Merge tag 'v3.5-rc4' into drm-intel-next-queued

I want to merge the "no more fake agp on gen6+" patches into
drm-intel-next (well, the last pieces). But a patch in 3.5-rc4 also
adds a new use of dev->agp. Hence the backmarge to sort this out, for
otherwise drm-intel-next merged into Linus' tree would conflict in the
relevant code, things would compile but nicely OOPS at driver load :(

Conflicts in this merge are just simple cases of "both branches
changed/added lines at the same place". The only tricky part is to
keep the order correct wrt the unwind code in case of errors in
intel_ringbuffer.c (and the MI_DISPLAY_FLIP #defines in i915_reg.h
together, obviously).

Conflicts:
	drivers/gpu/drm/i915/i915_reg.h
	drivers/gpu/drm/i915/intel_ringbuffer.c

Signed-Off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

9 files changed, 245 insertions, 110 deletions

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index a42d3ae3964..ff5bdee4716 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -241,6 +241,26 @@ config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE
 	default 0 if !BOOTPARAM_SOFTLOCKUP_PANIC
 	default 1 if BOOTPARAM_SOFTLOCKUP_PANIC
 
+config PANIC_ON_OOPS
+	bool "Panic on Oops" if EXPERT
+	default n
+	help
+	  Say Y here to enable the kernel to panic when it oopses. This
+	  has the same effect as setting oops=panic on the kernel command
+	  line.
+
+	  This feature is useful to ensure that the kernel does not do
+	  anything erroneous after an oops which could result in data
+	  corruption or other issues.
+
+	  Say N if unsure.
+
+config PANIC_ON_OOPS_VALUE
+	int
+	range 0 1
+	default 0 if !PANIC_ON_OOPS
+	default 1 if PANIC_ON_OOPS
+
 config DETECT_HUNG_TASK
 	bool "Detect Hung Tasks"
 	depends on DEBUG_KERNEL
diff --git a/lib/btree.c b/lib/btree.c
index e5ec1e9c1aa..f9a484676cb 100644
--- a/lib/btree.c
+++ b/lib/btree.c
@@ -319,8 +319,8 @@ void *btree_get_prev(struct btree_head *head, struct btree_geo *geo,
 
 	if (head->height == 0)
 		return NULL;
-retry:
 	longcpy(key, __key, geo->keylen);
+retry:
 	dec_key(geo, key);
 
 	node = head->node;
@@ -351,7 +351,7 @@ retry:
 	}
 miss:
 	if (retry_key) {
-		__key = retry_key;
+		longcpy(key, retry_key, geo->keylen);
 		retry_key = NULL;
 		goto retry;
 	}
@@ -509,6 +509,7 @@ retry:
 int btree_insert(struct btree_head *head, struct btree_geo *geo,
 		unsigned long *key, void *val, gfp_t gfp)
 {
+	BUG_ON(!val);
 	return btree_insert_level(head, geo, key, val, 1, gfp);
 }
 EXPORT_SYMBOL_GPL(btree_insert);
diff --git a/lib/dynamic_queue_limits.c b/lib/dynamic_queue_limits.c
index 6ab4587d052..0777c5a45fa 100644
--- a/lib/dynamic_queue_limits.c
+++ b/lib/dynamic_queue_limits.c
@@ -10,23 +10,27 @@
 #include <linux/jiffies.h>
 #include <linux/dynamic_queue_limits.h>
 
-#define POSDIFF(A, B) ((A) > (B) ? (A) - (B) : 0)
+#define POSDIFF(A, B) ((int)((A) - (B)) > 0 ? (A) - (B) : 0)
+#define AFTER_EQ(A, B) ((int)((A) - (B)) >= 0)
 
 /* Records completed count and recalculates the queue limit */
 void dql_completed(struct dql *dql, unsigned int count)
 {
 	unsigned int inprogress, prev_inprogress, limit;
-	unsigned int ovlimit, all_prev_completed, completed;
+	unsigned int ovlimit, completed, num_queued;
+	bool all_prev_completed;
+
+	num_queued = ACCESS_ONCE(dql->num_queued);
 
