Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Andrei Vagin <avagin@gmail.com>
To:     Vincenzo Frascino <vincenzo.frascino@arm.com>,
        Catalin Marinas <catalin.marinas@arm.com>,
        Will Deacon <will@kernel.org>
Cc:     linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org,
        Mark Rutland <mark.rutland@arm.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Andrei Vagin <avagin@gmail.com>,
        Dmitry Safonov <dima@arista.com>
Subject: [PATCH 4/6] arm64/vdso: Handle faults on timens page
Date:   Wed, 15 Apr 2020 22:26:16 -0700
Message-Id: <20200416052618.804515-5-avagin@gmail.com>
In-Reply-To: <20200416052618.804515-1-avagin@gmail.com>
References: <20200416052618.804515-1-avagin@gmail.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

If a task belongs to a time namespace then the VVAR page which contains
the system wide VDSO data is replaced with a namespace specific page
which has the same layout as the VVAR page.

Reviewed-by: Vincenzo Frascino <vincenzo.frascino@arm.com>
Signed-off-by: Andrei Vagin <avagin@gmail.com>
---
 arch/arm64/kernel/vdso.c | 57 +++++++++++++++++++++++++++++++++++++---
 1 file changed, 53 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index b3e7ce24e59b..fb32c6f76078 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -18,6 +18,7 @@
 #include <linux/sched.h>
 #include <linux/signal.h>
 #include <linux/slab.h>
+#include <linux/time_namespace.h>
 #include <linux/timekeeper_internal.h>
 #include <linux/vmalloc.h>
 #include <vdso/datapage.h>
@@ -175,15 +176,63 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns)
 	up_write(&mm->mmap_sem);
 	return 0;
 }
+
+static struct page *find_timens_vvar_page(struct vm_area_struct *vma)
+{
+	if (likely(vma->vm_mm == current->mm))
+		return current->nsproxy->time_ns->vvar_page;
+
+	/*
+	 * VM_PFNMAP | VM_IO protect .fault() handler from being called
+	 * through interfaces like /proc/$pid/mem or
+	 * process_vm_{readv,writev}() as long as there's no .access()
+	 * in special_mapping_vmops().
+	 * For more details check_vma_flags() and __access_remote_vm()
+	 */
+
+	WARN(1, "vvar_page accessed remotely");
+
+	return NULL;
+}
+#else
+static inline struct page *find_timens_vvar_page(struct vm_area_struct *vma)
+{
+	return NULL;
+}
 #endif
 
 static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
 			     struct vm_area_struct *vma, struct vm_fault *vmf)
 {
-	if (vmf->pgoff == 0)
-		return vmf_insert_pfn(vma, vmf->address,
-				sym_to_pfn(vdso_data));
-	return VM_FAULT_SIGBUS;
+	struct page *timens_page = find_timens_vvar_page(vma);
+	unsigned long pfn;
+
+	switch (vmf->pgoff) {
+	case VVAR_DATA_PAGE_OFFSET:
+		if (timens_page)
+			pfn = page_to_pfn(timens_page);
+		else
+			pfn = sym_to_pfn(vdso_data);
+		break;
+#ifdef CONFIG_TIME_NS
+	case VVAR_TIMENS_PAGE_OFFSET:
+		/*
+		 * If a task belongs to a time namespace then a namespace
+		 * specific VVAR is mapped with the VVAR_DATA_PAGE_OFFSET and
+		 * the real VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET
+		 * offset.
+		 * See also the comment near timens_setup_vdso_data().
+		 */
+		if (!timens_page)
+			return VM_FAULT_SIGBUS;
+		pfn = sym_to_pfn(vdso_data);
+		break;
+#endif /* CONFIG_TIME_NS */
+	default:
+		return VM_FAULT_SIGBUS;
+	}
+
+	return vmf_insert_pfn(vma, vmf->address, pfn);
 }
 
 static int __setup_additional_pages(enum arch_vdso_type arch_index,
-- 
2.24.1