From f35320288c5306ddbcb5ecac046b73519837299c Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Tue, 2 Jul 2013 16:15:10 +0200
Subject: KVM: PPC: Book3S: Ignore DABR register

We don't emulate breakpoints yet, so just ignore reads and writes
to / from DABR.

This fixes booting of more recent Linux guest kernels for me.

Reported-by: Nello Martuscielli <ppc.addon@gmail.com>
Tested-by: Nello Martuscielli <ppc.addon@gmail.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_emulate.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index 1f6344c4408d..360ce68c9809 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -458,6 +458,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, ulong spr_val)
 	case SPRN_PMC4_GEKKO:
 	case SPRN_WPAR_GEKKO:
 	case SPRN_MSSSR0:
+	case SPRN_DABR:
 		break;
 unprivileged:
 	default:
@@ -555,6 +556,7 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, ulong *spr_val)
 	case SPRN_PMC4_GEKKO:
 	case SPRN_WPAR_GEKKO:
 	case SPRN_MSSSR0:
+	case SPRN_DABR:
 		*spr_val = 0;
 		break;
 	default:
-- 
cgit v1.2.3


From fa61a4e376d2129690c82dfb05b31705a67d6e0b Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Tue, 2 Jul 2013 11:15:16 +0530
Subject: powerpc/kvm: Contiguous memory allocator based hash page table
 allocation

Powerpc architecture uses a hash based page table mechanism for mapping virtual
addresses to physical address. The architecture require this hash page table to
be physically contiguous. With KVM on Powerpc currently we use early reservation
mechanism for allocating guest hash page table. This implies that we need to
reserve a big memory region to ensure we can create large number of guest
simultaneously with KVM on Power. Another disadvantage is that the reserved memory
is not available to rest of the subsystems and and that implies we limit the total
available memory in the host.

This patch series switch the guest hash page table allocation to use
contiguous memory allocator.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_book3s_64.h |   1 -
 arch/powerpc/include/asm/kvm_host.h      |   2 +-
 arch/powerpc/include/asm/kvm_ppc.h       |   8 +-
 arch/powerpc/kernel/setup_64.c           |   2 +
 arch/powerpc/kvm/Kconfig                 |   1 +
 arch/powerpc/kvm/Makefile                |   1 +
 arch/powerpc/kvm/book3s_64_mmu_hv.c      |  37 +++--
 arch/powerpc/kvm/book3s_hv_builtin.c     |  91 +++++++++----
 arch/powerpc/kvm/book3s_hv_cma.c         | 227 +++++++++++++++++++++++++++++++
 arch/powerpc/kvm/book3s_hv_cma.h         |  22 +++
 10 files changed, 341 insertions(+), 51 deletions(-)
 create mode 100644 arch/powerpc/kvm/book3s_hv_cma.c
 create mode 100644 arch/powerpc/kvm/book3s_hv_cma.h

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 9c1ff330c805..f8355a902ac5 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -37,7 +37,6 @@ static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu)
 
 #ifdef CONFIG_KVM_BOOK3S_64_HV
 #define KVM_DEFAULT_HPT_ORDER	24	/* 16MB HPT by default */
-extern int kvm_hpt_order;		/* order of preallocated HPTs */
 #endif
 
 #define VRMA_VSID	0x1ffffffUL	/* 1TB VSID reserved for VRMA */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index af326cde7cb6..0097dab3d601 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -259,7 +259,7 @@ struct kvm_arch {
 	spinlock_t slot_phys_lock;
 	cpumask_t need_tlb_flush;
 	struct kvmppc_vcore *vcores[KVM_MAX_VCORES];
-	struct kvmppc_linear_info *hpt_li;
+	int hpt_cma_alloc;
 #endif /* CONFIG_KVM_BOOK3S_64_HV */
 #ifdef CONFIG_PPC_BOOK3S_64
 	struct list_head spapr_tce_tables;
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index a5287fe03d77..b5ef7a3c606b 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -139,8 +139,8 @@ extern long kvm_vm_ioctl_allocate_rma(struct kvm *kvm,
 				struct kvm_allocate_rma *rma);
 extern struct kvmppc_linear_info *kvm_alloc_rma(void);
 extern void kvm_release_rma(struct kvmppc_linear_info *ri);
-extern struct kvmppc_linear_info *kvm_alloc_hpt(void);
-extern void kvm_release_hpt(struct kvmppc_linear_info *li);
+extern struct page *kvm_alloc_hpt(unsigned long nr_pages);
+extern void kvm_release_hpt(struct page *page, unsigned long nr_pages);
 extern int kvmppc_core_init_vm(struct kvm *kvm);
 extern void kvmppc_core_destroy_vm(struct kvm *kvm);
 extern void kvmppc_core_free_memslot(struct kvm_memory_slot *free,
@@ -261,6 +261,7 @@ void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid);
 struct openpic;
 
 #ifdef CONFIG_KVM_BOOK3S_64_HV
+extern void kvm_cma_reserve(void) __init;
 static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
 {
 	paca[cpu].kvm_hstate.xics_phys = addr;
@@ -284,6 +285,9 @@ extern void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu);
 extern void kvm_linear_init(void);
 
 #else
+static inline void __init kvm_cma_reserve(void)
+{}
+
 static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
 {}
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index e379d3fd1694..ee28d1f4b853 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -229,6 +229,8 @@ void __init early_setup(unsigned long dt_ptr)
 	/* Initialize the hash table or TLB handling */
 	early_init_mmu();
 
+	kvm_cma_reserve();
+
 	/*
 	 * Reserve any gigantic pages requested on the command line.
 	 * memblock needs to have been initialized by the time this is
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index eb643f862579..ffaef2cb101a 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -72,6 +72,7 @@ config KVM_BOOK3S_64_HV
 	bool "KVM support for POWER7 and PPC970 using hypervisor mode in host"
 	depends on KVM_BOOK3S_64
 	select MMU_NOTIFIER
+	select CMA
 	---help---
 	  Support running unmodified book3s_64 guest kernels in
 	  virtual machines on POWER7 and PPC970 processors that have
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 008cd856c5b5..6646c952c5e3 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -81,6 +81,7 @@ kvm-book3s_64-builtin-objs-$(CONFIG_KVM_BOOK3S_64_HV) := \
 	book3s_64_vio_hv.o \
 	book3s_hv_ras.o \
 	book3s_hv_builtin.o \
+	book3s_hv_cma.o \
 	$(kvm-book3s_64-builtin-xics-objs-y)
 
 kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 5880dfb31074..354f4bb21f5c 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -52,8 +52,8 @@ long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp)
 {
 	unsigned long hpt;
 	struct revmap_entry *rev;
-	struct kvmppc_linear_info *li;
-	long order = kvm_hpt_order;
+	struct page *page = NULL;
+	long order = KVM_DEFAULT_HPT_ORDER;
 
 	if (htab_orderp) {
 		order = *htab_orderp;
@@ -61,26 +61,22 @@ long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp)
 			order = PPC_MIN_HPT_ORDER;
 	}
 
+	kvm->arch.hpt_cma_alloc = 0;
 	/*
-	 * If the user wants a different size from default,
 	 * try first to allocate it from the kernel page allocator.
+	 * We keep the CMA reserved for failed allocation.
 	 */
-	hpt = 0;
-	if (order != kvm_hpt_order) {
-		hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT|
-				       __GFP_NOWARN, order - PAGE_SHIFT);
-		if (!hpt)
-			--order;
-	}
+	hpt = __get_free_pages(GFP_KERNEL | __GFP_ZERO | __GFP_REPEAT |
+			       __GFP_NOWARN, order - PAGE_SHIFT);
 
 	/* Next try to allocate from the preallocated pool */
 	if (!hpt) {
-		li = kvm_alloc_hpt();
-		if (li) {
-			hpt = (ulong)li->base_virt;
-			kvm->arch.hpt_li = li;
-			order = kvm_hpt_order;
-		}
+		page = kvm_alloc_hpt(1 << (order - PAGE_SHIFT));
+		if (page) {
+			hpt = (unsigned long)pfn_to_kaddr(page_to_pfn(page));
+			kvm->arch.hpt_cma_alloc = 1;
+		} else
+			--order;
 	}
 
 	/* Lastly try successively smaller sizes from the page allocator */
@@ -118,8 +114,8 @@ long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp)
 	return 0;
 
  out_freehpt:
-	if (kvm->arch.hpt_li)
-		kvm_release_hpt(kvm->arch.hpt_li);
+	if (kvm->arch.hpt_cma_alloc)
+		kvm_release_hpt(page, 1 << (order - PAGE_SHIFT));
 	else
 		free_pages(hpt, order - PAGE_SHIFT);
 	return -ENOMEM;
@@ -165,8 +161,9 @@ void kvmppc_free_hpt(struct kvm *kvm)
 {
 	kvmppc_free_lpid(kvm->arch.lpid);
 	vfree(kvm->arch.revmap);
-	if (kvm->arch.hpt_li)
-		kvm_release_hpt(kvm->arch.hpt_li);
+	if (kvm->arch.hpt_cma_alloc)
+		kvm_release_hpt(virt_to_page(kvm->arch.hpt_virt),
+				1 << (kvm->arch.hpt_order - PAGE_SHIFT));
 	else
 		free_pages(kvm->arch.hpt_virt,
 			   kvm->arch.hpt_order - PAGE_SHIFT);
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index ec0a9e5de100..4b865c553331 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -13,20 +13,30 @@
 #include <linux/spinlock.h>
 #include <linux/bootmem.h>
 #include <linux/init.h>
+#include <linux/memblock.h>
+#include <linux/sizes.h>
 
 #include <asm/cputable.h>
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
 
+#include "book3s_hv_cma.h"
+
 #define KVM_LINEAR_RMA		0
 #define KVM_LINEAR_HPT		1
 
 static void __init kvm_linear_init_one(ulong size, int count, int type);
 static struct kvmppc_linear_info *kvm_alloc_linear(int type);
 static void kvm_release_linear(struct kvmppc_linear_info *ri);
-
-int kvm_hpt_order = KVM_DEFAULT_HPT_ORDER;
-EXPORT_SYMBOL_GPL(kvm_hpt_order);
+/*
+ * Hash page table alignment on newer cpus(CPU_FTR_ARCH_206)
+ * should be power of 2.
+ */
+#define HPT_ALIGN_PAGES		((1 << 18) >> PAGE_SHIFT) /* 256k */
+/*
+ * By default we reserve 5% of memory for hash pagetable allocation.
+ */
+static unsigned long kvm_cma_resv_ratio = 5;
 
