KVM: Dirty ring interface
Subsystems (8)
v2 cover KVM: Dirty ring interface
Branch is here: https://github.com/xzpeter/linux/tree/kvm-dirty-ring
(based on 5.4.0)
This is v2 of the dirty ring series, and also the first non-RFC version of it. I didn't put a changelog from v1-rfc because I feel like it would be easier to go into the patchset comparing to read that lengthy and probably helpless changelog. However I do like to do a summary here on what has majorly changed, and also some conclusions on the previous v1 discussions.
======================
* Per-vm ring is dropped
For x86 (which is still the major focus for now), we found that kvmgt is probably the only one that still writes to the guest without a vcpu context. It would be a complete pity if we keep the per-vm ring only for kvmgt (who shouldn't write directly to guest via kvm api after all...), so remove it. Work should be ongoing in parallel to refactor kvmgt to not use kvm apis like kvm_write_guest().
However I don't want to break kvmgt before it's fixed. So this series uses an interim way to solve this by fallback no-vcpu-context writes to vcpu0 if there is. So we will keep the interface clean (per-vcpu only), while we don't break the code base. After kvmgt is fixed, we can probably even drop this special fallback and kvm->dirty_ring_lock.
* Waitqueue is still kept (for now)
We did plan to drop the waitqueue, however again if with kvmgt we still have chance to ful-fill a ring (and I feel like it'll definitely happen if we migrate a kvmgt guest). This series will only trigger the waitqueue mechanism if it's the special case (no-vcpu-context) and actually it naturally avoids another mmu lock deadlock issue I've encountered, which is good.
For vcpu context writes, now the series is even more strict that we'll directly fail the KVM_RUN if the dirty ring is soft full, until the userspace collects the dirty rings first. That'll guarantee the ring will never be full. With that, I dropped KVM_REQ_DIRTY_RING_FULL together because then it's not needed.
Potentially this could still also be used by ARM when there're code paths that dump the ARM device information to the guests (e.g. KVM_DEV_ARM_ITS_SAVE_TABLES). We'll see. No matter what, even if the code is there, x86 (as long as without kvmgt) should never trigger waitqueue.
Although the waitqueue is kept, I dropped the complete waitqueue test, simply because now I can never trigger it without kvmgt...
* Why not virtio?
There's already some discussion during v1 patchset on whether it's good to use virtio for the data path of delivering dirty pages [1]. I'd confess the only thing that we might consider to use is the vring layout (because virtqueue is tightly bound to devices, while we don't have a device contet here), however it's a pity that even we only use the most low-level vring api it'll be at least iov based which is already an overkill for dirty ring (which is literally an array of addresses). So I just kept things easy.
======================
About the patchset:
Patch 1-5: Mostly cleanups Patch 6,7: Prepare for the dirty ring interface Patch 8-10: Dirty ring implementation (majorly patch 8) Patch 11-17: Test cases update
Please have a look, thanks.
[1] V1 is here: https://lore.kernel.org/kvm/[email protected]
Paolo Bonzini (1):
KVM: Move running VCPU from ARM to common code
Peter Xu (16):
KVM: Remove kvm_read_guest_atomic()
KVM: X86: Change parameter for fast_page_fault tracepoint
KVM: X86: Don't track dirty for KVM_SET_[TSS_ADDR|IDENTITY_MAP_ADDR]
KVM: Cache as_id in kvm_memory_slot
KVM: Add build-time error check on kvm_run size
KVM: Pass in kvm pointer into mark_page_dirty_in_slot()
KVM: X86: Implement ring-based dirty memory tracking
KVM: Make dirty ring exclusive to dirty bitmap log
KVM: Don't allocate dirty bitmap if dirty ring is enabled
KVM: selftests: Always clear dirty bitmap after iteration
KVM: selftests: Sync uapi/linux/kvm.h to tools/
KVM: selftests: Use a single binary for dirty/clear log test
KVM: selftests: Introduce after_vcpu_run hook for dirty log test
KVM: selftests: Add dirty ring buffer test
KVM: selftests: Let dirty_log_test async for dirty ring test
KVM: selftests: Add "-c" parameter to dirty log test
Documentation/virt/kvm/api.txt | 96 ++++ arch/arm/include/asm/kvm_host.h | 2 - arch/arm64/include/asm/kvm_host.h | 2 - arch/x86/include/asm/kvm_host.h | 3 + arch/x86/include/uapi/asm/kvm.h | 1 + arch/x86/kvm/Makefile | 3 +- arch/x86/kvm/mmu.c | 6 + arch/x86/kvm/mmutrace.h | 9 +- arch/x86/kvm/vmx/vmx.c | 25 +- arch/x86/kvm/x86.c | 9 + include/linux/kvm_dirty_ring.h | 57 +++ include/linux/kvm_host.h | 44 +- include/trace/events/kvm.h | 78 ++++ include/uapi/linux/kvm.h | 31 ++ tools/include/uapi/linux/kvm.h | 36 ++ tools/testing/selftests/kvm/Makefile | 2 - .../selftests/kvm/clear_dirty_log_test.c | 2 - tools/testing/selftests/kvm/dirty_log_test.c | 420 ++++++++++++++++-- .../testing/selftests/kvm/include/kvm_util.h | 4 + tools/testing/selftests/kvm/lib/kvm_util.c | 64 +++ .../selftests/kvm/lib/kvm_util_internal.h | 3 + virt/kvm/arm/arch_timer.c | 2 +- virt/kvm/arm/arm.c | 29 -- virt/kvm/arm/perf.c | 6 +- virt/kvm/arm/vgic/vgic-mmio.c | 15 +- virt/kvm/dirty_ring.c | 201 +++++++++ virt/kvm/kvm_main.c | 269 +++++++++-- 27 files changed, 1274 insertions(+), 145 deletions(-) create mode 100644 include/linux/kvm_dirty_ring.h delete mode 100644 tools/testing/selftests/kvm/clear_dirty_log_test.c create mode 100644 virt/kvm/dirty_ring.c
Signature · 1 line
2.24.1
PATCH v2 1/17 KVM: Remove kvm_read_guest_atomic()
Remove kvm_read_guest_atomic() because it's not used anywhere.
