summaryrefslogtreecommitdiffstats
path: root/arch/mips/cavium-octeon/csrc-octeon.c
blob: ce6483a9302a8989a3f26a0bf52e352d08de8f98 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
/*
 * This file is subject to the terms and conditions of the GNU General Public
 * License.  See the file "COPYING" in the main directory of this archive
 * for more details.
 *
 * Copyright (C) 2007 by Ralf Baechle
 * Copyright (C) 2009, 2010 Cavium Networks, Inc.
 */
#include <linux/clocksource.h>
#include <linux/export.h>
#include <linux/init.h>
#include <linux/smp.h>

#include <asm/cpu-info.h>
#include <asm/time.h>

#include <asm/octeon/octeon.h>
#include <asm/octeon/cvmx-ipd-defs.h>
#include <asm/octeon/cvmx-mio-defs.h>

/*
 * Set the current core's cvmcount counter to the value of the
 * IPD_CLK_COUNT.  We do this on all cores as they are brought
 * on-line.  This allows for a read from a local cpu register to
 * access a synchronized counter.
 *
 * On CPU_CAVIUM_OCTEON2 the IPD_CLK_COUNT is scaled by rdiv/sdiv.
 */
void octeon_init_cvmcount(void)
{
	unsigned long flags;
	unsigned loops = 2;
	u64 f = 0;
	u64 rdiv = 0;
	u64 sdiv = 0;
	if (current_cpu_type() == CPU_CAVIUM_OCTEON2) {
		union cvmx_mio_rst_boot rst_boot;
		rst_boot.u64 = cvmx_read_csr(CVMX_MIO_RST_BOOT);
		rdiv = rst_boot.s.c_mul;	/* CPU clock */
		sdiv = rst_boot.s.pnr_mul;	/* I/O clock */
		f = (0x8000000000000000ull / sdiv) * 2;
	}


	/* Clobber loops so GCC will not unroll the following while loop. */
	asm("" : "+r" (loops));

	local_irq_save(flags);
	/*
	 * Loop several times so we are executing from the cache,
	 * which should give more deterministic timing.
	 */
	while (loops--) {
		u64 ipd_clk_count = cvmx_read_csr(CVMX_IPD_CLK_COUNT);
		if (rdiv != 0) {
			ipd_clk_count *= rdiv;
			if (f != 0) {
				asm("dmultu\t%[cnt],%[f]\n\t"
				    "mfhi\t%[cnt]"
				    : [cnt] "+r" (ipd_clk_count),
				      [f] "=r" (f)
				    : : "hi", "lo");
			}
		}
		write_c0_cvmcount(ipd_clk_count);
	}
	local_irq_restore(flags);
}

static cycle_t octeon_cvmcount_read(struct clocksource *cs)
{
	return read_c0_cvmcount();
}

static struct clocksource clocksource_mips = {
	.name		= "OCTEON_CVMCOUNT",
	.read		= octeon_cvmcount_read,
	.mask		= CLOCKSOURCE_MASK(64),
	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
};

unsigned long long notrace sched_clock(void)
{
	/* 64-bit arithmatic can overflow, so use 128-bit.  */
	u64 t1, t2, t3;
	unsigned long long rv;
	u64 mult = clocksource_mips.mult;
	u64 shift = clocksource_mips.shift;
	u64 cnt = read_c0_cvmcount();

	asm (
		"dmultu\t%[cnt],%[mult]\n\t"
		"nor\t%[t1],$0,%[shift]\n\t"
		"mfhi\t%[t2]\n\t"
		"mflo\t%[t3]\n\t"
		"dsll\t%[t2],%[t2],1\n\t"
		"dsrlv\t%[rv],%[t3],%[shift]\n\t"
		"dsllv\t%[t1],%[t2],%[t1]\n\t"
		"or\t%[rv],%[t1],%[rv]\n\t"
		: [rv] "=&r" (rv), [t1] "=&r" (t1), [t2] "=&r" (t2), [t3] "=&r" (t3)
		: [cnt] "r" (cnt), [mult] "r" (mult), [shift] "r" (shift)
		: "hi", "lo");
	return rv;
}

void __init plat_time_init(void)
{
	clocksource_mips.rating = 300;
	clocksource_register_hz(&clocksource_mips, octeon_get_clock_rate());
}

static u64 octeon_udelay_factor;
static u64 octeon_ndelay_factor;

void __init octeon_setup_delays(void)
{
	octeon_udelay_factor = octeon_get_clock_rate() / 1000000;
	/*
	 * For __ndelay we divide by 2^16, so the factor is multiplied
	 * by the same amount.
	 */
	octeon_ndelay_factor = (octeon_udelay_factor * 0x10000ull) / 1000ull;

	preset_lpj = octeon_get_clock_rate() / HZ;
}

void __udelay(unsigned long us)
{
	u64 cur, end, inc;

	cur = read_c0_cvmcount();

	inc = us * octeon_udelay_factor;
	end = cur + inc;

	while (end > cur)
		cur = read_c0_cvmcount();
}
EXPORT_SYMBOL(__udelay);

void __ndelay(unsigned long ns)
{
	u64 cur, end, inc;

	cur = read_c0_cvmcount();

	inc = ((ns * octeon_ndelay_factor) >> 16);
	end = cur + inc;

	while (end > cur)
		cur = read_c0_cvmcount();
}
EXPORT_SYMBOL(__ndelay);

void __delay(unsigned long loops)
{
	u64 cur, end;

	cur = read_c0_cvmcount();
	end = cur + loops;

	while (end > cur)
		cur = read_c0_cvmcount();
}
EXPORT_SYMBOL(__delay);