* [PATCH v3 01/15] KVM: async_pf: Move struct kvm_async_pf around
2021-05-07 8:40 [PATCH v3 00/15] Support Asynchronous Page Fault Gavin Shan
@ 2021-05-07 8:40 ` Gavin Shan
2021-05-07 8:40 ` [PATCH v3 02/15] KVM: async_pf: Add helper function to check completion queue Gavin Shan
` (13 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Gavin Shan @ 2021-05-07 8:40 UTC (permalink / raw)
To: kvmarm
Cc: linux-kernel, maz, will, pbonzini, james.morse, mark.rutland,
Jonathan.Cameron, shan.gavin
This moves the definitions of "struct kvm_async_pf" and the related
functions after "struct kvm_vcpu" so that newly added inline functions
in the subsequent patches can dereference "struct kvm_vcpu" properly.
Otherwise, the unexpected build error will be raised:
error: dereferencing pointer to incomplete type ‘struct kvm_vcpu’
return !list_empty_careful(&vcpu->async_pf.done);
^~
Some cleanups are also applied since we're here:
* The sepator between type and field is replaced by tab for "struct
kvm_async_pf".
* Added stub kvm_check_async_pf_completion() when CONFIG_KVM_ASYMC_PF
is disabled.
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
include/linux/kvm_host.h | 44 +++++++++++++++++++++-------------------
1 file changed, 23 insertions(+), 21 deletions(-)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 8895b95b6a22..d54adba6ebf7 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -197,27 +197,6 @@ int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,
gpa_t addr);
-#ifdef CONFIG_KVM_ASYNC_PF
-struct kvm_async_pf {
- struct work_struct work;
- struct list_head link;
- struct list_head queue;
- struct kvm_vcpu *vcpu;
- struct mm_struct *mm;
- gpa_t cr2_or_gpa;
- unsigned long addr;
- struct kvm_arch_async_pf arch;
- bool wakeup_all;
- bool notpresent_injected;
-};
-
-void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu);
-void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu);
-bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
- unsigned long hva, struct kvm_arch_async_pf *arch);
-int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
-#endif
-
#ifdef KVM_ARCH_WANT_MMU_NOTIFIER
struct kvm_gfn_range {
struct kvm_memory_slot *slot;
@@ -338,6 +317,29 @@ struct kvm_vcpu {
struct kvm_dirty_ring dirty_ring;
};
+#ifdef CONFIG_KVM_ASYNC_PF
+struct kvm_async_pf {
+ struct work_struct work;
+ struct list_head link;
+ struct list_head queue;
+ struct kvm_vcpu *vcpu;
+ struct mm_struct *mm;
+ gpa_t cr2_or_gpa;
+ unsigned long addr;
+ struct kvm_arch_async_pf arch;
+ bool wakeup_all;
+ bool notpresent_injected;
+};
+
+void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu);
+void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu);
+bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
+ unsigned long hva, struct kvm_arch_async_pf *arch);
+int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
+#else
+static inline void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu) { }
+#endif
+
static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)
{
/*
--
2.23.0
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v3 02/15] KVM: async_pf: Add helper function to check completion queue
2021-05-07 8:40 [PATCH v3 00/15] Support Asynchronous Page Fault Gavin Shan
2021-05-07 8:40 ` [PATCH v3 01/15] KVM: async_pf: Move struct kvm_async_pf around Gavin Shan
@ 2021-05-07 8:40 ` Gavin Shan
2021-05-07 8:40 ` [PATCH v3 03/15] KVM: async_pf: Make GFN slot management generic Gavin Shan
` (12 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Gavin Shan @ 2021-05-07 8:40 UTC (permalink / raw)
To: kvmarm
Cc: linux-kernel, maz, will, pbonzini, james.morse, mark.rutland,
Jonathan.Cameron, shan.gavin
This adds inline function kvm_check_async_pf_completion_queue() to
check if there are pending completion in the queue. The empty stub
is also added on !CONFIG_KVM_ASYNC_PF so that the caller needn't
consider if CONFIG_KVM_ASYNC_PF is enabled.
All checks on the completion queue is done by the newly added inline
function since list_empty() and list_empty_careful() are interchangeable.
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
arch/x86/kvm/x86.c | 2 +-
include/linux/kvm_host.h | 10 ++++++++++
virt/kvm/async_pf.c | 10 +++++-----
virt/kvm/kvm_main.c | 4 +---
4 files changed, 17 insertions(+), 9 deletions(-)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index cebdaa1e3cf5..300661dc6ca4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -11075,7 +11075,7 @@ static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
{
- if (!list_empty_careful(&vcpu->async_pf.done))
+ if (kvm_check_async_pf_completion_queue(vcpu))
return true;
if (kvm_apic_has_events(vcpu))
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index d54adba6ebf7..00811de013d0 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -331,12 +331,22 @@ struct kvm_async_pf {
bool notpresent_injected;
};
+static inline bool kvm_check_async_pf_completion_queue(struct kvm_vcpu *vcpu)
+{
+ return !list_empty_careful(&vcpu->async_pf.done);
+}
+
void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu);
void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu);
bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
unsigned long hva, struct kvm_arch_async_pf *arch);
int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
#else
+static inline bool kvm_check_async_pf_completion_queue(struct kvm_vcpu *vcpu)
+{
+ return false;
+}
+
static inline void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu) { }
#endif
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index dd777688d14a..d145a61a046a 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -70,7 +70,7 @@ static void async_pf_execute(struct work_struct *work)
kvm_arch_async_page_present(vcpu, apf);
spin_lock(&vcpu->async_pf.lock);
- first = list_empty(&vcpu->async_pf.done);
+ first = !kvm_check_async_pf_completion_queue(vcpu);
list_add_tail(&apf->link, &vcpu->async_pf.done);
apf->vcpu = NULL;
spin_unlock(&vcpu->async_pf.lock);
@@ -122,7 +122,7 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
spin_lock(&vcpu->async_pf.lock);
}
- while (!list_empty(&vcpu->async_pf.done)) {
+ while (kvm_check_async_pf_completion_queue(vcpu)) {
struct kvm_async_pf *work =
list_first_entry(&vcpu->async_pf.done,
typeof(*work), link);
@@ -138,7 +138,7 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu)
{
struct kvm_async_pf *work;
- while (!list_empty_careful(&vcpu->async_pf.done) &&
+ while (kvm_check_async_pf_completion_queue(vcpu) &&
kvm_arch_can_dequeue_async_page_present(vcpu)) {
spin_lock(&vcpu->async_pf.lock);
work = list_first_entry(&vcpu->async_pf.done, typeof(*work),
@@ -205,7 +205,7 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu)
struct kvm_async_pf *work;
bool first;
- if (!list_empty_careful(&vcpu->async_pf.done))
+ if (kvm_check_async_pf_completion_queue(vcpu))
return 0;
work = kmem_cache_zalloc(async_pf_cache, GFP_ATOMIC);
@@ -216,7 +216,7 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu)
INIT_LIST_HEAD(&work->queue); /* for list_del to work */
spin_lock(&vcpu->async_pf.lock);
- first = list_empty(&vcpu->async_pf.done);
+ first = !kvm_check_async_pf_completion_queue(vcpu);
list_add_tail(&work->link, &vcpu->async_pf.done);
spin_unlock(&vcpu->async_pf.lock);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 2799c6660cce..d3a473f9811f 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -3129,10 +3129,8 @@ static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu)
if (kvm_arch_dy_runnable(vcpu))
return true;
-#ifdef CONFIG_KVM_ASYNC_PF
- if (!list_empty_careful(&vcpu->async_pf.done))
+ if (kvm_check_async_pf_completion_queue(vcpu))
return true;
-#endif
return false;
}
--
2.23.0
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v3 03/15] KVM: async_pf: Make GFN slot management generic
2021-05-07 8:40 [PATCH v3 00/15] Support Asynchronous Page Fault Gavin Shan
2021-05-07 8:40 ` [PATCH v3 01/15] KVM: async_pf: Move struct kvm_async_pf around Gavin Shan
2021-05-07 8:40 ` [PATCH v3 02/15] KVM: async_pf: Add helper function to check completion queue Gavin Shan
@ 2021-05-07 8:40 ` Gavin Shan
2021-05-07 8:40 ` [PATCH v3 04/15] KVM: x86: Use generic async PF slot management Gavin Shan
` (11 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Gavin Shan @ 2021-05-07 8:40 UTC (permalink / raw)
To: kvmarm
Cc: linux-kernel, maz, will, pbonzini, james.morse, mark.rutland,
Jonathan.Cameron, shan.gavin
It's not allowed to fire duplicate notification for same GFN on
x86 platform, with help of a hash table. This mechanism is going
to be used by arm64 and this makes the code generic and shareable
by multiple platforms.
* As this mechanism isn't needed by all platforms, a new kernel
config option (CONFIG_ASYNC_PF_SLOT) is introduced so that it
can be disabled at compiling time.
* The code is basically copied from x86 platform and the functions
are renamed to reflect the fact: (a) the input parameters are
vCPU and GFN. (b) The operations are resetting, searching, adding
and removing.
* Helper stub is also added on !CONFIG_KVM_ASYNC_PF because we're
going to use IS_ENABLED() instead of #ifdef on arm64 when the
asynchronous page fault is supported.
This is preparatory work to use the newly introduced functions on x86
platform and arm64 in subsequent patches.
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
include/linux/kvm_host.h | 18 +++++++++
virt/kvm/Kconfig | 3 ++
virt/kvm/async_pf.c | 85 ++++++++++++++++++++++++++++++++++++++++
3 files changed, 106 insertions(+)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 00811de013d0..bade8f306ee8 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -292,6 +292,9 @@ struct kvm_vcpu {
#ifdef CONFIG_KVM_ASYNC_PF
struct {
+#ifdef CONFIG_KVM_ASYNC_PF_SLOT
+ gfn_t gfns[ASYNC_PF_PER_VCPU];
+#endif
u32 queued;
struct list_head queue;
struct list_head done;
@@ -331,6 +334,13 @@ struct kvm_async_pf {
bool notpresent_injected;
};
+#ifdef CONFIG_KVM_ASYNC_PF_SLOT
+void kvm_async_pf_reset_slot(struct kvm_vcpu *vcpu);
+void kvm_async_pf_add_slot(struct kvm_vcpu *vcpu, gfn_t gfn);
+void kvm_async_pf_remove_slot(struct kvm_vcpu *vcpu, gfn_t gfn);
+bool kvm_async_pf_find_slot(struct kvm_vcpu *vcpu, gfn_t gfn);
+#endif
+
static inline bool kvm_check_async_pf_completion_queue(struct kvm_vcpu *vcpu)
{
return !list_empty_careful(&vcpu->async_pf.done);
@@ -342,6 +352,14 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
unsigned long hva, struct kvm_arch_async_pf *arch);
int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
#else
+static inline void kvm_async_pf_reset_slot(struct kvm_vcpu *vcpu) { }
+static inline void kvm_async_pf_add_slot(struct kvm_vcpu *vcpu, gfn_t gfn) { }
+static inline void kvm_async_pf_remove_slot(struct kvm_vcpu *vcpu, gfn_t gfn) { }
+static inline bool kvm_async_pf_find_slot(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+ return false;
+}
+
static inline bool kvm_check_async_pf_completion_queue(struct kvm_vcpu *vcpu)
{
return false;
diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 1c37ccd5d402..74f33151e0b1 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -23,6 +23,9 @@ config KVM_MMIO
config KVM_ASYNC_PF
bool
+config KVM_ASYNC_PF_SLOT
+ bool
+
# Toggle to switch between direct notification and batch job
config KVM_ASYNC_PF_SYNC
bool
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index d145a61a046a..0d1fdb2932af 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -13,12 +13,97 @@
#include <linux/module.h>
#include <linux/mmu_context.h>
#include <linux/sched/mm.h>
+#ifdef CONFIG_KVM_ASYNC_PF_SLOT
+#include <linux/hash.h>
+#endif
#include "async_pf.h"
#include <trace/events/kvm.h>
static struct kmem_cache *async_pf_cache;
+#ifdef CONFIG_KVM_ASYNC_PF_SLOT
+static inline u32 kvm_async_pf_hash(gfn_t gfn)
+{
+ BUILD_BUG_ON(!is_power_of_2(ASYNC_PF_PER_VCPU));
+
+ return hash_32(gfn & 0xffffffff, order_base_2(ASYNC_PF_PER_VCPU));
+}
+
+static inline u32 kvm_async_pf_next_slot(u32 key)
+{
+ return (key + 1) & (ASYNC_PF_PER_VCPU - 1);
+}
+
+static u32 kvm_async_pf_slot(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+ u32 key = kvm_async_pf_hash(gfn);
+ int i;
+
+ for (i = 0; i < ASYNC_PF_PER_VCPU &&
+ (vcpu->async_pf.gfns[key] != gfn &&
+ vcpu->async_pf.gfns[key] != ~0); i++)
+ key = kvm_async_pf_next_slot(key);
+
+ return key;
+}
+
+void kvm_async_pf_reset_slot(struct kvm_vcpu *vcpu)
+{
+ int i;
+
+ for (i = 0; i < ASYNC_PF_PER_VCPU; i++)
+ vcpu->async_pf.gfns[i] = ~0;
+}
+
+void kvm_async_pf_add_slot(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+ u32 key = kvm_async_pf_hash(gfn);
+
+ while (vcpu->async_pf.gfns[key] != ~0)
+ key = kvm_async_pf_next_slot(key);
+
+ vcpu->async_pf.gfns[key] = gfn;
+}
+
+void kvm_async_pf_remove_slot(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+ u32 i, j, k;
+
+ i = j = kvm_async_pf_slot(vcpu, gfn);
+
+ if (WARN_ON_ONCE(vcpu->async_pf.gfns[i] != gfn))
+ return;
+
+ while (true) {
+ vcpu->async_pf.gfns[i] = ~0;
+
+ do {
+ j = kvm_async_pf_next_slot(j);
+ if (vcpu->async_pf.gfns[j] == ~0)
+ return;
+
+ k = kvm_async_pf_hash(vcpu->async_pf.gfns[j]);
+ /*
+ * k lies cyclically in ]i,j]
+ * | i.k.j |
+ * |....j i.k.| or |.k..j i...|
+ */
+ } while ((i <= j) ? (i < k && k <= j) : (i < k || k <= j));
+
+ vcpu->async_pf.gfns[i] = vcpu->async_pf.gfns[j];
+ i = j;
+ }
+}
+
+bool kvm_async_pf_find_slot(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+ u32 key = kvm_async_pf_slot(vcpu, gfn);
+
+ return vcpu->async_pf.gfns[key] == gfn;
+}
+#endif /* CONFIG_KVM_ASYNC_PF_SLOT */
+
int kvm_async_pf_init(void)
{
async_pf_cache = KMEM_CACHE(kvm_async_pf, 0);
--
2.23.0
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v3 04/15] KVM: x86: Use generic async PF slot management
2021-05-07 8:40 [PATCH v3 00/15] Support Asynchronous Page Fault Gavin Shan
` (2 preceding siblings ...)
