| David Daney | 4c076fb | 2010-07-24 10:16:05 -0700 | [diff] [blame] | 1 | /* | 
|  | 2 | * Octeon Watchdog driver | 
|  | 3 | * | 
|  | 4 | * Copyright (C) 2007, 2008, 2009, 2010 Cavium Networks | 
|  | 5 | * | 
|  | 6 | * Some parts derived from wdt.c | 
|  | 7 | * | 
|  | 8 | *	(c) Copyright 1996-1997 Alan Cox <alan@lxorguk.ukuu.org.uk>, | 
|  | 9 | *						All Rights Reserved. | 
|  | 10 | * | 
|  | 11 | *	This program is free software; you can redistribute it and/or | 
|  | 12 | *	modify it under the terms of the GNU General Public License | 
|  | 13 | *	as published by the Free Software Foundation; either version | 
|  | 14 | *	2 of the License, or (at your option) any later version. | 
|  | 15 | * | 
|  | 16 | *	Neither Alan Cox nor CymruNet Ltd. admit liability nor provide | 
|  | 17 | *	warranty for any of this software. This material is provided | 
|  | 18 | *	"AS-IS" and at no charge. | 
|  | 19 | * | 
|  | 20 | *	(c) Copyright 1995    Alan Cox <alan@lxorguk.ukuu.org.uk> | 
|  | 21 | * | 
|  | 22 | * This file is subject to the terms and conditions of the GNU General Public | 
|  | 23 | * License.  See the file "COPYING" in the main directory of this archive | 
|  | 24 | * for more details. | 
|  | 25 | * | 
|  | 26 | * | 
|  | 27 | * The OCTEON watchdog has a maximum timeout of 2^32 * io_clock. | 
|  | 28 | * For most systems this is less than 10 seconds, so to allow for | 
|  | 29 | * software to request longer watchdog heartbeats, we maintain software | 
|  | 30 | * counters to count multiples of the base rate.  If the system locks | 
|  | 31 | * up in such a manner that we can not run the software counters, the | 
|  | 32 | * only result is a watchdog reset sooner than was requested.  But | 
|  | 33 | * that is OK, because in this case userspace would likely not be able | 
|  | 34 | * to do anything anyhow. | 
|  | 35 | * | 
|  | 36 | * The hardware watchdog interval we call the period.  The OCTEON | 
|  | 37 | * watchdog goes through several stages, after the first period an | 
|  | 38 | * irq is asserted, then if it is not reset, after the next period NMI | 
|  | 39 | * is asserted, then after an additional period a chip wide soft reset. | 
|  | 40 | * So for the software counters, we reset watchdog after each period | 
|  | 41 | * and decrement the counter.  But for the last two periods we need to | 
|  | 42 | * let the watchdog progress to the NMI stage so we disable the irq | 
|  | 43 | * and let it proceed.  Once in the NMI, we print the register state | 
|  | 44 | * to the serial port and then wait for the reset. | 
|  | 45 | * | 
|  | 46 | * A watchdog is maintained for each CPU in the system, that way if | 
|  | 47 | * one CPU suffers a lockup, we also get a register dump and reset. | 
|  | 48 | * The userspace ping resets the watchdog on all CPUs. | 
|  | 49 | * | 
|  | 50 | * Before userspace opens the watchdog device, we still run the | 
|  | 51 | * watchdogs to catch any lockups that may be kernel related. | 
|  | 52 | * | 
|  | 53 | */ | 
|  | 54 |  | 
|  | 55 | #include <linux/miscdevice.h> | 
|  | 56 | #include <linux/interrupt.h> | 
|  | 57 | #include <linux/watchdog.h> | 
|  | 58 | #include <linux/cpumask.h> | 
|  | 59 | #include <linux/bitops.h> | 
|  | 60 | #include <linux/kernel.h> | 
|  | 61 | #include <linux/module.h> | 
|  | 62 | #include <linux/string.h> | 
|  | 63 | #include <linux/delay.h> | 
|  | 64 | #include <linux/cpu.h> | 
|  | 65 | #include <linux/smp.h> | 
|  | 66 | #include <linux/fs.h> | 
| David Howells | ca4d3e67 | 2010-10-07 14:08:54 +0100 | [diff] [blame] | 67 | #include <linux/irq.h> | 
| David Daney | 4c076fb | 2010-07-24 10:16:05 -0700 | [diff] [blame] | 68 |  | 
|  | 69 | #include <asm/mipsregs.h> | 
