Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To:     linux-kernel@vger.kernel.org
Cc:     Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        stable@vger.kernel.org, Andy Lutomirski <luto@kernel.org>,
        Thomas Gleixner <tglx@linutronix.de>,
        Rik van Riel <riel@surriel.com>,
        Nadav Amit <nadav.amit@gmail.com>,
        Borislav Petkov <bp@alien8.de>, Jann Horn <jannh@google.com>,
        Peter Zijlstra <peterz@infradead.org>
Subject: [PATCH 4.14 136/165] x86/nmi: Fix NMI uaccess race against CR3 switching
Date:   Mon,  3 Sep 2018 18:57:02 +0200
Message-Id: <20180903165702.368309717@linuxfoundation.org>
In-Reply-To: <20180903165655.003605184@linuxfoundation.org>
References: <20180903165655.003605184@linuxfoundation.org>
User-Agent: quilt/0.65
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

4.14-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Andy Lutomirski <luto@kernel.org>

commit 4012e77a903d114f915fc607d6d2ed54a3d6c9b1 upstream.

A NMI can hit in the middle of context switching or in the middle of
switch_mm_irqs_off().  In either case, CR3 might not match current->mm,
which could cause copy_from_user_nmi() and friends to read the wrong
memory.

Fix it by adding a new nmi_uaccess_okay() helper and checking it in
copy_from_user_nmi() and in __copy_from_user_nmi()'s callers.

Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Rik van Riel <riel@surriel.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jann Horn <jannh@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/dd956eba16646fd0b15c3c0741269dfd84452dac.1535557289.git.luto@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

---
 arch/x86/events/core.c          |    2 +-
 arch/x86/include/asm/tlbflush.h |   40 ++++++++++++++++++++++++++++++++++++++++
 arch/x86/lib/usercopy.c         |    5 +++++
 arch/x86/mm/tlb.c               |    7 +++++++
 4 files changed, 53 insertions(+), 1 deletion(-)

--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2462,7 +2462,7 @@ perf_callchain_user(struct perf_callchai
 
 	perf_callchain_store(entry, regs->ip);
 
-	if (!current->mm)
+	if (!nmi_uaccess_okay())
 		return;
 
 	if (perf_callchain_user32(regs, entry))
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -175,8 +175,16 @@ struct tlb_state {
 	 * are on.  This means that it may not match current->active_mm,
 	 * which will contain the previous user mm when we're in lazy TLB
 	 * mode even if we've already switched back to swapper_pg_dir.
+	 *
+	 * During switch_mm_irqs_off(), loaded_mm will be set to
+	 * LOADED_MM_SWITCHING during the brief interrupts-off window
+	 * when CR3 and loaded_mm would otherwise be inconsistent.  This
+	 * is for nmi_uaccess_okay()'s benefit.
 	 */
 	struct mm_struct *loaded_mm;
+
+#define LOADED_MM_SWITCHING ((struct mm_struct *)1)
+
 	u16 loaded_mm_asid;
 	u16 next_asid;
 	/* last user mm's ctx id */
@@ -246,6 +254,38 @@ struct tlb_state {
 };
 DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate);
 
+/*
+ * Blindly accessing user memory from NMI context can be dangerous
+ * if we're in the middle of switching the current user task or
+ * switching the loaded mm.  It can also be dangerous if we
+ * interrupted some kernel code that was temporarily using a
+ * different mm.
+ */
+static inline bool nmi_uaccess_okay(void)
+{
+	struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
+	struct mm_struct *current_mm = current->mm;
+
+	VM_WARN_ON_ONCE(!loaded_mm);
+
+	/*
+	 * The condition we want to check is
+	 * current_mm->pgd == __va(read_cr3_pa()).  This may be slow, though,
+	 * if we're running in a VM with shadow paging, and nmi_uaccess_okay()
+	 * is supposed to be reasonably fast.
+	 *
+	 * Instead, we check the almost equivalent but somewhat conservative
+	 * condition below, and we rely on the fact that switch_mm_irqs_off()
+	 * sets loaded_mm to LOADED_MM_SWITCHING before writing to CR3.
+	 */
+	if (loaded_mm != current_mm)
+		return false;
+
+	VM_WARN_ON_ONCE(current_mm->pgd != __va(read_cr3_pa()));
+
+	return true;
+}
+
 /* Initialize cr4 shadow for this CPU. */
 static inline void cr4_init_shadow(void)
 {
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -7,6 +7,8 @@
 #include <linux/uaccess.h>
 #include <linux/export.h>
 
+#include <asm/tlbflush.h>
+
 /*
  * We rely on the nested NMI work to allow atomic faults from the NMI path; the
  * nested NMI paths are careful to preserve CR2.
@@ -19,6 +21,9 @@ copy_from_user_nmi(void *to, const void
 	if (__range_not_ok(from, n, TASK_SIZE))
 		return n;
 
+	if (!nmi_uaccess_okay())
+		return n;
+
 	/*
 	 * Even though this function is typically called from NMI/IRQ context
 	 * disable pagefaults so that its behaviour is consistent even when
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -292,6 +292,10 @@ void switch_mm_irqs_off(struct mm_struct
 
 		choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush);
 
+		/* Let nmi_uaccess_okay() know that we're changing CR3. */
+		this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING);
+		barrier();
+
 		if (need_flush) {
 			this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
 			this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
@@ -322,6 +326,9 @@ void switch_mm_irqs_off(struct mm_struct
 		if (next != &init_mm)
 			this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id);
 
+		/* Make sure we write CR3 before loaded_mm. */
+		barrier();
+
 		this_cpu_write(cpu_tlbstate.loaded_mm, next);
 		this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);
 	}