Merge pull request #4 from moddingg33k/kitkat

fixes and suggestions

arch/arm/Kconfig

@@ -1711,6 +1711,9 @@ config HZ
 	default SHMOBILE_TIMER_HZ if ARCH_SHMOBILE
 	default 100
 
+config SCHED_HRTICK
+	def_bool HIGH_RES_TIMERS
+
 config THUMB2_KERNEL
 	bool "Compile the kernel in Thumb-2 mode (EXPERIMENTAL)"
 	depends on CPU_V7 && !CPU_V6 && !CPU_V6K && EXPERIMENTAL

arch/arm/include/asm/types.h

@@ -1,16 +1,48 @@
-#ifndef __ASM_ARM_TYPES_H
-#define __ASM_ARM_TYPES_H
+#ifndef _ASM_TYPES_H
+#define _ASM_TYPES_H
 
 #include <asm-generic/int-ll64.h>
 
 /*
- * These aren't exported outside the kernel to avoid name space clashes
+ * The C99 types uintXX_t that are usually defined in 'stdint.h' are not as
+ * unambiguous on ARM as you would expect. For the types below, there is a
+ * difference on ARM between GCC built for bare metal ARM, GCC built for glibc
+ * and the kernel itself, which results in build errors if you try to build with
+ * -ffreestanding and include 'stdint.h' (such as when you include 'arm_neon.h'
+ * in order to use NEON intrinsics)
+ *
+ * As the typedefs for these types in 'stdint.h' are based on builtin defines
+ * supplied by GCC, we can tweak these to align with the kernel's idea of those
+ * types, so 'linux/types.h' and 'stdint.h' can be safely included from the same
+ * source file (provided that -ffreestanding is used).
+ *
+ *                    int32_t         uint32_t               uintptr_t
+ * bare metal GCC     long            unsigned long          unsigned int
+ * glibc GCC          int             unsigned int           unsigned int
+ * kernel             int             unsigned int           unsigned long
  */
-#ifdef __KERNEL__
 
-#define BITS_PER_LONG 32
+#ifdef __INT32_TYPE__
+#undef __INT32_TYPE__
+#define __INT32_TYPE__		int
+#endif
 
-#endif /* __KERNEL__ */
+#ifdef __UINT32_TYPE__
+#undef __UINT32_TYPE__
+#define __UINT32_TYPE__	unsigned int
+#endif
 
+#ifdef __UINTPTR_TYPE__
+#undef __UINTPTR_TYPE__
+#define __UINTPTR_TYPE__	unsigned long
 #endif
 
+/*
+ * These aren't exported outside the kernel to avoid name space clashes
+ */
+#ifdef __KERNEL__
+
+#define BITS_PER_LONG 32
+
+#endif	/* __KERNEL__ */
+#endif /* _ASM_TYPES_H */

arch/arm/lib/memset.S

@@ -14,27 +14,15 @@
 
 	.text
 	.align	5
-	.word	0
-
-1:	subs	r2, r2, #4		@ 1 do we have enough
-	blt	5f			@ 1 bytes to align with?
-	cmp	r3, #2			@ 1
-	strltb	r1, [r0], #1		@ 1
-	strleb	r1, [r0], #1		@ 1
-	strb	r1, [r0], #1		@ 1
-	add	r2, r2, r3		@ 1 (r2 = r2 - (4 - r3))
-/*
- * The pointer is now aligned and the length is adjusted.  Try doing the
- * memset again.
- */
 
 ENTRY(memset)
 	ands	r3, r0, #3		@ 1 unaligned?
-	bne	1b			@ 1
+	mov	ip, r0			@ preserve r0 as return value
+	bne	6f			@ 1
 /*
- * we know that the pointer in r0 is aligned to a word boundary.
+ * we know that the pointer in ip is aligned to a word boundary.
  */
-	orr	r1, r1, r1, lsl #8
+1:	orr	r1, r1, r1, lsl #8
 	orr	r1, r1, r1, lsl #16
 	mov	r3, r1
 	cmp	r2, #16
@@ -43,29 +31,28 @@ ENTRY(memset)
 #if ! CALGN(1)+0
 