|  | 70 | #include <asm/uasm.h> | 
|  | 71 |  | 
|  | 72 | #include <asm/octeon/octeon.h> | 
|  | 73 |  | 
|  | 74 | /* The count needed to achieve timeout_sec. */ | 
|  | 75 | static unsigned int timeout_cnt; | 
|  | 76 |  | 
|  | 77 | /* The maximum period supported. */ | 
|  | 78 | static unsigned int max_timeout_sec; | 
|  | 79 |  | 
|  | 80 | /* The current period.  */ | 
|  | 81 | static unsigned int timeout_sec; | 
|  | 82 |  | 
|  | 83 | /* Set to non-zero when userspace countdown mode active */ | 
|  | 84 | static int do_coundown; | 
|  | 85 | static unsigned int countdown_reset; | 
|  | 86 | static unsigned int per_cpu_countdown[NR_CPUS]; | 
|  | 87 |  | 
|  | 88 | static cpumask_t irq_enabled_cpus; | 
|  | 89 |  | 
|  | 90 | #define WD_TIMO 60			/* Default heartbeat = 60 seconds */ | 
|  | 91 |  | 
|  | 92 | static int heartbeat = WD_TIMO; | 
|  | 93 | module_param(heartbeat, int, S_IRUGO); | 
|  | 94 | MODULE_PARM_DESC(heartbeat, | 
|  | 95 | "Watchdog heartbeat in seconds. (0 < heartbeat, default=" | 
|  | 96 | __MODULE_STRING(WD_TIMO) ")"); | 
|  | 97 |  | 
|  | 98 | static int nowayout = WATCHDOG_NOWAYOUT; | 
|  | 99 | module_param(nowayout, int, S_IRUGO); | 
|  | 100 | MODULE_PARM_DESC(nowayout, | 
|  | 101 | "Watchdog cannot be stopped once started (default=" | 
|  | 102 | __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); | 
|  | 103 |  | 
|  | 104 | static unsigned long octeon_wdt_is_open; | 
|  | 105 | static char expect_close; | 
|  | 106 |  | 
|  | 107 | static u32 __initdata nmi_stage1_insns[64]; | 
|  | 108 | /* We need one branch and therefore one relocation per target label. */ | 
|  | 109 | static struct uasm_label __initdata labels[5]; | 
|  | 110 | static struct uasm_reloc __initdata relocs[5]; | 
|  | 111 |  | 
|  | 112 | enum lable_id { | 
|  | 113 | label_enter_bootloader = 1 | 
|  | 114 | }; | 
|  | 115 |  | 
|  | 116 | /* Some CP0 registers */ | 
|  | 117 | #define K0		26 | 
|  | 118 | #define C0_CVMMEMCTL 11, 7 | 
|  | 119 | #define C0_STATUS 12, 0 | 
|  | 120 | #define C0_EBASE 15, 1 | 
|  | 121 | #define C0_DESAVE 31, 0 | 
|  | 122 |  | 
|  | 123 | void octeon_wdt_nmi_stage2(void); | 
|  | 124 |  | 
|  | 125 | static void __init octeon_wdt_build_stage1(void) | 
|  | 126 | { | 
|  | 127 | int i; | 
|  | 128 | int len; | 
|  | 129 | u32 *p = nmi_stage1_insns; | 
|  | 130 | #ifdef CONFIG_HOTPLUG_CPU | 
|  | 131 | struct uasm_label *l = labels; | 
|  | 132 | struct uasm_reloc *r = relocs; | 
|  | 133 | #endif | 
|  | 134 |  | 
|  | 135 | /* | 
|  | 136 | * For the next few instructions running the debugger may | 
|  | 137 | * cause corruption of k0 in the saved registers. Since we're | 
|  | 138 | * about to crash, nobody probably cares. | 
|  | 139 | * | 
|  | 140 | * Save K0 into the debug scratch register | 
|  | 141 | */ | 
|  | 142 | uasm_i_dmtc0(&p, K0, C0_DESAVE); | 
|  | 143 |  | 
|  | 144 | uasm_i_mfc0(&p, K0, C0_STATUS); | 
|  | 145 | #ifdef CONFIG_HOTPLUG_CPU | 
|  | 146 | uasm_il_bbit0(&p, &r, K0, ilog2(ST0_NMI), label_enter_bootloader); | 
|  | 147 | #endif | 
|  | 148 | /* Force 64-bit addressing enabled */ | 
|  | 149 | uasm_i_ori(&p, K0, K0, ST0_UX | ST0_SX | ST0_KX); | 
|  | 150 | uasm_i_mtc0(&p, K0, C0_STATUS); | 
|  | 151 |  | 
|  | 152 | #ifdef CONFIG_HOTPLUG_CPU | 
|  | 153 | uasm_i_mfc0(&p, K0, C0_EBASE); | 
|  | 154 | /* Coreid number in K0 */ | 
|  | 155 | uasm_i_andi(&p, K0, K0, 0xf); | 
|  | 156 | /* 8 * coreid in bits 16-31 */ | 
|  | 157 | uasm_i_dsll_safe(&p, K0, K0, 3 + 16); | 
|  | 158 | uasm_i_ori(&p, K0, K0, 0x8001); | 
|  | 159 | uasm_i_dsll_safe(&p, K0, K0, 16); | 
|  | 160 | uasm_i_ori(&p, K0, K0, 0x0700); | 
|  | 161 | uasm_i_drotr_safe(&p, K0, K0, 32); | 
