kvm: rename pfn_t to kvm_pfn_t

To date, we have implemented two I/O usage models for persistent memory,
PMEM (a persistent "ram disk") and DAX (mmap persistent memory into
userspace).  This series adds a third, DAX-GUP, that allows DAX mappings
to be the target of direct-i/o.  It allows userspace to coordinate
DMA/RDMA from/to persistent memory.

The implementation leverages the ZONE_DEVICE mm-zone that went into
4.3-rc1 (also discussed at kernel summit) to flag pages that are owned
and dynamically mapped by a device driver.  The pmem driver, after
mapping a persistent memory range into the system memmap via
devm_memremap_pages(), arranges for DAX to distinguish pfn-only versus
page-backed pmem-pfns via flags in the new pfn_t type.

The DAX code, upon seeing a PFN_DEV+PFN_MAP flagged pfn, flags the
resulting pte(s) inserted into the process page tables with a new
_PAGE_DEVMAP flag.  Later, when get_user_pages() is walking ptes it keys
off _PAGE_DEVMAP to pin the device hosting the page range active.
Finally, get_page() and put_page() are modified to take references
against the device driver established page mapping.

Finally, this need for "struct page" for persistent memory requires
memory capacity to store the memmap array.  Given the memmap array for a
large pool of persistent may exhaust available DRAM introduce a
mechanism to allocate the memmap from persistent memory.  The new
"struct vmem_altmap *" parameter to devm_memremap_pages() enables
arch_add_memory() to use reserved pmem capacity rather than the page
allocator.

This patch (of 18):

The core has developed a need for a "pfn_t" type [1].  Move the existing
pfn_t in KVM to kvm_pfn_t [2].

[1]: https://lists.01.org/pipermail/linux-nvdimm/2015-September/002199.html
[2]: https://lists.01.org/pipermail/linux-nvdimm/2015-September/002218.html

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Acked-by: Christoffer Dall <christoffer.dall@linaro.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

6 files changed, 31 insertions, 29 deletions

diff --git a/arch/x86/kvm/iommu.c b/arch/x86/kvm/iommu.c
index 5c520ebf6343..a22a488b4622 100644
--- a/arch/x86/kvm/iommu.c
+++ b/arch/x86/kvm/iommu.c
@@ -43,11 +43,11 @@ static int kvm_iommu_unmap_memslots(struct kvm *kvm);
 static void kvm_iommu_put_pages(struct kvm *kvm,
 				gfn_t base_gfn, unsigned long npages);
 
-static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn,
+static kvm_pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn,
 			   unsigned long npages)
 {
 	gfn_t end_gfn;
-	pfn_t pfn;
+	kvm_pfn_t pfn;
 
 	pfn     = gfn_to_pfn_memslot(slot, gfn);
 	end_gfn = gfn + npages;
@@ -62,7 +62,8 @@ static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn,
 	return pfn;
 }
 
-static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages)
+static void kvm_unpin_pages(struct kvm *kvm, kvm_pfn_t pfn,
+		unsigned long npages)
 {
 	unsigned long i;
 
@@ -73,7 +74,7 @@ static void kvm_unpin_pages(struct kvm *kvm, pfn_t pfn, unsigned long npages)
 int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
 {
 	gfn_t gfn, end_gfn;
-	pfn_t pfn;
+	kvm_pfn_t pfn;
 	int r = 0;
 	struct iommu_domain *domain = kvm->arch.iommu_domain;
 	int flags;
@@ -275,7 +276,7 @@ static void kvm_iommu_put_pages(struct kvm *kvm,
 {
 	struct iommu_domain *domain;
 	gfn_t end_gfn, gfn;
-	pfn_t pfn;
+	kvm_pfn_t pfn;
 	u64 phys;
 
 	domain  = kvm->arch.iommu_domain;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 420a5ca3c0ee..95a955de5964 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -259,7 +259,7 @@ static unsigned get_mmio_spte_access(u64 spte)
 }
 
 static bool set_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn,
-			  pfn_t pfn, unsigned access)
+			  kvm_pfn_t pfn, unsigned access)
 {
 	if (unlikely(is_noslot_pfn(pfn))) {
 		mark_mmio_spte(vcpu, sptep, gfn, access);
@@ -320,7 +320,7 @@ static int is_last_spte(u64 pte, int level)
 	return 0;
 }
 