--- include/linux/kvm_host.h | 2 -- virt/kvm/kvm_main.c | 11 ----------- 2 files changed, 13 deletions(-)
include/linux/kvm_host.h +0 -2
@@ -730,8 +730,6 @@ void kvm_get_pfn(kvm_pfn_t pfn);int kvm_read_guest_page (struct kvm *kvm,gfn_t gfn,void *data,int offset,int len); -int kvm_read_guest_atomic (struct kvm *kvm,gpa_t gpa,void *data, -unsigned long len);int kvm_read_guest (struct kvm *kvm,gpa_t gpa,void *data,unsigned long len);int kvm_read_guest_cached (struct kvm *kvm,struct gfn_to_hva_cache *ghc,void *data,unsigned long len);
virt/kvm/kvm_main.c +0 -11
@@ -2039,17 +2039,6 @@ static int __kvm_read_guest_atomic(struct kvm_memory_slot *slot, gfn_t gfn,return 0 ; } -int kvm_read_guest_atomic (struct kvm *kvm,gpa_t gpa,void *data, -unsigned long len) -{ -gfn_t gfn = gpa >>PAGE_SHIFT ; -struct kvm_memory_slot *slot =gfn_to_memslot (kvm, gfn); -int offset =offset_in_page (gpa); - -return __kvm_read_guest_atomic (slot, gfn, data, offset, len); -} -EXPORT_SYMBOL_GPL (kvm_read_guest_atomic); -int kvm_vcpu_read_guest_atomic (struct kvm_vcpu *vcpu,gpa_t gpa,void *data,unsigned long len) {
Signature · 1 line
2.24.1
PATCH v2 2/17 KVM: X86: Change parameter for fast_page_fault tracepoint
In reply to Peter XuIt would be clearer to dump the return value to know easily on whether did we go through the fast path for handling current page fault. Remove the old two last parameters because after all the old/new sptes were dumped in the same line.
--- arch/x86/kvm/mmutrace.h | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-)
arch/x86/kvm/mmutrace.h +2 -7
@@ -244,9 +244,6 @@ TRACE_EVENT( __entry->access) ); -#define __spte_satisfied (__spte) \ - (__entry->retry && is_writable_pte(__entry->__spte)) - TRACE_EVENT( fast_page_fault, TP_PROTO(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code,
@@ -274,12 +271,10 @@ TRACE_EVENT( ),TP_printk ("vcpu %d gva %lx error_code %s sptep %p old %#llx" -" new %llx spurious %d fixed %d" , __entry->vcpu_id, +" new %llx ret %d" , __entry->vcpu_id, __entry->gva,__print_flags (__entry->error_code,"|" , kvm_mmu_trace_pferr_flags), __entry->sptep, - __entry->old_spte, __entry->new_spte, -__spte_satisfied (old_spte),__spte_satisfied (new_spte) - ) + __entry->old_spte, __entry->new_spte, __entry->retry) ); TRACE_EVENT(
Signature · 1 line
2.24.1
PATCH v2 3/17 KVM: X86: Don't track dirty for KVM_SET_[TSS_ADDR|IDENTITY_MAP_ADDR]
In reply to Peter XuOriginally, we have three code paths that can dirty a page without vcpu context for X86:
- init_rmode_identity_map
- init_rmode_tss
- kvmgt_rw_gpa
init_rmode_identity_map and init_rmode_tss will be setup on destination VM no matter what (and the guest cannot even see them), so it does not make sense to track them at all.
To do this, a new parameter is added to kvm_[write|clear]_guest_page() to show whether we would like to track dirty bits for the operations. With that, pass in "false" to this new parameter for any guest memory write of the ioctls (KVM_SET_TSS_ADDR, KVM_SET_IDENTITY_MAP_ADDR).
--- arch/x86/kvm/vmx/vmx.c | 18 ++++++++++-------- include/linux/kvm_host.h | 5 +++-- virt/kvm/kvm_main.c | 25 ++++++++++++++++--------- 3 files changed, 29 insertions(+), 19 deletions(-)
arch/x86/kvm/vmx/vmx.c +10 -8
@@ -3452,24 +3452,24 @@ static int init_rmode_tss(struct kvm *kvm) idx =srcu_read_lock (&kvm->srcu); fn =to_kvm_vmx (kvm)->tss_addr >>PAGE_SHIFT ; - r =kvm_clear_guest_page (kvm, fn,0 ,PAGE_SIZE ); + r =kvm_clear_guest_page (kvm, fn,0 ,PAGE_SIZE , false);if (r <0 ) goto out; data =TSS_BASE_SIZE +TSS_REDIRECTION_SIZE ; r =kvm_write_guest_page (kvm, fn++, &data, -TSS_IOPB_BASE_OFFSET ,sizeof (u16)); +TSS_IOPB_BASE_OFFSET ,sizeof (u16), false);if (r <0 ) goto out; - r =kvm_clear_guest_page (kvm, fn++,0 ,PAGE_SIZE ); + r =kvm_clear_guest_page (kvm, fn++,0 ,PAGE_SIZE , false);if (r <0 ) goto out; - r =kvm_clear_guest_page (kvm, fn,0 ,PAGE_SIZE ); + r =kvm_clear_guest_page (kvm, fn,0 ,PAGE_SIZE , false);if (r <0 ) goto out; data = ~0 ; r =kvm_write_guest_page (kvm, fn, &data,RMODE_TSS_SIZE -2 *PAGE_SIZE -1 , -sizeof (u8)); +sizeof (u8), false); out:srcu_read_unlock (&kvm->srcu, idx);return r;
@@ -3498,7 +3498,7 @@ static int init_rmode_identity_map(struct kvm *kvm) goto out2; idx =srcu_read_lock (&kvm->srcu); - r =kvm_clear_guest_page (kvm, identity_map_pfn,0 ,PAGE_SIZE ); + r =kvm_clear_guest_page (kvm, identity_map_pfn,0 ,PAGE_SIZE , false);if (r <0 ) goto out;/* Set up identity-mapping pagetable for EPT in real mode */
@@ -3506,7 +3506,8 @@ static int init_rmode_identity_map(struct kvm *kvm) tmp = (i <<22 ) + (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_PSE); r =kvm_write_guest_page (kvm, identity_map_pfn, - &tmp, i *sizeof (tmp),sizeof (tmp)); + &tmp, i *sizeof (tmp), +sizeof (tmp), false);if (r <0 ) goto out; }
@@ -7265,7 +7266,8 @@ static int vmx_write_pml_buffer(struct kvm_vcpu *vcpu) dst = vmcs12->pml_address +sizeof (u64) * vmcs12->guest_pml_index;if (kvm_write_guest_page (vcpu->kvm,gpa_to_gfn (dst), &gpa, -offset_in_page (dst),sizeof (gpa))) +offset_in_page (dst),sizeof (gpa), + false))return 0 ; vmcs12->guest_pml_index--;
