| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1 | #ifndef _ASM_IA64_PROCESSOR_H | 
 | 2 | #define _ASM_IA64_PROCESSOR_H | 
 | 3 |  | 
 | 4 | /* | 
 | 5 |  * Copyright (C) 1998-2004 Hewlett-Packard Co | 
 | 6 |  *	David Mosberger-Tang <davidm@hpl.hp.com> | 
 | 7 |  *	Stephane Eranian <eranian@hpl.hp.com> | 
 | 8 |  * Copyright (C) 1999 Asit Mallick <asit.k.mallick@intel.com> | 
 | 9 |  * Copyright (C) 1999 Don Dugger <don.dugger@intel.com> | 
 | 10 |  * | 
 | 11 |  * 11/24/98	S.Eranian	added ia64_set_iva() | 
 | 12 |  * 12/03/99	D. Mosberger	implement thread_saved_pc() via kernel unwind API | 
 | 13 |  * 06/16/00	A. Mallick	added csd/ssd/tssd for ia32 support | 
 | 14 |  */ | 
 | 15 |  | 
 | 16 | #include <linux/config.h> | 
 | 17 |  | 
 | 18 | #include <asm/intrinsics.h> | 
 | 19 | #include <asm/kregs.h> | 
 | 20 | #include <asm/ptrace.h> | 
 | 21 | #include <asm/ustack.h> | 
 | 22 |  | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 23 | #define IA64_NUM_DBG_REGS	8 | 
 | 24 | /* | 
 | 25 |  * Limits for PMC and PMD are set to less than maximum architected values | 
 | 26 |  * but should be sufficient for a while | 
 | 27 |  */ | 
| Stephane Eranian | 9179cb6 | 2006-01-10 03:10:43 -0800 | [diff] [blame] | 28 | #define IA64_NUM_PMC_REGS	64 | 
 | 29 | #define IA64_NUM_PMD_REGS	64 | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 30 |  | 
 | 31 | #define DEFAULT_MAP_BASE	__IA64_UL_CONST(0x2000000000000000) | 
 | 32 | #define DEFAULT_TASK_SIZE	__IA64_UL_CONST(0xa000000000000000) | 
 | 33 |  | 
 | 34 | /* | 
 | 35 |  * TASK_SIZE really is a mis-named.  It really is the maximum user | 
 | 36 |  * space address (plus one).  On IA-64, there are five regions of 2TB | 
 | 37 |  * each (assuming 8KB page size), for a total of 8TB of user virtual | 
 | 38 |  * address space. | 
 | 39 |  */ | 
 | 40 | #define TASK_SIZE		(current->thread.task_size) | 
 | 41 |  | 
 | 42 | /* | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 43 |  * This decides where the kernel will search for a free chunk of vm | 
 | 44 |  * space during mmap's. | 
 | 45 |  */ | 
 | 46 | #define TASK_UNMAPPED_BASE	(current->thread.map_base) | 
 | 47 |  | 
 | 48 | #define IA64_THREAD_FPH_VALID	(__IA64_UL(1) << 0)	/* floating-point high state valid? */ | 
 | 49 | #define IA64_THREAD_DBG_VALID	(__IA64_UL(1) << 1)	/* debug registers valid? */ | 
 | 50 | #define IA64_THREAD_PM_VALID	(__IA64_UL(1) << 2)	/* performance registers valid? */ | 
 | 51 | #define IA64_THREAD_UAC_NOPRINT	(__IA64_UL(1) << 3)	/* don't log unaligned accesses */ | 
 | 52 | #define IA64_THREAD_UAC_SIGBUS	(__IA64_UL(1) << 4)	/* generate SIGBUS on unaligned acc. */ | 
 | 53 | 							/* bit 5 is currently unused */ | 
 | 54 | #define IA64_THREAD_FPEMU_NOPRINT (__IA64_UL(1) << 6)	/* don't log any fpswa faults */ | 
 | 55 | #define IA64_THREAD_FPEMU_SIGFPE  (__IA64_UL(1) << 7)	/* send a SIGFPE for fpswa faults */ | 
 | 56 |  | 
 | 57 | #define IA64_THREAD_UAC_SHIFT	3 | 
 | 58 | #define IA64_THREAD_UAC_MASK	(IA64_THREAD_UAC_NOPRINT | IA64_THREAD_UAC_SIGBUS) | 
 | 59 | #define IA64_THREAD_FPEMU_SHIFT	6 | 
 | 60 | #define IA64_THREAD_FPEMU_MASK	(IA64_THREAD_FPEMU_NOPRINT | IA64_THREAD_FPEMU_SIGFPE) | 
 | 61 |  | 
 | 62 |  | 
 | 63 | /* | 
 | 64 |  * This shift should be large enough to be able to represent 1000000000/itc_freq with good | 
 | 65 |  * accuracy while being small enough to fit 10*1000000000<<IA64_NSEC_PER_CYC_SHIFT in 64 bits | 
 | 66 |  * (this will give enough slack to represent 10 seconds worth of time as a scaled number). | 
 | 67 |  */ | 