 /*************** RMA *************/
 
@@ -101,36 +111,29 @@ void kvm_release_rma(struct kvmppc_linear_info *ri)
 }
 EXPORT_SYMBOL_GPL(kvm_release_rma);
 
-/*************** HPT *************/
-
-/*
- * This maintains a list of big linear HPT tables that contain the GVA->HPA
- * memory mappings. If we don't reserve those early on, we might not be able
- * to get a big (usually 16MB) linear memory region from the kernel anymore.
- */
-
-static unsigned long kvm_hpt_count;
-
-static int __init early_parse_hpt_count(char *p)
+static int __init early_parse_kvm_cma_resv(char *p)
 {
+	pr_debug("%s(%s)\n", __func__, p);
 	if (!p)
-		return 1;
-
-	kvm_hpt_count = simple_strtoul(p, NULL, 0);
-
-	return 0;
+		return -EINVAL;
+	return kstrtoul(p, 0, &kvm_cma_resv_ratio);
 }
-early_param("kvm_hpt_count", early_parse_hpt_count);
+early_param("kvm_cma_resv_ratio", early_parse_kvm_cma_resv);
 
-struct kvmppc_linear_info *kvm_alloc_hpt(void)
+struct page *kvm_alloc_hpt(unsigned long nr_pages)
 {
-	return kvm_alloc_linear(KVM_LINEAR_HPT);
+	unsigned long align_pages = HPT_ALIGN_PAGES;
+
+	/* Old CPUs require HPT aligned on a multiple of its size */
+	if (!cpu_has_feature(CPU_FTR_ARCH_206))
+		align_pages = nr_pages;
+	return kvm_alloc_cma(nr_pages, align_pages);
 }
 EXPORT_SYMBOL_GPL(kvm_alloc_hpt);
 
-void kvm_release_hpt(struct kvmppc_linear_info *li)
+void kvm_release_hpt(struct page *page, unsigned long nr_pages)
 {
-	kvm_release_linear(li);
+	kvm_release_cma(page, nr_pages);
 }
 EXPORT_SYMBOL_GPL(kvm_release_hpt);
 
@@ -211,9 +214,6 @@ static void kvm_release_linear(struct kvmppc_linear_info *ri)
  */
 void __init kvm_linear_init(void)
 {
-	/* HPT */
-	kvm_linear_init_one(1 << kvm_hpt_order, kvm_hpt_count, KVM_LINEAR_HPT);
-
 	/* RMA */
 	/* Only do this on PPC970 in HV mode */
 	if (!cpu_has_feature(CPU_FTR_HVMODE) ||
@@ -231,3 +231,40 @@ void __init kvm_linear_init(void)
 
 	kvm_linear_init_one(kvm_rma_size, kvm_rma_count, KVM_LINEAR_RMA);
 }
+
+/**
+ * kvm_cma_reserve() - reserve area for kvm hash pagetable
+ *
+ * This function reserves memory from early allocator. It should be
+ * called by arch specific code once the early allocator (memblock or bootmem)
+ * has been activated and all other subsystems have already allocated/reserved
+ * memory.
+ */
+void __init kvm_cma_reserve(void)
+{
+	unsigned long align_size;
+	struct memblock_region *reg;
+	phys_addr_t selected_size = 0;
+	/*
+	 * We cannot use memblock_phys_mem_size() here, because
+	 * memblock_analyze() has not been called yet.
+	 */
+	for_each_memblock(memory, reg)
+		selected_size += memblock_region_memory_end_pfn(reg) -
+				 memblock_region_memory_base_pfn(reg);
+
+	selected_size = (selected_size * kvm_cma_resv_ratio / 100) << PAGE_SHIFT;
+	if (selected_size) {
+		pr_debug("%s: reserving %ld MiB for global area\n", __func__,
+			 (unsigned long)selected_size / SZ_1M);
+		/*
+		 * Old CPUs require HPT aligned on a multiple of its size. So for them
+		 * make the alignment as max size we could request.
+		 */
+		if (!cpu_has_feature(CPU_FTR_ARCH_206))
+			align_size = __rounddown_pow_of_two(selected_size);
+		else
+			align_size = HPT_ALIGN_PAGES << PAGE_SHIFT;
+		kvm_cma_declare_contiguous(selected_size, align_size);
+	}
+}
diff --git a/arch/powerpc/kvm/book3s_hv_cma.c b/arch/powerpc/kvm/book3s_hv_cma.c
new file mode 100644
index 000000000000..e04b269b9c5b
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_hv_cma.c
@@ -0,0 +1,227 @@
+/*
+ * Contiguous Memory Allocator for ppc KVM hash pagetable  based on CMA
+ * for DMA mapping framework
+ *
+ * Copyright IBM Corporation, 2013
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License or (at your optional) any later version of the license.
+ *
+ */
+#define pr_fmt(fmt) "kvm_cma: " fmt
+
+#ifdef CONFIG_CMA_DEBUG
+#ifndef DEBUG
+#  define DEBUG
+#endif
+#endif
+
+#include <linux/memblock.h>
+#include <linux/mutex.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+
+struct kvm_cma {
+	unsigned long	base_pfn;
+	unsigned long	count;
+	unsigned long	*bitmap;
+};
+
+static DEFINE_MUTEX(kvm_cma_mutex);
+static struct kvm_cma kvm_cma_area;
+
+/**
+ * kvm_cma_declare_contiguous() - reserve area for contiguous memory handling
+ *			          for kvm hash pagetable
+ * @size:  Size of the reserved memory.
+ * @alignment:  Alignment for the contiguous memory area
+ *
+ * This function reserves memory for kvm cma area. It should be
+ * called by arch code when early allocator (memblock or bootmem)
+ * is still activate.
+ */
+long __init kvm_cma_declare_contiguous(phys_addr_t size, phys_addr_t alignment)
+{
+	long base_pfn;
+	phys_addr_t addr;
+	struct kvm_cma *cma = &kvm_cma_area;
+
+	pr_debug("%s(size %lx)\n", __func__, (unsigned long)size);
+
+	if (!size)
+		return -EINVAL;
+	/*
+	 * Sanitise input arguments.
+	 * We should be pageblock aligned for CMA.
+	 */
+	alignment = max(alignment, (phys_addr_t)(PAGE_SIZE << pageblock_order));
+	size = ALIGN(size, alignment);
+	/*
+	 * Reserve memory
+	 * Use __memblock_alloc_base() since
+	 * memblock_alloc_base() panic()s.
+	 */
+	addr = __memblock_alloc_base(size, alignment, 0);
+	if (!addr) {
+		base_pfn = -ENOMEM;
+		goto err;
+	} else
+		base_pfn = PFN_DOWN(addr);
+
+	/*
+	 * Each reserved area must be initialised later, when more kernel
+	 * subsystems (like slab allocator) are available.
+	 */
+	cma->base_pfn = base_pfn;
+	cma->count    = size >> PAGE_SHIFT;
+	pr_info("CMA: reserved %ld MiB\n", (unsigned long)size / SZ_1M);
+	return 0;
+err:
+	pr_err("CMA: failed to reserve %ld MiB\n", (unsigned long)size / SZ_1M);
+	return base_pfn;
+}
+
+/**
+ * kvm_alloc_cma() - allocate pages from contiguous area
+ * @nr_pages: Requested number of pages.
+ * @align_pages: Requested alignment in number of pages
+ *
+ * This function allocates memory buffer for hash pagetable.
+ */
+struct page *kvm_alloc_cma(unsigned long nr_pages, unsigned long align_pages)
+{
+	int ret;
+	struct page *page = NULL;
+	struct kvm_cma *cma = &kvm_cma_area;
+	unsigned long mask, pfn, pageno, start = 0;
+
+
+	if (!cma || !cma->count)
+		return NULL;
+
+	pr_debug("%s(cma %p, count %lu, align pages %lu)\n", __func__,
+		 (void *)cma, nr_pages, align_pages);
+
+	if (!nr_pages)
+		return NULL;
+
+	VM_BUG_ON(!is_power_of_2(align_pages));
+	mask = align_pages - 1;
+
+	mutex_lock(&kvm_cma_mutex);
+	for (;;) {
+		pageno = bitmap_find_next_zero_area(cma->bitmap, cma->count,
+						    start, nr_pages, mask);
+		if (pageno >= cma->count)
+			break;
+
+		pfn = cma->base_pfn + pageno;
+		ret = alloc_contig_range(pfn, pfn + nr_pages, MIGRATE_CMA);
+		if (ret == 0) {
+			bitmap_set(cma->bitmap, pageno, nr_pages);
+			page = pfn_to_page(pfn);
+			memset(pfn_to_kaddr(pfn), 0, nr_pages << PAGE_SHIFT);
+			break;
+		} else if (ret != -EBUSY) {
+			break;
+		}
+		pr_debug("%s(): memory range at %p is busy, retrying\n",
+			 __func__, pfn_to_page(pfn));
+		/* try again with a bit different memory target */
+		start = pageno + mask + 1;
+	}
+	mutex_unlock(&kvm_cma_mutex);
+	pr_debug("%s(): returned %p\n", __func__, page);
+	return page;
+}
+
+/**
+ * kvm_release_cma() - release allocated pages for hash pagetable
+ * @pages: Allocated pages.
+ * @nr_pages: Number of allocated pages.
+ *
+ * This function releases memory allocated by kvm_alloc_cma().
+ * It returns false when provided pages do not belong to contiguous area and
+ * true otherwise.
+ */
+bool kvm_release_cma(struct page *pages, unsigned long nr_pages)
+{
+	unsigned long pfn;
+	struct kvm_cma *cma = &kvm_cma_area;
+
+
+	if (!cma || !pages)
+		return false;
+
+	pr_debug("%s(page %p count %lu)\n", __func__, (void *)pages, nr_pages);
+
+	pfn = page_to_pfn(pages);
+
+	if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count)
+		return false;
+
+	VM_BUG_ON(pfn + nr_pages > cma->base_pfn + cma->count);
+
+	mutex_lock(&kvm_cma_mutex);
+	bitmap_clear(cma->bitmap, pfn - cma->base_pfn, nr_pages);
+	free_contig_range(pfn, nr_pages);
+	mutex_unlock(&kvm_cma_mutex);
+
+	return true;
+}
+
+static int __init kvm_cma_activate_area(unsigned long base_pfn,
+					unsigned long count)
+{
+	unsigned long pfn = base_pfn;
+	unsigned i = count >> pageblock_order;
+	struct zone *zone;
+
+	WARN_ON_ONCE(!pfn_valid(pfn));
+	zone = page_zone(pfn_to_page(pfn));
+	do {
+		unsigned j;
+		base_pfn = pfn;
+		for (j = pageblock_nr_pages; j; --j, pfn++) {
+			WARN_ON_ONCE(!pfn_valid(pfn));
+			/*
+			 * alloc_contig_range requires the pfn range
+			 * specified to be in the same zone. Make this
+			 * simple by forcing the entire CMA resv range
+			 * to be in the same zone.
+			 */
+			if (page_zone(pfn_to_page(pfn)) != zone)
+				return -EINVAL;
+		}
+		init_cma_reserved_pageblock(pfn_to_page(base_pfn));
+	} while (--i);
+	return 0;
+}
+
+static int __init kvm_cma_init_reserved_areas(void)
+{
+	int bitmap_size, ret;
+	struct kvm_cma *cma = &kvm_cma_area;
+
+	pr_debug("%s()\n", __func__);
+	if (!cma->count)
+		return 0;
+
+	bitmap_size = BITS_TO_LONGS(cma->count) * sizeof(long);
+	cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+	if (!cma->bitmap)
+		return -ENOMEM;
+
+	ret = kvm_cma_activate_area(cma->base_pfn, cma->count);
+	if (ret)
+		goto error;
+	return 0;
+
+error:
+	kfree(cma->bitmap);
+	return ret;
+}
+core_initcall(kvm_cma_init_reserved_areas);
diff --git a/arch/powerpc/kvm/book3s_hv_cma.h b/arch/powerpc/kvm/book3s_hv_cma.h
new file mode 100644
index 000000000000..788bc3b73104
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_hv_cma.h
@@ -0,0 +1,22 @@
+/*
+ * Contiguous Memory Allocator for ppc KVM hash pagetable  based on CMA
+ * for DMA mapping framework
+ *
+ * Copyright IBM Corporation, 2013
+ * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of the
+ * License or (at your optional) any later version of the license.
+ *
+ */
+
+#ifndef __POWERPC_KVM_CMA_ALLOC_H__
+#define __POWERPC_KVM_CMA_ALLOC_H__
+extern struct page *kvm_alloc_cma(unsigned long nr_pages,
+				  unsigned long align_pages);
+extern bool kvm_release_cma(struct page *pages, unsigned long nr_pages);
+extern long kvm_cma_declare_contiguous(phys_addr_t size,
+				       phys_addr_t alignment) __init;
+#endif
-- 
cgit v1.2.3


