[RFC PATCH v2 0/4] kvmppc: HMM backend driver to manage pages of secure guest

[RFC PATCH v2 0/4] kvmppc: HMM backend driver to manage pages of secure guest

[Bharata B Rao]

Hi,

A pseries guest can be run as a secure guest on Ultravisor-enabled
POWER platforms. On such platforms, this driver will be used to manage
the movement of guest pages between the normal memory managed by
hypervisor (HV) and secure memory managed by Ultravisor (UV).

This is an early post of HMM driver patches that manage page migration
between normal and secure memory.

Private ZONE_DEVICE memory equal to the amount of secure memory
available in the platform for running secure guests is created
via a HMM device. The movement of pages between normal and secure
memory is done by ->alloc_and_copy() callback routine of migrate_vma().

The page-in or page-out requests from UV will come to HV as hcalls and
HV will call back into UV via uvcalls to satisfy these page requests.

The implementation of uvcall themselves are not present in this post
and will be posted separately.

Changes in v2
=============
- Removed the HMM PFN hash table as the same information is now being
  stored in kvm_memory_slot->arch.rmap[] array as suggested by
  Paul Mackerras.
- Addressed the review comments from v1.

Bharata B Rao (4):
  kvmppc: HMM backend driver to manage pages of secure guest
  kvmppc: Add support for shared pages in HMM driver
  kvmppc: H_SVM_INIT_START and H_SVM_INIT_DONE hcalls
  kvmppc: Handle memory plug/unplug to secure VM

 arch/powerpc/include/asm/hvcall.h    |   9 +
 arch/powerpc/include/asm/kvm_host.h  |  15 +
 arch/powerpc/include/asm/kvm_ppc.h   |  46 ++-
 arch/powerpc/include/asm/ucall-api.h |  33 ++
 arch/powerpc/kvm/Makefile            |   3 +
 arch/powerpc/kvm/book3s.c            |   5 +-
 arch/powerpc/kvm/book3s_hv.c         |  49 ++-
 arch/powerpc/kvm/book3s_hv_hmm.c     | 542 +++++++++++++++++++++++++++
 arch/powerpc/kvm/book3s_pr.c         |   3 +-
 arch/powerpc/kvm/powerpc.c           |   2 +-
 10 files changed, 700 insertions(+), 7 deletions(-)
 create mode 100644 arch/powerpc/include/asm/ucall-api.h
 create mode 100644 arch/powerpc/kvm/book3s_hv_hmm.c

-- 
2.17.1

[RFC PATCH v2 1/4] kvmppc: HMM backend driver to manage pages of secure guest

[Bharata B Rao]

HMM driver for KVM PPC to manage page transitions of
secure guest via H_SVM_PAGE_IN and H_SVM_PAGE_OUT hcalls.

H_SVM_PAGE_IN: Move the content of a normal page to secure page
H_SVM_PAGE_OUT: Move the content of a secure page to normal page

Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>
---
 arch/powerpc/include/asm/hvcall.h    |   4 +
 arch/powerpc/include/asm/kvm_host.h  |  14 +
 arch/powerpc/include/asm/kvm_ppc.h   |  28 ++
 arch/powerpc/include/asm/ucall-api.h |  22 ++
 arch/powerpc/kvm/Makefile            |   3 +
 arch/powerpc/kvm/book3s_hv.c         |  21 ++
 arch/powerpc/kvm/book3s_hv_hmm.c     | 457 +++++++++++++++++++++++++++
 7 files changed, 549 insertions(+)
 create mode 100644 arch/powerpc/include/asm/ucall-api.h
 create mode 100644 arch/powerpc/kvm/book3s_hv_hmm.c

diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index 33a4fc891947..c900f47c0a9f 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -336,6 +336,10 @@
 #define H_ENTER_NESTED		0xF804
 #define H_TLB_INVALIDATE	0xF808
 
+/* Platform-specific hcalls used by the Ultravisor */
+#define H_SVM_PAGE_IN		0xFF00
+#define H_SVM_PAGE_OUT		0xFF04
+
 /* Values for 2nd argument to H_SET_MODE */
 #define H_SET_MODE_RESOURCE_SET_CIABR		1
 #define H_SET_MODE_RESOURCE_SET_DAWR		2
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index fac6f631ed29..729bdea22250 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -842,4 +842,18 @@ static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
 
+#ifdef CONFIG_PPC_SVM
+extern int kvmppc_hmm_init(void);
+extern void kvmppc_hmm_free(void);
+extern void kvmppc_hmm_release_pfns(struct kvm_memory_slot *free);
+#else
+static inline int kvmppc_hmm_init(void)
+{
+	return 0;
+}
+
+static inline void kvmppc_hmm_free(void) {}
+static inline void kvmppc_hmm_release_pfns(struct kvm_memory_slot *free) {}
+#endif /* CONFIG_PPC_SVM */
+
 #endif /* __POWERPC_KVM_HOST_H__ */
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 9b89b1918dfc..659c80982497 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -908,4 +908,32 @@ static inline ulong kvmppc_get_ea_indexed(struct kvm_vcpu *vcpu, int ra, int rb)
 
 extern void xics_wake_cpu(int cpu);
 
