[PULL 0/5] ppc patch queue 2012-02-02

[PULL 0/5] ppc patch queue 2012-02-02

[Alexander Graf]

Hi Avi / Marcelo,

This is my current patch queue for ppc. Please pull.

Alex


The following changes since commit e27aad2f39d85009e8b6ce8f58b9809b22083c23:
  Avi Kivity (1):
        Merge remote-tracking branch 'upstream' into next

are available in the git repository at:

  git://github.com/agraf/linux-2.6.git for-upstream

Alexander Graf (4):
      KVM: PPC: E500: Fail init when not on e500v2
      KVM: PPC: Convert RMA allocation into generic code
      KVM: PPC: Initialize linears with zeros
      KVM: PPC: Add HPT preallocator

Paul Mackerras (1):
      KVM: Move gfn_to_memslot() to kvm_host.h

 arch/powerpc/include/asm/kvm_host.h  |    8 +-
 arch/powerpc/include/asm/kvm_ppc.h   |   10 +-
 arch/powerpc/kernel/setup_64.c       |    2 +-
 arch/powerpc/kvm/book3s_64_mmu_hv.c  |   19 +++-
 arch/powerpc/kvm/book3s_hv.c         |    8 +-
 arch/powerpc/kvm/book3s_hv_builtin.c |  209 +++++++++++++++++++++++-----------
 arch/powerpc/kvm/book3s_hv_rm_mmu.c  |   23 +----
 arch/powerpc/kvm/e500.c              |    4 +
 include/linux/kvm_host.h             |   25 ++++
 virt/kvm/kvm_main.c                  |   21 +----
 10 files changed, 205 insertions(+), 124 deletions(-)

[PATCH 1/5] KVM: Move gfn_to_memslot() to kvm_host.h

[Alexander Graf]

From: Paul Mackerras <paulus@samba.org>

This moves __gfn_to_memslot() and search_memslots() from kvm_main.c to
kvm_host.h to reduce the code duplication caused by the need for
non-modular code in arch/powerpc/kvm/book3s_hv_rm_mmu.c to call
gfn_to_memslot() in real mode.

Rather than putting gfn_to_memslot() itself in a header, which would
lead to increased code size, this puts __gfn_to_memslot() in a header.
Then, the non-modular uses of gfn_to_memslot() are changed to call
__gfn_to_memslot() instead.  This way there is only one place in the
source code that needs to be changed should the gfn_to_memslot()
implementation need to be modified.

On powerpc, the Book3S HV style of KVM has code that is called from
real mode which needs to call gfn_to_memslot() and thus needs this.
(Module code is allocated in the vmalloc region, which can't be
accessed in real mode.)

With this, we can remove builtin_gfn_to_memslot() from book3s_hv_rm_mmu.c.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Acked-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_hv_rm_mmu.c |   23 ++---------------------
 include/linux/kvm_host.h            |   25 +++++++++++++++++++++++++
 virt/kvm/kvm_main.c                 |   21 +--------------------
 3 files changed, 28 insertions(+), 41 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 5f3c60b..def880a 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -21,25 +21,6 @@
 #include <asm/synch.h>
 #include <asm/ppc-opcode.h>
 
-/*
- * Since this file is built in even if KVM is a module, we need
- * a local copy of this function for the case where kvm_main.c is
- * modular.
- */
-static struct kvm_memory_slot *builtin_gfn_to_memslot(struct kvm *kvm,
-						gfn_t gfn)
-{
-	struct kvm_memslots *slots;
-	struct kvm_memory_slot *memslot;
-
-	slots = kvm_memslots(kvm);
-	kvm_for_each_memslot(memslot, slots)
-		if (gfn >= memslot->base_gfn &&
-		      gfn < memslot->base_gfn + memslot->npages)
-			return memslot;
-	return NULL;
-}
-
 /* Translate address of a vmalloc'd thing to a linear map address */
 static void *real_vmalloc_addr(void *x)
 {
@@ -99,7 +80,7 @@ static void remove_revmap_chain(struct kvm *kvm, long pte_index,
 	rcbits = hpte_r & (HPTE_R_R | HPTE_R_C);
 	ptel = rev->guest_rpte |= rcbits;
 	gfn = hpte_rpn(ptel, hpte_page_size(hpte_v, ptel));
-	memslot = builtin_gfn_to_memslot(kvm, gfn);
+	memslot = __gfn_to_memslot(kvm_memslots(kvm), gfn);
 	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
 		return;
 