include/linux/kvm_host.h +3 -2
@@ -734,7 +734,7 @@ int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len);int kvm_read_guest_cached (struct kvm *kvm,struct gfn_to_hva_cache *ghc,void *data,unsigned long len);int kvm_write_guest_page (struct kvm *kvm,gfn_t gfn,const void *data, -int offset,int len); +int offset,int len,bool track_dirty);int kvm_write_guest (struct kvm *kvm,gpa_t gpa,const void *data,unsigned long len); int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
@@ -744,7 +744,8 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, unsigned long len);int kvm_gfn_to_hva_cache_init (struct kvm *kvm,struct gfn_to_hva_cache *ghc,gpa_t gpa,unsigned long len); -int kvm_clear_guest_page (struct kvm *kvm,gfn_t gfn,int offset,int len); +int kvm_clear_guest_page (struct kvm *kvm,gfn_t gfn,int offset,int len, +bool track_dirty);int kvm_clear_guest (struct kvm *kvm,gpa_t gpa,unsigned long len);struct kvm_memory_slot *gfn_to_memslot (struct kvm *kvm,gfn_t gfn);bool kvm_is_visible_gfn (struct kvm *kvm,gfn_t gfn);
virt/kvm/kvm_main.c +16 -9
@@ -2051,7 +2051,8 @@ int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa,EXPORT_SYMBOL_GPL (kvm_vcpu_read_guest_atomic);static int __kvm_write_guest_page (struct kvm_memory_slot *memslot,gfn_t gfn, -const void *data,int offset,int len) +const void *data,int offset,int len, +bool track_dirty) {int r;unsigned long addr;
@@ -2062,16 +2063,19 @@ static int __kvm_write_guest_page(struct kvm_memory_slot *memslot, gfn_t gfn, r =__copy_to_user ((void __user *)addr + offset, data, len);if (r)return -EFAULT ; -mark_page_dirty_in_slot (memslot, gfn); +if (track_dirty) +mark_page_dirty_in_slot (memslot, gfn);return 0 ; }int kvm_write_guest_page (struct kvm *kvm,gfn_t gfn, -const void *data,int offset,int len) +const void *data,int offset,int len, +bool track_dirty) {struct kvm_memory_slot *slot =gfn_to_memslot (kvm, gfn); -return __kvm_write_guest_page (slot, gfn, data, offset, len); +return __kvm_write_guest_page (slot, gfn, data, offset, len, + track_dirty); }EXPORT_SYMBOL_GPL (kvm_write_guest_page);
@@ -2080,7 +2084,8 @@ int kvm_vcpu_write_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, {struct kvm_memory_slot *slot =kvm_vcpu_gfn_to_memslot (vcpu, gfn); -return __kvm_write_guest_page (slot, gfn, data, offset, len); +return __kvm_write_guest_page (slot, gfn, data, offset, + len, true); }EXPORT_SYMBOL_GPL (kvm_vcpu_write_guest_page);
@@ -2093,7 +2098,7 @@ int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data,int ret;while ((seg =next_segment (len, offset)) !=0 ) { - ret =kvm_write_guest_page (kvm, gfn, data, offset, seg); + ret =kvm_write_guest_page (kvm, gfn, data, offset, seg, true);if (ret <0 )return ret; offset =0 ;
@@ -2232,11 +2237,13 @@ int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, }EXPORT_SYMBOL_GPL (kvm_read_guest_cached); -int kvm_clear_guest_page (struct kvm *kvm,gfn_t gfn,int offset,int len) +int kvm_clear_guest_page (struct kvm *kvm,gfn_t gfn,int offset,int len, +bool track_dirty) {const void *zero_page = (const void *)__va (page_to_phys (ZERO_PAGE (0 ))); -return kvm_write_guest_page (kvm, gfn, zero_page, offset, len); +return kvm_write_guest_page (kvm, gfn, zero_page, offset, len, + track_dirty); }EXPORT_SYMBOL_GPL (kvm_clear_guest_page);
@@ -2248,7 +2255,7 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len)int ret;while ((seg =next_segment (len, offset)) !=0 ) { - ret =kvm_clear_guest_page (kvm, gfn, offset, seg); + ret =kvm_clear_guest_page (kvm, gfn, offset, seg, true);if (ret <0 )return ret; offset =0 ;
Signature · 1 line
2.24.1
PATCH v2 4/17 KVM: Cache as_id in kvm_memory_slot
In reply to Peter XuLet's cache the address space ID just like the slot ID.
--- include/linux/kvm_host.h | 1 + virt/kvm/kvm_main.c | 2 ++ 2 files changed, 3 insertions(+)
include/linux/kvm_host.h +1 -0
@@ -348,6 +348,7 @@ struct kvm_memory_slot {unsigned long userspace_addr;u32 flags;short id; +u8 as_id; };static inline unsigned long kvm_dirty_bitmap_bytes (struct kvm_memory_slot *memslot)
virt/kvm/kvm_main.c +2 -0
@@ -1027,6 +1027,8 @@ int __kvm_set_memory_region(struct kvm *kvm, new = old = *slot; +BUILD_BUG_ON (U8_MAX <KVM_ADDRESS_SPACE_NUM ); + new.as_id = as_id; new.id = id; new.base_gfn = base_gfn; new.npages = npages;
Signature · 1 line
2.24.1
PATCH v2 5/17 KVM: Add build-time error check on kvm_run size
In reply to Peter XuIt's already going to reach 2400 Bytes (which is over half of page size on 4K page archs), so maybe it's good to have this build-time check in case it overflows when adding new fields.
--- virt/kvm/kvm_main.c | 1 + 1 file changed, 1 insertion(+)
virt/kvm/kvm_main.c +1 -0
@@ -338,6 +338,7 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) vcpu->pre_pcpu =-1 ;INIT_LIST_HEAD (&vcpu->blocked_vcpu_list); +BUILD_BUG_ON (sizeof (struct kvm_run ) >PAGE_SIZE ); page =alloc_page (GFP_KERNEL | __GFP_ZERO);if (!page) { r = -ENOMEM ;
Signature · 1 line
2.24.1
PATCH v2 6/17 KVM: Pass in kvm pointer into mark_page_dirty_in_slot()
In reply to Peter XuThe context will be needed to implement the kvm dirty ring.