From 6c45b810989d1c04194499d666f695d3f811965f Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Tue, 2 Jul 2013 11:15:17 +0530
Subject: powerpc/kvm: Contiguous memory allocator based RMA allocation

Older version of power architecture use Real Mode Offset register and Real Mode Limit
Selector for mapping guest Real Mode Area. The guest RMA should be physically
contigous since we use the range when address translation is not enabled.

This patch switch RMA allocation code to use contigous memory allocator. The patch
also remove the the linear allocator which not used any more

Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_book3s_64.h |   1 +
 arch/powerpc/include/asm/kvm_host.h      |  12 +--
 arch/powerpc/include/asm/kvm_ppc.h       |   8 +-
 arch/powerpc/kernel/setup_64.c           |   2 -
 arch/powerpc/kvm/book3s_hv.c             |  27 +++--
 arch/powerpc/kvm/book3s_hv_builtin.c     | 167 ++++++++-----------------------
 6 files changed, 65 insertions(+), 152 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index f8355a902ac5..76ff0b5c9996 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -37,6 +37,7 @@ static inline void svcpu_put(struct kvmppc_book3s_shadow_vcpu *svcpu)
 
 #ifdef CONFIG_KVM_BOOK3S_64_HV
 #define KVM_DEFAULT_HPT_ORDER	24	/* 16MB HPT by default */
+extern unsigned long kvm_rma_pages;
 #endif
 
 #define VRMA_VSID	0x1ffffffUL	/* 1TB VSID reserved for VRMA */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 0097dab3d601..33283532e9d8 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -183,13 +183,9 @@ struct kvmppc_spapr_tce_table {
 	struct page *pages[0];
 };
 
-struct kvmppc_linear_info {
-	void		*base_virt;
-	unsigned long	 base_pfn;
-	unsigned long	 npages;
-	struct list_head list;
-	atomic_t	 use_count;
-	int		 type;
+struct kvm_rma_info {
+	atomic_t use_count;
+	unsigned long base_pfn;
 };
 
 /* XICS components, defined in book3s_xics.c */
@@ -246,7 +242,7 @@ struct kvm_arch {
 	int tlbie_lock;
 	unsigned long lpcr;
 	unsigned long rmor;
-	struct kvmppc_linear_info *rma;
+	struct kvm_rma_info *rma;
 	unsigned long vrma_slb_v;
 	int rma_setup_done;
 	int using_mmu_notifiers;
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index b5ef7a3c606b..5a26bfcd0bbc 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -137,8 +137,8 @@ extern long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 			     unsigned long ioba, unsigned long tce);
 extern long kvm_vm_ioctl_allocate_rma(struct kvm *kvm,
 				struct kvm_allocate_rma *rma);
-extern struct kvmppc_linear_info *kvm_alloc_rma(void);
-extern void kvm_release_rma(struct kvmppc_linear_info *ri);
+extern struct kvm_rma_info *kvm_alloc_rma(void);
+extern void kvm_release_rma(struct kvm_rma_info *ri);
 extern struct page *kvm_alloc_hpt(unsigned long nr_pages);
 extern void kvm_release_hpt(struct page *page, unsigned long nr_pages);
 extern int kvmppc_core_init_vm(struct kvm *kvm);
@@ -282,7 +282,6 @@ static inline void kvmppc_set_host_ipi(int cpu, u8 host_ipi)
 }
 
 extern void kvmppc_fast_vcpu_kick(struct kvm_vcpu *vcpu);
-extern void kvm_linear_init(void);
 
 #else
 static inline void __init kvm_cma_reserve(void)
@@ -291,9 +290,6 @@ static inline void __init kvm_cma_reserve(void)
 static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
 {}
 
-static inline void kvm_linear_init(void)
-{}
-
 static inline u32 kvmppc_get_xics_latch(void)
 {
 	return 0;
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index ee28d1f4b853..8a022f5de0ef 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -611,8 +611,6 @@ void __init setup_arch(char **cmdline_p)
 	/* Initialize the MMU context management stuff */
 	mmu_context_init();
 
-	kvm_linear_init();
-
 	/* Interrupt code needs to be 64K-aligned */
 	if ((unsigned long)_stext & 0xffff)
 		panic("Kernelbase not 64K-aligned (0x%lx)!\n",
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 2efa9dde741a..2b95c45e17d9 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1511,10 +1511,10 @@ static inline int lpcr_rmls(unsigned long rma_size)
 
 static int kvm_rma_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	struct kvmppc_linear_info *ri = vma->vm_file->private_data;
 	struct page *page;
+	struct kvm_rma_info *ri = vma->vm_file->private_data;
 
-	if (vmf->pgoff >= ri->npages)
+	if (vmf->pgoff >= kvm_rma_pages)
 		return VM_FAULT_SIGBUS;
 
 	page = pfn_to_page(ri->base_pfn + vmf->pgoff);
@@ -1536,7 +1536,7 @@ static int kvm_rma_mmap(struct file *file, struct vm_area_struct *vma)
 
 static int kvm_rma_release(struct inode *inode, struct file *filp)
 {
-	struct kvmppc_linear_info *ri = filp->private_data;
+	struct kvm_rma_info *ri = filp->private_data;
 
 	kvm_release_rma(ri);
 	return 0;
@@ -1549,8 +1549,17 @@ static const struct file_operations kvm_rma_fops = {
 
 long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, struct kvm_allocate_rma *ret)
 {
-	struct kvmppc_linear_info *ri;
 	long fd;
+	struct kvm_rma_info *ri;
+	/*
+	 * Only do this on PPC970 in HV mode
+	 */
+	if (!cpu_has_feature(CPU_FTR_HVMODE) ||
+	    !cpu_has_feature(CPU_FTR_ARCH_201))
+		return -EINVAL;
+
+	if (!kvm_rma_pages)
+		return -EINVAL;
 
 	ri = kvm_alloc_rma();
 	if (!ri)
@@ -1560,7 +1569,7 @@ long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, struct kvm_allocate_rma *ret)
 	if (fd < 0)
 		kvm_release_rma(ri);
 
-	ret->rma_size = ri->npages << PAGE_SHIFT;
+	ret->rma_size = kvm_rma_pages << PAGE_SHIFT;
 	return fd;
 }
 
@@ -1725,7 +1734,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 {
 	int err = 0;
 	struct kvm *kvm = vcpu->kvm;
-	struct kvmppc_linear_info *ri = NULL;
+	struct kvm_rma_info *ri = NULL;
 	unsigned long hva;
 	struct kvm_memory_slot *memslot;
 	struct vm_area_struct *vma;
@@ -1803,7 +1812,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 
 	} else {
 		/* Set up to use an RMO region */
-		rma_size = ri->npages;
+		rma_size = kvm_rma_pages;
 		if (rma_size > memslot->npages)
 			rma_size = memslot->npages;
 		rma_size <<= PAGE_SHIFT;
@@ -1831,14 +1840,14 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 			/* POWER7 */
 			lpcr &= ~(LPCR_VPM0 | LPCR_VRMA_L);
 			lpcr |= rmls << LPCR_RMLS_SH;
-			kvm->arch.rmor = kvm->arch.rma->base_pfn << PAGE_SHIFT;
+			kvm->arch.rmor = ri->base_pfn << PAGE_SHIFT;
 		}
 		kvm->arch.lpcr = lpcr;
 		pr_info("KVM: Using RMO at %lx size %lx (LPCR = %lx)\n",
 			ri->base_pfn << PAGE_SHIFT, rma_size, lpcr);
 
 		/* Initialize phys addrs of pages in RMO */
-		npages = ri->npages;
+		npages = kvm_rma_pages;
 		porder = __ilog2(npages);
 		physp = memslot->arch.slot_phys;
 		if (physp) {
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 4b865c553331..8cd0daebb82d 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -21,13 +21,6 @@
 #include <asm/kvm_book3s.h>
 
