From cf6501689012ef346cc835a38cbebb1e398d0834 Mon Sep 17 00:00:00 2001 From: Andrew Scull Date: Tue, 15 Sep 2020 11:46:39 +0100 Subject: smccc: Define vendor hyp owned service call region Vendor specific hypervisor services have their own region of function identifiers reserved by SMCCC. Extend the list of owners to include this case. Signed-off-by: Andrew Scull Signed-off-by: Marc Zyngier Cc: Sudeep Holla Link: https://lore.kernel.org/r/20200915104643.2543892-16-ascull@google.com --- include/linux/arm-smccc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index 15c706fb0a37..ee286f5de239 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -49,6 +49,7 @@ #define ARM_SMCCC_OWNER_OEM 3 #define ARM_SMCCC_OWNER_STANDARD 4 #define ARM_SMCCC_OWNER_STANDARD_HYP 5 +#define ARM_SMCCC_OWNER_VENDOR_HYP 6 #define ARM_SMCCC_OWNER_TRUSTED_APP 48 #define ARM_SMCCC_OWNER_TRUSTED_APP_END 49 #define ARM_SMCCC_OWNER_TRUSTED_OS 50 -- cgit v1.2.3 From 0794a974d74dc777a212a3c58dd236f507360348 Mon Sep 17 00:00:00 2001 From: Andrew Scull Date: Tue, 15 Sep 2020 11:46:40 +0100 Subject: smccc: Use separate variables for args and results Using the same register-bound variable for both arguments and results means these values share a type. That type must allow the arguments to be assigned to it and must also be assignable to the unsigned long fields of struct arm_smccc_res. This restriction on types causes compiler warnings when the argument cannot be implicitly assigned to an unsigned long, for example the pointers that are used in the KVM hyp interface. By separating the arguments and results into their own variables, the type constraint is lifted allowing the arguments to avoid the need for any type conversion. Signed-off-by: Andrew Scull Signed-off-by: Marc Zyngier Cc: Sudeep Holla Link: https://lore.kernel.org/r/20200915104643.2543892-17-ascull@google.com --- include/linux/arm-smccc.h | 73 +++++++++++++++++++---------------------------- 1 file changed, 29 insertions(+), 44 deletions(-) (limited to 'include/linux') diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h index ee286f5de239..885c9ffc835c 100644 --- a/include/linux/arm-smccc.h +++ b/include/linux/arm-smccc.h @@ -228,87 +228,67 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, #define __count_args(...) \ ___count_args(__VA_ARGS__, 7, 6, 5, 4, 3, 2, 1, 0) -#define __constraint_write_0 \ - "+r" (r0), "=&r" (r1), "=&r" (r2), "=&r" (r3) -#define __constraint_write_1 \ - "+r" (r0), "+r" (r1), "=&r" (r2), "=&r" (r3) -#define __constraint_write_2 \ - "+r" (r0), "+r" (r1), "+r" (r2), "=&r" (r3) -#define __constraint_write_3 \ - "+r" (r0), "+r" (r1), "+r" (r2), "+r" (r3) -#define __constraint_write_4 __constraint_write_3 -#define __constraint_write_5 __constraint_write_4 -#define __constraint_write_6 __constraint_write_5 -#define __constraint_write_7 __constraint_write_6 - -#define __constraint_read_0 -#define __constraint_read_1 -#define __constraint_read_2 -#define __constraint_read_3 -#define __constraint_read_4 "r" (r4) -#define __constraint_read_5 __constraint_read_4, "r" (r5) -#define __constraint_read_6 __constraint_read_5, "r" (r6) -#define __constraint_read_7 __constraint_read_6, "r" (r7) +#define __constraint_read_0 "r" (arg0) +#define __constraint_read_1 __constraint_read_0, "r" (arg1) +#define __constraint_read_2 __constraint_read_1, "r" (arg2) +#define __constraint_read_3 __constraint_read_2, "r" (arg3) +#define __constraint_read_4 __constraint_read_3, "r" (arg4) +#define __constraint_read_5 __constraint_read_4, "r" (arg5) +#define __constraint_read_6 __constraint_read_5, "r" (arg6) +#define __constraint_read_7 __constraint_read_6, "r" (arg7) #define __declare_arg_0(a0, res) \ struct arm_smccc_res *___res = res; \ - register unsigned long r0 asm("r0") = (u32)a0; \ - register unsigned long r1 asm("r1"); \ - register unsigned long r2 asm("r2"); \ - register unsigned long r3 asm("r3") + register unsigned long arg0 asm("r0") = (u32)a0 #define __declare_arg_1(a0, a1, res) \ typeof(a1) __a1 = a1; \ struct arm_smccc_res *___res = res; \ - register unsigned long r0 asm("r0") = (u32)a0; \ - register unsigned long r1 asm("r1") = __a1; \ - register unsigned long r2 asm("r2"); \ - register unsigned long r3 asm("r3") + register unsigned long arg0 asm("r0") = (u32)a0; \ + register typeof(a1) arg1 asm("r1") = __a1 #define __declare_arg_2(a0, a1, a2, res) \ typeof(a1) __a1 = a1; \ typeof(a2) __a2 = a2; \ struct arm_smccc_res *___res = res; \ - register unsigned long r0 asm("r0") = (u32)a0; \ - register unsigned long r1 asm("r1") = __a1; \ - register unsigned long r2 asm("r2") = __a2; \ - register unsigned long r3 asm("r3") + register unsigned long arg0 asm("r0") = (u32)a0; \ + register typeof(a1) arg1 asm("r1") = __a1; \ + register typeof(a2) arg2 asm("r2") = __a2 #define __declare_arg_3(a0, a1, a2, a3, res) \ typeof(a1) __a1 = a1; \ typeof(a2) __a2 = a2; \ typeof(a3) __a3 = a3; \ struct arm_smccc_res *___res = res; \ - register unsigned long r0 asm("r0") = (u32)a0; \ - register unsigned long r1 asm("r1") = __a1; \ - register unsigned long r2 asm("r2") = __a2; \ - register unsigned long r3 asm("r3") = __a3 + register unsigned long arg0 asm("r0") = (u32)a0; \ + register typeof(a1) arg1 asm("r1") = __a1; \ + register typeof(a2) arg2 asm("r2") = __a2; \ + register typeof(a3) arg3 asm("r3") = __a3 #define __declare_arg_4(a0, a1, a2, a3, a4, res) \ typeof(a4) __a4 = a4; \ __declare_arg_3(a0, a1, a2, a3, res); \ - register unsigned long r4 asm("r4") = __a4 + register typeof(a4) arg4 asm("r4") = __a4 #define __declare_arg_5(a0, a1, a2, a3, a4, a5, res) \ typeof(a5) __a5 = a5; \ __declare_arg_4(a0, a1, a2, a3, a4, res); \ - register unsigned long r5 asm("r5") = __a5 + register typeof(a5) arg5 asm("r5") = __a5 #define __declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res) \ typeof(a6) __a6 = a6; \ __declare_arg_5(a0, a1, a2, a3, a4, a5, res); \ - register unsigned long r6 asm("r6") = __a6 + register typeof(a6) arg6 asm("r6") = __a6 #define __declare_arg_7(a0, a1, a2, a3, a4, a5, a6, a7, res) \ typeof(a7) __a7 = a7; \ __declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res); \ - register unsigned long r7 asm("r7") = __a7 + register typeof(a7) arg7 asm("r7") = __a7 #define ___declare_args(count, ...) __declare_arg_ ## count(__VA_ARGS__) #define __declare_args(count, ...) ___declare_args(count, __VA_ARGS__) #define ___constraints(count) \ - : __constraint_write_ ## count \ : __constraint_read_ ## count \ : "memory" #define __constraints(count) ___constraints(count) @@ -320,8 +300,13 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, */ #define __arm_smccc_1_1(inst, ...) \ do { \ + register unsigned long r0 asm("r0"); \ + register unsigned long r1 asm("r1"); \ + register unsigned long r2 asm("r2"); \ + register unsigned long r3 asm("r3"); \ __declare_args(__count_args(__VA_ARGS__), __VA_ARGS__); \ - asm volatile(inst "\n" \ + asm volatile(inst "\n" : \ + "=r" (r0), "=r" (r1), "=r" (r2), "=r" (r3) \ __constraints(__count_args(__VA_ARGS__))); \ if (___res) \ *___res = (typeof(*___res)){r0, r1, r2, r3}; \ @@ -367,7 +352,7 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1, #define __fail_smccc_1_1(...) \ do { \ __declare_args(__count_args(__VA_ARGS__), __VA_ARGS__); \ - asm ("" __constraints(__count_args(__VA_ARGS__))); \ + asm ("" : __constraints(__count_args(__VA_ARGS__))); \ if (___res) \ ___res->a0 = SMCCC_RET_NOT_SUPPORTED; \ } while (0) -- cgit v1.2.3 From 9e9eb226b91225fc199bbafc06f3cd70bfce0100 Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Wed, 14 Oct 2020 11:26:46 -0700 Subject: KVM: Cache as_id in kvm_memory_slot Cache the address space ID just like the slot ID. It will be used in order to fill in the dirty ring entries. Suggested-by: Paolo Bonzini Suggested-by: Sean Christopherson Reviewed-by: Sean Christopherson Signed-off-by: Peter Xu Message-Id: <20201014182700.2888246-7-bgardon@google.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 1 + virt/kvm/kvm_main.c | 6 ++++++ 2 files changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 05e3c2fb3ef7..c6f45687ba89 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -346,6 +346,7 @@ struct kvm_memory_slot { unsigned long userspace_addr; u32 flags; short id; + u16 as_id; }; static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 68edd25dcb11..2e8539213125 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1247,6 +1247,11 @@ static int kvm_delete_memslot(struct kvm *kvm, memset(&new, 0, sizeof(new)); new.id = old->id; + /* + * This is only for debugging purpose; it should never be referenced + * for a removed memslot. + */ + new.as_id = as_id; r = kvm_set_memslot(kvm, mem, old, &new, as_id, KVM_MR_DELETE); if (r) @@ -1313,6 +1318,7 @@ int __kvm_set_memory_region(struct kvm *kvm, if (!mem->memory_size) return kvm_delete_memslot(kvm, mem, &old, as_id); + new.as_id = as_id; new.id = id; new.base_gfn = mem->guest_phys_addr >> PAGE_SHIFT; new.npages = mem->memory_size >> PAGE_SHIFT; -- cgit v1.2.3 From a6a0b05da9f37ff56faa6b8351ed6e0b55032460 Mon Sep 17 00:00:00 2001 From: Ben Gardon Date: Wed, 14 Oct 2020 11:26:55 -0700 Subject: kvm: x86/mmu: Support dirty logging for the TDP MMU Dirty logging is a key feature of the KVM MMU and must be supported by the TDP MMU. Add support for both the write protection and PML dirty logging modes. Tested by running kvm-unit-tests and KVM selftests on an Intel Haswell machine. This series introduced no new failures. This series can be viewed in Gerrit at: https://linux-review.googlesource.com/c/virt/kvm/kvm/+/2538 Signed-off-by: Ben Gardon Message-Id: <20201014182700.2888246-16-bgardon@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 14 +++ arch/x86/kvm/mmu/tdp_iter.h | 7 +- arch/x86/kvm/mmu/tdp_mmu.c | 299 +++++++++++++++++++++++++++++++++++++++++++- arch/x86/kvm/mmu/tdp_mmu.h | 10 ++ include/linux/kvm_host.h | 1 + virt/kvm/kvm_main.c | 6 +- 6 files changed, 328 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 41f0354c7489..0c64643819b9 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1223,6 +1223,9 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, { struct kvm_rmap_head *rmap_head; + if (kvm->arch.tdp_mmu_enabled) + kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot, + slot->base_gfn + gfn_offset, mask, true); while (mask) { rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), PG_LEVEL_4K, slot); @@ -1249,6 +1252,9 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, { struct kvm_rmap_head *rmap_head; + if (kvm->arch.tdp_mmu_enabled) + kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot, + slot->base_gfn + gfn_offset, mask, false); while (mask) { rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), PG_LEVEL_4K, slot); @@ -5473,6 +5479,8 