All of lore.kernel.org
 help / color / mirror / Atom feed
From: Will Deacon <will@kernel.org>
To: kvmarm@lists.cs.columbia.edu
Cc: Marc Zyngier <maz@kernel.org>,
	kernel-team@android.com, kvm@vger.kernel.org,
	Andy Lutomirski <luto@amacapital.net>,
	linux-arm-kernel@lists.infradead.org,
	Michael Roth <michael.roth@amd.com>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Chao Peng <chao.p.peng@linux.intel.com>,
	Will Deacon <will@kernel.org>
Subject: [PATCH v2 07/24] KVM: arm64: Implement do_donate() helper for donating memory
Date: Thu, 30 Jun 2022 14:57:30 +0100	[thread overview]
Message-ID: <20220630135747.26983-8-will@kernel.org> (raw)
In-Reply-To: <20220630135747.26983-1-will@kernel.org>

From: Quentin Perret <qperret@google.com>

Transferring ownership information of a memory region from one component
to another can be achieved using a "donate" operation, which results
in the previous owner losing access to the underlying pages entirely.

Implement a do_donate() helper, along the same lines as do_{un,}share,
and provide this functionality for the host-{to,from}-hyp cases as this
will later be used to donate/reclaim memory pages to store VM metadata
at EL2.

Signed-off-by: Quentin Perret <qperret@google.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kvm/hyp/include/nvhe/mem_protect.h |   2 +
 arch/arm64/kvm/hyp/nvhe/mem_protect.c         | 239 ++++++++++++++++++
 2 files changed, 241 insertions(+)

diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
index f5705a1e972f..c87b19b2d468 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
@@ -60,6 +60,8 @@ enum pkvm_component_id {
 int __pkvm_prot_finalize(void);
 int __pkvm_host_share_hyp(u64 pfn);
 int __pkvm_host_unshare_hyp(u64 pfn);
+int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages);
+int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages);
 
 bool addr_is_memory(phys_addr_t phys);
 int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot);
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 10390b8dc841..f475d554c9fd 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -395,6 +395,9 @@ struct pkvm_mem_transition {
 				/* Address in the completer's address space */
 				u64	completer_addr;
 			} host;
+			struct {
+				u64	completer_addr;
+			} hyp;
 		};
 	} initiator;
 
@@ -408,6 +411,10 @@ struct pkvm_mem_share {
 	const enum kvm_pgtable_prot		completer_prot;
 };
 
+struct pkvm_mem_donation {
+	const struct pkvm_mem_transition	tx;
+};
+
 struct check_walk_data {
 	enum pkvm_page_state	desired;
 	enum pkvm_page_state	(*get_page_state)(kvm_pte_t pte);
@@ -507,6 +514,46 @@ static int host_initiate_unshare(u64 *completer_addr,
 	return __host_set_page_state_range(addr, size, PKVM_PAGE_OWNED);
 }
 
+static int host_initiate_donation(u64 *completer_addr,
+				  const struct pkvm_mem_transition *tx)
+{
+	u8 owner_id = tx->completer.id;
+	u64 size = tx->nr_pages * PAGE_SIZE;
+
+	*completer_addr = tx->initiator.host.completer_addr;
+	return host_stage2_set_owner_locked(tx->initiator.addr, size, owner_id);
+}
+
+static bool __host_ack_skip_pgtable_check(const struct pkvm_mem_transition *tx)
+{
+	return !(IS_ENABLED(CONFIG_NVHE_EL2_DEBUG) ||
+		 tx->initiator.id != PKVM_ID_HYP);
+}
+
+static int __host_ack_transition(u64 addr, const struct pkvm_mem_transition *tx,
+				 enum pkvm_page_state state)
+{
+	u64 size = tx->nr_pages * PAGE_SIZE;
+
+	if (__host_ack_skip_pgtable_check(tx))
+		return 0;
+
+	return __host_check_page_state_range(addr, size, state);
+}
+
+static int host_ack_donation(u64 addr, const struct pkvm_mem_transition *tx)
+{
+	return __host_ack_transition(addr, tx, PKVM_NOPAGE);
+}
+
+static int host_complete_donation(u64 addr, const struct pkvm_mem_transition *tx)
+{
+	u64 size = tx->nr_pages * PAGE_SIZE;
+	u8 host_id = tx->completer.id;
+
+	return host_stage2_set_owner_locked(addr, size, host_id);
+}
+
 static enum pkvm_page_state hyp_get_page_state(kvm_pte_t pte)
 {
 	if (!kvm_pte_valid(pte))
@@ -527,6 +574,27 @@ static int __hyp_check_page_state_range(u64 addr, u64 size,
 	return check_page_state_range(&pkvm_pgtable, addr, size, &d);
 }
 
