Merge tag 'ia64-3.5-merge' of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux

Pull Itanium fixes from Tony Luck.

* tag 'ia64-3.5-merge' of git://git.kernel.org/pub/scm/linux/kernel/git/aegl/linux:
  [IA64] Liberate the signal layer from IA64 assembler
  [IA64] Add cmpxchg.h to exported userspace headers
  [IA64] Fix fast syscall version of getcpu()
  [IA64] Removed "task_size" element from thread_struct - it is now constant

3 files changed, 15 insertions, 182 deletions

diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild
index 241d1c53ba6..d4eb9383f5f 100644
--- a/arch/ia64/include/asm/Kbuild
+++ b/arch/ia64/include/asm/Kbuild
@@ -1,6 +1,7 @@
 include include/asm-generic/Kbuild.asm
 
 header-y += break.h
+header-y += cmpxchg.h
 header-y += fpu.h
 header-y += gcc_intrin.h
 header-y += ia64regs.h
diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h
index 5a994ec8f06..832dd3789e9 100644
--- a/arch/ia64/include/asm/processor.h
+++ b/arch/ia64/include/asm/processor.h
@@ -34,8 +34,7 @@
  * each (assuming 8KB page size), for a total of 8TB of user virtual
  * address space.
  */
-#define TASK_SIZE_OF(tsk)	((tsk)->thread.task_size)
-#define TASK_SIZE       	TASK_SIZE_OF(current)
+#define TASK_SIZE       	DEFAULT_TASK_SIZE
 
 /*
  * This decides where the kernel will search for a free chunk of vm
@@ -280,7 +279,6 @@ struct thread_struct {
 	__u8 pad[3];
 	__u64 ksp;			/* kernel stack pointer */
 	__u64 map_base;			/* base address for get_unmapped_area() */
-	__u64 task_size;		/* limit for task size */
 	__u64 rbs_bot;			/* the base address for the RBS */
 	int last_fph_cpu;		/* CPU that may hold the contents of f32-f127 */
 
@@ -303,7 +301,6 @@ struct thread_struct {
 	.ksp =		0,					\
 	.map_base =	DEFAULT_MAP_BASE,			\
 	.rbs_bot =	STACK_TOP - DEFAULT_USER_STACK_SIZE,	\
-	.task_size =	DEFAULT_TASK_SIZE,			\
 	.last_fph_cpu =  -1,					\
 	INIT_THREAD_PM						\
 	.dbr =		{0, },					\
diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S
index cc26edac0ec..e662f178b99 100644
--- a/arch/ia64/kernel/fsys.S
+++ b/arch/ia64/kernel/fsys.S
@@ -372,175 +372,6 @@ ENTRY(fsys_clock_gettime)
 END(fsys_clock_gettime)
 