@@ -181,7 +162,7 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 	/* Find the memslot (if any) for this address */
 	gpa = (ptel & HPTE_R_RPN) & ~(psize - 1);
 	gfn = gpa >> PAGE_SHIFT;
-	memslot = builtin_gfn_to_memslot(kvm, gfn);
+	memslot = __gfn_to_memslot(kvm_memslots(kvm), gfn);
 	pa = 0;
 	is_io = ~0ul;
 	rmap = NULL;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index eada8e6..9698080 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -651,6 +651,31 @@ static inline void kvm_guest_exit(void)
 	current->flags &= ~PF_VCPU;
 }
 
+/*
+ * search_memslots() and __gfn_to_memslot() are here because they are
+ * used in non-modular code in arch/powerpc/kvm/book3s_hv_rm_mmu.c.
+ * gfn_to_memslot() itself isn't here as an inline because that would
+ * bloat other code too much.
+ */
+static inline struct kvm_memory_slot *
+search_memslots(struct kvm_memslots *slots, gfn_t gfn)
+{
+	struct kvm_memory_slot *memslot;
+
+	kvm_for_each_memslot(memslot, slots)
+		if (gfn >= memslot->base_gfn &&
+		      gfn < memslot->base_gfn + memslot->npages)
+			return memslot;
+
+	return NULL;
+}
+
+static inline struct kvm_memory_slot *
+__gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn)
+{
+	return search_memslots(slots, gfn);
+}
+
 static inline int memslot_id(struct kvm *kvm, gfn_t gfn)
 {
 	return gfn_to_memslot(kvm, gfn)->id;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 9f32bff..470e305 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -640,19 +640,6 @@ static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot)
 }
 #endif /* !CONFIG_S390 */
 
-static struct kvm_memory_slot *
-search_memslots(struct kvm_memslots *slots, gfn_t gfn)
-{
-	struct kvm_memory_slot *memslot;
-
-	kvm_for_each_memslot(memslot, slots)
-		if (gfn >= memslot->base_gfn &&
-		      gfn < memslot->base_gfn + memslot->npages)
-			return memslot;
-
-	return NULL;
-}
-
 static int cmp_memslot(const void *slot1, const void *slot2)
 {
 	struct kvm_memory_slot *s1, *s2;
@@ -1031,12 +1018,6 @@ int kvm_is_error_hva(unsigned long addr)
 }
 EXPORT_SYMBOL_GPL(kvm_is_error_hva);
 
-static struct kvm_memory_slot *__gfn_to_memslot(struct kvm_memslots *slots,
-						gfn_t gfn)
-{
-	return search_memslots(slots, gfn);
-}
-
 struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
 {
 	return __gfn_to_memslot(kvm_memslots(kvm), gfn);
@@ -1459,7 +1440,7 @@ int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 
 	ghc->gpa = gpa;
 	ghc->generation = slots->generation;
-	ghc->memslot = __gfn_to_memslot(slots, gfn);
+	ghc->memslot = gfn_to_memslot(kvm, gfn);
 	ghc->hva = gfn_to_hva_many(ghc->memslot, gfn, NULL);
 	if (!kvm_is_error_hva(ghc->hva))
 		ghc->hva += offset;
-- 
1.6.0.2

[PATCH 2/5] KVM: PPC: E500: Fail init when not on e500v2

[Alexander Graf]

When enabling the current KVM code on e500mc, I get the following oops:

    Oops: Exception in kernel mode, sig: 4 [#1]
    SMP NR_CPUS=8 P2041 RDB
    Modules linked in:
    NIP: c067df4c LR: c067df44 CTR: 00000000
    REGS: ee055ed0 TRAP: 0700   Not tainted  (3.2.0-10391-g36c5afe)
    MSR: 00029002 <CE,EE,ME>  CR: 24042022  XER: 00000000
    TASK = ee0429b0[1] 'swapper/0' THREAD: ee054000 CPU: 2
    GPR00: c067df44 ee055f80 ee0429b0 00000000 00000058 0000003f ee211600 60c6b864
    GPR08: 7cc903a6 0000002c 00000000 00000001 44042082 2d180088 00000000 00000000
    GPR16: c0000a00 00000014 3fffffff 03fe9000 00000015 7ff3be68 c06e0000 00000000
    GPR24: 00000000 00000000 00001720 c067df1c c06e0000 00000000 ee054000 c06ab51c
    NIP [c067df4c] kvmppc_e500_init+0x30/0xf8
    LR [c067df44] kvmppc_e500_init+0x28/0xf8
    Call Trace:
    [ee055f80] [c067df44] kvmppc_e500_init+0x28/0xf8 (unreliable)
    [ee055fb0] [c0001d30] do_one_initcall+0x50/0x1f0
    [ee055fe0] [c06721dc] kernel_init+0xa4/0x14c
    [ee055ff0] [c000e910] kernel_thread+0x4c/0x68
    Instruction dump:
    9421ffd0 7c0802a6 93410018 9361001c 90010034 93810020 93a10024 93c10028
    93e1002c 4bfffe7d 2c030000 408200a4 <7c1082a6> 90010008 7c1182a6 9001000c
    ---[ end trace b8ef4903fcbf9dd3 ]---

Since it doesn't make sense to run the init function on any non-supported
platform, we can just call our "is this platform supported?" function and
bail out of init() if it's not.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/e500.c |    4 ++++
 1 files changed, 4 insertions(+), 0 deletions(-)

diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index 709d82f..ddcd896 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -229,6 +229,10 @@ static int __init kvmppc_e500_init(void)
 	unsigned long ivor[3];
 	unsigned long max_ivor = 0;
 
+	r = kvmppc_core_check_processor_compat();
+	if (r)
+		return r;
+
 	r = kvmppc_booke_init();
 	if (r)
 		return r;
-- 
1.6.0.2

[PATCH 3/5] KVM: PPC: Convert RMA allocation into generic code

[Alexander Graf]

We have code to allocate big chunks of linear memory on bootup for later use.
This code is currently used for RMA allocation, but can be useful beyond that
extent.

Make it generic so we can reuse it for other stuff later.

Signed-off-by: Alexander Graf <agraf@suse.de>
Acked-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/include/asm/kvm_host.h  |    7 +-
 arch/powerpc/include/asm/kvm_ppc.h   |    8 +-
 arch/powerpc/kernel/setup_64.c       |    2 +-
 arch/powerpc/kvm/book3s_hv.c         |    8 +-
 arch/powerpc/kvm/book3s_hv_builtin.c |  175 ++++++++++++++++++++--------------
 5 files changed, 118 insertions(+), 82 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index af438b1..8221e71 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -173,12 +173,13 @@ struct kvmppc_spapr_tce_table {
 	struct page *pages[0];
 };
 
-struct kvmppc_rma_info {
+struct kvmppc_linear_info {
 	void		*base_virt;
 	unsigned long	 base_pfn;
 	unsigned long	 npages;
 	struct list_head list;
-	atomic_t 	 use_count;
+	atomic_t	 use_count;
+	int		 type;
 };
 
 /*
@@ -224,7 +225,7 @@ struct kvm_arch {
 	int tlbie_lock;
 	unsigned long lpcr;
 	unsigned long rmor;
-	struct kvmppc_rma_info *rma;
+	struct kvmppc_linear_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 a61b5b5..1c37a2f 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -128,8 +128,8 @@ extern long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 				struct kvm_create_spapr_tce *args);
 extern long kvm_vm_ioctl_allocate_rma(struct kvm *kvm,
 				struct kvm_allocate_rma *rma);
-extern struct kvmppc_rma_info *kvm_alloc_rma(void);
-extern void kvm_release_rma(struct kvmppc_rma_info *ri);
+extern struct kvmppc_linear_info *kvm_alloc_rma(void);
+extern void kvm_release_rma(struct kvmppc_linear_info *ri);
 extern int kvmppc_core_init_vm(struct kvm *kvm);
 extern void kvmppc_core_destroy_vm(struct kvm *kvm);
 extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,
@@ -187,13 +187,13 @@ static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
 	paca[cpu].kvm_hstate.xics_phys = addr;
 }
 
-extern void kvm_rma_init(void);
+extern void kvm_linear_init(void);
 