 #include "book3s_hv_cma.h"
-
-#define KVM_LINEAR_RMA		0
-#define KVM_LINEAR_HPT		1
-
-static void __init kvm_linear_init_one(ulong size, int count, int type);
-static struct kvmppc_linear_info *kvm_alloc_linear(int type);
-static void kvm_release_linear(struct kvmppc_linear_info *ri);
 /*
  * Hash page table alignment on newer cpus(CPU_FTR_ARCH_206)
  * should be power of 2.
@@ -37,19 +30,17 @@ static void kvm_release_linear(struct kvmppc_linear_info *ri);
  * By default we reserve 5% of memory for hash pagetable allocation.
  */
 static unsigned long kvm_cma_resv_ratio = 5;
-
-/*************** RMA *************/
-
 /*
- * This maintains a list of RMAs (real mode areas) for KVM guests to use.
+ * We allocate RMAs (real mode areas) for KVM guests from the KVM CMA area.
  * Each RMA has to be physically contiguous and of a size that the
  * hardware supports.  PPC970 and POWER7 support 64MB, 128MB and 256MB,
  * and other larger sizes.  Since we are unlikely to be allocate that
  * much physically contiguous memory after the system is up and running,
- * we preallocate a set of RMAs in early boot for KVM to use.
+ * we preallocate a set of RMAs in early boot using CMA.
+ * should be power of 2.
  */
-static unsigned long kvm_rma_size = 64 << 20;	/* 64MB */
-static unsigned long kvm_rma_count;
+unsigned long kvm_rma_pages = (1 << 27) >> PAGE_SHIFT;	/* 128MB */
+EXPORT_SYMBOL_GPL(kvm_rma_pages);
 
 /* Work out RMLS (real mode limit selector) field value for a given RMA size.
    Assumes POWER7 or PPC970. */
@@ -79,35 +70,50 @@ static inline int lpcr_rmls(unsigned long rma_size)
 
 static int __init early_parse_rma_size(char *p)
 {
-	if (!p)
-		return 1;
+	unsigned long kvm_rma_size;
 
+	pr_debug("%s(%s)\n", __func__, p);
+	if (!p)
+		return -EINVAL;
 	kvm_rma_size = memparse(p, &p);
-
+	/*
+	 * Check that the requested size is one supported in hardware
+	 */
+	if (lpcr_rmls(kvm_rma_size) < 0) {
+		pr_err("RMA size of 0x%lx not supported\n", kvm_rma_size);
+		return -EINVAL;
+	}
+	kvm_rma_pages = kvm_rma_size >> PAGE_SHIFT;
 	return 0;
 }
 early_param("kvm_rma_size", early_parse_rma_size);
 
-static int __init early_parse_rma_count(char *p)
+struct kvm_rma_info *kvm_alloc_rma()
 {
-	if (!p)
-		return 1;
-
-	kvm_rma_count = simple_strtoul(p, NULL, 0);
-
-	return 0;
-}
-early_param("kvm_rma_count", early_parse_rma_count);
-
-struct kvmppc_linear_info *kvm_alloc_rma(void)
-{
-	return kvm_alloc_linear(KVM_LINEAR_RMA);
+	struct page *page;
+	struct kvm_rma_info *ri;
+
+	ri = kmalloc(sizeof(struct kvm_rma_info), GFP_KERNEL);
+	if (!ri)
+		return NULL;
+	page = kvm_alloc_cma(kvm_rma_pages, kvm_rma_pages);
+	if (!page)
+		goto err_out;
+	atomic_set(&ri->use_count, 1);
+	ri->base_pfn = page_to_pfn(page);
+	return ri;
+err_out:
+	kfree(ri);
+	return NULL;
 }
 EXPORT_SYMBOL_GPL(kvm_alloc_rma);
 
-void kvm_release_rma(struct kvmppc_linear_info *ri)
+void kvm_release_rma(struct kvm_rma_info *ri)
 {
-	kvm_release_linear(ri);
+	if (atomic_dec_and_test(&ri->use_count)) {
+		kvm_release_cma(pfn_to_page(ri->base_pfn), kvm_rma_pages);
+		kfree(ri);
+	}
 }
 EXPORT_SYMBOL_GPL(kvm_release_rma);
 
@@ -137,101 +143,6 @@ void kvm_release_hpt(struct page *page, unsigned long nr_pages)
 }
 EXPORT_SYMBOL_GPL(kvm_release_hpt);
 
-/*************** generic *************/
-
-static LIST_HEAD(free_linears);
-static DEFINE_SPINLOCK(linear_lock);
-
-static void __init kvm_linear_init_one(ulong size, int count, int type)
-{
-	unsigned long i;
-	unsigned long j, npages;
-	void *linear;
-	struct page *pg;
-	const char *typestr;
-	struct kvmppc_linear_info *linear_info;
-
-	if (!count)
-		return;
-
-	typestr = (type == KVM_LINEAR_RMA) ? "RMA" : "HPT";
-
-	npages = size >> PAGE_SHIFT;
-	linear_info = alloc_bootmem(count * sizeof(struct kvmppc_linear_info));
-	for (i = 0; i < count; ++i) {
-		linear = alloc_bootmem_align(size, size);
-		pr_debug("Allocated KVM %s at %p (%ld MB)\n", typestr, linear,
-			 size >> 20);
-		linear_info[i].base_virt = linear;
-		linear_info[i].base_pfn = __pa(linear) >> PAGE_SHIFT;
-		linear_info[i].npages = npages;
-		linear_info[i].type = type;
-		list_add_tail(&linear_info[i].list, &free_linears);
-		atomic_set(&linear_info[i].use_count, 0);
-
-		pg = pfn_to_page(linear_info[i].base_pfn);
-		for (j = 0; j < npages; ++j) {
-			atomic_inc(&pg->_count);
-			++pg;
-		}
-	}
-}
-
-static struct kvmppc_linear_info *kvm_alloc_linear(int type)
-{
-	struct kvmppc_linear_info *ri, *ret;
-
-	ret = NULL;
-	spin_lock(&linear_lock);
-	list_for_each_entry(ri, &free_linears, list) {
-		if (ri->type != type)
-			continue;
-
-		list_del(&ri->list);
-		atomic_inc(&ri->use_count);
-		memset(ri->base_virt, 0, ri->npages << PAGE_SHIFT);
-		ret = ri;
-		break;
-	}
-	spin_unlock(&linear_lock);
-	return ret;
-}
-
-static void kvm_release_linear(struct kvmppc_linear_info *ri)
-{
-	if (atomic_dec_and_test(&ri->use_count)) {
-		spin_lock(&linear_lock);
-		list_add_tail(&ri->list, &free_linears);
-		spin_unlock(&linear_lock);
-
-	}
-}
-
-/*
- * Called at boot time while the bootmem allocator is active,
- * to allocate contiguous physical memory for the hash page
- * tables for guests.
- */
-void __init kvm_linear_init(void)
-{
-	/* RMA */
-	/* Only do this on PPC970 in HV mode */
-	if (!cpu_has_feature(CPU_FTR_HVMODE) ||
-	    !cpu_has_feature(CPU_FTR_ARCH_201))
-		return;
-
-	if (!kvm_rma_size || !kvm_rma_count)
-		return;
-
-	/* Check that the requested size is one supported in hardware */
-	if (lpcr_rmls(kvm_rma_size) < 0) {
-		pr_err("RMA size of 0x%lx not supported\n", kvm_rma_size);
-		return;
-	}
-
-	kvm_linear_init_one(kvm_rma_size, kvm_rma_count, KVM_LINEAR_RMA);
-}
-
 /**
  * kvm_cma_reserve() - reserve area for kvm hash pagetable
  *
@@ -265,6 +176,8 @@ void __init kvm_cma_reserve(void)
 			align_size = __rounddown_pow_of_two(selected_size);
 		else
 			align_size = HPT_ALIGN_PAGES << PAGE_SHIFT;
+
+		align_size = max(kvm_rma_pages << PAGE_SHIFT, align_size);
 		kvm_cma_declare_contiguous(selected_size, align_size);
 	}
 }
-- 
cgit v1.2.3


From 990978e99359e1f3a843563b9f96f9dc7bb7c05a Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Tue, 2 Jul 2013 11:15:18 +0530
Subject: powerpc/kvm: Use 256K chunk to track both RMA and hash page table
 allocation.

Both RMA and hash page table request will be a multiple of 256K. We can use
a chunk size of 256K to track the free/used 256K chunk in the bitmap. This
should help to reduce the bitmap size.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_64_mmu_hv.c |  3 +++
 arch/powerpc/kvm/book3s_hv_cma.c    | 35 ++++++++++++++++++++++++-----------
 arch/powerpc/kvm/book3s_hv_cma.h    |  5 +++++
 3 files changed, 32 insertions(+), 11 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 354f4bb21f5c..7eb5ddab1203 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -37,6 +37,8 @@
 #include <asm/ppc-opcode.h>
 #include <asm/cputable.h>
 
+#include "book3s_hv_cma.h"
+
 /* POWER7 has 10-bit LPIDs, PPC970 has 6-bit LPIDs */
 #define MAX_LPID_970	63
 
@@ -71,6 +73,7 @@ long kvmppc_alloc_hpt(struct kvm *kvm, u32 *htab_orderp)
 
 	/* Next try to allocate from the preallocated pool */
 	if (!hpt) {
+		VM_BUG_ON(order < KVM_CMA_CHUNK_ORDER);
 		page = kvm_alloc_hpt(1 << (order - PAGE_SHIFT));
 		if (page) {
 			hpt = (unsigned long)pfn_to_kaddr(page_to_pfn(page));
diff --git a/arch/powerpc/kvm/book3s_hv_cma.c b/arch/powerpc/kvm/book3s_hv_cma.c
index e04b269b9c5b..d9d3d8553d51 100644
--- a/arch/powerpc/kvm/book3s_hv_cma.c
+++ b/arch/powerpc/kvm/book3s_hv_cma.c
@@ -24,6 +24,8 @@
 #include <linux/sizes.h>
 #include <linux/slab.h>
 
+#include "book3s_hv_cma.h"
+
 struct kvm_cma {
 	unsigned long	base_pfn;
 	unsigned long	count;
@@ -96,6 +98,7 @@ struct page *kvm_alloc_cma(unsigned long nr_pages, unsigned long align_pages)
 	int ret;
 	struct page *page = NULL;
 	struct kvm_cma *cma = &kvm_cma_area;
+	unsigned long chunk_count, nr_chunk;
 	unsigned long mask, pfn, pageno, start = 0;
 
 
@@ -107,21 +110,27 @@ struct page *kvm_alloc_cma(unsigned long nr_pages, unsigned long align_pages)
 
 	if (!nr_pages)
 		return NULL;
-
+	/*
+	 * align mask with chunk size. The bit tracks pages in chunk size
+	 */
 	VM_BUG_ON(!is_power_of_2(align_pages));
-	mask = align_pages - 1;
+	mask = (align_pages >> (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT)) - 1;
+	BUILD_BUG_ON(PAGE_SHIFT > KVM_CMA_CHUNK_ORDER);
+
+	chunk_count = cma->count >>  (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT);
+	nr_chunk = nr_pages >> (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT);
 
 	mutex_lock(&kvm_cma_mutex);
 	for (;;) {
-		pageno = bitmap_find_next_zero_area(cma->bitmap, cma->count,
-						    start, nr_pages, mask);
-		if (pageno >= cma->count)
+		pageno = bitmap_find_next_zero_area(cma->bitmap, chunk_count,
+						    start, nr_chunk, mask);
+		if (pageno >= chunk_count)
 			break;
 
