[PATCH v13 16/85] KVM: Replace "async" pointer in gfn=>pfn with "no_wait" and error code

From: Sean Christopherson
Date: Thu Oct 10 2024 - 14:31:02 EST


From: David Stevens <stevensd@xxxxxxxxxxxx>

Add a pfn error code to communicate that hva_to_pfn() failed because I/O
was needed and disallowed, and convert @async to a constant @no_wait
boolean. This will allow eliminating the @no_wait param by having callers
pass in FOLL_NOWAIT along with other FOLL_* flags.

Tested-by: Alex Bennée <alex.bennee@xxxxxxxxxx>
Signed-off-by: David Stevens <stevensd@xxxxxxxxxxxx>
Co-developed-by: Sean Christopherson <seanjc@xxxxxxxxxx>
Signed-off-by: Sean Christopherson <seanjc@xxxxxxxxxx>
---
arch/x86/kvm/mmu/mmu.c | 18 +++++++++++-------
include/linux/kvm_host.h | 3 ++-
virt/kvm/kvm_main.c | 27 ++++++++++++++-------------
virt/kvm/kvm_mm.h | 2 +-
virt/kvm/pfncache.c | 4 ++--
5 files changed, 30 insertions(+), 24 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 0e235f276ee5..fa8f3fb7c14b 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -4374,17 +4374,21 @@ static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,

static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
{
- bool async;
-
if (fault->is_private)
return kvm_faultin_pfn_private(vcpu, fault);

- async = false;
- fault->pfn = __gfn_to_pfn_memslot(fault->slot, fault->gfn, false, &async,
+ fault->pfn = __gfn_to_pfn_memslot(fault->slot, fault->gfn, false, true,
fault->write, &fault->map_writable,
&fault->hva);
- if (!async)
- return RET_PF_CONTINUE; /* *pfn has correct page already */
+
+ /*
+ * If resolving the page failed because I/O is needed to fault-in the
+ * page, then either set up an asynchronous #PF to do the I/O, or if
+ * doing an async #PF isn't possible, retry with I/O allowed. All
+ * other failures are terminal, i.e. retrying won't help.
+ */
+ if (fault->pfn != KVM_PFN_ERR_NEEDS_IO)
+ return RET_PF_CONTINUE;

if (!fault->prefetch && kvm_can_do_async_pf(vcpu)) {
trace_kvm_try_async_get_page(fault->addr, fault->gfn);
@@ -4402,7 +4406,7 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
* to wait for IO. Note, gup always bails if it is unable to quickly
* get a page and a fatal signal, i.e. SIGKILL, is pending.
*/
- fault->pfn = __gfn_to_pfn_memslot(fault->slot, fault->gfn, true, NULL,
+ fault->pfn = __gfn_to_pfn_memslot(fault->slot, fault->gfn, true, true,
fault->write, &fault->map_writable,
&fault->hva);
return RET_PF_CONTINUE;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 2faafc7a56ae..071a0a1f1c60 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -97,6 +97,7 @@
#define KVM_PFN_ERR_HWPOISON (KVM_PFN_ERR_MASK + 1)
#define KVM_PFN_ERR_RO_FAULT (KVM_PFN_ERR_MASK + 2)
#define KVM_PFN_ERR_SIGPENDING (KVM_PFN_ERR_MASK + 3)
+#define KVM_PFN_ERR_NEEDS_IO (KVM_PFN_ERR_MASK + 4)

/*
* error pfns indicate that the gfn is in slot but faild to
@@ -1233,7 +1234,7 @@ kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
bool *writable);
kvm_pfn_t gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn);
kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn,
- bool interruptible, bool *async,
+ bool interruptible, bool no_wait,
bool write_fault, bool *writable, hva_t *hva);

void kvm_release_pfn_clean(kvm_pfn_t pfn);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 87f81e74cbc0..dd5839abef6c 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2778,7 +2778,7 @@ static bool hva_to_pfn_fast(unsigned long addr, bool write_fault,
* The slow path to get the pfn of the specified host virtual address,
* 1 indicates success, -errno is returned if error is detected.
*/
-static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
+static int hva_to_pfn_slow(unsigned long addr, bool no_wait, bool write_fault,
bool interruptible, bool *writable, kvm_pfn_t *pfn)
{
/*
@@ -2801,7 +2801,7 @@ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,