 	/* Can't complete more than what's in queue */
-	BUG_ON(count > dql->num_queued - dql->num_completed);
+	BUG_ON(count > num_queued - dql->num_completed);
 
 	completed = dql->num_completed + count;
 	limit = dql->limit;
-	ovlimit = POSDIFF(dql->num_queued - dql->num_completed, limit);
-	inprogress = dql->num_queued - completed;
+	ovlimit = POSDIFF(num_queued - dql->num_completed, limit);
+	inprogress = num_queued - completed;
 	prev_inprogress = dql->prev_num_queued - dql->num_completed;
-	all_prev_completed = POSDIFF(completed, dql->prev_num_queued);
+	all_prev_completed = AFTER_EQ(completed, dql->prev_num_queued);
 
 	if ((ovlimit && !inprogress) ||
 	    (dql->prev_ovlimit && all_prev_completed)) {
@@ -104,7 +108,7 @@ void dql_completed(struct dql *dql, unsigned int count)
 	dql->prev_ovlimit = ovlimit;
 	dql->prev_last_obj_cnt = dql->last_obj_cnt;
 	dql->num_completed = completed;
-	dql->prev_num_queued = dql->num_queued;
+	dql->prev_num_queued = num_queued;
 }
 EXPORT_SYMBOL(dql_completed);
 
diff --git a/lib/fault-inject.c b/lib/fault-inject.c
index 6805453c18e..f7210ad6cff 100644
--- a/lib/fault-inject.c
+++ b/lib/fault-inject.c
@@ -101,6 +101,10 @@ static inline bool fail_stacktrace(struct fault_attr *attr)
 
 bool should_fail(struct fault_attr *attr, ssize_t size)
 {
+	/* No need to check any other properties if the probability is 0 */
+	if (attr->probability == 0)
+		return false;
+
 	if (attr->task_filter && !fail_task(attr, current))
 		return false;
 
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index d7c878cc006..e7964296fd5 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -686,6 +686,9 @@ void **radix_tree_next_chunk(struct radix_tree_root *root,
 	 * during iterating; it can be zero only at the beginning.
 	 * And we cannot overflow iter->next_index in a single step,
 	 * because RADIX_TREE_MAP_SHIFT < BITS_PER_LONG.
+	 *
+	 * This condition also used by radix_tree_next_slot() to stop
+	 * contiguous iterating, and forbid swithing to the next chunk.
 	 */
 	index = iter->next_index;
 	if (!index && iter->index)
diff --git a/lib/raid6/recov.c b/lib/raid6/recov.c
index 1805a5cc5da..a95bccb8497 100644
--- a/lib/raid6/recov.c
+++ b/lib/raid6/recov.c
@@ -22,8 +22,8 @@
 #include <linux/raid/pq.h>
 
 /* Recover two failed data blocks. */
-void raid6_2data_recov_intx1(int disks, size_t bytes, int faila, int failb,
-		       void **ptrs)
+static void raid6_2data_recov_intx1(int disks, size_t bytes, int faila,
+		int failb, void **ptrs)
 {
 	u8 *p, *q, *dp, *dq;
 	u8 px, qx, db;
@@ -66,7 +66,8 @@ void raid6_2data_recov_intx1(int disks, size_t bytes, int faila, int failb,
 }
 
 /* Recover failure of one data block plus the P block */
-void raid6_datap_recov_intx1(int disks, size_t bytes, int faila, void **ptrs)
+static void raid6_datap_recov_intx1(int disks, size_t bytes, int faila,
+		void **ptrs)
 {
 	u8 *p, *q, *dq;
 	const u8 *qmul;		/* Q multiplier table */
diff --git a/lib/raid6/recov_ssse3.c b/lib/raid6/recov_ssse3.c
index 37ae6193055..ecb710c0b4d 100644
--- a/lib/raid6/recov_ssse3.c
+++ b/lib/raid6/recov_ssse3.c
@@ -19,8 +19,8 @@ static int raid6_has_ssse3(void)
 		boot_cpu_has(X86_FEATURE_SSSE3);
 }
 