-static pfn_t spte_to_pfn(u64 pte)
+static kvm_pfn_t spte_to_pfn(u64 pte)
 {
 	return (pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
 }
@@ -582,7 +582,7 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte)
  */
 static int mmu_spte_clear_track_bits(u64 *sptep)
 {
-	pfn_t pfn;
+	kvm_pfn_t pfn;
 	u64 old_spte = *sptep;
 
 	if (!spte_has_volatile_bits(old_spte))
@@ -1372,7 +1372,7 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
 	int need_flush = 0;
 	u64 new_spte;
 	pte_t *ptep = (pte_t *)data;
-	pfn_t new_pfn;
+	kvm_pfn_t new_pfn;
 
 	WARN_ON(pte_huge(*ptep));
 	new_pfn = pte_pfn(*ptep);
@@ -2450,7 +2450,7 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn,
 	return 0;
 }
 
-static bool kvm_is_mmio_pfn(pfn_t pfn)
+static bool kvm_is_mmio_pfn(kvm_pfn_t pfn)
 {
 	if (pfn_valid(pfn))
 		return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn));
@@ -2460,7 +2460,7 @@ static bool kvm_is_mmio_pfn(pfn_t pfn)
 
 static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		    unsigned pte_access, int level,
-		    gfn_t gfn, pfn_t pfn, bool speculative,
+		    gfn_t gfn, kvm_pfn_t pfn, bool speculative,
 		    bool can_unsync, bool host_writable)
 {
 	u64 spte;
@@ -2539,7 +2539,7 @@ done:
 }
 
 static bool mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access,
-			 int write_fault, int level, gfn_t gfn, pfn_t pfn,
+			 int write_fault, int level, gfn_t gfn, kvm_pfn_t pfn,
 			 bool speculative, bool host_writable)
 {
 	int was_rmapped = 0;
@@ -2602,7 +2602,7 @@ static bool mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, unsigned pte_access,
 	return emulate;
 }
 
-static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn,
+static kvm_pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn,
 				     bool no_dirty_log)
 {
 	struct kvm_memory_slot *slot;
@@ -2684,7 +2684,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep)
 }
 
 static int __direct_map(struct kvm_vcpu *vcpu, int write, int map_writable,
-			int level, gfn_t gfn, pfn_t pfn, bool prefault)
+			int level, gfn_t gfn, kvm_pfn_t pfn, bool prefault)
 {
 	struct kvm_shadow_walk_iterator iterator;
 	struct kvm_mmu_page *sp;
@@ -2732,7 +2732,7 @@ static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *
 	send_sig_info(SIGBUS, &info, tsk);
 }
 
-static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, pfn_t pfn)
+static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn)
 {
 	/*
 	 * Do not cache the mmio info caused by writing the readonly gfn
@@ -2752,9 +2752,10 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, pfn_t pfn)
 }
 
 static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
-					gfn_t *gfnp, pfn_t *pfnp, int *levelp)
+					gfn_t *gfnp, kvm_pfn_t *pfnp,
+					int *levelp)
 {
-	pfn_t pfn = *pfnp;
+	kvm_pfn_t pfn = *pfnp;
 	gfn_t gfn = *gfnp;
 	int level = *levelp;
 
@@ -2793,7 +2794,7 @@ static void transparent_hugepage_adjust(struct kvm_vcpu *vcpu,
 }
 
 static bool handle_abnormal_pfn(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
-				pfn_t pfn, unsigned access, int *ret_val)
+				kvm_pfn_t pfn, unsigned access, int *ret_val)
 {
 	bool ret = true;
 
