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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PTRACE_H #define _ASM_X86_PTRACE_H #include <asm/segment.h> #include <asm/page_types.h> #include <uapi/asm/ptrace.h> #ifndef __ASSEMBLY__ #ifdef __i386__ struct pt_regs { /* * NB: 32-bit x86 CPUs are inconsistent as what happens in the * following cases (where %seg represents a segment register): * * - pushl %seg: some do a 16-bit write and leave the high * bits alone * - movl %seg, [mem]: some do a 16-bit write despite the movl * - IDT entry: some (e.g. 486) will leave the high bits of CS * and (if applicable) SS undefined. * * Fortunately, x86-32 doesn't read the high bits on POP or IRET, * so we can just treat all of the segment registers as 16-bit * values. */ unsigned long bx; unsigned long cx; unsigned long dx; unsigned long si; unsigned long di; unsigned long bp; unsigned long ax; unsigned short ds; unsigned short __dsh; unsigned short es; unsigned short __esh; unsigned short fs; unsigned short __fsh; /* On interrupt, gs and __gsh store the vector number. */ unsigned short gs; unsigned short __gsh; /* On interrupt, this is the error code. */ unsigned long orig_ax; unsigned long ip; unsigned short cs; unsigned short __csh; unsigned long flags; unsigned long sp; unsigned short ss; unsigned short __ssh; }; #else /* __i386__ */ struct pt_regs { /* * C ABI says these regs are callee-preserved. They aren't saved on kernel entry * unless syscall needs a complete, fully filled "struct pt_regs". */ unsigned long r15; unsigned long r14; unsigned long r13; unsigned long r12; unsigned long bp; unsigned long bx; /* These regs are callee-clobbered. Always saved on kernel entry. */ unsigned long r11; unsigned long r10; unsigned long r9; unsigned long r8; unsigned long ax; unsigned long cx; unsigned long dx; unsigned long si; unsigned long di; /* * On syscall entry, this is syscall#. On CPU exception, this is error code. * On hw interrupt, it's IRQ number: */ unsigned long orig_ax; /* Return frame for iretq */ unsigned long ip; unsigned long cs; unsigned long flags; unsigned long sp; unsigned long ss; /* top of stack page */ }; #endif /* !__i386__ */ #ifdef CONFIG_PARAVIRT #include <asm/paravirt_types.h> #endif #include <asm/proto.h> struct cpuinfo_x86; struct task_struct; extern unsigned long profile_pc(struct pt_regs *regs); extern unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs); extern void send_sigtrap(struct pt_regs *regs, int error_code, int si_code); static inline unsigned long regs_return_value(struct pt_regs *regs) { return regs->ax; } static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc) { regs->ax = rc; } /* * user_mode(regs) determines whether a register set came from user * mode. On x86_32, this is true if V8086 mode was enabled OR if the * register set was from protected mode with RPL-3 CS value. This * tricky test checks that with one comparison. * * On x86_64, vm86 mode is mercifully nonexistent, and we don't need * the extra check. */ static __always_inline int user_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_32 return ((regs->cs & SEGMENT_RPL_MASK) | (regs->flags & X86_VM_MASK)) >= USER_RPL; #else return !!(regs->cs & 3); #endif } static inline int v8086_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_32 return (regs->flags & X86_VM_MASK); #else return 0; /* No V86 mode support in long mode */ #endif } static inline bool user_64bit_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_64 #ifndef CONFIG_PARAVIRT_XXL /* * On non-paravirt systems, this is the only long mode CPL 3 * selector. We do not allow long mode selectors in the LDT. */ return regs->cs == __USER_CS; #else /* Headers are too twisted for this to go in paravirt.h. */ return regs->cs == __USER_CS || regs->cs == pv_info.extra_user_64bit_cs; #endif #else /* !CONFIG_X86_64 */ return false; #endif } /* * Determine whether the register set came from any context that is running in * 64-bit mode. */ static inline bool any_64bit_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_64 return !user_mode(regs) || user_64bit_mode(regs); #else return false; #endif } #ifdef CONFIG_X86_64 #define current_user_stack_pointer() current_pt_regs()->sp #define compat_user_stack_pointer() current_pt_regs()->sp static inline bool ip_within_syscall_gap(struct pt_regs *regs) { bool ret = (regs->ip >= (unsigned long)entry_SYSCALL_64 && regs->ip < (unsigned long)entry_SYSCALL_64_safe_stack); #ifdef CONFIG_IA32_EMULATION ret = ret || (regs->ip >= (unsigned long)entry_SYSCALL_compat && regs->ip < (unsigned long)entry_SYSCALL_compat_safe_stack); #endif return ret; } #endif static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) { return regs->sp; } static inline unsigned long instruction_pointer(struct pt_regs *regs) { return regs->ip; } static inline void instruction_pointer_set(struct pt_regs *regs, unsigned long val) { regs->ip = val; } static inline unsigned long frame_pointer(struct pt_regs *regs) { return regs->bp; } static inline unsigned long user_stack_pointer(struct pt_regs *regs) { return regs->sp; } static inline void user_stack_pointer_set(struct pt_regs *regs, unsigned long val) { regs->sp = val; } static __always_inline bool regs_irqs_disabled(struct pt_regs *regs) { return !