--- virt/kvm/kvm_main.c | 24 ++++++++++++++---------- 1 file changed, 14 insertions(+), 10 deletions(-)
virt/kvm/kvm_main.c +14 -10
@@ -144,7 +144,9 @@ static void hardware_disable_all(void);static void kvm_io_bus_destroy (struct kvm_io_bus *bus); -static void mark_page_dirty_in_slot (struct kvm_memory_slot *memslot,gfn_t gfn); +static void mark_page_dirty_in_slot (struct kvm *kvm, +struct kvm_memory_slot *memslot, +gfn_t gfn); __visible bool kvm_rebooting;EXPORT_SYMBOL_GPL (kvm_rebooting);
@@ -2053,8 +2055,9 @@ int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa, }EXPORT_SYMBOL_GPL (kvm_vcpu_read_guest_atomic); -static int __kvm_write_guest_page (struct kvm_memory_slot *memslot,gfn_t gfn, -const void *data,int offset,int len, +static int __kvm_write_guest_page (struct kvm *kvm, +struct kvm_memory_slot *memslot,gfn_t gfn, +const void *data,int offset,int len,bool track_dirty) {int r;
@@ -2067,7 +2070,7 @@ static int __kvm_write_guest_page(struct kvm_memory_slot *memslot, gfn_t gfn,if (r)return -EFAULT ;if (track_dirty) -mark_page_dirty_in_slot (memslot, gfn); +mark_page_dirty_in_slot (kvm, memslot, gfn);return 0 ; }
@@ -2077,7 +2080,7 @@ int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, {struct kvm_memory_slot *slot =gfn_to_memslot (kvm, gfn); -return __kvm_write_guest_page (slot, gfn, data, offset, len, +return __kvm_write_guest_page (kvm, slot, gfn, data, offset, len, track_dirty); }EXPORT_SYMBOL_GPL (kvm_write_guest_page);
@@ -2087,7 +2090,7 @@ int kvm_vcpu_write_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, {struct kvm_memory_slot *slot =kvm_vcpu_gfn_to_memslot (vcpu, gfn); -return __kvm_write_guest_page (slot, gfn, data, offset, +return __kvm_write_guest_page (vcpu->kvm, slot, gfn, data, offset, len, true); }EXPORT_SYMBOL_GPL (kvm_vcpu_write_guest_page);
@@ -2202,7 +2205,7 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, r =__copy_to_user ((void __user *)ghc->hva + offset, data, len);if (r)return -EFAULT ; -mark_page_dirty_in_slot (ghc->memslot, gpa >>PAGE_SHIFT ); +mark_page_dirty_in_slot (kvm, ghc->memslot, gpa >>PAGE_SHIFT );return 0 ; }
@@ -2269,7 +2272,8 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len) }EXPORT_SYMBOL_GPL (kvm_clear_guest); -static void mark_page_dirty_in_slot (struct kvm_memory_slot *memslot, +static void mark_page_dirty_in_slot (struct kvm *kvm, +struct kvm_memory_slot *memslot,gfn_t gfn) {if (memslot && memslot->dirty_bitmap) {
@@ -2284,7 +2288,7 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn)struct kvm_memory_slot *memslot; memslot =gfn_to_memslot (kvm, gfn); -mark_page_dirty_in_slot (memslot, gfn); +mark_page_dirty_in_slot (kvm, memslot, gfn); }EXPORT_SYMBOL_GPL (mark_page_dirty);
@@ -2293,7 +2297,7 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn)struct kvm_memory_slot *memslot; memslot =kvm_vcpu_gfn_to_memslot (vcpu, gfn); -mark_page_dirty_in_slot (memslot, gfn); +mark_page_dirty_in_slot (vcpu->kvm, memslot, gfn); }EXPORT_SYMBOL_GPL (kvm_vcpu_mark_page_dirty);
Signature · 1 line
2.24.1
PATCH v2 7/17 KVM: Move running VCPU from ARM to common code
In reply to Peter XuFrom: Paolo Bonzini <[email protected]>
For ring-based dirty log tracking, it will be more efficient to account writes during schedule-out or schedule-in to the currently running VCPU. We would like to do it even if the write doesn't use the current VCPU's address space, as is the case for cached writes (see commit 4e335d9e7ddb, "Revert "KVM: Support vCPU-based gfn->hva cache"", 2017-05-02).
Therefore, add a mechanism to track the currently-loaded kvm_vcpu struct. There is already something similar in KVM/ARM; one important difference is that kvm_arch_vcpu_{load,put} have two callers in virt/kvm/kvm_main.c:
we have to update both the architecture-independent vcpu_{load,put} and the preempt notifiers.
Another change made in the process is to allow using kvm_get_running_vcpu() in preemptible code. This is allowed because preempt notifiers ensure that the value does not change even after the VCPU thread is migrated.
--- arch/arm/include/asm/kvm_host.h | 2 -- arch/arm64/include/asm/kvm_host.h | 2 -- include/linux/kvm_host.h | 3 +++ virt/kvm/arm/arch_timer.c | 2 +- virt/kvm/arm/arm.c | 29 ----------------------------- virt/kvm/arm/perf.c | 6 +++--- virt/kvm/arm/vgic/vgic-mmio.c | 15 +++------------ virt/kvm/kvm_main.c | 25 ++++++++++++++++++++++++- 8 files changed, 34 insertions(+), 50 deletions(-)
arch/arm/include/asm/kvm_host.h +0 -2
@@ -274,8 +274,6 @@ int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);int kvm_age_hva (struct kvm *kvm,unsigned long start,unsigned long end);int kvm_test_age_hva (struct kvm *kvm,unsigned long hva); -struct kvm_vcpu *kvm_arm_get_running_vcpu (void ); -struct kvm_vcpu __percpu **kvm_get_running_vcpus (void );void kvm_arm_halt_guest (struct kvm *kvm);void kvm_arm_resume_guest (struct kvm *kvm);
arch/arm64/include/asm/kvm_host.h +0 -2
@@ -430,8 +430,6 @@ int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);int kvm_age_hva (struct kvm *kvm,unsigned long start,unsigned long end);int kvm_test_age_hva (struct kvm *kvm,unsigned long hva); -struct kvm_vcpu *kvm_arm_get_running_vcpu (void ); -struct kvm_vcpu *__percpu *kvm_get_running_vcpus (void );void kvm_arm_halt_guest (struct kvm *kvm);void kvm_arm_resume_guest (struct kvm *kvm);
include/linux/kvm_host.h +3 -0
@@ -1323,6 +1323,9 @@ static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val) }#endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */ +struct kvm_vcpu *kvm_get_running_vcpu (void ); +struct kvm_vcpu __percpu **kvm_get_running_vcpus (void ); +#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS bool kvm_arch_has_irq_bypass (void ); int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *,
virt/kvm/arm/arch_timer.c +1 -1
@@ -1022,7 +1022,7 @@ static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu)bool kvm_arch_timer_get_input_level (int vintid) { -struct kvm_vcpu *vcpu =kvm_arm_get_running_vcpu (); +struct kvm_vcpu *vcpu =kvm_get_running_vcpu ();struct arch_timer_context *timer;if (vintid ==vcpu_vtimer (vcpu)->irq.irq)
virt/kvm/arm/arm.c +0 -29
@@ -47,9 +47,6 @@ __asm__(".arch_extension virt");DEFINE_PER_CPU (kvm_host_data_t, kvm_host_data); static DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page); -/* Per-CPU variable containing the currently running vcpu. */ -static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_arm_running_vcpu); -/* The VMID used in the VTTBR */ static atomic64_t kvm_vmid_gen =ATOMIC64_INIT (1 );static u32 kvm_next_vmid;