 | 68 | #define IA64_NSEC_PER_CYC_SHIFT	30 | 
 | 69 |  | 
 | 70 | #ifndef __ASSEMBLY__ | 
 | 71 |  | 
 | 72 | #include <linux/cache.h> | 
 | 73 | #include <linux/compiler.h> | 
 | 74 | #include <linux/threads.h> | 
 | 75 | #include <linux/types.h> | 
 | 76 |  | 
 | 77 | #include <asm/fpu.h> | 
 | 78 | #include <asm/page.h> | 
 | 79 | #include <asm/percpu.h> | 
 | 80 | #include <asm/rse.h> | 
 | 81 | #include <asm/unwind.h> | 
 | 82 | #include <asm/atomic.h> | 
 | 83 | #ifdef CONFIG_NUMA | 
 | 84 | #include <asm/nodedata.h> | 
 | 85 | #endif | 
 | 86 |  | 
 | 87 | /* like above but expressed as bitfields for more efficient access: */ | 
 | 88 | struct ia64_psr { | 
 | 89 | 	__u64 reserved0 : 1; | 
 | 90 | 	__u64 be : 1; | 
 | 91 | 	__u64 up : 1; | 
 | 92 | 	__u64 ac : 1; | 
 | 93 | 	__u64 mfl : 1; | 
 | 94 | 	__u64 mfh : 1; | 
 | 95 | 	__u64 reserved1 : 7; | 
 | 96 | 	__u64 ic : 1; | 
 | 97 | 	__u64 i : 1; | 
 | 98 | 	__u64 pk : 1; | 
 | 99 | 	__u64 reserved2 : 1; | 
 | 100 | 	__u64 dt : 1; | 
 | 101 | 	__u64 dfl : 1; | 
 | 102 | 	__u64 dfh : 1; | 
 | 103 | 	__u64 sp : 1; | 
 | 104 | 	__u64 pp : 1; | 
 | 105 | 	__u64 di : 1; | 
 | 106 | 	__u64 si : 1; | 
 | 107 | 	__u64 db : 1; | 
 | 108 | 	__u64 lp : 1; | 
 | 109 | 	__u64 tb : 1; | 
 | 110 | 	__u64 rt : 1; | 
 | 111 | 	__u64 reserved3 : 4; | 
 | 112 | 	__u64 cpl : 2; | 
 | 113 | 	__u64 is : 1; | 
 | 114 | 	__u64 mc : 1; | 
 | 115 | 	__u64 it : 1; | 
 | 116 | 	__u64 id : 1; | 
 | 117 | 	__u64 da : 1; | 
 | 118 | 	__u64 dd : 1; | 
 | 119 | 	__u64 ss : 1; | 
 | 120 | 	__u64 ri : 2; | 
 | 121 | 	__u64 ed : 1; | 
 | 122 | 	__u64 bn : 1; | 
 | 123 | 	__u64 reserved4 : 19; | 
 | 124 | }; | 
 | 125 |  | 
 | 126 | /* | 
 | 127 |  * CPU type, hardware bug flags, and per-CPU state.  Frequently used | 
 | 128 |  * state comes earlier: | 
 | 129 |  */ | 
 | 130 | struct cpuinfo_ia64 { | 
 | 131 | 	__u32 softirq_pending; | 
 | 132 | 	__u64 itm_delta;	/* # of clock cycles between clock ticks */ | 
 | 133 | 	__u64 itm_next;		/* interval timer mask value to use for next clock tick */ | 
 | 134 | 	__u64 nsec_per_cyc;	/* (1000000000<<IA64_NSEC_PER_CYC_SHIFT)/itc_freq */ | 
 | 135 | 	__u64 unimpl_va_mask;	/* mask of unimplemented virtual address bits (from PAL) */ | 
 | 136 | 	__u64 unimpl_pa_mask;	/* mask of unimplemented physical address bits (from PAL) */ | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 137 | 	__u64 itc_freq;		/* frequency of ITC counter */ | 
 | 138 | 	__u64 proc_freq;	/* frequency of processor */ | 
 | 139 | 	__u64 cyc_per_usec;	/* itc_freq/1000000 */ | 
 | 140 | 	__u64 ptce_base; | 
 | 141 | 	__u32 ptce_count[2]; | 
 | 142 | 	__u32 ptce_stride[2]; | 
 | 143 | 	struct task_struct *ksoftirqd;	/* kernel softirq daemon for this CPU */ | 
 | 144 |  | 
 | 145 | #ifdef CONFIG_SMP | 
 | 146 | 	__u64 loops_per_jiffy; | 
 | 147 | 	int cpu; | 
| Suresh Siddha | e927ecb | 2005-04-25 13:25:06 -0700 | [diff] [blame] | 148 | 	__u32 socket_id;	/* physical processor socket id */ | 
 | 149 | 	__u16 core_id;		/* core id */ | 
 | 150 | 	__u16 thread_id;	/* thread id */ | 
 | 151 | 	__u16 num_log;		/* Total number of logical processors on | 
 | 152 | 				 * this socket that were successfully booted */ | 
 | 153 | 	__u8  cores_per_socket;	/* Cores per processor socket */ | 
 | 154 | 	__u8  threads_per_core;	/* Threads per core */ | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 155 | #endif | 
 | 156 |  | 
 | 157 | 	/* CPUID-derived information: */ | 
 | 158 | 	__u64 ppn; | 
 | 159 | 	__u64 features; | 
 | 160 | 	__u8 number; | 
 | 161 | 	__u8 revision; | 