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, spin_lock(&kvm->mmu_lock); flush = slot_handle_level(kvm, memslot, slot_rmap_write_protect, start_level, KVM_MAX_HUGEPAGE_LEVEL, false); + if (kvm->arch.tdp_mmu_enabled) + flush |= kvm_tdp_mmu_wrprot_slot(kvm, memslot, PG_LEVEL_4K); spin_unlock(&kvm->mmu_lock); /* @@ -5561,6 +5569,8 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, spin_lock(&kvm->mmu_lock); flush = slot_handle_leaf(kvm, memslot, __rmap_clear_dirty, false); + if (kvm->arch.tdp_mmu_enabled) + flush |= kvm_tdp_mmu_clear_dirty_slot(kvm, memslot); spin_unlock(&kvm->mmu_lock); /* @@ -5582,6 +5592,8 @@ void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm, spin_lock(&kvm->mmu_lock); flush = slot_handle_large_level(kvm, memslot, slot_rmap_write_protect, false); + if (kvm->arch.tdp_mmu_enabled) + flush |= kvm_tdp_mmu_wrprot_slot(kvm, memslot, PG_LEVEL_2M); spin_unlock(&kvm->mmu_lock); if (flush) @@ -5596,6 +5608,8 @@ void kvm_mmu_slot_set_dirty(struct kvm *kvm, spin_lock(&kvm->mmu_lock); flush = slot_handle_all_level(kvm, memslot, __rmap_set_dirty, false); + if (kvm->arch.tdp_mmu_enabled) + flush |= kvm_tdp_mmu_slot_set_dirty(kvm, memslot); spin_unlock(&kvm->mmu_lock); if (flush) diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h index 884ed2c70bfe..47170d0dc98e 100644 --- a/arch/x86/kvm/mmu/tdp_iter.h +++ b/arch/x86/kvm/mmu/tdp_iter.h @@ -41,11 +41,14 @@ struct tdp_iter { * Iterates over every SPTE mapping the GFN range [start, end) in a * preorder traversal. */ -#define for_each_tdp_pte(iter, root, root_level, start, end) \ - for (tdp_iter_start(&iter, root, root_level, PG_LEVEL_4K, start); \ +#define for_each_tdp_pte_min_level(iter, root, root_level, min_level, start, end) \ + for (tdp_iter_start(&iter, root, root_level, min_level, start); \ iter.valid && iter.gfn < end; \ tdp_iter_next(&iter)) +#define for_each_tdp_pte(iter, root, root_level, start, end) \ + for_each_tdp_pte_min_level(iter, root, root_level, PG_LEVEL_4K, start, end) + u64 *spte_to_child_pt(u64 pte, int level); void tdp_iter_start(struct tdp_iter *iter, u64 *root_pt, int root_level, diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 64e640cfcff9..7181b4ab54d0 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -161,6 +161,24 @@ static void handle_changed_spte_acc_track(u64 old_spte, u64 new_spte, int level) kvm_set_pfn_accessed(spte_to_pfn(old_spte)); } +static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn, + u64 old_spte, u64 new_spte, int level) +{ + bool pfn_changed; + struct kvm_memory_slot *slot; + + if (level > PG_LEVEL_4K) + return; + + pfn_changed = spte_to_pfn(old_spte) != spte_to_pfn(new_spte); + + if ((!is_writable_pte(old_spte) || pfn_changed) && + is_writable_pte(new_spte)) { + slot = __gfn_to_memslot(__kvm_memslots(kvm, as_id), gfn); + mark_page_dirty_in_slot(slot, gfn); + } +} + /** * handle_changed_spte - handle bookkeeping associated with an SPTE change * @kvm: kvm instance @@ -273,10 +291,13 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, { __handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level); handle_changed_spte_acc_track(old_spte, new_spte, level); + handle_changed_spte_dirty_log(kvm, as_id, gfn, old_spte, + new_spte, level); } static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, - u64 new_spte, bool record_acc_track) + u64 new_spte, bool record_acc_track, + bool record_dirty_log) { u64 *root_pt = tdp_iter_root_pt(iter); struct kvm_mmu_page *root = sptep_to_sp(root_pt); @@ -289,19 +310,30 @@ static inline void __tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, if (record_acc_track) handle_changed_spte_acc_track(iter->old_spte, new_spte, iter->level); + if (record_dirty_log) + handle_changed_spte_dirty_log(kvm, as_id, iter->gfn, + iter->old_spte, new_spte, + iter->level); } static inline void tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, u64 new_spte) { - __tdp_mmu_set_spte(kvm, iter, new_spte, true); + __tdp_mmu_set_spte(kvm, iter, new_spte, true, true); } static inline void tdp_mmu_set_spte_no_acc_track(struct kvm *kvm, struct tdp_iter *iter, u64 new_spte) { - __tdp_mmu_set_spte(kvm, iter, new_spte, false); + __tdp_mmu_set_spte(kvm, iter, new_spte, false, true); +} + +static inline void tdp_mmu_set_spte_no_dirty_log(struct kvm *kvm, + struct tdp_iter *iter, + u64 new_spte) +{ + __tdp_mmu_set_spte(kvm, iter, new_spte, true, false); } #define tdp_root_for_each_pte(_iter, _root, _start, _end) \ @@ -334,6 +366,14 @@ static bool tdp_mmu_iter_flush_cond_resched(struct kvm *kvm, struct tdp_iter *it } } +static void tdp_mmu_iter_cond_resched(struct kvm *kvm, struct tdp_iter *iter) +{ + if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { + cond_resched_lock(&kvm->mmu_lock); + tdp_iter_refresh_walk(iter); + } +} + /* * Tears down the mappings for the range of gfns, [start, end), and frees the * non-root pages mapping GFNs strictly within that range. Returns true if @@ -638,6 +678,7 @@ static int age_gfn_range(struct kvm *kvm, struct kvm_memory_slot *slot, new_spte = mark_spte_for_access_track(new_spte); } + new_spte &= ~shadow_dirty_mask; tdp_mmu_set_spte_no_acc_track(kvm, &iter, new_spte); young = 1; @@ -727,3 +768,255 @@ int kvm_tdp_mmu_set_spte_hva(struct kvm *kvm, unsigned long address, set_tdp_spte); } +/* + * Remove write access from all the SPTEs mapping GFNs [start, end). If + * skip_4k is set, SPTEs that map 4k pages, will not be write-protected. + * Returns true if an SPTE has been changed and the TLBs need to be flushed. + */ +static bool wrprot_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, + gfn_t start, gfn_t end, int min_level) +{ + struct tdp_iter iter; + u64 new_spte; + bool spte_set = false; + + BUG_ON(min_level > KVM_MAX_HUGEPAGE_LEVEL); + + for_each_tdp_pte_min_level(iter, root->spt, root->role.level, + min_level, start, end) { + if (!is_shadow_present_pte(iter.old_spte) || + !is_last_spte(iter.old_spte, iter.level)) + continue; + + new_spte = iter.old_spte & ~PT_WRITABLE_MASK; + + tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte); + spte_set = true; + + tdp_mmu_iter_cond_resched(kvm, &iter); + } + return spte_set; +} + +/* + * Remove write access from all the SPTEs mapping GFNs in the memslot. Will + * only affect leaf SPTEs down to min_level. + * Returns true if an SPTE has been changed and the TLBs need to be flushed. + */ +bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm, struct kvm_memory_slot *slot, + int min_level) +{ + struct kvm_mmu_page *root; + int root_as_id; + bool spte_set = false; + + for_each_tdp_mmu_root(kvm, root) { + root_as_id = kvm_mmu_page_as_id(root); + if (root_as_id != slot->as_id) + continue; + + /* + * Take a reference on the root so that it cannot be freed if + * this thread releases the MMU lock and yields in this loop. + */ + kvm_mmu_get_root(kvm, root); + + spte_set |= wrprot_gfn_range(kvm, root, slot->base_gfn, + slot->base_gfn + slot->npages, min_level); + + kvm_mmu_put_root(kvm, root); + } + + return spte_set; +} + +/* + * Clear the dirty status of all the SPTEs mapping GFNs in the memslot. If + * AD bits are enabled, this will involve clearing the dirty bit on each SPTE. + * If AD bits are not enabled, this