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>
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 314c777..a11cfd2 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -111,7 +111,7 @@
static void kvm_io_bus_destroy(struct kvm_io_bus *bus);
-static void kvm_release_pfn_dirty(pfn_t pfn);
+static void kvm_release_pfn_dirty(kvm_pfn_t pfn);
static void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn);
__visible bool kvm_rebooting;
@@ -119,7 +119,7 @@
static bool largepages_enabled = true;
-bool kvm_is_reserved_pfn(pfn_t pfn)
+bool kvm_is_reserved_pfn(kvm_pfn_t pfn)
{
if (pfn_valid(pfn))
return PageReserved(pfn_to_page(pfn));
@@ -1289,7 +1289,7 @@
* true indicates success, otherwise false is returned.
*/
static bool hva_to_pfn_fast(unsigned long addr, bool atomic, bool *async,
- bool write_fault, bool *writable, pfn_t *pfn)
+ bool write_fault, bool *writable, kvm_pfn_t *pfn)
{
struct page *page[1];
int npages;
@@ -1322,7 +1322,7 @@
* 1 indicates success, -errno is returned if error is detected.
*/
static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
- bool *writable, pfn_t *pfn)
+ bool *writable, kvm_pfn_t *pfn)
{
struct page *page[1];
int npages = 0;
@@ -1386,11 +1386,11 @@
* 2): @write_fault = false && @writable, @writable will tell the caller
* whether the mapping is writable.
*/
-static pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
+static kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
bool write_fault, bool *writable)
{
struct vm_area_struct *vma;
- pfn_t pfn = 0;
+ kvm_pfn_t pfn = 0;
int npages;
/* we can do it either atomically or asynchronously, not both */
@@ -1431,8 +1431,9 @@
return pfn;
}
-pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic,
- bool *async, bool write_fault, bool *writable)
+kvm_pfn_t __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn,
+ bool atomic, bool *async, bool write_fault,
+ bool *writable)
{
unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault);
@@ -1453,7 +1454,7 @@
}
EXPORT_SYMBOL_GPL(__gfn_to_pfn_memslot);
-pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
+kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
bool *writable)
{
return __gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn, false, NULL,
@@ -1461,37 +1462,37 @@
}
EXPORT_SYMBOL_GPL(gfn_to_pfn_prot);
-pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn)
+kvm_pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn)
{
return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL);
}
EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot);
-pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn)
+kvm_pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn)
{
return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL);
}
EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic);
-pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn)
+kvm_pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn)
{
return gfn_to_pfn_memslot_atomic(gfn_to_memslot(kvm, gfn), gfn);
}
EXPORT_SYMBOL_GPL(gfn_to_pfn_atomic);
-pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn)
+kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn)
{
return gfn_to_pfn_memslot_atomic(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_pfn_atomic);
-pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn)
+kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn)
{
return gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn);
}
EXPORT_SYMBOL_GPL(gfn_to_pfn);
-pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn)
+kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn)
{
return gfn_to_pfn_memslot(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn);
}
@@ -1514,7 +1515,7 @@
}
EXPORT_SYMBOL_GPL(gfn_to_page_many_atomic);
-static struct page *kvm_pfn_to_page(pfn_t pfn)
+static struct page *kvm_pfn_to_page(kvm_pfn_t pfn)
{
if (is_error_noslot_pfn(pfn))
return KVM_ERR_PTR_BAD_PAGE;
@@ -1529,7 +1530,7 @@
struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
{
- pfn_t pfn;
+ kvm_pfn_t pfn;
pfn = gfn_to_pfn(kvm, gfn);
@@ -1539,7 +1540,7 @@
struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn)
{
- pfn_t pfn;
+ kvm_pfn_t pfn;
pfn = kvm_vcpu_gfn_to_pfn(vcpu, gfn);
@@ -1555,7 +1556,7 @@
}
EXPORT_SYMBOL_GPL(kvm_release_page_clean);
-void kvm_release_pfn_clean(pfn_t pfn)
+void kvm_release_pfn_clean(kvm_pfn_t pfn)
{
if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_pfn(pfn))
put_page(pfn_to_page(pfn));
@@ -1570,13 +1571,13 @@
}
EXPORT_SYMBOL_GPL(kvm_release_page_dirty);
-static void kvm_release_pfn_dirty(pfn_t pfn)
+static void kvm_release_pfn_dirty(kvm_pfn_t pfn)
{
kvm_set_pfn_dirty(pfn);
kvm_release_pfn_clean(pfn);
}
-void kvm_set_pfn_dirty(pfn_t pfn)
+void kvm_set_pfn_dirty(kvm_pfn_t pfn)
{
if (!kvm_is_reserved_pfn(pfn)) {
struct page *page = pfn_to_page(pfn);
@@ -1587,14 +1588,14 @@
}
EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty);
-void kvm_set_pfn_accessed(pfn_t pfn)
+void kvm_set_pfn_accessed(kvm_pfn_t pfn)
{
if (!kvm_is_reserved_pfn(pfn))
mark_page_accessed(pfn_to_page(pfn));
}
EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed);
-void kvm_get_pfn(pfn_t pfn)
+void kvm_get_pfn(kvm_pfn_t pfn)
{
if (!kvm_is_reserved_pfn(pfn))
get_page(pfn_to_page(pfn));