 | 162 | 	__u8 model; | 
 | 163 | 	__u8 family; | 
 | 164 | 	__u8 archrev; | 
 | 165 | 	char vendor[16]; | 
 | 166 |  | 
 | 167 | #ifdef CONFIG_NUMA | 
 | 168 | 	struct ia64_node_data *node_data; | 
 | 169 | #endif | 
 | 170 | }; | 
 | 171 |  | 
 | 172 | DECLARE_PER_CPU(struct cpuinfo_ia64, cpu_info); | 
 | 173 |  | 
 | 174 | /* | 
 | 175 |  * The "local" data variable.  It refers to the per-CPU data of the currently executing | 
 | 176 |  * CPU, much like "current" points to the per-task data of the currently executing task. | 
 | 177 |  * Do not use the address of local_cpu_data, since it will be different from | 
 | 178 |  * cpu_data(smp_processor_id())! | 
 | 179 |  */ | 
 | 180 | #define local_cpu_data		(&__ia64_per_cpu_var(cpu_info)) | 
 | 181 | #define cpu_data(cpu)		(&per_cpu(cpu_info, cpu)) | 
 | 182 |  | 
 | 183 | extern void identify_cpu (struct cpuinfo_ia64 *); | 
 | 184 | extern void print_cpu_info (struct cpuinfo_ia64 *); | 
 | 185 |  | 
 | 186 | typedef struct { | 
 | 187 | 	unsigned long seg; | 
 | 188 | } mm_segment_t; | 
 | 189 |  | 
 | 190 | #define SET_UNALIGN_CTL(task,value)								\ | 
 | 191 | ({												\ | 
 | 192 | 	(task)->thread.flags = (((task)->thread.flags & ~IA64_THREAD_UAC_MASK)			\ | 
 | 193 | 				| (((value) << IA64_THREAD_UAC_SHIFT) & IA64_THREAD_UAC_MASK));	\ | 
 | 194 | 	0;											\ | 
 | 195 | }) | 
 | 196 | #define GET_UNALIGN_CTL(task,addr)								\ | 
 | 197 | ({												\ | 
 | 198 | 	put_user(((task)->thread.flags & IA64_THREAD_UAC_MASK) >> IA64_THREAD_UAC_SHIFT,	\ | 
 | 199 | 		 (int __user *) (addr));							\ | 
 | 200 | }) | 
 | 201 |  | 
 | 202 | #define SET_FPEMU_CTL(task,value)								\ | 
 | 203 | ({												\ | 
 | 204 | 	(task)->thread.flags = (((task)->thread.flags & ~IA64_THREAD_FPEMU_MASK)		\ | 
 | 205 | 			  | (((value) << IA64_THREAD_FPEMU_SHIFT) & IA64_THREAD_FPEMU_MASK));	\ | 
 | 206 | 	0;											\ | 
 | 207 | }) | 
 | 208 | #define GET_FPEMU_CTL(task,addr)								\ | 
 | 209 | ({												\ | 
 | 210 | 	put_user(((task)->thread.flags & IA64_THREAD_FPEMU_MASK) >> IA64_THREAD_FPEMU_SHIFT,	\ | 
 | 211 | 		 (int __user *) (addr));							\ | 
 | 212 | }) | 
 | 213 |  | 
 | 214 | #ifdef CONFIG_IA32_SUPPORT | 
 | 215 | struct desc_struct { | 
 | 216 | 	unsigned int a, b; | 
 | 217 | }; | 
 | 218 |  | 
 | 219 | #define desc_empty(desc)		(!((desc)->a + (desc)->b)) | 
 | 220 | #define desc_equal(desc1, desc2)	(((desc1)->a == (desc2)->a) && ((desc1)->b == (desc2)->b)) | 
 | 221 |  | 
 | 222 | #define GDT_ENTRY_TLS_ENTRIES	3 | 
 | 223 | #define GDT_ENTRY_TLS_MIN	6 | 
 | 224 | #define GDT_ENTRY_TLS_MAX 	(GDT_ENTRY_TLS_MIN + GDT_ENTRY_TLS_ENTRIES - 1) | 
 | 225 |  | 
 | 226 | #define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES * 8) | 
 | 227 |  | 
 | 228 | struct partial_page_list; | 
 | 229 | #endif | 
 | 230 |  | 
 | 231 | struct thread_struct { | 
 | 232 | 	__u32 flags;			/* various thread flags (see IA64_THREAD_*) */ | 
 | 233 | 	/* writing on_ustack is performance-critical, so it's worth spending 8 bits on it... */ | 
 | 234 | 	__u8 on_ustack;			/* executing on user-stacks? */ | 
 | 235 | 	__u8 pad[3]; | 
 | 236 | 	__u64 ksp;			/* kernel stack pointer */ | 
 | 237 | 	__u64 map_base;			/* base address for get_unmapped_area() */ | 
 | 238 | 	__u64 task_size;		/* limit for task size */ | 
 | 239 | 	__u64 rbs_bot;			/* the base address for the RBS */ | 
 | 240 | 	int last_fph_cpu;		/* CPU that may hold the contents of f32-f127 */ | 
 | 241 |  | 
 | 242 | #ifdef CONFIG_IA32_SUPPORT | 
 | 243 | 	__u64 eflag;			/* IA32 EFLAGS reg */ | 
