Merge tiger.hpl.hp.com:/data1/bk/vanilla/linux-2.5

into tiger.hpl.hp.com:/data1/bk/lia64/to-linus-2.5

arch/ia64/kernel/entry.S

@@ -701,7 +701,7 @@ GLOBAL_ENTRY(ia64_leave_kernel)
 	 * NOTE: alloc, loadrs, and cover can't be predicated.
 	 */
 (pNonSys) br.cond.dpnt dont_preserve_current_frame
-	cover				// add current frame into dirty partition
+	cover				// add current frame into dirty partition and set cr.ifs
 	;;
 	mov r19=ar.bsp			// get new backing store pointer
 	sub r16=r16,r18			// krbs = old bsp - size of dirty partition
@@ -727,7 +727,7 @@ dont_preserve_current_frame:
 #	define Nregs	14
 #endif
 	alloc loc0=ar.pfs,2,Nregs-2,2,0
-	shr.u loc1=r18,9		// RNaTslots <= dirtySize / (64*8) + 1
+	shr.u loc1=r18,9		// RNaTslots <= floor(dirtySize / (64*8))
 	sub r17=r17,r18			// r17 = (physStackedSize + 8) - dirtySize
 	;;
 	mov ar.rsc=r19			// load ar.rsc to be used for "loadrs"
@@ -774,13 +774,13 @@ rse_clear_invalid:
 	;;
 	mov loc3=0
 	mov loc4=0
-	mov loc9=0
 	mov loc5=0
 	mov loc6=0
+	mov loc7=0
 (pRecurse) br.call.sptk.many b6=rse_clear_invalid
 	;;
-	mov loc7=0
 	mov loc8=0
+	mov loc9=0
 	cmp.ne pReturn,p0=r0,in1	// if recursion count != 0, we need to do a br.ret
 	mov loc10=0
 	mov loc11=0
@@ -904,13 +904,14 @@ ENTRY(notify_resume_user)
 	mov r9=ar.unat
 	mov loc0=rp				// save return address
 	mov out0=0				// there is no "oldset"
-	adds out1=0,sp				// out1=&sigscratch
+	adds out1=8,sp				// out1=&sigscratch->ar_pfs
 (pSys)	mov out2=1				// out2==1 => we're in a syscall
 	;;
 (pNonSys) mov out2=0				// out2==0 => not a syscall
 	.fframe 16
 	.spillpsp ar.unat, 16			// (note that offset is relative to psp+0x10!)
 	st8 [sp]=r9,-16				// allocate space for ar.unat and save it
+	st8 [out1]=loc1,-8			// save ar.pfs, out1=&sigscratch
 	.body
 	br.call.sptk.many rp=do_notify_resume_user
 .ret15:	.restore sp
@@ -931,11 +932,12 @@ GLOBAL_ENTRY(sys_rt_sigsuspend)
 	mov loc0=rp				// save return address
 	mov out0=in0				// mask
 	mov out1=in1				// sigsetsize
-	adds out2=0,sp				// out2=&sigscratch
+	adds out2=8,sp				// out2=&sigscratch->ar_pfs
 	;;
 	.fframe 16
 	.spillpsp ar.unat, 16			// (note that offset is relative to psp+0x10!)
 	st8 [sp]=r9,-16				// allocate space for ar.unat and save it
+	st8 [out2]=loc1,-8			// save ar.pfs, out2=&sigscratch
 	.body
 	br.call.sptk.many rp=ia64_rt_sigsuspend
 .ret17:	.restore sp

arch/ia64/kernel/gate.S

@@ -145,11 +145,12 @@ END(fsys_fallback_syscall)
 	 */
 
 #define SIGTRAMP_SAVES										\
-	.unwabi @svr4, 's'		// mark this as a sigtramp handler (saves scratch regs)	\
-	.savesp ar.unat, UNAT_OFF+SIGCONTEXT_OFF						\
-	.savesp ar.fpsr, FPSR_OFF+SIGCONTEXT_OFF						\
-	.savesp pr, PR_OFF+SIGCONTEXT_OFF							\
-	.savesp rp, RP_OFF+SIGCONTEXT_OFF							\
+	.unwabi @svr4, 's';	/* mark this as a sigtramp handler (saves scratch regs) */	\
+	.savesp ar.unat, UNAT_OFF+SIGCONTEXT_OFF;						\
+	.savesp ar.fpsr, FPSR_OFF+SIGCONTEXT_OFF;						\
+	.savesp pr, PR_OFF+SIGCONTEXT_OFF;     							\
+	.savesp rp, RP_OFF+SIGCONTEXT_OFF;							\
+	.savesp ar.pfs, CFM_OFF+SIGCONTEXT_OFF;							\
 	.vframesp SP_OFF+SIGCONTEXT_OFF
 