-void raid6_2data_recov_ssse3(int disks, size_t bytes, int faila, int failb,
-		       void **ptrs)
+static void raid6_2data_recov_ssse3(int disks, size_t bytes, int faila,
+		int failb, void **ptrs)
 {
 	u8 *p, *q, *dp, *dq;
 	const u8 *pbmul;	/* P multiplier table for B data */
@@ -194,7 +194,8 @@ void raid6_2data_recov_ssse3(int disks, size_t bytes, int faila, int failb,
 }
 
 
-void raid6_datap_recov_ssse3(int disks, size_t bytes, int faila, void **ptrs)
+static void raid6_datap_recov_ssse3(int disks, size_t bytes, int faila,
+		void **ptrs)
 {
 	u8 *p, *q, *dq;
 	const u8 *qmul;		/* Q multiplier table */
diff --git a/lib/spinlock_debug.c b/lib/spinlock_debug.c
index d0ec4f3d159..e91fbc23fff 100644
--- a/lib/spinlock_debug.c
+++ b/lib/spinlock_debug.c
@@ -118,7 +118,7 @@ static void __spin_lock_debug(raw_spinlock_t *lock)
 		/* lockup suspected: */
 		if (print_once) {
 			print_once = 0;
-			spin_dump(lock, "lockup");
+			spin_dump(lock, "lockup suspected");
 #ifdef CONFIG_SMP
 			trigger_all_cpu_backtrace();
 #endif
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 5391299c1e7..c3f36d415bd 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -112,106 +112,199 @@ int skip_atoi(const char **s)
 /* Decimal conversion is by far the most typical, and is used
  * for /proc and /sys data. This directly impacts e.g. top performance
  * with many processes running. We optimize it for speed
- * using code from
- * http://www.cs.uiowa.edu/~jones/bcd/decimal.html
- * (with permission from the author, Douglas W. Jones). */
+ * using ideas described at <http://www.cs.uiowa.edu/~jones/bcd/divide.html>
+ * (with permission from the author, Douglas W. Jones).
+ */
 
-/* Formats correctly any integer in [0,99999].
- * Outputs from one to five digits depending on input.
- * On i386 gcc 4.1.2 -O2: ~250 bytes of code. */
+#if BITS_PER_LONG != 32 || BITS_PER_LONG_LONG != 64
+/* Formats correctly any integer in [0, 999999999] */
 static noinline_for_stack
-char *put_dec_trunc(char *buf, unsigned q)
+char *put_dec_full9(char *buf, unsigned q)
 {
-	unsigned d3, d2, d1, d0;
-	d1 = (q>>4) & 0xf;
-	d2 = (q>>8) & 0xf;
-	d3 = (q>>12);
-
-	d0 = 6*(d3 + d2 + d1) + (q & 0xf);
-	q = (d0 * 0xcd) >> 11;
-	d0 = d0 - 10*q;
-	*buf++ = d0 + '0'; /* least significant digit */
-	d1 = q + 9*d3 + 5*d2 + d1;
-	if (d1 != 0) {
-		q = (d1 * 0xcd) >> 11;
-		d1 = d1 - 10*q;
-		*buf++ = d1 + '0'; /* next digit */
-
-		d2 = q + 2*d2;
-		if ((d2 != 0) || (d3 != 0)) {
-			q = (d2 * 0xd) >> 7;
-			d2 = d2 - 10*q;
-			*buf++ = d2 + '0'; /* next digit */
-
-			d3 = q + 4*d3;
-			if (d3 != 0) {
-				q = (d3 * 0xcd) >> 11;
-				d3 = d3 - 10*q;
-				*buf++ = d3 + '0';  /* next digit */
-				if (q != 0)
-					*buf++ = q + '0'; /* most sign. digit */
-			}
-		}
-	}
+	unsigned r;
 