+#ifdef CONFIG_PPC_SVM
+extern unsigned long kvmppc_h_svm_page_in(struct kvm *kvm,
+					  unsigned int lpid,
+					  unsigned long gra,
+					  unsigned long flags,
+					  unsigned long page_shift);
+extern unsigned long kvmppc_h_svm_page_out(struct kvm *kvm,
+					  unsigned int lpid,
+					  unsigned long gra,
+					  unsigned long flags,
+					  unsigned long page_shift);
+#else
+static inline unsigned long
+kvmppc_h_svm_page_in(struct kvm *kvm, unsigned int lpid,
+		     unsigned long gra, unsigned long flags,
+		     unsigned long page_shift)
+{
+	return H_UNSUPPORTED;
+}
+
+static inline unsigned long
+kvmppc_h_svm_page_out(struct kvm *kvm, unsigned int lpid,
+		      unsigned long gra, unsigned long flags,
+		      unsigned long page_shift)
+{
+	return H_UNSUPPORTED;
+}
+#endif
 #endif /* __POWERPC_KVM_PPC_H__ */
diff --git a/arch/powerpc/include/asm/ucall-api.h b/arch/powerpc/include/asm/ucall-api.h
new file mode 100644
index 000000000000..a84dc2abd172
--- /dev/null
+++ b/arch/powerpc/include/asm/ucall-api.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_UCALL_API_H
+#define _ASM_POWERPC_UCALL_API_H
+
+#define U_SUCCESS 0
+
+/*
+ * TODO: Dummy uvcalls, will be replaced by real calls
+ */
+static inline int uv_page_in(u64 lpid, u64 src_ra, u64 dst_gpa, u64 flags,
+			     u64 page_shift)
+{
+	return U_SUCCESS;
+}
+
+static inline int uv_page_out(u64 lpid, u64 dst_ra, u64 src_gpa, u64 flags,
+			      u64 page_shift)
+{
+	return U_SUCCESS;
+}
+
+#endif	/* _ASM_POWERPC_UCALL_API_H */
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 64f1135e7732..a9547318662e 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -76,6 +76,9 @@ kvm-hv-y += \
 	book3s_64_mmu_radix.o \
 	book3s_hv_nested.o
 
+kvm-hv-$(CONFIG_PPC_SVM) += \
+	book3s_hv_hmm.o
+
 kvm-hv-$(CONFIG_PPC_TRANSACTIONAL_MEM) += \
 	book3s_hv_tm.o
 
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index d65b961661fb..7e413605e7c4 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -74,6 +74,7 @@
 #include <asm/opal.h>
 #include <asm/xics.h>
 #include <asm/xive.h>
+#include <asm/kvm_host.h>
 
 #include "book3s.h"
 
@@ -991,6 +992,20 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 		if (nesting_enabled(vcpu->kvm))
 			ret = kvmhv_do_nested_tlbie(vcpu);
 		break;
+	case H_SVM_PAGE_IN:
+		ret = kvmppc_h_svm_page_in(vcpu->kvm,
+					   kvmppc_get_gpr(vcpu, 4),
+					   kvmppc_get_gpr(vcpu, 5),
+					   kvmppc_get_gpr(vcpu, 6),
+					   kvmppc_get_gpr(vcpu, 7));
+		break;
+	case H_SVM_PAGE_OUT:
+		ret = kvmppc_h_svm_page_out(vcpu->kvm,
+					    kvmppc_get_gpr(vcpu, 4),
+					    kvmppc_get_gpr(vcpu, 5),
+					    kvmppc_get_gpr(vcpu, 6),
+					    kvmppc_get_gpr(vcpu, 7));
+		break;
 
 	default:
 		return RESUME_HOST;
@@ -4345,6 +4360,7 @@ static void kvmppc_core_free_memslot_hv(struct kvm_memory_slot *free,
 					struct kvm_memory_slot *dont)
 {
 	if (!dont || free->arch.rmap != dont->arch.rmap) {
+		kvmppc_hmm_release_pfns(free);
 		vfree(free->arch.rmap);
 		free->arch.rmap = NULL;
 	}
@@ -5357,11 +5373,16 @@ static int kvmppc_book3s_init_hv(void)
 			no_mixing_hpt_and_radix = true;
 	}
 
+	r = kvmppc_hmm_init();
+	if (r < 0)
+		pr_err("KVM-HV: kvmppc_hmm_init failed %d\n", r);
+
 	return r;
 }
 