2021-05-07 8:40 ` [PATCH v3 03/15] KVM: async_pf: Make GFN slot management generic Gavin Shan
@ 2021-05-07 8:40 ` Gavin Shan
2021-05-07 8:40 ` [PATCH v3 05/15] KVM: arm64: Export kvm_handle_user_mem_abort() Gavin Shan
` (10 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Gavin Shan @ 2021-05-07 8:40 UTC (permalink / raw)
To: kvmarm
Cc: linux-kernel, maz, will, pbonzini, james.morse, mark.rutland,
Jonathan.Cameron, shan.gavin
This uses the generic slot management mechanism for asynchronous
page fault by enabling CONFIG_KVM_ASYNC_PF_SLOT because the private
implementation is totally duplicate to the generic one.
The changes introduced by this is pretty mechanical and shouldn't
cause any logical changes.
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
arch/x86/include/asm/kvm_host.h | 2 -
arch/x86/kvm/Kconfig | 1 +
arch/x86/kvm/mmu/mmu.c | 2 +-
arch/x86/kvm/x86.c | 86 +++------------------------------
4 files changed, 8 insertions(+), 83 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index cbbcee0a84f9..9b344a71f083 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -766,7 +766,6 @@ struct kvm_vcpu_arch {
struct {
bool halted;
- gfn_t gfns[ASYNC_PF_PER_VCPU];
struct gfn_to_hva_cache data;
u64 msr_en_val; /* MSR_KVM_ASYNC_PF_EN */
u64 msr_int_val; /* MSR_KVM_ASYNC_PF_INT */
@@ -1797,7 +1796,6 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,
struct kvm_async_pf *work);
void kvm_arch_async_page_present_queued(struct kvm_vcpu *vcpu);
bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu);
-extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu);
int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err);
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index f6b93a35ce14..8b8ae8a0467d 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -34,6 +34,7 @@ config KVM
select HAVE_KVM_IRQ_ROUTING
select HAVE_KVM_EVENTFD
select KVM_ASYNC_PF
+ select KVM_ASYNC_PF_SLOT
select USER_RETURN_NOTIFIER
select KVM_MMIO
select TASKSTATS
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 4b3ee244ebe0..c355d980fd9a 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3701,7 +3701,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
if (!prefault && kvm_can_do_async_pf(vcpu)) {
trace_kvm_try_async_get_page(cr2_or_gpa, gfn);
- if (kvm_find_async_pf_gfn(vcpu, gfn)) {
+ if (kvm_async_pf_find_slot(vcpu, gfn)) {
trace_kvm_async_pf_doublefault(cr2_or_gpa, gfn);
kvm_make_request(KVM_REQ_APF_HALT, vcpu);
return true;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 300661dc6ca4..55d53082a8df 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -305,13 +305,6 @@ static struct kmem_cache *kvm_alloc_emulator_cache(void)
static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt);
-static inline void kvm_async_pf_hash_reset(struct kvm_vcpu *vcpu)
-{
- int i;
- for (i = 0; i < ASYNC_PF_PER_VCPU; i++)
- vcpu->arch.apf.gfns[i] = ~0;
-}
-
static void kvm_on_user_return(struct user_return_notifier *urn)
{
unsigned slot;
@@ -829,7 +822,7 @@ void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned lon
if ((cr0 ^ old_cr0) & X86_CR0_PG) {
kvm_clear_async_pf_completion_queue(vcpu);
- kvm_async_pf_hash_reset(vcpu);
+ kvm_async_pf_reset_slot(vcpu);
}
if ((cr0 ^ old_cr0) & update_bits)
@@ -2959,7 +2952,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
if (!kvm_pv_async_pf_enabled(vcpu)) {
kvm_clear_async_pf_completion_queue(vcpu);
- kvm_async_pf_hash_reset(vcpu);
+ kvm_async_pf_reset_slot(vcpu);
return 0;
}
@@ -10264,7 +10257,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT;
- kvm_async_pf_hash_reset(vcpu);
+ kvm_async_pf_reset_slot(vcpu);
kvm_pmu_init(vcpu);
vcpu->arch.pending_external_vector = -1;
@@ -10381,7 +10374,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
kvmclock_reset(vcpu);
kvm_clear_async_pf_completion_queue(vcpu);
- kvm_async_pf_hash_reset(vcpu);
+ kvm_async_pf_reset_slot(vcpu);
vcpu->arch.apf.halted = false;
if (vcpu->arch.guest_fpu && kvm_mpx_supported()) {
@@ -11221,73 +11214,6 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true);
}
-static inline u32 kvm_async_pf_hash_fn(gfn_t gfn)
-{
- BUILD_BUG_ON(!is_power_of_2(ASYNC_PF_PER_VCPU));
-
- return hash_32(gfn & 0xffffffff, order_base_2(ASYNC_PF_PER_VCPU));
-}
-
-static inline u32 kvm_async_pf_next_probe(u32 key)
-{
- return (key + 1) & (ASYNC_PF_PER_VCPU - 1);
-}
-
-static void kvm_add_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
-{
- u32 key = kvm_async_pf_hash_fn(gfn);
-
- while (vcpu->arch.apf.gfns[key] != ~0)
- key = kvm_async_pf_next_probe(key);
-
- vcpu->arch.apf.gfns[key] = gfn;
-}
-
-static u32 kvm_async_pf_gfn_slot(struct kvm_vcpu *vcpu, gfn_t gfn)
-{
- int i;
- u32 key = kvm_async_pf_hash_fn(gfn);
-
- for (i = 0; i < ASYNC_PF_PER_VCPU &&
- (vcpu->arch.apf.gfns[key] != gfn &&
- vcpu->arch.apf.gfns[key] != ~0); i++)
- key = kvm_async_pf_next_probe(key);
-
- return key;
-}
-
-bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
-{
- return vcpu->arch.apf.gfns[kvm_async_pf_gfn_slot(vcpu, gfn)] == gfn;
-}
-
-static void kvm_del_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
-{
- u32 i, j, k;
-
- i = j = kvm_async_pf_gfn_slot(vcpu, gfn);
-
- if (WARN_ON_ONCE(vcpu->arch.apf.gfns[i] != gfn))
- return;
-
- while (true) {
- vcpu->arch.apf.gfns[i] = ~0;
- do {
- j = kvm_async_pf_next_probe(j);
- if (vcpu->arch.apf.gfns[j] == ~0)
- return;
- k = kvm_async_pf_hash_fn(vcpu->arch.apf.gfns[j]);
- /*
- * k lies cyclically in ]i,j]
- * | i.k.j |
- * |....j i.k.| or |.k..j i...|
- */
- } while ((i <= j) ? (i < k && k <= j) : (i < k || k <= j));
- vcpu->arch.apf.gfns[i] = vcpu->arch.apf.gfns[j];
- i = j;
- }
-}
-
static inline int apf_put_user_notpresent(struct kvm_vcpu *vcpu)
{
u32 reason = KVM_PV_REASON_PAGE_NOT_PRESENT;
@@ -11351,7 +11277,7 @@ bool kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
struct x86_exception fault;
trace_kvm_async_pf_not_present(work->arch.token, work->cr2_or_gpa);
- kvm_add_async_pf_gfn(vcpu, work->arch.gfn);
+ kvm_async_pf_add_slot(vcpu, work->arch.gfn);
if (kvm_can_deliver_async_pf(vcpu) &&
!apf_put_user_notpresent(vcpu)) {
@@ -11388,7 +11314,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
if (work->wakeup_all)
work->arch.token = ~0; /* broadcast wakeup */
else
- kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
+ kvm_async_pf_remove_slot(vcpu, work->arch.gfn);
trace_kvm_async_pf_ready(work->arch.token, work->cr2_or_gpa);
if ((work->wakeup_all || work->notpresent_injected) &&
--
2.23.0
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v3 05/15] KVM: arm64: Export kvm_handle_user_mem_abort()
2021-05-07 8:40 [PATCH v3 00/15] Support Asynchronous Page Fault Gavin Shan
` (3 preceding siblings ...)
2021-05-07 8:40 ` [PATCH v3 04/15] KVM: x86: Use generic async PF slot management Gavin Shan
@ 2021-05-07 8:40 ` Gavin Shan
2021-05-07 8:40 ` [PATCH v3 06/15] KVM: arm64: Add paravirtualization header files Gavin Shan
` (9 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Gavin Shan @ 2021-05-07 8:40 UTC (permalink / raw)
To: kvmarm
Cc: linux-kernel, maz, will, pbonzini, james.morse, mark.rutland,
Jonathan.Cameron, shan.gavin
The main work of stage-2 page fault is handled by user_mem_abort().
When asynchronous page fault is supported, one page fault need to
be handled with two calls to this function. It means the page fault
needs to be replayed asynchronously in that case.
* This renames the function to kvm_handle_user_mem_abort() and
exports it.
* Add arguments @esr and @prefault to user_mem_abort(). @esr is
the cached value of ESR_EL2 instead of fetching from the current
vCPU when the page fault is replayed in scenario of asynchronous
page fault. @prefault is used to indicate the page fault is replayed
one or not.
* Define helper functions esr_dbat_*() in asm/esr.h to extract
or check various fields of the passed ESR_EL2 value because
those helper functions defined in asm/kvm_emulate.h assumes
the ESR_EL2 value has been cached in vCPU struct. It won't
be true on handling the replayed page fault in scenario of
asynchronous page fault.
* Some helper functions defined in asm/kvm_emulate.h are used
by mmu.c only and seem not to be used by other source file
in near future. They are moved to mmu.c and renamed accordingly.
is_exec_fault: kvm_vcpu_trap_is_exec_fault
is_write_fault: kvm_is_write_fault()
esr_abt_fault_level: kvm_vcpu_trap_get_fault_level
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
arch/arm64/include/asm/esr.h | 6 ++++
arch/arm64/include/asm/kvm_emulate.h | 27 ++---------------
arch/arm64/include/asm/kvm_host.h | 4 +++
arch/arm64/kvm/mmu.c | 43 ++++++++++++++++++++++------
4 files changed, 48 insertions(+), 32 deletions(-)
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 29f97eb3dad4..0f2cb27691de 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -321,8 +321,14 @@
ESR_ELx_CP15_32_ISS_DIR_READ)
#ifndef __ASSEMBLY__
+#include <linux/bitfield.h>
#include <asm/types.h>
+#define esr_dabt_fault_type(esr) (esr & ESR_ELx_FSC_TYPE)
+#define esr_dabt_fault_level(esr) (FIELD_GET(ESR_ELx_FSC_LEVEL, esr))
+#define esr_dabt_is_wnr(esr) (!!(FIELD_GET(ESR_ELx_WNR, esr)))
+#define esr_dabt_is_s1ptw(esr) (!!(FIELD_GET(ESR_ELx_S1PTW, esr)))
+
static inline bool esr_is_data_abort(u32 esr)
{
const u32 ec = ESR_ELx_EC(esr);
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 0ef213b715a5..4dd6a658ff86 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -282,13 +282,13 @@ static __always_inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu)
static __always_inline bool kvm_vcpu_abt_iss1tw(const struct kvm_vcpu *vcpu)
{
- return !!(kvm_vcpu_get_esr(vcpu) & ESR_ELx_S1PTW);
+ return esr_dabt_is_s1ptw(kvm_vcpu_get_esr(vcpu));
}
/* Always check for S1PTW *before* using this. */
static __always_inline bool kvm_vcpu_dabt_iswrite(const struct kvm_vcpu *vcpu)
{
- return kvm_vcpu_get_esr(vcpu) & ESR_ELx_WNR;
+ return esr_dabt_is_wnr(kvm_vcpu_get_esr(vcpu));
}
static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu)
@@ -317,11 +317,6 @@ static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu)
return kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_IABT_LOW;
}
-static inline bool kvm_vcpu_trap_is_exec_fault(const struct kvm_vcpu *vcpu)
-{
- return kvm_vcpu_trap_is_iabt(vcpu) && !kvm_vcpu_abt_iss1tw(vcpu);
-}
-
static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu)
{
return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC;
@@ -329,12 +324,7 @@ static __always_inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu)
static __always_inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu)
{
- return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_TYPE;
-}
-
-static __always_inline u8 kvm_vcpu_trap_get_fault_level(const struct kvm_vcpu *vcpu)
-{
- return kvm_vcpu_get_esr(vcpu) & ESR_ELx_FSC_LEVEL;
+ return esr_dabt_fault_type(kvm_vcpu_get_esr(vcpu));
}
static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu)
@@ -362,17 +352,6 @@ static __always_inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu)
return ESR_ELx_SYS64_ISS_RT(esr);
}
-static inline bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
-{
- if (kvm_vcpu_abt_iss1tw(vcpu))
- return true;
-
- if (kvm_vcpu_trap_is_iabt(vcpu))
- return false;
-
- return kvm_vcpu_dabt_iswrite(vcpu);
-}
-
static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
{
return vcpu_read_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK;
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 8944176efa94..822781f94cb0 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -599,6 +599,10 @@ int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu,
#define KVM_ARCH_WANT_MMU_NOTIFIER
+int kvm_handle_user_mem_abort(struct kvm_vcpu *vcpu,
+ struct kvm_memory_slot *memslot,
+ phys_addr_t fault_ipa, unsigned long hva,
+ unsigned int esr, bool prefault);
void kvm_arm_halt_guest(struct kvm *kvm);
void kvm_arm_resume_guest(struct kvm *kvm);
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index c5d1f3c87dbd..2b8035fc7b47 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -822,9 +822,34 @@ transparent_hugepage_adjust(struct kvm_memory_slot *memslot,
return PAGE_SIZE;
}
-static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
- struct kvm_memory_slot *memslot, unsigned long hva,
- unsigned long fault_status)
+static inline bool is_exec_fault(unsigned int esr)
+{
+ if (ESR_ELx_EC(esr) != ESR_ELx_EC_IABT_LOW)
+ return false;
+
+ if (esr_dabt_is_s1ptw(esr))
+ return false;
+
+ return true;
+}
+
+static inline bool is_write_fault(unsigned int esr)
+{
+ if (esr_dabt_is_s1ptw(esr))
+ return true;
+
+ if (ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_LOW)
+ return false;
+
+ return esr_dabt_is_wnr(esr);
+}
+
+int kvm_handle_user_mem_abort(struct kvm_vcpu *vcpu,
+ struct kvm_memory_slot *memslot,
+ phys_addr_t fault_ipa,
+ unsigned long hva,
+ unsigned int esr,
+ bool prefault)
{
int ret = 0;
bool write_fault, writable, force_pte = false;
@@ -838,14 +863,15 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
gfn_t gfn;
kvm_pfn_t pfn;
bool logging_active = memslot_is_logging(memslot);
- unsigned long fault_level = kvm_vcpu_trap_get_fault_level(vcpu);
+ unsigned int fault_status = esr_dabt_fault_type(esr);
+ unsigned long fault_level = esr_dabt_fault_level(esr);
unsigned long vma_pagesize, fault_granule;
enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_R;
struct kvm_pgtable *pgt;
fault_granule = 1UL << ARM64_HW_PGTABLE_LEVEL_SHIFT(fault_level);
- write_fault = kvm_is_write_fault(vcpu);
- exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
+ write_fault = is_write_fault(kvm_vcpu_get_esr(vcpu));
+ exec_fault = is_exec_fault(kvm_vcpu_get_esr(vcpu));
VM_BUG_ON(write_fault && exec_fault);
if (fault_status == FSC_PERM && !write_fault && !exec_fault) {
@@ -1085,7 +1111,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
gfn = fault_ipa >> PAGE_SHIFT;
memslot = gfn_to_memslot(vcpu->kvm, gfn);
hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable);
- write_fault = kvm_is_write_fault(vcpu);
+ write_fault = is_write_fault(kvm_vcpu_get_esr(vcpu));
if (kvm_is_error_hva(hva) || (write_fault && !writable)) {
/*
* The guest has put either its instructions or its page-tables
@@ -1140,7 +1166,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
goto out_unlock;
}
- ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status);
+ ret = kvm_handle_user_mem_abort(vcpu, memslot, fault_ipa, hva,
+ kvm_vcpu_get_esr(vcpu), false);
if (ret == 0)
ret = 1;
out:
--
2.23.0
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v3 06/15] KVM: arm64: Add paravirtualization header files
2021-05-07 8:40 [PATCH v3 00/15] Support Asynchronous Page Fault Gavin Shan
` (4 preceding siblings ...)