 #else
 static inline void kvmppc_set_xics_phys(int cpu, unsigned long addr)
 {}
 
-static inline void kvm_rma_init(void)
+static inline void kvm_linear_init(void)
 {}
 #endif
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 4cb8f1e..4721b0c 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -598,7 +598,7 @@ void __init setup_arch(char **cmdline_p)
 	/* Initialize the MMU context management stuff */
 	mmu_context_init();
 
-	kvm_rma_init();
+	kvm_linear_init();
 
 	ppc64_boot_msg(0x15, "Setup Done");
 }
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 3580db8..ce1cac7 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1055,7 +1055,7 @@ 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_rma_info *ri = vma->vm_file->private_data;
+	struct kvmppc_linear_info *ri = vma->vm_file->private_data;
 	struct page *page;
 
 	if (vmf->pgoff >= ri->npages)
@@ -1080,7 +1080,7 @@ 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_rma_info *ri = filp->private_data;
+	struct kvmppc_linear_info *ri = filp->private_data;
 
 	kvm_release_rma(ri);
 	return 0;
@@ -1093,7 +1093,7 @@ static struct file_operations kvm_rma_fops = {
 
 long kvm_vm_ioctl_allocate_rma(struct kvm *kvm, struct kvm_allocate_rma *ret)
 {
-	struct kvmppc_rma_info *ri;
+	struct kvmppc_linear_info *ri;
 	long fd;
 
 	ri = kvm_alloc_rma();
@@ -1212,7 +1212,7 @@ static int kvmppc_hv_setup_rma(struct kvm_vcpu *vcpu)
 {
 	int err = 0;
 	struct kvm *kvm = vcpu->kvm;
-	struct kvmppc_rma_info *ri = NULL;
+	struct kvmppc_linear_info *ri = NULL;
 	unsigned long hva;
 	struct kvm_memory_slot *memslot;
 	struct vm_area_struct *vma;
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index a795a13..1c7e6ab 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -18,6 +18,14 @@
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
 
+#define KVM_LINEAR_RMA		0
+
+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);
+
+/*************** RMA *************/
+
 /*
  * This maintains a list of RMAs (real mode areas) for KVM guests to use.
  * Each RMA has to be physically contiguous and of a size that the
@@ -29,32 +37,6 @@
 static unsigned long kvm_rma_size = 64 << 20;	/* 64MB */
 static unsigned long kvm_rma_count;
 
-static int __init early_parse_rma_size(char *p)
-{
-	if (!p)
-		return 1;
-
-	kvm_rma_size = memparse(p, &p);
-
-	return 0;
-}
-early_param("kvm_rma_size", early_parse_rma_size);
-
-static int __init early_parse_rma_count(char *p)
-{
-	if (!p)
-		return 1;
-
-	kvm_rma_count = simple_strtoul(p, NULL, 0);
-
-	return 0;
-}
-early_param("kvm_rma_count", early_parse_rma_count);
-
-static struct kvmppc_rma_info *rma_info;
-static LIST_HEAD(free_rmas);
-static DEFINE_SPINLOCK(rma_lock);
-
 /* Work out RMLS (real mode limit selector) field value for a given RMA size.
    Assumes POWER7 or PPC970. */
 static inline int lpcr_rmls(unsigned long rma_size)
@@ -81,45 +63,73 @@ static inline int lpcr_rmls(unsigned long rma_size)
 	}
 }
 
-/*
- * Called at boot time while the bootmem allocator is active,
- * to allocate contiguous physical memory for the real memory
- * areas for guests.
- */
-void __init kvm_rma_init(void)
+static int __init early_parse_rma_size(char *p)
+{
+	if (!p)
+		return 1;
+
+	kvm_rma_size = memparse(p, &p);
+
+	return 0;
+}
+early_param("kvm_rma_size", early_parse_rma_size);
+
+static int __init early_parse_rma_count(char *p)
+{
+	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);
+}
+EXPORT_SYMBOL_GPL(kvm_alloc_rma);
+
+void kvm_release_rma(struct kvmppc_linear_info *ri)
+{
+	kvm_release_linear(ri);
+}
+EXPORT_SYMBOL_GPL(kvm_release_rma);
+
+/*************** 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 *rma;
+	void *linear;
 	struct page *pg;
+	const char *typestr;
+	struct kvmppc_linear_info *linear_info;
 
