[RFC PATCH 2/6] KVM: guestmem_fd: Make error_remove_page callback to unmap guest memory

From: isaku.yamahata@intel.com
To: kvm@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: isaku.yamahata@intel.com, isaku.yamahata@gmail.com,
	Michael Roth <michael.roth@amd.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	Sean Christopherson <seanjc@google.com>,
	erdemaktas@google.com, Sagi Shahar <sagis@google.com>,
	David Matlack <dmatlack@google.com>,
	Kai Huang <kai.huang@intel.com>,
	Zhi Wang <zhi.wang.linux@gmail.com>,
	chen.bo@intel.com, linux-coco@lists.linux.dev,
	Chao Peng <chao.p.peng@linux.intel.com>,
	Ackerley Tng <ackerleytng@google.com>,
	Vishal Annapurve <vannapurve@google.com>,
	Yuan Yao <yuan.yao@linux.intel.com>,
	Jarkko Sakkinen <jarkko@kernel.org>,
	Xu Yilun <yilun.xu@intel.com>,
	Quentin Perret <qperret@google.com>,
	wei.w.wang@intel.com, Fuad Tabba <tabba@google.com>
Subject: [RFC PATCH 2/6] KVM: guestmem_fd: Make error_remove_page callback to unmap guest memory
Date: Wed, 13 Sep 2023 03:48:51 -0700	[thread overview]
Message-ID: <d6601227769ec82eed95270053ef58e13c2c0a09.1694599703.git.isaku.yamahata@intel.com> (raw)
In-Reply-To: <cover.1694599703.git.isaku.yamahata@intel.com>

From: Isaku Yamahata <isaku.yamahata@intel.com>

Implement error_remove_page inode method for KVM gmem.  Update struct
kvm_gfn_range to indicate unmapping gufs because page is poisoned.

Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
---
 include/linux/kvm_host.h |  2 ++
 virt/kvm/guest_mem.c     | 47 +++++++++++++++++++++++++++-------------
 2 files changed, 34 insertions(+), 15 deletions(-)

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 091bc89ae805..e81a7123c84f 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -266,8 +266,10 @@ struct kvm_gfn_range {
 		pte_t pte;
 		unsigned long attributes;
 		u64 raw;
+		struct page *page;
 	} arg;
 	bool may_block;
+	bool memory_error;
 };
 bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range);
 bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range);
diff --git a/virt/kvm/guest_mem.c b/virt/kvm/guest_mem.c
index 35d8f03e7937..746e683df589 100644
--- a/virt/kvm/guest_mem.c
+++ b/virt/kvm/guest_mem.c
@@ -305,7 +305,7 @@ static int kvm_gmem_error_page(struct address_space *mapping, struct page *page)
 	struct kvm_gmem *gmem;
 	unsigned long index;
 	pgoff_t start, end;
-	gfn_t gfn;
+	bool flush;
 
 	if (!IS_ENABLED(CONFIG_HAVE_GENERIC_PRIVATE_MEM_HANDLE_ERROR))
 		return MF_IGNORED;
@@ -316,26 +316,43 @@ static int kvm_gmem_error_page(struct address_space *mapping, struct page *page)
 	end = start + thp_nr_pages(page);
 
 	list_for_each_entry(gmem, gmem_list, entry) {
+		struct kvm *kvm = gmem->kvm;
+
+		KVM_MMU_LOCK(kvm);
+		kvm_mmu_invalidate_begin(kvm);
+		KVM_MMU_UNLOCK(kvm);
+
+		flush = false;
 		xa_for_each_range(&gmem->bindings, index, slot, start, end - 1) {
-			for (gfn = start; gfn < end; gfn++) {
-				if (WARN_ON_ONCE(gfn < slot->base_gfn ||
-						gfn >= slot->base_gfn + slot->npages))
-					continue;
-
-				/*
-				 * FIXME: Tell userspace that the *private*
-				 * memory encountered an error.
-				 */
-				send_sig_mceerr(BUS_MCEERR_AR,
-						(void __user *)gfn_to_hva_memslot(slot, gfn),
-						PAGE_SHIFT, current);
-			}
+			pgoff_t pgoff;
+
+			if (WARN_ON_ONCE(end < slot->base_gfn ||
+					 start >= slot->base_gfn + slot->npages))
+				continue;
+
+			pgoff = slot->gmem.pgoff;
+			struct kvm_gfn_range gfn_range = {
+				.slot = slot,
+				.start = slot->base_gfn + max(pgoff, start) - pgoff,
+				.end = slot->base_gfn + min(pgoff + slot->npages, end) - pgoff,
+				.arg.page = page,
+				.may_block = true,
+				.memory_error = true,
+			};
+
+			flush |= kvm_mmu_unmap_gfn_range(kvm, &gfn_range);
 		}
+		if (flush)
+			kvm_flush_remote_tlbs(kvm);
+
+		KVM_MMU_LOCK(kvm);
+		kvm_mmu_invalidate_end(kvm);
+		KVM_MMU_UNLOCK(kvm);
 	}
 
 	filemap_invalidate_unlock_shared(mapping);
 
-	return 0;
+	return MF_DELAYED;
 }
 
 static const struct address_space_operations kvm_gmem_aops = {
-- 
2.25.1