 /*
- * long fsys_rt_sigprocmask (int how, sigset_t *set, sigset_t *oset, size_t sigsetsize).
- */
-#if _NSIG_WORDS != 1
-# error Sorry, fsys_rt_sigprocmask() needs to be updated for _NSIG_WORDS != 1.
-#endif
-ENTRY(fsys_rt_sigprocmask)
-	.prologue
-	.altrp b6
-	.body
-
-	add r2=IA64_TASK_BLOCKED_OFFSET,r16
-	add r9=TI_FLAGS+IA64_TASK_SIZE,r16
-	cmp4.ltu p6,p0=SIG_SETMASK,r32
-
-	cmp.ne p15,p0=r0,r34			// oset != NULL?
-	tnat.nz p8,p0=r34
-	add r31=IA64_TASK_SIGHAND_OFFSET,r16
-	;;
-	ld8 r3=[r2]				// read/prefetch current->blocked
-	ld4 r9=[r9]
-	tnat.nz.or p6,p0=r35
-
-	cmp.ne.or p6,p0=_NSIG_WORDS*8,r35
-	tnat.nz.or p6,p0=r32
-(p6)	br.spnt.few .fail_einval		// fail with EINVAL
-	;;
-#ifdef CONFIG_SMP
-	ld8 r31=[r31]				// r31 <- current->sighand
-#endif
-	and r9=TIF_ALLWORK_MASK,r9
-	tnat.nz.or p8,p0=r33
-	;;
-	cmp.ne p7,p0=0,r9
-	cmp.eq p6,p0=r0,r33			// set == NULL?
-	add r31=IA64_SIGHAND_SIGLOCK_OFFSET,r31	// r31 <- current->sighand->siglock
-(p8)	br.spnt.few .fail_efault		// fail with EFAULT
-(p7)	br.spnt.many fsys_fallback_syscall	// got pending kernel work...
-(p6)	br.dpnt.many .store_mask		// -> short-circuit to just reading the signal mask
-
-	/* Argh, we actually have to do some work and _update_ the signal mask: */
-
-EX(.fail_efault, probe.r.fault r33, 3)		// verify user has read-access to *set
-EX(.fail_efault, ld8 r14=[r33])			// r14 <- *set
-	mov r17=(1 << (SIGKILL - 1)) | (1 << (SIGSTOP - 1))
-	;;
-
-	RSM_PSR_I(p0, r18, r19)			// mask interrupt delivery
-	andcm r14=r14,r17			// filter out SIGKILL & SIGSTOP
-	mov r8=EINVAL			// default to EINVAL
-
-#ifdef CONFIG_SMP
-	// __ticket_spin_trylock(r31)
-	ld4 r17=[r31]
-	;;
-	mov.m ar.ccv=r17
-	extr.u r9=r17,17,15
-	adds r19=1,r17
-	extr.u r18=r17,0,15
-	;;
-	cmp.eq p6,p7=r9,r18
-	;;
-(p6)	cmpxchg4.acq r9=[r31],r19,ar.ccv
-(p6)	dep.z r20=r19,1,15		// next serving ticket for unlock
-(p7)	br.cond.spnt.many .lock_contention
-	;;
-	cmp4.eq p0,p7=r9,r17
-	adds r31=2,r31
-(p7)	br.cond.spnt.many .lock_contention
-	ld8 r3=[r2]			// re-read current->blocked now that we hold the lock
-	;;
-#else
-	ld8 r3=[r2]			// re-read current->blocked now that we hold the lock
-#endif
-	add r18=IA64_TASK_PENDING_OFFSET+IA64_SIGPENDING_SIGNAL_OFFSET,r16
-	add r19=IA64_TASK_SIGNAL_OFFSET,r16
-	cmp4.eq p6,p0=SIG_BLOCK,r32
-	;;
-	ld8 r19=[r19]			// r19 <- current->signal
-	cmp4.eq p7,p0=SIG_UNBLOCK,r32
-	cmp4.eq p8,p0=SIG_SETMASK,r32
-	;;
-	ld8 r18=[r18]			// r18 <- current->pending.signal
-	.pred.rel.mutex p6,p7,p8
-(p6)	or r14=r3,r14			// SIG_BLOCK
-(p7)	andcm r14=r3,r14		// SIG_UNBLOCK
-
-(p8)	mov r14=r14			// SIG_SETMASK
-(p6)	mov r8=0			// clear error code
-	// recalc_sigpending()
-	add r17=IA64_SIGNAL_GROUP_STOP_COUNT_OFFSET,r19
-
-	add r19=IA64_SIGNAL_SHARED_PENDING_OFFSET+IA64_SIGPENDING_SIGNAL_OFFSET,r19
-	;;
-	ld4 r17=[r17]		// r17 <- current->signal->group_stop_count
-(p7)	mov r8=0		// clear error code
-
-	ld8 r19=[r19]		// r19 <- current->signal->shared_pending
-	;;
-	cmp4.gt p6,p7=r17,r0	// p6/p7 <- (current->signal->group_stop_count > 0)?
-(p8)	mov r8=0		// clear error code
-
-	or r18=r18,r19		// r18 <- current->pending | current->signal->shared_pending
-	;;
-	// r18 <- (current->pending | current->signal->shared_pending) & ~current->blocked:
-	andcm r18=r18,r14
-	add r9=TI_FLAGS+IA64_TASK_SIZE,r16
-	;;
-
-(p7)	cmp.ne.or.andcm p6,p7=r18,r0		// p6/p7 <- signal pending
-	mov r19=0					// i must not leak kernel bits...
-(p6)	br.cond.dpnt.many .sig_pending
-	;;
-
