KVM: PPC: Allocate RMAs (Real Mode Areas) at boot for use by guests

This adds infrastructure which will be needed to allow book3s_hv KVM to
run on older POWER processors, including PPC970, which don't support
the Virtual Real Mode Area (VRMA) facility, but only the Real Mode
Offset (RMO) facility.  These processors require a physically
contiguous, aligned area of memory for each guest.  When the guest does
an access in real mode (MMU off), the address is compared against a
limit value, and if it is lower, the address is ORed with an offset
value (from the Real Mode Offset Register (RMOR)) and the result becomes
the real address for the access.  The size of the RMA has to be one of
a set of supported values, which usually includes 64MB, 128MB, 256MB
and some larger powers of 2.

Since we are unlikely to be able to allocate 64MB or more of physically
contiguous memory after the kernel has been running for a while, we
allocate a pool of RMAs at boot time using the bootmem allocator.  The
size and number of the RMAs can be set using the kvm_rma_size=xx and
kvm_rma_count=xx kernel command line options.

KVM exports a new capability, KVM_CAP_PPC_RMA, to signal the availability
of the pool of preallocated RMAs.  The capability value is 1 if the
processor can use an RMA but doesn't require one (because it supports
the VRMA facility), or 2 if the processor requires an RMA for each guest.

This adds a new ioctl, KVM_ALLOCATE_RMA, which allocates an RMA from the
pool and returns a file descriptor which can be used to map the RMA.  It
also returns the size of the RMA in the argument structure.

Having an RMA means we will get multiple KMV_SET_USER_MEMORY_REGION
ioctl calls from userspace.  To cope with this, we now preallocate the
kvm->arch.ram_pginfo array when the VM is created with a size sufficient
for up to 64GB of guest memory.  Subsequently we will get rid of this
array and use memory associated with each memslot instead.

This moves most of the code that translates the user addresses into
host pfns (page frame numbers) out of kvmppc_prepare_vrma up one level
to kvmppc_core_prepare_memory_region.  Also, instead of having to look
up the VMA for each page in order to check the page size, we now check
that the pages we get are compound pages of 16MB.  However, if we are
adding memory that is mapped to an RMA, we don't bother with calling
get_user_pages_fast and instead just offset from the base pfn for the
RMA.

Typically the RMA gets added after vcpus are created, which makes it
inconvenient to have the LPCR (logical partition control register) value
in the vcpu->arch struct, since the LPCR controls whether the processor
uses RMA or VRMA for the guest.  This moves the LPCR value into the
kvm->arch struct and arranges for the MER (mediated external request)
bit, which is the only bit that varies between vcpus, to be set in
assembly code when going into the guest if there is a pending external
interrupt request.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Alexander Graf <agraf@suse.de>

1 files changed, 152 insertions, 0 deletions

diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
new file mode 100644
index 000000000000..736df3cbbc55
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -0,0 +1,152 @@
+/*
+ * Copyright 2011 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/preempt.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
+#include <linux/bootmem.h>
+#include <linux/init.h>
+
+#include <asm/cputable.h>
+#include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s.h>
+
+/*
+ * 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
+ * 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.
+ */
+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. */
+static inline int lpcr_rmls(unsigned long rma_size)
+{
+	switch (rma_size) {
+	case 32ul << 20:	/* 32 MB */
+		return 8;
+	case 64ul << 20:	/* 64 MB */
+		return 3;
+	case 128ul << 20:	/* 128 MB */
+		return 7;
+	case 256ul << 20:	/* 256 MB */
+		return 4;
+	case 1ul << 30:		/* 1 GB */
+		return 2;
+	case 16ul << 30:	/* 16 GB */
+		return 1;
+	case 256ul << 30:	/* 256 GB */
+		return 0;
+	default:
+		return -1;
+	}
+}
+
+/*
+ * Called at boot time while the bootmem allocator is active,
+ * to allocate contiguous physical memory for the real memory
+ * areas for guests.
+ */
+void kvm_rma_init(void)
+{
+	unsigned long i;
+	unsigned long j, npages;
+	void *rma;
+	struct page *pg;
+
+	/* Only do this on POWER7 in HV mode */
+	if (!cpu_has_feature(CPU_FTR_HVMODE_206))
+		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;
+	}
+
+	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);
+		for (j = 0; j < npages; ++j) {
+			atomic_inc(&pg->_count);
+			++pg;
+		}
+	}
+}
+
+struct kvmppc_rma_info *kvm_alloc_rma(void)
+{
+	struct kvmppc_rma_info *ri;
+
+	ri = NULL;
+	spin_lock(&rma_lock);
+	if (!list_empty(&free_rmas)) {
+		ri = list_first_entry(&free_rmas, struct kvmppc_rma_info, list);
+		list_del(&ri->list);
+		atomic_inc(&ri->use_count);
+	}
+	spin_unlock(&rma_lock);
+	return ri;
+}
+EXPORT_SYMBOL_GPL(kvm_alloc_rma);
+
+void kvm_release_rma(struct kvmppc_rma_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);
+
+	}
+}
+EXPORT_SYMBOL_GPL(kvm_release_rma);
+