@@ -58,31 +55,8 @@ static DEFINE_SPINLOCK(kvm_vmid_lock);static bool vgic_present; static DEFINE_PER_CPU(unsigned char, kvm_arm_hardware_enabled); - -static void kvm_arm_set_running_vcpu (struct kvm_vcpu *vcpu) -{ -__this_cpu_write (kvm_arm_running_vcpu, vcpu); -} -DEFINE_STATIC_KEY_FALSE (userspace_irqchip_in_use); -/** -* kvm_arm_get_running_vcpu - get the vcpu running on the current CPU. -* Must be called from non-preemptible context -*/ -struct kvm_vcpu *kvm_arm_get_running_vcpu (void ) -{ -return __this_cpu_read (kvm_arm_running_vcpu); -} - -/** -* kvm_arm_get_running_vcpus - get the per-CPU array of currently running vcpus. -*/ -struct kvm_vcpu *__percpu *kvm_get_running_vcpus (void ) -{ -return &kvm_arm_running_vcpu; -} -int kvm_arch_vcpu_should_kick (struct kvm_vcpu *vcpu) {return kvm_vcpu_exiting_guest_mode (vcpu) ==IN_GUEST_MODE ;
@@ -374,7 +348,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) vcpu->cpu = cpu; vcpu->arch.host_cpu_context = &cpu_data->host_ctxt; -kvm_arm_set_running_vcpu (vcpu);kvm_vgic_load (vcpu);kvm_timer_vcpu_load (vcpu);kvm_vcpu_load_sysregs (vcpu);
@@ -398,8 +371,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)kvm_vcpu_pmu_restore_host (vcpu); vcpu->cpu =-1 ; - -kvm_arm_set_running_vcpu (NULL ); }static void vcpu_power_off (struct kvm_vcpu *vcpu)
virt/kvm/arm/perf.c +3 -3
@@ -13,14 +13,14 @@static int kvm_is_in_guest (void ) { -return kvm_arm_get_running_vcpu () !=NULL ; +return kvm_get_running_vcpu () !=NULL ; }static int kvm_is_user_mode (void ) {struct kvm_vcpu *vcpu; - vcpu =kvm_arm_get_running_vcpu (); + vcpu =kvm_get_running_vcpu ();if (vcpu)return !vcpu_mode_priv (vcpu);
@@ -32,7 +32,7 @@ static unsigned long kvm_get_guest_ip(void) {struct kvm_vcpu *vcpu; - vcpu =kvm_arm_get_running_vcpu (); + vcpu =kvm_get_running_vcpu ();if (vcpu)return *vcpu_pc (vcpu);
virt/kvm/arm/vgic/vgic-mmio.c +3 -12
@@ -190,15 +190,6 @@ unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,* value later will give us the same value as we update the per-CPU variable * in the preempt notifier handlers. */ -static struct kvm_vcpu *vgic_get_mmio_requester_vcpu (void ) -{ -struct kvm_vcpu *vcpu; - -preempt_disable (); - vcpu =kvm_arm_get_running_vcpu (); -preempt_enable (); -return vcpu; -}/* Must be called with irq->irq_lock held */ static void vgic_hw_irq_spending(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
@@ -221,7 +212,7 @@ void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { - bool is_uaccess = !vgic_get_mmio_requester_vcpu(); + bool is_uaccess = !kvm_get_running_vcpu();u32 intid =VGIC_ADDR_TO_INTID (addr,1 );int i;unsigned long flags;
@@ -274,7 +265,7 @@ void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { - bool is_uaccess = !vgic_get_mmio_requester_vcpu(); + bool is_uaccess = !kvm_get_running_vcpu();u32 intid =VGIC_ADDR_TO_INTID (addr,1 );int i;unsigned long flags;
@@ -335,7 +326,7 @@ static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, bool active) {unsigned long flags; -struct kvm_vcpu *requester_vcpu =vgic_get_mmio_requester_vcpu (); +struct kvm_vcpu *requester_vcpu =kvm_get_running_vcpu ();raw_spin_lock_irqsave (&irq->irq_lock, flags);
virt/kvm/kvm_main.c +24 -1
@@ -108,6 +108,7 @@ struct kmem_cache *kvm_vcpu_cache;EXPORT_SYMBOL_GPL (kvm_vcpu_cache);static __read_mostly struct preempt_ops kvm_preempt_ops; +static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_running_vcpu);struct dentry *kvm_debugfs_dir;EXPORT_SYMBOL_GPL (kvm_debugfs_dir);
@@ -199,6 +200,8 @@ bool kvm_is_reserved_pfn(kvm_pfn_t pfn)void vcpu_load (struct kvm_vcpu *vcpu) {int cpu =get_cpu (); + +__this_cpu_write (kvm_running_vcpu, vcpu);preempt_notifier_register (&vcpu->preempt_notifier);kvm_arch_vcpu_load (vcpu, cpu);put_cpu ();
@@ -210,6 +213,7 @@ void vcpu_put(struct kvm_vcpu *vcpu)preempt_disable ();kvm_arch_vcpu_put (vcpu);preempt_notifier_unregister (&vcpu->preempt_notifier); +__this_cpu_write (kvm_running_vcpu,NULL );preempt_enable (); }EXPORT_SYMBOL_GPL (vcpu_put);
@@ -4294,8 +4298,8 @@ static void kvm_sched_in(struct preempt_notifier *pn, int cpu)WRITE_ONCE (vcpu->preempted, false);WRITE_ONCE (vcpu->ready, false); +__this_cpu_write (kvm_running_vcpu, vcpu);kvm_arch_sched_in (vcpu, cpu); -kvm_arch_vcpu_load (vcpu, cpu); }
@@ -4309,6 +4313,25 @@ static void kvm_sched_out(struct preempt_notifier *pn,WRITE_ONCE (vcpu->ready, true); }kvm_arch_vcpu_put (vcpu); +__this_cpu_write (kvm_running_vcpu,NULL ); +} + +/** +* kvm_get_running_vcpu - get the vcpu running on the current CPU. +* Thanks to preempt notifiers, this can also be called from +* preemptible context. +*/ +struct kvm_vcpu *kvm_get_running_vcpu (void ) +{ +return __this_cpu_read (kvm_running_vcpu); +} + +/** +* kvm_get_running_vcpus - get the per-CPU array of currently running vcpus. +*/ +struct kvm_vcpu *__percpu *kvm_get_running_vcpus (void ) +{ +return &kvm_running_vcpu; }static void check_processor_compat (void *rtn)
Signature · 1 line
2.24.1
PATCH v2 8/17 KVM: X86: Implement ring-based dirty memory tracking
In reply to Peter XuThis patch is heavily based on previous work from Lei Cao <[email protected]> and Paolo Bonzini <[email protected]>. [1]
KVM currently uses large bitmaps to track dirty memory. These bitmaps are copied to userspace when userspace queries KVM for its dirty page information. The use of bitmaps is mostly sufficient for live migration, as large parts of memory are be dirtied from one log-dirty pass to another. However, in a checkpointing system, the number of dirty pages is small and in fact it is often bounded---the VM is paused when it has dirtied a pre-defined number of pages. Traversing a large, sparsely populated bitmap to find set bits is time-consuming, as is copying the bitmap to user-space.
A similar issue will be there for live migration when the guest memory is huge while the page dirty procedure is trivial. In that case for each dirty sync we need to pull the whole dirty bitmap to userspace and analyse every bit even if it's mostly zeros.
The preferred data structure for above scenarios is a dense list of guest frame numbers (GFN). This patch series stores the dirty list in kernel memory that can be memory mapped into userspace to allow speedy harvesting.
This patch enables dirty ring for X86 only. However it should be easily extended to other archs as well.