+	/*
+	 * Possible ways to approx. divide by 10
+	 * (x * 0x1999999a) >> 32 x < 1073741829 (multiply must be 64-bit)
+	 * (x * 0xcccd) >> 19     x <      81920 (x < 262149 when 64-bit mul)
+	 * (x * 0x6667) >> 18     x <      43699
+	 * (x * 0x3334) >> 17     x <      16389
+	 * (x * 0x199a) >> 16     x <      16389
+	 * (x * 0x0ccd) >> 15     x <      16389
+	 * (x * 0x0667) >> 14     x <       2739
+	 * (x * 0x0334) >> 13     x <       1029
+	 * (x * 0x019a) >> 12     x <       1029
+	 * (x * 0x00cd) >> 11     x <       1029 shorter code than * 0x67 (on i386)
+	 * (x * 0x0067) >> 10     x <        179
+	 * (x * 0x0034) >>  9     x <         69 same
+	 * (x * 0x001a) >>  8     x <         69 same
+	 * (x * 0x000d) >>  7     x <         69 same, shortest code (on i386)
+	 * (x * 0x0007) >>  6     x <         19
+	 * See <http://www.cs.uiowa.edu/~jones/bcd/divide.html>
+	 */
+	r      = (q * (uint64_t)0x1999999a) >> 32;
+	*buf++ = (q - 10 * r) + '0'; /* 1 */
+	q      = (r * (uint64_t)0x1999999a) >> 32;
+	*buf++ = (r - 10 * q) + '0'; /* 2 */
+	r      = (q * (uint64_t)0x1999999a) >> 32;
+	*buf++ = (q - 10 * r) + '0'; /* 3 */
+	q      = (r * (uint64_t)0x1999999a) >> 32;
+	*buf++ = (r - 10 * q) + '0'; /* 4 */
+	r      = (q * (uint64_t)0x1999999a) >> 32;
+	*buf++ = (q - 10 * r) + '0'; /* 5 */
+	/* Now value is under 10000, can avoid 64-bit multiply */
+	q      = (r * 0x199a) >> 16;
+	*buf++ = (r - 10 * q)  + '0'; /* 6 */
+	r      = (q * 0xcd) >> 11;
+	*buf++ = (q - 10 * r)  + '0'; /* 7 */
+	q      = (r * 0xcd) >> 11;
+	*buf++ = (r - 10 * q) + '0'; /* 8 */
+	*buf++ = q + '0'; /* 9 */
 	return buf;
 }
-/* Same with if's removed. Always emits five digits */
+#endif
+
+/* Similar to above but do not pad with zeros.
+ * Code can be easily arranged to print 9 digits too, but our callers
+ * always call put_dec_full9() instead when the number has 9 decimal digits.
+ */
 static noinline_for_stack
-char *put_dec_full(char *buf, unsigned q)
+char *put_dec_trunc8(char *buf, unsigned r)
 {
-	/* BTW, if q is in [0,9999], 8-bit ints will be enough, */
-	/* but anyway, gcc produces better code with full-sized ints */
-	unsigned d3, d2, d1, d0;
-	d1 = (q>>4) & 0xf;
-	d2 = (q>>8) & 0xf;
-	d3 = (q>>12);
+	unsigned q;
+
+	/* Copy of previous function's body with added early returns */
+	q      = (r * (uint64_t)0x1999999a) >> 32;
+	*buf++ = (r - 10 * q) + '0'; /* 2 */
+	if (q == 0)
+		return buf;
+	r      = (q * (uint64_t)0x1999999a) >> 32;
+	*buf++ = (q - 10 * r) + '0'; /* 3 */
+	if (r == 0)
+		return buf;
+	q      = (r * (uint64_t)0x1999999a) >> 32;
+	*buf++ = (r - 10 * q) + '0'; /* 4 */
+	if (q == 0)
+		return buf;
+	r      = (q * (uint64_t)0x1999999a) >> 32;
+	*buf++ = (q - 10 * r) + '0'; /* 5 */
+	if (r == 0)
+		return buf;
+	q      = (r * 0x199a) >> 16;
+	*buf++ = (r - 10 * q)  + '0'; /* 6 */
+	if (q == 0)
+		return buf;
+	r      = (q * 0xcd) >> 11;
+	*buf++ = (q - 10 * r)  + '0'; /* 7 */
+	if (r == 0)
+		return buf;
+	q      = (r * 0xcd) >> 11;
+	*buf++ = (r - 10 * q) + '0'; /* 8 */
+	if (q == 0)
+		return buf;
+	*buf++ = q + '0'; /* 9 */
+	return buf;
+}
 
