From 8284765f03b7a0b18968cefeb5e78aca647b8f8b Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 9 Jan 2024 17:15:32 -0800 Subject: KVM: Get reference to VM's address space in the async #PF worker Get a reference to the target VM's address space in async_pf_execute() instead of gifting a reference from kvm_setup_async_pf(). Keeping the address space alive just to service an async #PF is counter-productive, i.e. if the process is exiting and all vCPUs are dead, then NOT doing get_user_pages_remote() and freeing the address space asap is desirable. Handling the mm reference entirely within async_pf_execute() also simplifies the async #PF flows as a whole, e.g. it's not immediately obvious when the worker task vs. the vCPU task is responsible for putting the gifted mm reference. Reviewed-by: Vitaly Kuznetsov Reviewed-by: Xu Yilun Link: https://lore.kernel.org/r/20240110011533.503302-4-seanjc@google.com Signed-off-by: Sean Christopherson --- include/linux/kvm_host.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7e7fd25b09b3..bbfefd7e612f 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -238,7 +238,6 @@ struct kvm_async_pf { 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; -- cgit v1.2.3 From 3c7a8e190bc580813ddd9259f62971c8d2a6b5ad Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 12 Dec 2023 11:15:28 -0500 Subject: uapi: introduce uapi-friendly macros for GENMASK Move __GENMASK and __GENMASK_ULL from include/ to include/uapi/ so that they can be used to define masks in userspace API headers. Compared to what is already in include/linux/bits.h, the definitions need to use the uglified versions of UL(), ULL(), BITS_PER_LONG and BITS_PER_LONG_LONG (which did not even exist), but otherwise expand to the same content. Signed-off-by: Paolo Bonzini --- include/linux/bits.h | 8 +------- include/uapi/asm-generic/bitsperlong.h | 4 ++++ include/uapi/linux/bits.h | 15 +++++++++++++++ 3 files changed, 20 insertions(+), 7 deletions(-) create mode 100644 include/uapi/linux/bits.h (limited to 'include/linux') diff --git a/include/linux/bits.h b/include/linux/bits.h index 7c0cf5031abe..0eb24d21aac2 100644 --- a/include/linux/bits.h +++ b/include/linux/bits.h @@ -4,6 +4,7 @@ #include #include +#include #include #define BIT_MASK(nr) (UL(1) << ((nr) % BITS_PER_LONG)) @@ -30,15 +31,8 @@ #define GENMASK_INPUT_CHECK(h, l) 0 #endif -#define __GENMASK(h, l) \ - (((~UL(0)) - (UL(1) << (l)) + 1) & \ - (~UL(0) >> (BITS_PER_LONG - 1 - (h)))) #define GENMASK(h, l) \ (GENMASK_INPUT_CHECK(h, l) + __GENMASK(h, l)) - -#define __GENMASK_ULL(h, l) \ - (((~ULL(0)) - (ULL(1) << (l)) + 1) & \ - (~ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h)))) #define GENMASK_ULL(h, l) \ (GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l)) diff --git a/include/uapi/asm-generic/bitsperlong.h b/include/uapi/asm-generic/bitsperlong.h index 352cb81947b8..fadb3f857f28 100644 --- a/include/uapi/asm-generic/bitsperlong.h +++ b/include/uapi/asm-generic/bitsperlong.h @@ -24,4 +24,8 @@ #endif #endif +#ifndef __BITS_PER_LONG_LONG +#define __BITS_PER_LONG_LONG 64 +#endif + #endif /* _UAPI__ASM_GENERIC_BITS_PER_LONG */ diff --git a/include/uapi/linux/bits.h b/include/uapi/linux/bits.h new file mode 100644 index 000000000000..3c2a101986a3 --- /dev/null +++ b/include/uapi/linux/bits.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* bits.h: Macros for dealing with bitmasks. */ + +#ifndef _UAPI_LINUX_BITS_H +#define _UAPI_LINUX_BITS_H + +#define __GENMASK(h, l) \ + (((~_UL(0)) - (_UL(1) << (l)) + 1) & \ + (~_UL(0) >> (__BITS_PER_LONG - 1 - (h)))) + +#define __GENMASK_ULL(h, l) \ + (((~_ULL(0)) - (_ULL(1) << (l)) + 1) & \ + (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h)))) + +#endif /* _UAPI_LINUX_BITS_H */ -- cgit v1.2.3 From 78b74638eb6dffd9b24bc3b121556a9039292df6 Mon Sep 17 00:00:00 2001 From: Paul Durrant Date: Thu, 15 Feb 2024 15:28:59 +0000 Subject: KVM: pfncache: add a mark-dirty helper At the moment pages are marked dirty by open-coded calls to mark_page_dirty_in_slot(), directly deferefencing the gpa and memslot from the cache. After a subsequent patch these may not always be set so add a helper now so that caller will protected from the need to know about this detail. Signed-off-by: Paul Durrant Reviewed-by: David Woodhouse Link: https://lore.kernel.org/r/20240215152916.1158-5-paul@xen.org [sean: decrease indentation, use gpa_to_gfn()] Signed-off-by: Sean Christopherson --- arch/x86/kvm/x86.c | 2 +- arch/x86/kvm/xen.c | 6 +++--- include/linux/kvm_host.h | 10 ++++++++++ 3 files changed, 14 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index