sparc64: Validate linear D-TLB misses.

When page alloc debugging is not enabled, we essentially accept any
virtual address for linear kernel TLB misses.  But with kgdb, kernel
address probing, and other facilities we can try to access arbitrary
crap.

So, make sure the address we miss on will translate to physical memory
that actually exists.

In order to make this work we have to embed the valid address bitmap
into the kernel image.  And in order to make that less expensive we
make an adjustment, in that the max physical memory address is
decreased to "1 << 41", even on the chips that support a 42-bit
physical address space.  We can do this because bit 41 indicates
"I/O space" and thus covers non-memory ranges.

The result of this is that:

1) kpte_linear_bitmap shrinks from 2K to 1K in size

2) we need 64K more for the valid address bitmap

We can't let the valid address bitmap be dynamically allocated
once we start using it to validate TLB misses, otherwise we have
crazy issues to deal with wrt. recursive TLB misses and such.

If we're in a TLB miss it could be the deepest trap level that's legal
inside of the cpu.  So if we TLB miss referencing the bitmap, the cpu
will be out of trap levels and enter RED state.

To guard against out-of-range accesses to the bitmap, we have to check
to make sure no bits in the physical address above bit 40 are set.  We
could export and use last_valid_pfn for this check, but that's just an
unnecessary extra memory reference.

On the plus side of all this, since we load all of these translations
into the special 4MB mapping TSB, and we check the TSB first for TLB
misses, there should be absolutely no real cost for these new checks
in the TLB miss path.

Reported-by: heyongli@gmail.com
Signed-off-by: David S. Miller <davem@davemloft.net>

arch/sparc/include/asm/pgtable_64.h

@@ -726,11 +726,17 @@ extern unsigned long pte_file(pte_t);
 extern pte_t pgoff_to_pte(unsigned long);
 #define PTE_FILE_MAX_BITS	(64UL - PAGE_SHIFT - 1UL)
 
-extern unsigned long *sparc64_valid_addr_bitmap;
+extern unsigned long sparc64_valid_addr_bitmap[];
 
 /* Needs to be defined here and not in linux/mm.h, as it is arch dependent */
-#define kern_addr_valid(addr)	\
-	(test_bit(__pa((unsigned long)(addr))>>22, sparc64_valid_addr_bitmap))
+static inline bool kern_addr_valid(unsigned long addr)
+{
+	unsigned long paddr = __pa(addr);
+
+	if ((paddr >> 41UL) != 0UL)
+		return false;
+	return test_bit(paddr >> 22, sparc64_valid_addr_bitmap);
+}
 
 extern int page_in_phys_avail(unsigned long paddr);
 

arch/sparc/kernel/ktlb.S

@@ -151,12 +151,46 @@ kvmap_dtlb_4v:
 	 * Must preserve %g1 and %g6 (TAG).
 	 */
 kvmap_dtlb_tsb4m_miss:
-	sethi		%hi(kpte_linear_bitmap), %g2
-	or		%g2, %lo(kpte_linear_bitmap), %g2
+	/* Clear the PAGE_OFFSET top virtual bits, shift
+	 * down to get PFN, and make sure PFN is in range.
+	 */
+	sllx		%g4, 21, %g5
 
-	/* Clear the PAGE_OFFSET top virtual bits, then shift
-	 * down to get a 256MB physical address index.
+	/* Check to see if we know about valid memory at the 4MB
+	 * chunk this physical address will reside within.
 	 */
+	srlx		%g5, 21 + 41, %g2
+	brnz,pn		%g2, kvmap_dtlb_longpath
+	 nop
+
+	/* This unconditional branch and delay-slot nop gets patched
+	 * by the sethi sequence once the bitmap is properly setup.
+	 */
+	.globl		valid_addr_bitmap_insn
+valid_addr_bitmap_insn:
+	ba,pt		%xcc, 2f
+	 nop
+	.subsection	2
+	.globl		valid_addr_bitmap_patch
+valid_addr_bitmap_patch:
+	sethi		%hi(sparc64_valid_addr_bitmap), %g7
+	or		%g7, %lo(sparc64_valid_addr_bitmap), %g7
+	.previous
+
+	srlx		%g5, 21 + 22, %g2
+	srlx		%g2, 6, %g5
+	and		%g2, 63, %g2
+	sllx		%g5, 3, %g5
+	ldx		[%g7 + %g5], %g5
+	mov		1, %g7
+	sllx		%g7, %g2, %g7
+	andcc		%g5, %g7, %g0
+	be,pn		%xcc, kvmap_dtlb_longpath
+
+2:	 sethi		%hi(kpte_linear_bitmap), %g2
+	or		%g2, %lo(kpte_linear_bitmap), %g2
+
+	/* Get the 256MB physical address index. */
 	sllx		%g4, 21, %g5
 	mov		1, %g7
 	srlx		%g5, 21 + 28, %g5

arch/sparc/mm/init_64.c

@@ -145,7 +145,8 @@ static void __init read_obp_memory(const char *property,
 	     cmp_p64, NULL);
 }
 