will require clearing the writable bit on + * each SPTE. Returns true if an SPTE has been changed and the TLBs need to + * be flushed. + */ +static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, + gfn_t start, gfn_t end) +{ + struct tdp_iter iter; + u64 new_spte; + bool spte_set = false; + + tdp_root_for_each_leaf_pte(iter, root, start, end) { + if (spte_ad_need_write_protect(iter.old_spte)) { + if (is_writable_pte(iter.old_spte)) + new_spte = iter.old_spte & ~PT_WRITABLE_MASK; + else + continue; + } else { + if (iter.old_spte & shadow_dirty_mask) + new_spte = iter.old_spte & ~shadow_dirty_mask; + else + continue; + } + + tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte); + spte_set = true; + + tdp_mmu_iter_cond_resched(kvm, &iter); + } + return spte_set; +} + +/* + * Clear the dirty status of all the SPTEs mapping GFNs in the memslot. If + * AD bits are enabled, this will involve clearing the dirty bit on each SPTE. + * If AD bits are not enabled, this will require clearing the writable bit on + * each SPTE. Returns true if an SPTE has been changed and the TLBs need to + * be flushed. + */ +bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, struct kvm_memory_slot *slot) +{ + struct kvm_mmu_page *root; + int root_as_id; + bool spte_set = false; + + for_each_tdp_mmu_root(kvm, root) { + root_as_id = kvm_mmu_page_as_id(root); + if (root_as_id != slot->as_id) + continue; + + /* + * Take a reference on the root so that it cannot be freed if + * this thread releases the MMU lock and yields in this loop. + */ + kvm_mmu_get_root(kvm, root); + + spte_set |= clear_dirty_gfn_range(kvm, root, slot->base_gfn, + slot->base_gfn + slot->npages); + + kvm_mmu_put_root(kvm, root); + } + + return spte_set; +} + +/* + * Clears the dirty status of all the 4k SPTEs mapping GFNs for which a bit is + * set in mask, starting at gfn. The given memslot is expected to contain all + * the GFNs represented by set bits in the mask. If AD bits are enabled, + * clearing the dirty status will involve clearing the dirty bit on each SPTE + * or, if AD bits are not enabled, clearing the writable bit on each SPTE. + */ +static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, + gfn_t gfn, unsigned long mask, bool wrprot) +{ + struct tdp_iter iter; + u64 new_spte; + + tdp_root_for_each_leaf_pte(iter, root, gfn + __ffs(mask), + gfn + BITS_PER_LONG) { + if (!mask) + break; + + if (iter.level > PG_LEVEL_4K || + !(mask & (1UL << (iter.gfn - gfn)))) + continue; + + if (wrprot || spte_ad_need_write_protect(iter.old_spte)) { + if (is_writable_pte(iter.old_spte)) + new_spte = iter.old_spte & ~PT_WRITABLE_MASK; + else + continue; + } else { + if (iter.old_spte & shadow_dirty_mask) + new_spte = iter.old_spte & ~shadow_dirty_mask; + else + continue; + } + + tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte); + + mask &= ~(1UL << (iter.gfn - gfn)); + } +} + +/* + * Clears the dirty status of all the 4k SPTEs mapping GFNs for which a bit is + * set in mask, starting at gfn. The given memslot is expected to contain all + * the GFNs represented by set bits in the mask. If AD bits are enabled, + * clearing the dirty status will involve clearing the dirty bit on each SPTE + * or, if AD bits are not enabled, clearing the writable bit on each SPTE. + */ +void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, + struct kvm_memory_slot *slot, + gfn_t gfn, unsigned long mask, + bool wrprot) +{ + struct kvm_mmu_page *root; + int root_as_id; + + lockdep_assert_held(&kvm->mmu_lock); + for_each_tdp_mmu_root(kvm, root) { + root_as_id = kvm_mmu_page_as_id(root); + if (root_as_id != slot->as_id) + continue; + + clear_dirty_pt_masked(kvm, root, gfn, mask, wrprot); + } +} + +/* + * Set the dirty status of all the SPTEs mapping GFNs in the memslot. This is + * only used for PML, and so will involve setting the dirty bit on each SPTE. + * Returns true if an SPTE has been changed and the TLBs need to be flushed. + */ +static bool set_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, + gfn_t start, gfn_t end) +{ + struct tdp_iter iter; + u64 new_spte; + bool spte_set = false; + + tdp_root_for_each_pte(iter, root, start, end) { + if (!is_shadow_present_pte(iter.old_spte)) + continue; + + new_spte = iter.old_spte | shadow_dirty_mask; + + tdp_mmu_set_spte(kvm, &iter, new_spte); + spte_set = true; + + tdp_mmu_iter_cond_resched(kvm, &iter); + } + + return spte_set; +} + +/* + * Set the dirty status of all the SPTEs mapping GFNs in the memslot. This is + * only used for PML, and so will involve setting the dirty bit on each SPTE. + * Returns true if an SPTE has been changed and the TLBs need to be flushed. + */ +bool kvm_tdp_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *slot) +{ + struct kvm_mmu_page *root; + int root_as_id; + bool spte_set = false; + + for_each_tdp_mmu_root(kvm, root) { + root_as_id = kvm_mmu_page_as_id(root); + if (root_as_id != slot->as_id) + continue; + + /* + * Take a reference on the root so that it cannot be freed if + * this thread releases the MMU lock and yields in this loop. + */ + kvm_mmu_get_root(kvm, root); + + spte_set |= set_dirty_gfn_range(kvm, root, slot->base_gfn, + slot->base_gfn + slot->npages); + + kvm_mmu_put_root(kvm, root); + } + return spte_set; +} + diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index aeee3ce7b3f4..ece66f10d85f 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -28,4 +28,14 @@ int kvm_tdp_mmu_test_age_hva(struct kvm *kvm, unsigned long hva); int kvm_tdp_mmu_set_spte_hva(struct kvm *kvm, unsigned long address, pte_t *host_ptep); + +bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm, struct kvm_memory_slot *slot, + int min_level); +bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, + struct kvm_memory_slot *slot); +void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, + struct kvm_memory_slot *slot, + gfn_t gfn, unsigned long mask, + bool wrprot); +bool kvm_tdp_mmu_slot_set_dirty(struct kvm *kvm, struct kvm_memory_slot *slot); #endif /* __KVM_X86_MMU_TDP_MMU_H */ diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c6f45687ba89..7f2e2a09ebbd 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -798,6 +798,7 @@ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn); bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn); +void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn); void mark_page_dirty(struct kvm *kvm, gfn_t gfn); struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 2e8539213125..2541a17ff1c4 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -143,8 +143,6 @@ 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); - __visible bool kvm_rebooting; EXPORT_SYMBOL_GPL(kvm_rebooting); @@ -2645,8 +2643,7 @@ 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, - gfn_t gfn) +void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn) { if (memslot && memslot->dirty_bitmap) { unsigned long rel_gfn = gfn - memslot->base_gfn; @@ -2654,6 +2651,7 @@ static void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, set_bit_le(rel_gfn, memslot->dirty_bitmap); } } +EXPORT_SYMBOL_GPL(mark_page_dirty_in_slot); void mark_page_dirty(struct kvm *kvm, gfn_t gfn) { -- cgit v1.2.3