KVM: PPC: e500: MMU API

This implements a shared-memory API for giving host userspace access to
the guest's TLB.
Signed-off-by: Scott Wood <scottwood@freescale.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>

Documentation/virtual/kvm/api.txt

@@ -1409,6 +1409,38 @@ The following flags are defined:
 If datamatch flag is set, the event will be signaled only if the written value
 to the registered address is equal to datamatch in struct kvm_ioeventfd.
 
+4.59 KVM_DIRTY_TLB
+
+Capability: KVM_CAP_SW_TLB
+Architectures: ppc
+Type: vcpu ioctl
+Parameters: struct kvm_dirty_tlb (in)
+Returns: 0 on success, -1 on error
+
+struct kvm_dirty_tlb {
+	__u64 bitmap;
+	__u32 num_dirty;
+};
+
+This must be called whenever userspace has changed an entry in the shared
+TLB, prior to calling KVM_RUN on the associated vcpu.
+
+The "bitmap" field is the userspace address of an array.  This array
+consists of a number of bits, equal to the total number of TLB entries as
+determined by the last successful call to KVM_CONFIG_TLB, rounded up to the
+nearest multiple of 64.
+
+Each bit corresponds to one TLB entry, ordered the same as in the shared TLB
+array.
+
+The array is little-endian: the bit 0 is the least significant bit of the
+first byte, bit 8 is the least significant bit of the second byte, etc.
+This avoids any complications with differing word sizes.
+
+The "num_dirty" field is a performance hint for KVM to determine whether it
+should skip processing the bitmap and just invalidate everything.  It must
+be set to the number of set bits in the bitmap.
+
 4.62 KVM_CREATE_SPAPR_TCE
 
 Capability: KVM_CAP_SPAPR_TCE
@@ -1842,3 +1874,45 @@ HTAB address part of SDR1 contains an HVA instead of a GPA, as PAPR keeps the
 HTAB invisible to the guest.
 
 When this capability is enabled, KVM_EXIT_PAPR_HCALL can occur.
+
+6.3 KVM_CAP_SW_TLB
+
+Architectures: ppc
+Parameters: args[0] is the address of a struct kvm_config_tlb
+Returns: 0 on success; -1 on error
+
+struct kvm_config_tlb {
+	__u64 params;
+	__u64 array;
+	__u32 mmu_type;
+	__u32 array_len;
+};
+
+Configures the virtual CPU's TLB array, establishing a shared memory area
+between userspace and KVM.  The "params" and "array" fields are userspace
+addresses of mmu-type-specific data structures.  The "array_len" field is an
+safety mechanism, and should be set to the size in bytes of the memory that
+userspace has reserved for the array.  It must be at least the size dictated
+by "mmu_type" and "params".
+
+While KVM_RUN is active, the shared region is under control of KVM.  Its
+contents are undefined, and any modification by userspace results in
+boundedly undefined behavior.
+
+On return from KVM_RUN, the shared region will reflect the current state of
+the guest's TLB.  If userspace makes any changes, it must call KVM_DIRTY_TLB
+to tell KVM which entries have been changed, prior to calling KVM_RUN again
+on this vcpu.
+
+For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV:
+ - The "params" field is of type "struct kvm_book3e_206_tlb_params".
+ - The "array" field points to an array of type "struct
+   kvm_book3e_206_tlb_entry".
+ - The array consists of all entries in the first TLB, followed by all
+   entries in the second TLB.
+ - Within a TLB, entries are ordered first by increasing set number.  Within a
+   set, entries are ordered by way (increasing ESEL).
+ - The hash for determining set number in TLB0 is: (MAS2 >> 12) & (num_sets - 1)
+   where "num_sets" is the tlb_sizes[] value divided by the tlb_ways[] value.
+ - The tsize field of mas1 shall be set to 4K on TLB0, even though the
+   hardware ignores this value for TLB0.

arch/powerpc/include/asm/kvm.h

@@ -296,4 +296,39 @@ struct kvm_allocate_rma {
 	__u64 rma_size;
 };
 