 static void kvmppc_book3s_exit_hv(void)
 {
+	kvmppc_hmm_free();
 	kvmppc_free_host_rm_ops();
 	if (kvmppc_radix_possible())
 		kvmppc_radix_exit();
diff --git a/arch/powerpc/kvm/book3s_hv_hmm.c b/arch/powerpc/kvm/book3s_hv_hmm.c
new file mode 100644
index 000000000000..5f2a924a4f16
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_hv_hmm.c
@@ -0,0 +1,457 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * HMM driver to manage page migration between normal and secure
+ * memory.
+ *
+ * Based on Jérôme Glisse's HMM dummy driver.
+ *
+ * Copyright 2018 Bharata B Rao, IBM Corp. <bharata@linux.ibm.com>
+ */
+
+/*
+ * A pseries guest can be run as a secure guest on Ultravisor-enabled
+ * POWER platforms. On such platforms, this driver will be used to manage
+ * the movement of guest pages between the normal memory managed by
+ * hypervisor (HV) and secure memory managed by Ultravisor (UV).
+ *
+ * Private ZONE_DEVICE memory equal to the amount of secure memory
+ * available in the platform for running secure guests is created
+ * via a HMM device. The movement of pages between normal and secure
+ * memory is done by ->alloc_and_copy() callback routine of migrate_vma().
+ *
+ * The page-in or page-out requests from UV will come to HV as hcalls and
+ * HV will call back into UV via uvcalls to satisfy these page requests.
+ *
+ * For each page that gets moved into secure memory, a HMM PFN is used
+ * on the HV side and HMM migration PTE corresponding to that PFN would be
+ * populated in the QEMU page tables.
+ */
+
+#include <linux/hmm.h>
+#include <linux/kvm_host.h>
+#include <linux/sched/mm.h>
+#include <asm/ucall-api.h>
+
+struct kvmppc_hmm_device {
+	struct hmm_device *device;
+	struct hmm_devmem *devmem;
+	unsigned long *pfn_bitmap;
+};
+
+static struct kvmppc_hmm_device kvmppc_hmm;
+spinlock_t kvmppc_hmm_lock;
+
+struct kvmppc_hmm_page_pvt {
+	unsigned long *rmap;
+	unsigned int lpid;
+	unsigned long gpa;
+};
+
+struct kvmppc_hmm_migrate_args {
+	unsigned long *rmap;
+	unsigned int lpid;
+	unsigned long gpa;
+	unsigned long page_shift;
+};
+
+#define KVMPPC_PFN_HMM		(0x1ULL << 61)
+
+static inline bool kvmppc_is_hmm_pfn(unsigned long pfn)
+{
+	return !!(pfn & KVMPPC_PFN_HMM);
+}
+
+void kvmppc_hmm_release_pfns(struct kvm_memory_slot *free)
+{
+	int i;
+
+	for (i = 0; i < free->npages; i++) {
+		unsigned long *rmap = &free->arch.rmap[i];
+
+		if (kvmppc_is_hmm_pfn(*rmap))
+			put_page(pfn_to_page(*rmap & ~KVMPPC_PFN_HMM));
+	}
+}
+
+/*
+ * Get a free HMM PFN from the pool
+ *
+ * Called when a normal page is moved to secure memory (UV_PAGE_IN). HMM
+ * PFN will be used to keep track of the secure page on HV side.
+ */
+/*
+ * TODO: In this and subsequent functions, we pass around and access
+ * individual elements of kvm_memory_slot->arch.rmap[] without any
+ * protection. Figure out the safe way to access this.
+ */
+static struct page *kvmppc_hmm_get_page(unsigned long *rmap,
+					unsigned long gpa, unsigned int lpid)
+{
+	struct page *dpage = NULL;
+	unsigned long bit, hmm_pfn;
+	unsigned long nr_pfns = kvmppc_hmm.devmem->pfn_last -
+				kvmppc_hmm.devmem->pfn_first;
+	unsigned long flags;
+	struct kvmppc_hmm_page_pvt *pvt;
+
+	if (kvmppc_is_hmm_pfn(*rmap))
+		return NULL;
+
+	spin_lock_irqsave(&kvmppc_hmm_lock, flags);
+	bit = find_first_zero_bit(kvmppc_hmm.pfn_bitmap, nr_pfns);
+	if (bit >= nr_pfns)
+		goto out;
+
+	bitmap_set(kvmppc_hmm.pfn_bitmap, bit, 1);
+	hmm_pfn = bit + kvmppc_hmm.devmem->pfn_first;
+	dpage = pfn_to_page(hmm_pfn);
+
+	if (!trylock_page(dpage))
+		goto out_clear;
+
+	*rmap = hmm_pfn | KVMPPC_PFN_HMM;
+	pvt = kzalloc(sizeof(*pvt), GFP_ATOMIC);
+	if (!pvt)
+		goto out_unlock;
+	pvt->rmap = rmap;
+	pvt->gpa = gpa;
+	pvt->lpid = lpid;
+	hmm_devmem_page_set_drvdata(dpage, (unsigned long)pvt);
+	spin_unlock_irqrestore(&kvmppc_hmm_lock, flags);
+
+	get_page(dpage);
+	return dpage;
+
+out_unlock:
+	unlock_page(dpage);
+out_clear:
+	bitmap_clear(kvmppc_hmm.pfn_bitmap,
+		     hmm_pfn - kvmppc_hmm.devmem->pfn_first, 1);
+out:
+	spin_unlock_irqrestore(&kvmppc_hmm_lock, flags);
+	return NULL;
+}
+
+/*
+ * Release the HMM PFN back to the pool
+ *
+ * Called when secure page becomes a normal page during UV_PAGE_OUT.
+ */