 /*
- * We need an extra register for this loop - save the return address and
- * use the LR
+ * We need 2 extra registers for this loop - use r8 and the LR
  */
-	str	lr, [sp, #-4]!
-	mov	ip, r1
+	stmfd	sp!, {r8, lr}
+	mov	r8, r1
 	mov	lr, r1
 
 2:	subs	r2, r2, #64
-	stmgeia	r0!, {r1, r3, ip, lr}	@ 64 bytes at a time.
-	stmgeia	r0!, {r1, r3, ip, lr}
-	stmgeia	r0!, {r1, r3, ip, lr}
-	stmgeia	r0!, {r1, r3, ip, lr}
+	stmgeia	ip!, {r1, r3, r8, lr}	@ 64 bytes at a time.
+	stmgeia	ip!, {r1, r3, r8, lr}
+	stmgeia	ip!, {r1, r3, r8, lr}
+	stmgeia	ip!, {r1, r3, r8, lr}
 	bgt	2b
-	ldmeqfd	sp!, {pc}		@ Now <64 bytes to go.
+	ldmeqfd	sp!, {r8, pc}		@ Now <64 bytes to go.
 /*
  * No need to correct the count; we're only testing bits from now on
  */
 	tst	r2, #32
-	stmneia	r0!, {r1, r3, ip, lr}
-	stmneia	r0!, {r1, r3, ip, lr}
+	stmneia	ip!, {r1, r3, r8, lr}
+	stmneia	ip!, {r1, r3, r8, lr}
 	tst	r2, #16
-	stmneia	r0!, {r1, r3, ip, lr}
-	ldr	lr, [sp], #4
+	stmneia	ip!, {r1, r3, r8, lr}
+	ldmfd	sp!, {r8, lr}
 
 #else
 
@@ -74,54 +61,63 @@ ENTRY(memset)
  * whole cache lines at once.
  */
 
-	stmfd	sp!, {r4-r7, lr}
+	stmfd	sp!, {r4-r8, lr}
 	mov	r4, r1
 	mov	r5, r1
 	mov	r6, r1
 	mov	r7, r1
-	mov	ip, r1
+	mov	r8, r1
 	mov	lr, r1
 
 	cmp	r2, #96
-	tstgt	r0, #31
+	tstgt	ip, #31
 	ble	3f
 
-	and	ip, r0, #31
-	rsb	ip, ip, #32
-	sub	r2, r2, ip
-	movs	ip, ip, lsl #(32 - 4)
-	stmcsia	r0!, {r4, r5, r6, r7}
-	stmmiia	r0!, {r4, r5}
-	tst	ip, #(1 << 30)
-	mov	ip, r1
-	strne	r1, [r0], #4
+	and	r8, ip, #31
+	rsb	r8, r8, #32
+	sub	r2, r2, r8
+	movs	r8, r8, lsl #(32 - 4)
+	stmcsia	ip!, {r4, r5, r6, r7}
+	stmmiia	ip!, {r4, r5}
+	tst	r8, #(1 << 30)
+	mov	r8, r1
+	strne	r1, [ip], #4
 
 3:	subs	r2, r2, #64
-	stmgeia	r0!, {r1, r3-r7, ip, lr}
-	stmgeia	r0!, {r1, r3-r7, ip, lr}
+	stmgeia	ip!, {r1, r3-r8, lr}
+	stmgeia	ip!, {r1, r3-r8, lr}
 	bgt	3b
-	ldmeqfd	sp!, {r4-r7, pc}
+	ldmeqfd	sp!, {r4-r8, pc}
 
 	tst	r2, #32
-	stmneia	r0!, {r1, r3-r7, ip, lr}
+	stmneia	ip!, {r1, r3-r8, lr}
 	tst	r2, #16
-	stmneia	r0!, {r4-r7}
-	ldmfd	sp!, {r4-r7, lr}
+	stmneia	ip!, {r4-r7}
+	ldmfd	sp!, {r4-r8, lr}
 
