ARM: redo TTBR setup code for LPAE

Re-engineer the LPAE TTBR setup code.  Rather than passing some shifted
address in order to fit in a CPU register, pass either a full physical
address (in the case of r4, r5 for TTBR0) or a PFN (for TTBR1).

This removes the ARCH_PGD_SHIFT hack, and the last dangerous user of
cpu_set_ttbr() in the secondary CPU startup code path (which was there
to re-set TTBR1 to the appropriate high physical address space on
Keystone2.)

Tested-by: Murali Karicheri <m-karicheri2@ti.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>

3 files changed, 38 insertions, 16 deletions

diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index aebfbf79a1a3..84da14b7cd04 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -123,7 +123,7 @@ ENTRY(secondary_startup)
 ENDPROC(secondary_startup)
 
 ENTRY(__secondary_switched)
-	ldr	sp, [r7, #8]			@ set up the stack pointer
+	ldr	sp, [r7, #12]			@ set up the stack pointer
 	mov	fp, #0
 	b	secondary_start_kernel
 ENDPROC(__secondary_switched)
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 3637973a9708..7304b4c44b52 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -131,13 +131,30 @@ ENTRY(stext)
 	 * The following calls CPU specific code in a position independent
 	 * manner.  See arch/arm/mm/proc-*.S for details.  r10 = base of
 	 * xxx_proc_info structure selected by __lookup_processor_type
-	 * above.  On return, the CPU will be ready for the MMU to be
-	 * turned on, and r0 will hold the CPU control register value.
+	 * above.
+	 *
+	 * The processor init function will be called with:
+	 *  r1 - machine type
+	 *  r2 - boot data (atags/dt) pointer
+	 *  r4 - translation table base (low word)
+	 *  r5 - translation table base (high word, if LPAE)
+	 *  r8 - translation table base 1 (pfn if LPAE)
+	 *  r9 - cpuid
+	 *  r13 - virtual address for __enable_mmu -> __turn_mmu_on
+	 *
+	 * On return, the CPU will be ready for the MMU to be turned on,
+	 * r0 will hold the CPU control register value, r1, r2, r4, and
+	 * r9 will be preserved.  r5 will also be preserved if LPAE.
 	 */
 	ldr	r13, =__mmap_switched		@ address to jump to after
 						@ mmu has been enabled
 	adr	lr, BSYM(1f)			@ return (PIC) address
+#ifdef CONFIG_ARM_LPAE
+	mov	r5, #0				@ high TTBR0
+	mov	r8, r4, lsr #12			@ TTBR1 is swapper_pg_dir pfn
+#else
 	mov	r8, r4				@ set TTBR1 to swapper_pg_dir
+#endif
 	ldr	r12, [r10, #PROCINFO_INITFUNC]
 	add	r12, r12, r10
 	ret	r12
@@ -158,7 +175,7 @@ ENDPROC(stext)
  *
  * Returns:
  *  r0, r3, r5-r7 corrupted
- *  r4 = page table (see ARCH_PGD_SHIFT in asm/memory.h)
+ *  r4 = physical page table address
  */
 __create_page_tables:
 	pgtbl	r4, r8				@ page table address
@@ -333,7 +350,6 @@ __create_page_tables:
 #endif
 #ifdef CONFIG_ARM_LPAE
 	sub	r4, r4, #0x1000		@ point to the PGD table
-	mov	r4, r4, lsr #ARCH_PGD_SHIFT
 #endif
 	ret	lr
 ENDPROC(__create_page_tables)
@@ -381,9 +397,9 @@ ENTRY(secondary_startup)
 	adr	r4, __secondary_data
 	ldmia	r4, {r5, r7, r12}		@ address to jump to after
 	sub	lr, r4, r5			@ mmu has been enabled
-	ldr	r4, [r7, lr]			@ get secondary_data.pgdir
-	add	r7, r7, #4
-	ldr	r8, [r7, lr]			@ get secondary_data.swapper_pg_dir
+	add	r3, r7, lr
+	ldrd	r4, [r3, #0]			@ get secondary_data.pgdir
+	ldr	r8, [r3, #8]			@ get secondary_data.swapper_pg_dir
 	adr	lr, BSYM(__enable_mmu)		@ return address
 	mov	r13, r12			@ __secondary_switched address
 	ldr	r12, [r10, #PROCINFO_INITFUNC]
@@ -397,7 +413,7 @@ ENDPROC(secondary_startup_arm)
 	 * r6  = &secondary_data
 	 */
 ENTRY(__secondary_switched)
-	ldr	sp, [r7, #4]			@ get secondary_data.stack
+	ldr	sp, [r7, #12]			@ get secondary_data.stack
 	mov	fp, #0
 	b	secondary_start_kernel
 ENDPROC(__secondary_switched)
@@ -416,12 +432,14 @@ __secondary_data:
 /*
  * Setup common bits before finally enabling the MMU.  Essentially
  * this is just loading the page table pointer and domain access
- * registers.
+ * registers.  All these registers need to be preserved by the
+ * processor setup function (or set in the case of r0)
  *
  *  r0  = cp#15 control register
  *  r1  = machine ID
  *  r2  = atags or dtb pointer
- *  r4  = page table (see ARCH_PGD_SHIFT in asm/memory.h)
+ *  r4  = TTBR pointer (low word)
+ *  r5  = TTBR pointer (high word if LPAE)
  *  r9  = processor ID
  *  r13 = *virtual* address to jump to upon completion
  */
@@ -440,7 +458,9 @@ __enable_mmu:
 #ifdef CONFIG_CPU_ICACHE_DISABLE
 	bic	r0, r0, #CR_I
 #endif
-#ifndef CONFIG_ARM_LPAE
+#ifdef CONFIG_ARM_LPAE
+	mcrr	p15, 0, r4, r5, c2		@ load TTBR0
+#else
 	mov	r5, #(domain_val(DOMAIN_USER, DOMAIN_MANAGER) | \
 		      domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) | \
 		      domain_val(DOMAIN_TABLE, DOMAIN_MANAGER) | \
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index cca5b8758185..90dfbedfbfb8 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -86,9 +86,11 @@ void __init smp_set_ops(struct smp_operations *ops)
 
 static unsigned long get_arch_pgd(pgd_t *pgd)
 {
-	phys_addr_t pgdir = virt_to_idmap(pgd);
-	BUG_ON(pgdir & ARCH_PGD_MASK);
-	return pgdir >> ARCH_PGD_SHIFT;
+#ifdef CONFIG_ARM_LPAE
+	return __phys_to_pfn(virt_to_phys(pgd));
+#else
+	return virt_to_phys(pgd);
+#endif
 }
 
 int __cpu_up(unsigned int cpu, struct task_struct *idle)
@@ -108,7 +110,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 #endif
 
 #ifdef CONFIG_MMU
-	secondary_data.pgdir = get_arch_pgd(idmap_pgd);
+	secondary_data.pgdir = virt_to_phys(idmap_pgd);
 	secondary_data.swapper_pg_dir = get_arch_pgd(swapper_pg_dir);
 #endif
 	sync_cache_w(&secondary_data);