-		pfn = cma->base_pfn + pageno;
+		pfn = cma->base_pfn + (pageno << (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT));
 		ret = alloc_contig_range(pfn, pfn + nr_pages, MIGRATE_CMA);
 		if (ret == 0) {
-			bitmap_set(cma->bitmap, pageno, nr_pages);
+			bitmap_set(cma->bitmap, pageno, nr_chunk);
 			page = pfn_to_page(pfn);
 			memset(pfn_to_kaddr(pfn), 0, nr_pages << PAGE_SHIFT);
 			break;
@@ -150,9 +159,9 @@ struct page *kvm_alloc_cma(unsigned long nr_pages, unsigned long align_pages)
 bool kvm_release_cma(struct page *pages, unsigned long nr_pages)
 {
 	unsigned long pfn;
+	unsigned long nr_chunk;
 	struct kvm_cma *cma = &kvm_cma_area;
 
-
 	if (!cma || !pages)
 		return false;
 
@@ -164,9 +173,12 @@ bool kvm_release_cma(struct page *pages, unsigned long nr_pages)
 		return false;
 
 	VM_BUG_ON(pfn + nr_pages > cma->base_pfn + cma->count);
+	nr_chunk = nr_pages >>  (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT);
 
 	mutex_lock(&kvm_cma_mutex);
-	bitmap_clear(cma->bitmap, pfn - cma->base_pfn, nr_pages);
+	bitmap_clear(cma->bitmap,
+		     (pfn - cma->base_pfn) >> (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT),
+		     nr_chunk);
 	free_contig_range(pfn, nr_pages);
 	mutex_unlock(&kvm_cma_mutex);
 
@@ -204,13 +216,14 @@ static int __init kvm_cma_activate_area(unsigned long base_pfn,
 static int __init kvm_cma_init_reserved_areas(void)
 {
 	int bitmap_size, ret;
+	unsigned long chunk_count;
 	struct kvm_cma *cma = &kvm_cma_area;
 
 	pr_debug("%s()\n", __func__);
 	if (!cma->count)
 		return 0;
-
-	bitmap_size = BITS_TO_LONGS(cma->count) * sizeof(long);
+	chunk_count = cma->count >> (KVM_CMA_CHUNK_ORDER - PAGE_SHIFT);
+	bitmap_size = BITS_TO_LONGS(chunk_count) * sizeof(long);
 	cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
 	if (!cma->bitmap)
 		return -ENOMEM;
diff --git a/arch/powerpc/kvm/book3s_hv_cma.h b/arch/powerpc/kvm/book3s_hv_cma.h
index 788bc3b73104..655144f75fa5 100644
--- a/arch/powerpc/kvm/book3s_hv_cma.h
+++ b/arch/powerpc/kvm/book3s_hv_cma.h
@@ -14,6 +14,11 @@
 
 #ifndef __POWERPC_KVM_CMA_ALLOC_H__
 #define __POWERPC_KVM_CMA_ALLOC_H__
+/*
+ * Both RMA and Hash page allocation will be multiple of 256K.
+ */
+#define KVM_CMA_CHUNK_ORDER	18
+
 extern struct page *kvm_alloc_cma(unsigned long nr_pages,
 				  unsigned long align_pages);
 extern bool kvm_release_cma(struct page *pages, unsigned long nr_pages);
-- 
cgit v1.2.3


From 5448050124d9d289bc2f5177318c68c0484ca413 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Mon, 8 Jul 2013 20:08:25 +1000
Subject: KVM: PPC: Book3S HV: Correct tlbie usage

This corrects the usage of the tlbie (TLB invalidate entry) instruction
in HV KVM.  The tlbie instruction changed between PPC970 and POWER7.
On the PPC970, the bit to select large vs. small page is in the instruction,
not in the RB register value.  This changes the code to use the correct
form on PPC970.

On POWER7 we were calculating the AVAL (Abbreviated Virtual Address, Lower)
field of the RB value incorrectly for 64k pages.  This fixes it.

Since we now have several cases to handle for the tlbie instruction, this
factors out the code to do a sequence of tlbies into a new function,
do_tlbies(), and calls that from the various places where the code was
doing tlbie instructions inline.  It also makes kvmppc_h_bulk_remove()
use the same global_invalidates() function for determining whether to do
local or global TLB invalidations as is used in other places, for
consistency, and also to make sure that kvm->arch.need_tlb_flush gets
updated properly.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_book3s_64.h |   2 +-
 arch/powerpc/kvm/book3s_hv_rm_mmu.c      | 139 ++++++++++++++++++-------------
 2 files changed, 82 insertions(+), 59 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h
index 76ff0b5c9996..154ba3f6b7a9 100644
--- a/arch/powerpc/include/asm/kvm_book3s_64.h
+++ b/arch/powerpc/include/asm/kvm_book3s_64.h
@@ -100,7 +100,7 @@ static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r,
 			/* (masks depend on page size) */
 			rb |= 0x1000;		/* page encoding in LP field */
 			rb |= (va_low & 0x7f) << 16; /* 7b of VA in AVA/LP field */
-			rb |= (va_low & 0xfe);	/* AVAL field (P7 doesn't seem to care) */
+			rb |= ((va_low << 4) & 0xf0);	/* AVAL field (P7 doesn't seem to care) */
 		}
 	} else {
 		/* 4kB page */
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 6dcbb49105a4..105b00f24f27 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -385,6 +385,80 @@ static inline int try_lock_tlbie(unsigned int *lock)
 	return old == 0;
 }
 
+/*
+ * tlbie/tlbiel is a bit different on the PPC970 compared to later
+ * processors such as POWER7; the large page bit is in the instruction
+ * not RB, and the top 16 bits and the bottom 12 bits of the VA
+ * in RB must be 0.
+ */
+static void do_tlbies_970(struct kvm *kvm, unsigned long *rbvalues,
+			  long npages, int global, bool need_sync)
+{
+	long i;
+
+	if (global) {
+		while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
+			cpu_relax();
+		if (need_sync)
+			asm volatile("ptesync" : : : "memory");
+		for (i = 0; i < npages; ++i) {
+			unsigned long rb = rbvalues[i];
+
+			if (rb & 1)		/* large page */
+				asm volatile("tlbie %0,1" : :
+					     "r" (rb & 0x0000fffffffff000ul));
+			else
+				asm volatile("tlbie %0,0" : :
+					     "r" (rb & 0x0000fffffffff000ul));
+		}
+		asm volatile("eieio; tlbsync; ptesync" : : : "memory");
+		kvm->arch.tlbie_lock = 0;
+	} else {
+		if (need_sync)
+			asm volatile("ptesync" : : : "memory");
+		for (i = 0; i < npages; ++i) {
+			unsigned long rb = rbvalues[i];
+
+			if (rb & 1)		/* large page */
+				asm volatile("tlbiel %0,1" : :
+					     "r" (rb & 0x0000fffffffff000ul));
+			else
+				asm volatile("tlbiel %0,0" : :
+					     "r" (rb & 0x0000fffffffff000ul));
+		}
+		asm volatile("ptesync" : : : "memory");
+	}
+}
+
+static void do_tlbies(struct kvm *kvm, unsigned long *rbvalues,
+		      long npages, int global, bool need_sync)
+{
+	long i;
+
+	if (cpu_has_feature(CPU_FTR_ARCH_201)) {
+		/* PPC970 tlbie instruction is a bit different */
+		do_tlbies_970(kvm, rbvalues, npages, global, need_sync);
+		return;
+	}
+	if (global) {
+		while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
+			cpu_relax();
+		if (need_sync)
+			asm volatile("ptesync" : : : "memory");
+		for (i = 0; i < npages; ++i)
+			asm volatile(PPC_TLBIE(%1,%0) : :
+				     "r" (rbvalues[i]), "r" (kvm->arch.lpid));
+		asm volatile("eieio; tlbsync; ptesync" : : : "memory");
+		kvm->arch.tlbie_lock = 0;
+	} else {
+		if (need_sync)
+			asm volatile("ptesync" : : : "memory");
+		for (i = 0; i < npages; ++i)
+			asm volatile("tlbiel %0" : : "r" (rbvalues[i]));
+		asm volatile("ptesync" : : : "memory");
+	}
+}
+
 long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
 			unsigned long pte_index, unsigned long avpn,
 			unsigned long *hpret)
@@ -410,19 +484,7 @@ long kvmppc_do_h_remove(struct kvm *kvm, unsigned long flags,
 	if (v & HPTE_V_VALID) {
 		hpte[0] &= ~HPTE_V_VALID;
 		rb = compute_tlbie_rb(v, hpte[1], pte_index);
-		if (global_invalidates(kvm, flags)) {
-			while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
-				cpu_relax();
-			asm volatile("ptesync" : : : "memory");
-			asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
-				     : : "r" (rb), "r" (kvm->arch.lpid));
-			asm volatile("ptesync" : : : "memory");
-			kvm->arch.tlbie_lock = 0;
-		} else {
-			asm volatile("ptesync" : : : "memory");
-			asm volatile("tlbiel %0" : : "r" (rb));
-			asm volatile("ptesync" : : : "memory");
-		}
+		do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags), true);
 		/* Read PTE low word after tlbie to get final R/C values */
 		remove_revmap_chain(kvm, pte_index, rev, v, hpte[1]);
 	}
@@ -450,12 +512,11 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
 	unsigned long *hp, *hptes[4], tlbrb[4];
 	long int i, j, k, n, found, indexes[4];
 	unsigned long flags, req, pte_index, rcbits;
-	long int local = 0;
+	int global;
 	long int ret = H_SUCCESS;
 	struct revmap_entry *rev, *revs[4];
 
-	if (atomic_read(&kvm->online_vcpus) == 1)
-		local = 1;
+	global = global_invalidates(kvm, 0);
 	for (i = 0; i < 4 && ret == H_SUCCESS; ) {
 		n = 0;
 		for (; i < 4; ++i) {
@@ -531,22 +592,7 @@ long kvmppc_h_bulk_remove(struct kvm_vcpu *vcpu)
 			break;
 