+static int hyp_request_donation(u64 *completer_addr,
+				const struct pkvm_mem_transition *tx)
+{
+	u64 size = tx->nr_pages * PAGE_SIZE;
+	u64 addr = tx->initiator.addr;
+
+	*completer_addr = tx->initiator.hyp.completer_addr;
+	return __hyp_check_page_state_range(addr, size, PKVM_PAGE_OWNED);
+}
+
+static int hyp_initiate_donation(u64 *completer_addr,
+				 const struct pkvm_mem_transition *tx)
+{
+	u64 size = tx->nr_pages * PAGE_SIZE;
+	int ret;
+
+	*completer_addr = tx->initiator.hyp.completer_addr;
+	ret = kvm_pgtable_hyp_unmap(&pkvm_pgtable, tx->initiator.addr, size);
+	return (ret != size) ? -EFAULT : 0;
+}
+
 static bool __hyp_ack_skip_pgtable_check(const struct pkvm_mem_transition *tx)
 {
 	return !(IS_ENABLED(CONFIG_NVHE_EL2_DEBUG) ||
@@ -558,6 +626,16 @@ static int hyp_ack_unshare(u64 addr, const struct pkvm_mem_transition *tx)
 					    PKVM_PAGE_SHARED_BORROWED);
 }
 
+static int hyp_ack_donation(u64 addr, const struct pkvm_mem_transition *tx)
+{
+	u64 size = tx->nr_pages * PAGE_SIZE;
+
+	if (__hyp_ack_skip_pgtable_check(tx))
+		return 0;
+
+	return __hyp_check_page_state_range(addr, size, PKVM_NOPAGE);
+}
+
 static int hyp_complete_share(u64 addr, const struct pkvm_mem_transition *tx,
 			      enum kvm_pgtable_prot perms)
 {
@@ -576,6 +654,15 @@ static int hyp_complete_unshare(u64 addr, const struct pkvm_mem_transition *tx)
 	return (ret != size) ? -EFAULT : 0;
 }
 
+static int hyp_complete_donation(u64 addr,
+				 const struct pkvm_mem_transition *tx)
+{
+	void *start = (void *)addr, *end = start + (tx->nr_pages * PAGE_SIZE);
+	enum kvm_pgtable_prot prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_OWNED);
+
+	return pkvm_create_mappings_locked(start, end, prot);
+}
+
 static int check_share(struct pkvm_mem_share *share)
 {
 	const struct pkvm_mem_transition *tx = &share->tx;
@@ -728,6 +815,94 @@ static int do_unshare(struct pkvm_mem_share *share)
 	return WARN_ON(__do_unshare(share));
 }
 
+static int check_donation(struct pkvm_mem_donation *donation)
+{
+	const struct pkvm_mem_transition *tx = &donation->tx;
+	u64 completer_addr;
+	int ret;
+
+	switch (tx->initiator.id) {
+	case PKVM_ID_HOST:
+		ret = host_request_owned_transition(&completer_addr, tx);
+		break;
+	case PKVM_ID_HYP:
+		ret = hyp_request_donation(&completer_addr, tx);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	if (ret)
+		return ret;
+
+	switch (tx->completer.id){
+	case PKVM_ID_HOST:
+		ret = host_ack_donation(completer_addr, tx);
+		break;
+	case PKVM_ID_HYP:
+		ret = hyp_ack_donation(completer_addr, tx);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static int __do_donate(struct pkvm_mem_donation *donation)
+{
+	const struct pkvm_mem_transition *tx = &donation->tx;
+	u64 completer_addr;
+	int ret;
+
+	switch (tx->initiator.id) {
+	case PKVM_ID_HOST:
+		ret = host_initiate_donation(&completer_addr, tx);
+		break;
+	case PKVM_ID_HYP:
+		ret = hyp_initiate_donation(&completer_addr, tx);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	if (ret)
+		return ret;
+
+	switch (tx->completer.id){
+	case PKVM_ID_HOST:
+		ret = host_complete_donation(completer_addr, tx);
+		break;
+	case PKVM_ID_HYP:
+		ret = hyp_complete_donation(completer_addr, tx);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+/*
+ * do_donate():
+ *
+ * The page owner transfers ownership to another component, losing access
+ * as a consequence.
+ *
+ * Initiator: OWNED	=> NOPAGE
+ * Completer: NOPAGE	=> OWNED
+ */
+static int do_donate(struct pkvm_mem_donation *donation)
+{
+	int ret;
+
+	ret = check_donation(donation);
+	if (ret)
+		return ret;
+
+	return WARN_ON(__do_donate(donation));
+}
+
 int __pkvm_host_share_hyp(u64 pfn)
 {
 	int ret;
@@ -793,3 +968,67 @@ int __pkvm_host_unshare_hyp(u64 pfn)
 
 	return ret;
 }
+
+int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages)
+{
+	int ret;
+	u64 host_addr = hyp_pfn_to_phys(pfn);
+	u64 hyp_addr = (u64)__hyp_va(host_addr);
+	struct pkvm_mem_donation donation = {
+		.tx	= {
+			.nr_pages	= nr_pages,
+			.initiator	= {
+				.id	= PKVM_ID_HOST,
+				.addr	= host_addr,
+				.host	= {
+					.completer_addr = hyp_addr,
+				},
+			},
+			.completer	= {
+				.id	= PKVM_ID_HYP,
+			},
+		},
+	};
+
+	host_lock_component();
+	hyp_lock_component();
+
+	ret = do_donate(&donation);
+
+	hyp_unlock_component();
+	host_unlock_component();
+
+	return ret;
+}
+
+int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages)
+{
+	int ret;
+	u64 host_addr = hyp_pfn_to_phys(pfn);
+	u64 hyp_addr = (u64)__hyp_va(host_addr);
+	struct pkvm_mem_donation donation = {
+		.tx	= {
+			.nr_pages	= nr_pages,
+			.initiator	= {
+				.id	= PKVM_ID_HYP,
+				.addr	= hyp_addr,
+				.hyp	= {
+					.completer_addr = host_addr,
+				},
+			},
+			.completer	= {
+				.id	= PKVM_ID_HOST,
+			},
+		},
+	};
+
+	host_lock_component();
+	hyp_lock_component();
+
+	ret = do_donate(&donation);
+
+	hyp_unlock_component();
+	host_unlock_component();
+
+	return ret;
+}
-- 
2.37.0.rc0.161.g10f37bed90-goog