bf10a9073a09..f0f37c769a3a 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3160,7 +3160,7 @@ static void kvm_setup_guest_pvclock(struct kvm_vcpu *v, guest_hv_clock->version = ++vcpu->hv_clock.version; - mark_page_dirty_in_slot(v->kvm, gpc->memslot, gpc->gpa >> PAGE_SHIFT); + kvm_gpc_mark_dirty_in_slot(gpc); read_unlock_irqrestore(&gpc->lock, flags); trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock); diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index f3327508ae41..2d001a9c6378 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -453,11 +453,11 @@ static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic) } if (user_len2) { - mark_page_dirty_in_slot(v->kvm, gpc2->memslot, gpc2->gpa >> PAGE_SHIFT); + kvm_gpc_mark_dirty_in_slot(gpc2); read_unlock(&gpc2->lock); } - mark_page_dirty_in_slot(v->kvm, gpc1->memslot, gpc1->gpa >> PAGE_SHIFT); + kvm_gpc_mark_dirty_in_slot(gpc1); read_unlock_irqrestore(&gpc1->lock, flags); } @@ -565,7 +565,7 @@ void kvm_xen_inject_pending_events(struct kvm_vcpu *v) WRITE_ONCE(vi->evtchn_upcall_pending, 1); } - mark_page_dirty_in_slot(v->kvm, gpc->memslot, gpc->gpa >> PAGE_SHIFT); + kvm_gpc_mark_dirty_in_slot(gpc); read_unlock_irqrestore(&gpc->lock, flags); /* For the per-vCPU lapic vector, deliver it as MSI. */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7e7fd25b09b3..604ae285d9a9 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1795,6 +1795,16 @@ static inline bool kvm_is_error_gpa(struct kvm *kvm, gpa_t gpa) return kvm_is_error_hva(hva); } +static inline void kvm_gpc_mark_dirty_in_slot(struct gfn_to_pfn_cache *gpc) +{ + lockdep_assert_held(&gpc->lock); + + if (!gpc->memslot) + return; + + mark_page_dirty_in_slot(gpc->kvm, gpc->memslot, gpa_to_gfn(gpc->gpa)); +} + enum kvm_stat_kind { KVM_STAT_VM, KVM_STAT_VCPU, -- cgit v1.2.3 From a4bff3df51472f555ab8dea05a3d2faf4abbf199 Mon Sep 17 00:00:00 2001 From: Paul Durrant Date: Thu, 15 Feb 2024 15:29:00 +0000 Subject: KVM: pfncache: remove KVM_GUEST_USES_PFN usage As noted in [1] the KVM_GUEST_USES_PFN usage flag is never set by any callers of kvm_gpc_init(), and for good reason: the implementation is incomplete/broken. And it's not clear that there will ever be a user of KVM_GUEST_USES_PFN, as coordinating vCPUs with mmu_notifier events is non-trivial. Remove KVM_GUEST_USES_PFN and all related code, e.g. dropping KVM_GUEST_USES_PFN also makes the 'vcpu' argument redundant, to avoid having to reason about broken code as __kvm_gpc_refresh() evolves. Moreover, all existing callers specify KVM_HOST_USES_PFN so the usage check in hva_to_pfn_retry() and hence the 'usage' argument to kvm_gpc_init() are also redundant. [1] https://lore.kernel.org/all/ZQiR8IpqOZrOpzHC@google.com Signed-off-by: Paul Durrant Reviewed-by: David Woodhouse Link: https://lore.kernel.org/r/20240215152916.1158-6-paul@xen.org [sean: explicitly call out that guest usage is incomplete] Signed-off-by: Sean Christopherson --- arch/x86/kvm/x86.c | 2 +- arch/x86/kvm/xen.c | 14 ++++------- include/linux/kvm_host.h | 11 +-------- include/linux/kvm_types.h | 8 ------- virt/kvm/pfncache.c | 61 +++++++---------------------------------------- 5 files changed, 16 insertions(+), 80 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f0f37c769a3a..415723a28dce 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -12056,7 +12056,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.regs_avail = ~0; vcpu->arch.regs_dirty = ~0; - kvm_gpc_init(&vcpu->arch.pv_time, vcpu->kvm, vcpu, KVM_HOST_USES_PFN); + kvm_gpc_init(&vcpu->arch.pv_time, vcpu->kvm); if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 2d001a9c6378..e90464225467 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -2108,14 +2108,10 @@ void kvm_xen_init_vcpu(struct kvm_vcpu *vcpu) timer_setup(&vcpu->arch.xen.poll_timer, cancel_evtchn_poll, 0); - kvm_gpc_init(&vcpu->arch.xen.runstate_cache, vcpu->kvm, NULL, - KVM_HOST_USES_PFN); - kvm_gpc_init(&vcpu->arch.xen.runstate2_cache, vcpu->kvm, NULL, - KVM_HOST_USES_PFN); - kvm_gpc_init(&vcpu->arch.xen.vcpu_info_cache, vcpu->kvm, NULL, - KVM_HOST_USES_PFN); - kvm_gpc_init(&vcpu->arch.xen.vcpu_time_info_cache, vcpu->kvm, NULL, - KVM_HOST_USES_PFN); + kvm_gpc_init(&vcpu->arch.xen.runstate_cache, vcpu->kvm); + kvm_gpc_init(&vcpu->arch.xen.runstate2_cache, vcpu->kvm); + kvm_gpc_init(&vcpu->arch.xen.vcpu_info_cache, vcpu->kvm); + kvm_gpc_init(&vcpu->arch.xen.vcpu_time_info_cache, vcpu->kvm); } void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu) @@ -2158,7 +2154,7 @@ void kvm_xen_init_vm(struct kvm *kvm) { mutex_init(&kvm->arch.xen.xen_lock); idr_init(&kvm->arch.xen.evtchn_ports); - kvm_gpc_init(&kvm->arch.xen.shinfo_cache, kvm, NULL, KVM_HOST_USES_PFN); + kvm_gpc_init(&kvm->arch.xen.shinfo_cache, kvm); } void kvm_xen_destroy_vm(struct kvm *kvm) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 604ae285d9a9..3e1c04608c67 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1319,21 +1319,12 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn); * * @gpc: struct gfn_to_pfn_cache object. * @kvm: pointer to kvm instance. - * @vcpu: vCPU to be used for marking pages dirty and to be woken on - * invalidation. - * @usage: indicates if the resulting host physical PFN is used while - * the @vcpu is IN_GUEST_MODE (in which case invalidation of - * the cache from MMU notifiers---but not for KVM memslot - * changes!---will also force @vcpu to exit the guest and - * refresh the cache); and/or if the PFN used directly - * by KVM (and thus needs a kernel virtual mapping). * * This sets up a gfn_to_pfn_cache by initializing locks and assigning the * immutable attributes. Note, the cache must be zero-allocated (or zeroed by * the caller before init). */ -void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm, - struct kvm_vcpu *vcpu, enum pfn_cache_usage usage); +void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm); /** * kvm_gpc_activate - prepare a cached kernel mapping and HPA for a given guest diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 9d1f7835d8c1..d93f6522b2c3 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -49,12 +49,6 @@ typedef u64 hfn_t; typedef hfn_t kvm_pfn_t; -enum pfn_cache_usage { - KVM_GUEST_USES_PFN = BIT(0), - KVM_HOST_USES_PFN = BIT(1), - KVM_GUEST_AND_HOST_USE_PFN = KVM_GUEST_USES_PFN | KVM_HOST_USES_PFN, -}; - struct gfn_to_hva_cache { u64 generation; gpa_t gpa; @@ -69,13 +63,11 @@ struct gfn_to_pfn_cache { unsigned long uhva; struct kvm_memory_slot *memslot; struct kvm *kvm; - struct kvm_vcpu *vcpu; struct list_head list; rwlock_t lock; struct mutex refresh_lock; void *khva; kvm_pfn_t pfn; - enum pfn_cache_usage usage; bool active; bool valid; }; diff --git a/virt/kvm/pfncache.c b/virt/kvm/pfncache.c index f3571f44d9af..6f4b537eb25b 100644 --- a/virt/kvm/pfncache.c +++ b/virt/kvm/pfncache.c @@ -25,9 +25,7 @@ void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, unsigned long start, unsigned long end, bool may_block) { - DECLARE_BITMAP(vcpu_bitmap, KVM_MAX_VCPUS); struct gfn_to_pfn_cache *gpc; - bool evict_vcpus = false; spin_lock(&kvm->gpc_lock); list_for_each_entry(gpc, &kvm->gpc_list, list) { @@ -37,43 +35,10 @@ void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, unsigned long start, if (gpc->valid && !is_error_noslot_pfn(gpc->pfn) && gpc->uhva >= start && gpc->uhva < end) { gpc->valid = false; - - /* - * If a guest vCPU could be using the physical address, - * it needs to be forced out of guest mode. - */ - if (gpc->usage & KVM_GUEST_USES_PFN) { - if (!evict_vcpus) { - evict_vcpus = true; - bitmap_zero(vcpu_bitmap, KVM_MAX_VCPUS); - } - __set_bit(gpc->vcpu->vcpu_idx, vcpu_bitmap); - } } write_unlock_irq(&gpc->lock); } spin_unlock(&kvm->gpc_lock); - - if (evict_vcpus) { - /* - * KVM needs to ensure the vCPU is fully out of guest context - * before allowing the invalidation to continue. - */ - unsigned int req = KVM_REQ_OUTSIDE_GUEST_MODE; - bool called; - - /* - * If the OOM reaper is active, then all vCPUs should have - * been stopped already, so perform the request without - * KVM_REQUEST_WAIT and be sad if any needed to be IPI'd. - */ - if (!may_block) - req &= ~KVM_REQUEST_WAIT; - - called = kvm_make_vcpus_request_mask(kvm, req, vcpu_bitmap); - - WARN_ON_ONCE(called && !may_block); - } } bool kvm_gpc_check(struct gfn_to_pfn_cache *gpc, unsigned long len) @@ -206,16 +171,14 @@ static kvm_pfn_t hva_to_pfn_retry(struct gfn_to_pfn_cache *gpc) * pfn. Note, kmap() and memremap() can both sleep, so this * too must be done outside of gpc->lock! */ - if (gpc->usage & KVM_HOST_USES_PFN) { - if (new_pfn == gpc->pfn) - new_khva = old_khva; - else - new_khva = gpc_map(new_pfn); - - if (!new_khva) { - kvm_release_pfn_clean(new_pfn); - goto out_error; - } + if (new_pfn == gpc->pfn) + new_khva = old_khva; + else + new_khva = gpc_map(new_pfn); + + if (!new_khva) { + kvm_release_pfn_clean(new_pfn); + goto out_error; } write_lock_irq(&gpc->lock); @@ -346,18 +309,12 @@ int kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, unsigned long len) return __kvm_gpc_refresh(gpc, gpc->gpa, len); } -void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm, - struct kvm_vcpu *vcpu, enum pfn_cache_usage usage) +void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm) { - WARN_ON_ONCE(!usage || (usage & KVM_GUEST_AND_HOST_USE_PFN) != usage); - WARN_ON_ONCE((usage & KVM_GUEST_USES_PFN) && !vcpu); - rwlock_init(&gpc->lock); mutex_init(&gpc->refresh_lock); gpc->kvm = kvm; - gpc->vcpu = vcpu; - gpc->usage = usage; gpc->pfn = KVM_PFN_ERR_FAULT; gpc->uhva = KVM_HVA_ERR_BAD; } -- cgit v1.2.3 From 9e7325acb3dc8df8a6370ebc18aef107aae17ef0 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 15 Feb 2024 15:29:03 +0000 Subject: KVM: s390: Refactor kvm_is_error_gpa() into kvm_is_gpa_in_memslot() Rename kvm_is_error_gpa() to kvm_is_gpa_in_memslot() and invert the polarity accordingly in order to (a) free up kvm_is_error_gpa() to match with kvm_is_error_{hva,page}(), and (b) to make it more obvious that the helper is doing a memslot lookup, i.e. not simply checking for INVALID_GPA. No functional change intended. Link: https://lore.kernel.org/r/20240215152916.1158-9-paul@xen.org Signed-off-by: Sean Christopherson --- arch/s390/kvm/diag.c | 2 +- arch/s390/kvm/gaccess.c | 14 +++++++------- arch/s390/kvm/kvm-s390.c | 4 ++-- arch/s390/kvm/priv.c | 4 ++-- arch/s390/kvm/sigp.c | 2 +- include/linux/kvm_host.h | 4 ++-- 6 files changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 3c65b8258ae6..2a32438e09ce 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -102,7 +102,7 @@ static int __diag_page_ref_service(struct kvm_vcpu *vcpu) parm.token_addr & 7 || parm.zarch != 0x8000000000000000ULL) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - if (kvm_is_error_gpa(vcpu->kvm, parm.token_addr)) + if (!kvm_is_gpa_in_memslot(vcpu->kvm, parm.token_addr)) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); vcpu->arch.pfault_token = parm.token_addr; diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 5bfcc50c1a68..415c99649e43 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -664,7 +664,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, case ASCE_TYPE_REGION1: { union region1_table_entry rfte; - if (kvm_is_error_gpa(vcpu->kvm, ptr)) + if (!kvm_is_gpa_in_memslot(vcpu->kvm, ptr)) return PGM_ADDRESSING; if (deref_table(vcpu->kvm, ptr, &rfte.val)) return -EFAULT; @@ -682,7 +682,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, case ASCE_TYPE_REGION2: { union region2_table_entry rste; - if (kvm_is_error_gpa(vcpu->kvm, ptr)) + if (!kvm_is_gpa_in_memslot(vcpu->kvm, ptr)) return PGM_ADDRESSING; if (deref_table(vcpu->kvm, ptr, &rste.val)) return -EFAULT; @@ -700,7 +700,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, case ASCE_TYPE_REGION3: { union region3_table_entry rtte; - if (kvm_is_error_gpa(vcpu->kvm, ptr)) + if (!kvm_is_gpa_in_memslot(vcpu->kvm, ptr)) return PGM_ADDRESSING; if (deref_table(vcpu->kvm, ptr, &rtte.val)) return -EFAULT; @@ -728,7 +728,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, case ASCE_TYPE_SEGMENT: { union segment_table_entry ste; - if (kvm_is_error_gpa(vcpu->kvm, ptr)) + if (!kvm_is_gpa_in_memslot(vcpu->kvm, ptr)) return PGM_ADDRESSING; if (deref_table(vcpu->kvm, ptr, &ste.val)) return -EFAULT; @@ -748,7 +748,7 @@ static unsigned long guest_translate(struct kvm_vcpu *vcpu, unsigned long gva, ptr = ste.fc0.pto * (PAGE_SIZE / 2) + vaddr.px * 8; } } - if (kvm_is_error_gpa(vcpu->kvm, ptr)) + if (!kvm_is_gpa_in_memslot(vcpu->kvm, ptr)) return PGM_ADDRESSING; if (deref_table(vcpu->kvm, ptr, &pte.val)) return -EFAULT; @@ -770,7 +770,7 @@ absolute_address: *prot = PROT_TYPE_IEP; return PGM_PROTECTION; } - if (kvm_is_error_gpa(vcpu->kvm, raddr.addr)) + if (!kvm_is_gpa_in_memslot(vcpu->kvm, raddr.addr)) return PGM_ADDRESSING; *gpa = raddr.addr; return 0; @@ -957,7 +957,7 @@ static int guest_range_to_gpas(struct kvm_vcpu *vcpu, unsigned long ga, u8 ar, return rc; } else { gpa = kvm_s390_real_to_abs(vcpu, ga); - if (kvm_is_error_gpa(vcpu->kvm, gpa)) { + if (!kvm_is_gpa_in_memslot(vcpu->kvm, gpa)) { rc = PGM_ADDRESSING; prot = PROT_NONE; } diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index ea63ac769889..3e5a1d7aa81a 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -2878,7 +2878,7 @@ static int kvm_s390_vm_mem_op_abs(struct kvm *kvm, struct kvm_s390_mem_op *mop) srcu_idx = srcu_read_lock(&kvm->srcu); - if (kvm_is_error_gpa(kvm, mop->gaddr)) { + if (!kvm_is_gpa_in_memslot(kvm, mop->gaddr)) { r = PGM_ADDRESSING; goto out_unlock; } @@ -2940,7 +2940,7 @@ static int kvm_s390_vm_mem_op_cmpxchg(struct kvm *kvm, struct kvm_s390_mem_op *m srcu_idx = srcu_read_lock(&kvm->srcu); - if (kvm_is_error_gpa(kvm, mop->gaddr)) { + if (!kvm_is_gpa_in_memslot(kvm, mop->gaddr)) { r = PGM_ADDRESSING; goto out_unlock; } diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index f875a404a0a0..1be19cc9d73c 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -149,7 +149,7 @@ static int handle_set_prefix(struct kvm_vcpu *vcpu) * first page, since address is 8k aligned and memory pieces are always * at least 1MB aligned and have at least a size of 1MB. */ - if (kvm_is_error_gpa(vcpu->kvm, address)) + if (!kvm_is_gpa_in_memslot(vcpu->kvm, address)) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); kvm_s390_set_prefix(vcpu, address); @@ -464,7 +464,7 @@ static int handle_test_block(struct kvm_vcpu *vcpu) return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm); addr = kvm_s390_real_to_abs(vcpu, addr); - if (kvm_is_error_gpa(vcpu->kvm, addr)) + if (!kvm_is_gpa_in_memslot(vcpu->kvm, addr)) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); /* * We don't expect errors on modern systems, and do not care diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c index d9696b530064..55c34cb35428 100644 --- a/arch/s390/kvm/sigp.c +++ b/arch/s390/kvm/sigp.c @@ -172,7 +172,7 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, struct kvm_vcpu *dst_vcpu, * first page, since address is 8k aligned and memory pieces are always * at least 1MB aligned and have at least a size of 1MB. */ - if (kvm_is_error_gpa(vcpu->kvm, irq.u.prefix.address)) { + if (!kvm_is_gpa_in_memslot(vcpu->kvm, irq.u.prefix.address)) { *reg &= 0xffffffff00000000UL; *reg |= SIGP_STATUS_INVALID_PARAMETER; return SIGP_CC_STATUS_STORED; diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 3e1c04608c67..81a9d1cf91a2 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1779,11 +1779,11 @@ static inline hpa_t pfn_to_hpa(kvm_pfn_t pfn) return (hpa_t)pfn << PAGE_SHIFT; } -static inline bool kvm_is_error_gpa(struct kvm *kvm, gpa_t gpa) +static inline bool kvm_is_gpa_in_memslot(struct kvm *kvm, gpa_t gpa) { unsigned long hva = gfn_to_hva(kvm, gpa_to_gfn(gpa)); - return kvm_is_error_hva(hva); + return !kvm_is_error_hva(hva); } static inline void kvm_gpc_mark_dirty_in_slot(struct gfn_to_pfn_cache *gpc) -- cgit v1.2.3 From 721f5b0dda784829b833039fbb42f420b9f86575 Mon Sep 17 00:00:00 2001 From: Paul Durrant Date: Thu, 15 Feb 2024 15:29:04 +0000 Subject: KVM: pfncache: allow a cache to be activated with a fixed (userspace) HVA Some pfncache pages may actually be overlays on guest memory that have a fixed HVA within the VMM. It's pointless to invalidate such cached mappings if the overlay is moved so allow a cache to be activated directly with the HVA to cater for such cases. A subsequent patch will make use of this facility. Signed-off-by: Paul Durrant Reviewed-by: David Woodhouse Link: https://lore.kernel.org/r/20240215152916.1158-10-paul@xen.org Signed-off-by: Sean Christopherson --- include/linux/kvm_host.h | 31 +++++++++++++++ virt/kvm/pfncache.c | 98 ++++++++++++++++++++++++++++++++++-------------- 2 files changed, 101 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 81a9d1cf91a2..fa070c36f98a 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -148,6 +148,11 @@ static inline bool kvm_is_error_hva(unsigned long addr) #endif +static inline bool kvm_is_error_gpa(gpa_t gpa) +{ + return gpa == INVALID_GPA; +} + #define KVM_ERR_PTR_BAD_PAGE (ERR_PTR(-ENOENT)) static inline bool is_error_page(struct page *page) @@ -1344,6 +1349,22 @@ void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm); */ int kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long len); +/** + * kvm_gpc_activate_hva - prepare a cached kernel mapping and HPA for a given HVA. + * + * @gpc: struct gfn_to_pfn_cache object. + * @hva: userspace virtual address to map. + * @len: sanity check; the range being access must fit a single page. + * + * @return: 0 for success. + * -EINVAL for a mapping which would cross a page boundary. + * -EFAULT for an untranslatable guest physical address. + * + * The semantics of this function are the same as those of kvm_gpc_activate(). It + * merely bypasses a layer of address translation. + */ +int kvm_gpc_activate_hva(struct gfn_to_pfn_cache *gpc, unsigned long hva, unsigned long len); + /** * kvm_gpc_check - check validity of a gfn_to_pfn_cache. * @@ -1390,6 +1411,16 @@ int kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, unsigned long len); */ void kvm_gpc_deactivate(struct gfn_to_pfn_cache *gpc); +static inline bool kvm_gpc_is_gpa_active(struct gfn_to_pfn_cache *gpc) +{ + return gpc->active && !kvm_is_error_gpa(gpc->gpa); +} + +static inline bool kvm_gpc_is_hva_active(struct gfn_to_pfn_cache *gpc) +{ + return gpc->active && kvm_is_error_gpa(gpc->gpa); +} + void kvm_sigset_activate(struct kvm_vcpu *vcpu); void kvm_sigset_deactivate(struct kvm_vcpu *vcpu); diff --git a/virt/kvm/pfncache.c b/virt/kvm/pfncache.c