(regs->flags & X86_EFLAGS_IF); } /* Query offset/name of register from its name/offset */ extern int regs_query_register_offset(const char *name); extern const char *regs_query_register_name(unsigned int offset); #define MAX_REG_OFFSET (offsetof(struct pt_regs, ss)) /** * regs_get_register() - get register value from its offset * @regs: pt_regs from which register value is gotten. * @offset: offset number of the register. * * regs_get_register returns the value of a register. The @offset is the * offset of the register in struct pt_regs address which specified by @regs. * If @offset is bigger than MAX_REG_OFFSET, this returns 0. */ static inline unsigned long regs_get_register(struct pt_regs *regs, unsigned int offset) { if (unlikely(offset > MAX_REG_OFFSET)) return 0; #ifdef CONFIG_X86_32 /* The selector fields are 16-bit. */ if (offset == offsetof(struct pt_regs, cs) || offset == offsetof(struct pt_regs, ss) || offset == offsetof(struct pt_regs, ds) || offset == offsetof(struct pt_regs, es) || offset == offsetof(struct pt_regs, fs) || offset == offsetof(struct pt_regs, gs)) { return *(u16 *)((unsigned long)regs + offset); } #endif return *(unsigned long *)((unsigned long)regs + offset); } /** * regs_within_kernel_stack() - check the address in the stack * @regs: pt_regs which contains kernel stack pointer. * @addr: address which is checked. * * regs_within_kernel_stack() checks @addr is within the kernel stack page(s). * If @addr is within the kernel stack, it returns true. If not, returns false. */ static inline int regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr) { return ((addr & ~(THREAD_SIZE - 1)) == (regs->sp & ~(THREAD_SIZE - 1))); } /** * regs_get_kernel_stack_nth_addr() - get the address of the Nth entry on stack * @regs: pt_regs which contains kernel stack pointer. * @n: stack entry number. * * regs_get_kernel_stack_nth() returns the address of the @n th entry of the * kernel stack which is specified by @regs. If the @n th entry is NOT in * the kernel stack, this returns NULL. */ static inline unsigned long *regs_get_kernel_stack_nth_addr(struct pt_regs *regs, unsigned int n) { unsigned long *addr = (unsigned long *)regs->sp; addr += n; if (regs_within_kernel_stack(regs, (unsigned long)addr)) return addr; else return NULL; } /* To avoid include hell, we can't include uaccess.h */ extern long copy_from_kernel_nofault(void *dst, const void *src, size_t size); /** * regs_get_kernel_stack_nth() - get Nth entry of the stack * @regs: pt_regs which contains kernel stack pointer. * @n: stack entry number. * * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which * is specified by @regs. If the @n th entry is NOT in the kernel stack * this returns 0. */ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n) { unsigned long *addr; unsigned long val; long ret; addr = regs_get_kernel_stack_nth_addr(regs, n); if (addr) { ret = copy_from_kernel_nofault(&val, addr, sizeof(val)); if (!ret) return val; } return 0; } /** * regs_get_kernel_argument() - get Nth function argument in kernel * @regs: pt_regs of that context * @n: function argument number (start from 0) * * regs_get_argument() returns @n th argument of the function call. * Note that this chooses most probably assignment, in some case * it can be incorrect. * This is expected to be called from kprobes or ftrace with regs * where the top of stack is the return address. */ static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, unsigned int n) { static const unsigned int argument_offs[] = { #ifdef __i386__ offsetof(struct pt_regs, ax), offsetof(struct pt_regs, dx), offsetof(struct pt_regs, cx), #define NR_REG_ARGUMENTS 3 #else offsetof(struct pt_regs, di), offsetof(struct pt_regs, si), offsetof(struct pt_regs, dx), offsetof(struct pt_regs, cx), offsetof(struct pt_regs, r8), offsetof(struct pt_regs, r9), #define NR_REG_ARGUMENTS 6 #endif }; if (n >= NR_REG_ARGUMENTS) { n -= NR_REG_ARGUMENTS - 1; return regs_get_kernel_stack_nth(regs, n); } else return regs_get_register(regs, argument_offs[n]); } #define arch_has_single_step() (1) #ifdef CONFIG_X86_DEBUGCTLMSR #define arch_has_block_step() (1) #else #define arch_has_block_step() (boot_cpu_data.x86 >= 6) #endif #define ARCH_HAS_USER_SINGLE_STEP_REPORT struct user_desc; extern int do_get_thread_area(struct task_struct *p, int idx, struct user_desc __user *info); extern int do_set_thread_area(struct task_struct *p, int idx, struct user_desc __user *info, int can_allocate); #ifdef CONFIG_X86_64 # define do_set_thread_area_64(p, s, t) do_arch_prctl_64(p, s, t) #else # define do_set_thread_area_64(p, s, t) (0) #endif #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_PTRACE_H */
