Merge branch 'kvm-ppc-next' of git://git.kernel.org/pub/scm/linux/ker…

…nel/git/paulus/powerpc into HEAD

Paul Mackerras writes:

    The highlights are:

    * Reduced latency for interrupts from PCI pass-through devices, from
      Suresh Warrier and me.
    * Halt-polling implementation from Suraj Jitindar Singh.
    * 64-bit VCPU statistics, also from Suraj.
    * Various other minor fixes and improvements.

arch/arm/include/asm/kvm_host.h

@@ -183,15 +183,15 @@ struct kvm_vcpu_arch {
 };
 
 struct kvm_vm_stat {
-	u32 remote_tlb_flush;
+	ulong remote_tlb_flush;
 };
 
 struct kvm_vcpu_stat {
-	u32 halt_successful_poll;
-	u32 halt_attempted_poll;
-	u32 halt_poll_invalid;
-	u32 halt_wakeup;
-	u32 hvc_exit_stat;
+	u64 halt_successful_poll;
+	u64 halt_attempted_poll;
+	u64 halt_poll_invalid;
+	u64 halt_wakeup;
+	u64 hvc_exit_stat;
 	u64 wfe_exit_stat;
 	u64 wfi_exit_stat;
 	u64 mmio_exit_user;

arch/arm64/include/asm/kvm_host.h

@@ -290,15 +290,15 @@ struct kvm_vcpu_arch {
 #endif
 
 struct kvm_vm_stat {
-	u32 remote_tlb_flush;
+	ulong remote_tlb_flush;
 };
 
 struct kvm_vcpu_stat {
-	u32 halt_successful_poll;
-	u32 halt_attempted_poll;
-	u32 halt_poll_invalid;
-	u32 halt_wakeup;
-	u32 hvc_exit_stat;
+	u64 halt_successful_poll;
+	u64 halt_attempted_poll;
+	u64 halt_poll_invalid;
+	u64 halt_wakeup;
+	u64 hvc_exit_stat;
 	u64 wfe_exit_stat;
 	u64 wfi_exit_stat;
 	u64 mmio_exit_user;

arch/mips/include/asm/kvm_host.h

@@ -110,32 +110,32 @@
 extern atomic_t kvm_mips_instance;
 
 struct kvm_vm_stat {
-	u32 remote_tlb_flush;
+	ulong remote_tlb_flush;
 };
 
 struct kvm_vcpu_stat {
-	u32 wait_exits;
-	u32 cache_exits;
-	u32 signal_exits;
-	u32 int_exits;
-	u32 cop_unusable_exits;
-	u32 tlbmod_exits;
-	u32 tlbmiss_ld_exits;
-	u32 tlbmiss_st_exits;
-	u32 addrerr_st_exits;
-	u32 addrerr_ld_exits;
-	u32 syscall_exits;
-	u32 resvd_inst_exits;
-	u32 break_inst_exits;
-	u32 trap_inst_exits;
-	u32 msa_fpe_exits;
-	u32 fpe_exits;
-	u32 msa_disabled_exits;
-	u32 flush_dcache_exits;
-	u32 halt_successful_poll;
-	u32 halt_attempted_poll;
-	u32 halt_poll_invalid;
-	u32 halt_wakeup;
+	u64 wait_exits;
+	u64 cache_exits;
+	u64 signal_exits;
+	u64 int_exits;
+	u64 cop_unusable_exits;
+	u64 tlbmod_exits;
+	u64 tlbmiss_ld_exits;
+	u64 tlbmiss_st_exits;
+	u64 addrerr_st_exits;
+	u64 addrerr_ld_exits;
+	u64 syscall_exits;
+	u64 resvd_inst_exits;
+	u64 break_inst_exits;
+	u64 trap_inst_exits;
+	u64 msa_fpe_exits;
+	u64 fpe_exits;
+	u64 msa_disabled_exits;
+	u64 flush_dcache_exits;
+	u64 halt_successful_poll;
+	u64 halt_attempted_poll;
+	u64 halt_poll_invalid;
+	u64 halt_wakeup;
 };
 
 struct kvm_arch_memory_slot {

arch/powerpc/include/asm/book3s/64/mmu-hash.h

@@ -244,6 +244,43 @@ static inline int segment_shift(int ssize)
 	return SID_SHIFT_1T;
 }
 