|  | 162 | /* | 
|  | 163 | * Should result in: 0x8001,0700,0000,8*coreid which is | 
|  | 164 | * CVMX_CIU_WDOGX(coreid) - 0x0500 | 
|  | 165 | * | 
|  | 166 | * Now ld K0, CVMX_CIU_WDOGX(coreid) | 
|  | 167 | */ | 
|  | 168 | uasm_i_ld(&p, K0, 0x500, K0); | 
|  | 169 | /* | 
|  | 170 | * If bit one set handle the NMI as a watchdog event. | 
|  | 171 | * otherwise transfer control to bootloader. | 
|  | 172 | */ | 
|  | 173 | uasm_il_bbit0(&p, &r, K0, 1, label_enter_bootloader); | 
|  | 174 | uasm_i_nop(&p); | 
|  | 175 | #endif | 
|  | 176 |  | 
|  | 177 | /* Clear Dcache so cvmseg works right. */ | 
|  | 178 | uasm_i_cache(&p, 1, 0, 0); | 
|  | 179 |  | 
|  | 180 | /* Use K0 to do a read/modify/write of CVMMEMCTL */ | 
|  | 181 | uasm_i_dmfc0(&p, K0, C0_CVMMEMCTL); | 
|  | 182 | /* Clear out the size of CVMSEG	*/ | 
|  | 183 | uasm_i_dins(&p, K0, 0, 0, 6); | 
|  | 184 | /* Set CVMSEG to its largest value */ | 
|  | 185 | uasm_i_ori(&p, K0, K0, 0x1c0 | 54); | 
|  | 186 | /* Store the CVMMEMCTL value */ | 
|  | 187 | uasm_i_dmtc0(&p, K0, C0_CVMMEMCTL); | 
|  | 188 |  | 
|  | 189 | /* Load the address of the second stage handler */ | 
|  | 190 | UASM_i_LA(&p, K0, (long)octeon_wdt_nmi_stage2); | 
|  | 191 | uasm_i_jr(&p, K0); | 
|  | 192 | uasm_i_dmfc0(&p, K0, C0_DESAVE); | 
|  | 193 |  | 
|  | 194 | #ifdef CONFIG_HOTPLUG_CPU | 
|  | 195 | uasm_build_label(&l, p, label_enter_bootloader); | 
|  | 196 | /* Jump to the bootloader and restore K0 */ | 
|  | 197 | UASM_i_LA(&p, K0, (long)octeon_bootloader_entry_addr); | 
|  | 198 | uasm_i_jr(&p, K0); | 
|  | 199 | uasm_i_dmfc0(&p, K0, C0_DESAVE); | 
|  | 200 | #endif | 
|  | 201 | uasm_resolve_relocs(relocs, labels); | 
|  | 202 |  | 
|  | 203 | len = (int)(p - nmi_stage1_insns); | 
|  | 204 | pr_debug("Synthesized NMI stage 1 handler (%d instructions).\n", len); | 
|  | 205 |  | 
|  | 206 | pr_debug("\t.set push\n"); | 
|  | 207 | pr_debug("\t.set noreorder\n"); | 
|  | 208 | for (i = 0; i < len; i++) | 
|  | 209 | pr_debug("\t.word 0x%08x\n", nmi_stage1_insns[i]); | 
|  | 210 | pr_debug("\t.set pop\n"); | 
|  | 211 |  | 
|  | 212 | if (len > 32) | 
|  | 213 | panic("NMI stage 1 handler exceeds 32 instructions, was %d\n", len); | 
|  | 214 | } | 
|  | 215 |  | 
|  | 216 | static int cpu2core(int cpu) | 
|  | 217 | { | 
|  | 218 | #ifdef CONFIG_SMP | 
|  | 219 | return cpu_logical_map(cpu); | 
|  | 220 | #else | 
|  | 221 | return cvmx_get_core_num(); | 
|  | 222 | #endif | 
|  | 223 | } | 
|  | 224 |  | 
|  | 225 | static int core2cpu(int coreid) | 
|  | 226 | { | 
|  | 227 | #ifdef CONFIG_SMP | 
|  | 228 | return cpu_number_map(coreid); | 
|  | 229 | #else | 
|  | 230 | return 0; | 
|  | 231 | #endif | 
|  | 232 | } | 
|  | 233 |  | 
|  | 234 | /** | 
|  | 235 | * Poke the watchdog when an interrupt is received | 
|  | 236 | * | 
|  | 237 | * @cpl: | 
|  | 238 | * @dev_id: | 
|  | 239 | * | 
|  | 240 | * Returns | 
|  | 241 | */ | 
|  | 242 | static irqreturn_t octeon_wdt_poke_irq(int cpl, void *dev_id) | 
|  | 243 | { | 
|  | 244 | unsigned int core = cvmx_get_core_num(); | 
|  | 245 | int cpu = core2cpu(core); | 
|  | 246 |  | 
|  | 247 | if (do_coundown) { | 
|  | 248 | if (per_cpu_countdown[cpu] > 0) { | 
|  | 249 | /* We're alive, poke the watchdog */ | 
|  | 250 | cvmx_write_csr(CVMX_CIU_PP_POKEX(core), 1); | 
|  | 251 | per_cpu_countdown[cpu]--; | 
|  | 252 | } else { | 
|  | 253 | /* Bad news, you are about to reboot. */ | 
|  | 254 | disable_irq_nosync(cpl); | 
|  | 255 | cpumask_clear_cpu(cpu, &irq_enabled_cpus); | 
|  | 256 | } | 
|  | 257 | } else { | 
|  | 258 | /* Not open, just ping away... */ | 
|  | 259 | cvmx_write_csr(CVMX_CIU_PP_POKEX(core), 1); | 
|  | 260 | } | 