_______________________________________________
kvmarm mailing list
kvmarm@lists.cs.columbia.edu
https://lists.cs.columbia.edu/mailman/listinfo/kvmarm

WARNING: multiple messages have this Message-ID (diff)
From: Will Deacon <will@kernel.org>
To: kvmarm@lists.cs.columbia.edu
Cc: Will Deacon <will@kernel.org>, Ard Biesheuvel <ardb@kernel.org>,
	Sean Christopherson <seanjc@google.com>,
	Alexandru Elisei <alexandru.elisei@arm.com>,
	Andy Lutomirski <luto@amacapital.net>,
	Catalin Marinas <catalin.marinas@arm.com>,
	James Morse <james.morse@arm.com>,
	Chao Peng <chao.p.peng@linux.intel.com>,
	Quentin Perret <qperret@google.com>,
	Suzuki K Poulose <suzuki.poulose@arm.com>,
	Michael Roth <michael.roth@amd.com>,
	Mark Rutland <mark.rutland@arm.com>,
	Fuad Tabba <tabba@google.com>,
	Oliver Upton <oliver.upton@linux.dev>,
	Marc Zyngier <maz@kernel.org>,
	kernel-team@android.com, kvm@vger.kernel.org,
	linux-arm-kernel@lists.infradead.org
Subject: [PATCH v2 07/24] KVM: arm64: Implement do_donate() helper for donating memory
Date: Thu, 30 Jun 2022 14:57:30 +0100	[thread overview]
Message-ID: <20220630135747.26983-8-will@kernel.org> (raw)
In-Reply-To: <20220630135747.26983-1-will@kernel.org>

From: Quentin Perret <qperret@google.com>

Transferring ownership information of a memory region from one component
to another can be achieved using a "donate" operation, which results
in the previous owner losing access to the underlying pages entirely.

Implement a do_donate() helper, along the same lines as do_{un,}share,
and provide this functionality for the host-{to,from}-hyp cases as this
will later be used to donate/reclaim memory pages to store VM metadata
at EL2.

Signed-off-by: Quentin Perret <qperret@google.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kvm/hyp/include/nvhe/mem_protect.h |   2 +
 arch/arm64/kvm/hyp/nvhe/mem_protect.c         | 239 ++++++++++++++++++
 2 files changed, 241 insertions(+)

diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
index f5705a1e972f..c87b19b2d468 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
@@ -60,6 +60,8 @@ enum pkvm_component_id {
 int __pkvm_prot_finalize(void);
 int __pkvm_host_share_hyp(u64 pfn);
 int __pkvm_host_unshare_hyp(u64 pfn);
+int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages);
+int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages);
 
 bool addr_is_memory(phys_addr_t phys);
 int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot);
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 10390b8dc841..f475d554c9fd 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -395,6 +395,9 @@ struct pkvm_mem_transition {
 				/* Address in the completer's address space */
 				u64	completer_addr;
 			} host;
+			struct {
+				u64	completer_addr;
+			} hyp;
 		};
 	} initiator;
 
@@ -408,6 +411,10 @@ struct pkvm_mem_share {
 	const enum kvm_pgtable_prot		completer_prot;
 };
 
+struct pkvm_mem_donation {
+	const struct pkvm_mem_transition	tx;
+};
+
 struct check_walk_data {
 	enum pkvm_page_state	desired;
 	enum pkvm_page_state	(*get_page_state)(kvm_pte_t pte);
@@ -507,6 +514,46 @@ static int host_initiate_unshare(u64 *completer_addr,
 	return __host_set_page_state_range(addr, size, PKVM_PAGE_OWNED);
 }
 