 | 244 | 	__u64 fsr;			/* IA32 floating pt status reg */ | 
 | 245 | 	__u64 fcr;			/* IA32 floating pt control reg */ | 
 | 246 | 	__u64 fir;			/* IA32 fp except. instr. reg */ | 
 | 247 | 	__u64 fdr;			/* IA32 fp except. data reg */ | 
 | 248 | 	__u64 old_k1;			/* old value of ar.k1 */ | 
 | 249 | 	__u64 old_iob;			/* old IOBase value */ | 
 | 250 | 	struct partial_page_list *ppl;	/* partial page list for 4K page size issue */ | 
 | 251 |         /* cached TLS descriptors. */ | 
 | 252 | 	struct desc_struct tls_array[GDT_ENTRY_TLS_ENTRIES]; | 
 | 253 |  | 
 | 254 | # define INIT_THREAD_IA32	.eflag =	0,			\ | 
 | 255 | 				.fsr =		0,			\ | 
 | 256 | 				.fcr =		0x17800000037fULL,	\ | 
 | 257 | 				.fir =		0,			\ | 
 | 258 | 				.fdr =		0,			\ | 
 | 259 | 				.old_k1 =	0,			\ | 
 | 260 | 				.old_iob =	0,			\ | 
 | 261 | 				.ppl =		NULL, | 
 | 262 | #else | 
 | 263 | # define INIT_THREAD_IA32 | 
 | 264 | #endif /* CONFIG_IA32_SUPPORT */ | 
 | 265 | #ifdef CONFIG_PERFMON | 
 | 266 | 	__u64 pmcs[IA64_NUM_PMC_REGS]; | 
 | 267 | 	__u64 pmds[IA64_NUM_PMD_REGS]; | 
 | 268 | 	void *pfm_context;		     /* pointer to detailed PMU context */ | 
 | 269 | 	unsigned long pfm_needs_checking;    /* when >0, pending perfmon work on kernel exit */ | 
 | 270 | # define INIT_THREAD_PM		.pmcs =			{0UL, },  \ | 
 | 271 | 				.pmds =			{0UL, },  \ | 
 | 272 | 				.pfm_context =		NULL,     \ | 
 | 273 | 				.pfm_needs_checking =	0UL, | 
 | 274 | #else | 
 | 275 | # define INIT_THREAD_PM | 
 | 276 | #endif | 
 | 277 | 	__u64 dbr[IA64_NUM_DBG_REGS]; | 
 | 278 | 	__u64 ibr[IA64_NUM_DBG_REGS]; | 
 | 279 | 	struct ia64_fpreg fph[96];	/* saved/loaded on demand */ | 
 | 280 | }; | 
 | 281 |  | 
 | 282 | #define INIT_THREAD {						\ | 
 | 283 | 	.flags =	0,					\ | 
 | 284 | 	.on_ustack =	0,					\ | 
 | 285 | 	.ksp =		0,					\ | 
 | 286 | 	.map_base =	DEFAULT_MAP_BASE,			\ | 
 | 287 | 	.rbs_bot =	STACK_TOP - DEFAULT_USER_STACK_SIZE,	\ | 
 | 288 | 	.task_size =	DEFAULT_TASK_SIZE,			\ | 
 | 289 | 	.last_fph_cpu =  -1,					\ | 
 | 290 | 	INIT_THREAD_IA32					\ | 
 | 291 | 	INIT_THREAD_PM						\ | 
 | 292 | 	.dbr =		{0, },					\ | 
 | 293 | 	.ibr =		{0, },					\ | 
 | 294 | 	.fph =		{{{{0}}}, }				\ | 
 | 295 | } | 
 | 296 |  | 
 | 297 | #define start_thread(regs,new_ip,new_sp) do {							\ | 
 | 298 | 	set_fs(USER_DS);									\ | 
 | 299 | 	regs->cr_ipsr = ((regs->cr_ipsr | (IA64_PSR_BITS_TO_SET | IA64_PSR_CPL))		\ | 
 | 300 | 			 & ~(IA64_PSR_BITS_TO_CLEAR | IA64_PSR_RI | IA64_PSR_IS));		\ | 
 | 301 | 	regs->cr_iip = new_ip;									\ | 
 | 302 | 	regs->ar_rsc = 0xf;		/* eager mode, privilege level 3 */			\ | 
 | 303 | 	regs->ar_rnat = 0;									\ | 
 | 304 | 	regs->ar_bspstore = current->thread.rbs_bot;						\ | 
 | 305 | 	regs->ar_fpsr = FPSR_DEFAULT;								\ | 
 | 306 | 	regs->loadrs = 0;									\ | 
 | 307 | 	regs->r8 = current->mm->dumpable;	/* set "don't zap registers" flag */		\ | 
 | 308 | 	regs->r12 = new_sp - 16;	/* allocate 16 byte scratch area */			\ | 
 | 309 | 	if (unlikely(!current->mm->dumpable)) {							\ | 
 | 310 | 		/*										\ | 
 | 311 | 		 * Zap scratch regs to avoid leaking bits between processes with different	\ | 
 | 312 | 		 * uid/privileges.								\ | 
 | 313 | 		 */										\ | 
 | 314 | 		regs->ar_pfs = 0; regs->b0 = 0; regs->pr = 0;					\ | 
 | 315 | 		regs->r1 = 0; regs->r9  = 0; regs->r11 = 0; regs->r13 = 0; regs->r15 = 0;	\ | 
 | 316 | 	}											\ | 
 | 317 | } while (0) | 
 | 318 |  | 
 | 319 | /* Forward declarations, a strange C thing... */ | 
 | 320 | struct mm_struct; | 