|  | 261 | return IRQ_HANDLED; | 
|  | 262 | } | 
|  | 263 |  | 
|  | 264 | /* From setup.c */ | 
|  | 265 | extern int prom_putchar(char c); | 
|  | 266 |  | 
|  | 267 | /** | 
|  | 268 | * Write a string to the uart | 
|  | 269 | * | 
|  | 270 | * @str:        String to write | 
|  | 271 | */ | 
|  | 272 | static void octeon_wdt_write_string(const char *str) | 
|  | 273 | { | 
|  | 274 | /* Just loop writing one byte at a time */ | 
|  | 275 | while (*str) | 
|  | 276 | prom_putchar(*str++); | 
|  | 277 | } | 
|  | 278 |  | 
|  | 279 | /** | 
|  | 280 | * Write a hex number out of the uart | 
|  | 281 | * | 
|  | 282 | * @value:      Number to display | 
|  | 283 | * @digits:     Number of digits to print (1 to 16) | 
|  | 284 | */ | 
|  | 285 | static void octeon_wdt_write_hex(u64 value, int digits) | 
|  | 286 | { | 
|  | 287 | int d; | 
|  | 288 | int v; | 
|  | 289 | for (d = 0; d < digits; d++) { | 
|  | 290 | v = (value >> ((digits - d - 1) * 4)) & 0xf; | 
|  | 291 | if (v >= 10) | 
|  | 292 | prom_putchar('a' + v - 10); | 
|  | 293 | else | 
|  | 294 | prom_putchar('0' + v); | 
|  | 295 | } | 
|  | 296 | } | 
|  | 297 |  | 
|  | 298 | const char *reg_name[] = { | 
|  | 299 | "$0", "at", "v0", "v1", "a0", "a1", "a2", "a3", | 
|  | 300 | "a4", "a5", "a6", "a7", "t0", "t1", "t2", "t3", | 
|  | 301 | "s0", "s1", "s2", "s3", "s4", "s5", "s6", "s7", | 
|  | 302 | "t8", "t9", "k0", "k1", "gp", "sp", "s8", "ra" | 
|  | 303 | }; | 
|  | 304 |  | 
|  | 305 | /** | 
|  | 306 | * NMI stage 3 handler. NMIs are handled in the following manner: | 
|  | 307 | * 1) The first NMI handler enables CVMSEG and transfers from | 
|  | 308 | * the bootbus region into normal memory. It is careful to not | 
|  | 309 | * destroy any registers. | 
|  | 310 | * 2) The second stage handler uses CVMSEG to save the registers | 
|  | 311 | * and create a stack for C code. It then calls the third level | 
|  | 312 | * handler with one argument, a pointer to the register values. | 
|  | 313 | * 3) The third, and final, level handler is the following C | 
|  | 314 | * function that prints out some useful infomration. | 
|  | 315 | * | 
|  | 316 | * @reg:    Pointer to register state before the NMI | 
|  | 317 | */ | 
|  | 318 | void octeon_wdt_nmi_stage3(u64 reg[32]) | 
|  | 319 | { | 
|  | 320 | u64 i; | 
|  | 321 |  | 
|  | 322 | unsigned int coreid = cvmx_get_core_num(); | 
|  | 323 | /* | 
|  | 324 | * Save status and cause early to get them before any changes | 
|  | 325 | * might happen. | 
|  | 326 | */ | 
|  | 327 | u64 cp0_cause = read_c0_cause(); | 
|  | 328 | u64 cp0_status = read_c0_status(); | 
|  | 329 | u64 cp0_error_epc = read_c0_errorepc(); | 
|  | 330 | u64 cp0_epc = read_c0_epc(); | 
|  | 331 |  | 
|  | 332 | /* Delay so output from all cores output is not jumbled together. */ | 
|  | 333 | __delay(100000000ull * coreid); | 
|  | 334 |  | 
|  | 335 | octeon_wdt_write_string("\r\n*** NMI Watchdog interrupt on Core 0x"); | 
|  | 336 | octeon_wdt_write_hex(coreid, 1); | 
|  | 337 | octeon_wdt_write_string(" ***\r\n"); | 
|  | 338 | for (i = 0; i < 32; i++) { | 
|  | 339 | octeon_wdt_write_string("\t"); | 
|  | 340 | octeon_wdt_write_string(reg_name[i]); | 
|  | 341 | octeon_wdt_write_string("\t0x"); | 
|  | 342 | octeon_wdt_write_hex(reg[i], 16); | 
|  | 343 | if (i & 1) | 
|  | 344 | octeon_wdt_write_string("\r\n"); | 
|  | 345 | } | 
|  | 346 | octeon_wdt_write_string("\terr_epc\t0x"); | 
|  | 347 | octeon_wdt_write_hex(cp0_error_epc, 16); | 
|  | 348 |  | 
|  | 349 | octeon_wdt_write_string("\tepc\t0x"); | 
|  | 350 | octeon_wdt_write_hex(cp0_epc, 16); | 
|  | 351 | octeon_wdt_write_string("\r\n"); | 
|  | 352 |  | 
|  | 353 | octeon_wdt_write_string("\tstatus\t0x"); | 
