Skip to contentSkip to conversation

x86/asm changes for v3.20

GIT PULL Ingo Molnar 1 participant 1 message Feb 9, 2015

Subsystems (3)
lore
Share & tools
lore
#0 lore raw

Linus,

Please pull the latest x86-asm-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-asm-for-linus

# HEAD: b57c0b5175ddbe9b477801f9994a5b330702c1ba Merge tag 'pr-20150201-x86-entry' of git://git.kernel.org/pub/scm/linux/kernel/git/luto/linux into x86/asm

[ NOTE: there's a (single) RCU commit this tree depends on
semantically (734d16801349), which is also present in the RCU tree, which might throw off your diffstat. ]

The main changes in this cycle were the x86/entry and sysret enhancements from Andy Lutomirski, see merge commits 772a9aca125 and b57c0b5175dd for details.

out-of-topic modifications in x86-asm-for-linus:
--------------------------------------------------
kernel/rcu/tree.c # 734d16801349: rcu: Make rcu_nmi_enter() ha

Thanks,

Ingo

------------------>
Andrey Skvortsov (1):
x86, vdso: teach 'make clean' remove vdso64 binaries

Andy Lutomirski (8):
x86, entry: Switch stacks on a paranoid entry from userspace x86, traps: Track entry into and exit from IST context
x86: Clean up current_stack_pointer
x86, traps: Add ist_begin_non_atomic and ist_end_non_atomic x86_64 entry: Fix RCX for ptraced syscalls
x86, traps: Fix ist_enter from userspace
x86_64, entry: Use sysret to return to userspace when possible x86_64, entry: Remove the syscall exit audit and schedule optimizations

Denys Vlasenko (3):
x86: entry_64.S: delete unused code
x86: ia32entry.S: fix wrong symbolic constant usage: R11->ARGOFFSET
x86: entry_64.S: fold SAVE_ARGS_IRQ macro into its sole user

Paul E. McKenney (1):
rcu: Make rcu_nmi_enter() handle nesting

Tony Luck (1):
x86, mce: Get rid of TIF_MCE_NOTIFY and associated mce tricks

 Documentation/x86/entry_64.txt         |  18 +-
 Documentation/x86/x86_64/kernel-stacks |   8 +-
 arch/x86/ia32/ia32entry.S              |   4 +-
 arch/x86/include/asm/calling.h         |   1 -
 arch/x86/include/asm/mce.h             |   1 -
 arch/x86/include/asm/thread_info.h     |  15 +-
 arch/x86/include/asm/traps.h           |   6 +
 arch/x86/kernel/cpu/mcheck/mce.c       | 114 ++++--------
 arch/x86/kernel/cpu/mcheck/p5.c        |   6 +
 arch/x86/kernel/cpu/mcheck/winchip.c   |   5 +
 arch/x86/kernel/entry_64.S             | 317 +++++++++++++++------------------
 arch/x86/kernel/irq_32.c               |  13 +-
 arch/x86/kernel/signal.c               |   6 -
 arch/x86/kernel/traps.c                | 119 ++++++++++---
 arch/x86/vdso/Makefile                 |   2 +-
 kernel/rcu/tree.c                      |  66 +++++--
 16 files changed, 374 insertions(+), 327 deletions(-)
Documentation/x86/entry_64.txt +12 -6
index 4a1c5c2dc5a9..9132b86176a3 100644
@@ -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 +5 -3
index a01eec5d1d0b..e3c8a49d1a2f 100644
@@ -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 +2 -2
index 82e8a1d44658..156ebcab4ada 100644
@@ -179,8 +179,8 @@ ENTRY(ia32_sysenter_target)
 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 +0 -1
index 76659b67fd11..1f1297b46f83 100644
@@ -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 +0 -1
index 51b26e895933..9b3de99dc004 100644
@@ -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 +12 -3
index 547e344a6dc6..e82e95abc92b 100644
@@ -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 +6 -0
index 707adc6549d8..4e49d7dff78e 100644
@@ -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 +30 -84

156 lines not on this page · raw message

arch/x86/kernel/cpu/mcheck/p5.c +6 -0
index a3042989398c..ec2663a708e4 100644
@@ -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 +5 -0
index 7dc5564d0cdf..bd5d46a32210 100644
@@ -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 */
arch/x86/kernel/entry_64.S +148 -169

407 lines not on this page · raw message

arch/x86/kernel/irq_32.c +3 -10
index 63ce838e5a54..28d28f5eb8f4 100644
@@ -69,16 +69,9 @@ static void call_on_stack(void *func, void *stack)
 		     : "memory", "cc", "edx", "ecx", "eax");
 }
 
-/* how to get the current stack pointer from C */
-#define current_stack_pointer ({		\
-	unsigned long sp;			\
-	asm("mov %%esp,%0" : "=g" (sp));	\
-	sp;					\
-})
-
 static inline void *current_stack(void)
 {
-	return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1));
+	return (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1));
 }
 
 static inline int
@@ -103,7 +96,7 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
 
 	/* Save the next esp at the bottom of the stack */
 	prev_esp = (u32 *)irqstk;
-	*prev_esp = current_stack_pointer;
+	*prev_esp = current_stack_pointer();
 
 	if (unlikely(overflow))
 		call_on_stack(print_stack_overflow, isp);
@@ -156,7 +149,7 @@ void do_softirq_own_stack(void)
 
 	/* Push the previous esp onto the stack */
 	prev_esp = (u32 *)irqstk;
-	*prev_esp = current_stack_pointer;
+	*prev_esp = current_stack_pointer();
 
 	call_on_stack(__do_softirq, isp);
 }
arch/x86/kernel/signal.c +0 -6
index ed37a768d0fc..2a33c8f68319 100644
@@ -740,12 +740,6 @@ do_notify_resume(struct pt_regs *regs, void *unused, __u32 thread_info_flags)
 {
 	user_exit();
 
-#ifdef CONFIG_X86_MCE
-	/* notify userspace of pending MCEs */
-	if (thread_info_flags & _TIF_MCE_NOTIFY)
-		mce_notify_process();
-#endif /* CONFIG_X86_64 && CONFIG_X86_MCE */
-
 	if (thread_info_flags & _TIF_UPROBE)
 		uprobe_notify_resume(regs);
 
arch/x86/kernel/traps.c +95 -24

173 lines not on this page · raw message

arch/x86/vdso/Makefile +1 -1
index 5a4affe025e8..09297c8e1fcd 100644
@@ -205,4 +205,4 @@ $(vdso_img_insttargets): install_%: $(obj)/%.dbg $(MODLIB)/vdso FORCE
 PHONY += vdso_install $(vdso_img_insttargets)
 vdso_install: $(vdso_img_insttargets) FORCE
 
-clean-files := vdso32-syscall* vdso32-sysenter* vdso32-int80*
+clean-files := vdso32-syscall* vdso32-sysenter* vdso32-int80* vdso64*
kernel/rcu/tree.c +49 -17

88 lines not on this page · raw message