-	/*
-	 * Possible ways to approx. divide by 10
-	 * gcc -O2 replaces multiply with shifts and adds
-	 * (x * 0xcd) >> 11: 11001101 - shorter code than * 0x67 (on i386)
-	 * (x * 0x67) >> 10:  1100111
-	 * (x * 0x34) >> 9:    110100 - same
-	 * (x * 0x1a) >> 8:     11010 - same
-	 * (x * 0x0d) >> 7:      1101 - same, shortest code (on i386)
-	 */
-	d0 = 6*(d3 + d2 + d1) + (q & 0xf);
-	q = (d0 * 0xcd) >> 11;
-	d0 = d0 - 10*q;
-	*buf++ = d0 + '0';
-	d1 = q + 9*d3 + 5*d2 + d1;
-		q = (d1 * 0xcd) >> 11;
-		d1 = d1 - 10*q;
-		*buf++ = d1 + '0';
-
-		d2 = q + 2*d2;
-			q = (d2 * 0xd) >> 7;
-			d2 = d2 - 10*q;
-			*buf++ = d2 + '0';
-
-			d3 = q + 4*d3;
-				q = (d3 * 0xcd) >> 11; /* - shorter code */
-				/* q = (d3 * 0x67) >> 10; - would also work */
-				d3 = d3 - 10*q;
-				*buf++ = d3 + '0';
-					*buf++ = q + '0';
+/* There are two algorithms to print larger numbers.
+ * One is generic: divide by 1000000000 and repeatedly print
+ * groups of (up to) 9 digits. It's conceptually simple,
+ * but requires a (unsigned long long) / 1000000000 division.
+ *
+ * Second algorithm splits 64-bit unsigned long long into 16-bit chunks,
+ * manipulates them cleverly and generates groups of 4 decimal digits.
+ * It so happens that it does NOT require long long division.
+ *
+ * If long is > 32 bits, division of 64-bit values is relatively easy,
+ * and we will use the first algorithm.
+ * If long long is > 64 bits (strange architecture with VERY large long long),
+ * second algorithm can't be used, and we again use the first one.
+ *
+ * Else (if long is 32 bits and long long is 64 bits) we use second one.
+ */
 
-	return buf;
+#if BITS_PER_LONG != 32 || BITS_PER_LONG_LONG != 64
+
+/* First algorithm: generic */
+
+static
+char *put_dec(char *buf, unsigned long long n)
+{
+	if (n >= 100*1000*1000) {
+		while (n >= 1000*1000*1000)
+			buf = put_dec_full9(buf, do_div(n, 1000*1000*1000));
+		if (n >= 100*1000*1000)
+			return put_dec_full9(buf, n);
+	}
+	return put_dec_trunc8(buf, n);
 }
-/* No inlining helps gcc to use registers better */
+
+#else
+
+/* Second algorithm: valid only for 64-bit long longs */
+
 static noinline_for_stack
-char *put_dec(char *buf, unsigned long long num)
+char *put_dec_full4(char *buf, unsigned q)
 {
-	while (1) {
-		unsigned rem;
-		if (num < 100000)
-			return put_dec_trunc(buf, num);
-		rem = do_div(num, 100000);
-		buf = put_dec_full(buf, rem);
-	}
+	unsigned r;
+	r      = (q * 0xcccd) >> 19;
+	*buf++ = (q - 10 * r) + '0';
+	q      = (r * 0x199a) >> 16;
+	*buf++ = (r - 10 * q)  + '0';
+	r      = (q * 0xcd) >> 11;
+	*buf++ = (q - 10 * r)  + '0';
+	*buf++ = r + '0';
+	return buf;
 }
 