|  | 354 | octeon_wdt_write_hex(cp0_status, 16); | 
|  | 355 | octeon_wdt_write_string("\tcause\t0x"); | 
|  | 356 | octeon_wdt_write_hex(cp0_cause, 16); | 
|  | 357 | octeon_wdt_write_string("\r\n"); | 
|  | 358 |  | 
|  | 359 | octeon_wdt_write_string("\tsum0\t0x"); | 
|  | 360 | octeon_wdt_write_hex(cvmx_read_csr(CVMX_CIU_INTX_SUM0(coreid * 2)), 16); | 
|  | 361 | octeon_wdt_write_string("\ten0\t0x"); | 
|  | 362 | octeon_wdt_write_hex(cvmx_read_csr(CVMX_CIU_INTX_EN0(coreid * 2)), 16); | 
|  | 363 | octeon_wdt_write_string("\r\n"); | 
|  | 364 |  | 
|  | 365 | octeon_wdt_write_string("*** Chip soft reset soon ***\r\n"); | 
|  | 366 | } | 
|  | 367 |  | 
|  | 368 | static void octeon_wdt_disable_interrupt(int cpu) | 
|  | 369 | { | 
|  | 370 | unsigned int core; | 
|  | 371 | unsigned int irq; | 
|  | 372 | union cvmx_ciu_wdogx ciu_wdog; | 
|  | 373 |  | 
|  | 374 | core = cpu2core(cpu); | 
|  | 375 |  | 
|  | 376 | irq = OCTEON_IRQ_WDOG0 + core; | 
|  | 377 |  | 
|  | 378 | /* Poke the watchdog to clear out its state */ | 
|  | 379 | cvmx_write_csr(CVMX_CIU_PP_POKEX(core), 1); | 
|  | 380 |  | 
|  | 381 | /* Disable the hardware. */ | 
|  | 382 | ciu_wdog.u64 = 0; | 
|  | 383 | cvmx_write_csr(CVMX_CIU_WDOGX(core), ciu_wdog.u64); | 
|  | 384 |  | 
|  | 385 | free_irq(irq, octeon_wdt_poke_irq); | 
|  | 386 | } | 
|  | 387 |  | 
|  | 388 | static void octeon_wdt_setup_interrupt(int cpu) | 
|  | 389 | { | 
|  | 390 | unsigned int core; | 
|  | 391 | unsigned int irq; | 
|  | 392 | union cvmx_ciu_wdogx ciu_wdog; | 
|  | 393 |  | 
|  | 394 | core = cpu2core(cpu); | 
|  | 395 |  | 
|  | 396 | /* Disable it before doing anything with the interrupts. */ | 
|  | 397 | ciu_wdog.u64 = 0; | 
|  | 398 | cvmx_write_csr(CVMX_CIU_WDOGX(core), ciu_wdog.u64); | 
|  | 399 |  | 
|  | 400 | per_cpu_countdown[cpu] = countdown_reset; | 
|  | 401 |  | 
|  | 402 | irq = OCTEON_IRQ_WDOG0 + core; | 
|  | 403 |  | 
|  | 404 | if (request_irq(irq, octeon_wdt_poke_irq, | 
| Venkat Subbiah | 47bfd05 | 2011-10-03 17:22:04 -0700 | [diff] [blame] | 405 | IRQF_NO_THREAD, "octeon_wdt", octeon_wdt_poke_irq)) | 
| David Daney | 4c076fb | 2010-07-24 10:16:05 -0700 | [diff] [blame] | 406 | panic("octeon_wdt: Couldn't obtain irq %d", irq); | 
|  | 407 |  | 
|  | 408 | cpumask_set_cpu(cpu, &irq_enabled_cpus); | 
|  | 409 |  | 
|  | 410 | /* Poke the watchdog to clear out its state */ | 
|  | 411 | cvmx_write_csr(CVMX_CIU_PP_POKEX(core), 1); | 
|  | 412 |  | 
|  | 413 | /* Finally enable the watchdog now that all handlers are installed */ | 
|  | 414 | ciu_wdog.u64 = 0; | 
|  | 415 | ciu_wdog.s.len = timeout_cnt; | 
|  | 416 | ciu_wdog.s.mode = 3;	/* 3 = Interrupt + NMI + Soft-Reset */ | 
|  | 417 | cvmx_write_csr(CVMX_CIU_WDOGX(core), ciu_wdog.u64); | 
|  | 418 | } | 
|  | 419 |  | 
|  | 420 | static int octeon_wdt_cpu_callback(struct notifier_block *nfb, | 
|  | 421 | unsigned long action, void *hcpu) | 
|  | 422 | { | 
|  | 423 | unsigned int cpu = (unsigned long)hcpu; | 
|  | 424 |  | 
|  | 425 | switch (action) { | 
|  | 426 | case CPU_DOWN_PREPARE: | 
|  | 427 | octeon_wdt_disable_interrupt(cpu); | 
|  | 428 | break; | 
|  | 429 | case CPU_ONLINE: | 
|  | 430 | case CPU_DOWN_FAILED: | 
|  | 431 | octeon_wdt_setup_interrupt(cpu); | 
|  | 432 | break; | 
|  | 433 | default: | 
|  | 434 | break; | 
|  | 435 | } | 
|  | 436 | return NOTIFY_OK; | 
|  | 437 | } | 
|  | 438 |  | 
|  | 439 | static void octeon_wdt_ping(void) | 
|  | 440 | { | 
|  | 441 | int cpu; | 
|  | 442 | int coreid; | 
|  | 443 |  | 
|  | 444 | for_each_online_cpu(cpu) { | 
|  | 445 | coreid = cpu2core(cpu); | 
|  | 446 | cvmx_write_csr(CVMX_CIU_PP_POKEX(coreid), 1); | 
|  | 447 | per_cpu_countdown[cpu] = countdown_reset; | 