+static void kvmppc_hmm_put_page(struct page *page)
+{
+	unsigned long pfn = page_to_pfn(page);
+	unsigned long flags;
+	struct kvmppc_hmm_page_pvt *pvt;
+
+	spin_lock_irqsave(&kvmppc_hmm_lock, flags);
+	pvt = (struct kvmppc_hmm_page_pvt *)hmm_devmem_page_get_drvdata(page);
+	hmm_devmem_page_set_drvdata(page, 0);
+
+	bitmap_clear(kvmppc_hmm.pfn_bitmap,
+		     pfn - kvmppc_hmm.devmem->pfn_first, 1);
+	*(pvt->rmap) = 0;
+	spin_unlock_irqrestore(&kvmppc_hmm_lock, flags);
+	kfree(pvt);
+}
+
+/*
+ * migrate_vma() callback to move page from normal memory to secure memory.
+ *
+ * We don't capture the return value of uv_page_in() here because when
+ * UV asks for a page and then fails to copy it over, we don't care.
+ */
+static void
+kvmppc_hmm_migrate_alloc_and_copy(struct vm_area_struct *vma,
+				  const unsigned long *src_pfn,
+				  unsigned long *dst_pfn,
+				  unsigned long start,
+				  unsigned long end,
+				  void *private)
+{
+	struct kvmppc_hmm_migrate_args *args = private;
+	struct page *spage = migrate_pfn_to_page(*src_pfn);
+	unsigned long pfn = *src_pfn >> MIGRATE_PFN_SHIFT;
+	struct page *dpage;
+
+	*dst_pfn = 0;
+	if (!(*src_pfn & MIGRATE_PFN_MIGRATE))
+		return;
+
+	dpage = kvmppc_hmm_get_page(args->rmap, args->gpa, args->lpid);
+	if (!dpage)
+		return;
+
+	if (spage)
+		uv_page_in(args->lpid, pfn << args->page_shift,
+			   args->gpa, 0, args->page_shift);
+
+	*dst_pfn = migrate_pfn(page_to_pfn(dpage)) |
+		    MIGRATE_PFN_DEVICE | MIGRATE_PFN_LOCKED;
+}
+
+/*
+ * This migrate_vma() callback is typically used to updated device
+ * page tables after successful migration. We have nothing to do here.
+ *
+ * Also as we don't care if UV successfully copied over the page in
+ * kvmppc_hmm_migrate_alloc_and_copy(), we don't bother to check
+ * dst_pfn for any errors here.
+ */
+static void
+kvmppc_hmm_migrate_finalize_and_map(struct vm_area_struct *vma,
+				    const unsigned long *src_pfn,
+				    const unsigned long *dst_pfn,
+				    unsigned long start,
+				    unsigned long end,
+				    void *private)
+{
+}
+
+static const struct migrate_vma_ops kvmppc_hmm_migrate_ops = {
+	.alloc_and_copy = kvmppc_hmm_migrate_alloc_and_copy,
+	.finalize_and_map = kvmppc_hmm_migrate_finalize_and_map,
+};
+
+/*
+ * Move page from normal memory to secure memory.
+ */
+unsigned long
+kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
+		     unsigned long flags, unsigned long page_shift)
+{
+	unsigned long addr, end;
+	unsigned long src_pfn, dst_pfn;
+	struct kvmppc_hmm_migrate_args args;
+	struct mm_struct *mm = get_task_mm(current);
+	struct vm_area_struct *vma;
+	int srcu_idx;
+	unsigned long gfn = gpa >> page_shift;
+	struct kvm_memory_slot *slot;
+	unsigned long *rmap;
+	int ret = H_SUCCESS;
+
+	if (page_shift != PAGE_SHIFT)
+		return H_P3;
+
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+	slot = gfn_to_memslot(kvm, gfn);
+	rmap = &slot->arch.rmap[gfn - slot->base_gfn];
+	addr = gfn_to_hva(kvm, gpa >> page_shift);
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+	if (kvm_is_error_hva(addr))
+		return H_PARAMETER;
+
+	end = addr + (1UL << page_shift);
+
+	if (flags)
+		return H_P2;
+
+	args.rmap = rmap;
+	args.lpid = kvm->arch.lpid;
+	args.gpa = gpa;
+	args.page_shift = page_shift;
+
+	down_read(&mm->mmap_sem);
+	vma = find_vma_intersection(mm, addr, end);
+	if (!vma || vma->vm_start > addr || vma->vm_end < end) {
+		ret = H_PARAMETER;
+		goto out;
+	}
+	ret = migrate_vma(&kvmppc_hmm_migrate_ops, vma, addr, end,
+			  &src_pfn, &dst_pfn, &args);
+	if (ret < 0)
+		ret = H_PARAMETER;
+out:
+	up_read(&mm->mmap_sem);
+	return ret;
+}
+
+static void
+kvmppc_hmm_fault_migrate_alloc_and_copy(struct vm_area_struct *vma,
+					const unsigned long *src_pfn,
+					unsigned long *dst_pfn,
+					unsigned long start,
+					unsigned long end,
+					void *private)
+{
+	struct page *dpage, *spage;
+	struct kvmppc_hmm_page_pvt *pvt;
+	unsigned long pfn;
+	int ret = U_SUCCESS;
+
+	*dst_pfn = MIGRATE_PFN_ERROR;
+	spage = migrate_pfn_to_page(*src_pfn);
+	if (!spage || !(*src_pfn & MIGRATE_PFN_MIGRATE))
+		return;
+	if (!is_zone_device_page(spage))
+		return;
+	dpage = hmm_vma_alloc_locked_page(vma, start);
+	if (!dpage)
+		return;