+/*
+ * This array is indexed by the LP field of the HPTE second dword.
+ * Since this field may contain some RPN bits, some entries are
+ * replicated so that we get the same value irrespective of RPN.
+ * The top 4 bits are the page size index (MMU_PAGE_*) for the
+ * actual page size, the bottom 4 bits are the base page size.
+ */
+extern u8 hpte_page_sizes[1 << LP_BITS];
+
+static inline unsigned long __hpte_page_size(unsigned long h, unsigned long l,
+					     bool is_base_size)
+{
+	unsigned int i, lp;
+
+	if (!(h & HPTE_V_LARGE))
+		return 1ul << 12;
+
+	/* Look at the 8 bit LP value */
+	lp = (l >> LP_SHIFT) & ((1 << LP_BITS) - 1);
+	i = hpte_page_sizes[lp];
+	if (!i)
+		return 0;
+	if (!is_base_size)
+		i >>= 4;
+	return 1ul << mmu_psize_defs[i & 0xf].shift;
+}
+
+static inline unsigned long hpte_page_size(unsigned long h, unsigned long l)
+{
+	return __hpte_page_size(h, l, 0);
+}
+
+static inline unsigned long hpte_base_page_size(unsigned long h, unsigned long l)
+{
+	return __hpte_page_size(h, l, 1);
+}
+
 /*
  * The current system page and segment sizes
  */

arch/powerpc/include/asm/hmi.h

@@ -21,7 +21,7 @@
 #ifndef __ASM_PPC64_HMI_H__
 #define __ASM_PPC64_HMI_H__
 
-#ifdef CONFIG_PPC_BOOK3S_64
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 
 #define	CORE_TB_RESYNC_REQ_BIT		63
 #define MAX_SUBCORE_PER_CORE		4

arch/powerpc/include/asm/io.h

@@ -241,6 +241,35 @@ static inline void out_be64(volatile u64 __iomem *addr, u64 val)
 #endif
 #endif /* __powerpc64__ */
 
+
+/*
+ * Simple Cache inhibited accessors
+ * Unlike the DEF_MMIO_* macros, these don't include any h/w memory
+ * barriers, callers need to manage memory barriers on their own.
+ * These can only be used in hypervisor real mode.
+ */
+
+static inline u32 _lwzcix(unsigned long addr)
+{
+	u32 ret;
+
+	__asm__ __volatile__("lwzcix %0,0, %1"
+			     : "=r" (ret) : "r" (addr) : "memory");
+	return ret;
+}
+
+static inline void _stbcix(u64 addr, u8 val)
+{
+	__asm__ __volatile__("stbcix %0,0,%1"
+		: : "r" (val), "r" (addr) : "memory");
+}
+
+static inline void _stwcix(u64 addr, u32 val)
+{
+	__asm__ __volatile__("stwcix %0,0,%1"
+		: : "r" (val), "r" (addr) : "memory");
+}
+
 /*
  * Low level IO stream instructions are defined out of line for now
  */

arch/powerpc/include/asm/kvm_asm.h

@@ -105,6 +105,15 @@
 #define BOOK3S_INTERRUPT_FAC_UNAVAIL	0xf60
 #define BOOK3S_INTERRUPT_H_FAC_UNAVAIL	0xf80
 
+/* book3s_hv */
+
+/*
+ * Special trap used to indicate to host that this is a
+ * passthrough interrupt that could not be handled
+ * completely in the guest.
+ */
+#define BOOK3S_INTERRUPT_HV_RM_HARD	0x5555
+
 #define BOOK3S_IRQPRIO_SYSTEM_RESET		0
 #define BOOK3S_IRQPRIO_DATA_SEGMENT		1
 #define BOOK3S_IRQPRIO_INST_SEGMENT		2
@@ -136,6 +145,7 @@
 #define RESUME_FLAG_NV          (1<<0)  /* Reload guest nonvolatile state? */
 #define RESUME_FLAG_HOST        (1<<1)  /* Resume host? */
 #define RESUME_FLAG_ARCH1	(1<<2)
+#define RESUME_FLAG_ARCH2	(1<<3)
 
 #define RESUME_GUEST            0
 #define RESUME_GUEST_NV         RESUME_FLAG_NV

arch/powerpc/include/asm/kvm_book3s.h

@@ -69,6 +69,42 @@ struct hpte_cache {
 	int pagesize;
 };
 
+/*
+ * Struct for a virtual core.
+ * Note: entry_exit_map combines a bitmap of threads that have entered
+ * in the bottom 8 bits and a bitmap of threads that have exited in the
+ * next 8 bits.  This is so that we can atomically set the entry bit
+ * iff the exit map is 0 without taking a lock.
+ */
+struct kvmppc_vcore {
+	int n_runnable;
+	int num_threads;
+	int entry_exit_map;
+	int napping_threads;
+	int first_vcpuid;
+	u16 pcpu;
+	u16 last_cpu;
+	u8 vcore_state;
+	u8 in_guest;
+	struct kvmppc_vcore *master_vcore;
+	struct kvm_vcpu *runnable_threads[MAX_SMT_THREADS];
+	struct list_head preempt_list;
+	spinlock_t lock;
+	struct swait_queue_head wq;
+	spinlock_t stoltb_lock;	/* protects stolen_tb and preempt_tb */
+	u64 stolen_tb;
+	u64 preempt_tb;
+	struct kvm_vcpu *runner;
+	struct kvm *kvm;
+	u64 tb_offset;		/* guest timebase - host timebase */
+	ulong lpcr;
+	u32 arch_compat;
+	ulong pcr;
+	ulong dpdes;		/* doorbell state (POWER8) */
+	ulong conferring_threads;
+	unsigned int halt_poll_ns;
+};
+
 struct kvmppc_vcpu_book3s {
 	struct kvmppc_sid_map sid_map[SID_MAP_NUM];
 	struct {
@@ -191,6 +227,7 @@ extern void kvmppc_copy_to_svcpu(struct kvmppc_book3s_shadow_vcpu *svcpu,
 				 struct kvm_vcpu *vcpu);
 extern void kvmppc_copy_from_svcpu(struct kvm_vcpu *vcpu,
 				   struct kvmppc_book3s_shadow_vcpu *svcpu);
+extern int kvm_irq_bypass;
 