2021-05-07 8:40 ` [PATCH v3 05/15] KVM: arm64: Export kvm_handle_user_mem_abort() Gavin Shan
@ 2021-05-07 8:40 ` Gavin Shan
2021-05-07 8:40 ` [PATCH v3 07/15] KVM: arm64: Support page-not-present notification Gavin Shan
` (8 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Gavin Shan @ 2021-05-07 8:40 UTC (permalink / raw)
To: kvmarm
Cc: linux-kernel, maz, will, pbonzini, james.morse, mark.rutland,
Jonathan.Cameron, shan.gavin
We need put more stuff in the paravirtualization header files when
the asynchronous page fault is supported. The generic header files
can't meet the goal. This duplicate the generic header files to be
our platform specific header files. It's the preparatory work to
support the asynchronous page fault in the subsequent patches:
include/uapi/asm-generic/kvm_para.h
include/asm-generic/kvm_para.h
arch/arm64/include/uapi/asm/kvm_para.h
arch/arm64/include/asm/kvm_para.h
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
arch/arm64/include/asm/kvm_para.h | 27 ++++++++++++++++++++++++++
arch/arm64/include/uapi/asm/Kbuild | 2 --
arch/arm64/include/uapi/asm/kvm_para.h | 5 +++++
3 files changed, 32 insertions(+), 2 deletions(-)
create mode 100644 arch/arm64/include/asm/kvm_para.h
create mode 100644 arch/arm64/include/uapi/asm/kvm_para.h
diff --git a/arch/arm64/include/asm/kvm_para.h b/arch/arm64/include/asm/kvm_para.h
new file mode 100644
index 000000000000..0ea481dd1c7a
--- /dev/null
+++ b/arch/arm64/include/asm/kvm_para.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ARM_KVM_PARA_H
+#define _ASM_ARM_KVM_PARA_H
+
+#include <uapi/asm/kvm_para.h>
+
+static inline bool kvm_check_and_clear_guest_paused(void)
+{
+ return false;
+}
+
+static inline unsigned int kvm_arch_para_features(void)
+{
+ return 0;
+}
+
+static inline unsigned int kvm_arch_para_hints(void)
+{
+ return 0;
+}
+
+static inline bool kvm_para_available(void)
+{
+ return false;
+}
+
+#endif /* _ASM_ARM_KVM_PARA_H */
diff --git a/arch/arm64/include/uapi/asm/Kbuild b/arch/arm64/include/uapi/asm/Kbuild
index 602d137932dc..f66554cd5c45 100644
--- a/arch/arm64/include/uapi/asm/Kbuild
+++ b/arch/arm64/include/uapi/asm/Kbuild
@@ -1,3 +1 @@
# SPDX-License-Identifier: GPL-2.0
-
-generic-y += kvm_para.h
diff --git a/arch/arm64/include/uapi/asm/kvm_para.h b/arch/arm64/include/uapi/asm/kvm_para.h
new file mode 100644
index 000000000000..cd212282b90c
--- /dev/null
+++ b/arch/arm64/include/uapi/asm/kvm_para.h
@@ -0,0 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_ASM_ARM_KVM_PARA_H
+#define _UAPI_ASM_ARM_KVM_PARA_H
+
+#endif /* _UAPI_ASM_ARM_KVM_PARA_H */
--
2.23.0
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v3 07/15] KVM: arm64: Support page-not-present notification
2021-05-07 8:40 [PATCH v3 00/15] Support Asynchronous Page Fault Gavin Shan
` (5 preceding siblings ...)
2021-05-07 8:40 ` [PATCH v3 06/15] KVM: arm64: Add paravirtualization header files Gavin Shan
@ 2021-05-07 8:40 ` Gavin Shan
2021-05-07 8:40 ` [PATCH v3 08/15] KVM: arm64: Support page-ready notification Gavin Shan
` (7 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Gavin Shan @ 2021-05-07 8:40 UTC (permalink / raw)
To: kvmarm
Cc: linux-kernel, maz, will, pbonzini, james.morse, mark.rutland,
Jonathan.Cameron, shan.gavin
The requested page might be not resident in memory during the stage-2
page fault. For example, the requested page could be resident in swap
device (file). In this case, disk I/O is issued in order to fetch the
requested page and it could take tens of milliseconds, even hundreds
of milliseconds in extreme situation. During the period, the guest's
vCPU is suspended until the requested page becomes ready. Actually,
the something else on the guest's vCPU could be rescheduled during
the period, so that the time slice isn't wasted as the guest's vCPU
can see. This is the primary goal of the feature (Asynchronous Page
Fault).
This supports delivery of page-not-present notification through SDEI
event when the requested page isn't present. When the notification is
received on the guest's vCPU, something else (another process) can be
scheduled. The design is highlighted as below:
* There is dedicated memory region shared by host and guest. It's
represented by "struct kvm_vcpu_pv_apf_data". The field @reason
indicates the reason why the SDEI event is triggered, while the
unique @token is used by guest to associate the event with the
suspended process.
* One control block is associated with each guest's vCPU and it's
represented by "struct kvm_arch_async_pf_control". It allows the
guest to configure the functionality to indicate the situations
where the host can deliver the page-not-present notification to
kick off asyncrhonous page fault. Besides, runtime states are
also maintained in this struct.
* Before the page-not-present notification is sent to the guest's
vCPU, a worker is started and executed asynchronously on host,
to fetch the requested page. "struct kvm{_,_arch}async_pf" is
associated with the worker, to track the work.
The feature isn't enabled by CONFIG_KVM_ASYNC_PF yet. Also, the
page-ready notification delivery and control path isn't implemented
and will be done in the subsequent patches.
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
arch/arm64/include/asm/kvm_host.h | 50 +++++++++
arch/arm64/include/uapi/asm/kvm_para.h | 15 +++
arch/arm64/kvm/Makefile | 1 +
arch/arm64/kvm/arm.c | 3 +
arch/arm64/kvm/async_pf.c | 145 +++++++++++++++++++++++++
arch/arm64/kvm/mmu.c | 33 +++++-
6 files changed, 245 insertions(+), 2 deletions(-)
create mode 100644 arch/arm64/kvm/async_pf.c
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 822781f94cb0..e241a93c6485 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -272,6 +272,31 @@ struct vcpu_reset_state {
bool reset;
};
+/* Should be a power of two number */
+#define ASYNC_PF_PER_VCPU 64
+
+/*
+ * The association of gfn and token. The token will be sent to guest as
+ * page fault address. Also, the guest could be in aarch32 mode. So its
+ * length should be 32-bits.
+ */
+struct kvm_arch_async_pf {
+ u32 token;
+ gfn_t gfn;
+ u32 esr;
+};
+
+struct kvm_arch_async_pf_control {
+ struct gfn_to_hva_cache cache;
+ u64 control_block;
+ bool send_user_only;
+ u64 sdei_event_num;
+
+ u16 id;
+ bool notpresent_pending;
+ u32 notpresent_token;
+};
+
struct kvm_vcpu_arch {
struct kvm_cpu_context ctxt;
void *sve_state;
@@ -376,6 +401,7 @@ struct kvm_vcpu_arch {
} steal;
struct kvm_sdei_vcpu *sdei;
+ struct kvm_arch_async_pf_control *apf;
};
/* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */
@@ -731,6 +757,30 @@ int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,
int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu,
struct kvm_device_attr *attr);
+#ifdef CONFIG_KVM_ASYNC_PF
+void kvm_arch_async_pf_create_vcpu(struct kvm_vcpu *vcpu);
+bool kvm_arch_async_not_present_allowed(struct kvm_vcpu *vcpu);
+bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu,
+ u32 esr, gpa_t gpa, gfn_t gfn);
+bool kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
+ struct kvm_async_pf *work);
+void kvm_arch_async_pf_destroy_vcpu(struct kvm_vcpu *vcpu);
+#else
+static inline void kvm_arch_async_pf_create_vcpu(struct kvm_vcpu *vcpu) { }
+static inline void kvm_arch_async_pf_destroy_vcpu(struct kvm_vcpu *vcpu) { }
+
+static inline bool kvm_arch_async_not_present_allowed(struct kvm_vcpu *vcpu)
+{
+ return false;
+}
+
+static inline bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu,
+ u32 esr, gpa_t gpa, gfn_t gfn)
+{
+ return false;
+}
+#endif
+
/* Guest/host FPSIMD coordination helpers */
int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu);
void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu);
diff --git a/arch/arm64/include/uapi/asm/kvm_para.h b/arch/arm64/include/uapi/asm/kvm_para.h
index cd212282b90c..3fa04006714e 100644
--- a/arch/arm64/include/uapi/asm/kvm_para.h
+++ b/arch/arm64/include/uapi/asm/kvm_para.h
@@ -2,4 +2,19 @@
#ifndef _UAPI_ASM_ARM_KVM_PARA_H
#define _UAPI_ASM_ARM_KVM_PARA_H
+#include <linux/types.h>
+
+/* Async PF */
+#define KVM_ASYNC_PF_ENABLED (1 << 0)
+#define KVM_ASYNC_PF_SEND_ALWAYS (1 << 1)
+
+#define KVM_PV_REASON_PAGE_NOT_PRESENT 1
+
+struct kvm_vcpu_pv_apf_data {
+ __u32 reason;
+ __u32 token;
+ __u8 pad[56];
+ __u32 enabled;
+};
+
#endif /* _UAPI_ASM_ARM_KVM_PARA_H */
diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile
index 695dbefb3a3c..6bb3ec03cce5 100644
--- a/arch/arm64/kvm/Makefile
+++ b/arch/arm64/kvm/Makefile
@@ -25,3 +25,4 @@ kvm-y := $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o \
vgic/vgic-its.o vgic/vgic-debug.o
kvm-$(CONFIG_HW_PERF_EVENTS) += pmu-emul.o
+kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o async_pf.o
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index ab8071aec005..f77aab668c90 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -333,6 +333,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
kvm_sdei_create_vcpu(vcpu);
+ kvm_arch_async_pf_create_vcpu(vcpu);
+
vcpu->arch.hw_mmu = &vcpu->kvm->arch.mmu;
err = kvm_vgic_vcpu_init(vcpu);
@@ -354,6 +356,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
kvm_timer_vcpu_terminate(vcpu);
kvm_pmu_vcpu_destroy(vcpu);
+ kvm_arch_async_pf_destroy_vcpu(vcpu);
kvm_sdei_destroy_vcpu(vcpu);
kvm_arm_vcpu_destroy(vcpu);
diff --git a/arch/arm64/kvm/async_pf.c b/arch/arm64/kvm/async_pf.c
new file mode 100644
index 000000000000..742bb8a0a8c0
--- /dev/null
+++ b/arch/arm64/kvm/async_pf.c
@@ -0,0 +1,145 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Asynchronous page fault support.
+ *
+ * Copyright (C) 2021 Red Hat, Inc.
+ *
+ * Author(s): Gavin Shan <gshan@redhat.com>
+ */
+
+#include <linux/arm-smccc.h>
+#include <linux/kvm_host.h>
+#include <asm/kvm_emulate.h>
+#include <kvm/arm_hypercalls.h>
+#include <kvm/arm_vgic.h>
+#include <asm/kvm_sdei.h>
+
+static inline int read_cache(struct kvm_vcpu *vcpu, u32 offset, u32 *val)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_arch_async_pf_control *apf = vcpu->arch.apf;
+
+ return kvm_read_guest_offset_cached(kvm, &apf->cache,
+ val, offset, sizeof(*val));
+}
+
+static inline int write_cache(struct kvm_vcpu *vcpu, u32 offset, u32 val)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_arch_async_pf_control *apf = vcpu->arch.apf;
+
+ return kvm_write_guest_offset_cached(kvm, &apf->cache,
+ &val, offset, sizeof(val));
+}
+
+void kvm_arch_async_pf_create_vcpu(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.apf = kzalloc(sizeof(*(vcpu->arch.apf)), GFP_KERNEL);
+}
+
+bool kvm_arch_async_not_present_allowed(struct kvm_vcpu *vcpu)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_arch_async_pf_control *apf = vcpu->arch.apf;
+ struct kvm_sdei_vcpu *vsdei = vcpu->arch.sdei;
+ u32 reason, token;
+ int ret;
+
+ if (!apf || !(apf->control_block & KVM_ASYNC_PF_ENABLED))
+ return false;
+
+ if (apf->send_user_only && vcpu_mode_priv(vcpu))
+ return false;
+
+ if (!irqchip_in_kernel(vcpu->kvm))
+ return false;
+
+ if (!vsdei || vsdei->critical_event || vsdei->normal_event)
+ return false;
+
+ /* Pending page fault, which isn't acknowledged by guest */
+ ret = read_cache(vcpu, offsetof(struct kvm_vcpu_pv_apf_data, reason),
+ &reason);
+ if (ret) {
+ kvm_err("%s: Error %d to read reason (%d-%d)\n",
+ __func__, ret, kvm->userspace_pid, vcpu->vcpu_idx);
+ return false;
+ }
+
+ ret = read_cache(vcpu, offsetof(struct kvm_vcpu_pv_apf_data, token),
+ &token);
+ if (ret) {
+ kvm_err("%s: Error %d to read token %d-%d\n",
+ __func__, ret, kvm->userspace_pid, vcpu->vcpu_idx);
+ return false;
+ }
+
+ if (reason || token)
+ return false;
+
+ return true;
+}
+
+bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu,
+ u32 esr, gpa_t gpa, gfn_t gfn)
+{
+ struct kvm_arch_async_pf_control *apf = vcpu->arch.apf;
+ struct kvm_arch_async_pf arch;
+ unsigned long hva = kvm_vcpu_gfn_to_hva(vcpu, gfn);
+
+ arch.token = (apf->id++ << 12) | vcpu->vcpu_id;
+ arch.gfn = gfn;
+ arch.esr = esr;
+
+ return kvm_setup_async_pf(vcpu, gpa, hva, &arch);
+}
+
+/*
+ * It's guaranteed that no pending asynchronous page fault when this is
+ * called. It means all previous issued asynchronous page faults have
+ * been acknowledged.