+static int host_initiate_donation(u64 *completer_addr,
+				  const struct pkvm_mem_transition *tx)
+{
+	u8 owner_id = tx->completer.id;
+	u64 size = tx->nr_pages * PAGE_SIZE;
+
+	*completer_addr = tx->initiator.host.completer_addr;
+	return host_stage2_set_owner_locked(tx->initiator.addr, size, owner_id);
+}
+
+static bool __host_ack_skip_pgtable_check(const struct pkvm_mem_transition *tx)
+{
+	return !(IS_ENABLED(CONFIG_NVHE_EL2_DEBUG) ||
+		 tx->initiator.id != PKVM_ID_HYP);
+}
+
+static int __host_ack_transition(u64 addr, const struct pkvm_mem_transition *tx,
+				 enum pkvm_page_state state)
+{
+	u64 size = tx->nr_pages * PAGE_SIZE;
+
+	if (__host_ack_skip_pgtable_check(tx))
+		return 0;
+
+	return __host_check_page_state_range(addr, size, state);
+}
+
+static int host_ack_donation(u64 addr, const struct pkvm_mem_transition *tx)
+{
+	return __host_ack_transition(addr, tx, PKVM_NOPAGE);
+}
+
+static int host_complete_donation(u64 addr, const struct pkvm_mem_transition *tx)
+{
+	u64 size = tx->nr_pages * PAGE_SIZE;
+	u8 host_id = tx->completer.id;
+
+	return host_stage2_set_owner_locked(addr, size, host_id);
+}
+
 static enum pkvm_page_state hyp_get_page_state(kvm_pte_t pte)
 {
 	if (!kvm_pte_valid(pte))
@@ -527,6 +574,27 @@ static int __hyp_check_page_state_range(u64 addr, u64 size,
 	return check_page_state_range(&pkvm_pgtable, addr, size, &d);
 }
 
+static int hyp_request_donation(u64 *completer_addr,
+				const struct pkvm_mem_transition *tx)
+{
+	u64 size = tx->nr_pages * PAGE_SIZE;
+	u64 addr = tx->initiator.addr;
+
+	*completer_addr = tx->initiator.hyp.completer_addr;
+	return __hyp_check_page_state_range(addr, size, PKVM_PAGE_OWNED);
+}
+
+static int hyp_initiate_donation(u64 *completer_addr,
+				 const struct pkvm_mem_transition *tx)
+{
+	u64 size = tx->nr_pages * PAGE_SIZE;
+	int ret;
+
+	*completer_addr = tx->initiator.hyp.completer_addr;
+	ret = kvm_pgtable_hyp_unmap(&pkvm_pgtable, tx->initiator.addr, size);
+	return (ret != size) ? -EFAULT : 0;
+}
+
 static bool __hyp_ack_skip_pgtable_check(const struct pkvm_mem_transition *tx)
 {
 	return !(IS_ENABLED(CONFIG_NVHE_EL2_DEBUG) ||
@@ -558,6 +626,16 @@ static int hyp_ack_unshare(u64 addr, const struct pkvm_mem_transition *tx)
 					    PKVM_PAGE_SHARED_BORROWED);
 }
 
+static int hyp_ack_donation(u64 addr, const struct pkvm_mem_transition *tx)
+{
+	u64 size = tx->nr_pages * PAGE_SIZE;
+
+	if (__hyp_ack_skip_pgtable_check(tx))
+		return 0;
+
+	return __hyp_check_page_state_range(addr, size, PKVM_NOPAGE);
+}
+
 static int hyp_complete_share(u64 addr, const struct pkvm_mem_transition *tx,
 			      enum kvm_pgtable_prot perms)
 {
@@ -576,6 +654,15 @@ static int hyp_complete_unshare(u64 addr, const struct pkvm_mem_transition *tx)
 	return (ret != size) ? -EFAULT : 0;
 }
 
+static int hyp_complete_donation(u64 addr,
+				 const struct pkvm_mem_transition *tx)
+{
+	void *start = (void *)addr, *end = start + (tx->nr_pages * PAGE_SIZE);
+	enum kvm_pgtable_prot prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_OWNED);
+
+	return pkvm_create_mappings_locked(start, end, prot);
+}
+
 static int check_share(struct pkvm_mem_share *share)
 {
 	const struct pkvm_mem_transition *tx = &share->tx;
@@ -728,6 +815,94 @@ static int do_unshare(struct pkvm_mem_share *share)
 	return WARN_ON(__do_unshare(share));
 }
 
+static int check_donation(struct pkvm_mem_donation *donation)
+{
+	const struct pkvm_mem_transition *tx = &donation->tx;
+	u64 completer_addr;
+	int ret;
+
+	switch (tx->initiator.id) {
+	case PKVM_ID_HOST:
+		ret = host_request_owned_transition(&completer_addr, tx);
+		break;
+	case PKVM_ID_HYP:
+		ret = hyp_request_donation(&completer_addr, tx);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	if (ret)
+		return ret;
+
+	switch (tx->completer.id){
+	case PKVM_ID_HOST:
+		ret = host_ack_donation(completer_addr, tx);
+		break;
+	case PKVM_ID_HYP:
+		ret = hyp_ack_donation(completer_addr, tx);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static int __do_donate(struct pkvm_mem_donation *donation)
+{
+	const struct pkvm_mem_transition *tx = &donation->tx;
+	u64 completer_addr;
+	int ret;
+
+	switch (tx->initiator.id) {
+	case PKVM_ID_HOST:
+		ret = host_initiate_donation(&completer_addr, tx);
+		break;
+	case PKVM_ID_HYP:
+		ret = hyp_initiate_donation(&completer_addr, tx);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	if (ret)
+		return ret;
+
+	switch (tx->completer.id){
+	case PKVM_ID_HOST:
+		ret = host_complete_donation(completer_addr, tx);
+		break;
+	case PKVM_ID_HYP:
+		ret = hyp_complete_donation(completer_addr, tx);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+/*
+ * do_donate():
+ *
+ * The page owner transfers ownership to another component, losing access
+ * as a consequence.
+ *
+ * Initiator: OWNED	=> NOPAGE
+ * Completer: NOPAGE	=> OWNED
+ */
+static int do_donate(struct pkvm_mem_donation *donation)
+{
+	int ret;
+
+	ret = check_donation(donation);
+	if (ret)
+		return ret;
+
+	return WARN_ON(__do_donate(donation));
+}
+
 int __pkvm_host_share_hyp(u64 pfn)
 {
 	int ret;
@@ -793,3 +968,67 @@ int __pkvm_host_unshare_hyp(u64 pfn)
 