+	pvt = (struct kvmppc_hmm_page_pvt *)
+	       hmm_devmem_page_get_drvdata(spage);
+
+	pfn = page_to_pfn(dpage);
+	ret = uv_page_out(pvt->lpid, pfn << PAGE_SHIFT,
+			  pvt->gpa, 0, PAGE_SHIFT);
+	if (ret == U_SUCCESS)
+		*dst_pfn = migrate_pfn(pfn) | MIGRATE_PFN_LOCKED;
+}
+
+/*
+ * This migrate_vma() callback is typically used to updated device
+ * page tables after successful migration. We have nothing to do here.
+ */
+static void
+kvmppc_hmm_fault_migrate_finalize_and_map(struct vm_area_struct *vma,
+					  const unsigned long *src_pfn,
+					  const unsigned long *dst_pfn,
+					  unsigned long start,
+					  unsigned long end,
+					  void *private)
+{
+}
+
+static const struct migrate_vma_ops kvmppc_hmm_fault_migrate_ops = {
+	.alloc_and_copy = kvmppc_hmm_fault_migrate_alloc_and_copy,
+	.finalize_and_map = kvmppc_hmm_fault_migrate_finalize_and_map,
+};
+
+/*
+ * Fault handler callback when HV touches any page that has been
+ * moved to secure memory, we ask UV to give back the page by
+ * issuing a UV_PAGE_OUT uvcall.
+ */
+static int kvmppc_hmm_devmem_fault(struct hmm_devmem *devmem,
+				   struct vm_area_struct *vma,
+				   unsigned long addr,
+				   const struct page *page,
+				   unsigned int flags,
+				   pmd_t *pmdp)
+{
+	unsigned long end = addr + PAGE_SIZE;
+	unsigned long src_pfn, dst_pfn = 0;
+
+	if (migrate_vma(&kvmppc_hmm_fault_migrate_ops, vma, addr, end,
+			&src_pfn, &dst_pfn, NULL))
+		return VM_FAULT_SIGBUS;
+	if (dst_pfn == MIGRATE_PFN_ERROR)
+		return VM_FAULT_SIGBUS;
+	return 0;
+}
+
+static void kvmppc_hmm_devmem_free(struct hmm_devmem *devmem,
+				   struct page *page)
+{
+	kvmppc_hmm_put_page(page);
+}
+
+static const struct hmm_devmem_ops kvmppc_hmm_devmem_ops = {
+	.free = kvmppc_hmm_devmem_free,
+	.fault = kvmppc_hmm_devmem_fault,
+};
+
+/*
+ * Move page from secure memory to normal memory.
+ */
+unsigned long
+kvmppc_h_svm_page_out(struct kvm *kvm, unsigned long gpa,
+		      unsigned long flags, unsigned long page_shift)
+{
+	unsigned long addr, end;
+	struct mm_struct *mm = get_task_mm(current);
+	struct vm_area_struct *vma;
+	unsigned long src_pfn, dst_pfn = 0;
+	int srcu_idx;
+	int ret = H_SUCCESS;
+
+	if (page_shift != PAGE_SHIFT)
+		return H_P3;
+
+	if (flags)
+		return H_P2;
+
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+	addr = gfn_to_hva(kvm, gpa >> page_shift);
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+	if (kvm_is_error_hva(addr))
+		return H_PARAMETER;
+
+	end = addr + (1UL << page_shift);
+
+	down_read(&mm->mmap_sem);
+	vma = find_vma_intersection(mm, addr, end);
+	if (!vma || vma->vm_start > addr || vma->vm_end < end) {
+		ret = H_PARAMETER;
+		goto out;
+	}
+	ret = migrate_vma(&kvmppc_hmm_fault_migrate_ops, vma, addr, end,
+			  &src_pfn, &dst_pfn, NULL);
+	if (ret < 0)
+		ret = H_PARAMETER;
+out:
+	up_read(&mm->mmap_sem);
+	return ret;
+}
+
+/*
+ * TODO: Number of secure pages and the page size order would probably come
+ * via DT or via some uvcall. Return 8G for now.
+ */
+static unsigned long kvmppc_get_secmem_size(void)
+{
+	return (1UL << 33);
+}
+
+static int kvmppc_hmm_pages_init(void)
+{
+	unsigned long nr_pfns = kvmppc_hmm.devmem->pfn_last -
+				kvmppc_hmm.devmem->pfn_first;
+
+	kvmppc_hmm.pfn_bitmap = kcalloc(BITS_TO_LONGS(nr_pfns),
+					 sizeof(unsigned long), GFP_KERNEL);
+	if (!kvmppc_hmm.pfn_bitmap)
+		return -ENOMEM;
+
+	spin_lock_init(&kvmppc_hmm_lock);
+
+	return 0;
+}
+
+int kvmppc_hmm_init(void)
+{
+	int ret = 0;
+	unsigned long size = kvmppc_get_secmem_size();
+
+	kvmppc_hmm.device = hmm_device_new(NULL);
+	if (IS_ERR(kvmppc_hmm.device)) {
+		ret = PTR_ERR(kvmppc_hmm.device);
+		goto out;
+	}
+
+	kvmppc_hmm.devmem = hmm_devmem_add(&kvmppc_hmm_devmem_ops,
+					   &kvmppc_hmm.device->device, size);
+	if (IS_ERR(kvmppc_hmm.devmem)) {
+		ret = PTR_ERR(kvmppc_hmm.devmem);
+		goto out_device;
+	}
+	ret = kvmppc_hmm_pages_init();
+	if (ret < 0)
+		goto out_devmem;
+
+	return ret;
+
+out_devmem:
+	hmm_devmem_remove(kvmppc_hmm.devmem);
+out_device:
+	hmm_device_put(kvmppc_hmm.device);
+out:
+	return ret;
+}
+
+void kvmppc_hmm_free(void)
+{
+	kfree(kvmppc_hmm.pfn_bitmap);
+	hmm_devmem_remove(kvmppc_hmm.devmem);
+	hmm_device_put(kvmppc_hmm.device);
+}
-- 
2.17.1