 | 321 | struct task_struct; | 
 | 322 |  | 
 | 323 | /* | 
 | 324 |  * Free all resources held by a thread. This is called after the | 
 | 325 |  * parent of DEAD_TASK has collected the exit status of the task via | 
 | 326 |  * wait(). | 
 | 327 |  */ | 
 | 328 | #define release_thread(dead_task) | 
 | 329 |  | 
 | 330 | /* Prepare to copy thread state - unlazy all lazy status */ | 
 | 331 | #define prepare_to_copy(tsk)	do { } while (0) | 
 | 332 |  | 
 | 333 | /* | 
 | 334 |  * This is the mechanism for creating a new kernel thread. | 
 | 335 |  * | 
 | 336 |  * NOTE 1: Only a kernel-only process (ie the swapper or direct | 
 | 337 |  * descendants who haven't done an "execve()") should use this: it | 
 | 338 |  * will work within a system call from a "real" process, but the | 
 | 339 |  * process memory space will not be free'd until both the parent and | 
 | 340 |  * the child have exited. | 
 | 341 |  * | 
 | 342 |  * NOTE 2: This MUST NOT be an inlined function.  Otherwise, we get | 
 | 343 |  * into trouble in init/main.c when the child thread returns to | 
 | 344 |  * do_basic_setup() and the timing is such that free_initmem() has | 
 | 345 |  * been called already. | 
 | 346 |  */ | 
 | 347 | extern pid_t kernel_thread (int (*fn)(void *), void *arg, unsigned long flags); | 
 | 348 |  | 
 | 349 | /* Get wait channel for task P.  */ | 
 | 350 | extern unsigned long get_wchan (struct task_struct *p); | 
 | 351 |  | 
 | 352 | /* Return instruction pointer of blocked task TSK.  */ | 
 | 353 | #define KSTK_EIP(tsk)					\ | 
 | 354 |   ({							\ | 
| Al Viro | 6450578 | 2006-01-12 01:06:06 -0800 | [diff] [blame] | 355 | 	struct pt_regs *_regs = task_pt_regs(tsk);	\ | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 356 | 	_regs->cr_iip + ia64_psr(_regs)->ri;		\ | 
 | 357 |   }) | 
 | 358 |  | 
 | 359 | /* Return stack pointer of blocked task TSK.  */ | 
 | 360 | #define KSTK_ESP(tsk)  ((tsk)->thread.ksp) | 
 | 361 |  | 
 | 362 | extern void ia64_getreg_unknown_kr (void); | 
 | 363 | extern void ia64_setreg_unknown_kr (void); | 
 | 364 |  | 
 | 365 | #define ia64_get_kr(regnum)					\ | 
 | 366 | ({								\ | 
 | 367 | 	unsigned long r = 0;					\ | 
 | 368 | 								\ | 
 | 369 | 	switch (regnum) {					\ | 
 | 370 | 	    case 0: r = ia64_getreg(_IA64_REG_AR_KR0); break;	\ | 
 | 371 | 	    case 1: r = ia64_getreg(_IA64_REG_AR_KR1); break;	\ | 
 | 372 | 	    case 2: r = ia64_getreg(_IA64_REG_AR_KR2); break;	\ | 
 | 373 | 	    case 3: r = ia64_getreg(_IA64_REG_AR_KR3); break;	\ | 
 | 374 | 	    case 4: r = ia64_getreg(_IA64_REG_AR_KR4); break;	\ | 
 | 375 | 	    case 5: r = ia64_getreg(_IA64_REG_AR_KR5); break;	\ | 
 | 376 | 	    case 6: r = ia64_getreg(_IA64_REG_AR_KR6); break;	\ | 
 | 377 | 	    case 7: r = ia64_getreg(_IA64_REG_AR_KR7); break;	\ | 
 | 378 | 	    default: ia64_getreg_unknown_kr(); break;		\ | 
 | 379 | 	}							\ | 
 | 380 | 	r;							\ | 
 | 381 | }) | 
 | 382 |  | 
 | 383 | #define ia64_set_kr(regnum, r) 					\ | 
 | 384 | ({								\ | 
 | 385 | 	switch (regnum) {					\ | 
 | 386 | 	    case 0: ia64_setreg(_IA64_REG_AR_KR0, r); break;	\ | 
 | 387 | 	    case 1: ia64_setreg(_IA64_REG_AR_KR1, r); break;	\ | 
 | 388 | 	    case 2: ia64_setreg(_IA64_REG_AR_KR2, r); break;	\ | 
 | 389 | 	    case 3: ia64_setreg(_IA64_REG_AR_KR3, r); break;	\ | 
 | 390 | 	    case 4: ia64_setreg(_IA64_REG_AR_KR4, r); break;	\ | 
 | 391 | 	    case 5: ia64_setreg(_IA64_REG_AR_KR5, r); break;	\ | 
 | 392 | 	    case 6: ia64_setreg(_IA64_REG_AR_KR6, r); break;	\ | 
