally 0 means no and 1 means yes, but some extensions may report
 additional information in the integer return value.
 
+Based on their initialization different VMs may have different capabilities.
+It is thus encouraged to use the vm ioctl to query for capabilities (available
+with KVM_CAP_CHECK_EXTENSION_VM on the vm fd)
 
 4.5 KVM_GET_VCPU_MMAP_SIZE
 
@@ -1892,7 +1895,8 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_PID               | 64
   PPC   | KVM_REG_PPC_ACOP              | 64
   PPC   | KVM_REG_PPC_VRSAVE            | 32
-  PPC   | KVM_REG_PPC_LPCR              | 64
+  PPC   | KVM_REG_PPC_LPCR              | 32
+  PPC   | KVM_REG_PPC_LPCR_64           | 64
   PPC   | KVM_REG_PPC_PPR               | 64
   PPC   | KVM_REG_PPC_ARCH_COMPAT       | 32
   PPC   | KVM_REG_PPC_DABRX             | 32
@@ -2677,8 +2681,8 @@ The 'data' member contains, in its first 'len' bytes, the value as it would
 appear if the VCPU performed a load or store of the appropriate width directly
 to the byte array.
 
-NOTE: For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_DCR,
-      KVM_EXIT_PAPR and KVM_EXIT_EPR the corresponding
+NOTE: For KVM_EXIT_IO, KVM_EXIT_MMIO, KVM_EXIT_OSI, KVM_EXIT_PAPR and
+      KVM_EXIT_EPR the corresponding
 operations are complete (and guest state is consistent) only after userspace
 has re-entered the kernel with KVM_RUN.  The kernel side will first finish
 incomplete operations and then check for pending signals.  Userspace
@@ -2749,7 +2753,7 @@ Principles of Operation Book in the Chapter for Dynamic Address Translation
 			__u8  is_write;
 		} dcr;
 
-powerpc specific.
+Deprecated - was used for 440 KVM.
 
 		/* KVM_EXIT_OSI */
 		struct {
@@ -2931,8 +2935,8 @@ The fields in each entry are defined as follows:
          this function/index combination
 
 
-6. Capabilities that can be enabled
------------------------------------
+6. Capabilities that can be enabled on vCPUs
+--------------------------------------------
 
 There are certain capabilities that change the behavior of the virtual CPU or
 the virtual machine when enabled. To enable them, please see section 4.37.
@@ -3091,3 +3095,43 @@ Parameters: none
 
 This capability enables the in-kernel irqchip for s390. Please refer to
 "4.24 KVM_CREATE_IRQCHIP" for details.
+
+7. Capabilities that can be enabled on VMs
+------------------------------------------
+
+There are certain capabilities that change the behavior of the virtual
+machine when enabled. To enable them, please see section 4.37. Below
+you can find a list of capabilities and what their effect on the VM
+is when enabling them.
+
+The following information is provided along with the description:
+
+  Architectures: which instruction set architectures provide this ioctl.
+      x86 includes both i386 and x86_64.
+
+  Parameters: what parameters are accepted by the capability.
+
+  Returns: the return value.  General error numbers (EBADF, ENOMEM, EINVAL)
+      are not detailed, but errors with specific meanings are.
+
+
+7.1 KVM_CAP_PPC_ENABLE_HCALL
+
+Architectures: ppc
+Parameters: args[0] is the sPAPR hcall number
+	    args[1] is 0 to disable, 1 to enable in-kernel handling
+
+This capability controls whether individual sPAPR hypercalls (hcalls)
+get handled by the kernel or not.  Enabling or disabling in-kernel
+handling of an hcall is effective across the VM.  On creation, an
+initial set of hcalls are enabled for in-kernel handling, which
+consists of those hcalls for which in-kernel handlers were implemented
+before this capability was implemented.  If disabled, the kernel will
+not to attempt to handle the hcall, but will always exit to userspace
+to handle it.  Note that it may not make sense to enable some and
+disable others of a group of related hcalls, but KVM does not prevent
+userspace from doing that.
+
+If the hcall number specified is not one that has an in-kernel
+implementation, the KVM_ENABLE_CAP ioctl will fail with an EINVAL
+error.