 	return ret;
 }
+
+int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages)
+{
+	int ret;
+	u64 host_addr = hyp_pfn_to_phys(pfn);
+	u64 hyp_addr = (u64)__hyp_va(host_addr);
+	struct pkvm_mem_donation donation = {
+		.tx	= {
+			.nr_pages	= nr_pages,
+			.initiator	= {
+				.id	= PKVM_ID_HOST,
+				.addr	= host_addr,
+				.host	= {
+					.completer_addr = hyp_addr,
+				},
+			},
+			.completer	= {
+				.id	= PKVM_ID_HYP,
+			},
+		},
+	};
+
+	host_lock_component();
+	hyp_lock_component();
+
+	ret = do_donate(&donation);
+
+	hyp_unlock_component();
+	host_unlock_component();
+
+	return ret;
+}
+
+int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages)
+{
+	int ret;
+	u64 host_addr = hyp_pfn_to_phys(pfn);
+	u64 hyp_addr = (u64)__hyp_va(host_addr);
+	struct pkvm_mem_donation donation = {
+		.tx	= {
+			.nr_pages	= nr_pages,
+			.initiator	= {
+				.id	= PKVM_ID_HYP,
+				.addr	= hyp_addr,
+				.hyp	= {
+					.completer_addr = host_addr,
+				},
+			},
+			.completer	= {
+				.id	= PKVM_ID_HOST,
+			},
+		},
+	};
+
+	host_lock_component();
+	hyp_lock_component();
+
+	ret = do_donate(&donation);
+
+	hyp_unlock_component();
+	host_unlock_component();
+
+	return ret;
+}
-- 
2.37.0.rc0.161.g10f37bed90-goog


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

WARNING: multiple messages have this Message-ID (diff)
From: Will Deacon <will@kernel.org>
To: kvmarm@lists.cs.columbia.edu
Cc: Will Deacon <will@kernel.org>, Ard Biesheuvel <ardb@kernel.org>,
	Sean Christopherson <seanjc@google.com>,
	Alexandru Elisei <alexandru.elisei@arm.com>,
	Andy Lutomirski <luto@amacapital.net>,
	Catalin Marinas <catalin.marinas@arm.com>,
	James Morse <james.morse@arm.com>,
	Chao Peng <chao.p.peng@linux.intel.com>,
	Quentin Perret <qperret@google.com>,
	Suzuki K Poulose <suzuki.poulose@arm.com>,
	Michael Roth <michael.roth@amd.com>,
	Mark Rutland <mark.rutland@arm.com>,
	Fuad Tabba <tabba@google.com>,
	Oliver Upton <oliver.upton@linux.dev>,
	Marc Zyngier <maz@kernel.org>,
	kernel-team@android.com, kvm@vger.kernel.org,
	linux-arm-kernel@lists.infradead.org
Subject: [PATCH v2 07/24] KVM: arm64: Implement do_donate() helper for donating memory
Date: Thu, 30 Jun 2022 14:57:30 +0100	[thread overview]
Message-ID: <20220630135747.26983-8-will@kernel.org> (raw)
In-Reply-To: <20220630135747.26983-1-will@kernel.org>

From: Quentin Perret <qperret@google.com>

Transferring ownership information of a memory region from one component
to another can be achieved using a "donate" operation, which results
in the previous owner losing access to the underlying pages entirely.

Implement a do_donate() helper, along the same lines as do_{un,}share,
and provide this functionality for the host-{to,from}-hyp cases as this
will later be used to donate/reclaim memory pages to store VM metadata
at EL2.

Signed-off-by: Quentin Perret <qperret@google.com>
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/kvm/hyp/include/nvhe/mem_protect.h |   2 +
 arch/arm64/kvm/hyp/nvhe/mem_protect.c         | 239 ++++++++++++++++++
 2 files changed, 241 insertions(+)

diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
index f5705a1e972f..c87b19b2d468 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
@@ -60,6 +60,8 @@ enum pkvm_component_id {
 int __pkvm_prot_finalize(void);
 int __pkvm_host_share_hyp(u64 pfn);
 int __pkvm_host_unshare_hyp(u64 pfn);
+int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages);
+int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages);
 
 bool addr_is_memory(phys_addr_t phys);
 int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot);
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index 10390b8dc841..f475d554c9fd 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -395,6 +395,9 @@ struct pkvm_mem_transition {
 				/* Address in the completer's address space */
 				u64	completer_addr;
 			} host;
+			struct {
+				u64	completer_addr;
+			} hyp;
 		};
 	} initiator;
 
@@ -408,6 +411,10 @@ struct pkvm_mem_share {
 	const enum kvm_pgtable_prot		completer_prot;
 };
 