 | 393 | 	    case 7: ia64_setreg(_IA64_REG_AR_KR7, r); break;	\ | 
 | 394 | 	    default: ia64_setreg_unknown_kr(); break;		\ | 
 | 395 | 	}							\ | 
 | 396 | }) | 
 | 397 |  | 
 | 398 | /* | 
 | 399 |  * The following three macros can't be inline functions because we don't have struct | 
 | 400 |  * task_struct at this point. | 
 | 401 |  */ | 
 | 402 |  | 
| Peter Chubb | 05062d9 | 2005-06-08 15:50:20 -0700 | [diff] [blame] | 403 | /* | 
 | 404 |  * Return TRUE if task T owns the fph partition of the CPU we're running on. | 
 | 405 |  * Must be called from code that has preemption disabled. | 
 | 406 |  */ | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 407 | #define ia64_is_local_fpu_owner(t)								\ | 
 | 408 | ({												\ | 
 | 409 | 	struct task_struct *__ia64_islfo_task = (t);						\ | 
 | 410 | 	(__ia64_islfo_task->thread.last_fph_cpu == smp_processor_id()				\ | 
 | 411 | 	 && __ia64_islfo_task == (struct task_struct *) ia64_get_kr(IA64_KR_FPU_OWNER));	\ | 
 | 412 | }) | 
 | 413 |  | 
| Peter Chubb | 05062d9 | 2005-06-08 15:50:20 -0700 | [diff] [blame] | 414 | /* | 
 | 415 |  * Mark task T as owning the fph partition of the CPU we're running on. | 
 | 416 |  * Must be called from code that has preemption disabled. | 
 | 417 |  */ | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 418 | #define ia64_set_local_fpu_owner(t) do {						\ | 
 | 419 | 	struct task_struct *__ia64_slfo_task = (t);					\ | 
 | 420 | 	__ia64_slfo_task->thread.last_fph_cpu = smp_processor_id();			\ | 
 | 421 | 	ia64_set_kr(IA64_KR_FPU_OWNER, (unsigned long) __ia64_slfo_task);		\ | 
 | 422 | } while (0) | 
 | 423 |  | 
 | 424 | /* Mark the fph partition of task T as being invalid on all CPUs.  */ | 
 | 425 | #define ia64_drop_fpu(t)	((t)->thread.last_fph_cpu = -1) | 
 | 426 |  | 
 | 427 | extern void __ia64_init_fpu (void); | 
 | 428 | extern void __ia64_save_fpu (struct ia64_fpreg *fph); | 
 | 429 | extern void __ia64_load_fpu (struct ia64_fpreg *fph); | 
 | 430 | extern void ia64_save_debug_regs (unsigned long *save_area); | 
 | 431 | extern void ia64_load_debug_regs (unsigned long *save_area); | 
 | 432 |  | 
 | 433 | #ifdef CONFIG_IA32_SUPPORT | 
 | 434 | extern void ia32_save_state (struct task_struct *task); | 
 | 435 | extern void ia32_load_state (struct task_struct *task); | 
 | 436 | #endif | 
 | 437 |  | 
 | 438 | #define ia64_fph_enable()	do { ia64_rsm(IA64_PSR_DFH); ia64_srlz_d(); } while (0) | 
 | 439 | #define ia64_fph_disable()	do { ia64_ssm(IA64_PSR_DFH); ia64_srlz_d(); } while (0) | 
 | 440 |  | 
 | 441 | /* load fp 0.0 into fph */ | 
 | 442 | static inline void | 
 | 443 | ia64_init_fpu (void) { | 
 | 444 | 	ia64_fph_enable(); | 
 | 445 | 	__ia64_init_fpu(); | 
 | 446 | 	ia64_fph_disable(); | 
 | 447 | } | 
 | 448 |  | 
 | 449 | /* save f32-f127 at FPH */ | 
 | 450 | static inline void | 
 | 451 | ia64_save_fpu (struct ia64_fpreg *fph) { | 
 | 452 | 	ia64_fph_enable(); | 
 | 453 | 	__ia64_save_fpu(fph); | 
 | 454 | 	ia64_fph_disable(); | 
 | 455 | } | 
 | 456 |  | 
 | 457 | /* load f32-f127 from FPH */ | 
 | 458 | static inline void | 
 | 459 | ia64_load_fpu (struct ia64_fpreg *fph) { | 
 | 460 | 	ia64_fph_enable(); | 
 | 461 | 	__ia64_load_fpu(fph); | 
 | 462 | 	ia64_fph_disable(); | 
 | 463 | } | 
 | 464 |  | 
 | 465 | static inline __u64 | 
 | 466 | ia64_clear_ic (void) | 
 | 467 | { | 
 | 468 | 	__u64 psr; | 
 | 469 | 	psr = ia64_getreg(_IA64_REG_PSR); | 
 | 470 | 	ia64_stop(); | 
 | 471 | 	ia64_rsm(IA64_PSR_I | IA64_PSR_IC); | 
 | 472 | 	ia64_srlz_i(); | 
 | 473 | 	return psr; | 