arch/arm/include/asm/kvm_asm.h

@@ -61,6 +61,24 @@
 #define ARM_EXCEPTION_FIQ	  6
 #define ARM_EXCEPTION_HVC	  7
 
+/*
+ * The rr_lo_hi macro swaps a pair of registers depending on
+ * current endianness. It is used in conjunction with ldrd and strd
+ * instructions that load/store a 64-bit value from/to memory to/from
+ * a pair of registers which are used with the mrrc and mcrr instructions.
+ * If used with the ldrd/strd instructions, the a1 parameter is the first
+ * source/destination register and the a2 parameter is the second
+ * source/destination register. Note that the ldrd/strd instructions
+ * already swap the bytes within the words correctly according to the
+ * endianness setting, but the order of the registers need to be effectively
+ * swapped when used with the mrrc/mcrr instructions.
+ */
+#ifdef CONFIG_CPU_ENDIAN_BE8
+#define rr_lo_hi(a1, a2) a2, a1
+#else
+#define rr_lo_hi(a1, a2) a1, a2
+#endif
+
 #ifndef __ASSEMBLY__
 struct kvm;
 struct kvm_vcpu;

arch/arm/include/asm/kvm_emulate.h

@@ -185,9 +185,16 @@ static inline unsigned long vcpu_data_guest_to_host(struct kvm_vcpu *vcpu,
 		default:
 			return be32_to_cpu(data);
 		}
+	} else {
+		switch (len) {
+		case 1:
+			return data & 0xff;
+		case 2:
+			return le16_to_cpu(data & 0xffff);
+		default:
+			return le32_to_cpu(data);
+		}
 	}
-
-	return data;		/* Leave LE untouched */
 }
 
 static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu,
@@ -203,9 +210,16 @@ static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu,
 		default:
 			return cpu_to_be32(data);
 		}
+	} else {
+		switch (len) {
+		case 1:
+			return data & 0xff;
+		case 2:
+			return cpu_to_le16(data & 0xffff);
+		default:
+			return cpu_to_le32(data);
+		}
 	}
-
-	return data;		/* Leave LE untouched */
 }
 
 #endif /* __ARM_KVM_EMULATE_H__ */

arch/arm/include/asm/kvm_host.h

@@ -225,10 +225,12 @@ static inline int kvm_arch_dev_ioctl_check_extension(long ext)
 	return 0;
 }
 
+static inline void vgic_arch_setup(const struct vgic_params *vgic)
+{
+	BUG_ON(vgic->type != VGIC_V2);
+}
+
 int kvm_perf_init(void);
 int kvm_perf_teardown(void);
 
-u64 kvm_arm_timer_get_reg(struct kvm_vcpu *, u64 regid);
-int kvm_arm_timer_set_reg(struct kvm_vcpu *, u64 regid, u64 value);
-
 #endif /* __ARM_KVM_HOST_H__ */

arch/arm/include/asm/kvm_mmu.h

@@ -127,6 +127,18 @@ static inline void kvm_set_s2pmd_writable(pmd_t *pmd)
 	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
 })
 
+static inline bool kvm_page_empty(void *ptr)
+{
+	struct page *ptr_page = virt_to_page(ptr);
+	return page_count(ptr_page) == 1;
+}
+
+
+#define kvm_pte_table_empty(ptep) kvm_page_empty(ptep)
+#define kvm_pmd_table_empty(pmdp) kvm_page_empty(pmdp)
+#define kvm_pud_table_empty(pudp) (0)
+
+
 struct kvm;
 