|  | 448 | if ((countdown_reset || !do_coundown) && | 
|  | 449 | !cpumask_test_cpu(cpu, &irq_enabled_cpus)) { | 
|  | 450 | /* We have to enable the irq */ | 
|  | 451 | int irq = OCTEON_IRQ_WDOG0 + coreid; | 
|  | 452 | enable_irq(irq); | 
|  | 453 | cpumask_set_cpu(cpu, &irq_enabled_cpus); | 
|  | 454 | } | 
|  | 455 | } | 
|  | 456 | } | 
|  | 457 |  | 
|  | 458 | static void octeon_wdt_calc_parameters(int t) | 
|  | 459 | { | 
|  | 460 | unsigned int periods; | 
|  | 461 |  | 
|  | 462 | timeout_sec = max_timeout_sec; | 
|  | 463 |  | 
|  | 464 |  | 
|  | 465 | /* | 
|  | 466 | * Find the largest interrupt period, that can evenly divide | 
|  | 467 | * the requested heartbeat time. | 
|  | 468 | */ | 
|  | 469 | while ((t % timeout_sec) != 0) | 
|  | 470 | timeout_sec--; | 
|  | 471 |  | 
|  | 472 | periods = t / timeout_sec; | 
|  | 473 |  | 
|  | 474 | /* | 
|  | 475 | * The last two periods are after the irq is disabled, and | 
|  | 476 | * then to the nmi, so we subtract them off. | 
|  | 477 | */ | 
|  | 478 |  | 
|  | 479 | countdown_reset = periods > 2 ? periods - 2 : 0; | 
|  | 480 | heartbeat = t; | 
| David Daney | 468ffde | 2010-10-07 16:03:52 -0700 | [diff] [blame] | 481 | timeout_cnt = ((octeon_get_io_clock_rate() >> 8) * timeout_sec) >> 8; | 
| David Daney | 4c076fb | 2010-07-24 10:16:05 -0700 | [diff] [blame] | 482 | } | 
|  | 483 |  | 
|  | 484 | static int octeon_wdt_set_heartbeat(int t) | 
|  | 485 | { | 
|  | 486 | int cpu; | 
|  | 487 | int coreid; | 
|  | 488 | union cvmx_ciu_wdogx ciu_wdog; | 
|  | 489 |  | 
|  | 490 | if (t <= 0) | 
|  | 491 | return -1; | 
|  | 492 |  | 
|  | 493 | octeon_wdt_calc_parameters(t); | 
|  | 494 |  | 
|  | 495 | for_each_online_cpu(cpu) { | 
|  | 496 | coreid = cpu2core(cpu); | 
|  | 497 | cvmx_write_csr(CVMX_CIU_PP_POKEX(coreid), 1); | 
|  | 498 | ciu_wdog.u64 = 0; | 
|  | 499 | ciu_wdog.s.len = timeout_cnt; | 
|  | 500 | ciu_wdog.s.mode = 3;	/* 3 = Interrupt + NMI + Soft-Reset */ | 
|  | 501 | cvmx_write_csr(CVMX_CIU_WDOGX(coreid), ciu_wdog.u64); | 
|  | 502 | cvmx_write_csr(CVMX_CIU_PP_POKEX(coreid), 1); | 
|  | 503 | } | 
|  | 504 | octeon_wdt_ping(); /* Get the irqs back on. */ | 
|  | 505 | return 0; | 
|  | 506 | } | 
|  | 507 |  | 
|  | 508 | /** | 
|  | 509 | *	octeon_wdt_write: | 
|  | 510 | *	@file: file handle to the watchdog | 
|  | 511 | *	@buf: buffer to write (unused as data does not matter here | 
|  | 512 | *	@count: count of bytes | 
|  | 513 | *	@ppos: pointer to the position to write. No seeks allowed | 
|  | 514 | * | 
|  | 515 | *	A write to a watchdog device is defined as a keepalive signal. Any | 
|  | 516 | *	write of data will do, as we we don't define content meaning. | 
|  | 517 | */ | 
|  | 518 |  | 
|  | 519 | static ssize_t octeon_wdt_write(struct file *file, const char __user *buf, | 
|  | 520 | size_t count, loff_t *ppos) | 
|  | 521 | { | 
|  | 522 | if (count) { | 
|  | 523 | if (!nowayout) { | 
|  | 524 | size_t i; | 
|  | 525 |  | 
|  | 526 | /* In case it was set long ago */ | 
|  | 527 | expect_close = 0; | 
|  | 528 |  | 
|  | 529 | for (i = 0; i != count; i++) { | 
|  | 530 | char c; | 
|  | 531 | if (get_user(c, buf + i)) | 
|  | 532 | return -EFAULT; | 
|  | 533 | if (c == 'V') | 
|  | 534 | expect_close = 1; | 
|  | 535 | } | 
|  | 536 | } | 
|  | 537 | octeon_wdt_ping(); | 
|  | 538 | } | 
|  | 539 | return count; | 
|  | 540 | } | 
|  | 541 |  | 
|  | 542 | /** | 
|  | 543 | *	octeon_wdt_ioctl: | 
|  | 544 | *	@file: file handle to the device | 
|  | 545 | *	@cmd: watchdog command | 
|  | 546 | *	@arg: argument pointer | 
|  | 547 | * | 
|  | 548 | *	The watchdog API defines a common set of functions for all | 