if (write_fault)
flags |= FOLL_WRITE;
- if (async)
+ if (no_wait)
flags |= FOLL_NOWAIT;
if (interruptible)
flags |= FOLL_INTERRUPTIBLE;
@@ -2912,8 +2912,8 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma,
* Pin guest page in memory and return its pfn.
* @addr: host virtual address which maps memory to the guest
* @interruptible: whether the process can be interrupted by non-fatal signals
- * @async: whether this function need to wait IO complete if the
- * host page is not in the memory
+ * @no_wait: whether or not this function need to wait IO complete if the
+ * host page is not in the memory
* @write_fault: whether we should get a writable host page
* @writable: whether it allows to map a writable host page for !@write_fault
*
@@ -2922,7 +2922,7 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma,
* 2): @write_fault = false && @writable, @writable will tell the caller
* whether the mapping is writable.
*/
-kvm_pfn_t hva_to_pfn(unsigned long addr, bool interruptible, bool *async,
+kvm_pfn_t hva_to_pfn(unsigned long addr, bool interruptible, bool no_wait,
bool write_fault, bool *writable)
{
struct vm_area_struct *vma;
@@ -2934,7 +2934,7 @@ kvm_pfn_t hva_to_pfn(unsigned long addr, bool interruptible, bool *async,
if (hva_to_pfn_fast(addr, write_fault, writable, &pfn))
return pfn;

- npages = hva_to_pfn_slow(addr, async, write_fault, interruptible,
+ npages = hva_to_pfn_slow(addr, no_wait, write_fault, interruptible,
writable, &pfn);
if (npages == 1)
return pfn;
@@ -2956,16 +2956,17 @@ kvm_pfn_t hva_to_pfn(unsigned long addr, bool interruptible, bool *async,
if (r < 0)
pfn = KVM_PFN_ERR_FAULT;
} else {
- if (async && vma_is_valid(vma, write_fault))
- *async = true;
- pfn = KVM_PFN_ERR_FAULT;
+ if (no_wait && vma_is_valid(vma, write_fault))
+ pfn = KVM_PFN_ERR_NEEDS_IO;
+ else
+ pfn = KVM_PFN_ERR_FAULT;
}
mmap_read_unlock(current->mm);
return pfn;
}

kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn,
- bool interruptible, bool *async,
+ bool interruptible, bool no_wait,
bool write_fault, bool *writable, hva_t *hva)
{
unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault);
@@ -2987,21 +2988,21 @@ kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn,
writable = NULL;
}

- return hva_to_pfn(addr, interruptible, async, write_fault, writable);
+ return hva_to_pfn(addr, interruptible, no_wait, write_fault, writable);
}
EXPORT_SYMBOL_GPL(__gfn_to_pfn_memslot);

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,
+ return __gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn, false, false,
write_fault, writable, NULL);
}
EXPORT_SYMBOL_GPL(gfn_to_pfn_prot);

kvm_pfn_t gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn)
{
- return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL, NULL);
+ return __gfn_to_pfn_memslot(slot, gfn, false, false, true, NULL, NULL);
}
EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot);

diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h
index a3fa86f60d6c..51f3fee4ca3f 100644
--- a/virt/kvm/kvm_mm.h
+++ b/virt/kvm/kvm_mm.h
@@ -20,7 +20,7 @@
#define KVM_MMU_UNLOCK(kvm) spin_unlock(&(kvm)->mmu_lock)
#endif /* KVM_HAVE_MMU_RWLOCK */

-kvm_pfn_t hva_to_pfn(unsigned long addr, bool interruptible, bool *async,
+kvm_pfn_t hva_to_pfn(unsigned long addr, bool interruptible, bool no_wait,
bool write_fault, bool *writable);

#ifdef CONFIG_HAVE_KVM_PFNCACHE
diff --git a/virt/kvm/pfncache.c b/virt/kvm/pfncache.c
index 58c706a610e5..32dc61f48c81 100644
--- a/virt/kvm/pfncache.c
+++ b/virt/kvm/pfncache.c
@@ -197,8 +197,8 @@ static kvm_pfn_t hva_to_pfn_retry(struct gfn_to_pfn_cache *gpc)
cond_resched();
}

- /* We always request a writeable mapping */
- new_pfn = hva_to_pfn(gpc->uhva, false, NULL, true, NULL);
+ /* We always request a writable mapping */
+ new_pfn = hva_to_pfn(gpc->uhva, false, false, true, NULL);
if (is_error_noslot_pfn(new_pfn))
goto out_error;

--
2.47.0.rc1.288.g06298d1525-goog