-	/* 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)
+	if (!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;
-	}
-
-	npages = kvm_rma_size >> PAGE_SHIFT;
-	rma_info = alloc_bootmem(kvm_rma_count * sizeof(struct kvmppc_rma_info));
-	for (i = 0; i < kvm_rma_count; ++i) {
-		rma = alloc_bootmem_align(kvm_rma_size, kvm_rma_size);
-		pr_info("Allocated KVM RMA at %p (%ld MB)\n", rma,
-			kvm_rma_size >> 20);
-		rma_info[i].base_virt = rma;
-		rma_info[i].base_pfn = __pa(rma) >> PAGE_SHIFT;
-		rma_info[i].npages = npages;
-		list_add_tail(&rma_info[i].list, &free_rmas);
-		atomic_set(&rma_info[i].use_count, 0);
-
-		pg = pfn_to_page(rma_info[i].base_pfn);
+	typestr = (type == KVM_LINEAR_RMA) ? "RMA" : "";
+
+	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_info("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;
@@ -127,30 +137,55 @@ void __init kvm_rma_init(void)
 	}
 }
 
-struct kvmppc_rma_info *kvm_alloc_rma(void)
+static struct kvmppc_linear_info *kvm_alloc_linear(int type)
 {
-	struct kvmppc_rma_info *ri;
+	struct kvmppc_linear_info *ri;
 
 	ri = NULL;
-	spin_lock(&rma_lock);
-	if (!list_empty(&free_rmas)) {
-		ri = list_first_entry(&free_rmas, struct kvmppc_rma_info, list);
+	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);
+		break;
 	}
-	spin_unlock(&rma_lock);
+	spin_unlock(&linear_lock);
 	return ri;
 }
-EXPORT_SYMBOL_GPL(kvm_alloc_rma);
 
-void kvm_release_rma(struct kvmppc_rma_info *ri)
+static void kvm_release_linear(struct kvmppc_linear_info *ri)
 {
 	if (atomic_dec_and_test(&ri->use_count)) {
-		spin_lock(&rma_lock);
-		list_add_tail(&ri->list, &free_rmas);
-		spin_unlock(&rma_lock);
+		spin_lock(&linear_lock);
+		list_add_tail(&ri->list, &free_linears);
+		spin_unlock(&linear_lock);
 
 	}
 }
-EXPORT_SYMBOL_GPL(kvm_release_rma);
 
+/*
+ * 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);
+}
-- 
1.6.0.2

[PATCH 4/5] KVM: PPC: Initialize linears with zeros

[Alexander Graf]

RMAs and HPT preallocated spaces should be zeroed, so we don't accidently
leak information from previous VM executions.

Signed-off-by: Alexander Graf <agraf@suse.de>
Acked-by: Paul Mackerras <paulus@samba.org>
---
 arch/powerpc/kvm/book3s_hv_builtin.c |    1 +
 1 files changed, 1 insertions(+), 0 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 1c7e6ab..7caed1d 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -152,6 +152,7 @@ static struct kvmppc_linear_info *kvm_alloc_linear(int type)
 		break;
 	}
 	spin_unlock(&linear_lock);
+	memset(ri->base_virt, 0, ri->npages << PAGE_SHIFT);
 	return ri;
 }
 
-- 
1.6.0.2

[PATCH 5/5] KVM: PPC: Add HPT preallocator

[Alexander Graf]

We're currently allocating 16MB of linear memory on demand when creating
a guest. That does work some times, but finding 16MB of linear memory
available in the system at runtime is definitely not a given.

So let's add another command line option similar to the RMA preallocator,
that we can use to keep a pool of page tables around. Now, when a guest
gets created it has a pretty low chance of receiving an OOM.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_host.h  |    1 +
 arch/powerpc/include/asm/kvm_ppc.h   |    2 +
 arch/powerpc/kvm/book3s_64_mmu_hv.c  |   19 ++++++++++++++--
 arch/powerpc/kvm/book3s_hv_builtin.c |   39 +++++++++++++++++++++++++++++++++-
 4 files changed, 57 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 8221e71..1843d5d 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -235,6 +235,7 @@ struct kvm_arch {
 	int slot_npages[KVM_MEM_SLOTS_NUM];
 	unsigned short last_vcpu[NR_CPUS];
 	struct kvmppc_vcore *vcores[KVM_MAX_VCORES];
+	struct kvmppc_linear_info *hpt_li;
 #endif /* CONFIG_KVM_BOOK3S_64_HV */
 };
 
