Merge tag 'pr-20150114-x86-entry' of git://git.kernel.org/pub/scm/lin…

…ux/kernel/git/luto/linux into x86/asm

Pull x86/entry enhancements from Andy Lutomirski:

" This is my accumulated x86 entry work, part 1, for 3.20.  The meat
  of this is an IST rework.  When an IST exception interrupts user
  space, we will handle it on the per-thread kernel stack instead of
  on the IST stack.  This sounds messy, but it actually simplifies the
  IST entry/exit code, because it eliminates some ugly games we used
  to play in order to handle rescheduling, signal delivery, etc on the
  way out of an IST exception.

  The IST rework introduces proper context tracking to IST exception
  handlers.  I haven't seen any bug reports, but the old code could
  have incorrectly treated an IST exception handler as an RCU extended
  quiescent state.

  The memory failure change (included in this pull request with
  Borislav and Tony's permission) eliminates a bunch of code that
  is no longer needed now that user memory failure handlers are
  called in process context.

  Finally, this includes a few on Denys' uncontroversial and Obviously
  Correct (tm) cleanups.

  The IST and memory failure changes have been in -next for a while.

  LKML references:

  IST rework:
  http://lkml.kernel.org/r/cover.1416604491.git.luto@amacapital.net

  Memory failure change:
  http://lkml.kernel.org/r/54ab2ffa301102cd6e@agluck-desk.sc.intel.com

  Denys' cleanups:
  http://lkml.kernel.org/r/1420927210-19738-1-git-send-email-dvlasenk@redhat.com
"

This tree semantically depends on and is based on the following RCU commit:

  734d168 ("rcu: Make rcu_nmi_enter() handle nesting")

... and for that reason won't be pushed upstream before the RCU bits hit Linus's tree.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

Documentation/x86/entry_64.txt

@@ -78,9 +78,6 @@ The expensive (paranoid) way is to read back the MSR_GS_BASE value
 	xorl %ebx,%ebx
 1:	ret
 
-and the whole paranoid non-paranoid macro complexity is about whether
-to suffer that RDMSR cost.
-
 If we are at an interrupt or user-trap/gate-alike boundary then we can
 use the faster check: the stack will be a reliable indicator of
 whether SWAPGS was already done: if we see that we are a secondary
@@ -93,6 +90,15 @@ which might have triggered right after a normal entry wrote CS to the
 stack but before we executed SWAPGS, then the only safe way to check
 for GS is the slower method: the RDMSR.
 
-So we try only to mark those entry methods 'paranoid' that absolutely
-need the more expensive check for the GS base - and we generate all
-'normal' entry points with the regular (faster) entry macros.
+Therefore, super-atomic entries (except NMI, which is handled separately)
+must use idtentry with paranoid=1 to handle gsbase correctly.  This
+triggers three main behavior changes:
+
+ - Interrupt entry will use the slower gsbase check.
+ - Interrupt entry from user mode will switch off the IST stack.
+ - Interrupt exit to kernel mode will not attempt to reschedule.
+
+We try to only use IST entries and the paranoid entry code for vectors
+that absolutely need the more expensive check for the GS base - and we
+generate all 'normal' entry points with the regular (faster) paranoid=0
+variant.

Documentation/x86/x86_64/kernel-stacks

@@ -40,9 +40,11 @@ An IST is selected by a non-zero value in the IST field of an
 interrupt-gate descriptor.  When an interrupt occurs and the hardware
 loads such a descriptor, the hardware automatically sets the new stack
 pointer based on the IST value, then invokes the interrupt handler.  If
-software wants to allow nested IST interrupts then the handler must
-adjust the IST values on entry to and exit from the interrupt handler.
-(This is occasionally done, e.g. for debug exceptions.)
+the interrupt came from user mode, then the interrupt handler prologue
+will switch back to the per-thread stack.  If software wants to allow
+nested IST interrupts then the handler must adjust the IST values on
+entry to and exit from the interrupt handler.  (This is occasionally
+done, e.g. for debug exceptions.)
 
