x86/nmi: Fix NMI uaccess race against CR3 switching

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 <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Reviewed-by: Rik van Riel <[email protected]>
Cc: Nadav Amit <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Jann Horn <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: [email protected]
Link: https://lkml.kernel.org/r/dd956eba16646fd0b15c3c0741269dfd84452dac.1535557289.git.luto@kernel.org

arch/x86/events/core.c

@@ -2465,7 +2465,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 
 	perf_callchain_store(entry, regs->ip);
 
-	if (!current->mm)
+	if (!nmi_uaccess_okay())
 		return;
 
 	if (perf_callchain_user32(regs, entry))

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)
 {

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 __user *from, unsigned long n)
 	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

arch/x86/mm/tlb.c

@@ -305,6 +305,10 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 
 		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);
@@ -335,6 +339,9 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 		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);
 	}