|  | 549 | *	watchdogs according to their available features. We only | 
|  | 550 | *	actually usefully support querying capabilities and setting | 
|  | 551 | *	the timeout. | 
|  | 552 | */ | 
|  | 553 |  | 
|  | 554 | static long octeon_wdt_ioctl(struct file *file, unsigned int cmd, | 
|  | 555 | unsigned long arg) | 
|  | 556 | { | 
|  | 557 | void __user *argp = (void __user *)arg; | 
|  | 558 | int __user *p = argp; | 
|  | 559 | int new_heartbeat; | 
|  | 560 |  | 
|  | 561 | static struct watchdog_info ident = { | 
|  | 562 | .options =		WDIOF_SETTIMEOUT| | 
|  | 563 | WDIOF_MAGICCLOSE| | 
|  | 564 | WDIOF_KEEPALIVEPING, | 
|  | 565 | .firmware_version =	1, | 
|  | 566 | .identity =		"OCTEON", | 
|  | 567 | }; | 
|  | 568 |  | 
|  | 569 | switch (cmd) { | 
|  | 570 | case WDIOC_GETSUPPORT: | 
|  | 571 | return copy_to_user(argp, &ident, sizeof(ident)) ? -EFAULT : 0; | 
|  | 572 | case WDIOC_GETSTATUS: | 
|  | 573 | case WDIOC_GETBOOTSTATUS: | 
|  | 574 | return put_user(0, p); | 
|  | 575 | case WDIOC_KEEPALIVE: | 
|  | 576 | octeon_wdt_ping(); | 
|  | 577 | return 0; | 
|  | 578 | case WDIOC_SETTIMEOUT: | 
|  | 579 | if (get_user(new_heartbeat, p)) | 
|  | 580 | return -EFAULT; | 
|  | 581 | if (octeon_wdt_set_heartbeat(new_heartbeat)) | 
|  | 582 | return -EINVAL; | 
|  | 583 | /* Fall through. */ | 
|  | 584 | case WDIOC_GETTIMEOUT: | 
|  | 585 | return put_user(heartbeat, p); | 
|  | 586 | default: | 
|  | 587 | return -ENOTTY; | 
|  | 588 | } | 
|  | 589 | } | 
|  | 590 |  | 
|  | 591 | /** | 
|  | 592 | *	octeon_wdt_open: | 
|  | 593 | *	@inode: inode of device | 
|  | 594 | *	@file: file handle to device | 
|  | 595 | * | 
|  | 596 | *	The watchdog device has been opened. The watchdog device is single | 
|  | 597 | *	open and on opening we do a ping to reset the counters. | 
|  | 598 | */ | 
|  | 599 |  | 
|  | 600 | static int octeon_wdt_open(struct inode *inode, struct file *file) | 
|  | 601 | { | 
|  | 602 | if (test_and_set_bit(0, &octeon_wdt_is_open)) | 
|  | 603 | return -EBUSY; | 
|  | 604 | /* | 
|  | 605 | *	Activate | 
|  | 606 | */ | 
|  | 607 | octeon_wdt_ping(); | 
|  | 608 | do_coundown = 1; | 
|  | 609 | return nonseekable_open(inode, file); | 
|  | 610 | } | 
|  | 611 |  | 
|  | 612 | /** | 
|  | 613 | *	octeon_wdt_release: | 
|  | 614 | *	@inode: inode to board | 
|  | 615 | *	@file: file handle to board | 
|  | 616 | * | 
|  | 617 | *	The watchdog has a configurable API. There is a religious dispute | 
|  | 618 | *	between people who want their watchdog to be able to shut down and | 
|  | 619 | *	those who want to be sure if the watchdog manager dies the machine | 
|  | 620 | *	reboots. In the former case we disable the counters, in the latter | 
|  | 621 | *	case you have to open it again very soon. | 
|  | 622 | */ | 
|  | 623 |  | 
|  | 624 | static int octeon_wdt_release(struct inode *inode, struct file *file) | 
|  | 625 | { | 
|  | 626 | if (expect_close) { | 
|  | 627 | do_coundown = 0; | 
|  | 628 | octeon_wdt_ping(); | 
|  | 629 | } else { | 
|  | 630 | pr_crit("octeon_wdt: WDT device closed unexpectedly.  WDT will not stop!\n"); | 
|  | 631 | } | 
|  | 632 | clear_bit(0, &octeon_wdt_is_open); | 
|  | 633 | expect_close = 0; | 
|  | 634 | return 0; | 
|  | 635 | } | 
|  | 636 |  | 
|  | 637 | static const struct file_operations octeon_wdt_fops = { | 
|  | 638 | .owner		= THIS_MODULE, | 
|  | 639 | .llseek		= no_llseek, | 
|  | 640 | .write		= octeon_wdt_write, | 
|  | 641 | .unlocked_ioctl	= octeon_wdt_ioctl, | 
|  | 642 | .open		= octeon_wdt_open, | 
|  | 643 | .release	= octeon_wdt_release, | 
|  | 644 | }; | 
|  | 645 |  | 
|  | 646 | static struct miscdevice octeon_wdt_miscdev = { | 
|  | 647 | .minor	= WATCHDOG_MINOR, | 
