MIPS: Align swapper_pg_dir to 64K for better TLB Refill code.

We can save an instruction in the TLB Refill path for kernel mappings
by aligning swapper_pg_dir on a 64K boundary.  The address of
swapper_pg_dir can be generated with a single LUI instead of
LUI/{D}ADDUI.

The alignment of __init_end is bumped up to 64K so there are no holes
between it and swapper_pg_dir, which is placed at the very beginning
of .bss.

The alignment of invalid_pmd_table and invalid_pte_table can be
relaxed to PAGE_SIZE.  We do this by using __page_aligned_bss, which
has the added benefit of eliminating alignment holes in .bss.
Signed-off-by: David Daney <david.daney@cavium.com>
Cc: linux-mips@linux-mips.org
Cc: linux-arch@vger.kernel.org,
Cc: linux-kernel@vger.kernel.org
Acked-by: Arnd Bergmann <arnd@arndb.de>
Patchwork: https://patchwork.linux-mips.org/patch/4220/Signed-off-by: Ralf Baechle <ralf@linux-mips.org>

arch/mips/kernel/vmlinux.lds.S

 #include <asm/asm-offsets.h>
 #include <asm/page.h>
 #include <asm/thread_info.h>
+
+/*
+ * Put .bss..swapper_pg_dir as the first thing in .bss. This will
+ * ensure that it has .bss alignment (64K).
+ */
+#define BSS_FIRST_SECTIONS *(.bss..swapper_pg_dir)
+
 #include <asm-generic/vmlinux.lds.h>
 
 #undef mips
@@ -119,11 +126,21 @@ SECTIONS
 	}
 
 	PERCPU_SECTION(1 << CONFIG_MIPS_L1_CACHE_SHIFT)
-	. = ALIGN(PAGE_SIZE);
+	/*
+	 * Align to 64K in attempt to eliminate holes before the
+	 * .bss..swapper_pg_dir section at the start of .bss.  This
+	 * also satisfies PAGE_SIZE alignment as the largest page size
+	 * allowed is 64K.
+	 */
+	. = ALIGN(0x10000);
 	__init_end = .;
 	/* freed after init ends here */
 
-	BSS_SECTION(0, 0, 0)
+	/*
+	 * Force .bss to 64K alignment so that .bss..swapper_pg_dir
+	 * gets that alignment.  .sbss should be empty, so there will be
+	 * no holes after __init_end. */
+	BSS_SECTION(0, 0x10000, 0)
 
 	_end = . ;
 

arch/mips/mm/init.c

@@ -469,19 +469,20 @@ void __init_refok free_initmem(void)
 #ifndef CONFIG_MIPS_PGD_C0_CONTEXT
 unsigned long pgd_current[NR_CPUS];
 #endif
-/*
- * On 64-bit we've got three-level pagetables with a slightly
- * different layout ...
- */
-#define __page_aligned(order) __attribute__((__aligned__(PAGE_SIZE<<order)))
 
 /*
  * gcc 3.3 and older have trouble determining that PTRS_PER_PGD and PGD_ORDER
  * are constants.  So we use the variants from asm-offset.h until that gcc
  * will officially be retired.
+ *
+ * Align swapper_pg_dir in to 64K, allows its address to be loaded
+ * with a single LUI instruction in the TLB handlers.  If we used
+ * __aligned(64K), its size would get rounded up to the alignment
+ * size, and waste space.  So we place it in its own section and align
+ * it in the linker script.
  */
-pgd_t swapper_pg_dir[_PTRS_PER_PGD] __page_aligned(_PGD_ORDER);
+pgd_t swapper_pg_dir[_PTRS_PER_PGD] __section(.bss..swapper_pg_dir);
 #ifndef __PAGETABLE_PMD_FOLDED
-pmd_t invalid_pmd_table[PTRS_PER_PMD] __page_aligned(PMD_ORDER);
+pmd_t invalid_pmd_table[PTRS_PER_PMD] __page_aligned_bss;
 #endif
-pte_t invalid_pte_table[PTRS_PER_PTE] __page_aligned(PTE_ORDER);
+pte_t invalid_pte_table[PTRS_PER_PTE] __page_aligned_bss;