 GLOBAL_ENTRY(ia64_sigtramp)
@@ -173,9 +174,7 @@ GLOBAL_ENTRY(ia64_sigtramp)
 	.spillsp.p p8, ar.rnat, RNAT_OFF+SIGCONTEXT_OFF
 (p8)	br.cond.spnt setup_rbs		// yup -> (clobbers r14, r15, and r16)
 back_from_setup_rbs:
-
-	.spillreg ar.pfs, r8
-	alloc r8=ar.pfs,0,0,3,0		// get CFM0, EC0, and CPL0 into r8
+	alloc r8=ar.pfs,0,0,3,0
 	ld8 out0=[base0],16		// load arg0 (signum)
 	adds base1=(ARG1_OFF-(RBS_BASE_OFF+SIGCONTEXT_OFF)),base1
 	;;
@@ -184,17 +183,12 @@ back_from_setup_rbs:
 	;;
 	ld8 out2=[base0]		// load arg2 (sigcontextp)
 	ld8 gp=[r17]			// get signal handler's global pointer
-
 	adds base0=(BSP_OFF+SIGCONTEXT_OFF),sp
 	;;
 	.spillsp ar.bsp, BSP_OFF+SIGCONTEXT_OFF
-	st8 [base0]=r9,(CFM_OFF-BSP_OFF)	// save sc_ar_bsp
-	dep r8=0,r8,38,26			// clear EC0, CPL0 and reserved bits
-	adds base1=(FR6_OFF+16+SIGCONTEXT_OFF),sp
-	;;
-	.spillsp ar.pfs, CFM_OFF+SIGCONTEXT_OFF
-	st8 [base0]=r8				// save CFM0
+	st8 [base0]=r9			// save sc_ar_bsp
 	adds base0=(FR6_OFF+SIGCONTEXT_OFF),sp
+	adds base1=(FR6_OFF+16+SIGCONTEXT_OFF),sp
 	;;
 	stf.spill [base0]=f6,32
 	stf.spill [base1]=f7,32
@@ -217,7 +211,6 @@ back_from_setup_rbs:
 	ld8 r15=[base0],(CFM_OFF-BSP_OFF)	// fetch sc_ar_bsp and advance to CFM_OFF
 	mov r14=ar.bsp
 	;;
-	ld8 r8=[base0]				// restore (perhaps modified) CFM0, EC0, and CPL0
 	cmp.ne p8,p0=r14,r15			// do we need to restore the rbs?
 (p8)	br.cond.spnt restore_rbs		// yup -> (clobbers r14-r18, f6 & f7)
 	;;

arch/ia64/kernel/sigframe.h

 struct sigscratch {
 	unsigned long scratch_unat;	/* ar.unat for the general registers saved in pt */
-	unsigned long pad;
+	unsigned long ar_pfs;		/* for syscalls, the user-level function-state  */
 	struct pt_regs pt;
 };
 

arch/ia64/kernel/signal.c

@@ -315,7 +315,7 @@ ia64_rt_sigreturn (struct sigscratch *scr)
 static long
 setup_sigcontext (struct sigcontext *sc, sigset_t *mask, struct sigscratch *scr)
 {
-	unsigned long flags = 0, ifs, nat;
+	unsigned long flags = 0, ifs, cfm, nat;
 	long err;
 
 	ifs = scr->pt.cr_ifs;
@@ -325,7 +325,9 @@ setup_sigcontext (struct sigcontext *sc, sigset_t *mask, struct sigscratch *scr)
 	if ((ifs & (1UL << 63)) == 0) {
 		/* if cr_ifs isn't valid, we got here through a syscall */
 		flags |= IA64_SC_FLAG_IN_SYSCALL;
-	}
+		cfm = scr->ar_pfs & ((1UL << 38) - 1);
+	} else
+		cfm = ifs & ((1UL << 38) - 1);
 	ia64_flush_fph(current);
 	if ((current->thread.flags & IA64_THREAD_FPH_VALID)) {
 		flags |= IA64_SC_FLAG_FPH_VALID;
@@ -344,6 +346,7 @@ setup_sigcontext (struct sigcontext *sc, sigset_t *mask, struct sigscratch *scr)
 
 	err |= __put_user(nat, &sc->sc_nat);
 	err |= PUT_SIGSET(mask, &sc->sc_mask);
+	err |= __put_user(cfm, &sc->sc_cfm);
 	err |= __put_user(scr->pt.cr_ipsr & IA64_PSR_UM, &sc->sc_um);
 	err |= __put_user(scr->pt.ar_rsc, &sc->sc_ar_rsc);
 	err |= __put_user(scr->pt.ar_ccv, &sc->sc_ar_ccv);
@@ -422,6 +425,15 @@ setup_frame (int sig, struct k_sigaction *ka, siginfo_t *info, sigset_t *set,
 	scr->pt.ar_fpsr = FPSR_DEFAULT;			/* reset fpsr for signal handler */
 	scr->pt.cr_iip = tramp_addr;
 	ia64_psr(&scr->pt)->ri = 0;			/* start executing in first slot */
+	/*
+	 * Force the interruption function mask to zero.  This has no effect when a
+	 * system-call got interrupted by a signal (since, in that case, scr->pt_cr_ifs is
+	 * ignored), but it has the desirable effect of making it possible to deliver a
+	 * signal with an incomplete register frame (which happens when a mandatory RSE
+	 * load faults).  Furthermore, it has no negative effect on the getting the user's
+	 * dirty partition preserved, because that's governed by scr->pt.loadrs.
+	 */
+	scr->pt.cr_ifs = (1UL << 63);
 
 	/*
 	 * Note: this affects only the NaT bits of the scratch regs (the ones saved in

arch/ia64/tools/print_offsets.c

@@ -10,7 +10,7 @@
  * gets translated into an assembly file which, in turn, is processed
  * by awk to generate offsets.h.  So if you make any changes to this
  * file, be sure to verify that the awk procedure still works (see
- * prin_offsets.awk).
+ * print_offsets.awk).
  */
 #include <linux/config.h>