 static inline struct kvmppc_vcpu_book3s *to_book3s(struct kvm_vcpu *vcpu)
 {

arch/powerpc/include/asm/kvm_book3s_64.h

@@ -20,6 +20,8 @@
 #ifndef __ASM_KVM_BOOK3S_64_H__
 #define __ASM_KVM_BOOK3S_64_H__
 
+#include <asm/book3s/64/mmu-hash.h>
+
 #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 static inline struct kvmppc_book3s_shadow_vcpu *svcpu_get(struct kvm_vcpu *vcpu)
 {
@@ -97,56 +99,20 @@ static inline void __unlock_hpte(__be64 *hpte, unsigned long hpte_v)
 	hpte[0] = cpu_to_be64(hpte_v);
 }
 
-static inline int __hpte_actual_psize(unsigned int lp, int psize)
-{
-	int i, shift;
-	unsigned int mask;
-
-	/* start from 1 ignoring MMU_PAGE_4K */
-	for (i = 1; i < MMU_PAGE_COUNT; i++) {
-
-		/* invalid penc */
-		if (mmu_psize_defs[psize].penc[i] == -1)
-			continue;
-		/*
-		 * encoding bits per actual page size
-		 *        PTE LP     actual page size
-		 *    rrrr rrrz		>=8KB
-		 *    rrrr rrzz		>=16KB
-		 *    rrrr rzzz		>=32KB
-		 *    rrrr zzzz		>=64KB
-		 * .......
-		 */
-		shift = mmu_psize_defs[i].shift - LP_SHIFT;
-		if (shift > LP_BITS)
-			shift = LP_BITS;
-		mask = (1 << shift) - 1;
-		if ((lp & mask) == mmu_psize_defs[psize].penc[i])
-			return i;
-	}
-	return -1;
-}
-
 static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
 					     unsigned long pte_index)
 {
-	int b_psize = MMU_PAGE_4K, a_psize = MMU_PAGE_4K;
+	int i, b_psize = MMU_PAGE_4K, a_psize = MMU_PAGE_4K;
 	unsigned int penc;
 	unsigned long rb = 0, va_low, sllp;
 	unsigned int lp = (r >> LP_SHIFT) & ((1 << LP_BITS) - 1);
 
 	if (v & HPTE_V_LARGE) {
-		for (b_psize = 0; b_psize < MMU_PAGE_COUNT; b_psize++) {
-
-			/* valid entries have a shift value */
-			if (!mmu_psize_defs[b_psize].shift)
-				continue;
-
-			a_psize = __hpte_actual_psize(lp, b_psize);
-			if (a_psize != -1)
-				break;
-		}
+		i = hpte_page_sizes[lp];
+		b_psize = i & 0xf;
+		a_psize = i >> 4;
 	}
+
 	/*
 	 * Ignore the top 14 bits of va
 	 * v have top two bits covering segment size, hence move
@@ -215,45 +181,6 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
 	return rb;
 }
 
-static inline unsigned long __hpte_page_size(unsigned long h, unsigned long l,
-					     bool is_base_size)
-{
-
-	int size, a_psize;
-	/* Look at the 8 bit LP value */
-	unsigned int lp = (l >> LP_SHIFT) & ((1 << LP_BITS) - 1);
-
-	/* only handle 4k, 64k and 16M pages for now */
-	if (!(h & HPTE_V_LARGE))
-		return 1ul << 12;
-	else {
-		for (size = 0; size < MMU_PAGE_COUNT; size++) {
-			/* valid entries have a shift value */
-			if (!mmu_psize_defs[size].shift)
-				continue;
-
-			a_psize = __hpte_actual_psize(lp, size);
-			if (a_psize != -1) {
-				if (is_base_size)
-					return 1ul << mmu_psize_defs[size].shift;
-				return 1ul << mmu_psize_defs[a_psize].shift;
-			}
-		}
-
-	}
-	return 0;
-}
-
-static inline unsigned long hpte_page_size(unsigned long h, unsigned long l)
-{
-	return __hpte_page_size(h, l, 0);
-}
-
-static inline unsigned long hpte_base_page_size(unsigned long h, unsigned long l)
-{
-	return __hpte_page_size(h, l, 1);
-}
-
 static inline unsigned long hpte_rpn(unsigned long ptel, unsigned long psize)
 {
 	return ((ptel & HPTE_R_RPN) & ~(psize - 1)) >> PAGE_SHIFT;