 #endif
 
 4:	tst	r2, #8
-	stmneia	r0!, {r1, r3}
+	stmneia	ip!, {r1, r3}
 	tst	r2, #4
-	strne	r1, [r0], #4
+	strne	r1, [ip], #4
 /*
  * When we get here, we've got less than 4 bytes to zero.  We
  * may have an unaligned pointer as well.
  */
 5:	tst	r2, #2
-	strneb	r1, [r0], #1
-	strneb	r1, [r0], #1
+	strneb	r1, [ip], #1
+	strneb	r1, [ip], #1
 	tst	r2, #1
-	strneb	r1, [r0], #1
+	strneb	r1, [ip], #1
 	mov	pc, lr
+
+6:	subs	r2, r2, #4		@ 1 do we have enough
+	blt	5b			@ 1 bytes to align with?
+	cmp	r3, #2			@ 1
+	strltb	r1, [ip], #1		@ 1
+	strleb	r1, [ip], #1		@ 1
+	strb	r1, [ip], #1		@ 1
+	add	r2, r2, r3		@ 1 (r2 = r2 - (4 - r3))
+	b	1b
 ENDPROC(memset)

arch/arm/mach-msm/acpuclock-7627.c

@@ -321,10 +321,11 @@ static struct clkctl_acpu_speed pll0_960_pll1_196_pll2_1200_pll4_1401[] = {
 };
 
 /* 8625 PLL4 @ 1008MHz with GSM capable modem */
+/* Y300-100 */
 static struct clkctl_acpu_speed pll0_960_pll1_245_pll2_1200_pll4_1008_2p0[] = {
 	{ 0, 19200, ACPU_PLL_TCXO, 0, 0, 2400, 3, 0, 30720 },
 	{ 0, 61440, ACPU_PLL_1, 1, 3,  7680, 3, 0, 61440 },
-	{ 0, 122880, ACPU_PLL_1, 1, 1,  15360, 3, 1, 61440 },
+	{ 1, 122880, ACPU_PLL_1, 1, 1,  15360, 3, 1, 61440 },
 	{ 1, 245760, ACPU_PLL_1, 1, 0, 30720, 3, 1, 61440 },
 	{ 0, 300000, ACPU_PLL_2, 2, 3, 37500, 3, 2, 122880 },
 	{ 1, 320000, ACPU_PLL_0, 4, 2, 40000, 3, 2, 122880 },
@@ -1027,7 +1028,7 @@ static void __devinit select_freq_plan(void)
 	 * are using different clock plan based reprogramming method.
 	 */
 	if (cpu_is_msm8625() &&	pll_mhz[ACPU_PLL_4] == 1008) {
-		if (pll_mhz[ACPU_PLL_2] == 245)
+		if (pll_mhz[ACPU_PLL_1] == 245)
 			acpu_freq_tbl =
 				pll0_960_pll1_245_pll2_1200_pll4_1008_2p0;
 		else

arch/arm/mach-msm/msm_rq_stats.c

@@ -32,6 +32,68 @@
 #define DEFAULT_RQ_POLL_JIFFIES 1
 #define DEFAULT_DEF_TIMER_JIFFIES 5
 