+struct pkvm_mem_donation {
+	const struct pkvm_mem_transition	tx;
+};
+
 struct check_walk_data {
 	enum pkvm_page_state	desired;
 	enum pkvm_page_state	(*get_page_state)(kvm_pte_t pte);
@@ -507,6 +514,46 @@ static int host_initiate_unshare(u64 *completer_addr,
 	return __host_set_page_state_range(addr, size, PKVM_PAGE_OWNED);
 }
 
+static int host_initiate_donation(u64 *completer_addr,
+				  const struct pkvm_mem_transition *tx)
+{
+	u8 owner_id = tx->completer.id;
+	u64 size = tx->nr_pages * PAGE_SIZE;
+
+	*completer_addr = tx->initiator.host.completer_addr;
+	return host_stage2_set_owner_locked(tx->initiator.addr, size, owner_id);
+}
+
+static bool __host_ack_skip_pgtable_check(const struct pkvm_mem_transition *tx)
+{
+	return !(IS_ENABLED(CONFIG_NVHE_EL2_DEBUG) ||
+		 tx->initiator.id != PKVM_ID_HYP);
+}
+
+static int __host_ack_transition(u64 addr, const struct pkvm_mem_transition *tx,
+				 enum pkvm_page_state state)
+{
+	u64 size = tx->nr_pages * PAGE_SIZE;
+
+	if (__host_ack_skip_pgtable_check(tx))
+		return 0;
+
+	return __host_check_page_state_range(addr, size, state);
+}
+
+static int host_ack_donation(u64 addr, const struct pkvm_mem_transition *tx)
+{
+	return __host_ack_transition(addr, tx, PKVM_NOPAGE);
+}
+
+static int host_complete_donation(u64 addr, const struct pkvm_mem_transition *tx)
+{
+	u64 size = tx->nr_pages * PAGE_SIZE;
+	u8 host_id = tx->completer.id;
+
+	return host_stage2_set_owner_locked(addr, size, host_id);
+}
+
 static enum pkvm_page_state hyp_get_page_state(kvm_pte_t pte)
 {
 	if (!kvm_pte_valid(pte))
@@ -527,6 +574,27 @@ static int __hyp_check_page_state_range(u64 addr, u64 size,
 	return check_page_state_range(&pkvm_pgtable, addr, size, &d);
 }
 
+static int hyp_request_donation(u64 *completer_addr,
+				const struct pkvm_mem_transition *tx)
+{
+	u64 size = tx->nr_pages * PAGE_SIZE;
+	u64 addr = tx->initiator.addr;
+
+	*completer_addr = tx->initiator.hyp.completer_addr;
+	return __hyp_check_page_state_range(addr, size, PKVM_PAGE_OWNED);
+}
+
+static int hyp_initiate_donation(u64 *completer_addr,
+				 const struct pkvm_mem_transition *tx)
+{
+	u64 size = tx->nr_pages * PAGE_SIZE;
+	int ret;
+
+	*completer_addr = tx->initiator.hyp.completer_addr;
+	ret = kvm_pgtable_hyp_unmap(&pkvm_pgtable, tx->initiator.addr, size);
+	return (ret != size) ? -EFAULT : 0;
+}
+
 static bool __hyp_ack_skip_pgtable_check(const struct pkvm_mem_transition *tx)
 {
 	return !(IS_ENABLED(CONFIG_NVHE_EL2_DEBUG) ||
@@ -558,6 +626,16 @@ static int hyp_ack_unshare(u64 addr, const struct pkvm_mem_transition *tx)
 					    PKVM_PAGE_SHARED_BORROWED);
 }
 
+static int hyp_ack_donation(u64 addr, const struct pkvm_mem_transition *tx)
+{
+	u64 size = tx->nr_pages * PAGE_SIZE;
+
+	if (__hyp_ack_skip_pgtable_check(tx))
+		return 0;
+
+	return __hyp_check_page_state_range(addr, size, PKVM_NOPAGE);
+}
+
 static int hyp_complete_share(u64 addr, const struct pkvm_mem_transition *tx,
 			      enum kvm_pgtable_prot perms)
 {
@@ -576,6 +654,15 @@ static int hyp_complete_unshare(u64 addr, const struct pkvm_mem_transition *tx)
 	return (ret != size) ? -EFAULT : 0;
 }
 
+static int hyp_complete_donation(u64 addr,
+				 const struct pkvm_mem_transition *tx)
+{
+	void *start = (void *)addr, *end = start + (tx->nr_pages * PAGE_SIZE);
+	enum kvm_pgtable_prot prot = pkvm_mkstate(PAGE_HYP, PKVM_PAGE_OWNED);
+
+	return pkvm_create_mappings_locked(start, end, prot);
+}
+
 static int check_share(struct pkvm_mem_share *share)
 {
 	const struct pkvm_mem_transition *tx = &share->tx;
@@ -728,6 +815,94 @@ static int do_unshare(struct pkvm_mem_share *share)
 	return WARN_ON(__do_unshare(share));
 }
 