index 97eec8ee3449..a47ca6fd75c2 100644 --- a/virt/kvm/pfncache.c +++ b/virt/kvm/pfncache.c @@ -48,7 +48,14 @@ bool kvm_gpc_check(struct gfn_to_pfn_cache *gpc, unsigned long len) if (!gpc->active) return false; - if (gpc->generation != slots->generation || kvm_is_error_hva(gpc->uhva)) + /* + * If the page was cached from a memslot, make sure the memslots have + * not been re-configured. + */ + if (!kvm_is_error_gpa(gpc->gpa) && gpc->generation != slots->generation) + return false; + + if (kvm_is_error_hva(gpc->uhva)) return false; if (offset_in_page(gpc->uhva) + len > PAGE_SIZE) @@ -209,11 +216,10 @@ out_error: return -EFAULT; } -static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa, +static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long uhva, unsigned long len) { - struct kvm_memslots *slots = kvm_memslots(gpc->kvm); - unsigned long page_offset = offset_in_page(gpa); + unsigned long page_offset; bool unmap_old = false; unsigned long old_uhva; kvm_pfn_t old_pfn; @@ -221,10 +227,16 @@ static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa, void *old_khva; int ret; + /* Either gpa or uhva must be valid, but not both */ + if (WARN_ON_ONCE(kvm_is_error_gpa(gpa) == kvm_is_error_hva(uhva))) + return -EINVAL; + /* - * If must fit within a single page. The 'len' argument is - * only to enforce that. + * The cached acces must fit within a single page. The 'len' argument + * exists only to enforce that. */ + page_offset = kvm_is_error_gpa(gpa) ? offset_in_page(uhva) : + offset_in_page(gpa); if (page_offset + len > PAGE_SIZE) return -EINVAL; @@ -246,29 +258,39 @@ static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa, old_khva = (void *)PAGE_ALIGN_DOWN((uintptr_t)gpc->khva); old_uhva = PAGE_ALIGN_DOWN(gpc->uhva); - /* Refresh the userspace HVA if necessary */ - if (gpc->gpa != gpa || gpc->generation != slots->generation || - kvm_is_error_hva(gpc->uhva)) { - gfn_t gfn = gpa_to_gfn(gpa); - - gpc->gpa = gpa; - gpc->generation = slots->generation; - gpc->memslot = __gfn_to_memslot(slots, gfn); - gpc->uhva = gfn_to_hva_memslot(gpc->memslot, gfn); + if (kvm_is_error_gpa(gpa)) { + gpc->gpa = INVALID_GPA; + gpc->memslot = NULL; + gpc->uhva = PAGE_ALIGN_DOWN(uhva); - if (kvm_is_error_hva(gpc->uhva)) { - ret = -EFAULT; - goto out; - } - - /* - * Even if the GPA and/or the memslot generation changed, the - * HVA may still be the same. - */ if (gpc->uhva != old_uhva) hva_change = true; } else { - gpc->uhva = old_uhva; + struct kvm_memslots *slots = kvm_memslots(gpc->kvm); + + if (gpc->gpa != gpa || gpc->generation != slots->generation || + kvm_is_error_hva(gpc->uhva)) { + gfn_t gfn = gpa_to_gfn(gpa); + + gpc->gpa = gpa; + gpc->generation = slots->generation; + gpc->memslot = __gfn_to_memslot(slots, gfn); + gpc->uhva = gfn_to_hva_memslot(gpc->memslot, gfn); + + if (kvm_is_error_hva(gpc->uhva)) { + ret = -EFAULT; + goto out; + } + + /* + * Even if the GPA and/or the memslot generation changed, the + * HVA may still be the same. + */ + if (gpc->uhva != old_uhva) + hva_change = true; + } else { + gpc->uhva = old_uhva; + } } /* Note: the offset must be correct before calling hva_to_pfn_retry() */ @@ -319,7 +341,15 @@ out_unlock: int kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, unsigned long len) { - return __kvm_gpc_refresh(gpc, gpc->gpa, len); + /* + * If the GPA is valid then ignore the HVA, as a cache can be GPA-based + * or HVA-based, not both. For GPA-based caches, the HVA will be + * recomputed during refresh if necessary. + */ + unsigned long uhva = kvm_is_error_gpa(gpc->gpa) ? gpc->uhva : + KVM_HVA_ERR_BAD; + + return __kvm_gpc_refresh(gpc, gpc->gpa, uhva, len); } void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm) @@ -329,10 +359,12 @@ void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm) gpc->kvm = kvm; gpc->pfn = KVM_PFN_ERR_FAULT; + gpc->gpa = INVALID_GPA; gpc->uhva = KVM_HVA_ERR_BAD; } -int kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long len) +static int __kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long uhva, + unsigned long len) { struct kvm *kvm = gpc->kvm; @@ -353,7 +385,17 @@ int kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long len) gpc->active = true; write_unlock_irq(&gpc->lock); } - return __kvm_gpc_refresh(gpc, gpa, len); + return __kvm_gpc_refresh(gpc, gpa, uhva, len); +} + +int kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long len) +{ + return __kvm_gpc_activate(gpc, gpa, KVM_HVA_ERR_BAD, len); +} + +int kvm_gpc_activate_hva(struct gfn_to_pfn_cache *gpc, unsigned long uhva, unsigned long len) +{ + return __kvm_gpc_activate(gpc, INVALID_GPA, uhva, len); } void