+ */
+bool kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
+ struct kvm_async_pf *work)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_arch_async_pf_control *apf = vcpu->arch.apf;
+ int ret;
+
+ kvm_async_pf_add_slot(vcpu, work->arch.gfn);
+
+ ret = write_cache(vcpu, offsetof(struct kvm_vcpu_pv_apf_data, token),
+ work->arch.token);
+ if (ret) {
+ kvm_err("%s: Error %d to write token (%d-%d %08x)\n",
+ __func__, ret, kvm->userspace_pid,
+ vcpu->vcpu_idx, work->arch.token);
+ goto fail;
+ }
+
+ ret = write_cache(vcpu, offsetof(struct kvm_vcpu_pv_apf_data, reason),
+ KVM_PV_REASON_PAGE_NOT_PRESENT);
+ if (ret) {
+ kvm_err("%s: Error %d to write reason (%d-%d %08x)\n",
+ __func__, ret, kvm->userspace_pid,
+ vcpu->vcpu_idx, work->arch.token);
+ goto fail;
+ }
+
+ apf->notpresent_pending = true;
+ apf->notpresent_token = work->arch.token;
+
+ return !kvm_sdei_inject(vcpu, apf->sdei_event_num, true);
+
+fail:
+ write_cache(vcpu, offsetof(struct kvm_vcpu_pv_apf_data, token), 0);
+ write_cache(vcpu, offsetof(struct kvm_vcpu_pv_apf_data, reason), 0);
+ kvm_async_pf_remove_slot(vcpu, work->arch.gfn);
+ return false;
+}
+
+void kvm_arch_async_pf_destroy_vcpu(struct kvm_vcpu *vcpu)
+{
+ kfree(vcpu->arch.apf);
+ vcpu->arch.apf = NULL;
+}
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 2b8035fc7b47..a9f9f53aaeee 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -844,6 +844,33 @@ static inline bool is_write_fault(unsigned int esr)
return esr_dabt_is_wnr(esr);
}
+static bool try_async_pf(struct kvm_vcpu *vcpu, unsigned int esr,
+ gpa_t gpa, gfn_t gfn, kvm_pfn_t *pfn,
+ bool write, bool *writable, bool prefault)
+{
+ struct kvm_arch_async_pf_control *apf = vcpu->arch.apf;
+ struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
+ bool async = false;
+
+ if (apf) {
+ /* Bail if *pfn has correct page */
+ *pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async,
+ write, writable, NULL);
+ if (!async)
+ return false;
+
+ if (!prefault && kvm_arch_async_not_present_allowed(vcpu)) {
+ if (kvm_async_pf_find_slot(vcpu, gfn) ||
+ kvm_arch_setup_async_pf(vcpu, esr, gpa, gfn))
+ return true;
+ }
+ }
+
+ *pfn = __gfn_to_pfn_memslot(slot, gfn, false, NULL,
+ write, writable, NULL);
+ return false;
+}
+
int kvm_handle_user_mem_abort(struct kvm_vcpu *vcpu,
struct kvm_memory_slot *memslot,
phys_addr_t fault_ipa,
@@ -959,8 +986,10 @@ int kvm_handle_user_mem_abort(struct kvm_vcpu *vcpu,
*/
smp_rmb();
- pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL,
- write_fault, &writable, NULL);
+ if (try_async_pf(vcpu, esr, fault_ipa, gfn, &pfn,
+ write_fault, &writable, prefault))
+ return 1;
+
if (pfn == KVM_PFN_ERR_HWPOISON) {
kvm_send_hwpoison_signal(hva, vma_shift);
return 0;
--
2.23.0
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v3 08/15] KVM: arm64: Support page-ready notification
2021-05-07 8:40 [PATCH v3 00/15] Support Asynchronous Page Fault Gavin Shan
` (6 preceding siblings ...)
2021-05-07 8:40 ` [PATCH v3 07/15] KVM: arm64: Support page-not-present notification Gavin Shan
@ 2021-05-07 8:40 ` Gavin Shan
2021-05-07 8:40 ` [PATCH v3 09/15] KVM: arm64: Support async PF hypercalls Gavin Shan
` (6 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Gavin Shan @ 2021-05-07 8:40 UTC (permalink / raw)
To: kvmarm
Cc: linux-kernel, maz, will, pbonzini, james.morse, mark.rutland,
Jonathan.Cameron, shan.gavin
The asynchronous page fault starts with a worker when the requested
page isn't present. The worker makes the requested page present
in the background and the worker, together with the associated
information, is queued to the completion queue after that. The
worker and the completion queue are checked as below.
* A request (KVM_REQ_ASYNC_PF) is raised if the worker is the
first one enqueued to the completion queue. With the request,
the completion queue is checked and the worker is dequeued.
A PPI is sent to guest as the page-ready notification and
the guest should acknowledge the interrupt by SMCCC interface.
* When the notification (PPI) is acknowledged by guest, the
completion queue is checked again and next worker is dequeued
if we have one. For this particular worker, another notification
(PPI) is sent to the guest without raising the request. Once the
notification (PPI) is acknowledged by the guest, the completion
queue is checked to process next worker, which has been queued
to it.
Similar to page-not-present notification, the shared memory region
is used to convey the reason and token associated with the page-ready
notification. The region is represented by "struct kvm_vcpu_pv_apf_data".
The feature isn't enabled by CONFIG_KVM_ASYNC_PF yet. Also, the control
path isn't implemented and will be done in the subsequent patches.
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
arch/arm64/include/asm/kvm_host.h | 15 ++
arch/arm64/include/uapi/asm/kvm_para.h | 1 +
arch/arm64/kvm/arm.c | 24 ++-
arch/arm64/kvm/async_pf.c | 205 +++++++++++++++++++++++++
arch/arm64/kvm/hypercalls.c | 5 +
include/linux/arm-smccc.h | 10 ++
6 files changed, 257 insertions(+), 3 deletions(-)
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index e241a93c6485..98aab1c910d0 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -47,6 +47,7 @@
#define KVM_REQ_RECORD_STEAL KVM_ARCH_REQ(3)
#define KVM_REQ_RELOAD_GICv4 KVM_ARCH_REQ(4)
#define KVM_REQ_SDEI KVM_ARCH_REQ(5)
+#define KVM_REQ_ASYNC_PF KVM_ARCH_REQ(6)
#define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
KVM_DIRTY_LOG_INITIALLY_SET)
@@ -291,10 +292,12 @@ struct kvm_arch_async_pf_control {
u64 control_block;
bool send_user_only;
u64 sdei_event_num;
+ u32 irq;
u16 id;
bool notpresent_pending;
u32 notpresent_token;
+ bool pageready_pending;
};
struct kvm_vcpu_arch {
@@ -764,6 +767,13 @@ bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu,
u32 esr, gpa_t gpa, gfn_t gfn);
bool kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
struct kvm_async_pf *work);
+void kvm_arch_async_page_present_queued(struct kvm_vcpu *vcpu);
+bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu);
+void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,
+ struct kvm_async_pf *work);
+void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
+ struct kvm_async_pf *work);
+void kvm_arch_async_pf_hypercall(struct kvm_vcpu *vcpu, u64 *val);
void kvm_arch_async_pf_destroy_vcpu(struct kvm_vcpu *vcpu);
#else
static inline void kvm_arch_async_pf_create_vcpu(struct kvm_vcpu *vcpu) { }
@@ -779,6 +789,11 @@ static inline bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu,
{
return false;
}
+
+static inline void kvm_arch_async_pf_hypercall(struct kvm_vcpu *vcpu, u64 *val)
+{
+ val[0] = SMCCC_RET_NOT_SUPPORTED;
+}
#endif
/* Guest/host FPSIMD coordination helpers */
diff --git a/arch/arm64/include/uapi/asm/kvm_para.h b/arch/arm64/include/uapi/asm/kvm_para.h
index 3fa04006714e..162325e2638f 100644
--- a/arch/arm64/include/uapi/asm/kvm_para.h
+++ b/arch/arm64/include/uapi/asm/kvm_para.h
@@ -9,6 +9,7 @@
#define KVM_ASYNC_PF_SEND_ALWAYS (1 << 1)
#define KVM_PV_REASON_PAGE_NOT_PRESENT 1
+#define KVM_PV_REASON_PAGE_READY 2
struct kvm_vcpu_pv_apf_data {
__u32 reason;
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index f77aab668c90..70ba3593880a 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -494,9 +494,23 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
*/
int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
{
+ struct kvm_arch_async_pf_control *apf = v->arch.apf;
bool irq_lines = *vcpu_hcr(v) & (HCR_VI | HCR_VF);
- return ((irq_lines || kvm_vgic_vcpu_pending_irq(v))
- && !v->arch.power_off && !v->arch.pause);
+
+ if ((irq_lines || kvm_vgic_vcpu_pending_irq(v)) &&
+ !v->arch.power_off && !v->arch.pause)
+ return true;
+
+ if (apf && (apf->control_block & KVM_ASYNC_PF_ENABLED)) {
+ if (kvm_check_async_pf_completion_queue(v))
+ return true;
+
+ if (apf->notpresent_pending ||
+ apf->pageready_pending)
+ return true;
+ }
+
+ return false;
}
bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
@@ -686,6 +700,9 @@ static void check_vcpu_requests(struct kvm_vcpu *vcpu)
if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu))
kvm_reset_vcpu(vcpu);
+ if (kvm_check_request(KVM_REQ_ASYNC_PF, vcpu))
+ kvm_check_async_pf_completion(vcpu);
+
if (kvm_check_request(KVM_REQ_SDEI, vcpu))
kvm_sdei_deliver(vcpu);
@@ -801,7 +818,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
smp_store_mb(vcpu->mode, IN_GUEST_MODE);
if (ret <= 0 || need_new_vmid_gen(&vcpu->arch.hw_mmu->vmid) ||
- kvm_request_pending(vcpu)) {
+ (kvm_request_pending(vcpu) &&
+ READ_ONCE(vcpu->requests) != (1UL << KVM_REQ_ASYNC_PF))) {
vcpu->mode = OUTSIDE_GUEST_MODE;
isb(); /* Ensure work in x_flush_hwstate is committed */
kvm_pmu_sync_hwstate(vcpu);
diff --git a/arch/arm64/kvm/async_pf.c b/arch/arm64/kvm/async_pf.c
index 742bb8a0a8c0..0d2393e24ce6 100644
--- a/arch/arm64/kvm/async_pf.c
+++ b/arch/arm64/kvm/async_pf.c
@@ -138,6 +138,211 @@ bool kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
return false;
}
+void kvm_arch_async_page_present_queued(struct kvm_vcpu *vcpu)
+{
+ struct kvm_arch_async_pf_control *apf = vcpu->arch.apf;
+
+ kvm_make_request(KVM_REQ_ASYNC_PF, vcpu);
+ if (apf && !apf->pageready_pending)
+ kvm_vcpu_kick(vcpu);
+}
+
+bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_arch_async_pf_control *apf = vcpu->arch.apf;
+ struct kvm_async_pf *work;
+ u32 reason, token;
+ int ret;
+
+ if (!apf || !(apf->control_block & KVM_ASYNC_PF_ENABLED))
+ return true;
+
+ if (apf->pageready_pending)
+ goto fail;
+
+ ret = read_cache(vcpu, offsetof(struct kvm_vcpu_pv_apf_data, reason),
+ &reason);
+ if (ret) {
+ kvm_err("%s: Error %d to read reason (%d-%d)\n",
+ __func__, ret, kvm->userspace_pid, vcpu->vcpu_idx);
+ goto fail;
+ }
+
+ ret = read_cache(vcpu, offsetof(struct kvm_vcpu_pv_apf_data, token),
+ &token);
+ if (ret) {
+ kvm_err("%s: Error %d to read token (%d-%d)\n",
+ __func__, ret, kvm->userspace_pid, vcpu->vcpu_idx);
+ goto fail;
+ }
+
+ /*
+ * There might be pending page-not-present notification (SDEI)
+ * to be delivered. However, the corresponding work has been
+ * completed. For this case, we need to cancel the notification
+ * early to avoid the overhead because of the injected SDEI
+ * and interrupt.
+ */
+ if (apf->notpresent_pending) {
+ spin_lock(&vcpu->async_pf.lock);
+ work = list_first_entry_or_null(&vcpu->async_pf.done,
+ typeof(*work), link);
+ spin_unlock(&vcpu->async_pf.lock);
+ if (!work)
+ goto fail;
+
+ if (reason == KVM_PV_REASON_PAGE_NOT_PRESENT &&
+ work->arch.token == apf->notpresent_token &&
+ token == apf->notpresent_token) {
+ kvm_make_request(KVM_REQ_ASYNC_PF, vcpu);
+ return true;
+ }
+ }
+
+ if (reason || token)
+ goto fail;
+
+ return true;
+
+fail:
+ kvm_make_request(KVM_REQ_ASYNC_PF, vcpu);
+ return false;
+}
+
+void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,
+ struct kvm_async_pf *work)
+{
+ struct kvm_memory_slot *memslot;
+ unsigned int esr = work->arch.esr;
+ phys_addr_t gpa = work->cr2_or_gpa;
+ gfn_t gfn = gpa >> PAGE_SHIFT;
+ unsigned long hva;
+ bool write_fault, writable;
+ int idx;
+
+ /*
+ * We shouldn't issue prefault for special work to wake up
+ * all pending tasks because the associated token (address)
+ * is invalid.
+ */
+ if (work->wakeup_all)
+ return;
+
+ /*
+ * The gpa was validated before the work is started. However, the
+ * memory slots might be changed since then. So we need to redo the
+ * validatation here.
+ */
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
+
+ if (esr_dabt_is_s1ptw(esr))
+ write_fault = true;
+ else if (ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_LOW)
+ write_fault = false;
+ else
+ write_fault = esr_dabt_is_wnr(esr);
+
+ memslot = gfn_to_memslot(vcpu->kvm, gfn);
+ hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable);
+ if (kvm_is_error_hva(hva) || (write_fault && !writable))
+ goto out;
+
+ kvm_handle_user_mem_abort(vcpu, memslot, gpa, hva, esr, true);
+
+out:
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
+}
+
+/*
+ * It's guaranteed that no pending asynchronous page fault when this is
+ * called. It means all previous issued asynchronous page faults have
+ * been acknowledged.