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _KERNEL_PRINTK_RINGBUFFER_H #define _KERNEL_PRINTK_RINGBUFFER_H #include <linux/atomic.h> #include <linux/dev_printk.h> /* * Meta information about each stored message. * * All fields are set by the printk code except for @seq, which is * set by the ringbuffer code. */ struct printk_info { u64 seq; /* sequence number */ u64 ts_nsec; /* timestamp in nanoseconds */ u16 text_len; /* length of text message */ u8 facility; /* syslog facility */ u8 flags:5; /* internal record flags */ u8 level:3; /* syslog level */ u32 caller_id; /* thread id or processor id */ struct dev_printk_info dev_info; }; /* * A structure providing the buffers, used by writers and readers. * * Writers: * Using prb_rec_init_wr(), a writer sets @text_buf_size before calling * prb_reserve(). On success, prb_reserve() sets @info and @text_buf to * buffers reserved for that writer. * * Readers: * Using prb_rec_init_rd(), a reader sets all fields before calling * prb_read_valid(). Note that the reader provides the @info and @text_buf, * buffers. On success, the struct pointed to by @info will be filled and * the char array pointed to by @text_buf will be filled with text data. */ struct printk_record { struct printk_info *info; char *text_buf; unsigned int text_buf_size; }; /* Specifies the logical position and span of a data block. */ struct prb_data_blk_lpos { unsigned long begin; unsigned long next; }; /* * A descriptor: the complete meta-data for a record. * * @state_var: A bitwise combination of descriptor ID and descriptor state. */ struct prb_desc { atomic_long_t state_var; struct prb_data_blk_lpos text_blk_lpos; }; /* A ringbuffer of "ID + data" elements. */ struct prb_data_ring { unsigned int size_bits; char *data; atomic_long_t head_lpos; atomic_long_t tail_lpos; }; /* A ringbuffer of "struct prb_desc" elements. */ struct prb_desc_ring { unsigned int count_bits; struct prb_desc *descs; struct printk_info *infos; atomic_long_t head_id; atomic_long_t tail_id; }; /* * The high level structure representing the printk ringbuffer. * * @fail: Count of failed prb_reserve() calls where not even a data-less * record was created. */ struct printk_ringbuffer { struct prb_desc_ring desc_ring; struct prb_data_ring text_data_ring; atomic_long_t fail; }; /* * Used by writers as a reserve/commit handle. * * @rb: Ringbuffer where the entry is reserved. * @irqflags: Saved irq flags to restore on entry commit. * @id: ID of the reserved descriptor. * @text_space: Total occupied buffer space in the text data ring, including * ID, alignment padding, and wrapping data blocks. * * This structure is an opaque handle for writers. Its contents are only * to be used by the ringbuffer implementation. */ struct prb_reserved_entry { struct printk_ringbuffer *rb; unsigned long irqflags; unsigned long id; unsigned int text_space; }; /* The possible responses of a descriptor state-query. */ enum desc_state { desc_miss = -1, /* ID mismatch (pseudo state) */ desc_reserved = 0x0, /* reserved, in use by writer */ desc_committed = 0x1, /* committed by writer, could get reopened */ desc_finalized = 0x2, /* committed, no further modification allowed */ desc_reusable = 0x3, /* free, not yet used by any writer */ }; #define _DATA_SIZE(sz_bits) (1UL << (sz_bits)) #define _DESCS_COUNT(ct_bits) (1U << (ct_bits)) #define DESC_SV_BITS (sizeof(unsigned long) * 8) #define DESC_FLAGS_SHIFT (DESC_SV_BITS - 2) #define DESC_FLAGS_MASK (3UL << DESC_FLAGS_SHIFT) #define DESC_STATE(sv) (3UL & (sv >> DESC_FLAGS_SHIFT)) #define DESC_SV(id, state) (((unsigned long)state << DESC_FLAGS_SHIFT) | id) #define DESC_ID_MASK (~DESC_FLAGS_MASK) #define DESC_ID(sv) ((sv) & DESC_ID_MASK) #define FAILED_LPOS 0x1 #define NO_LPOS 0x3 #define FAILED_BLK_LPOS \ { \ .begin = FAILED_LPOS, \ .next = FAILED_LPOS, \ } /* * Descriptor Bootstrap * * The descriptor array is minimally initialized to allow immediate usage * by readers and writers. The requirements that the descriptor