 Events with different IST codes (i.e. with different stacks) can be
 nested.  For example, a debug interrupt can safely be interrupted by an

arch/x86/ia32/ia32entry.S

@@ -179,8 +179,8 @@ sysenter_dispatch:
 sysexit_from_sys_call:
 	andl    $~TS_COMPAT,TI_status+THREAD_INFO(%rsp,RIP-ARGOFFSET)
 	/* clear IF, that popfq doesn't enable interrupts early */
-	andl  $~0x200,EFLAGS-R11(%rsp) 
-	movl	RIP-R11(%rsp),%edx		/* User %eip */
+	andl	$~0x200,EFLAGS-ARGOFFSET(%rsp)
+	movl	RIP-ARGOFFSET(%rsp),%edx		/* User %eip */
 	CFI_REGISTER rip,rdx
 	RESTORE_ARGS 0,24,0,0,0,0
 	xorq	%r8,%r8

arch/x86/include/asm/calling.h

@@ -83,7 +83,6 @@ For 32-bit we have the following conventions - kernel is built with
 #define SS		160
 
 #define ARGOFFSET	R11
-#define SWFRAME		ORIG_RAX
 
 	.macro SAVE_ARGS addskip=0, save_rcx=1, save_r891011=1, rax_enosys=0
 	subq  $9*8+\addskip, %rsp

arch/x86/include/asm/mce.h

@@ -190,7 +190,6 @@ enum mcp_flags {
 void machine_check_poll(enum mcp_flags flags, mce_banks_t *b);
 
 int mce_notify_irq(void);
-void mce_notify_process(void);
 
 DECLARE_PER_CPU(struct mce, injectm);
 

arch/x86/include/asm/thread_info.h

@@ -75,7 +75,6 @@ struct thread_info {
 #define TIF_SYSCALL_EMU		6	/* syscall emulation active */
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
 #define TIF_SECCOMP		8	/* secure computing */
-#define TIF_MCE_NOTIFY		10	/* notify userspace of an MCE */
 #define TIF_USER_RETURN_NOTIFY	11	/* notify kernel of userspace return */
 #define TIF_UPROBE		12	/* breakpointed or singlestepping */
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
@@ -100,7 +99,6 @@ struct thread_info {
 #define _TIF_SYSCALL_EMU	(1 << TIF_SYSCALL_EMU)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
-#define _TIF_MCE_NOTIFY		(1 << TIF_MCE_NOTIFY)
 #define _TIF_USER_RETURN_NOTIFY	(1 << TIF_USER_RETURN_NOTIFY)
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
 #define _TIF_NOTSC		(1 << TIF_NOTSC)
@@ -140,7 +138,7 @@ struct thread_info {
 
 /* Only used for 64 bit */
 #define _TIF_DO_NOTIFY_MASK						\
-	(_TIF_SIGPENDING | _TIF_MCE_NOTIFY | _TIF_NOTIFY_RESUME |	\
+	(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME |				\
 	 _TIF_USER_RETURN_NOTIFY | _TIF_UPROBE)
 
 /* flags to check in __switch_to() */
@@ -170,6 +168,17 @@ static inline struct thread_info *current_thread_info(void)
 	return ti;
 }
 
+static inline unsigned long current_stack_pointer(void)
+{
+	unsigned long sp;
+#ifdef CONFIG_X86_64
+	asm("mov %%rsp,%0" : "=g" (sp));
+#else
+	asm("mov %%esp,%0" : "=g" (sp));
+#endif
+	return sp;
+}
+
 #else /* !__ASSEMBLY__ */
 