-1:	ld4 r17=[r9]				// r17 <- current->thread_info->flags
-	;;
-	mov ar.ccv=r17
-	and r18=~_TIF_SIGPENDING,r17		// r18 <- r17 & ~(1 << TIF_SIGPENDING)
-	;;
-
-	st8 [r2]=r14				// update current->blocked with new mask
-	cmpxchg4.acq r8=[r9],r18,ar.ccv		// current->thread_info->flags <- r18
-	;;
-	cmp.ne p6,p0=r17,r8			// update failed?
-(p6)	br.cond.spnt.few 1b			// yes -> retry
-
-#ifdef CONFIG_SMP
-	// __ticket_spin_unlock(r31)
-	st2.rel [r31]=r20
-	mov r20=0					// i must not leak kernel bits...
-#endif
-	SSM_PSR_I(p0, p9, r31)
-	;;
-
-	srlz.d					// ensure psr.i is set again
-	mov r18=0					// i must not leak kernel bits...
-
-.store_mask:
-EX(.fail_efault, (p15) probe.w.fault r34, 3)	// verify user has write-access to *oset
-EX(.fail_efault, (p15) st8 [r34]=r3)
-	mov r2=0					// i must not leak kernel bits...
-	mov r3=0					// i must not leak kernel bits...
-	mov r8=0				// return 0
-	mov r9=0					// i must not leak kernel bits...
-	mov r14=0					// i must not leak kernel bits...
-	mov r17=0					// i must not leak kernel bits...
-	mov r31=0					// i must not leak kernel bits...
-	FSYS_RETURN
-
-.sig_pending:
-#ifdef CONFIG_SMP
-	// __ticket_spin_unlock(r31)
-	st2.rel [r31]=r20			// release the lock
-#endif
-	SSM_PSR_I(p0, p9, r17)
-	;;
-	srlz.d
-	br.sptk.many fsys_fallback_syscall	// with signal pending, do the heavy-weight syscall
-
-#ifdef CONFIG_SMP
-.lock_contention:
-	/* Rather than spinning here, fall back on doing a heavy-weight syscall.  */
-	SSM_PSR_I(p0, p9, r17)
-	;;
-	srlz.d
-	br.sptk.many fsys_fallback_syscall
-#endif
-END(fsys_rt_sigprocmask)
-
-/*
  * fsys_getcpu doesn't use the third parameter in this implementation. It reads
  * current_thread_info()->cpu and corresponding node in cpu_to_node_map.
  */
@@ -559,11 +390,15 @@ ENTRY(fsys_getcpu)
 	;;
 	tnat.nz p7,p0 = r33			// I guard against NaT argument
 (p7)    br.cond.spnt.few .fail_einval		// B
+	;;
+	cmp.ne p6,p0=r32,r0
+	cmp.ne p7,p0=r33,r0
+	;;
 #ifdef CONFIG_NUMA
 	movl r17=cpu_to_node_map
 	;;
-EX(.fail_efault, probe.w.fault r32, 3)		// M This takes 5 cycles
-EX(.fail_efault, probe.w.fault r33, 3)		// M This takes 5 cycles
+EX(.fail_efault, (p6) probe.w.fault r32, 3)		// M This takes 5 cycles
+EX(.fail_efault, (p7) probe.w.fault r33, 3)		// M This takes 5 cycles
 	shladd r18=r3,1,r17
 	;;
 	ld2 r20=[r18]				// r20 = cpu_to_node_map[cpu]
@@ -573,20 +408,20 @@ EX(.fail_efault, probe.w.fault r33, 3)		// M This takes 5 cycles
 (p8)	br.spnt.many fsys_fallback_syscall
 	;;
 	;;
-EX(.fail_efault, st4 [r32] = r3)
-EX(.fail_efault, st2 [r33] = r20)
+EX(.fail_efault, (p6) st4 [r32] = r3)
+EX(.fail_efault, (p7) st2 [r33] = r20)
 	mov r8=0
 	;;
 #else
-EX(.fail_efault, probe.w.fault r32, 3)		// M This takes 5 cycles
-EX(.fail_efault, probe.w.fault r33, 3)		// M This takes 5 cycles
+EX(.fail_efault, (p6) probe.w.fault r32, 3)		// M This takes 5 cycles
+EX(.fail_efault, (p7) probe.w.fault r33, 3)		// M This takes 5 cycles
 	and r2 = TIF_ALLWORK_MASK,r2
 	;;
 	cmp.ne p8,p0=0,r2
 (p8)	br.spnt.many fsys_fallback_syscall
 	;;
-EX(.fail_efault, st4 [r32] = r3)
-EX(.fail_efault, st2 [r33] = r0)
+EX(.fail_efault, (p6) st4 [r32] = r3)
+EX(.fail_efault, (p7) st2 [r33] = r0)
 	mov r8=0
 	;;
 #endif
@@ -916,7 +751,7 @@ paravirt_fsyscall_table:
 	data8 0				// sigaltstack
 	data8 0				// rt_sigaction
 	data8 0				// rt_sigpending
-	data8 fsys_rt_sigprocmask	// rt_sigprocmask
+	data8 0				// rt_sigprocmask
 	data8 0				// rt_sigqueueinfo	// 1180
 	data8 0				// rt_sigreturn
 	data8 0				// rt_sigsuspend