 		/* Now that we've collected a batch, do the tlbies */
-		if (!local) {
-			while(!try_lock_tlbie(&kvm->arch.tlbie_lock))
-				cpu_relax();
-			asm volatile("ptesync" : : : "memory");
-			for (k = 0; k < n; ++k)
-				asm volatile(PPC_TLBIE(%1,%0) : :
-					     "r" (tlbrb[k]),
-					     "r" (kvm->arch.lpid));
-			asm volatile("eieio; tlbsync; ptesync" : : : "memory");
-			kvm->arch.tlbie_lock = 0;
-		} else {
-			asm volatile("ptesync" : : : "memory");
-			for (k = 0; k < n; ++k)
-				asm volatile("tlbiel %0" : : "r" (tlbrb[k]));
-			asm volatile("ptesync" : : : "memory");
-		}
+		do_tlbies(kvm, tlbrb, n, global, true);
 
 		/* Read PTE low words after tlbie to get final R/C values */
 		for (k = 0; k < n; ++k) {
@@ -605,19 +651,7 @@ long kvmppc_h_protect(struct kvm_vcpu *vcpu, unsigned long flags,
 	if (v & HPTE_V_VALID) {
 		rb = compute_tlbie_rb(v, r, pte_index);
 		hpte[0] = v & ~HPTE_V_VALID;
-		if (global_invalidates(kvm, flags)) {
-			while(!try_lock_tlbie(&kvm->arch.tlbie_lock))
-				cpu_relax();
-			asm volatile("ptesync" : : : "memory");
-			asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
-				     : : "r" (rb), "r" (kvm->arch.lpid));
-			asm volatile("ptesync" : : : "memory");
-			kvm->arch.tlbie_lock = 0;
-		} else {
-			asm volatile("ptesync" : : : "memory");
-			asm volatile("tlbiel %0" : : "r" (rb));
-			asm volatile("ptesync" : : : "memory");
-		}
+		do_tlbies(kvm, &rb, 1, global_invalidates(kvm, flags), true);
 		/*
 		 * If the host has this page as readonly but the guest
 		 * wants to make it read/write, reduce the permissions.
@@ -688,13 +722,7 @@ void kvmppc_invalidate_hpte(struct kvm *kvm, unsigned long *hptep,
 
 	hptep[0] &= ~HPTE_V_VALID;
 	rb = compute_tlbie_rb(hptep[0], hptep[1], pte_index);
-	while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
-		cpu_relax();
-	asm volatile("ptesync" : : : "memory");
-	asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
-		     : : "r" (rb), "r" (kvm->arch.lpid));
-	asm volatile("ptesync" : : : "memory");
-	kvm->arch.tlbie_lock = 0;
+	do_tlbies(kvm, &rb, 1, 1, true);
 }
 EXPORT_SYMBOL_GPL(kvmppc_invalidate_hpte);
 
@@ -708,12 +736,7 @@ void kvmppc_clear_ref_hpte(struct kvm *kvm, unsigned long *hptep,
 	rbyte = (hptep[1] & ~HPTE_R_R) >> 8;
 	/* modify only the second-last byte, which contains the ref bit */
 	*((char *)hptep + 14) = rbyte;
-	while (!try_lock_tlbie(&kvm->arch.tlbie_lock))
-		cpu_relax();
-	asm volatile(PPC_TLBIE(%1,%0)"; eieio; tlbsync"
-		     : : "r" (rb), "r" (kvm->arch.lpid));
-	asm volatile("ptesync" : : : "memory");
-	kvm->arch.tlbie_lock = 0;
+	do_tlbies(kvm, &rb, 1, 1, false);
 }
 EXPORT_SYMBOL_GPL(kvmppc_clear_ref_hpte);
 
-- 
cgit v1.2.3


From 4baa1d871c8c959084aa5367a9bf211f383941e5 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Mon, 8 Jul 2013 20:09:53 +1000
Subject: KVM: PPC: Book3S HV: Allow negative offsets to real-mode hcall
 handlers

The table of offsets to real-mode hcall handlers in book3s_hv_rmhandlers.S
can contain negative values, if some of the handlers end up before the
table in the vmlinux binary.  Thus we need to use a sign-extending load
to read the values in the table rather than a zero-extending load.
Without this, the host crashes when the guest does one of the hcalls
with negative offsets, due to jumping to a bogus address.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_hv_rmhandlers.S | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index b02f91e4c70d..60dce5bfab3f 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1381,7 +1381,7 @@ hcall_try_real_mode:
 	cmpldi	r3,hcall_real_table_end - hcall_real_table
 	bge	guest_exit_cont
 	LOAD_REG_ADDR(r4, hcall_real_table)
-	lwzx	r3,r3,r4
+	lwax	r3,r3,r4
 	cmpwi	r3,0
 	beq	guest_exit_cont
 	add	r3,r3,r4
-- 
cgit v1.2.3


From 5f1c248f52c12e155e0fe6a614178181f7629901 Mon Sep 17 00:00:00 2001
From: Scott Wood <scottwood@freescale.com>
Date: Wed, 10 Jul 2013 17:47:39 -0500
Subject: kvm/ppc: Call trace_hardirqs_on before entry

Currently this is only being done on 64-bit.  Rather than just move it
out of the 64-bit ifdef, move it to kvm_lazy_ee_enable() so that it is
consistent with lazy ee state, and so that we don't track more host
code as interrupts-enabled than necessary.

Rename kvm_lazy_ee_enable() to kvm_fix_ee_before_entry() to reflect
that this function now has a role on 32-bit as well.

Signed-off-by: Scott Wood <scottwood@freescale.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_ppc.h | 11 ++++++++---
 arch/powerpc/kvm/book3s_pr.c       |  4 ++--
 arch/powerpc/kvm/booke.c           |  4 ++--
 arch/powerpc/kvm/powerpc.c         |  2 --
 4 files changed, 12 insertions(+), 9 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 5a26bfcd0bbc..b15554a26c20 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -394,10 +394,15 @@ static inline void kvmppc_mmu_flush_icache(pfn_t pfn)
 	}
 }
 
-/* Please call after prepare_to_enter. This function puts the lazy ee state
-   back to normal mode, without actually enabling interrupts. */
-static inline void kvmppc_lazy_ee_enable(void)
+/*
+ * Please call after prepare_to_enter. This function puts the lazy ee and irq
+ * disabled tracking state back to normal mode, without actually enabling
+ * interrupts.
+ */
+static inline void kvmppc_fix_ee_before_entry(void)
 {
+	trace_hardirqs_on();
+
 #ifdef CONFIG_PPC64
 	/* Only need to enable IRQs by hard enabling them after this */
 	local_paca->irq_happened = 0;
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 19498a567a81..ddfaf560e503 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -890,7 +890,7 @@ program_interrupt:
 			local_irq_enable();
 			r = s;
 		} else {
-			kvmppc_lazy_ee_enable();
+			kvmppc_fix_ee_before_entry();
 		}
 	}
 
@@ -1161,7 +1161,7 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	if (vcpu->arch.shared->msr & MSR_FP)
 		kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);
 
-	kvmppc_lazy_ee_enable();
+	kvmppc_fix_ee_before_entry();
 
 	ret = __kvmppc_vcpu_run(kvm_run, vcpu);
 
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index dcc94f016007..6e353517c4ad 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -698,7 +698,7 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	kvmppc_load_guest_fp(vcpu);
 #endif
 
-	kvmppc_lazy_ee_enable();
+	kvmppc_fix_ee_before_entry();
 
 	ret = __kvmppc_vcpu_run(kvm_run, vcpu);
 
@@ -1168,7 +1168,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			local_irq_enable();
 			r = (s << 2) | RESUME_HOST | (r & RESUME_FLAG_NV);
 		} else {
-			kvmppc_lazy_ee_enable();
+			kvmppc_fix_ee_before_entry();
 		}
 	}
 
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 6316ee336e88..4e05f8c693b4 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -117,8 +117,6 @@ int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu)
 			kvm_guest_exit();
 			continue;
 		}
-
-		trace_hardirqs_on();
 #endif
 
 		kvm_guest_enter();
-- 
cgit v1.2.3


From c09ec198eb7d5d55fe2f23012a063b7ee107b34a Mon Sep 17 00:00:00 2001
From: Scott Wood <scottwood@freescale.com>
Date: Wed, 10 Jul 2013 17:47:41 -0500
Subject: kvm/ppc/booke: Don't call kvm_guest_enter twice

kvm_guest_enter() was already called by kvmppc_prepare_to_enter().
Don't call it again.

Signed-off-by: Scott Wood <scottwood@freescale.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/booke.c | 2 --
 1 file changed, 2 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 6e353517c4ad..17722d82f1d1 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -674,8 +674,6 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 		goto out;
 	}
 
-	kvm_guest_enter();
-
 #ifdef CONFIG_PPC_FPU
 	/* Save userspace FPU state in stack */
 	enable_kernel_fp();
-- 
cgit v1.2.3


From c8ae0ace104ff36d43311c148c8aeed9f194cbf2 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Thu, 11 Jul 2013 21:49:43 +1000
Subject: KVM: PPC: Book3S PR: Load up SPRG3 register with guest value on guest
 entry

Unlike the other general-purpose SPRs, SPRG3 can be read by usermode
code, and is used in recent kernels to store the CPU and NUMA node
numbers so that they can be read by VDSO functions.  Thus we need to
load the guest's SPRG3 value into the real SPRG3 register when entering
the guest, and restore the host's value when exiting the guest.  We don't
need to save the guest SPRG3 value when exiting the guest as usermode
code can't modify SPRG3.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/asm-offsets.c    |  1 +
 arch/powerpc/kvm/book3s_interrupts.S | 14 ++++++++++++++
 2 files changed, 15 insertions(+)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 6f16ffafa6f0..a67c76ef5feb 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -452,6 +452,7 @@ int main(void)
 	DEFINE(VCPU_SPRG2, offsetof(struct kvm_vcpu, arch.shregs.sprg2));
 	DEFINE(VCPU_SPRG3, offsetof(struct kvm_vcpu, arch.shregs.sprg3));
 #endif
+	DEFINE(VCPU_SHARED_SPRG3, offsetof(struct kvm_vcpu_arch_shared, sprg3));
 	DEFINE(VCPU_SHARED_SPRG4, offsetof(struct kvm_vcpu_arch_shared, sprg4));
 	DEFINE(VCPU_SHARED_SPRG5, offsetof(struct kvm_vcpu_arch_shared, sprg5));
 	DEFINE(VCPU_SHARED_SPRG6, offsetof(struct kvm_vcpu_arch_shared, sprg6));
diff --git a/arch/powerpc/kvm/book3s_interrupts.S b/arch/powerpc/kvm/book3s_interrupts.S
index 48cbbf862958..17cfae5497a3 100644
--- a/arch/powerpc/kvm/book3s_interrupts.S
+++ b/arch/powerpc/kvm/book3s_interrupts.S
@@ -92,6 +92,11 @@ kvm_start_lightweight:
 	PPC_LL	r3, VCPU_HFLAGS(r4)
 	rldicl	r3, r3, 0, 63		/* r3 &= 1 */
 	stb	r3, HSTATE_RESTORE_HID5(r13)
+
+	/* Load up guest SPRG3 value, since it's user readable */
+	ld	r3, VCPU_SHARED(r4)
+	ld	r3, VCPU_SHARED_SPRG3(r3)
+	mtspr	SPRN_SPRG3, r3
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
 	PPC_LL	r4, VCPU_SHADOW_MSR(r4)	/* get shadow_msr */
@@ -123,6 +128,15 @@ kvmppc_handler_highmem:
 	/* R7 = vcpu */
 	PPC_LL	r7, GPR4(r1)
 
