Merge branch 'kvm-ppc-infrastructure' into kvm-ppc-next

This merges the topic branch 'kvm-ppc-infrastructure' into kvm-ppc-next
so that I can then apply further patches that need the changes in the
kvm-ppc-infrastructure branch.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>

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_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;

arch/powerpc/include/asm/mmu.h

@@ -271,6 +271,7 @@ static inline bool early_radix_enabled(void)
 #define MMU_PAGE_16G	13
 #define MMU_PAGE_64G	14
 
+/* N.B. we need to change the type of hpte_page_sizes if this gets to be > 16 */
 #define MMU_PAGE_COUNT	15
 
 #ifdef CONFIG_PPC_BOOK3S_64

arch/powerpc/include/asm/paca.h

@@ -183,11 +183,6 @@ struct paca_struct {
 	 */
 	u16 in_mce;
 	u8 hmi_event_available;		 /* HMI event is available */
-	/*
-	 * Bitmap for sibling subcore status. See kvm/book3s_hv_ras.c for
-	 * more details
-	 */
-	struct sibling_subcore_state *sibling_subcore_state;
 #endif
 
 	/* Stuff for accurate time accounting */
@@ -202,6 +197,13 @@ struct paca_struct {
 	struct kvmppc_book3s_shadow_vcpu shadow_vcpu;
 #endif
 	struct kvmppc_host_state kvm_hstate;
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	/*
+	 * Bitmap for sibling subcore status. See kvm/book3s_hv_ras.c for
+	 * more details
+	 */
+	struct sibling_subcore_state *sibling_subcore_state;
+#endif
 #endif
 };
 

arch/powerpc/include/asm/pnv-pci.h

@@ -12,6 +12,7 @@
 
 #include <linux/pci.h>
 #include <linux/pci_hotplug.h>
+#include <linux/irq.h>
 #include <misc/cxl-base.h>
 #include <asm/opal-api.h>
 
@@ -33,6 +34,8 @@ int pnv_cxl_alloc_hwirqs(struct pci_dev *dev, int num);
 void pnv_cxl_release_hwirqs(struct pci_dev *dev, int hwirq, int num);
 int pnv_cxl_get_irq_count(struct pci_dev *dev);
 struct device_node *pnv_pci_get_phb_node(struct pci_dev *dev);
+int64_t pnv_opal_pci_msi_eoi(struct irq_chip *chip, unsigned int hw_irq);
+bool is_pnv_opal_msi(struct irq_chip *chip);
 
 #ifdef CONFIG_CXL_BASE
 int pnv_cxl_alloc_hwirq_ranges(struct cxl_irq_ranges *irqs,

arch/powerpc/kernel/Makefile

@@ -41,7 +41,7 @@ obj-$(CONFIG_VDSO32)		+= vdso32/
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_ppc970.o cpu_setup_pa6t.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_power.o
-obj-$(CONFIG_PPC_BOOK3S_64)	+= mce.o mce_power.o hmi.o
+obj-$(CONFIG_PPC_BOOK3S_64)	+= mce.o mce_power.o
 obj-$(CONFIG_PPC_BOOK3E_64)	+= exceptions-64e.o idle_book3e.o
 obj-$(CONFIG_PPC64)		+= vdso64/
 obj-$(CONFIG_ALTIVEC)		+= vecemu.o

arch/powerpc/kvm/Makefile

@@ -77,6 +77,7 @@ kvm-book3s_64-builtin-xics-objs-$(CONFIG_KVM_XICS) := \
 
 ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HANDLER) += \
+	book3s_hv_hmi.o \
 	book3s_hv_rmhandlers.o \
 	book3s_hv_rm_mmu.o \
 	book3s_hv_ras.o \

arch/powerpc/mm/hash_native_64.c

@@ -493,36 +493,6 @@ static void native_hugepage_invalidate(unsigned long vsid,
 }
 #endif
 
-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 void hpte_decode(struct hash_pte *hpte, unsigned long slot,
 			int *psize, int *apsize, int *ssize, unsigned long *vpn)
 {
@@ -538,16 +508,8 @@ static void hpte_decode(struct hash_pte *hpte, unsigned long slot,
 		size   = MMU_PAGE_4K;
 		a_size = MMU_PAGE_4K;
 	} else {
-		for (size = 0; size < MMU_PAGE_COUNT; size++) {
-
-			/* valid entries have a shift value */
-			if (!mmu_psize_defs[size].shift)
-				continue;
-
-			a_size = __hpte_actual_psize(lp, size);
-			if (a_size != -1)
-				break;
-		}
+		size = hpte_page_sizes[lp] & 0xf;
+		a_size = hpte_page_sizes[lp] >> 4;
 	}
 	/* This works for all page sizes, and for 256M and 1T segments */
 	if (cpu_has_feature(CPU_FTR_ARCH_300))

arch/powerpc/mm/hash_utils_64.c

@@ -93,6 +93,9 @@ static unsigned long _SDR1;
 struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT];
 EXPORT_SYMBOL_GPL(mmu_psize_defs);
 