+struct kvm_book3e_206_tlb_entry {
+	__u32 mas8;
+	__u32 mas1;
+	__u64 mas2;
+	__u64 mas7_3;
+};
+
+struct kvm_book3e_206_tlb_params {
+	/*
+	 * For mmu types KVM_MMU_FSL_BOOKE_NOHV and KVM_MMU_FSL_BOOKE_HV:
+	 *
+	 * - The number of ways of TLB0 must be a power of two between 2 and
+	 *   16.
+	 * - TLB1 must be fully associative.
+	 * - The size of TLB0 must be a multiple of the number of ways, and
+	 *   the number of sets must be a power of two.
+	 * - The size of TLB1 may not exceed 64 entries.
+	 * - TLB0 supports 4 KiB pages.
+	 * - The page sizes supported by TLB1 are as indicated by
+	 *   TLB1CFG (if MMUCFG[MAVN] = 0) or TLB1PS (if MMUCFG[MAVN] = 1)
+	 *   as returned by KVM_GET_SREGS.
+	 * - TLB2 and TLB3 are reserved, and their entries in tlb_sizes[]
+	 *   and tlb_ways[] must be zero.
+	 *
+	 * tlb_ways[n] = tlb_sizes[n] means the array is fully associative.
+	 *
+	 * KVM will adjust TLBnCFG based on the sizes configured here,
+	 * though arrays greater than 2048 entries will have TLBnCFG[NENTRY]
+	 * set to zero.
+	 */
+	__u32 tlb_sizes[4];
+	__u32 tlb_ways[4];
+	__u32 reserved[8];
+};
+
 #endif /* __LINUX_KVM_POWERPC_H */

arch/powerpc/include/asm/kvm_e500.h

@@ -22,13 +22,6 @@
 #define E500_PID_NUM   3
 #define E500_TLB_NUM   2
 
-struct tlbe{
-	u32 mas1;
-	u32 mas2;
-	u32 mas3;
-	u32 mas7;
-};
-
 #define E500_TLB_VALID 1
 #define E500_TLB_DIRTY 2
 
@@ -48,13 +41,17 @@ struct kvmppc_e500_tlb_params {
 };
 
 struct kvmppc_vcpu_e500 {
-	/* Unmodified copy of the guest's TLB. */
-	struct tlbe *gtlb_arch[E500_TLB_NUM];
+	/* Unmodified copy of the guest's TLB -- shared with host userspace. */
+	struct kvm_book3e_206_tlb_entry *gtlb_arch;
+
+	/* Starting entry number in gtlb_arch[] */
+	int gtlb_offset[E500_TLB_NUM];
 
 	/* KVM internal information associated with each guest TLB entry */
 	struct tlbe_priv *gtlb_priv[E500_TLB_NUM];
 
-	unsigned int gtlb_size[E500_TLB_NUM];
+	struct kvmppc_e500_tlb_params gtlb_params[E500_TLB_NUM];
+
 	unsigned int gtlb_nv[E500_TLB_NUM];
 
 	/*
@@ -68,7 +65,6 @@ struct kvmppc_vcpu_e500 {
 	 * and back, and our host TLB entries got evicted).
 	 */
 	struct tlbe_ref *tlb_refs[E500_TLB_NUM];
-
 	unsigned int host_tlb1_nv;
 
 	u32 host_pid[E500_PID_NUM];
@@ -78,11 +74,10 @@ struct kvmppc_vcpu_e500 {
 	u32 mas0;
 	u32 mas1;
 	u32 mas2;
-	u32 mas3;
+	u64 mas7_3;
 	u32 mas4;
 	u32 mas5;
 	u32 mas6;
-	u32 mas7;
 
 	/* vcpu id table */
 	struct vcpu_id_table *idt;
@@ -95,6 +90,9 @@ struct kvmppc_vcpu_e500 {
 	u32 tlb1cfg;
 	u64 mcar;
 
+	struct page **shared_tlb_pages;
+	int num_shared_tlb_pages;
+
 	struct kvm_vcpu vcpu;
 };
 

arch/powerpc/include/asm/kvm_ppc.h

@@ -193,4 +193,9 @@ static inline void kvm_rma_init(void)
 {}
 #endif
 
+int kvm_vcpu_ioctl_config_tlb(struct kvm_vcpu *vcpu,
+			      struct kvm_config_tlb *cfg);
+int kvm_vcpu_ioctl_dirty_tlb(struct kvm_vcpu *vcpu,
+			     struct kvm_dirty_tlb *cfg);
+
 #endif /* __POWERPC_KVM_PPC_H__ */

arch/powerpc/kvm/e500.c

@@ -121,7 +121,7 @@ void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 	sregs->u.e.mas0 = vcpu_e500->mas0;
 	sregs->u.e.mas1 = vcpu_e500->mas1;
 	sregs->u.e.mas2 = vcpu_e500->mas2;
-	sregs->u.e.mas7_3 = ((u64)vcpu_e500->mas7 << 32) | vcpu_e500->mas3;
+	sregs->u.e.mas7_3 = vcpu_e500->mas7_3;
 	sregs->u.e.mas4 = vcpu_e500->mas4;
 	sregs->u.e.mas6 = vcpu_e500->mas6;
 