+#ifdef CONFIG_PPC_BOOK3S_64
+	/*
+	 * Reload kernel SPRG3 value.
+	 * No need to save guest value as usermode can't modify SPRG3.
+	 */
+	ld	r3, PACA_SPRG3(r13)
+	mtspr	SPRN_SPRG3, r3
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
 	PPC_STL	r14, VCPU_GPR(R14)(r7)
 	PPC_STL	r15, VCPU_GPR(R15)(r7)
 	PPC_STL	r16, VCPU_GPR(R16)(r7)
-- 
cgit v1.2.3


From 87916442bd0ac0aaabcca4f7fcd7eb3d8bef0d34 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Thu, 22 Aug 2013 17:08:39 +0530
Subject: powerpc/kvm: Copy the pvr value after memset

Otherwise we would clear the pvr value

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_hv.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 2b95c45e17d9..1cbcb4ca5800 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -680,13 +680,12 @@ static int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 }
 
 int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
-                                  struct kvm_sregs *sregs)
+				  struct kvm_sregs *sregs)
 {
 	int i;
 
-	sregs->pvr = vcpu->arch.pvr;
-
 	memset(sregs, 0, sizeof(struct kvm_sregs));
+	sregs->pvr = vcpu->arch.pvr;
 	for (i = 0; i < vcpu->arch.slb_max; i++) {
 		sregs->u.s.ppc64.slb[i].slbe = vcpu->arch.slb[i].orige;
 		sregs->u.s.ppc64.slb[i].slbv = vcpu->arch.slb[i].origv;
@@ -696,7 +695,7 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 }
 
 int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
-                                  struct kvm_sregs *sregs)
+				  struct kvm_sregs *sregs)
 {
 	int i, j;
 
-- 
cgit v1.2.3


From 5d226ae56f4dee608099daa599d9df0d12e3b006 Mon Sep 17 00:00:00 2001
From: Chen Gang <gang.chen@asianux.com>
Date: Mon, 22 Jul 2013 14:32:35 +0800
Subject: arch: powerpc: kvm: add signed type cast for comparation

'rmls' is 'unsigned long', lpcr_rmls() will return negative number when
failure occurs, so it need a type cast for comparing.

'lpid' is 'unsigned long', kvmppc_alloc_lpid() return negative number
when failure occurs, so it need a type cast for comparing.

Signed-off-by: Chen Gang <gang.chen@asianux.com>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_hv.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 1cbcb4ca5800..8aadd237d453 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1817,7 +1817,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 		rma_size <<= PAGE_SHIFT;
 		rmls = lpcr_rmls(rma_size);
 		err = -EINVAL;
-		if (rmls < 0) {
+		if ((long)rmls < 0) {
 			pr_err("KVM: Can't use RMA of 0x%lx bytes\n", rma_size);
 			goto out_srcu;
 		}
@@ -1882,7 +1882,7 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 	/* Allocate the guest's logical partition ID */
 
 	lpid = kvmppc_alloc_lpid();
-	if (lpid < 0)
+	if ((long)lpid < 0)
 		return -ENOMEM;
 	kvm->arch.lpid = lpid;
 
-- 
cgit v1.2.3


From 7c7b406e6b2867b8dcd638519e42b199ae222358 Mon Sep 17 00:00:00 2001
From: Thadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
Date: Wed, 17 Jul 2013 12:10:29 -0300
Subject: KVM: PPC: Book3S PR: return appropriate error when allocation fails

err was overwritten by a previous function call, and checked to be 0. If
the following page allocation fails, 0 is going to be returned instead
of -ENOMEM.

Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_pr.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index ddfaf560e503..19cbac6f9d03 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1047,11 +1047,12 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	if (err)
 		goto free_shadow_vcpu;
 
+	err = -ENOMEM;
 	p = __get_free_page(GFP_KERNEL|__GFP_ZERO);
-	/* the real shared page fills the last 4k of our page */
-	vcpu->arch.shared = (void*)(p + PAGE_SIZE - 4096);
 	if (!p)
 		goto uninit_vcpu;
+	/* the real shared page fills the last 4k of our page */
+	vcpu->arch.shared = (void *)(p + PAGE_SIZE - 4096);
 
 #ifdef CONFIG_PPC_BOOK3S_64
 	/* default to book3s_64 (970fx) */
-- 
cgit v1.2.3


From 7bfa9ad55d691f2b836b576769b11eca2cf50816 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Tue, 6 Aug 2013 14:13:44 +1000
Subject: KVM: PPC: Book3S: Fix compile error in XICS emulation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 8e44ddc3f3 ("powerpc/kvm/book3s: Add support for H_IPOLL and
H_XIRR_X in XICS emulation") added a call to get_tb() but didn't
include the header that defines it, and on some configs this means
book3s_xics.c fails to compile:

arch/powerpc/kvm/book3s_xics.c: In function ‘kvmppc_xics_hcall’:
arch/powerpc/kvm/book3s_xics.c:812:3: error: implicit declaration of function ‘get_tb’ [-Werror=implicit-function-declaration]

Cc: stable@vger.kernel.org [v3.10, v3.11]
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_xics.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index 94c1dd46b83d..a3a5cb8ee7ea 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -19,6 +19,7 @@
 #include <asm/hvcall.h>
 #include <asm/xics.h>
 #include <asm/debug.h>
+#include <asm/time.h>
 
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
-- 
cgit v1.2.3


From 9d1ffdd8f34b1f89264effd10e75ea4d6272690e Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Tue, 6 Aug 2013 14:14:33 +1000
Subject: KVM: PPC: Book3S PR: Don't corrupt guest state when kernel uses VMX

Currently the code assumes that once we load up guest FP/VSX or VMX
state into the CPU, it stays valid in the CPU registers until we
explicitly flush it to the thread_struct.  However, on POWER7,
copy_page() and memcpy() can use VMX.  These functions do flush the
VMX state to the thread_struct before using VMX instructions, but if
this happens while we have guest state in the VMX registers, and we
then re-enter the guest, we don't reload the VMX state from the
thread_struct, leading to guest corruption.  This has been observed
to cause guest processes to segfault.

To fix this, we check before re-entering the guest that all of the
bits corresponding to facilities owned by the guest, as expressed
in vcpu->arch.guest_owned_ext, are set in current->thread.regs->msr.
Any bits that have been cleared correspond to facilities that have
been used by kernel code and thus flushed to the thread_struct, so
for them we reload the state from the thread_struct.

We also need to check current->thread.regs->msr before calling
giveup_fpu() or giveup_altivec(), since if the relevant bit is
clear, the state has already been flushed to the thread_struct and
to flush it again would corrupt it.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_pr.c | 29 +++++++++++++++++++++++++----
 1 file changed, 25 insertions(+), 4 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 19cbac6f9d03..983e5eda892f 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -468,7 +468,8 @@ void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr)
 		 * both the traditional FP registers and the added VSX
 		 * registers into thread.fpr[].
 		 */
-		giveup_fpu(current);
+		if (current->thread.regs->msr & MSR_FP)
+			giveup_fpu(current);
 		for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++)
 			vcpu_fpr[i] = thread_fpr[get_fpr_index(i)];
 
@@ -483,7 +484,8 @@ void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr)
 
 #ifdef CONFIG_ALTIVEC
 	if (msr & MSR_VEC) {
-		giveup_altivec(current);
+		if (current->thread.regs->msr & MSR_VEC)
+			giveup_altivec(current);
 		memcpy(vcpu->arch.vr, t->vr, sizeof(vcpu->arch.vr));
 		vcpu->arch.vscr = t->vscr;
 	}
@@ -575,8 +577,6 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
 	printk(KERN_INFO "Loading up ext 0x%lx\n", msr);
 #endif
 
-	current->thread.regs->msr |= msr;
-
 	if (msr & MSR_FP) {
 		for (i = 0; i < ARRAY_SIZE(vcpu->arch.fpr); i++)
 			thread_fpr[get_fpr_index(i)] = vcpu_fpr[i];
@@ -598,12 +598,32 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
 #endif
 	}
 
+	current->thread.regs->msr |= msr;
 	vcpu->arch.guest_owned_ext |= msr;
 	kvmppc_recalc_shadow_msr(vcpu);
 
 	return RESUME_GUEST;
 }
 
+/*
+ * Kernel code using FP or VMX could have flushed guest state to
+ * the thread_struct; if so, get it back now.
+ */
+static void kvmppc_handle_lost_ext(struct kvm_vcpu *vcpu)
+{
+	unsigned long lost_ext;
+
+	lost_ext = vcpu->arch.guest_owned_ext & ~current->thread.regs->msr;
+	if (!lost_ext)
+		return;
+
+	if (lost_ext & MSR_FP)
+		kvmppc_load_up_fpu();
+	if (lost_ext & MSR_VEC)
+		kvmppc_load_up_altivec();
+	current->thread.regs->msr |= lost_ext;
+}
+
 int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
                        unsigned int exit_nr)
 {
@@ -892,6 +912,7 @@ program_interrupt:
 		} else {
 			kvmppc_fix_ee_before_entry();
 		}
+		kvmppc_handle_lost_ext(vcpu);
 	}
 
 	trace_kvm_book3s_reenter(r, vcpu);
-- 
cgit v1.2.3


From 8b23de29489fd63fce753db9d53055e4bbf8f616 Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Tue, 6 Aug 2013 14:15:19 +1000
Subject: KVM: PPC: Book3S PR: Make instruction fetch fallback work for system
 calls

It turns out that if we exit the guest due to a hcall instruction (sc 1),
and the loading of the instruction in the guest exit path fails for any
reason, the call to kvmppc_ld() in kvmppc_get_last_inst() fetches the
instruction after the hcall instruction rather than the hcall itself.
This in turn means that the instruction doesn't get recognized as an
hcall in kvmppc_handle_exit_pr() but gets passed to the guest kernel
as a sc instruction.  That usually results in the guest kernel getting
a return code of 38 (ENOSYS) from an hcall, which often triggers a
BUG_ON() or other failure.