|  | 648 | .name	= "watchdog", | 
|  | 649 | .fops	= &octeon_wdt_fops, | 
|  | 650 | }; | 
|  | 651 |  | 
|  | 652 | static struct notifier_block octeon_wdt_cpu_notifier = { | 
|  | 653 | .notifier_call = octeon_wdt_cpu_callback, | 
|  | 654 | }; | 
|  | 655 |  | 
|  | 656 |  | 
|  | 657 | /** | 
|  | 658 | * Module/ driver initialization. | 
|  | 659 | * | 
|  | 660 | * Returns Zero on success | 
|  | 661 | */ | 
|  | 662 | static int __init octeon_wdt_init(void) | 
|  | 663 | { | 
|  | 664 | int i; | 
|  | 665 | int ret; | 
|  | 666 | int cpu; | 
|  | 667 | u64 *ptr; | 
|  | 668 |  | 
|  | 669 | /* | 
|  | 670 | * Watchdog time expiration length = The 16 bits of LEN | 
|  | 671 | * represent the most significant bits of a 24 bit decrementer | 
|  | 672 | * that decrements every 256 cycles. | 
|  | 673 | * | 
|  | 674 | * Try for a timeout of 5 sec, if that fails a smaller number | 
|  | 675 | * of even seconds, | 
|  | 676 | */ | 
|  | 677 | max_timeout_sec = 6; | 
|  | 678 | do { | 
|  | 679 | max_timeout_sec--; | 
| David Daney | 468ffde | 2010-10-07 16:03:52 -0700 | [diff] [blame] | 680 | timeout_cnt = ((octeon_get_io_clock_rate() >> 8) * max_timeout_sec) >> 8; | 
| David Daney | 4c076fb | 2010-07-24 10:16:05 -0700 | [diff] [blame] | 681 | } while (timeout_cnt > 65535); | 
|  | 682 |  | 
|  | 683 | BUG_ON(timeout_cnt == 0); | 
|  | 684 |  | 
|  | 685 | octeon_wdt_calc_parameters(heartbeat); | 
|  | 686 |  | 
|  | 687 | pr_info("octeon_wdt: Initial granularity %d Sec.\n", timeout_sec); | 
|  | 688 |  | 
|  | 689 | ret = misc_register(&octeon_wdt_miscdev); | 
|  | 690 | if (ret) { | 
|  | 691 | pr_err("octeon_wdt: cannot register miscdev on minor=%d (err=%d)\n", | 
|  | 692 | WATCHDOG_MINOR, ret); | 
|  | 693 | goto out; | 
|  | 694 | } | 
|  | 695 |  | 
|  | 696 | /* Build the NMI handler ... */ | 
|  | 697 | octeon_wdt_build_stage1(); | 
|  | 698 |  | 
|  | 699 | /* ... and install it. */ | 
|  | 700 | ptr = (u64 *) nmi_stage1_insns; | 
|  | 701 | for (i = 0; i < 16; i++) { | 
|  | 702 | cvmx_write_csr(CVMX_MIO_BOOT_LOC_ADR, i * 8); | 
|  | 703 | cvmx_write_csr(CVMX_MIO_BOOT_LOC_DAT, ptr[i]); | 
|  | 704 | } | 
|  | 705 | cvmx_write_csr(CVMX_MIO_BOOT_LOC_CFGX(0), 0x81fc0000); | 
|  | 706 |  | 
|  | 707 | cpumask_clear(&irq_enabled_cpus); | 
|  | 708 |  | 
|  | 709 | for_each_online_cpu(cpu) | 
|  | 710 | octeon_wdt_setup_interrupt(cpu); | 
|  | 711 |  | 
|  | 712 | register_hotcpu_notifier(&octeon_wdt_cpu_notifier); | 
|  | 713 | out: | 
|  | 714 | return ret; | 
|  | 715 | } | 
|  | 716 |  | 
|  | 717 | /** | 
|  | 718 | * Module / driver shutdown | 
|  | 719 | */ | 
|  | 720 | static void __exit octeon_wdt_cleanup(void) | 
|  | 721 | { | 
|  | 722 | int cpu; | 
|  | 723 |  | 
|  | 724 | misc_deregister(&octeon_wdt_miscdev); | 
|  | 725 |  | 
|  | 726 | unregister_hotcpu_notifier(&octeon_wdt_cpu_notifier); | 
|  | 727 |  | 
|  | 728 | for_each_online_cpu(cpu) { | 
|  | 729 | int core = cpu2core(cpu); | 
|  | 730 | /* Disable the watchdog */ | 
|  | 731 | cvmx_write_csr(CVMX_CIU_WDOGX(core), 0); | 
|  | 732 | /* Free the interrupt handler */ | 
|  | 733 | free_irq(OCTEON_IRQ_WDOG0 + core, octeon_wdt_poke_irq); | 
|  | 734 | } | 
|  | 735 | /* | 
|  | 736 | * Disable the boot-bus memory, the code it points to is soon | 
|  | 737 | * to go missing. | 
|  | 738 | */ | 
|  | 739 | cvmx_write_csr(CVMX_MIO_BOOT_LOC_CFGX(0), 0); | 
|  | 740 | } | 
|  | 741 |  | 
|  | 742 | MODULE_LICENSE("GPL"); | 
|  | 743 | MODULE_AUTHOR("Cavium Networks <support@caviumnetworks.com>"); | 
|  | 744 | MODULE_DESCRIPTION("Cavium Networks Octeon Watchdog driver."); | 
|  | 745 | module_init(octeon_wdt_init); | 
|  | 746 | module_exit(octeon_wdt_cleanup); |