kvm_gpc_deactivate(struct gfn_to_pfn_cache *gpc) -- cgit v1.2.3 From 77bcd9e6231a5297ef417a7d7f734d61c2bcceb6 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 9 Jan 2024 16:39:35 -0800 Subject: KVM: Add dedicated arch hook for querying if vCPU was preempted in-kernel Plumb in a dedicated hook for querying whether or not a vCPU was preempted in-kernel. Unlike literally every other architecture, x86's VMX can check if a vCPU is in kernel context if and only if the vCPU is loaded on the current pCPU. x86's kvm_arch_vcpu_in_kernel() works around the limitation by querying kvm_get_running_vcpu() and redirecting to vcpu->arch.preempted_in_kernel as needed. But that's unnecessary, confusing, and fragile, e.g. x86 has had at least one bug where KVM incorrectly used a stale preempted_in_kernel. No functional change intended. Reviewed-by: Yuan Yao Link: https://lore.kernel.org/r/20240110003938.490206-2-seanjc@google.com Signed-off-by: Sean Christopherson --- arch/x86/kvm/x86.c | 5 +++++ include/linux/kvm_host.h | 1 + virt/kvm/kvm_main.c | 14 +++++++++++++- 3 files changed, 19 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 019320580a84..94346490f407 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -13054,6 +13054,11 @@ bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu) return false; } +bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu) +{ + return kvm_arch_vcpu_in_kernel(vcpu); +} + bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) { if (READ_ONCE(vcpu->arch.pv.pv_unhalted)) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7e7fd25b09b3..28b020404a41 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1505,6 +1505,7 @@ bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu); int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu); bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu); +bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu); int kvm_arch_post_init_vm(struct kvm *kvm); void kvm_arch_pre_destroy_vm(struct kvm *kvm); int kvm_arch_create_vm_debugfs(struct kvm *kvm); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 10bfc88a69f7..9b92858c8b72 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -4042,6 +4042,18 @@ static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu) return false; } +/* + * By default, simply query the target vCPU's current mode when checking if a + * vCPU was preempted in kernel mode. All architectures except x86 (or more + * specifical, except VMX) allow querying whether or not a vCPU is in kernel + * mode even if the vCPU is NOT loaded, i.e. using kvm_arch_vcpu_in_kernel() + * directly for cross-vCPU checks is functionally correct and accurate. + */ +bool __weak kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu) +{ + return kvm_arch_vcpu_in_kernel(vcpu); +} + bool __weak kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu) { return false; @@ -4080,7 +4092,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) continue; if (READ_ONCE(vcpu->preempted) && yield_to_kernel_mode && !kvm_arch_dy_has_pending_interrupt(vcpu) && - !kvm_arch_vcpu_in_kernel(vcpu)) + !kvm_arch_vcpu_preempted_in_kernel(vcpu)) continue; if (!kvm_vcpu_eligible_for_directed_yield(vcpu)) continue; -- cgit v1.2.3 From 284851ee5caef1b42b513752bf1642ce4570bdc1 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Fri, 16 Feb 2024 15:59:41 +0000 Subject: KVM: Get rid of return value from kvm_arch_create_vm_debugfs() The general expectation with debugfs is that any initialization failure is nonfatal. Nevertheless, kvm_arch_create_vm_debugfs() allows implementations to return an error and kvm_create_vm_debugfs() allows that to fail VM creation. Change to a void return to discourage architectures from making debugfs failures fatal for the VM. Seems like everyone already had the right idea, as all implementations already return 0 unconditionally. Acked-by: Marc Zyngier Acked-by: Paolo Bonzini Link: https://lore.kernel.org/r/20240216155941.2029458-1-oliver.upton@linux.dev Signed-off-by: Oliver Upton --- arch/powerpc/kvm/powerpc.c | 3 +-- arch/x86/kvm/debugfs.c | 3 +-- include/linux/kvm_host.h | 2 +- virt/kvm/kvm_main.c | 8 ++------ 4 files changed, 5 insertions(+), 11 deletions(-) (limited to 'include/linux') diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index 23407fbd73c9..d32abe7fe6ab 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -2538,9 +2538,8 @@ void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_ vcpu->kvm->arch.kvm_ops->create_vcpu_debugfs(vcpu, debugfs_dentry); } -int kvm_arch_create_vm_debugfs(struct kvm *kvm) +void kvm_arch_create_vm_debugfs(struct kvm *kvm) { if (kvm->arch.kvm_ops->create_vm_debugfs) kvm->arch.kvm_ops->create_vm_debugfs(kvm); - return 0; } diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c index 95ea1a1f7403..999227fc7c66 100644 --- a/arch/x86/kvm/debugfs.c +++ b/arch/x86/kvm/debugfs.c @@ -189,9 +189,8 @@ static const struct file_operations mmu_rmaps_stat_fops = { .release = kvm_mmu_rmaps_stat_release, }; -int kvm_arch_create_vm_debugfs(struct kvm *kvm) +void kvm_arch_create_vm_debugfs(struct kvm *kvm) { debugfs_create_file("mmu_rmaps_stat", 0644, kvm->debugfs_dentry, kvm, &mmu_rmaps_stat_fops); - return 0; } diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7e7fd25b09b3..9a45f673f687 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1507,7 +1507,7 @@ bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu); bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu); int kvm_arch_post_init_vm(struct kvm *kvm); void kvm_arch_pre_destroy_vm(struct kvm *kvm); -int kvm_arch_create_vm_debugfs(struct kvm *kvm); +void kvm_arch_create_vm_debugfs(struct kvm *kvm); #ifndef __KVM_HAVE_ARCH_VM_ALLOC /* diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 10bfc88a69f7..c681149c382a 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1150,10 +1150,7 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, const char *fdname) &stat_fops_per_vm); } - ret = kvm_arch_create_vm_debugfs(kvm); - if (ret) - goto out_err; - + kvm_arch_create_vm_debugfs(kvm); return 0; out_err: kvm_destroy_vm_debugfs(kvm); @@ -1183,9 +1180,8 @@ void __weak kvm_arch_pre_destroy_vm(struct kvm *kvm) * Cleanup should be automatic done in kvm_destroy_vm_debugfs() recursively, so * a per-arch destroy interface is not needed. */ -int __weak kvm_arch_create_vm_debugfs(struct kvm *kvm) +void __weak kvm_arch_create_vm_debugfs(struct kvm *kvm) { - return 0; } static struct kvm *kvm_create_vm(unsigned long type, const char *fdname) -- cgit v1.2.3 From 5c656fcdd6c60f71fccb07fe7b9d8d7e6c9811ff Mon Sep 17 00:00:00 2001 From: Ankit Agrawal Date: Sat, 24 Feb 2024 20:35:44 +0530 Subject: mm: Introduce new flag to indicate wc safe The VM_ALLOW_ANY_UNCACHED flag is implemented for ARM64, allowing KVM stage 2 device mapping attributes to use NormalNC rather than DEVICE_nGnRE, which allows guest mappings supporting write-combining attributes (WC). ARM does not architecturally guarantee this is safe, and indeed some MMIO regions like the GICv2 VCPU interface can trigger uncontained faults if NormalNC is used. Even worse, the expectation is that there are platforms where even DEVICE_nGnRE can allow uncontained faults in corner cases. Unfortunately existing ARM IP requires platform integration to take responsibility to prevent this. To safely use VFIO in KVM the platform must guarantee full safety in the guest where no action taken against a MMIO mapping can trigger an uncontained failure. The assumption is that most VFIO PCI platforms support this for both mapping types, at least in common flows, based on some expectations of how PCI IP is integrated. This can be enabled more broadly, for instance into vfio-platform drivers, but only after the platform vendor completes auditing for safety. The VMA flag VM_ALLOW_ANY_UNCACHED was found to be the simplest and cleanest way to communicate the information from VFIO to KVM that mapping the region in S2 as NormalNC is safe. KVM consumes it to activate the code that does the S2 mapping as NormalNC. Suggested-by: Catalin Marinas Reviewed-by: Jason Gunthorpe Reviewed-by: Marc Zyngier Acked-by: David Hildenbrand Signed-off-by: Ankit Agrawal Link: https://lore.kernel.org/r/20240224150546.368-3-ankita@nvidia.com Signed-off-by: Oliver Upton --- include/linux/mm.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index f5a97dec5169..59576e56c58b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -391,6 +391,20 @@ extern unsigned int kobjsize(const void *objp); # define VM_UFFD_MINOR VM_NONE #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */ +/* + * This flag is used to connect VFIO to arch specific KVM code. It + * indicates that the memory under this VMA is safe for use with any + * non-cachable memory type inside KVM. Some VFIO devices, on some + * platforms, are thought to be unsafe and can cause machine crashes + * if KVM does not lock down the memory type. + */ +#ifdef CONFIG_64BIT +#define VM_ALLOW_ANY_UNCACHED_BIT 39 +#define VM_ALLOW_ANY_UNCACHED BIT(VM_ALLOW_ANY_UNCACHED_BIT) +#else +#define VM_ALLOW_ANY_UNCACHED VM_NONE +#endif + /* Bits set in the VMA until the stack is in its final location */ #define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ | VM_STACK_EARLY) -- cgit v1.2.3