x86/mce: Recover from poison found while copying from user space

Existing kernel code can only recover from a machine check on code that
is tagged in the exception table with a fault handling recovery path.

Add two new fields in the task structure to pass information from
machine check handler to the "task_work" that is queued to run before
the task returns to user mode:

+ mce_vaddr: will be initialized to the user virtual address of the fault
  in the case where the fault occurred in the kernel copying data from
  a user address.  This is so that kill_me_maybe() can provide that
  information to the user SIGBUS handler.

+ mce_kflags: copy of the struct mce.kflags needed by kill_me_maybe()
  to determine if mce_vaddr is applicable to this error.

Add code to recover from a machine check while copying data from user
space to the kernel. Action for this case is the same as if the user
touched the poison directly; unmap the page and send a SIGBUS to the task.

Use a new helper function to share common code between the "fault
in user mode" case and the "fault while copying from user" case.

New code paths will be activated by the next patch which sets
MCE_IN_KERNEL_COPYIN.

Suggested-by: Borislav Petkov <bp@alien8.de>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20201006210910.21062-6-tony.luck@intel.com

arch/x86/kernel/cpu/mce/core.c

@@ -1260,6 +1260,21 @@ static void kill_me_maybe(struct callback_head *cb)
 	kill_me_now(cb);
 }
 
+static void queue_task_work(struct mce *m, int kill_it)
+{
+	current->mce_addr = m->addr;
+	current->mce_kflags = m->kflags;
+	current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV);
+	current->mce_whole_page = whole_page(m);
+
+	if (kill_it)
+		current->mce_kill_me.func = kill_me_now;
+	else
+		current->mce_kill_me.func = kill_me_maybe;
+
+	task_work_add(current, &current->mce_kill_me, true);
+}
+
 /*
  * The actual machine check handler. This only handles real
  * exceptions when something got corrupted coming in through int 18.
@@ -1401,13 +1416,8 @@ noinstr void do_machine_check(struct pt_regs *regs)
 		/* If this triggers there is no way to recover. Die hard. */
 		BUG_ON(!on_thread_stack() || !user_mode(regs));
 
-		current->mce_addr = m.addr;
+		queue_task_work(&m, kill_it);
-		current->mce_ripv = !!(m.mcgstatus & MCG_STATUS_RIPV);
+
-		current->mce_whole_page = whole_page(&m);
-		current->mce_kill_me.func = kill_me_maybe;
-		if (kill_it)
-			current->mce_kill_me.func = kill_me_now;
-		task_work_add(current, &current->mce_kill_me, true);
 	} else {
 		/*
 		 * Handle an MCE which has happened in kernel space but from
@@ -1422,6 +1432,9 @@ noinstr void do_machine_check(struct pt_regs *regs)
 			if (!fixup_exception(regs, X86_TRAP_MC, 0, 0))
 				mce_panic("Failed kernel mode recovery", &m, msg);
 		}
+
+		if (m.kflags & MCE_IN_KERNEL_COPYIN)
+			queue_task_work(&m, kill_it);
 	}
 out:
 	mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);

include/linux/sched.h

@@ -1308,6 +1308,8 @@ struct task_struct {
 #endif
 
 #ifdef CONFIG_X86_MCE
+	void __user			*mce_vaddr;
+	__u64				mce_kflags;
 	u64				mce_addr;
 	__u64				mce_ripv : 1,
 					mce_whole_page : 1,