[RFC PATCH v2 2/4] kvmppc: Add support for shared pages in HMM driver

[Bharata B Rao]

A secure guest will share some of its pages with hypervisor (Eg. virtio
bounce buffers etc). Support shared pages in HMM driver.

Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>
---
 arch/powerpc/include/asm/hvcall.h |  3 ++
 arch/powerpc/kvm/book3s_hv_hmm.c  | 58 +++++++++++++++++++++++++++++--
 2 files changed, 58 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index c900f47c0a9f..34791c627f87 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -336,6 +336,9 @@
 #define H_ENTER_NESTED		0xF804
 #define H_TLB_INVALIDATE	0xF808
 
+/* Flags for H_SVM_PAGE_IN */
+#define H_PAGE_IN_SHARED        0x1
+
 /* Platform-specific hcalls used by the Ultravisor */
 #define H_SVM_PAGE_IN		0xFF00
 #define H_SVM_PAGE_OUT		0xFF04
diff --git a/arch/powerpc/kvm/book3s_hv_hmm.c b/arch/powerpc/kvm/book3s_hv_hmm.c
index 5f2a924a4f16..2730ab832330 100644
--- a/arch/powerpc/kvm/book3s_hv_hmm.c
+++ b/arch/powerpc/kvm/book3s_hv_hmm.c
@@ -45,6 +45,7 @@ struct kvmppc_hmm_page_pvt {
 	unsigned long *rmap;
 	unsigned int lpid;
 	unsigned long gpa;
+	bool skip_page_out;
 };
 
 struct kvmppc_hmm_migrate_args {
@@ -212,6 +213,45 @@ static const struct migrate_vma_ops kvmppc_hmm_migrate_ops = {
 	.finalize_and_map = kvmppc_hmm_migrate_finalize_and_map,
 };
 
+/*
+ * Shares the page with HV, thus making it a normal page.
+ *
+ * - If the page is already secure, then provision a new page and share
+ * - If the page is a normal page, share the existing page
+ *
+ * In the former case, uses the HMM fault handler to release the HMM page.
+ */
+static unsigned long
+kvmppc_share_page(struct kvm *kvm, unsigned long *rmap, unsigned long gpa,
+		  unsigned long addr, unsigned long page_shift)
+{
+
+	int ret;
+	unsigned int lpid = kvm->arch.lpid;
+	struct page *hmm_page;
+	struct kvmppc_hmm_page_pvt *pvt;
+	unsigned long pfn;
+	int srcu_idx;
+
+	if (kvmppc_is_hmm_pfn(*rmap)) {
+		hmm_page = pfn_to_page(*rmap & ~KVMPPC_PFN_HMM);
+		pvt = (struct kvmppc_hmm_page_pvt *)
+			hmm_devmem_page_get_drvdata(hmm_page);
+		pvt->skip_page_out = true;
+	}
+
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+	pfn = gfn_to_pfn(kvm, gpa >> page_shift);
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+	if (is_error_noslot_pfn(pfn))
+		return H_PARAMETER;
+
+	ret = uv_page_in(lpid, pfn << page_shift, gpa, 0, page_shift);
+	kvm_release_pfn_clean(pfn);
+
+	return (ret == U_SUCCESS) ? H_SUCCESS : H_PARAMETER;
+}
+
 /*
  * Move page from normal memory to secure memory.
  */
@@ -243,9 +283,12 @@ kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
 
 	end = addr + (1UL << page_shift);
 
-	if (flags)
+	if (flags & ~H_PAGE_IN_SHARED)
 		return H_P2;
 
+	if (flags & H_PAGE_IN_SHARED)
+		return kvmppc_share_page(kvm, rmap, gpa, addr, page_shift);
+
 	args.rmap = rmap;
 	args.lpid = kvm->arch.lpid;
 	args.gpa = gpa;
@@ -292,8 +335,17 @@ kvmppc_hmm_fault_migrate_alloc_and_copy(struct vm_area_struct *vma,
 	       hmm_devmem_page_get_drvdata(spage);
 
 	pfn = page_to_pfn(dpage);
-	ret = uv_page_out(pvt->lpid, pfn << PAGE_SHIFT,
-			  pvt->gpa, 0, PAGE_SHIFT);
+
+	/*
+	 * This same alloc_and_copy() callback is used in two cases:
+	 * - When HV touches a secure page, for which we do page-out
+	 * - When a secure page is converted to shared page, we touch
+	 *   the page to essentially discard the HMM page. In this case we
+	 *   skip page-out.
+	 */
+	if (!pvt->skip_page_out)
+		ret = uv_page_out(pvt->lpid, pfn << PAGE_SHIFT,
+				  pvt->gpa, 0, PAGE_SHIFT);
 	if (ret == U_SUCCESS)
 		*dst_pfn = migrate_pfn(pfn) | MIGRATE_PFN_LOCKED;
 }
-- 
2.17.1

[RFC PATCH v2 3/4] kvmppc: H_SVM_INIT_START and H_SVM_INIT_DONE hcalls

[Bharata B Rao]

H_SVM_INIT_START: Initiate securing a VM
H_SVM_INIT_DONE: Conclude securing a VM

During early guest init, these hcalls will be issued by UV.
As part of these hcalls, [un]register memslots with UV.

Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>
---
 arch/powerpc/include/asm/hvcall.h    |  2 ++
 arch/powerpc/include/asm/kvm_host.h  |  1 +
 arch/powerpc/include/asm/kvm_ppc.h   | 12 ++++++++++
 arch/powerpc/include/asm/ucall-api.h |  6 +++++
 arch/powerpc/kvm/book3s_hv.c         |  6 +++++
 arch/powerpc/kvm/book3s_hv_hmm.c     | 33 ++++++++++++++++++++++++++++
 6 files changed, 60 insertions(+)

diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index 34791c627f87..4872b044cca8 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -342,6 +342,8 @@
 /* Platform-specific hcalls used by the Ultravisor */
 #define H_SVM_PAGE_IN		0xFF00
 #define H_SVM_PAGE_OUT		0xFF04
+#define H_SVM_INIT_START	0xFF08
+#define H_SVM_INIT_DONE		0xFF0C
 
 /* Values for 2nd argument to H_SET_MODE */
 #define H_SET_MODE_RESOURCE_SET_CIABR		1
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 729bdea22250..174aa7e30ff7 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -296,6 +296,7 @@ struct kvm_arch {
 	struct dentry *htab_dentry;
 	struct dentry *radix_dentry;
 	struct kvm_resize_hpt *resize_hpt; /* protected by kvm->lock */
+	bool secure; /* Indicates H_SVM_INIT_START has been called */
 #endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
 	struct mutex hpt_mutex;
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 659c80982497..5f4b6a73789f 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -919,6 +919,8 @@ extern unsigned long kvmppc_h_svm_page_out(struct kvm *kvm,
 					  unsigned long gra,
 					  unsigned long flags,
 					  unsigned long page_shift);
+extern unsigned long kvmppc_h_svm_init_start(struct kvm *kvm);
+extern unsigned long kvmppc_h_svm_init_done(struct kvm *kvm);
 #else
 static inline unsigned long
 kvmppc_h_svm_page_in(struct kvm *kvm, unsigned int lpid,
@@ -935,5 +937,15 @@ kvmppc_h_svm_page_out(struct kvm *kvm, unsigned int lpid,
 {
 	return H_UNSUPPORTED;
 }
+
+static inline unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
+{
+	return H_UNSUPPORTED;
+}
+
+static inline unsigned long kvmppc_h_svm_init_done(struct kvm *kvm)
+{
+	return H_UNSUPPORTED;
+}
 #endif
 #endif /* __POWERPC_KVM_PPC_H__ */
diff --git a/arch/powerpc/include/asm/ucall-api.h b/arch/powerpc/include/asm/ucall-api.h
index a84dc2abd172..347637995b1b 100644
--- a/arch/powerpc/include/asm/ucall-api.h
+++ b/arch/powerpc/include/asm/ucall-api.h
@@ -19,4 +19,10 @@ static inline int uv_page_out(u64 lpid, u64 dst_ra, u64 src_gpa, u64 flags,
 	return U_SUCCESS;
 }
 
+static inline int uv_register_mem_slot(u64 lpid, u64 start_gpa, u64 size,
+				       u64 flags, u64 slotid)
+{
+	return 0;
+}
+
 #endif	/* _ASM_POWERPC_UCALL_API_H */
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 7e413605e7c4..d7aa85330016 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1006,6 +1006,12 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 					    kvmppc_get_gpr(vcpu, 6),
 					    kvmppc_get_gpr(vcpu, 7));
 		break;
+	case H_SVM_INIT_START:
+		ret = kvmppc_h_svm_init_start(vcpu->kvm);
+		break;
+	case H_SVM_INIT_DONE:
+		ret = kvmppc_h_svm_init_done(vcpu->kvm);
+		break;
 
 	default:
 		return RESUME_HOST;
diff --git a/arch/powerpc/kvm/book3s_hv_hmm.c b/arch/powerpc/kvm/book3s_hv_hmm.c
index 2730ab832330..e138b0edee9f 100644
--- a/arch/powerpc/kvm/book3s_hv_hmm.c
+++ b/arch/powerpc/kvm/book3s_hv_hmm.c
@@ -55,6 +55,39 @@ struct kvmppc_hmm_migrate_args {
 	unsigned long page_shift;
 };
 
+unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
+{
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+	int ret = H_SUCCESS;
+	int srcu_idx;
+
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+	slots = kvm_memslots(kvm);
+	kvm_for_each_memslot(memslot, slots) {
+		ret = uv_register_mem_slot(kvm->arch.lpid,
+					   memslot->base_gfn << PAGE_SHIFT,
+					   memslot->npages * PAGE_SIZE,
+					   0, memslot->id);
+		if (ret < 0) {
+			ret = H_PARAMETER; /* TODO: proper retval */
+			goto out;
+		}
+	}
+	kvm->arch.secure = true;
+out:
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+	return ret;
+}
+
+unsigned long kvmppc_h_svm_init_done(struct kvm *kvm)
+{
+	if (kvm->arch.secure)
+		return H_SUCCESS;
+	else
+		return H_UNSUPPORTED;
+}
+
 #define KVMPPC_PFN_HMM		(0x1ULL << 61)
 
 static inline bool kvmppc_is_hmm_pfn(unsigned long pfn)
-- 
2.17.1

[RFC PATCH v2 4/4] kvmppc: Handle memory plug/unplug to secure VM

[Bharata B Rao]

Register the new memslot with UV during plug and unregister
the memslot during unplug.