 | 474 | } | 
 | 475 |  | 
 | 476 | /* | 
 | 477 |  * Restore the psr. | 
 | 478 |  */ | 
 | 479 | static inline void | 
 | 480 | ia64_set_psr (__u64 psr) | 
 | 481 | { | 
 | 482 | 	ia64_stop(); | 
 | 483 | 	ia64_setreg(_IA64_REG_PSR_L, psr); | 
 | 484 | 	ia64_srlz_d(); | 
 | 485 | } | 
 | 486 |  | 
 | 487 | /* | 
 | 488 |  * Insert a translation into an instruction and/or data translation | 
 | 489 |  * register. | 
 | 490 |  */ | 
 | 491 | static inline void | 
 | 492 | ia64_itr (__u64 target_mask, __u64 tr_num, | 
 | 493 | 	  __u64 vmaddr, __u64 pte, | 
 | 494 | 	  __u64 log_page_size) | 
 | 495 | { | 
 | 496 | 	ia64_setreg(_IA64_REG_CR_ITIR, (log_page_size << 2)); | 
 | 497 | 	ia64_setreg(_IA64_REG_CR_IFA, vmaddr); | 
 | 498 | 	ia64_stop(); | 
 | 499 | 	if (target_mask & 0x1) | 
 | 500 | 		ia64_itri(tr_num, pte); | 
 | 501 | 	if (target_mask & 0x2) | 
 | 502 | 		ia64_itrd(tr_num, pte); | 
 | 503 | } | 
 | 504 |  | 
 | 505 | /* | 
 | 506 |  * Insert a translation into the instruction and/or data translation | 
 | 507 |  * cache. | 
 | 508 |  */ | 
 | 509 | static inline void | 
 | 510 | ia64_itc (__u64 target_mask, __u64 vmaddr, __u64 pte, | 
 | 511 | 	  __u64 log_page_size) | 
 | 512 | { | 
 | 513 | 	ia64_setreg(_IA64_REG_CR_ITIR, (log_page_size << 2)); | 
 | 514 | 	ia64_setreg(_IA64_REG_CR_IFA, vmaddr); | 
 | 515 | 	ia64_stop(); | 
 | 516 | 	/* as per EAS2.6, itc must be the last instruction in an instruction group */ | 
 | 517 | 	if (target_mask & 0x1) | 
 | 518 | 		ia64_itci(pte); | 
 | 519 | 	if (target_mask & 0x2) | 
 | 520 | 		ia64_itcd(pte); | 
 | 521 | } | 
 | 522 |  | 
 | 523 | /* | 
 | 524 |  * Purge a range of addresses from instruction and/or data translation | 
 | 525 |  * register(s). | 
 | 526 |  */ | 
 | 527 | static inline void | 
 | 528 | ia64_ptr (__u64 target_mask, __u64 vmaddr, __u64 log_size) | 
 | 529 | { | 
 | 530 | 	if (target_mask & 0x1) | 
 | 531 | 		ia64_ptri(vmaddr, (log_size << 2)); | 
 | 532 | 	if (target_mask & 0x2) | 
 | 533 | 		ia64_ptrd(vmaddr, (log_size << 2)); | 
 | 534 | } | 
 | 535 |  | 
 | 536 | /* Set the interrupt vector address.  The address must be suitably aligned (32KB).  */ | 
 | 537 | static inline void | 
 | 538 | ia64_set_iva (void *ivt_addr) | 
 | 539 | { | 
 | 540 | 	ia64_setreg(_IA64_REG_CR_IVA, (__u64) ivt_addr); | 
 | 541 | 	ia64_srlz_i(); | 
 | 542 | } | 
 | 543 |  | 
 | 544 | /* Set the page table address and control bits.  */ | 
 | 545 | static inline void | 
 | 546 | ia64_set_pta (__u64 pta) | 
 | 547 | { | 
 | 548 | 	/* Note: srlz.i implies srlz.d */ | 
 | 549 | 	ia64_setreg(_IA64_REG_CR_PTA, pta); | 
 | 550 | 	ia64_srlz_i(); | 
 | 551 | } | 
 | 552 |  | 
 | 553 | static inline void | 
 | 554 | ia64_eoi (void) | 
 | 555 | { | 
 | 556 | 	ia64_setreg(_IA64_REG_CR_EOI, 0); | 
 | 557 | 	ia64_srlz_d(); | 
 | 558 | } | 
 | 559 |  | 
 | 560 | #define cpu_relax()	ia64_hint(ia64_hint_pause) | 
 | 561 |  | 
 | 562 | static inline void | 
 | 563 | ia64_set_lrr0 (unsigned long val) | 
 | 564 | { | 
 | 565 | 	ia64_setreg(_IA64_REG_CR_LRR0, val); | 
 | 566 | 	ia64_srlz_d(); | 
 | 567 | } | 
 | 568 |  | 
 | 569 | static inline void | 
 | 570 | ia64_set_lrr1 (unsigned long val) | 
 | 571 | { | 
 | 572 | 	ia64_setreg(_IA64_REG_CR_LRR1, val); | 
 | 573 | 	ia64_srlz_d(); | 
 | 574 | } | 
 | 575 |  | 
 | 576 |  | 
 | 577 | /* | 
 | 578 |  * Given the address to which a spill occurred, return the unat bit | 
 | 579 |  * number that corresponds to this address. | 
 | 580 |  */ | 
 | 581 | static inline __u64 | 
 | 582 | ia64_unat_pos (void *spill_addr) | 