@@ -154,8 +154,7 @@ int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 		vcpu_e500->mas0 = sregs->u.e.mas0;
 		vcpu_e500->mas1 = sregs->u.e.mas1;
 		vcpu_e500->mas2 = sregs->u.e.mas2;
-		vcpu_e500->mas7 = sregs->u.e.mas7_3 >> 32;
-		vcpu_e500->mas3 = (u32)sregs->u.e.mas7_3;
+		vcpu_e500->mas7_3 = sregs->u.e.mas7_3;
 		vcpu_e500->mas4 = sregs->u.e.mas4;
 		vcpu_e500->mas6 = sregs->u.e.mas6;
 	}

arch/powerpc/kvm/e500_emulate.c

@@ -95,13 +95,17 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 	case SPRN_MAS2:
 		vcpu_e500->mas2 = spr_val; break;
 	case SPRN_MAS3:
-		vcpu_e500->mas3 = spr_val; break;
+		vcpu_e500->mas7_3 &= ~(u64)0xffffffff;
+		vcpu_e500->mas7_3 |= spr_val;
+		break;
 	case SPRN_MAS4:
 		vcpu_e500->mas4 = spr_val; break;
 	case SPRN_MAS6:
 		vcpu_e500->mas6 = spr_val; break;
 	case SPRN_MAS7:
-		vcpu_e500->mas7 = spr_val; break;
+		vcpu_e500->mas7_3 &= (u64)0xffffffff;
+		vcpu_e500->mas7_3 |= (u64)spr_val << 32;
+		break;
 	case SPRN_L1CSR0:
 		vcpu_e500->l1csr0 = spr_val;
 		vcpu_e500->l1csr0 &= ~(L1CSR0_DCFI | L1CSR0_CLFC);
@@ -158,13 +162,13 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 	case SPRN_MAS2:
 		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas2); break;
 	case SPRN_MAS3:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas3); break;
+		kvmppc_set_gpr(vcpu, rt, (u32)vcpu_e500->mas7_3); break;
 	case SPRN_MAS4:
 		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas4); break;
 	case SPRN_MAS6:
 		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas6); break;
 	case SPRN_MAS7:
-		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas7); break;
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->mas7_3 >> 32); break;
 
 	case SPRN_TLB0CFG:
 		kvmppc_set_gpr(vcpu, rt, vcpu_e500->tlb0cfg); break;

arch/powerpc/kvm/e500_tlb.h

@@ -20,13 +20,9 @@
 #include <asm/tlb.h>
 #include <asm/kvm_e500.h>
 
-#define KVM_E500_TLB0_WAY_SIZE_BIT	7	/* Fixed */
-#define KVM_E500_TLB0_WAY_SIZE		(1UL << KVM_E500_TLB0_WAY_SIZE_BIT)
-#define KVM_E500_TLB0_WAY_SIZE_MASK	(KVM_E500_TLB0_WAY_SIZE - 1)
-
-#define KVM_E500_TLB0_WAY_NUM_BIT	1	/* No greater than 7 */
-#define KVM_E500_TLB0_WAY_NUM		(1UL << KVM_E500_TLB0_WAY_NUM_BIT)
-#define KVM_E500_TLB0_WAY_NUM_MASK	(KVM_E500_TLB0_WAY_NUM - 1)
+/* This geometry is the legacy default -- can be overridden by userspace */
+#define KVM_E500_TLB0_WAY_SIZE		128
+#define KVM_E500_TLB0_WAY_NUM		2
 
 #define KVM_E500_TLB0_SIZE  (KVM_E500_TLB0_WAY_SIZE * KVM_E500_TLB0_WAY_NUM)
 #define KVM_E500_TLB1_SIZE  16
@@ -58,50 +54,54 @@ extern void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *);
 extern void kvmppc_e500_recalc_shadow_pid(struct kvmppc_vcpu_e500 *);
 
 /* TLB helper functions */
-static inline unsigned int get_tlb_size(const struct tlbe *tlbe)
+static inline unsigned int
+get_tlb_size(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
 	return (tlbe->mas1 >> 7) & 0x1f;
 }
 
-static inline gva_t get_tlb_eaddr(const struct tlbe *tlbe)
+static inline gva_t get_tlb_eaddr(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
 	return tlbe->mas2 & 0xfffff000;
 }
 
-static inline u64 get_tlb_bytes(const struct tlbe *tlbe)
+static inline u64 get_tlb_bytes(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
 	unsigned int pgsize = get_tlb_size(tlbe);
 	return 1ULL << 10 << pgsize;
 }
 
-static inline gva_t get_tlb_end(const struct tlbe *tlbe)
+static inline gva_t get_tlb_end(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
 	u64 bytes = get_tlb_bytes(tlbe);
 	return get_tlb_eaddr(tlbe) + bytes - 1;
 }
 