 #define kvm_flush_dcache_to_poc(a,l)	__cpuc_flush_dcache_area((a), (l))

arch/arm/kernel/asm-offsets.c

@@ -182,13 +182,13 @@ int main(void)
   DEFINE(VCPU_HYP_PC,		offsetof(struct kvm_vcpu, arch.fault.hyp_pc));
 #ifdef CONFIG_KVM_ARM_VGIC
   DEFINE(VCPU_VGIC_CPU,		offsetof(struct kvm_vcpu, arch.vgic_cpu));
-  DEFINE(VGIC_CPU_HCR,		offsetof(struct vgic_cpu, vgic_hcr));
-  DEFINE(VGIC_CPU_VMCR,		offsetof(struct vgic_cpu, vgic_vmcr));
-  DEFINE(VGIC_CPU_MISR,		offsetof(struct vgic_cpu, vgic_misr));
-  DEFINE(VGIC_CPU_EISR,		offsetof(struct vgic_cpu, vgic_eisr));
-  DEFINE(VGIC_CPU_ELRSR,	offsetof(struct vgic_cpu, vgic_elrsr));
-  DEFINE(VGIC_CPU_APR,		offsetof(struct vgic_cpu, vgic_apr));
-  DEFINE(VGIC_CPU_LR,		offsetof(struct vgic_cpu, vgic_lr));
+  DEFINE(VGIC_V2_CPU_HCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_hcr));
+  DEFINE(VGIC_V2_CPU_VMCR,	offsetof(struct vgic_cpu, vgic_v2.vgic_vmcr));
+  DEFINE(VGIC_V2_CPU_MISR,	offsetof(struct vgic_cpu, vgic_v2.vgic_misr));
+  DEFINE(VGIC_V2_CPU_EISR,	offsetof(struct vgic_cpu, vgic_v2.vgic_eisr));
+  DEFINE(VGIC_V2_CPU_ELRSR,	offsetof(struct vgic_cpu, vgic_v2.vgic_elrsr));
+  DEFINE(VGIC_V2_CPU_APR,	offsetof(struct vgic_cpu, vgic_v2.vgic_apr));
+  DEFINE(VGIC_V2_CPU_LR,	offsetof(struct vgic_cpu, vgic_v2.vgic_lr));
   DEFINE(VGIC_CPU_NR_LR,	offsetof(struct vgic_cpu, nr_lr));
 #ifdef CONFIG_KVM_ARM_TIMER
   DEFINE(VCPU_TIMER_CNTV_CTL,	offsetof(struct kvm_vcpu, arch.timer_cpu.cntv_ctl));

arch/arm/kernel/hyp-stub.S

@@ -134,9 +134,7 @@ ENTRY(__hyp_stub_install_secondary)
 	mcr	p15, 4, r7, c1, c1, 3	@ HSTR
 
 THUMB(	orr	r7, #(1 << 30)	)	@ HSCTLR.TE
-#ifdef CONFIG_CPU_BIG_ENDIAN
-	orr	r7, #(1 << 9)		@ HSCTLR.EE
-#endif
+ARM_BE8(orr	r7, r7, #(1 << 25))     @ HSCTLR.EE
 	mcr	p15, 4, r7, c1, c0, 0	@ HSCTLR
 
 	mrc	p15, 4, r7, c1, c1, 1	@ HDCR

arch/arm/kvm/Kconfig

@@ -23,7 +23,7 @@ config KVM
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select KVM_MMIO
 	select KVM_ARM_HOST
-	depends on ARM_VIRT_EXT && ARM_LPAE && !CPU_BIG_ENDIAN
+	depends on ARM_VIRT_EXT && ARM_LPAE
 	---help---
 	  Support hosting virtualized guest machines. You will also
 	  need to select one or more of the processor modules below.

arch/arm/kvm/Makefile

@@ -21,4 +21,5 @@ 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
 obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic.o
+obj-$(CONFIG_KVM_ARM_VGIC) += $(KVM)/arm/vgic-v2.o
 obj-$(CONFIG_KVM_ARM_TIMER) += $(KVM)/arm/arch_timer.o