This fixes the problem by adding a new variant of kvmppc_get_last_inst()
called kvmppc_get_last_sc(), which fetches the instruction if necessary
from pc - 4 rather than pc.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_book3s.h | 38 +++++++++++++++++++++++++++++++++++
 arch/powerpc/kvm/book3s_pr.c          |  2 +-
 2 files changed, 39 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 08891d07aeb6..fa19e2f1a874 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -334,6 +334,27 @@ static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu)
 	return r;
 }
 
+/*
+ * Like kvmppc_get_last_inst(), but for fetching a sc instruction.
+ * Because the sc instruction sets SRR0 to point to the following
+ * instruction, we have to fetch from pc - 4.
+ */
+static inline u32 kvmppc_get_last_sc(struct kvm_vcpu *vcpu)
+{
+	ulong pc = kvmppc_get_pc(vcpu) - 4;
+	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
+	u32 r;
+
+	/* Load the instruction manually if it failed to do so in the
+	 * exit path */
+	if (svcpu->last_inst == KVM_INST_FETCH_FAILED)
+		kvmppc_ld(vcpu, &pc, sizeof(u32), &svcpu->last_inst, false);
+
+	r = svcpu->last_inst;
+	svcpu_put(svcpu);
+	return r;
+}
+
 static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_book3s_shadow_vcpu *svcpu = svcpu_get(vcpu);
@@ -446,6 +467,23 @@ static inline u32 kvmppc_get_last_inst(struct kvm_vcpu *vcpu)
 	return vcpu->arch.last_inst;
 }
 
+/*
+ * Like kvmppc_get_last_inst(), but for fetching a sc instruction.
+ * Because the sc instruction sets SRR0 to point to the following
+ * instruction, we have to fetch from pc - 4.
+ */
+static inline u32 kvmppc_get_last_sc(struct kvm_vcpu *vcpu)
+{
+	ulong pc = kvmppc_get_pc(vcpu) - 4;
+
+	/* Load the instruction manually if it failed to do so in the
+	 * exit path */
+	if (vcpu->arch.last_inst == KVM_INST_FETCH_FAILED)
+		kvmppc_ld(vcpu, &pc, sizeof(u32), &vcpu->arch.last_inst, false);
+
+	return vcpu->arch.last_inst;
+}
+
 static inline ulong kvmppc_get_fault_dar(struct kvm_vcpu *vcpu)
 {
 	return vcpu->arch.fault_dar;
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 983e5eda892f..27db1e665959 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -792,7 +792,7 @@ program_interrupt:
 	}
 	case BOOK3S_INTERRUPT_SYSCALL:
 		if (vcpu->arch.papr_enabled &&
-		    (kvmppc_get_last_inst(vcpu) == 0x44000022) &&
+		    (kvmppc_get_last_sc(vcpu) == 0x44000022) &&
 		    !(vcpu->arch.shared->msr & MSR_PR)) {
 			/* SC 1 papr hypercalls */
 			ulong cmd = kvmppc_get_gpr(vcpu, 3);
-- 
cgit v1.2.3


From 7e48c101e0c53e6095c5f4f5e63d14df50aae8fc Mon Sep 17 00:00:00 2001
From: Paul Mackerras <paulus@samba.org>
Date: Tue, 6 Aug 2013 14:18:00 +1000
Subject: KVM: PPC: Book3S PR: Rework kvmppc_mmu_book3s_64_xlate()

This reworks kvmppc_mmu_book3s_64_xlate() to make it check the large
page bit in the hashed page table entries (HPTEs) it looks at, and
to simplify and streamline the code.  The checking of the first dword
of each HPTE is now done with a single mask and compare operation,
and all the code dealing with the matching HPTE, if we find one,
is consolidated in one place in the main line of the function flow.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_64_mmu.c | 150 +++++++++++++++++++--------------------
 1 file changed, 72 insertions(+), 78 deletions(-)

(limited to 'arch/powerpc/kvm')

diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index 739bfbadb85e..7e345e00661a 100644
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -182,10 +182,13 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	hva_t ptegp;
 	u64 pteg[16];
 	u64 avpn = 0;
+	u64 v, r;
+	u64 v_val, v_mask;
+	u64 eaddr_mask;
 	int i;
-	u8 key = 0;
+	u8 pp, key = 0;
 	bool found = false;
-	int second = 0;
+	bool second = false;
 	ulong mp_ea = vcpu->arch.magic_page_ea;
 
 	/* Magic page override */
@@ -208,8 +211,16 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 		goto no_seg_found;
 
 	avpn = kvmppc_mmu_book3s_64_get_avpn(slbe, eaddr);
+	v_val = avpn & HPTE_V_AVPN;
+
 	if (slbe->tb)
-		avpn |= SLB_VSID_B_1T;
+		v_val |= SLB_VSID_B_1T;
+	if (slbe->large)
+		v_val |= HPTE_V_LARGE;
+	v_val |= HPTE_V_VALID;
+
+	v_mask = SLB_VSID_B | HPTE_V_AVPN | HPTE_V_LARGE | HPTE_V_VALID |
+		HPTE_V_SECONDARY;
 
 do_second:
 	ptegp = kvmppc_mmu_book3s_64_get_pteg(vcpu_book3s, slbe, eaddr, second);
@@ -227,91 +238,74 @@ do_second:
 		key = 4;
 
 	for (i=0; i<16; i+=2) {
-		u64 v = pteg[i];
-		u64 r = pteg[i+1];
-
-		/* Valid check */
-		if (!(v & HPTE_V_VALID))
-			continue;
-		/* Hash check */
-		if ((v & HPTE_V_SECONDARY) != second)
-			continue;
-
-		/* AVPN compare */
-		if (HPTE_V_COMPARE(avpn, v)) {
-			u8 pp = (r & HPTE_R_PP) | key;
-			int eaddr_mask = 0xFFF;
-
-			gpte->eaddr = eaddr;
-			gpte->vpage = kvmppc_mmu_book3s_64_ea_to_vp(vcpu,
-								    eaddr,
-								    data);
-			if (slbe->large)
-				eaddr_mask = 0xFFFFFF;
-			gpte->raddr = (r & HPTE_R_RPN) | (eaddr & eaddr_mask);
-			gpte->may_execute = ((r & HPTE_R_N) ? false : true);
-			gpte->may_read = false;
-			gpte->may_write = false;
-
-			switch (pp) {
-			case 0:
-			case 1:
-			case 2:
-			case 6:
-				gpte->may_write = true;
-				/* fall through */
-			case 3:
-			case 5:
-			case 7:
-				gpte->may_read = true;
-				break;
-			}
-
-			dprintk("KVM MMU: Translated 0x%lx [0x%llx] -> 0x%llx "
-				"-> 0x%lx\n",
-				eaddr, avpn, gpte->vpage, gpte->raddr);
+		/* Check all relevant fields of 1st dword */
+		if ((pteg[i] & v_mask) == v_val) {
 			found = true;
 			break;
 		}
 	}
 
-	/* Update PTE R and C bits, so the guest's swapper knows we used the
-	 * page */
-	if (found) {
-		u32 oldr = pteg[i+1];
+	if (!found) {
+		if (second)
+			goto no_page_found;
+		v_val |= HPTE_V_SECONDARY;
+		second = true;
+		goto do_second;
+	}
 
-		if (gpte->may_read) {
-			/* Set the accessed flag */
-			pteg[i+1] |= HPTE_R_R;
-		}
-		if (gpte->may_write) {
-			/* Set the dirty flag */
-			pteg[i+1] |= HPTE_R_C;
-		} else {
-			dprintk("KVM: Mapping read-only page!\n");
-		}
+	v = pteg[i];
+	r = pteg[i+1];
+	pp = (r & HPTE_R_PP) | key;
+	eaddr_mask = 0xFFF;
+
+	gpte->eaddr = eaddr;
+	gpte->vpage = kvmppc_mmu_book3s_64_ea_to_vp(vcpu, eaddr, data);
+	if (slbe->large)
+		eaddr_mask = 0xFFFFFF;
+	gpte->raddr = (r & HPTE_R_RPN & ~eaddr_mask) | (eaddr & eaddr_mask);
+	gpte->may_execute = ((r & HPTE_R_N) ? false : true);
+	gpte->may_read = false;
+	gpte->may_write = false;
+
+	switch (pp) {
+	case 0:
+	case 1:
+	case 2:
+	case 6:
+		gpte->may_write = true;
+		/* fall through */
+	case 3:
+	case 5:
+	case 7:
+		gpte->may_read = true;
+		break;
+	}
 
-		/* Write back into the PTEG */
-		if (pteg[i+1] != oldr)
-			copy_to_user((void __user *)ptegp, pteg, sizeof(pteg));
+	dprintk("KVM MMU: Translated 0x%lx [0x%llx] -> 0x%llx "
+		"-> 0x%lx\n",
+		eaddr, avpn, gpte->vpage, gpte->raddr);
 
-		if (!gpte->may_read)
-			return -EPERM;
-		return 0;
-	} else {
-		dprintk("KVM MMU: No PTE found (ea=0x%lx sdr1=0x%llx "
-			"ptegp=0x%lx)\n",
-			eaddr, to_book3s(vcpu)->sdr1, ptegp);
-		for (i = 0; i < 16; i += 2)
-			dprintk("   %02d: 0x%llx - 0x%llx (0x%llx)\n",
-				i, pteg[i], pteg[i+1], avpn);
-
-		if (!second) {
-			second = HPTE_V_SECONDARY;
-			goto do_second;
-		}
+	/* Update PTE R and C bits, so the guest's swapper knows we used the
+	 * page */
+	if (gpte->may_read) {
+		/* Set the accessed flag */
+		r |= HPTE_R_R;
+	}
+	if (data && gpte->may_write) {
+		/* Set the dirty flag -- XXX even if not writing */
+		r |= HPTE_R_C;
+	}
+
+	/* Write back into the PTEG */
+	if (pteg[i+1] != r) {
+		pteg[i+1] = r;
+		copy_to_user((void __user *)ptegp, pteg, sizeof(pteg));
 	}
 
+	if (!gpte->may_read)
+		return -EPERM;
+	return 0;
+
 no_page_found:
 	return -ENOENT;
 
-- 
cgit v1.2.3