-static inline u64 get_tlb_raddr(const struct tlbe *tlbe)
+static inline u64 get_tlb_raddr(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
-	u64 rpn = tlbe->mas7;
-	return (rpn << 32) | (tlbe->mas3 & 0xfffff000);
+	return tlbe->mas7_3 & ~0xfffULL;
 }
 
-static inline unsigned int get_tlb_tid(const struct tlbe *tlbe)
+static inline unsigned int
+get_tlb_tid(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
 	return (tlbe->mas1 >> 16) & 0xff;
 }
 
-static inline unsigned int get_tlb_ts(const struct tlbe *tlbe)
+static inline unsigned int
+get_tlb_ts(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
 	return (tlbe->mas1 >> 12) & 0x1;
 }
 
-static inline unsigned int get_tlb_v(const struct tlbe *tlbe)
+static inline unsigned int
+get_tlb_v(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
 	return (tlbe->mas1 >> 31) & 0x1;
 }
 
-static inline unsigned int get_tlb_iprot(const struct tlbe *tlbe)
+static inline unsigned int
+get_tlb_iprot(const struct kvm_book3e_206_tlb_entry *tlbe)
 {
 	return (tlbe->mas1 >> 30) & 0x1;
 }
@@ -156,7 +156,7 @@ static inline unsigned int get_tlb_esel_bit(
 }
 
 static inline int tlbe_is_host_safe(const struct kvm_vcpu *vcpu,
-			const struct tlbe *tlbe)
+			const struct kvm_book3e_206_tlb_entry *tlbe)
 {
 	gpa_t gpa;
 

arch/powerpc/kvm/powerpc.c

@@ -222,6 +222,9 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_PPC_PAIRED_SINGLES:
 	case KVM_CAP_PPC_OSI:
 	case KVM_CAP_PPC_GET_PVINFO:
+#ifdef CONFIG_KVM_E500
+	case KVM_CAP_SW_TLB:
+#endif
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -602,6 +605,19 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 		r = 0;
 		vcpu->arch.papr_enabled = true;
 		break;
+#ifdef CONFIG_KVM_E500
+	case KVM_CAP_SW_TLB: {
+		struct kvm_config_tlb cfg;
+		void __user *user_ptr = (void __user *)(uintptr_t)cap->args[0];
+
+		r = -EFAULT;
+		if (copy_from_user(&cfg, user_ptr, sizeof(cfg)))
+			break;
+
+		r = kvm_vcpu_ioctl_config_tlb(vcpu, &cfg);
+		break;
+	}
+#endif
 	default:
 		r = -EINVAL;
 		break;
@@ -651,6 +667,18 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap);
 		break;
 	}
+
+#ifdef CONFIG_KVM_E500
+	case KVM_DIRTY_TLB: {
+		struct kvm_dirty_tlb dirty;
+		r = -EFAULT;
+		if (copy_from_user(&dirty, argp, sizeof(dirty)))
+			goto out;
+		r = kvm_vcpu_ioctl_dirty_tlb(vcpu, &dirty);
+		break;
+	}
+#endif
+
 	default:
 		r = -EINVAL;
 	}

include/linux/kvm.h

@@ -581,6 +581,7 @@ struct kvm_ppc_pvinfo {
 #define KVM_CAP_PPC_RMA	65
 #define KVM_CAP_MAX_VCPUS 66       /* returns max vcpus per vm */
 #define KVM_CAP_PPC_PAPR 68
+#define KVM_CAP_SW_TLB 69
 #define KVM_CAP_S390_GMAP 71
 #define KVM_CAP_TSC_DEADLINE_TIMER 72
 #define KVM_CAP_S390_UCONTROL 73
@@ -664,6 +665,21 @@ struct kvm_clock_data {
 	__u32 pad[9];
 };
 
+#define KVM_MMU_FSL_BOOKE_NOHV		0
+#define KVM_MMU_FSL_BOOKE_HV		1
+
+struct kvm_config_tlb {
+	__u64 params;
+	__u64 array;
+	__u32 mmu_type;
+	__u32 array_len;
+};
+
+struct kvm_dirty_tlb {
+	__u64 bitmap;
+	__u32 num_dirty;
+};
+
 /*
  * ioctls for VM fds
  */
@@ -801,6 +817,8 @@ struct kvm_s390_ucas_mapping {
 #define KVM_CREATE_SPAPR_TCE	  _IOW(KVMIO,  0xa8, struct kvm_create_spapr_tce)
 /* Available with KVM_CAP_RMA */
 #define KVM_ALLOCATE_RMA	  _IOR(KVMIO,  0xa9, struct kvm_allocate_rma)
+/* Available with KVM_CAP_SW_TLB */
+#define KVM_DIRTY_TLB		  _IOW(KVMIO,  0xaa, struct kvm_dirty_tlb)
 
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)