+ */
+void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
+ struct kvm_async_pf *work)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_arch_async_pf_control *apf = vcpu->arch.apf;
+ int ret;
+
+ /*
+ * The work could be completed prior to page-not-present notification
+ * delivery. In this case, what we need to do is just to cancel the
+ * page-not-present notification to avoid unnecessary overhead.
+ */
+ if (work->wakeup_all) {
+ work->arch.token = ~0;
+ } else {
+ kvm_async_pf_remove_slot(vcpu, work->arch.gfn);
+
+ if (apf->notpresent_pending &&
+ apf->notpresent_token == work->arch.token &&
+ !kvm_sdei_cancel(vcpu, apf->sdei_event_num)) {
+ apf->notpresent_pending = false;
+ apf->notpresent_token = 0;
+ goto done;
+ }
+ }
+
+ ret = write_cache(vcpu, offsetof(struct kvm_vcpu_pv_apf_data, token),
+ work->arch.token);
+ if (ret) {
+ kvm_err("%s: Error %d to write token (%d-%d %08x)\n",
+ __func__, ret, kvm->userspace_pid,
+ vcpu->vcpu_idx, work->arch.token);
+ goto done;
+ }
+
+ ret = write_cache(vcpu, offsetof(struct kvm_vcpu_pv_apf_data, reason),
+ KVM_PV_REASON_PAGE_READY);
+ if (ret) {
+ kvm_err("%s: Error %d to write reason (%d-%d %08x)\n",
+ __func__, ret, kvm->userspace_pid,
+ vcpu->vcpu_idx, work->arch.token);
+ goto done;
+ }
+
+ apf->pageready_pending = true;
+ kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_idx,
+ apf->irq, true, NULL);
+ return;
+
+done:
+ write_cache(vcpu, offsetof(struct kvm_vcpu_pv_apf_data, reason), 0);
+ write_cache(vcpu, offsetof(struct kvm_vcpu_pv_apf_data, token), 0);
+}
+
+void kvm_arch_async_pf_hypercall(struct kvm_vcpu *vcpu, u64 *val)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_arch_async_pf_control *apf = vcpu->arch.apf;
+ u32 func;
+ long ret = SMCCC_RET_SUCCESS;
+
+ if (!apf) {
+ val[0] = SMCCC_RET_NOT_SUPPORTED;
+ return;
+ }
+
+ func = smccc_get_arg1(vcpu);
+ switch (func) {
+ case ARM_SMCCC_KVM_FUNC_ASYNC_PF_IRQ_ACK:
+ if (!apf->pageready_pending)
+ break;
+
+ kvm_vgic_inject_irq(kvm, vcpu->vcpu_idx,
+ apf->irq, false, NULL);
+ apf->pageready_pending = false;
+ kvm_check_async_pf_completion(vcpu);
+ break;
+ default:
+ ret = SMCCC_RET_NOT_SUPPORTED;
+ }
+
+ val[0] = ret;
+}
+
void kvm_arch_async_pf_destroy_vcpu(struct kvm_vcpu *vcpu)
{
kfree(vcpu->arch.apf);
diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c
index d3fc893a4f58..bf423cb27280 100644
--- a/arch/arm64/kvm/hypercalls.c
+++ b/arch/arm64/kvm/hypercalls.c
@@ -129,10 +129,15 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
case ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID:
val[0] = BIT(ARM_SMCCC_KVM_FUNC_FEATURES);
val[0] |= BIT(ARM_SMCCC_KVM_FUNC_PTP);
+ if (vcpu->arch.apf)
+ val[0] |= BIT(ARM_SMCCC_KVM_FUNC_ASYNC_PF);
break;
case ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID:
kvm_ptp_get_time(vcpu, val);
break;
+ case ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID:
+ kvm_arch_async_pf_hypercall(vcpu, val);
+ break;
case ARM_SMCCC_TRNG_VERSION:
case ARM_SMCCC_TRNG_FEATURES:
case ARM_SMCCC_TRNG_GET_UUID:
diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index 6861489a1890..a3ef03a672be 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -104,6 +104,7 @@
/* KVM "vendor specific" services */
#define ARM_SMCCC_KVM_FUNC_FEATURES 0
#define ARM_SMCCC_KVM_FUNC_PTP 1
+#define ARM_SMCCC_KVM_FUNC_ASYNC_PF 2
#define ARM_SMCCC_KVM_FUNC_FEATURES_2 127
#define ARM_SMCCC_KVM_NUM_FUNCS 128
@@ -130,6 +131,15 @@
#define KVM_PTP_VIRT_COUNTER 0
#define KVM_PTP_PHYS_COUNTER 1
+/* Asynchronous page fault service */
+#define ARM_SMCCC_KVM_FUNC_ASYNC_PF_IRQ_ACK 5
+
+#define ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID \
+ ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
+ ARM_SMCCC_SMC_32, \
+ ARM_SMCCC_OWNER_VENDOR_HYP, \
+ ARM_SMCCC_KVM_FUNC_ASYNC_PF)
+
/* Paravirtualised time calls (defined by ARM DEN0057A) */
#define ARM_SMCCC_HV_PV_TIME_FEATURES \
ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \
--
2.23.0
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v3 09/15] KVM: arm64: Support async PF hypercalls
2021-05-07 8:40 [PATCH v3 00/15] Support Asynchronous Page Fault Gavin Shan
` (7 preceding siblings ...)
2021-05-07 8:40 ` [PATCH v3 08/15] KVM: arm64: Support page-ready notification Gavin Shan
@ 2021-05-07 8:40 ` Gavin Shan
2021-05-07 8:40 ` [PATCH v3 10/15] KVM: arm64: Support async PF ioctl commands Gavin Shan
` (5 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Gavin Shan @ 2021-05-07 8:40 UTC (permalink / raw)
To: kvmarm
Cc: linux-kernel, maz, will, pbonzini, james.morse, mark.rutland,
Jonathan.Cameron, shan.gavin
This introduces (SMCCC) KVM vendor specific services to configure
the asynchronous page fault functionality. The following services
are introduced:
* ARM_SMCCC_KVM_FUNC_ASYNC_PF_VERSION
Returns the version, which can be used to identify ABI changes
in the future.
* ARM_SMCCC_KVM_FUNC_ASYNC_PF_SLOTS
Return maximal number of tokens that current vCPU can have.
It's used by guest to allocate the required resources.
* ARM_SMCCC_KVM_FUNC_ASYNC_PF_{SDEI, IRQ}
Return the associated SDEI or (PPI) IRQ number, configured by
vCPU ioctl command.
* ARM_SMCCC_KVM_FUNC_ASYNC_PF_ENABLE
Enable or disable asynchronous page fault on current vCPU.
The corresponding SDEI event and (PPI) IRQ are owned by VMM. So they
are configured by vCPU ioctl interface and it will be implemented when
the asynchronous page fault capability is exported in the subsequent
patches.
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
arch/arm64/kvm/async_pf.c | 119 ++++++++++++++++++++++++++++++++++++++
include/linux/arm-smccc.h | 5 ++
2 files changed, 124 insertions(+)
diff --git a/arch/arm64/kvm/async_pf.c b/arch/arm64/kvm/async_pf.c
index 0d2393e24ce6..3bc69a631996 100644
--- a/arch/arm64/kvm/async_pf.c
+++ b/arch/arm64/kvm/async_pf.c
@@ -313,11 +313,114 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
write_cache(vcpu, offsetof(struct kvm_vcpu_pv_apf_data, token), 0);
}
+static void kvm_arch_async_sdei_notifier(struct kvm_vcpu *vcpu,
+ unsigned long num,
+ unsigned int state)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_arch_async_pf_control *apf = vcpu->arch.apf;
+
+ if (!apf)
+ return;
+
+ if (num != apf->sdei_event_num) {
+ kvm_err("%s: Invalid event number (%d-%d %lx-%llx)\n",
+ __func__, kvm->userspace_pid, vcpu->vcpu_idx,
+ num, apf->sdei_event_num);
+ return;
+ }
+
+ switch (state) {
+ case KVM_SDEI_NOTIFY_DELIVERED:
+ if (!apf->notpresent_pending)
+ break;
+
+ apf->notpresent_token = 0;
+ apf->notpresent_pending = false;
+ break;
+ case KVM_SDEI_NOTIFY_COMPLETED:
+ break;
+ default:
+ kvm_err("%s: Invalid state (%d-%d %lx-%d)\n",
+ __func__, kvm->userspace_pid, vcpu->vcpu_idx,
+ num, state);
+ }
+}
+
+static long kvm_arch_async_enable(struct kvm_vcpu *vcpu, u64 data)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_arch_async_pf_control *apf = vcpu->arch.apf;
+ gpa_t gpa = (data & ~0x3FUL);
+ bool enabled, enable;
+ int ret;
+
+ if (!apf || !irqchip_in_kernel(kvm))
+ return SMCCC_RET_NOT_SUPPORTED;
+
+ /* Bail if the state transition isn't allowed */
+ enabled = !!(apf->control_block & KVM_ASYNC_PF_ENABLED);
+ enable = !!(data & KVM_ASYNC_PF_ENABLED);
+ if (enable == enabled) {
+ kvm_debug("%s: Async PF has been %s on (%d-%d %llx-%llx)\n",
+ __func__, enabled ? "enabled" : "disabled",
+ kvm->userspace_pid, vcpu->vcpu_idx,
+ apf->control_block, data);
+ return SMCCC_RET_NOT_REQUIRED;
+ }
+
+ /* To disable the functinality */
+ if (!enable) {
+ kvm_clear_async_pf_completion_queue(vcpu);
+ apf->control_block = data;
+ return SMCCC_RET_SUCCESS;
+ }
+
+ /*
+ * The SDEI event and IRQ number should have been given
+ * prior to enablement.
+ */
+ if (!apf->sdei_event_num || !apf->irq) {
+ kvm_err("%s: Invalid SDEI event or IRQ (%d-%d %llx-%d)\n",
+ __func__, kvm->userspace_pid, vcpu->vcpu_idx,
+ apf->sdei_event_num, apf->irq);
+ return SMCCC_RET_INVALID_PARAMETER;
+ }
+
+ /* Register SDEI event notifier */
+ ret = kvm_sdei_register_notifier(kvm, apf->sdei_event_num,
+ kvm_arch_async_sdei_notifier);
+ if (ret) {
+ kvm_err("%s: Error %d registering SDEI notifier (%d-%d %llx)\n",
+ __func__, ret, kvm->userspace_pid, vcpu->vcpu_idx,
+ apf->sdei_event_num);
+ return SMCCC_RET_NOT_SUPPORTED;
+ }
+
+ /* Initialize cache shared by host and guest */
+ ret = kvm_gfn_to_hva_cache_init(kvm, &apf->cache, gpa,
+ offsetofend(struct kvm_vcpu_pv_apf_data, token));
+ if (ret) {
+ kvm_err("%s: Error %d initializing cache (%d-%d)\n",
+ __func__, ret, kvm->userspace_pid, vcpu->vcpu_idx);
+ return SMCCC_RET_NOT_SUPPORTED;
+ }
+
+ /* Flush the token table */
+ kvm_async_pf_reset_slot(vcpu);
+ apf->send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS);
+ kvm_async_pf_wakeup_all(vcpu);
+ apf->control_block = data;
+
+ return SMCCC_RET_SUCCESS;
+}
+
void kvm_arch_async_pf_hypercall(struct kvm_vcpu *vcpu, u64 *val)
{
struct kvm *kvm = vcpu->kvm;
struct kvm_arch_async_pf_control *apf = vcpu->arch.apf;
u32 func;
+ u64 data;
long ret = SMCCC_RET_SUCCESS;
if (!apf) {
@@ -327,6 +430,22 @@ void kvm_arch_async_pf_hypercall(struct kvm_vcpu *vcpu, u64 *val)
func = smccc_get_arg1(vcpu);
switch (func) {
+ case ARM_SMCCC_KVM_FUNC_ASYNC_PF_VERSION:
+ val[1] = 0x010000; /* v1.0.0 */
+ break;
+ case ARM_SMCCC_KVM_FUNC_ASYNC_PF_SLOTS:
+ val[1] = ASYNC_PF_PER_VCPU;
+ break;
+ case ARM_SMCCC_KVM_FUNC_ASYNC_PF_SDEI:
+ val[1] = apf->sdei_event_num;
+ break;
+ case ARM_SMCCC_KVM_FUNC_ASYNC_PF_IRQ:
+ val[1] = apf->irq;
+ break;
+ case ARM_SMCCC_KVM_FUNC_ASYNC_PF_ENABLE:
+ data = (smccc_get_arg3(vcpu) << 32) | smccc_get_arg2(vcpu);
+ ret = kvm_arch_async_enable(vcpu, data);
+ break;
case ARM_SMCCC_KVM_FUNC_ASYNC_PF_IRQ_ACK:
if (!apf->pageready_pending)
break;
diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index a3ef03a672be..abfcdeb789ae 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -132,6 +132,11 @@
#define KVM_PTP_PHYS_COUNTER 1
/* Asynchronous page fault service */
+#define ARM_SMCCC_KVM_FUNC_ASYNC_PF_VERSION 0
+#define ARM_SMCCC_KVM_FUNC_ASYNC_PF_SLOTS 1
+#define ARM_SMCCC_KVM_FUNC_ASYNC_PF_SDEI 2
+#define ARM_SMCCC_KVM_FUNC_ASYNC_PF_IRQ 3
+#define ARM_SMCCC_KVM_FUNC_ASYNC_PF_ENABLE 4
#define ARM_SMCCC_KVM_FUNC_ASYNC_PF_IRQ_ACK 5
#define ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID \
--
2.23.0
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v3 10/15] KVM: arm64: Support async PF ioctl commands
2021-05-07 8:40 [PATCH v3 00/15] Support Asynchronous Page Fault Gavin Shan
` (8 preceding siblings ...)