+/* Based on code by Douglas W. Jones found at
+ * <http://www.cs.uiowa.edu/~jones/bcd/decimal.html#sixtyfour>
+ * (with permission from the author).
+ * Performs no 64-bit division and hence should be fast on 32-bit machines.
+ */
+static
+char *put_dec(char *buf, unsigned long long n)
+{
+	uint32_t d3, d2, d1, q, h;
+
+	if (n < 100*1000*1000)
+		return put_dec_trunc8(buf, n);
+
+	d1  = ((uint32_t)n >> 16); /* implicit "& 0xffff" */
+	h   = (n >> 32);
+	d2  = (h      ) & 0xffff;
+	d3  = (h >> 16); /* implicit "& 0xffff" */
+
+	q   = 656 * d3 + 7296 * d2 + 5536 * d1 + ((uint32_t)n & 0xffff);
+
+	buf = put_dec_full4(buf, q % 10000);
+	q   = q / 10000;
+
+	d1  = q + 7671 * d3 + 9496 * d2 + 6 * d1;
+	buf = put_dec_full4(buf, d1 % 10000);
+	q   = d1 / 10000;
+
+	d2  = q + 4749 * d3 + 42 * d2;
+	buf = put_dec_full4(buf, d2 % 10000);
+	q   = d2 / 10000;
+
+	d3  = q + 281 * d3;
+	if (!d3)
+		goto done;
+	buf = put_dec_full4(buf, d3 % 10000);
+	q   = d3 / 10000;
+	if (!q)
+		goto done;
+	buf = put_dec_full4(buf, q);
+ done:
+	while (buf[-1] == '0')
+		--buf;
+
+	return buf;
+}
+
+#endif
+
 /*
  * Convert passed number to decimal string.
  * Returns the length of string.  On buffer overflow, returns 0.
@@ -220,16 +313,22 @@ char *put_dec(char *buf, unsigned long long num)
  */
 int num_to_str(char *buf, int size, unsigned long long num)
 {
-	char tmp[21];		/* Enough for 2^64 in decimal */
+	char tmp[sizeof(num) * 3];
 	int idx, len;
 
-	len = put_dec(tmp, num) - tmp;
+	/* put_dec() may work incorrectly for num = 0 (generate "", not "0") */
+	if (num <= 9) {
+		tmp[0] = '0' + num;
+		len = 1;
+	} else {
+		len = put_dec(tmp, num) - tmp;
+	}
 
 	if (len > size)
 		return 0;
 	for (idx = 0; idx < len; ++idx)
 		buf[idx] = tmp[len - idx - 1];
-	return  len;
+	return len;
 }
 
 #define ZEROPAD	1		/* pad with zero */
@@ -314,8 +413,8 @@ char *number(char *buf, char *end, unsigned long long num,
 
 	/* generate full string in tmp[], in reverse order */
 	i = 0;
-	if (num == 0)
-		tmp[i++] = '0';
+	if (num < spec.base)
+		tmp[i++] = digits[num] | locase;
 	/* Generic code, for any base:
 	else do {
 		tmp[i++] = (digits[do_div(num,base)] | locase);
@@ -611,7 +710,7 @@ char *ip4_string(char *p, const u8 *addr, const char *fmt)
 	}
 	for (i = 0; i < 4; i++) {
 		char temp[3];	/* hold each IP quad in reverse order */
-		int digits = put_dec_trunc(temp, addr[index]) - temp;
+		int digits = put_dec_trunc8(temp, addr[index]) - temp;
 		if (leading_zeros) {
 			if (digits < 3)
 				*p++ = '0';
@@ -870,13 +969,15 @@ static noinline_for_stack
 char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 	      struct printf_spec spec)
 {
+	int default_width = 2 * sizeof(void *) + (spec.flags & SPECIAL ? 2 : 0);
+
 	if (!ptr && *fmt != 'K') {
 		/*
 		 * Print (null) with the same width as a pointer so it makes
 		 * tabular output look nice.
 		 */
 		if (spec.field_width == -1)
-			spec.field_width = 2 * sizeof(void *);
+			spec.field_width = default_width;
 		return string(buf, end, "(null)", spec);
 	}
 
@@ -931,7 +1032,7 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 		 */
 		if (in_irq() || in_serving_softirq() || in_nmi()) {
 			if (spec.field_width == -1)
-				spec.field_width = 2 * sizeof(void *);
+				spec.field_width = default_width;
 			return string(buf, end, "pK-error", spec);
 		}
 		if (!((kptr_restrict == 0) ||
@@ -948,7 +1049,7 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 	}
 	spec.flags |= SMALL;
 	if (spec.field_width == -1) {
-		spec.field_width = 2 * sizeof(void *);
+		spec.field_width = default_width;
 		spec.flags |= ZEROPAD;
 	}
 	spec.base = 16;