sched/x86: Save [ER]FLAGS on context switch

Effectively reverts commit:

  2c7577a7 ("sched/x86_64: Don't save flags on context switch")

Specifically because SMAP uses FLAGS.AC which invalidates the claim
that the kernel has clean flags.

In particular; while preemption from interrupt return is fine (the
IRET frame on the exception stack contains FLAGS) it breaks any code
that does synchonous scheduling, including preempt_enable().

This has become a significant issue ever since commit:

  5b24a7a2 ("Add 'unsafe' user access functions for batched accesses")

provided for means of having 'normal' C code between STAC / CLAC,
exposing the FLAGS.AC state. So far this hasn't led to trouble,
however fix it before it comes apart.
Reported-by: Julien Thierry <julien.thierry@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@kernel.org
Fixes: 5b24a7a2 ("Add 'unsafe' user access functions for batched accesses")
Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/entry/entry_32.S

@@ -650,6 +650,7 @@ ENTRY(__switch_to_asm)
 	pushl	%ebx
 	pushl	%edi
 	pushl	%esi
+	pushfl
 
 	/* switch stack */
 	movl	%esp, TASK_threadsp(%eax)
@@ -672,6 +673,7 @@ ENTRY(__switch_to_asm)
 #endif
 
 	/* restore callee-saved registers */
+	popfl
 	popl	%esi
 	popl	%edi
 	popl	%ebx

arch/x86/entry/entry_64.S

@@ -291,6 +291,7 @@ ENTRY(__switch_to_asm)
 	pushq	%r13
 	pushq	%r14
 	pushq	%r15
+	pushfq
 
 	/* switch stack */
 	movq	%rsp, TASK_threadsp(%rdi)
@@ -313,6 +314,7 @@ ENTRY(__switch_to_asm)
 #endif
 
 	/* restore callee-saved registers */
+	popfq
 	popq	%r15
 	popq	%r14
 	popq	%r13

arch/x86/include/asm/switch_to.h

@@ -40,6 +40,7 @@ asmlinkage void ret_from_fork(void);
  * order of the fields must match the code in __switch_to_asm().
  */
 struct inactive_task_frame {
+	unsigned long flags;
 #ifdef CONFIG_X86_64
 	unsigned long r15;
 	unsigned long r14;

arch/x86/kernel/process_32.c

@@ -127,6 +127,13 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 	struct task_struct *tsk;
 	int err;
 
+	/*
+	 * For a new task use the RESET flags value since there is no before.
+	 * All the status flags are zero; DF and all the system flags must also
+	 * be 0, specifically IF must be 0 because we context switch to the new
+	 * task with interrupts disabled.
+	 */
+	frame->flags = X86_EFLAGS_FIXED;
 	frame->bp = 0;
 	frame->ret_addr = (unsigned long) ret_from_fork;
 	p->thread.sp = (unsigned long) fork_frame;

arch/x86/kernel/process_64.c

@@ -392,6 +392,14 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 	childregs = task_pt_regs(p);
 	fork_frame = container_of(childregs, struct fork_frame, regs);
 	frame = &fork_frame->frame;
+
+	/*
+	 * For a new task use the RESET flags value since there is no before.
+	 * All the status flags are zero; DF and all the system flags must also
+	 * be 0, specifically IF must be 0 because we context switch to the new
+	 * task with interrupts disabled.
+	 */
+	frame->flags = X86_EFLAGS_FIXED;
 	frame->bp = 0;
 	frame->ret_addr = (unsigned long) ret_from_fork;
 	p->thread.sp = (unsigned long) fork_frame;