+struct rq_data {
+	unsigned int rq_avg;
+	unsigned long rq_poll_jiffies;
+	unsigned long def_timer_jiffies;
+	unsigned long rq_poll_last_jiffy;
+	unsigned long rq_poll_total_jiffies;
+	unsigned long def_timer_last_jiffy;
+	unsigned int def_interval;
+	int64_t def_start_time;
+	struct attribute_group *attr_group;
+	struct kobject *kobj;
+	struct work_struct def_timer_work;
+	int init;
+};
+static struct rq_data rq_info;
+
+static struct workqueue_struct *rq_wq;
+static spinlock_t rq_lock;
+
+void msm_update_rq_stats(void)
+{
+	unsigned long flags, jiffy_gap;
+	unsigned int rq_avg;
+
+	if (!rq_info.init)
+		return;
+
+	jiffy_gap = jiffies - rq_info.rq_poll_last_jiffy;
+	if (jiffy_gap >= rq_info.rq_poll_jiffies) {
+
+		spin_lock_irqsave(&rq_lock, flags);
+
+		if (!rq_info.rq_avg)
+			rq_info.rq_poll_total_jiffies = 0;
+
+		rq_avg = nr_running() * 10;
+
+		if (rq_info.rq_poll_total_jiffies) {
+			rq_avg = (rq_avg * jiffy_gap) +
+				(rq_info.rq_avg *
+				 rq_info.rq_poll_total_jiffies);
+			do_div(rq_avg,
+			       rq_info.rq_poll_total_jiffies + jiffy_gap);
+		}
+
+		rq_info.rq_avg = rq_avg;
+		rq_info.rq_poll_total_jiffies += jiffy_gap;
+		rq_info.rq_poll_last_jiffy = jiffies;
+
+		spin_unlock_irqrestore(&rq_lock, flags);
+	}
+
+	/*
+	 * Wakeup user if needed
+	 */
+	jiffy_gap = jiffies - rq_info.def_timer_last_jiffy;
+	if (jiffy_gap >= rq_info.def_timer_jiffies) {
+		rq_info.def_timer_last_jiffy = jiffies;
+		queue_work(rq_wq, &rq_info.def_timer_work);
+	}
+}
+
 static void def_work_fn(struct work_struct *work)
 {
 	int64_t diff;

block/blk-merge.c

@@ -491,6 +491,10 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	if ((bio->bi_rw & REQ_SECURE) != (rq->bio->bi_rw & REQ_SECURE))
 		return false;
 
+	/* don't merge file system requests and sanitize requests */
+	if ((bio->bi_rw & REQ_SANITIZE) != (rq->bio->bi_rw & REQ_SANITIZE))
+		return false;
+
 	/* different data direction or already started, don't merge */
 	if (bio_data_dir(bio) != rq_data_dir(rq))
 		return false;

block/elevator.c

@@ -72,43 +72,7 @@ static int elv_iosched_allow_merge(struct request *rq, struct bio *bio)
  */
 bool elv_rq_merge_ok(struct request *rq, struct bio *bio)
 {
-	if (!rq_mergeable(rq))
-		return 0;
-
-	/*
-	 * Don't merge file system requests and discard requests
-	 */
-	if ((bio->bi_rw & REQ_DISCARD) != (rq->bio->bi_rw & REQ_DISCARD))
-		return 0;
-
-	/*
-	 * Don't merge discard requests and secure discard requests
-	 */
-	if ((bio->bi_rw & REQ_SECURE) != (rq->bio->bi_rw & REQ_SECURE))
-		return 0;
-
-	/*
-	 * Don't merge sanitize requests
-	 */
-	if ((bio->bi_rw & REQ_SANITIZE) != (rq->bio->bi_rw & REQ_SANITIZE))
-		return 0;
-
-	/*
-	 * different data direction or already started, don't merge
-	 */
-	if (bio_data_dir(bio) != rq_data_dir(rq))
-		return 0;
-
-	/*
-	 * must be same device and not a special request
-	 */
-	if (rq->rq_disk != bio->bi_bdev->bd_disk || rq->special)
-		return 0;
-
-	/*
-	 * only merge integrity protected bio into ditto rq
-	 */
-	if (bio_integrity(bio) != blk_integrity_rq(rq))
+	if (!blk_rq_merge_ok(rq, bio))
 		return 0;
 
 	if (!elv_iosched_allow_merge(rq, bio))