2021-05-07 8:40 ` [PATCH v3 09/15] KVM: arm64: Support async PF hypercalls Gavin Shan
@ 2021-05-07 8:40 ` Gavin Shan
2021-05-07 8:40 ` [PATCH v3 11/15] KVM: arm64: Export async PF capability Gavin Shan
` (4 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Gavin Shan @ 2021-05-07 8:40 UTC (permalink / raw)
To: kvmarm
Cc: linux-kernel, maz, will, pbonzini, james.morse, mark.rutland,
Jonathan.Cameron, shan.gavin
This supports ioctl commands for configuration and migration:
KVM_ARM_ASYNC_PF_CMD_GET_VERSION
Return implementation version
KVM_ARM_ASYNC_PF_CMD_GET_SDEI
Return SDEI event number used for page-not-present notification
KVM_ARM_ASYNC_PF_CMD_GET_IRQ
Return IRQ number used for page-ready notification
KVM_ARM_ASYNC_PF_CMD_GET_CONTROL
Get control block when VM is migrated
KVM_ARM_ASYNC_PF_CMD_SET_SDEI
Set SDEI event number when VM is started or migrated
KVM_ARM_ASYNC_PF_CMD_SET_IRQ
Set IRQ number during when VM is started or migrated
KVM_ARM_ASYNC_PF_CMD_SET_CONTROL
Set control block when VM is migrated
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
arch/arm64/include/asm/kvm_host.h | 14 +++++++
arch/arm64/include/uapi/asm/kvm.h | 19 +++++++++
arch/arm64/kvm/arm.c | 6 +++
arch/arm64/kvm/async_pf.c | 64 +++++++++++++++++++++++++++++++
include/uapi/linux/kvm.h | 3 ++
5 files changed, 106 insertions(+)
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 98aab1c910d0..f21b58733eba 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -774,6 +774,8 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,
void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
struct kvm_async_pf *work);
void kvm_arch_async_pf_hypercall(struct kvm_vcpu *vcpu, u64 *val);
+long kvm_arch_async_pf_vm_ioctl(struct kvm *kvm, unsigned long arg);
+long kvm_arch_async_pf_vcpu_ioctl(struct kvm_vcpu *vcpu, unsigned long arg);
void kvm_arch_async_pf_destroy_vcpu(struct kvm_vcpu *vcpu);
#else
static inline void kvm_arch_async_pf_create_vcpu(struct kvm_vcpu *vcpu) { }
@@ -794,6 +796,18 @@ static inline void kvm_arch_async_pf_hypercall(struct kvm_vcpu *vcpu, u64 *val)
{
val[0] = SMCCC_RET_NOT_SUPPORTED;
}
+
+static inline long kvm_arch_async_pf_vm_ioctl(struct kvm *kvm,
+ unsigned long arg)
+{
+ return -EPERM;
+}
+
+static inline long kvm_arch_async_pf_vcpu_ioctl(struct kvm_vcpu *vcpu,
+ unsigned long arg)
+{
+ return -EPERM;
+}
#endif
/* Guest/host FPSIMD coordination helpers */
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index 15499751997d..a6124068bee6 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -403,6 +403,25 @@ struct kvm_vcpu_events {
#define KVM_PSCI_RET_INVAL PSCI_RET_INVALID_PARAMS
#define KVM_PSCI_RET_DENIED PSCI_RET_DENIED
+/* Asynchronous page fault */
+#define KVM_ARM_ASYNC_PF_CMD_GET_VERSION 0
+#define KVM_ARM_ASYNC_PF_CMD_GET_SDEI 1
+#define KVM_ARM_ASYNC_PF_CMD_GET_IRQ 2
+#define KVM_ARM_ASYNC_PF_CMD_GET_CONTROL 3
+#define KVM_ARM_ASYNC_PF_CMD_SET_SDEI 4
+#define KVM_ARM_ASYNC_PF_CMD_SET_IRQ 5
+#define KVM_ARM_ASYNC_PF_CMD_SET_CONTROL 6
+
+struct kvm_arm_async_pf_cmd {
+ __u32 cmd;
+ union {
+ __u32 version;
+ __u64 sdei;
+ __u32 irq;
+ __u64 control;
+ };
+};
+
#endif
#endif /* __ARM_KVM_H__ */
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 70ba3593880a..1f869eaf93d6 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1299,6 +1299,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
case KVM_ARM_SDEI_COMMAND: {
return kvm_sdei_vcpu_ioctl(vcpu, arg);
}
+ case KVM_ARM_ASYNC_PF_COMMAND: {
+ return kvm_arch_async_pf_vcpu_ioctl(vcpu, arg);
+ }
default:
r = -EINVAL;
}
@@ -1376,6 +1379,9 @@ long kvm_arch_vm_ioctl(struct file *filp,
case KVM_ARM_SDEI_COMMAND: {
return kvm_sdei_vm_ioctl(kvm, arg);
}
+ case KVM_ARM_ASYNC_PF_COMMAND: {
+ return kvm_arch_async_pf_vm_ioctl(kvm, arg);
+ }
default:
return -EINVAL;
}
diff --git a/arch/arm64/kvm/async_pf.c b/arch/arm64/kvm/async_pf.c
index 3bc69a631996..3aaed516540f 100644
--- a/arch/arm64/kvm/async_pf.c
+++ b/arch/arm64/kvm/async_pf.c
@@ -462,6 +462,70 @@ void kvm_arch_async_pf_hypercall(struct kvm_vcpu *vcpu, u64 *val)
val[0] = ret;
}
+long kvm_arch_async_pf_vm_ioctl(struct kvm *kvm, unsigned long arg)
+{
+ struct kvm_arm_async_pf_cmd cmd;
+ unsigned int version = 0x010000; /* v1.0.0 */
+ void __user *argp = (void __user *)arg;
+
+ if (copy_from_user(&cmd, argp, sizeof(cmd)))
+ return -EFAULT;
+
+ if (cmd.cmd != KVM_ARM_ASYNC_PF_CMD_GET_VERSION)
+ return -EINVAL;
+
+ cmd.version = version;
+ if (copy_to_user(argp, &cmd, sizeof(cmd)))
+ return -EFAULT;
+
+ return 0;
+}
+
+long kvm_arch_async_pf_vcpu_ioctl(struct kvm_vcpu *vcpu, unsigned long arg)
+{
+ struct kvm_arch_async_pf_control *apf = vcpu->arch.apf;
+ struct kvm_arm_async_pf_cmd cmd;
+ void __user *argp = (void __user *)arg;
+ long ret = 0;
+
+ if (!apf)
+ return -EPERM;
+
+ if (copy_from_user(&cmd, argp, sizeof(cmd)))
+ return -EFAULT;
+
+ switch (cmd.cmd) {
+ case KVM_ARM_ASYNC_PF_CMD_GET_SDEI:
+ cmd.sdei = apf->sdei_event_num;
+ break;
+ case KVM_ARM_ASYNC_PF_CMD_GET_IRQ:
+ cmd.irq = apf->irq;
+ break;
+ case KVM_ARM_ASYNC_PF_CMD_GET_CONTROL:
+ cmd.control = apf->control_block;
+ break;
+ case KVM_ARM_ASYNC_PF_CMD_SET_SDEI:
+ apf->sdei_event_num = cmd.sdei;
+ break;
+ case KVM_ARM_ASYNC_PF_CMD_SET_IRQ:
+ apf->irq = cmd.irq;
+ break;
+ case KVM_ARM_ASYNC_PF_CMD_SET_CONTROL:
+ if (kvm_arch_async_enable(vcpu, cmd.control) !=
+ SMCCC_RET_SUCCESS)
+ ret = -EIO;
+
+ break;
+ default:
+ ret = -EINVAL;
+ }
+
+ if (!ret && copy_to_user(argp, &cmd, sizeof(cmd)))
+ ret = -EFAULT;
+
+ return ret;
+}
+
void kvm_arch_async_pf_destroy_vcpu(struct kvm_vcpu *vcpu)
{
kfree(vcpu->arch.apf);
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 96641e528526..8f5ec382954e 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1649,6 +1649,9 @@ struct kvm_xen_vcpu_attr {
/* Available with KVM_CAP_ARM_SDEI */
#define KVM_ARM_SDEI_COMMAND _IOWR(KVMIO, 0xcc, struct kvm_sdei_cmd)
+/* Available with KVM_CAP_ASYNC_PF or KVM_CAP_ASYNC_PF_INT */
+#define KVM_ARM_ASYNC_PF_COMMAND _IOWR(KVMIO, 0xcd, struct kvm_arm_async_pf_cmd)
+
/* Secure Encrypted Virtualization command */
enum sev_cmd_id {
/* Guest initialization commands */
--
2.23.0
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v3 11/15] KVM: arm64: Export async PF capability
2021-05-07 8:40 [PATCH v3 00/15] Support Asynchronous Page Fault Gavin Shan
` (9 preceding siblings ...)
2021-05-07 8:40 ` [PATCH v3 10/15] KVM: arm64: Support async PF ioctl commands Gavin Shan
@ 2021-05-07 8:40 ` Gavin Shan
2021-05-07 8:40 ` [PATCH v3 12/15] arm64: Detect async PF para-virtualization feature Gavin Shan
` (3 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Gavin Shan @ 2021-05-07 8:40 UTC (permalink / raw)
To: kvmarm
Cc: linux-kernel, maz, will, pbonzini, james.morse, mark.rutland,
Jonathan.Cameron, shan.gavin
This exports the asynchronous page fault capability:
* Identify capability KVM_CAP_ASYNC_{PF, PF_INT}.
* Standardize SDEI event for asynchronous page fault.
* Enable kernel config CONFIG_KVM_ASYNC_{PF, PF_SLOT}.
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
arch/arm64/include/uapi/asm/kvm_sdei.h | 1 +
arch/arm64/kvm/Kconfig | 2 ++
arch/arm64/kvm/arm.c | 4 ++++
arch/arm64/kvm/sdei.c | 5 +++++
4 files changed, 12 insertions(+)
diff --git a/arch/arm64/include/uapi/asm/kvm_sdei.h b/arch/arm64/include/uapi/asm/kvm_sdei.h
index f7a6b2b22b50..cbe8be3d0a25 100644
--- a/arch/arm64/include/uapi/asm/kvm_sdei.h
+++ b/arch/arm64/include/uapi/asm/kvm_sdei.h
@@ -16,6 +16,7 @@
#define KVM_SDEI_MAX_VCPUS 512
#define KVM_SDEI_INVALID_NUM 0
#define KVM_SDEI_DEFAULT_NUM 0x40400000
+#define KVM_SDEI_ASYNC_PF_NUM 0x40400001
struct kvm_sdei_event_state {
__u64 num;
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index 3964acf5451e..dfb3ed0de2ca 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -31,6 +31,8 @@ menuconfig KVM
select SRCU
select KVM_VFIO
select HAVE_KVM_EVENTFD
+ select KVM_ASYNC_PF
+ select KVM_ASYNC_PF_SLOT
select HAVE_KVM_IRQFD
select HAVE_KVM_MSI
select HAVE_KVM_IRQCHIP
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 1f869eaf93d6..eec77a7b61c6 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -272,6 +272,10 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_ARM_SDEI:
r = 1;
break;
+ case KVM_CAP_ASYNC_PF:
+ case KVM_CAP_ASYNC_PF_INT:
+ r = IS_ENABLED(CONFIG_KVM_ASYNC_PF) ? 1 : 0;
+ break;
default:
r = 0;
}
diff --git a/arch/arm64/kvm/sdei.c b/arch/arm64/kvm/sdei.c
index 4f5a582daa97..437303bfafba 100644
--- a/arch/arm64/kvm/sdei.c
+++ b/arch/arm64/kvm/sdei.c
@@ -19,6 +19,11 @@ static struct kvm_sdei_event_state defined_kse[] = {
1,
SDEI_EVENT_PRIORITY_CRITICAL
},
+ { KVM_SDEI_ASYNC_PF_NUM,
+ SDEI_EVENT_TYPE_PRIVATE,
+ 1,
+ SDEI_EVENT_PRIORITY_CRITICAL
+ },
};
static struct kvm_sdei_event *kvm_sdei_find_event(struct kvm *kvm,
--
2.23.0
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v3 12/15] arm64: Detect async PF para-virtualization feature
2021-05-07 8:40 [PATCH v3 00/15] Support Asynchronous Page Fault Gavin Shan
` (10 preceding siblings ...)
2021-05-07 8:40 ` [PATCH v3 11/15] KVM: arm64: Export async PF capability Gavin Shan
@ 2021-05-07 8:40 ` Gavin Shan
2021-05-07 8:40 ` [PATCH v3 13/15] arm64: Reschedule process on aync PF Gavin Shan
` (2 subsequent siblings)
14 siblings, 0 replies; 16+ messages in thread
From: Gavin Shan @ 2021-05-07 8:40 UTC (permalink / raw)
To: kvmarm
Cc: linux-kernel, maz, will, pbonzini, james.morse, mark.rutland,
Jonathan.Cameron, shan.gavin
This implements kvm_para_available() to check if para-virtualization
features are available or not. Besides, kvm_para_has_feature() is
enhanced to detect the asynchronous page fault para-virtualization
feature. These two functions are going to be used by guest kernel
to enable the asynchronous page fault.
This also adds kernel option (CONFIG_KVM_GUEST), which is the umbrella
for the optimizations related to KVM para-virtualization.
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
arch/arm64/Kconfig | 11 +++++++++++
arch/arm64/include/asm/kvm_para.h | 12 +++++++++++-
arch/arm64/include/uapi/asm/kvm_para.h | 2 ++
3 files changed, 24 insertions(+), 1 deletion(-)
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 7f2a80091337..c03499c1acd6 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1104,6 +1104,17 @@ config PARAVIRT_TIME_ACCOUNTING
If in doubt, say N here.
+config KVM_GUEST
+ bool "KVM Guest Support"
+ depends on PARAVIRT
+ default y
+ help
+ This option enables various optimizations for running under the KVM
+ hypervisor. Overhead for the kernel when not running inside KVM should
+ be minimal.
+
+ In case of doubt, say Y
+
config KEXEC
depends on PM_SLEEP_SMP
select KEXEC_CORE
diff --git a/arch/arm64/include/asm/kvm_para.h b/arch/arm64/include/asm/kvm_para.h
index 0ea481dd1c7a..8f39c60a6619 100644
--- a/arch/arm64/include/asm/kvm_para.h
+++ b/arch/arm64/include/asm/kvm_para.h
@@ -3,6 +3,8 @@
#define _ASM_ARM_KVM_PARA_H
#include <uapi/asm/kvm_para.h>
+#include <linux/of.h>
+#include <asm/hypervisor.h>
static inline bool kvm_check_and_clear_guest_paused(void)
{
@@ -11,7 +13,12 @@ static inline bool kvm_check_and_clear_guest_paused(void)
static inline unsigned int kvm_arch_para_features(void)
{
- return 0;
+ unsigned int features = 0;
+
+ if (kvm_arm_hyp_service_available(ARM_SMCCC_KVM_FUNC_ASYNC_PF))
+ features |= (1 << KVM_FEATURE_ASYNC_PF);
+
+ return features;
}
static inline unsigned int kvm_arch_para_hints(void)
@@ -21,6 +28,9 @@ static inline unsigned int kvm_arch_para_hints(void)
static inline bool kvm_para_available(void)
{
+ if (IS_ENABLED(CONFIG_KVM_GUEST))
+ return true;
+
return false;
}
diff --git a/arch/arm64/include/uapi/asm/kvm_para.h b/arch/arm64/include/uapi/asm/kvm_para.h
index 162325e2638f..70bbc7d1ec75 100644
--- a/arch/arm64/include/uapi/asm/kvm_para.h
+++ b/arch/arm64/include/uapi/asm/kvm_para.h
@@ -4,6 +4,8 @@
#include <linux/types.h>
+#define KVM_FEATURE_ASYNC_PF 0
+
/* Async PF */
#define KVM_ASYNC_PF_ENABLED (1 << 0)
#define KVM_ASYNC_PF_SEND_ALWAYS (1 << 1)
--
2.23.0
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v3 13/15] arm64: Reschedule process on aync PF
2021-05-07 8:40 [PATCH v3 00/15] Support Asynchronous Page Fault Gavin Shan
` (11 preceding siblings ...)