+static int check_donation(struct pkvm_mem_donation *donation)
+{
+	const struct pkvm_mem_transition *tx = &donation->tx;
+	u64 completer_addr;
+	int ret;
+
+	switch (tx->initiator.id) {
+	case PKVM_ID_HOST:
+		ret = host_request_owned_transition(&completer_addr, tx);
+		break;
+	case PKVM_ID_HYP:
+		ret = hyp_request_donation(&completer_addr, tx);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	if (ret)
+		return ret;
+
+	switch (tx->completer.id){
+	case PKVM_ID_HOST:
+		ret = host_ack_donation(completer_addr, tx);
+		break;
+	case PKVM_ID_HYP:
+		ret = hyp_ack_donation(completer_addr, tx);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+static int __do_donate(struct pkvm_mem_donation *donation)
+{
+	const struct pkvm_mem_transition *tx = &donation->tx;
+	u64 completer_addr;
+	int ret;
+
+	switch (tx->initiator.id) {
+	case PKVM_ID_HOST:
+		ret = host_initiate_donation(&completer_addr, tx);
+		break;
+	case PKVM_ID_HYP:
+		ret = hyp_initiate_donation(&completer_addr, tx);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	if (ret)
+		return ret;
+
+	switch (tx->completer.id){
+	case PKVM_ID_HOST:
+		ret = host_complete_donation(completer_addr, tx);
+		break;
+	case PKVM_ID_HYP:
+		ret = hyp_complete_donation(completer_addr, tx);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+/*
+ * do_donate():
+ *
+ * The page owner transfers ownership to another component, losing access
+ * as a consequence.
+ *
+ * Initiator: OWNED	=> NOPAGE
+ * Completer: NOPAGE	=> OWNED
+ */
+static int do_donate(struct pkvm_mem_donation *donation)
+{
+	int ret;
+
+	ret = check_donation(donation);
+	if (ret)
+		return ret;
+
+	return WARN_ON(__do_donate(donation));
+}
+
 int __pkvm_host_share_hyp(u64 pfn)
 {
 	int ret;
@@ -793,3 +968,67 @@ int __pkvm_host_unshare_hyp(u64 pfn)
 
 	return ret;
 }
+
+int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages)
+{
+	int ret;
+	u64 host_addr = hyp_pfn_to_phys(pfn);
+	u64 hyp_addr = (u64)__hyp_va(host_addr);
+	struct pkvm_mem_donation donation = {
+		.tx	= {
+			.nr_pages	= nr_pages,
+			.initiator	= {
+				.id	= PKVM_ID_HOST,
+				.addr	= host_addr,
+				.host	= {
+					.completer_addr = hyp_addr,
+				},
+			},
+			.completer	= {
+				.id	= PKVM_ID_HYP,
+			},
+		},
+	};
+
+	host_lock_component();
+	hyp_lock_component();
+
+	ret = do_donate(&donation);
+
+	hyp_unlock_component();
+	host_unlock_component();
+
+	return ret;
+}
+
+int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages)
+{
+	int ret;
+	u64 host_addr = hyp_pfn_to_phys(pfn);
+	u64 hyp_addr = (u64)__hyp_va(host_addr);
+	struct pkvm_mem_donation donation = {
+		.tx	= {
+			.nr_pages	= nr_pages,
+			.initiator	= {
+				.id	= PKVM_ID_HYP,
+				.addr	= hyp_addr,
+				.hyp	= {
+					.completer_addr = host_addr,
+				},
+			},
+			.completer	= {
+				.id	= PKVM_ID_HOST,
+			},
+		},
+	};
+
+	host_lock_component();
+	hyp_lock_component();
+
+	ret = do_donate(&donation);
+
+	hyp_unlock_component();
+	host_unlock_component();
+
+	return ret;
+}
-- 
2.37.0.rc0.161.g10f37bed90-goog


  parent reply	other threads:[~2022-06-30 13:58 UTC|newest]