@@ -2947,7 +2948,7 @@ exit:
 }
 
 static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
-			 gva_t gva, pfn_t *pfn, bool write, bool *writable);
+			 gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable);
 static void make_mmu_pages_available(struct kvm_vcpu *vcpu);
 
 static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
@@ -2956,7 +2957,7 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, u32 error_code,
 	int r;
 	int level;
 	bool force_pt_level = false;
-	pfn_t pfn;
+	kvm_pfn_t pfn;
 	unsigned long mmu_seq;
 	bool map_writable, write = error_code & PFERR_WRITE_MASK;
 
@@ -3410,7 +3411,7 @@ static bool can_do_async_pf(struct kvm_vcpu *vcpu)
 }
 
 static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
-			 gva_t gva, pfn_t *pfn, bool write, bool *writable)
+			 gva_t gva, kvm_pfn_t *pfn, bool write, bool *writable)
 {
 	struct kvm_memory_slot *slot;
 	bool async;
@@ -3448,7 +3449,7 @@ check_hugepage_cache_consistency(struct kvm_vcpu *vcpu, gfn_t gfn, int level)
 static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
 			  bool prefault)
 {
-	pfn_t pfn;
+	kvm_pfn_t pfn;
 	int r;
 	int level;
 	bool force_pt_level;
@@ -4601,7 +4602,7 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
 	u64 *sptep;
 	struct rmap_iterator iter;
 	int need_tlb_flush = 0;
-	pfn_t pfn;
+	kvm_pfn_t pfn;
 	struct kvm_mmu_page *sp;
 
 restart:
diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c
index 1cee3ec20dd2..dcce533d420c 100644
--- a/arch/x86/kvm/mmu_audit.c
+++ b/arch/x86/kvm/mmu_audit.c
@@ -97,7 +97,7 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level)
 {
 	struct kvm_mmu_page *sp;
 	gfn_t gfn;
-	pfn_t pfn;
+	kvm_pfn_t pfn;
 	hpa_t hpa;
 
 	sp = page_header(__pa(sptep));
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 91e939b486d1..6c9fed957cce 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -456,7 +456,7 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 {
 	unsigned pte_access;
 	gfn_t gfn;
-	pfn_t pfn;
+	kvm_pfn_t pfn;
 
 	if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte))
 		return false;
@@ -551,7 +551,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
 static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 			 struct guest_walker *gw,
 			 int write_fault, int hlevel,
-			 pfn_t pfn, bool map_writable, bool prefault)
+			 kvm_pfn_t pfn, bool map_writable, bool prefault)
 {
 	struct kvm_mmu_page *sp = NULL;
 	struct kvm_shadow_walk_iterator it;
@@ -694,7 +694,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
 	int user_fault = error_code & PFERR_USER_MASK;
 	struct guest_walker walker;
 	int r;
-	pfn_t pfn;
+	kvm_pfn_t pfn;
 	int level = PT_PAGE_TABLE_LEVEL;
 	bool force_pt_level = false;
 	unsigned long mmu_seq;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 04d61d496b14..e2951b6edbbc 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -4251,7 +4251,7 @@ out:
 static int init_rmode_identity_map(struct kvm *kvm)
 {
 	int i, idx, r = 0;
-	pfn_t identity_map_pfn;
+	kvm_pfn_t identity_map_pfn;
 	u32 tmp;
 
 	if (!enable_ept)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f53f5b13c677..4244c2baf57d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5148,7 +5148,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t cr2,
 				  int emulation_type)
 {
 	gpa_t gpa = cr2;
-	pfn_t pfn;
+	kvm_pfn_t pfn;
 
 	if (emulation_type & EMULTYPE_NO_REEXECUTE)
 		return false;