[1] https://patchwork.kernel.org/patch/10471409/
--- Documentation/virt/kvm/api.txt | 89 ++++++++++++++ arch/x86/include/asm/kvm_host.h | 3 + arch/x86/include/uapi/asm/kvm.h | 1 + arch/x86/kvm/Makefile | 3 +- arch/x86/kvm/mmu.c | 6 + arch/x86/kvm/vmx/vmx.c | 7 ++ arch/x86/kvm/x86.c | 9 ++ include/linux/kvm_dirty_ring.h | 57 +++++++++ include/linux/kvm_host.h | 28 +++++ include/trace/events/kvm.h | 78 +++++++++++++ include/uapi/linux/kvm.h | 31 +++++ virt/kvm/dirty_ring.c | 201 ++++++++++++++++++++++++++++++++ virt/kvm/kvm_main.c | 172 ++++++++++++++++++++++++++- 13 files changed, 682 insertions(+), 3 deletions(-) create mode 100644 include/linux/kvm_dirty_ring.h create mode 100644 virt/kvm/dirty_ring.c
Documentation/virt/kvm/api.txt +89 -0
@@ -231,6 +231,7 @@ Based on their initialization different VMs may have different capabilities. It is thus encouraged to use the vm ioctl to query for capabilities (available with KVM_CAP_CHECK_EXTENSION_VM on the vm fd) + 4.5 KVM_GET_VCPU_MMAP_SIZE Capability: basic
@@ -243,6 +244,18 @@ The KVM_RUN ioctl (cf.) communicates with userspace via a shared memory region. This ioctl returns the size of that region. See the KVM_RUN documentation for details. +Besides the size of the KVM_RUN communication region, other areas of +the VCPU file descriptor can be mmap-ed, including: + +- if KVM_CAP_COALESCED_MMIO is available, a page at + KVM_COALESCED_MMIO_PAGE_OFFSET * PAGE_SIZE; for historical reasons, + this page is included in the result of KVM_GET_VCPU_MMAP_SIZE. + KVM_CAP_COALESCED_MMIO is not documented yet. + +- if KVM_CAP_DIRTY_LOG_RING is available, a number of pages at + KVM_DIRTY_LOG_PAGE_OFFSET * PAGE_SIZE. For more information on + KVM_CAP_DIRTY_LOG_RING, see section 8.3. + 4.6 KVM_SET_MEMORY_REGION
@@ -5302,6 +5315,7 @@ CPU when the exception is taken. If this virtual SError is taken to EL1 using AArch64, this value will be reported in the ISS field of ESR_ELx. See KVM_CAP_VCPU_EVENTS for more details. + 8.20 KVM_CAP_HYPERV_SEND_IPI Architectures: x86
@@ -5309,6 +5323,7 @@ Architectures: x86 This capability indicates that KVM supports paravirtualized Hyper-V IPI send hypercalls: HvCallSendSyntheticClusterIpi, HvCallSendSyntheticClusterIpiEx. + 8.21 KVM_CAP_HYPERV_DIRECT_TLBFLUSH Architecture: x86
@@ -5322,3 +5337,77 @@ handling by KVM (as some KVM hypercall may be mistakenly treated as TLB flush hypercalls by Hyper-V) so userspace should disable KVM identification in CPUID and only exposes Hyper-V identification. In this case, guest thinks it's running on Hyper-V and only use Hyper-V hypercalls. + +8.22 KVM_CAP_DIRTY_LOG_RING + +Architectures: x86 +Parameters: args[0] - size of the dirty log ring + +KVM is capable of tracking dirty memory using ring buffers that are +mmaped into userspace; there is one dirty ring per vcpu. + +One dirty ring is defined as below internally: + +struct kvm_dirty_ring { + u32 dirty_index; + u32 reset_index; + u32 size; + u32 soft_limit; + struct kvm_dirty_gfn *dirty_gfns; + struct kvm_dirty_ring_indices *indices; + int index; +}; + +Dirty GFNs (Guest Frame Numbers) are stored in the dirty_gfns array. +For each of the dirty entry it's defined as: + +struct kvm_dirty_gfn { + __u32 pad; + __u32 slot; /* as_id | slot_id */ + __u64 offset; +}; + +Most of the ring structure is used by KVM internally, while only the +indices are exposed to userspace: + +struct kvm_dirty_ring_indices { + __u32 avail_index; /* set by kernel */ + __u32 fetch_index; /* set by userspace */ +}; + +The two indices in the ring buffer are free running counters. + +Userspace calls KVM_ENABLE_CAP ioctl right after KVM_CREATE_VM ioctl +to enable this capability for the new guest and set the size of the +rings. It is only allowed before creating any vCPU, and the size of +the ring must be a power of two. The larger the ring buffer, the less +likely the ring is full and the VM is forced to exit to userspace. The +optimal size depends on the workload, but it is recommended that it be +at least 64 KiB (4096 entries). + +Just like for dirty page bitmaps, the buffer tracks writes to +all user memory regions for which the KVM_MEM_LOG_DIRTY_PAGES flag was +set in KVM_SET_USER_MEMORY_REGION. Once a memory region is registered +with the flag set, userspace can start harvesting dirty pages from the +ring buffer. + +To harvest the dirty pages, userspace accesses the mmaped ring buffer +to read the dirty GFNs up to avail_index, and sets the fetch_index +accordingly. This can be done when the guest is running or paused, +and dirty pages need not be collected all at once. After processing +one or more entries in the ring buffer, userspace calls the VM ioctl +KVM_RESET_DIRTY_RINGS to notify the kernel that it has updated +fetch_index and to mark those pages clean. Therefore, the ioctl +must be called *before* reading the content of the dirty pages. + +However, there is a major difference comparing to the +KVM_GET_DIRTY_LOG interface in that when reading the dirty ring from +userspace it's still possible that the kernel has not yet flushed the +hardware dirty buffers into the kernel buffer (which was previously +done by the KVM_GET_DIRTY_LOG ioctl). To achieve that, one needs to +kick the vcpu out for a hardware buffer flush (vmexit) to make sure +all the existing dirty gfns are flushed to the dirty rings. + +If one of the ring buffers is full, the guest will exit to userspace +with the exit reason set to KVM_EXIT_DIRTY_LOG_FULL, and the KVM_RUN +ioctl will return to userspace with zero.
