x86, prctl: Hook L1D flushing in via prctl

Use the existing PR_GET/SET_SPECULATION_CTRL API to expose the L1D flush
capability. For L1D flushing PR_SPEC_FORCE_DISABLE and
PR_SPEC_DISABLE_NOEXEC are not supported.

Enabling L1D flush does not check if the task is running on an SMT enabled
core, rather a check is done at runtime (at the time of flush), if the task
runs on a SMT sibling then the task is sent a SIGBUS which is executed
before the task returns to user space or to a guest.

This is better than the other alternatives of:

  a. Ensuring strict affinity of the task (hard to enforce without further
     changes in the scheduler)

  b. Silently skipping flush for tasks that move to SMT enabled cores.

Hook up the core prctl and implement the x86 specific parts which in turn
makes it functional.

Suggested-by: Thomas Gleixner <[email protected]>
Signed-off-by: Balbir Singh <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

Author: balbir-aws

arch/x86/kernel/cpu/bugs.c

@@ -1252,6 +1252,24 @@ static void task_update_spec_tif(struct task_struct *tsk)
 		speculation_ctrl_update_current();
 }
 
+static int l1d_flush_prctl_set(struct task_struct *task, unsigned long ctrl)
+{
+
+	if (!static_branch_unlikely(&switch_mm_cond_l1d_flush))
+		return -EPERM;
+
+	switch (ctrl) {
+	case PR_SPEC_ENABLE:
+		set_ti_thread_flag(&task->thread_info, TIF_SPEC_L1D_FLUSH);
+		return 0;
+	case PR_SPEC_DISABLE:
+		clear_ti_thread_flag(&task->thread_info, TIF_SPEC_L1D_FLUSH);
+		return 0;
+	default:
+		return -ERANGE;
+	}
+}
+
 static int ssb_prctl_set(struct task_struct *task, unsigned long ctrl)
 {
 	if (ssb_mode != SPEC_STORE_BYPASS_PRCTL &&
@@ -1361,6 +1379,8 @@ int arch_prctl_spec_ctrl_set(struct task_struct *task, unsigned long which,
 		return ssb_prctl_set(task, ctrl);
 	case PR_SPEC_INDIRECT_BRANCH:
 		return ib_prctl_set(task, ctrl);
+	case PR_SPEC_L1D_FLUSH:
+		return l1d_flush_prctl_set(task, ctrl);
 	default:
 		return -ENODEV;
 	}
@@ -1377,6 +1397,17 @@ void arch_seccomp_spec_mitigate(struct task_struct *task)
 }
 #endif
 
+static int l1d_flush_prctl_get(struct task_struct *task)
+{
+	if (!static_branch_unlikely(&switch_mm_cond_l1d_flush))
+		return PR_SPEC_FORCE_DISABLE;
+
+	if (test_ti_thread_flag(&task->thread_info, TIF_SPEC_L1D_FLUSH))
+		return PR_SPEC_PRCTL | PR_SPEC_ENABLE;
+	else
+		return PR_SPEC_PRCTL | PR_SPEC_DISABLE;
+}
+
 static int ssb_prctl_get(struct task_struct *task)
 {
 	switch (ssb_mode) {
@@ -1427,6 +1458,8 @@ int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which)
 		return ssb_prctl_get(task);
 	case PR_SPEC_INDIRECT_BRANCH:
 		return ib_prctl_get(task);
+	case PR_SPEC_L1D_FLUSH:
+		return l1d_flush_prctl_get(task);
 	default:
 		return -ENODEV;
 	}

include/uapi/linux/prctl.h

@@ -213,6 +213,7 @@ struct prctl_mm_map {
 /* Speculation control variants */
 # define PR_SPEC_STORE_BYPASS		0
 # define PR_SPEC_INDIRECT_BRANCH	1
+# define PR_SPEC_L1D_FLUSH		2
 /* Return and control values for PR_SET/GET_SPECULATION_CTRL */
 # define PR_SPEC_NOT_AFFECTED		0
 # define PR_SPEC_PRCTL			(1UL << 0)