This needs addition of kvm_mr_change argument to
kvm_ops->commit_memory_region()

Signed-off-by: Bharata B Rao <bharata@linux.ibm.com>
---
 arch/powerpc/include/asm/kvm_ppc.h   |  6 ++++--
 arch/powerpc/include/asm/ucall-api.h |  5 +++++
 arch/powerpc/kvm/book3s.c            |  5 +++--
 arch/powerpc/kvm/book3s_hv.c         | 22 +++++++++++++++++++++-
 arch/powerpc/kvm/book3s_pr.c         |  3 ++-
 arch/powerpc/kvm/powerpc.c           |  2 +-
 6 files changed, 36 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 5f4b6a73789f..1ac920f2e18b 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -224,7 +224,8 @@ extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 extern void kvmppc_core_commit_memory_region(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,
 				const struct kvm_memory_slot *old,
-				const struct kvm_memory_slot *new);
+				const struct kvm_memory_slot *new,
+				enum kvm_mr_change change);
 extern int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm,
 				      struct kvm_ppc_smmu_info *info);
 extern void kvmppc_core_flush_memslot(struct kvm *kvm,
@@ -294,7 +295,8 @@ struct kvmppc_ops {
 	void (*commit_memory_region)(struct kvm *kvm,
 				     const struct kvm_userspace_memory_region *mem,
 				     const struct kvm_memory_slot *old,
-				     const struct kvm_memory_slot *new);
+				     const struct kvm_memory_slot *new,
+				     enum kvm_mr_change change);
 	int (*unmap_hva_range)(struct kvm *kvm, unsigned long start,
 			   unsigned long end);
 	int (*age_hva)(struct kvm *kvm, unsigned long start, unsigned long end);
diff --git a/arch/powerpc/include/asm/ucall-api.h b/arch/powerpc/include/asm/ucall-api.h
index 347637995b1b..02c9be311a4f 100644
--- a/arch/powerpc/include/asm/ucall-api.h
+++ b/arch/powerpc/include/asm/ucall-api.h
@@ -25,4 +25,9 @@ static inline int uv_register_mem_slot(u64 lpid, u64 start_gpa, u64 size,
 	return 0;
 }
 
+static inline int uv_unregister_mem_slot(u64 lpid, u64 dw0)
+{
+	return 0;
+}
+
 #endif	/* _ASM_POWERPC_UCALL_API_H */
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index fd9893bc7aa1..a35fb4099094 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -830,9 +830,10 @@ int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 void kvmppc_core_commit_memory_region(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,
 				const struct kvm_memory_slot *old,
-				const struct kvm_memory_slot *new)
+				const struct kvm_memory_slot *new,
+				enum kvm_mr_change change)
 {
-	kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old, new);
+	kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old, new, change);
 }
 
 int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index d7aa85330016..351ce259d8bb 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -75,6 +75,7 @@
 #include <asm/xics.h>
 #include <asm/xive.h>
 #include <asm/kvm_host.h>
+#include <asm/ucall-api.h>
 
 #include "book3s.h"
 
@@ -4392,7 +4393,8 @@ static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm,
 static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,
 				const struct kvm_memory_slot *old,
-				const struct kvm_memory_slot *new)
+				const struct kvm_memory_slot *new,
+				enum kvm_mr_change change)
 {
 	unsigned long npages = mem->memory_size >> PAGE_SHIFT;
 
@@ -4404,6 +4406,24 @@ static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm,
 	 */
 	if (npages)
 		atomic64_inc(&kvm->arch.mmio_update);
+	/*
+	 * If UV hasn't yet called H_SVM_INIT_START, don't register memslots.
+	 */
+	if (!kvm->arch.secure)
+		return;
+
+	/*
+	 * TODO: Handle KVM_MR_MOVE
+	 */
+	if (change == KVM_MR_CREATE) {
+		uv_register_mem_slot(kvm->arch.lpid,
+					   new->base_gfn << PAGE_SHIFT,
+					   new->npages * PAGE_SIZE,
+					   0,
+					   new->id);
+	} else if (change == KVM_MR_DELETE) {
+		uv_unregister_mem_slot(kvm->arch.lpid, old->id);
+	}
 }
 
 /*
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index 4efd65d9e828..3aeb17b88de7 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1913,7 +1913,8 @@ static int kvmppc_core_prepare_memory_region_pr(struct kvm *kvm,
 static void kvmppc_core_commit_memory_region_pr(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,
 				const struct kvm_memory_slot *old,
-				const struct kvm_memory_slot *new)
+				const struct kvm_memory_slot *new,
+				enum kvm_mr_change change)
 {
 	return;
 }
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 2869a299c4ed..6a7a6a101efd 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -696,7 +696,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 				   const struct kvm_memory_slot *new,
 				   enum kvm_mr_change change)
 {
-	kvmppc_core_commit_memory_region(kvm, mem, old, new);
+	kvmppc_core_commit_memory_region(kvm, mem, old, new, change);
 }
 
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
-- 
2.17.1