 /* how to get the thread information struct from ASM */

arch/x86/include/asm/traps.h

@@ -1,6 +1,7 @@
 #ifndef _ASM_X86_TRAPS_H
 #define _ASM_X86_TRAPS_H
 
+#include <linux/context_tracking_state.h>
 #include <linux/kprobes.h>
 
 #include <asm/debugreg.h>
@@ -110,6 +111,11 @@ asmlinkage void smp_thermal_interrupt(void);
 asmlinkage void mce_threshold_interrupt(void);
 #endif
 
+extern enum ctx_state ist_enter(struct pt_regs *regs);
+extern void ist_exit(struct pt_regs *regs, enum ctx_state prev_state);
+extern void ist_begin_non_atomic(struct pt_regs *regs);
+extern void ist_end_non_atomic(void);
+
 /* Interrupts/Exceptions */
 enum {
 	X86_TRAP_DE = 0,	/*  0, Divide-by-zero */

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

@@ -43,6 +43,7 @@
 #include <linux/export.h>
 
 #include <asm/processor.h>
+#include <asm/traps.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
 
@@ -1002,51 +1003,6 @@ static void mce_clear_state(unsigned long *toclear)
 	}
 }
 
-/*
- * Need to save faulting physical address associated with a process
- * in the machine check handler some place where we can grab it back
- * later in mce_notify_process()
- */
-#define	MCE_INFO_MAX	16
-
-struct mce_info {
-	atomic_t		inuse;
-	struct task_struct	*t;
-	__u64			paddr;
-	int			restartable;
-} mce_info[MCE_INFO_MAX];
-
-static void mce_save_info(__u64 addr, int c)
-{
-	struct mce_info *mi;
-
-	for (mi = mce_info; mi < &mce_info[MCE_INFO_MAX]; mi++) {
-		if (atomic_cmpxchg(&mi->inuse, 0, 1) == 0) {
-			mi->t = current;
-			mi->paddr = addr;
-			mi->restartable = c;
-			return;
-		}
-	}
-
-	mce_panic("Too many concurrent recoverable errors", NULL, NULL);
-}
-
-static struct mce_info *mce_find_info(void)
-{
-	struct mce_info *mi;
-
-	for (mi = mce_info; mi < &mce_info[MCE_INFO_MAX]; mi++)
-		if (atomic_read(&mi->inuse) && mi->t == current)
-			return mi;
-	return NULL;
-}
-
-static void mce_clear_info(struct mce_info *mi)
-{
-	atomic_set(&mi->inuse, 0);
-}
-
 /*
  * The actual machine check handler. This only handles real
  * exceptions when something got corrupted coming in through int 18.
@@ -1063,6 +1019,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 {
 	struct mca_config *cfg = &mca_cfg;
 	struct mce m, *final;
+	enum ctx_state prev_state;
 	int i;
 	int worst = 0;
 	int severity;
@@ -1084,6 +1041,10 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	DECLARE_BITMAP(toclear, MAX_NR_BANKS);
 	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
 	char *msg = "Unknown";
+	u64 recover_paddr = ~0ull;
+	int flags = MF_ACTION_REQUIRED;
+
+	prev_state = ist_enter(regs);
 
 	this_cpu_inc(mce_exception_count);
 
@@ -1203,9 +1164,9 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		if (no_way_out)
 			mce_panic("Fatal machine check on current CPU", &m, msg);
 		if (worst == MCE_AR_SEVERITY) {
-			/* schedule action before return to userland */
-			mce_save_info(m.addr, m.mcgstatus & MCG_STATUS_RIPV);
-			set_thread_flag(TIF_MCE_NOTIFY);
+			recover_paddr = m.addr;
+			if (!(m.mcgstatus & MCG_STATUS_RIPV))
+				flags |= MF_MUST_KILL;
 		} else if (kill_it) {
 			force_sig(SIGBUS, current);
 		}
@@ -1216,6 +1177,27 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
 out:
 	sync_core();
+
+	if (recover_paddr == ~0ull)
+		goto done;
+
+	pr_err("Uncorrected hardware memory error in user-access at %llx",
+		 recover_paddr);
+	/*
+	 * We must call memory_failure() here even if the current process is
+	 * doomed. We still need to mark the page as poisoned and alert any
+	 * other users of the page.
+	 */
+	ist_begin_non_atomic(regs);
+	local_irq_enable();
+	if (memory_failure(recover_paddr >> PAGE_SHIFT, MCE_VECTOR, flags) < 0) {
+		pr_err("Memory error not recovered");
+		force_sig(SIGBUS, current);
+	}
+	local_irq_disable();
+	ist_end_non_atomic();
+done:
+	ist_exit(regs, prev_state);
 }
 EXPORT_SYMBOL_GPL(do_machine_check);
 
