Commit ba049e93 authored by Dan Williams's avatar Dan Williams Committed by Linus Torvalds
Browse files

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: default avatarDan Williams <dan.j.williams@intel.com>
Acked-by: default avatarChristoffer Dall <christoffer.dall@linaro.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 16da3068

arch/arm/include/asm/kvm_mmu.h

+3 −2
Original line number Diff line number Diff line
@@ -182,7 +182,8 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) 
	return (vcpu->arch.cp15[c1_SCTLR] & 0b101) == 0b101;

}



static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn,

static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu,

					       kvm_pfn_t pfn,

					       unsigned long size,

					       bool ipa_uncached)

{
@@ -246,7 +247,7 @@ static inline void __kvm_flush_dcache_pte(pte_t pte) 
static inline void __kvm_flush_dcache_pmd(pmd_t pmd)

{

	unsigned long size = PMD_SIZE;

	pfn_t pfn = pmd_pfn(pmd);

	kvm_pfn_t pfn = pmd_pfn(pmd);



	while (size) {

		void *va = kmap_atomic_pfn(pfn);

arch/arm/kvm/mmu.c

+5 −5
Original line number Diff line number Diff line
@@ -992,9 +992,9 @@ out: 
	return ret;

}



static bool transparent_hugepage_adjust(pfn_t *pfnp, phys_addr_t *ipap)

static bool transparent_hugepage_adjust(kvm_pfn_t *pfnp, phys_addr_t *ipap)

{

	pfn_t pfn = *pfnp;

	kvm_pfn_t pfn = *pfnp;

	gfn_t gfn = *ipap >> PAGE_SHIFT;



	if (PageTransCompound(pfn_to_page(pfn))) {
@@ -1201,7 +1201,7 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, 
	kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);

}



static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn,

static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, kvm_pfn_t pfn,

				      unsigned long size, bool uncached)

{

	__coherent_cache_guest_page(vcpu, pfn, size, uncached);
@@ -1218,7 +1218,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, 
	struct kvm *kvm = vcpu->kvm;

	struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;

	struct vm_area_struct *vma;

	pfn_t pfn;

	kvm_pfn_t pfn;

	pgprot_t mem_type = PAGE_S2;

	bool fault_ipa_uncached;

	bool logging_active = memslot_is_logging(memslot);
@@ -1346,7 +1346,7 @@ static void handle_access_fault(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa) 
{

	pmd_t *pmd;

	pte_t *pte;

	pfn_t pfn;

	kvm_pfn_t pfn;

	bool pfn_valid = false;



	trace_kvm_access_fault(fault_ipa);

arch/arm64/include/asm/kvm_mmu.h

+2 −1
Original line number Diff line number Diff line
@@ -230,7 +230,8 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) 
	return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101;

}



static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu, pfn_t pfn,

static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu,

					       kvm_pfn_t pfn,

					       unsigned long size,

					       bool ipa_uncached)

{

arch/mips/include/asm/kvm_host.h

+3 −3
Original line number Diff line number Diff line
@@ -101,9 +101,9 @@ 
#define CAUSEF_DC			(_ULCAST_(1) << 27)



extern atomic_t kvm_mips_instance;

extern pfn_t(*kvm_mips_gfn_to_pfn) (struct kvm *kvm, gfn_t gfn);

extern void (*kvm_mips_release_pfn_clean) (pfn_t pfn);

extern bool(*kvm_mips_is_error_pfn) (pfn_t pfn);

extern kvm_pfn_t (*kvm_mips_gfn_to_pfn)(struct kvm *kvm, gfn_t gfn);

extern void (*kvm_mips_release_pfn_clean)(kvm_pfn_t pfn);

extern bool (*kvm_mips_is_error_pfn)(kvm_pfn_t pfn);



struct kvm_vm_stat {

	u32 remote_tlb_flush;

arch/mips/kvm/emulate.c

+1 −1
Original line number Diff line number Diff line
@@ -1525,7 +1525,7 @@ int kvm_mips_sync_icache(unsigned long va, struct kvm_vcpu *vcpu) 
	struct kvm *kvm = vcpu->kvm;

	unsigned long pa;

	gfn_t gfn;

	pfn_t pfn;

	kvm_pfn_t pfn;



	gfn = va >> PAGE_SHIFT;

CRA Git | Maintained and supported by SUSTech CRA and CCSE