-unsigned long *sparc64_valid_addr_bitmap __read_mostly;
+unsigned long sparc64_valid_addr_bitmap[VALID_ADDR_BITMAP_BYTES /
+					sizeof(unsigned long)];
 EXPORT_SYMBOL(sparc64_valid_addr_bitmap);
 
 /* Kernel physical address base and size in bytes.  */
@@ -1874,7 +1875,7 @@ static int pavail_rescan_ents __initdata;
  * memory list again, and make sure it provides at least as much
  * memory as 'pavail' does.
  */
-static void __init setup_valid_addr_bitmap_from_pavail(void)
+static void __init setup_valid_addr_bitmap_from_pavail(unsigned long *bitmap)
 {
 	int i;
 
@@ -1897,8 +1898,7 @@ static void __init setup_valid_addr_bitmap_from_pavail(void)
 
 				if (new_start <= old_start &&
 				    new_end >= (old_start + PAGE_SIZE)) {
-					set_bit(old_start >> 22,
-						sparc64_valid_addr_bitmap);
+					set_bit(old_start >> 22, bitmap);
 					goto do_next_page;
 				}
 			}
@@ -1919,20 +1919,21 @@ static void __init setup_valid_addr_bitmap_from_pavail(void)
 	}
 }
 
+static void __init patch_tlb_miss_handler_bitmap(void)
+{
+	extern unsigned int valid_addr_bitmap_insn[];
+	extern unsigned int valid_addr_bitmap_patch[];
+
+	valid_addr_bitmap_insn[1] = valid_addr_bitmap_patch[1];
+	mb();
+	valid_addr_bitmap_insn[0] = valid_addr_bitmap_patch[0];
+	flushi(&valid_addr_bitmap_insn[0]);
+}
+
 void __init mem_init(void)
 {
 	unsigned long codepages, datapages, initpages;
 	unsigned long addr, last;
-	int i;
-
-	i = last_valid_pfn >> ((22 - PAGE_SHIFT) + 6);
-	i += 1;
-	sparc64_valid_addr_bitmap = (unsigned long *) alloc_bootmem(i << 3);
-	if (sparc64_valid_addr_bitmap == NULL) {
-		prom_printf("mem_init: Cannot alloc valid_addr_bitmap.\n");
-		prom_halt();
-	}
-	memset(sparc64_valid_addr_bitmap, 0, i << 3);
 
 	addr = PAGE_OFFSET + kern_base;
 	last = PAGE_ALIGN(kern_size) + addr;
@@ -1941,15 +1942,19 @@ void __init mem_init(void)
 		addr += PAGE_SIZE;
 	}
 
-	setup_valid_addr_bitmap_from_pavail();
+	setup_valid_addr_bitmap_from_pavail(sparc64_valid_addr_bitmap);
+	patch_tlb_miss_handler_bitmap();
 
 	high_memory = __va(last_valid_pfn << PAGE_SHIFT);
 
 #ifdef CONFIG_NEED_MULTIPLE_NODES
-	for_each_online_node(i) {
-		if (NODE_DATA(i)->node_spanned_pages != 0) {
-			totalram_pages +=
-				free_all_bootmem_node(NODE_DATA(i));
+	{
+		int i;
+		for_each_online_node(i) {
+			if (NODE_DATA(i)->node_spanned_pages != 0) {
+				totalram_pages +=
+					free_all_bootmem_node(NODE_DATA(i));
+			}
 		}
 	}
 #else

arch/sparc/mm/init_64.h

@@ -5,10 +5,13 @@
  * marked non-static so that assembler code can get at them.
  */
 
-#define MAX_PHYS_ADDRESS	(1UL << 42UL)
-#define KPTE_BITMAP_CHUNK_SZ	(256UL * 1024UL * 1024UL)
+#define MAX_PHYS_ADDRESS	(1UL << 41UL)
+#define KPTE_BITMAP_CHUNK_SZ		(256UL * 1024UL * 1024UL)
 #define KPTE_BITMAP_BYTES	\
 	((MAX_PHYS_ADDRESS / KPTE_BITMAP_CHUNK_SZ) / 8)
+#define VALID_ADDR_BITMAP_CHUNK_SZ	(4UL * 1024UL * 1024UL)
+#define VALID_ADDR_BITMAP_BYTES	\
+	((MAX_PHYS_ADDRESS / VALID_ADDR_BITMAP_CHUNK_SZ) / 8)
 
 extern unsigned long kern_linear_pte_xor[2];
 extern unsigned long kpte_linear_bitmap[KPTE_BITMAP_BYTES / sizeof(unsigned long)];