@@ -1232,42 +1214,6 @@ int memory_failure(unsigned long pfn, int vector, int flags)
 }
 #endif
 
-/*
- * Called in process context that interrupted by MCE and marked with
- * TIF_MCE_NOTIFY, just before returning to erroneous userland.
- * This code is allowed to sleep.
- * Attempt possible recovery such as calling the high level VM handler to
- * process any corrupted pages, and kill/signal current process if required.
- * Action required errors are handled here.
- */
-void mce_notify_process(void)
-{
-	unsigned long pfn;
-	struct mce_info *mi = mce_find_info();
-	int flags = MF_ACTION_REQUIRED;
-
-	if (!mi)
-		mce_panic("Lost physical address for unconsumed uncorrectable error", NULL, NULL);
-	pfn = mi->paddr >> PAGE_SHIFT;
-
-	clear_thread_flag(TIF_MCE_NOTIFY);
-
-	pr_err("Uncorrected hardware memory error in user-access at %llx",
-		 mi->paddr);
-	/*
-	 * We must call memory_failure() here even if the current process is
-	 * doomed. We still need to mark the page as poisoned and alert any
-	 * other users of the page.
-	 */
-	if (!mi->restartable)
-		flags |= MF_MUST_KILL;
-	if (memory_failure(pfn, MCE_VECTOR, flags) < 0) {
-		pr_err("Memory error not recovered");
-		force_sig(SIGBUS, current);
-	}
-	mce_clear_info(mi);
-}
-
 /*
  * Action optional processing happens here (picking up
  * from the list of faulting pages that do_machine_check()

arch/x86/kernel/cpu/mcheck/p5.c

@@ -8,6 +8,7 @@
 #include <linux/smp.h>
 
 #include <asm/processor.h>
+#include <asm/traps.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
 
@@ -17,8 +18,11 @@ int mce_p5_enabled __read_mostly;
 /* Machine check handler for Pentium class Intel CPUs: */
 static void pentium_machine_check(struct pt_regs *regs, long error_code)
 {
+	enum ctx_state prev_state;
 	u32 loaddr, hi, lotype;
 
+	prev_state = ist_enter(regs);
+
 	rdmsr(MSR_IA32_P5_MC_ADDR, loaddr, hi);
 	rdmsr(MSR_IA32_P5_MC_TYPE, lotype, hi);
 
@@ -33,6 +37,8 @@ static void pentium_machine_check(struct pt_regs *regs, long error_code)
 	}
 
 	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
+
+	ist_exit(regs, prev_state);
 }
 
 /* Set up machine check reporting for processors with Intel style MCE: */

arch/x86/kernel/cpu/mcheck/winchip.c

@@ -7,14 +7,19 @@
 #include <linux/types.h>
 
 #include <asm/processor.h>
+#include <asm/traps.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
 
 /* Machine check handler for WinChip C6: */
 static void winchip_machine_check(struct pt_regs *regs, long error_code)
 {
+	enum ctx_state prev_state = ist_enter(regs);
+
 	printk(KERN_EMERG "CPU0: Machine Check Exception.\n");
 	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
+
+	ist_exit(regs, prev_state);
 }
 
 /* Set up machine check reporting on the Winchip C6 series */