Thread overview: 135+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-06-30 13:57 [PATCH v2 00/24] KVM: arm64: Introduce pKVM shadow state at EL2 Will Deacon
2022-06-30 13:57 ` Will Deacon
2022-06-30 13:57 ` Will Deacon
2022-06-30 13:57 ` [PATCH v2 01/24] KVM: arm64: Move hyp refcount manipulation helpers Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57 ` [PATCH v2 02/24] KVM: arm64: Allow non-coalescable pages in a hyp_pool Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57 ` [PATCH v2 03/24] KVM: arm64: Add flags to struct hyp_page Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-07-18 10:54   ` Vincent Donnefort
2022-07-18 10:54     ` Vincent Donnefort
2022-07-18 10:54     ` Vincent Donnefort
2022-07-18 10:57     ` Vincent Donnefort
2022-07-18 10:57       ` Vincent Donnefort
2022-07-18 10:57       ` Vincent Donnefort
2022-06-30 13:57 ` [PATCH v2 04/24] KVM: arm64: Back hyp_vmemmap for all of memory Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57 ` [PATCH v2 05/24] KVM: arm64: Make hyp stage-1 refcnt correct on the whole range Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57 ` [PATCH v2 06/24] KVM: arm64: Unify identifiers used to distinguish host and hypervisor Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-07-20 15:11   ` Oliver Upton
2022-07-20 15:11     ` Oliver Upton
2022-07-20 15:11     ` Oliver Upton
2022-07-20 18:14     ` Will Deacon
2022-07-20 18:14       ` Will Deacon
2022-07-20 18:14       ` Will Deacon
2022-07-29 19:28       ` Oliver Upton
2022-07-29 19:28         ` Oliver Upton
2022-07-29 19:28         ` Oliver Upton
2022-06-30 13:57 ` Will Deacon [this message]
2022-06-30 13:57   ` [PATCH v2 07/24] KVM: arm64: Implement do_donate() helper for donating memory Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57 ` [PATCH v2 08/24] KVM: arm64: Prevent the donation of no-map pages Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57 ` [PATCH v2 09/24] KVM: arm64: Add helpers to pin memory shared with hyp Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57 ` [PATCH v2 10/24] KVM: arm64: Include asm/kvm_mmu.h in nvhe/mem_protect.h Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57 ` [PATCH v2 11/24] KVM: arm64: Add hyp_spinlock_t static initializer Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57 ` [PATCH v2 12/24] KVM: arm64: Introduce shadow VM state at EL2 Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-07-18 18:40   ` Vincent Donnefort
2022-07-18 18:40     ` Vincent Donnefort
2022-07-18 18:40     ` Vincent Donnefort
2022-07-19  9:41     ` Marc Zyngier
2022-07-19  9:41       ` Marc Zyngier
2022-07-19  9:41       ` Marc Zyngier
2022-07-20 18:20     ` Will Deacon
2022-07-20 18:20       ` Will Deacon
2022-07-20 18:20       ` Will Deacon
2022-06-30 13:57 ` [PATCH v2 13/24] KVM: arm64: Instantiate VM shadow data from EL1 Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57 ` [PATCH v2 14/24] KVM: arm64: Add pcpu fixmap infrastructure at EL2 Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-07-19 13:30   ` Vincent Donnefort
2022-07-19 13:30     ` Vincent Donnefort
2022-07-19 13:30     ` Vincent Donnefort
2022-07-19 14:09     ` Quentin Perret
2022-07-19 14:09       ` Quentin Perret
2022-07-19 14:09       ` Quentin Perret
2022-07-19 14:10       ` Quentin Perret
2022-07-19 14:10         ` Quentin Perret
2022-07-19 14:10         ` Quentin Perret
2022-06-30 13:57 ` [PATCH v2 15/24] KVM: arm64: Initialise hyp symbols regardless of pKVM Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57 ` [PATCH v2 16/24] KVM: arm64: Provide I-cache invalidation by VA at EL2 Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57 ` [PATCH v2 17/24] KVM: arm64: Add generic hyp_memcache helpers Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57 ` [PATCH v2 18/24] KVM: arm64: Instantiate guest stage-2 page-tables at EL2 Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-07-19 13:32   ` Vincent Donnefort
2022-07-19 13:32     ` Vincent Donnefort
2022-07-19 13:32     ` Vincent Donnefort
2022-07-20 18:26     ` Will Deacon
2022-07-20 18:26       ` Will Deacon
2022-07-20 18:26       ` Will Deacon
2022-06-30 13:57 ` [PATCH v2 19/24] KVM: arm64: Return guest memory from EL2 via dedicated teardown memcache Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57 ` [PATCH v2 20/24] KVM: arm64: Unmap kvm_arm_hyp_percpu_base from the host Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57 ` [PATCH v2 21/24] KVM: arm64: Maintain a copy of 'kvm_arm_vmid_bits' at EL2 Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57 ` [PATCH v2 22/24] KVM: arm64: Explicitly map kvm_vgic_global_state " Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57 ` [PATCH v2 23/24] KVM: arm64: Don't map host sections in pkvm Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57 ` [RFC PATCH v2 24/24] KVM: arm64: Use the shadow vCPU structure in handle___kvm_vcpu_run() Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-06-30 13:57   ` Will Deacon
2022-07-06 19:17 ` [PATCH v2 00/24] KVM: arm64: Introduce pKVM shadow state at EL2 Sean Christopherson
2022-07-06 19:17   ` Sean Christopherson
2022-07-06 19:17   ` Sean Christopherson
2022-07-08 16:23   ` Will Deacon
2022-07-08 16:23     ` Will Deacon
2022-07-08 16:23     ` Will Deacon
2022-07-19 16:11     ` Sean Christopherson
2022-07-19 16:11       ` Sean Christopherson
2022-07-19 16:11       ` Sean Christopherson
2022-07-20  9:25       ` Marc Zyngier
2022-07-20  9:25         ` Marc Zyngier
2022-07-20  9:25         ` Marc Zyngier
2022-07-20 18:48       ` Will Deacon
2022-07-20 18:48         ` Will Deacon
2022-07-20 18:48         ` Will Deacon
2022-07-20 21:17         ` Sean Christopherson
2022-07-20 21:17           ` Sean Christopherson
2022-07-20 21:17           ` Sean Christopherson
2022-07-19 14:24 ` Vincent Donnefort
2022-07-19 14:24   ` Vincent Donnefort
2022-07-19 14:24   ` Vincent Donnefort

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220630135747.26983-8-will@kernel.org \
    --to=will@kernel.org \
    --cc=catalin.marinas@arm.com \
    --cc=chao.p.peng@linux.intel.com \
    --cc=kernel-team@android.com \
    --cc=kvm@vger.kernel.org \
    --cc=kvmarm@lists.cs.columbia.edu \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=luto@amacapital.net \
    --cc=maz@kernel.org \
    --cc=michael.roth@amd.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.