arch/x86/include/asm/kvm_host.h +3 -0
@@ -1159,6 +1159,7 @@ struct kvm_x86_ops {struct kvm_memory_slot *slot, gfn_t offset, unsigned long mask);int (*write_log_dirty)(struct kvm_vcpu *vcpu); +int (*cpu_dirty_log_size)(void );/* pmu operations of sub-arch */ const struct kvm_pmu_ops *pmu_ops;
@@ -1641,4 +1642,6 @@ static inline int kvm_cpu_get_apicid(int mps_cpu)#define GET_SMSTATE (type, buf, offset) \ (*(type *)((buf) + (offset) - 0x7e00)) +int kvm_cpu_dirty_log_size (void ); +#endif /* _ASM_X86_KVM_HOST_H */
arch/x86/include/uapi/asm/kvm.h +1 -0
@@ -12,6 +12,7 @@#define KVM_PIO_PAGE_OFFSET 1#define KVM_COALESCED_MMIO_PAGE_OFFSET 2 +#define KVM_DIRTY_LOG_PAGE_OFFSET 64#define DE_VECTOR 0#define DB_VECTOR 1
arch/x86/kvm/Makefile +2 -1
@@ -5,7 +5,8 @@ ccflags-y += -Iarch/x86/kvm KVM := ../../../virt/kvm kvm-y += $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \ - $(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o + $(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o \ + $(KVM)/dirty_ring.o kvm-$(CONFIG_KVM_ASYNC_PF) += $(KVM)/async_pf.o kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
arch/x86/kvm/mmu.c +6 -0
@@ -1818,7 +1818,13 @@ int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu) {if (kvm_x86_ops->write_log_dirty)return kvm_x86_ops->write_log_dirty (vcpu); +return 0 ; +} +int kvm_cpu_dirty_log_size (void ) +{ +if (kvm_x86_ops->cpu_dirty_log_size) +return kvm_x86_ops->cpu_dirty_log_size ();return 0 ; }
arch/x86/kvm/vmx/vmx.c +7 -0
@@ -7686,6 +7686,7 @@ static __init int hardware_setup(void) kvm_x86_ops->slot_disable_log_dirty =NULL ; kvm_x86_ops->flush_log_dirty =NULL ; kvm_x86_ops->enable_log_dirty_pt_masked =NULL ; + kvm_x86_ops->cpu_dirty_log_size =NULL ; }if (!cpu_has_vmx_preemption_timer ())
@@ -7750,6 +7751,11 @@ static __exit void hardware_unsetup(void)free_kvm_area (); } +static int vmx_cpu_dirty_log_size (void ) +{ +return enable_pml ?PML_ENTITY_NUM :0 ; +} +static struct kvm_x86_ops vmx_x86_ops__ro_after_init = { .cpu_has_kvm_support = cpu_has_kvm_support, .disabled_by_bios = vmx_disabled_by_bios,
@@ -7873,6 +7879,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .flush_log_dirty = vmx_flush_log_dirty, .enable_log_dirty_pt_masked = vmx_enable_log_dirty_pt_masked, .write_log_dirty = vmx_write_pml_buffer, + .cpu_dirty_log_size = vmx_cpu_dirty_log_size, .pre_block = vmx_pre_block, .post_block = vmx_post_block,
arch/x86/kvm/x86.c +9 -0
@@ -7965,6 +7965,15 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)bool req_immediate_exit = false; +/* Forbid vmenter if vcpu dirty ring is soft-full */ +if (unlikely (vcpu->kvm->dirty_ring_size && +kvm_dirty_ring_soft_full (&vcpu->dirty_ring))) { + vcpu->run->exit_reason =KVM_EXIT_DIRTY_RING_FULL ; +trace_kvm_dirty_ring_exit (vcpu); + r =0 ; + goto out; + } +if (kvm_request_pending (vcpu)) {if (kvm_check_request (KVM_REQ_GET_VMCS12_PAGES , vcpu)) {if (unlikely (!kvm_x86_ops->get_vmcs12_pages (vcpu))) {
include/linux/kvm_dirty_ring.h new file +57 -0
57 lines not on this page · raw message
include/linux/kvm_host.h +28 -0
@@ -34,6 +34,7 @@#include <linux/kvm_types.h> #include <asm/kvm_host.h> +#include <linux/kvm_dirty_ring.h> #ifndef KVM_MAX_VCPU_ID #define KVM_MAX_VCPU_ID KVM_MAX_VCPUS
@@ -321,6 +322,7 @@ struct kvm_vcpu {bool ready;struct kvm_vcpu_arch arch;struct dentry *debugfs_dentry; +struct kvm_dirty_ring dirty_ring; };static inline int kvm_vcpu_exiting_guest_mode (struct kvm_vcpu *vcpu)
@@ -502,6 +504,9 @@ struct kvm {struct srcu_struct srcu;struct srcu_struct irq_srcu;pid_t userspace_pid; +u32 dirty_ring_size; +struct spinlock dirty_ring_lock; +wait_queue_head_t dirty_ring_waitqueue; };#define kvm_err (fmt, ...) \
@@ -813,6 +818,8 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,gfn_t gfn_offset, unsigned long mask); +void kvm_reset_dirty_gfn (struct kvm *kvm,u32 slot,u64 offset,u64 mask); +int kvm_vm_ioctl_get_dirty_log (struct kvm *kvm,struct kvm_dirty_log *log); int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm,
@@ -1392,4 +1399,25 @@ int kvm_vm_create_worker_thread(struct kvm *kvm, kvm_vm_thread_fn_t thread_fn, uintptr_t data, const char *name, struct task_struct **thread_ptr); +/* +* This defines how many reserved entries we want to keep before we +* kick the vcpu to the userspace to avoid dirty ring full. This +* value can be tuned to higher if e.g. PML is enabled on the host. +*/ +#define KVM_DIRTY_RING_RSVD_ENTRIES 64 + +/* Max number of entries allowed for each kvm dirty ring */ +#define KVM_DIRTY_RING_MAX_ENTRIES 65536 + +/* +* Arch needs to define these macro after implementing the dirty ring +* feature. KVM_DIRTY_LOG_PAGE_OFFSET should be defined as the +* starting page offset of the dirty ring structures, while +* KVM_DIRTY_RING_VERSION should be defined as >=1. By default, this +* feature is off on all archs. +*/ +#ifndef KVM_DIRTY_LOG_PAGE_OFFSET +#define KVM_DIRTY_LOG_PAGE_OFFSET 0 +#endif +#endif
include/trace/events/kvm.h +78 -0
84 lines not on this page · raw message
include/uapi/linux/kvm.h +31 -0
@@ -235,6 +235,7 @@ struct kvm_hyperv_exit {#define KVM_EXIT_S390_STSI 25#define KVM_EXIT_IOAPIC_EOI 26#define KVM_EXIT_HYPERV 27 +#define KVM_EXIT_DIRTY_RING_FULL 28/* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */
@@ -246,6 +247,11 @@ struct kvm_hyperv_exit {/* Encounter unexpected vm-exit reason */ #define KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON 4 +struct kvm_dirty_ring_indices { +__u32 avail_index;/* set by kernel */ +__u32 fetch_index;/* set by userspace */ +}; +/* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */ struct kvm_run {/* in */
@@ -415,6 +421,8 @@ struct kvm_run {struct kvm_sync_regs regs;char padding[SYNC_REGS_SIZE_BYTES ]; } s; + +struct kvm_dirty_ring_indices vcpu_ring_indices; };/* for KVM_REGISTER_COALESCED_MMIO / KVM_UNREGISTER_COALESCED_MMIO */
@@ -1000,6 +1008,7 @@ struct kvm_ppc_resize_hpt {#define KVM_CAP_PMU_EVENT_FILTER 173#define KVM_CAP_ARM_IRQ_LINE_LAYOUT_2 174#define KVM_CAP_HYPERV_DIRECT_TLBFLUSH 175 +#define KVM_CAP_DIRTY_LOG_RING 176#ifdef KVM_CAP_IRQ_ROUTING
@@ -1461,6 +1470,9 @@ struct kvm_enc_region {/* Available with KVM_CAP_ARM_SVE */ #define KVM_ARM_VCPU_FINALIZE _IOW(KVMIO, 0xc2, int) +/* Available with KVM_CAP_DIRTY_LOG_RING */ +#define KVM_RESET_DIRTY_RINGS _IO(KVMIO, 0xc3) +/* Secure Encrypted Virtualization command */ enum sev_cmd_id {/* Guest initialization commands */
@@ -1611,4 +1623,23 @@ struct kvm_hyperv_eventfd {#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0) +/* +* The following are the requirements for supporting dirty log ring +* (by enabling KVM_DIRTY_LOG_PAGE_OFFSET). +* +* 1. Memory accesses by KVM should call kvm_vcpu_write_* instead +* of kvm_write_* so that the global dirty ring is not filled up +* too quickly. +* 2. kvm_arch_mmu_enable_log_dirty_pt_masked should be defined for +* enabling dirty logging. +* 3. There should not be a separate step to synchronize hardware +* dirty bitmap with KVM's. +*/ + +struct kvm_dirty_gfn { +__u32 pad; +__u32 slot; +__u64 offset; +}; +#endif /* __LINUX_KVM_H */
virt/kvm/dirty_ring.c new file +201 -0
201 lines not on this page · raw message
virt/kvm/kvm_main.c +170 -2
254 lines not on this page · raw message
Signature · 1 line
2.24.1
PATCH v2 9/17 KVM: Make dirty ring exclusive to dirty bitmap log
In reply to Peter XuThere's no good reason to use both the dirty bitmap logging and the new dirty ring buffer to track dirty bits. We should be able to even support both of them at the same time, but it could complicate things which could actually help little. Let's simply make it the rule before we enable dirty ring on any arch, that we don't allow these two interfaces to be used together.