+u8 hpte_page_sizes[1 << LP_BITS];
+EXPORT_SYMBOL_GPL(hpte_page_sizes);
+
 struct hash_pte *htab_address;
 unsigned long htab_size_bytes;
 unsigned long htab_hash_mask;
@@ -564,8 +567,60 @@ static void __init htab_scan_page_sizes(void)
 #endif /* CONFIG_HUGETLB_PAGE */
 }
 
+/*
+ * Fill in the hpte_page_sizes[] array.
+ * We go through the mmu_psize_defs[] array looking for all the
+ * supported base/actual page size combinations.  Each combination
+ * has a unique pagesize encoding (penc) value in the low bits of
+ * the LP field of the HPTE.  For actual page sizes less than 1MB,
+ * some of the upper LP bits are used for RPN bits, meaning that
+ * we need to fill in several entries in hpte_page_sizes[].
+ *
+ * In diagrammatic form, with r = RPN bits and z = page size bits:
+ *        PTE LP     actual page size
+ *    rrrr rrrz		>=8KB
+ *    rrrr rrzz		>=16KB
+ *    rrrr rzzz		>=32KB
+ *    rrrr zzzz		>=64KB
+ *    ...
+ *
+ * The zzzz bits are implementation-specific but are chosen so that
+ * no encoding for a larger page size uses the same value in its
+ * low-order N bits as the encoding for the 2^(12+N) byte page size
+ * (if it exists).
+ */
+static void init_hpte_page_sizes(void)
+{
+	long int ap, bp;
+	long int shift, penc;
+
+	for (bp = 0; bp < MMU_PAGE_COUNT; ++bp) {
+		if (!mmu_psize_defs[bp].shift)
+			continue;	/* not a supported page size */
+		for (ap = bp; ap < MMU_PAGE_COUNT; ++ap) {
+			penc = mmu_psize_defs[bp].penc[ap];
+			if (penc == -1)
+				continue;
+			shift = mmu_psize_defs[ap].shift - LP_SHIFT;
+			if (shift <= 0)
+				continue;	/* should never happen */
+			/*
+			 * For page sizes less than 1MB, this loop
+			 * replicates the entry for all possible values
+			 * of the rrrr bits.
+			 */
+			while (penc < (1 << LP_BITS)) {
+				hpte_page_sizes[penc] = (ap << 4) | bp;
+				penc += 1 << shift;
+			}
+		}
+	}
+}
+
 static void __init htab_init_page_sizes(void)
 {
+	init_hpte_page_sizes();
+
 	if (!debug_pagealloc_enabled()) {
 		/*
 		 * Pick a size for the linear mapping. Currently, we only

arch/powerpc/platforms/powernv/pci-ioda.c

@@ -2710,15 +2710,21 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb,
 }
 
 #ifdef CONFIG_PCI_MSI
-static void pnv_ioda2_msi_eoi(struct irq_data *d)
+int64_t pnv_opal_pci_msi_eoi(struct irq_chip *chip, unsigned int hw_irq)
 {
-	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
-	struct irq_chip *chip = irq_data_get_irq_chip(d);
 	struct pnv_phb *phb = container_of(chip, struct pnv_phb,
 					   ioda.irq_chip);
+
+	return opal_pci_msi_eoi(phb->opal_id, hw_irq);
+}
+
+static void pnv_ioda2_msi_eoi(struct irq_data *d)
+{
 	int64_t rc;
+	unsigned int hw_irq = (unsigned int)irqd_to_hwirq(d);
+	struct irq_chip *chip = irq_data_get_irq_chip(d);
 
-	rc = opal_pci_msi_eoi(phb->opal_id, hw_irq);
+	rc = pnv_opal_pci_msi_eoi(chip, hw_irq);
 	WARN_ON_ONCE(rc);
 
 	icp_native_eoi(d);
@@ -2748,6 +2754,16 @@ void pnv_set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq)
 	irq_set_chip(virq, &phb->ioda.irq_chip);
 }
 
+/*
+ * Returns true iff chip is something that we could call
+ * pnv_opal_pci_msi_eoi for.
+ */
+bool is_pnv_opal_msi(struct irq_chip *chip)
+{
+	return chip->irq_eoi == pnv_ioda2_msi_eoi;
+}
+EXPORT_SYMBOL_GPL(is_pnv_opal_msi);
+
 static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
 				  unsigned int hwirq, unsigned int virq,
 				  unsigned int is_64, struct msi_msg *msg)