[POWERPC] Use 1TB segments

This makes the kernel use 1TB segments for all kernel mappings and for
user addresses of 1TB and above, on machines which support them
(currently POWER5+, POWER6 and PA6T).

We detect that the machine supports 1TB segments by looking at the
ibm,processor-segment-sizes property in the device tree.

We don't currently use 1TB segments for user addresses < 1T, since
that would effectively prevent 32-bit processes from using huge pages
unless we also had a way to revert to using 256MB segments.  That
would be possible but would involve extra complications (such as
keeping track of which segment size was used when HPTEs were inserted)
and is not addressed here.

Parts of this patch were originally written by Ben Herrenschmidt.

Signed-off-by: Paul Mackerras <paulus@samba.org>

arch/powerpc/kernel/entry_64.S

@@ -372,9 +372,17 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	std	r6,PACACURRENT(r13)	/* Set new 'current' */
 
 	ld	r8,KSP(r4)	/* new stack pointer */
+BEGIN_FTR_SECTION
+	b	2f
+END_FTR_SECTION_IFCLR(CPU_FTR_SLB)
 BEGIN_FTR_SECTION
 	clrrdi	r6,r8,28	/* get its ESID */
 	clrrdi	r9,r1,28	/* get current sp ESID */
+END_FTR_SECTION_IFCLR(CPU_FTR_1T_SEGMENT)
+BEGIN_FTR_SECTION
+	clrrdi	r6,r8,40	/* get its 1T ESID */
+	clrrdi	r9,r1,40	/* get current sp 1T ESID */
+END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT)
 	clrldi.	r0,r6,2		/* is new ESID c00000000? */
 	cmpd	cr1,r6,r9	/* or is new ESID the same as current ESID? */
 	cror	eq,4*cr1+eq,eq
@@ -384,6 +392,11 @@ BEGIN_FTR_SECTION
 	ld	r7,KSP_VSID(r4)	/* Get new stack's VSID */
 	oris	r0,r6,(SLB_ESID_V)@h
 	ori	r0,r0,(SLB_NUM_BOLTED-1)@l
+BEGIN_FTR_SECTION
+	li	r9,MMU_SEGSIZE_1T	/* insert B field */
+	oris	r6,r6,(MMU_SEGSIZE_1T << SLBIE_SSIZE_SHIFT)@h
+	rldimi	r7,r9,SLB_VSID_SSIZE_SHIFT,0
+END_FTR_SECTION_IFSET(CPU_FTR_1T_SEGMENT)
 
 	/* Update the last bolted SLB.  No write barriers are needed
 	 * here, provided we only update the current CPU's SLB shadow
@@ -401,7 +414,6 @@ BEGIN_FTR_SECTION
 	isync
 
 2:
-END_FTR_SECTION_IFSET(CPU_FTR_SLB)
 	clrrdi	r7,r8,THREAD_SHIFT	/* base of new stack */
 	/* Note: this uses SWITCH_FRAME_SIZE rather than INT_FRAME_SIZE
 	   because we don't need to leave the 288-byte ABI gap at the

arch/powerpc/kernel/head_64.S

@@ -935,7 +935,7 @@ _GLOBAL(do_stab_bolted)
 
 	/* Calculate VSID */
 	/* This is a kernel address, so protovsid = ESID */
-	ASM_VSID_SCRAMBLE(r11, r9)
+	ASM_VSID_SCRAMBLE(r11, r9, 256M)
 	rldic	r9,r11,12,16	/* r9 = vsid << 12 */
 
 	/* Search the primary group for a free entry */

arch/powerpc/kernel/process.c

@@ -564,10 +564,15 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long usp,
 
 #ifdef CONFIG_PPC64
 	if (cpu_has_feature(CPU_FTR_SLB)) {
-		unsigned long sp_vsid = get_kernel_vsid(sp);
+		unsigned long sp_vsid;
 		unsigned long llp = mmu_psize_defs[mmu_linear_psize].sllp;
 
-		sp_vsid <<= SLB_VSID_SHIFT;
+		if (cpu_has_feature(CPU_FTR_1T_SEGMENT))
+			sp_vsid = get_kernel_vsid(sp, MMU_SEGSIZE_1T)
+				<< SLB_VSID_SHIFT_1T;
+		else
+			sp_vsid = get_kernel_vsid(sp, MMU_SEGSIZE_256M)
+				<< SLB_VSID_SHIFT;
 		sp_vsid |= SLB_VSID_KERNEL | llp;
 		p->thread.ksp_vsid = sp_vsid;
 	}