 | 583 | { | 
 | 584 | 	return ((__u64) spill_addr >> 3) & 0x3f; | 
 | 585 | } | 
 | 586 |  | 
 | 587 | /* | 
 | 588 |  * Set the NaT bit of an integer register which was spilled at address | 
 | 589 |  * SPILL_ADDR.  UNAT is the mask to be updated. | 
 | 590 |  */ | 
 | 591 | static inline void | 
 | 592 | ia64_set_unat (__u64 *unat, void *spill_addr, unsigned long nat) | 
 | 593 | { | 
 | 594 | 	__u64 bit = ia64_unat_pos(spill_addr); | 
 | 595 | 	__u64 mask = 1UL << bit; | 
 | 596 |  | 
 | 597 | 	*unat = (*unat & ~mask) | (nat << bit); | 
 | 598 | } | 
 | 599 |  | 
 | 600 | /* | 
 | 601 |  * Return saved PC of a blocked thread. | 
 | 602 |  * Note that the only way T can block is through a call to schedule() -> switch_to(). | 
 | 603 |  */ | 
 | 604 | static inline unsigned long | 
 | 605 | thread_saved_pc (struct task_struct *t) | 
 | 606 | { | 
 | 607 | 	struct unw_frame_info info; | 
 | 608 | 	unsigned long ip; | 
 | 609 |  | 
 | 610 | 	unw_init_from_blocked_task(&info, t); | 
 | 611 | 	if (unw_unwind(&info) < 0) | 
 | 612 | 		return 0; | 
 | 613 | 	unw_get_ip(&info, &ip); | 
 | 614 | 	return ip; | 
 | 615 | } | 
 | 616 |  | 
 | 617 | /* | 
 | 618 |  * Get the current instruction/program counter value. | 
 | 619 |  */ | 
 | 620 | #define current_text_addr() \ | 
 | 621 | 	({ void *_pc; _pc = (void *)ia64_getreg(_IA64_REG_IP); _pc; }) | 
 | 622 |  | 
 | 623 | static inline __u64 | 
 | 624 | ia64_get_ivr (void) | 
 | 625 | { | 
 | 626 | 	__u64 r; | 
 | 627 | 	ia64_srlz_d(); | 
 | 628 | 	r = ia64_getreg(_IA64_REG_CR_IVR); | 
 | 629 | 	ia64_srlz_d(); | 
 | 630 | 	return r; | 
 | 631 | } | 
 | 632 |  | 
 | 633 | static inline void | 
 | 634 | ia64_set_dbr (__u64 regnum, __u64 value) | 
 | 635 | { | 
 | 636 | 	__ia64_set_dbr(regnum, value); | 
 | 637 | #ifdef CONFIG_ITANIUM | 
 | 638 | 	ia64_srlz_d(); | 
 | 639 | #endif | 
 | 640 | } | 
 | 641 |  | 
 | 642 | static inline __u64 | 
 | 643 | ia64_get_dbr (__u64 regnum) | 
 | 644 | { | 
 | 645 | 	__u64 retval; | 
 | 646 |  | 
 | 647 | 	retval = __ia64_get_dbr(regnum); | 
 | 648 | #ifdef CONFIG_ITANIUM | 
 | 649 | 	ia64_srlz_d(); | 
 | 650 | #endif | 
 | 651 | 	return retval; | 
 | 652 | } | 
 | 653 |  | 
 | 654 | static inline __u64 | 
 | 655 | ia64_rotr (__u64 w, __u64 n) | 
 | 656 | { | 
 | 657 | 	return (w >> n) | (w << (64 - n)); | 
 | 658 | } | 
 | 659 |  | 
 | 660 | #define ia64_rotl(w,n)	ia64_rotr((w), (64) - (n)) | 
 | 661 |  | 
 | 662 | /* | 
 | 663 |  * Take a mapped kernel address and return the equivalent address | 
 | 664 |  * in the region 7 identity mapped virtual area. | 
 | 665 |  */ | 
 | 666 | static inline void * | 
 | 667 | ia64_imva (void *addr) | 
 | 668 | { | 
 | 669 | 	void *result; | 
 | 670 | 	result = (void *) ia64_tpa(addr); | 
 | 671 | 	return __va(result); | 
 | 672 | } | 
 | 673 |  | 
 | 674 | #define ARCH_HAS_PREFETCH | 
 | 675 | #define ARCH_HAS_PREFETCHW | 
 | 676 | #define ARCH_HAS_SPINLOCK_PREFETCH | 
 | 677 | #define PREFETCH_STRIDE			L1_CACHE_BYTES | 
 | 678 |  | 
 | 679 | static inline void | 
 | 680 | prefetch (const void *x) | 
 | 681 | { | 
 | 682 | 	 ia64_lfetch(ia64_lfhint_none, x); | 
 | 683 | } | 
 | 684 |  | 
 | 685 | static inline void | 
 | 686 | prefetchw (const void *x) | 
 | 687 | { | 
 | 688 | 	ia64_lfetch_excl(ia64_lfhint_none, x); | 
 | 689 | } | 
 | 690 |  | 
 | 691 | #define spin_lock_prefetch(x)	prefetchw(x) | 
 | 692 |  | 
 | 693 | extern unsigned long boot_option_idle_override; | 
 | 694 |  | 
 | 695 | #endif /* !__ASSEMBLY__ */ | 
 | 696 |  | 
 | 697 | #endif /* _ASM_IA64_PROCESSOR_H */ |