2021-05-07 8:40 ` [PATCH v3 12/15] arm64: Detect async PF para-virtualization feature Gavin Shan
@ 2021-05-07 8:40 ` Gavin Shan
2021-05-07 8:40 ` [PATCH v3 14/15] arm64: Enable async PF Gavin Shan
2021-05-07 8:40 ` [PATCH v3 15/15] KVM: arm64: Add async PF document Gavin Shan
14 siblings, 0 replies; 16+ messages in thread
From: Gavin Shan @ 2021-05-07 8:40 UTC (permalink / raw)
To: kvmarm
Cc: linux-kernel, maz, will, pbonzini, james.morse, mark.rutland,
Jonathan.Cameron, shan.gavin
The page-not-present notification is delivered by SDEI event. The
guest reschedules current process to another one when the SDEI event
is received. It's not safe to do so in the SDEI event handler because
the SDEI event should be acknowledged as soon as possible.
So the rescheduling is postponed until the current process switches
from kernel to user mode. In order to trigger the switch, the SDEI
event handler sends (reschedule) IPI to current CPU and it's delivered
in time after the SDEI event is acknowledged.
A new thread flag (TIF_ASYNC_PF) is introduced in order to track the
state for the process, to be rescheduled. With the flag is set, there
is a head of wait-queue is associated with the process. The process
keeps rescheduling itself until the flag is cleared when page-ready
notification is received through (PPI) interrupt.
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
arch/arm64/include/asm/processor.h | 1 +
arch/arm64/include/asm/thread_info.h | 4 +++-
arch/arm64/kernel/signal.c | 17 +++++++++++++++++
3 files changed, 21 insertions(+), 1 deletion(-)
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 9df3feeee890..003788834a12 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -154,6 +154,7 @@ struct thread_struct {
u64 gcr_user_excl;
#endif
u64 sctlr_user;
+ void *data;
};
#define SCTLR_USER_MASK \
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 6623c99f0984..38567adb26be 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -67,6 +67,7 @@ int arch_dup_task_struct(struct task_struct *dst,
#define TIF_UPROBE 4 /* uprobe breakpoint or singlestep */
#define TIF_MTE_ASYNC_FAULT 5 /* MTE Asynchronous Tag Check Fault */
#define TIF_NOTIFY_SIGNAL 6 /* signal notifications exist */
+#define TIF_ASYNC_PF 7 /* Asynchronous page fault */
#define TIF_SYSCALL_TRACE 8 /* syscall trace active */
#define TIF_SYSCALL_AUDIT 9 /* syscall auditing */
#define TIF_SYSCALL_TRACEPOINT 10 /* syscall tracepoint for ftrace */
@@ -97,11 +98,12 @@ int arch_dup_task_struct(struct task_struct *dst,
#define _TIF_SVE (1 << TIF_SVE)
#define _TIF_MTE_ASYNC_FAULT (1 << TIF_MTE_ASYNC_FAULT)
#define _TIF_NOTIFY_SIGNAL (1 << TIF_NOTIFY_SIGNAL)
+#define _TIF_ASYNC_PF (1 << TIF_ASYNC_PF)
#define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
_TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \
_TIF_UPROBE | _TIF_MTE_ASYNC_FAULT | \
- _TIF_NOTIFY_SIGNAL)
+ _TIF_NOTIFY_SIGNAL | _TIF_ASYNC_PF)
#define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
_TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 6237486ff6bb..2cd2d13aa905 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -915,6 +915,23 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
unsigned long thread_flags)
{
do {
+ if (thread_flags & _TIF_ASYNC_PF) {
+ struct swait_queue_head *wq =
+ READ_ONCE(current->thread.data);
+ DECLARE_SWAITQUEUE(wait);
+
+ local_daif_restore(DAIF_PROCCTX_NOIRQ);
+
+ do {
+ prepare_to_swait_exclusive(wq,
+ &wait, TASK_UNINTERRUPTIBLE);
+ if (!test_thread_flag(TIF_ASYNC_PF))
+ break;
+
+ schedule();
+ } while (test_thread_flag(TIF_ASYNC_PF));
+ }
+
if (thread_flags & _TIF_NEED_RESCHED) {
/* Unmask Debug and SError for the next task */
local_daif_restore(DAIF_PROCCTX_NOIRQ);
--
2.23.0
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v3 14/15] arm64: Enable async PF
2021-05-07 8:40 [PATCH v3 00/15] Support Asynchronous Page Fault Gavin Shan
` (12 preceding siblings ...)
2021-05-07 8:40 ` [PATCH v3 13/15] arm64: Reschedule process on aync PF Gavin Shan
@ 2021-05-07 8:40 ` Gavin Shan
2021-05-07 8:40 ` [PATCH v3 15/15] KVM: arm64: Add async PF document Gavin Shan
14 siblings, 0 replies; 16+ messages in thread
From: Gavin Shan @ 2021-05-07 8:40 UTC (permalink / raw)
To: kvmarm
Cc: linux-kernel, maz, will, pbonzini, james.morse, mark.rutland,
Jonathan.Cameron, shan.gavin
This enables asynchronous page fault from guest side. The design
is highlighted as below:
* The per-vCPU shared memory region, which is represented by
"struct kvm_vcpu_pv_apf_data", is allocated. The reason and
token associated with the received notifications of asynchronous
page fault are delivered through it.
* A per-vCPU table, which is represented by "struct kvm_apf_table",
is allocated. The process, on which the page-not-present notification
is received, is added into the table so that it can reschedule
itself on switching from kernel to user mode. Afterwards, the
process, identified by token, is removed from the table and put
into runnable state when page-ready notification is received.
* During CPU hotplug, the (private) SDEI event is expected to be
enabled or disabled on the affected CPU by SDEI client driver.
The (PPI) interrupt is enabled or disabled on the affected CPU
by ourself. When the system is going to reboot, the SDEI event
is disabled and unregistered and the (PPI) interrupt is disabled.
* The SDEI event and (PPI) interrupt number are retrieved from host
through SMCCC interface. Besides, the version of the asynchronous
page fault is validated when the feature is enabled on the guest.
* The feature is disabled on guest when boot parameter "no-kvmapf"
is specified.
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
arch/arm64/kernel/Makefile | 1 +
arch/arm64/kernel/kvm.c | 452 +++++++++++++++++++++++++++++++++++++
2 files changed, 453 insertions(+)
create mode 100644 arch/arm64/kernel/kvm.c
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 6cc97730790e..af1b9e29f314 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -52,6 +52,7 @@ obj-$(CONFIG_ACPI) += acpi.o
obj-$(CONFIG_ACPI_NUMA) += acpi_numa.o
obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL) += acpi_parking_protocol.o
obj-$(CONFIG_PARAVIRT) += paravirt.o
+obj-$(CONFIG_KVM_GUEST) += kvm.o
obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
obj-$(CONFIG_HIBERNATION) += hibernate.o hibernate-asm.o
obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o \
diff --git a/arch/arm64/kernel/kvm.c b/arch/arm64/kernel/kvm.c
new file mode 100644
index 000000000000..effe8dc7e921
--- /dev/null
+++ b/arch/arm64/kernel/kvm.c
@@ -0,0 +1,452 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Asynchronous page fault support.
+ *
+ * Copyright (C) 2021 Red Hat, Inc.
+ *
+ * Author(s): Gavin Shan <gshan@redhat.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/arm-smccc.h>
+#include <linux/kvm_para.h>
+#include <linux/arm_sdei.h>
+#include <linux/acpi.h>
+#include <linux/cpuhotplug.h>
+#include <linux/reboot.h>
+
+struct kvm_apf_task {
+ unsigned int token;
+ struct task_struct *task;
+ struct swait_queue_head wq;
+};
+
+struct kvm_apf_table {
+ raw_spinlock_t lock;
+ unsigned int count;
+ struct kvm_apf_task tasks[0];
+};
+
+static bool async_pf_available = true;
+static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_data) __aligned(64);
+static struct kvm_apf_table __percpu *apf_tables;
+static unsigned int apf_tasks;
+static unsigned int apf_sdei_num;
+static unsigned int apf_ppi_num;
+static int apf_irq;
+
+static bool kvm_async_pf_add_task(struct task_struct *task,
+ unsigned int token)
+{
+ struct kvm_apf_table *table = this_cpu_ptr(apf_tables);
+ unsigned int i, index = apf_tasks;
+ bool ret = false;
+
+ raw_spin_lock(&table->lock);
+
+ if (WARN_ON(table->count >= apf_tasks))
+ goto unlock;
+
+ for (i = 0; i < apf_tasks; i++) {
+ if (!table->tasks[i].task) {
+ if (index == apf_tasks) {
+ ret = true;
+ index = i;
+ }
+ } else if (table->tasks[i].task == task) {
+ WARN_ON(table->tasks[i].token != token);
+ ret = false;
+ break;
+ }
+ }
+
+ if (!ret)
+ goto unlock;
+
+ task->thread.data = &table->tasks[index].wq;
+ set_tsk_thread_flag(task, TIF_ASYNC_PF);
+
+ table->count++;
+ table->tasks[index].task = task;
+ table->tasks[index].token = token;
+
+unlock:
+ raw_spin_unlock(&table->lock);
+ return ret;
+}
+
+static inline void kvm_async_pf_remove_one_task(struct kvm_apf_table *table,
+ unsigned int index)
+{
+ clear_tsk_thread_flag(table->tasks[index].task, TIF_ASYNC_PF);
+ WRITE_ONCE(table->tasks[index].task->thread.data, NULL);
+
+ table->count--;
+ table->tasks[index].task = NULL;
+ table->tasks[index].token = 0;
+
+ swake_up_one(&table->tasks[index].wq);
+}
+
+static bool kvm_async_pf_remove_task(unsigned int token)
+{
+ struct kvm_apf_table *table = this_cpu_ptr(apf_tables);
+ unsigned int i;
+ bool ret = (token == UINT_MAX);
+
+ raw_spin_lock(&table->lock);
+
+ for (i = 0; i < apf_tasks; i++) {
+ if (!table->tasks[i].task)
+ continue;
+
+ /* Wakeup all */
+ if (token == UINT_MAX) {
+ kvm_async_pf_remove_one_task(table, i);
+ continue;
+ }
+
+ if (table->tasks[i].token == token) {
+ kvm_async_pf_remove_one_task(table, i);
+ ret = true;
+ break;
+ }
+ }
+
+ raw_spin_unlock(&table->lock);
+
+ return ret;
+}
+
+static int kvm_async_pf_sdei_handler(unsigned int event,
+ struct pt_regs *regs,
+ void *arg)
+{
+ unsigned int reason = __this_cpu_read(apf_data.reason);
+ unsigned int token = __this_cpu_read(apf_data.token);
+ bool ret;
+
+ if (reason != KVM_PV_REASON_PAGE_NOT_PRESENT) {
+ pr_warn("%s: Bogus notification (%d, 0x%08x)\n",
+ __func__, reason, token);
+ return -EINVAL;
+ }
+
+ ret = kvm_async_pf_add_task(current, token);
+ __this_cpu_write(apf_data.token, 0);
+ __this_cpu_write(apf_data.reason, 0);
+
+ if (!ret)
+ return -ENOSPC;
+
+ smp_send_reschedule(smp_processor_id());
+
+ return 0;
+}
+
+static irqreturn_t kvm_async_pf_irq_handler(int irq, void *dev_id)
+{
+ unsigned int reason = __this_cpu_read(apf_data.reason);
+ unsigned int token = __this_cpu_read(apf_data.token);
+ struct arm_smccc_res res;
+
+ if (reason != KVM_PV_REASON_PAGE_READY) {
+ pr_warn("%s: Bogus interrupt %d (%d, 0x%08x)\n",
+ __func__, irq, reason, token);
+ return IRQ_HANDLED;
+ }
+
+ kvm_async_pf_remove_task(token);
+
+ __this_cpu_write(apf_data.token, 0);
+ __this_cpu_write(apf_data.reason, 0);
+ arm_smccc_1_1_invoke(ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID,
+ ARM_SMCCC_KVM_FUNC_ASYNC_PF_IRQ_ACK, &res);
+
+ return IRQ_HANDLED;
+}
+
+static int __init kvm_async_pf_available(char *arg)
+{
+ async_pf_available = false;
+
+ return 0;
+}
+early_param("no-kvmapf", kvm_async_pf_available);
+
+static void kvm_async_pf_disable(void)
+{
+ struct arm_smccc_res res;
+ u32 enabled = __this_cpu_read(apf_data.enabled);
+
+ if (!enabled)
+ return;
+
+ /* Disable the functionality */
+ arm_smccc_1_1_invoke(ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID,
+ ARM_SMCCC_KVM_FUNC_ASYNC_PF_ENABLE,
+ 0, 0, &res);
+ if (res.a0 != SMCCC_RET_SUCCESS) {
+ pr_warn("%s: Error %ld to disable on CPU%d\n",
+ __func__, res.a0, smp_processor_id());
+ return;
+ }
+
+ __this_cpu_write(apf_data.enabled, 0);
+
+ pr_info("Async PF disabled on CPU%d\n", smp_processor_id());
+}
+
+static void kvm_async_pf_enable(void)
+{
+ struct arm_smccc_res res;
+ u32 enabled = __this_cpu_read(apf_data.enabled);
+ u64 val = virt_to_phys(this_cpu_ptr(&apf_data));
+
+ if (enabled)
+ return;
+
+ val |= KVM_ASYNC_PF_ENABLED;
+ arm_smccc_1_1_invoke(ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID,
+ ARM_SMCCC_KVM_FUNC_ASYNC_PF_ENABLE,
+ (u32)val, (u32)(val >> 32), &res);
+ if (res.a0 != SMCCC_RET_SUCCESS) {
+ pr_warn("%s: Error %ld to enable CPU%d\n",
+ __func__, res.a0, smp_processor_id());
+ return;
+ }
+
+ __this_cpu_write(apf_data.enabled, 1);
+
+ pr_info("Async PF enabled on CPU%d\n", smp_processor_id());
+}
+
+static void kvm_async_pf_cpu_disable(void *info)
+{
+ disable_percpu_irq(apf_irq);
+ kvm_async_pf_disable();
+}
+
+static void kvm_async_pf_cpu_enable(void *info)
+{
+ enable_percpu_irq(apf_irq, IRQ_TYPE_LEVEL_HIGH);
+ kvm_async_pf_enable();
+}
+
+static int kvm_async_pf_cpu_reboot_notify(struct notifier_block *nb,
+ unsigned long code,
+ void *unused)
+{
+ if (code == SYS_RESTART) {
+ sdei_event_disable(apf_sdei_num);
+ sdei_event_unregister(apf_sdei_num);
+
+ on_each_cpu(kvm_async_pf_cpu_disable, NULL, 1);
+ }
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block kvm_async_pf_cpu_reboot_nb = {
+ .notifier_call = kvm_async_pf_cpu_reboot_notify,
+};
+
+static int kvm_async_pf_cpu_online(unsigned int cpu)
+{
+ kvm_async_pf_cpu_enable(NULL);
+
+ return 0;
+}
+
+static int kvm_async_pf_cpu_offline(unsigned int cpu)
+{
+ kvm_async_pf_cpu_disable(NULL);
+
+ return 0;
+}
+
+static int __init kvm_async_pf_check_version(void)
+{
+ struct arm_smccc_res res;
+
+ /*
+ * Check the version and v1.0.0 or higher version is required
+ * to support the functionality.