The big world switch would be KVM_CAP_DIRTY_LOG_RING capability enablement. That's where we'll switch from the default dirty logging way to the dirty ring way. As long as kvm->dirty_ring_size is setup correctly, we'll once and for all switch to the dirty ring buffer mode for the current virtual machine.
--- Documentation/virt/kvm/api.txt | 7 +++++++ virt/kvm/kvm_main.c | 12 ++++++++++++ 2 files changed, 19 insertions(+)
Documentation/virt/kvm/api.txt +7 -0
@@ -5411,3 +5411,10 @@ all the existing dirty gfns are flushed to the dirty rings. If one of the ring buffers is full, the guest will exit to userspace with the exit reason set to KVM_EXIT_DIRTY_LOG_FULL, and the KVM_RUN ioctl will return to userspace with zero. + +NOTE: the KVM_CAP_DIRTY_LOG_RING capability and the new ioctl +KVM_RESET_DIRTY_RINGS are exclusive to the existing KVM_GET_DIRTY_LOG +interface. After enabling KVM_CAP_DIRTY_LOG_RING with an acceptable +dirty ring size, the virtual machine will switch to the dirty ring +tracking mode, and KVM_GET_DIRTY_LOG, KVM_CLEAR_DIRTY_LOG ioctls will +stop working.
virt/kvm/kvm_main.c +12 -0
@@ -1204,6 +1204,10 @@ int kvm_get_dirty_log(struct kvm *kvm,unsigned long n;unsigned long any =0 ; +/* Dirty ring tracking is exclusive to dirty log tracking */ +if (kvm->dirty_ring_size) +return -EINVAL ; + as_id = log->slot >>16 ; id = (u16 )log->slot;if (as_id >=KVM_ADDRESS_SPACE_NUM || id >=KVM_USER_MEM_SLOTS )
@@ -1261,6 +1265,10 @@ int kvm_get_dirty_log_protect(struct kvm *kvm,unsigned long *dirty_bitmap;unsigned long *dirty_bitmap_buffer; +/* Dirty ring tracking is exclusive to dirty log tracking */ +if (kvm->dirty_ring_size) +return -EINVAL ; + as_id = log->slot >>16 ; id = (u16 )log->slot;if (as_id >=KVM_ADDRESS_SPACE_NUM || id >=KVM_USER_MEM_SLOTS )
@@ -1332,6 +1340,10 @@ int kvm_clear_dirty_log_protect(struct kvm *kvm,unsigned long *dirty_bitmap;unsigned long *dirty_bitmap_buffer; +/* Dirty ring tracking is exclusive to dirty log tracking */ +if (kvm->dirty_ring_size) +return -EINVAL ; + as_id = log->slot >>16 ; id = (u16 )log->slot;if (as_id >=KVM_ADDRESS_SPACE_NUM || id >=KVM_USER_MEM_SLOTS )
Signature · 1 line
2.24.1
If you see three identical half-posted series which only contains patches 00-09... I am very sorry for ruining your inbox... I think my mail server is not happy to continue sending the rest of the patches, and I'll get this during sending the patch 10:
4.3.0 Temporary System Problem. Try again later (10). d25sm3385231qtq.11 - gsmtp
So far I don't see what's wrong with patch 10, either.
I'll try to fix it up before I send 4th time (or anyone knows please hint me)... Please ignore the previous three in-complete versions.
Signature · 1 line
Peter Xu
Quoted 11 lines · Peter Xu
If you see three identical half-posted series which only contains patches 00-09... I am very sorry for ruining your inbox... I think my mail server is not happy to continue sending the rest of the patches, and I'll get this during sending the patch 10:
4.3.0 Temporary System Problem. Try again later (10). d25sm3385231qtq.11 - gsmtp
So far I don't see what's wrong with patch 10, either.
I'll try to fix it up before I send 4th time (or anyone knows please hint me)... Please ignore the previous three in-complete versions.
Please add RESEND in the subject when resending an idential patch (set), it gives recipients a heads up that the two (or four :-)) sets are the same, e.g. previous versions can be ignored if he/she received both the original and RESEND version(s).
[PATCH RESEND v2 00/17] KVM: Dirty ring interface
Quoted 13 lines · Sean Christopherson
Quoted 11 lines · Peter Xu
If you see three identical half-posted series which only contains patches 00-09... I am very sorry for ruining your inbox... I think my mail server is not happy to continue sending the rest of the patches, and I'll get this during sending the patch 10:
4.3.0 Temporary System Problem. Try again later (10). d25sm3385231qtq.11 - gsmtp
So far I don't see what's wrong with patch 10, either.
I'll try to fix it up before I send 4th time (or anyone knows please hint me)... Please ignore the previous three in-complete versions.
Quoted 6 lines
Please add RESEND in the subject when resending an idential patch (set), it gives recipients a heads up that the two (or four :-)) sets are the same, e.g. previous versions can be ignored if he/she received both the original and RESEND version(s).
[PATCH RESEND v2 00/17] KVM: Dirty ring interface
Thanks Sean, new version sent. Just in case if anyone read the old
versions: they have exactly the same content with the RESEND series. I still resent the first 10 emails just to make things simple.
Signature · 1 line
Peter Xu