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 1c37a2f..9d6dee0 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -130,6 +130,8 @@ 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 int kvmppc_core_init_vm(struct kvm *kvm);
 extern void kvmppc_core_destroy_vm(struct kvm *kvm);
 extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index 783cd35..ddc485a 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -44,10 +44,20 @@ long kvmppc_alloc_hpt(struct kvm *kvm)
 	unsigned long hpt;
 	unsigned long lpid;
 	struct revmap_entry *rev;
+	struct kvmppc_linear_info *li;
 
 	/* Allocate guest's hashed page table */
-	hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT|__GFP_NOWARN,
-			       HPT_ORDER - PAGE_SHIFT);
+	li = kvm_alloc_hpt();
+	if (li) {
+		/* using preallocated memory */
+		hpt = (ulong)li->base_virt;
+		kvm->arch.hpt_li = li;
+	} else {
+		/* using dynamic memory */
+		hpt = __get_free_pages(GFP_KERNEL|__GFP_ZERO|__GFP_REPEAT|
+				       __GFP_NOWARN, HPT_ORDER - PAGE_SHIFT);
+	}
+
 	if (!hpt) {
 		pr_err("kvm_alloc_hpt: Couldn't alloc HPT\n");
 		return -ENOMEM;
@@ -88,7 +98,10 @@ void kvmppc_free_hpt(struct kvm *kvm)
 {
 	clear_bit(kvm->arch.lpid, lpid_inuse);
 	vfree(kvm->arch.revmap);
-	free_pages(kvm->arch.hpt_virt, HPT_ORDER - PAGE_SHIFT);
+	if (kvm->arch.hpt_li)
+		kvm_release_hpt(kvm->arch.hpt_li);
+	else
+		free_pages(kvm->arch.hpt_virt, HPT_ORDER - PAGE_SHIFT);
 }
 
 /* Bits in first HPTE dword for pagesize 4k, 64k or 16M */
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index 7caed1d..bed1279 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -19,6 +19,7 @@
 #include <asm/kvm_book3s.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);
@@ -97,6 +98,39 @@ 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)
+{
+	if (!p)
+		return 1;
+
+	kvm_hpt_count = simple_strtoul(p, NULL, 0);
+
+	return 0;
+}
+early_param("kvm_hpt_count", early_parse_hpt_count);
+
+struct kvmppc_linear_info *kvm_alloc_hpt(void)
+{
+	return kvm_alloc_linear(KVM_LINEAR_HPT);
+}
+EXPORT_SYMBOL_GPL(kvm_alloc_hpt);
+
+void kvm_release_hpt(struct kvmppc_linear_info *li)
+{
+	kvm_release_linear(li);
+}
+EXPORT_SYMBOL_GPL(kvm_release_hpt);
+
 /*************** generic *************/
 
 static LIST_HEAD(free_linears);
@@ -114,7 +148,7 @@ static void __init kvm_linear_init_one(ulong size, int count, int type)
 	if (!count)
 		return;
 
-	typestr = (type == KVM_LINEAR_RMA) ? "RMA" : "";
+	typestr = (type == KVM_LINEAR_RMA) ? "RMA" : "HPT";
 
 	npages = size >> PAGE_SHIFT;
 	linear_info = alloc_bootmem(count * sizeof(struct kvmppc_linear_info));
@@ -173,6 +207,9 @@ static void kvm_release_linear(struct kvmppc_linear_info *ri)
  */
 void __init kvm_linear_init(void)
 {
+	/* HPT */
+	kvm_linear_init_one(1 << HPT_ORDER, kvm_hpt_count, KVM_LINEAR_HPT);
+
 	/* RMA */
 	/* Only do this on PPC970 in HV mode */
 	if (!cpu_has_feature(CPU_FTR_HVMODE) ||
-- 
1.6.0.2

Re: [PULL 0/5] ppc patch queue 2012-02-02

[Avi Kivity]

On 02/02/2012 05:04 AM, Alexander Graf wrote:
> Hi Avi / Marcelo,
>
> This is my current patch queue for ppc. Please pull.
>

Pulled, thanks.

-- 
error compiling committee.c: too many arguments to function