+ */
+ arm_smccc_1_1_invoke(ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID,
+ ARM_SMCCC_KVM_FUNC_ASYNC_PF_VERSION, &res);
+ if (res.a0 != SMCCC_RET_SUCCESS) {
+ pr_warn("%s: Error %ld to get version\n",
+ __func__, res.a0);
+ return -EPERM;
+ }
+
+ if ((res.a1 & 0xFFFFFFFFFF000000) ||
+ ((res.a1 & 0xFF0000) >> 16) < 0x1) {
+ pr_warn("%s: Invalid version (0x%016lx)\n",
+ __func__, res.a1);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int __init kvm_async_pf_info(void)
+{
+ struct arm_smccc_res res;
+
+ /* Retrieve number of tokens */
+ arm_smccc_1_1_invoke(ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID,
+ ARM_SMCCC_KVM_FUNC_ASYNC_PF_SLOTS, &res);
+ if (res.a0 != SMCCC_RET_SUCCESS) {
+ pr_warn("%s: Error %ld to get token number\n",
+ __func__, res.a0);
+ return -EPERM;
+ }
+
+ apf_tasks = res.a1 * 2;
+
+ /* Retrieve SDEI event number */
+ arm_smccc_1_1_invoke(ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID,
+ ARM_SMCCC_KVM_FUNC_ASYNC_PF_SDEI, &res);
+ if (res.a0 != SMCCC_RET_SUCCESS) {
+ pr_warn("%s: Error %ld to get SDEI event number\n",
+ __func__, res.a0);
+ return -EPERM;
+ }
+
+ apf_sdei_num = res.a1;
+
+ /* Retrieve (PPI) interrupt number */
+ arm_smccc_1_1_invoke(ARM_SMCCC_VENDOR_HYP_KVM_ASYNC_PF_FUNC_ID,
+ ARM_SMCCC_KVM_FUNC_ASYNC_PF_IRQ, &res);
+ if (res.a0 != SMCCC_RET_SUCCESS) {
+ pr_warn("%s: Error %ld to get IRQ\n",
+ __func__, res.a0);
+ return -EPERM;
+ }
+
+ apf_ppi_num = res.a1;
+
+ return 0;
+}
+
+static int __init kvm_async_pf_init(void)
+{
+ struct kvm_apf_table *table;
+ size_t size;
+ int cpu, i, ret;
+
+ if (!kvm_para_has_feature(KVM_FEATURE_ASYNC_PF) ||
+ !async_pf_available)
+ return -EPERM;
+
+ ret = kvm_async_pf_check_version();
+ if (ret)
+ return ret;
+
+ ret = kvm_async_pf_info();
+ if (ret)
+ return ret;
+
+ /* Allocate and initialize the sleeper table */
+ size = sizeof(struct kvm_apf_table) +
+ apf_tasks * sizeof(struct kvm_apf_task);
+ apf_tables = __alloc_percpu(size, 0);
+ if (!apf_tables) {
+ pr_warn("%s: Unable to alloc async PF table\n",
+ __func__);
+ return -ENOMEM;
+ }
+
+ for_each_possible_cpu(cpu) {
+ table = per_cpu_ptr(apf_tables, cpu);
+ raw_spin_lock_init(&table->lock);
+ for (i = 0; i < apf_tasks; i++)
+ init_swait_queue_head(&table->tasks[i].wq);
+ }
+
+ /*
+ * Initialize SDEI event for page-not-present notification.
+ * The SDEI event number should have been retrieved from
+ * the host.
+ */
+ ret = sdei_event_register(apf_sdei_num,
+ kvm_async_pf_sdei_handler, NULL);
+ if (ret) {
+ pr_warn("%s: Error %d to register SDEI event\n",
+ __func__, ret);
+ ret = -EIO;
+ goto release_tables;
+ }
+
+ ret = sdei_event_enable(apf_sdei_num);
+ if (ret) {
+ pr_warn("%s: Error %d to enable SDEI event\n",
+ __func__, ret);
+ goto unregister_event;
+ }
+
+ /*
+ * Initialize interrupt for page-ready notification. The
+ * interrupt number and its properties should have been
+ * retrieved from the ACPI:APFT table.
+ */
+ apf_irq = acpi_register_gsi(NULL, apf_ppi_num,
+ ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_HIGH);
+ if (apf_irq <= 0) {
+ ret = -EIO;
+ pr_warn("%s: Error %d to register IRQ\n",
+ __func__, apf_irq);
+ goto disable_event;
+ }
+
+ ret = request_percpu_irq(apf_irq, kvm_async_pf_irq_handler,
+ "Asynchronous Page Fault", &apf_data);
+ if (ret) {
+ pr_warn("%s: Error %d to request IRQ\n",
+ __func__, ret);
+ goto unregister_irq;
+ }
+
+ register_reboot_notifier(&kvm_async_pf_cpu_reboot_nb);
+ ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+ "arm/kvm:online", kvm_async_pf_cpu_online,
+ kvm_async_pf_cpu_offline);
+ if (ret < 0) {
+ pr_warn("%s: Error %d to install cpu hotplug callbacks\n",
+ __func__, ret);
+ goto release_irq;
+ }
+
+ /* Enable async PF on the online CPUs */
+ on_each_cpu(kvm_async_pf_cpu_enable, NULL, 1);
+
+ return 0;
+
+release_irq:
+ free_percpu_irq(apf_irq, &apf_data);
+unregister_irq:
+ acpi_unregister_gsi(apf_ppi_num);
+disable_event:
+ sdei_event_disable(apf_sdei_num);
+unregister_event:
+ sdei_event_unregister(apf_sdei_num);
+release_tables:
+ free_percpu(apf_tables);
+
+ return ret;
+}
+
+static int __init kvm_guest_init(void)
+{
+ return kvm_async_pf_init();
+}
+
+fs_initcall(kvm_guest_init);
--
2.23.0
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v3 15/15] KVM: arm64: Add async PF document
2021-05-07 8:40 [PATCH v3 00/15] Support Asynchronous Page Fault Gavin Shan
` (13 preceding siblings ...)
2021-05-07 8:40 ` [PATCH v3 14/15] arm64: Enable async PF Gavin Shan
@ 2021-05-07 8:40 ` Gavin Shan
14 siblings, 0 replies; 16+ messages in thread
From: Gavin Shan @ 2021-05-07 8:40 UTC (permalink / raw)
To: kvmarm
Cc: linux-kernel, maz, will, pbonzini, james.morse, mark.rutland,
Jonathan.Cameron, shan.gavin
This adds document to explain the interface for asynchronous page
fault and how it works in general.
Signed-off-by: Gavin Shan <gshan@redhat.com>
---
Documentation/virt/kvm/arm/apf.rst | 143 +++++++++++++++++++++++++++
Documentation/virt/kvm/arm/index.rst | 1 +
2 files changed, 144 insertions(+)
create mode 100644 Documentation/virt/kvm/arm/apf.rst
diff --git a/Documentation/virt/kvm/arm/apf.rst b/Documentation/virt/kvm/arm/apf.rst
new file mode 100644
index 000000000000..4f5c01b6699f
--- /dev/null
+++ b/Documentation/virt/kvm/arm/apf.rst
@@ -0,0 +1,143 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Asynchronous Page Fault Support for arm64
+=========================================
+
+There are two stages of page faults when KVM module is enabled as accelerator
+to the guest. The guest is responsible for handling the stage-1 page faults,
+while the host handles the stage-2 page faults. During the period of handling
+the stage-2 page faults, the guest is suspended until the requested page is
+ready. It could take several milliseconds, even hundreds of milliseconds in
+extreme situations because I/O might be required to move the requested page
+from disk to DRAM. The guest does not do any work when it is suspended. The
+feature (Asynchronous Page Fault) is introduced to take advantage of the
+suspending period and to improve the overall performance.
+
+There are two paths in order to fulfil the asynchronous page fault, called
+as control path and data path. The control path allows the VMM or guest to
+configure the functionality, while the notifications are delivered in data
+path. The notifications are classified into page-not-present and page-ready
+notifications.
+
+Data Path
+---------
+
+There are two types of notifications delivered from host to guest in the
+data path: page-not-present and page-ready notification. They are delivered
+through SDEI event and (PPI) interrupt separately. Besides, there is a shared
+buffer between host and guest to indicate the reason and sequential token,
+which is used to identify the asynchronous page fault. The reason and token
+resident in the shared buffer is written by host, read and cleared by guest.
+An asynchronous page fault is delivered and completed as below.
+
+(1) When an asynchronous page fault starts, a (workqueue) worker is created
+ and queued to the vCPU's pending queue. The worker makes the requested
+ page ready and resident to DRAM in the background. The shared buffer is
+ updated with reason and sequential token. After that, SDEI event is sent
+ to guest as page-not-present notification.
+
+(2) When the SDEI event is received on guest, the current process is tagged
+ with TIF_ASYNC_PF and associated with a wait queue. The process is ready
+ to keep rescheduling itself on switching from kernel to user mode. After
+ that, a reschedule IPI is sent to current CPU and the received SDEI event
+ is acknowledged. Note that the IPI is delivered when the acknowledgment
+ on the SDEI event is received on host.
+
+(3) On the host, the worker is dequeued from the vCPU's pending queue and
+ enqueued to its completion queue when the requested page becomes ready.
+ In the mean while, KVM_REQ_ASYNC_PF request is sent the vCPU if the
+ worker is the first element enqueued to the completion queue.
+
+(4) With pending KVM_REQ_ASYNC_PF request, the first worker in the completion
+ queue is dequeued and destroyed. In the mean while, a (PPI) interrupt is
+ sent to guest with updated reason and token in the shared buffer.
+
+(5) When the (PPI) interrupt is received on guest, the affected process is
+ located using the token and waken up after its TIF_ASYNC_PF tag is cleared.
+ After that, the interrupt is acknowledged through SMCCC interface. The
+ workers in the completion queue is dequeued and destroyed if any workers
+ exist, and another (PPI) interrupt is sent to the guest.
+
+Control Path
+------------
+
+The configurations are passed through SMCCC or ioctl interface. The SDEI
+event and (PPI) interrupt are owned by VMM, so the SDEI event and interrupt
+numbers are configured through ioctl command on per-vCPU basis. Besides,
+the functionality might be enabled and configured through ioctl interface
+by VMM during migration:
+
+ * KVM_ARM_ASYNC_PF_CMD_GET_VERSION
+
+ Returns the current version of the feature, supported by the host. It is
+ made up of major, minor and revision fields. Each field is one byte in
+ length.
+
+ * KVM_ARM_ASYNC_PF_CMD_GET_SDEI:
+
+ Retrieve the SDEI event number, used for page-not-present notification,
+ so that it can be configured on destination VM in the scenario of
+ migration.
+
+ * KVM_ARM_ASYNC_PF_GET_IRQ:
+
+ Retrieve the IRQ (PPI) number, used for page-ready notification, so that
+ it can be configured on destination VM in the scenario of migration.
+
+ * KVM_ARM_ASYNC_PF_CMD_GET_CONTROL
+
+ Retrieve the address of control block, so that it can be configured on
+ destination VM in the scenario of migration.
+
+ * KVM_ARM_ASYNC_PF_CMD_SET_SDEI:
+
+ Used by VMM to configure number of SDEI event, which is used to deliver
+ page-not-present notification by host. This is used when VM is started
+ or migrated.
+
+ * KVM_ARM_ASYNC_PF_CMD_SET_IRQ
+
+ Used by VMM to configure number of (PPI) interrupt, which is used to
+ deliver page-ready notification by host. This is used when VM is started
+ or migrated.
+
+ * KVM_ARM_ASYNC_PF_CMD_SET_CONTROL
+
+ Set the control block on the destination VM in the scenario of migration.
+
+The other configurations are passed through SMCCC interface. The host exports
+the capability through KVM vendor specific service, which is identified by
+ARM_SMCCC_KVM_FUNC_ASYNC_PF_FUNC_ID. There are several functions defined for
+this:
+
+ * ARM_SMCCC_KVM_FUNC_ASYNC_PF_VERSION
+
+ Returns the current version of the feature, supported by the host. It is
+ made up of major, minor and revision fields. Each field is one byte in
+ length.
+
+ * ARM_SMCCC_KVM_FUNC_ASYNC_PF_SLOTS
+
+ Returns the size of the hashed GFN table. It is used by guest to set up
+ the capacity of waiting process table.
+
+ * ARM_SMCCC_KVM_FUNC_ASYNC_PF_SDEI
+ * ARM_SMCCC_KVM_FUNC_ASYNC_PF_IRQ
+
+ Used by the guest to retrieve the SDEI event and (PPI) interrupt number
+ that are configured by VMM.
+
+ * ARM_SMCCC_KVM_FUNC_ASYNC_PF_ENABLE
+
+ Used by the guest to enable or disable the feature on the specific vCPU.
+ The argument is made up of shared buffer and flags. The shared buffer
+ is written by host to indicate the reason about the delivered asynchronous
+ page fault and token (sequence number) to identify that. There are two
+ flags are supported: KVM_ASYNC_PF_ENABLED is used to enable or disable
+ the feature. KVM_ASYNC_PF_SEND_ALWAYS allows to deliver page-not-present
+ notification regardless of the guest's state. Otherwise, the notification
+ is delivered only when the guest is in user mode.
+
+ * ARM_SMCCC_KVM_FUNC_ASYNC_PF_IRQ_ACK
+
+ Used by the guest to acknowledge the completion of page-ready notification.
diff --git a/Documentation/virt/kvm/arm/index.rst b/Documentation/virt/kvm/arm/index.rst
index 78a9b670aafe..f43b5fe25f61 100644
--- a/Documentation/virt/kvm/arm/index.rst
+++ b/Documentation/virt/kvm/arm/index.rst
@@ -7,6 +7,7 @@ ARM
.. toctree::
:maxdepth: 2
+ apf
hyp-abi
psci
pvtime
--
2.23.0
^ permalink raw reply related [flat|nested] 16+ messages in thread