array * initialization must satisfy: * * Req1 * The tail must point to an existing (committed or reusable) descriptor. * This is required by the implementation of prb_first_seq(). * * Req2 * Readers must see that the ringbuffer is initially empty. * * Req3 * The first record reserved by a writer is assigned sequence number 0. * * To satisfy Req1, the tail initially points to a descriptor that is * minimally initialized (having no data block, i.e. data-less with the * data block's lpos @begin and @next values set to FAILED_LPOS). * * To satisfy Req2, the initial tail descriptor is initialized to the * reusable state. Readers recognize reusable descriptors as existing * records, but skip over them. * * To satisfy Req3, the last descriptor in the array is used as the initial * head (and tail) descriptor. This allows the first record reserved by a * writer (head + 1) to be the first descriptor in the array. (Only the first * descriptor in the array could have a valid sequence number of 0.) * * The first time a descriptor is reserved, it is assigned a sequence number * with the value of the array index. A "first time reserved" descriptor can * be recognized because it has a sequence number of 0 but does not have an * index of 0. (Only the first descriptor in the array could have a valid * sequence number of 0.) After the first reservation, all future reservations * (recycling) simply involve incrementing the sequence number by the array * count. * * Hack #1 * Only the first descriptor in the array is allowed to have the sequence * number 0. In this case it is not possible to recognize if it is being * reserved the first time (set to index value) or has been reserved * previously (increment by the array count). This is handled by _always_ * incrementing the sequence number by the array count when reserving the * first descriptor in the array. In order to satisfy Req3, the sequence * number of the first descriptor in the array is initialized to minus * the array count. Then, upon the first reservation, it is incremented * to 0, thus satisfying Req3. * * Hack #2 * prb_first_seq() can be called at any time by readers to retrieve the * sequence number of the tail descriptor. However, due to Req2 and Req3, * initially there are no records to report the sequence number of * (sequence numbers are u64 and there is nothing less than 0). To handle * this, the sequence number of the initial tail descriptor is initialized * to 0. Technically this is incorrect, because there is no record with * sequence number 0 (yet) and the tail descriptor is not the first * descriptor in the array. But it allows prb_read_valid() to correctly * report the existence of a record for _any_ given sequence number at all * times. Bootstrapping is complete when the tail is pushed the first * time, thus finally pointing to the first descriptor reserved by a * writer, which has the assigned sequence number 0. */ /* * Initiating Logical Value Overflows * * Both logical position (lpos) and ID values can be mapped to array indexes * but may experience overflows during the lifetime of the system. To ensure * that printk_ringbuffer can handle the overflows for these types, initial * values are chosen that map to the correct initial array indexes, but will * result in overflows soon. * * BLK0_LPOS * The initial @head_lpos and @tail_lpos for data rings. It is at index * 0 and the lpos value is such that it will overflow on the first wrap. * * DESC0_ID * The initial @head_id and @tail_id for the desc ring. It is at the last * index of the descriptor array (see Req3 above) and the ID value is such * that it will overflow on the second wrap. */ #define BLK0_LPOS(sz_bits) (-(_DATA_SIZE(sz_bits))) #define DESC0_ID(ct_bits) DESC_ID(-(_DESCS_COUNT(ct_bits) + 1)) #define DESC0_SV(ct_bits) DESC_SV(DESC0_ID(ct_bits), desc_reusable) /* * Define a ringbuffer with an external text data buffer. The same as * DEFINE_PRINTKRB() but requires specifying an external buffer for the * text data. * * Note: The specified external buffer must be of the size: * 2 ^ (descbits + avgtextbits) */ #define _DEFINE_PRINTKRB(name, descbits, avgtextbits, text_buf) \ static struct prb_desc _##name##_descs[_DESCS_COUNT(descbits)] = { \ /* the initial head and tail */ \ [_DESCS_COUNT(descbits) - 1] = { \ /* reusable */ \ .state_var = ATOMIC_INIT(DESC0_SV(descbits)), \ /* no associated data block */ \ .text_blk_lpos = FAILED_BLK_LPOS, \ }, \ }; \ static struct printk_info _##name##_infos[_DESCS_COUNT(descbits)] = { \ /* this will be the first record reserved by a writer */ \ [0] = { \ /* will be incremented to 0 on the first reservation */ \ .seq = -(u64)_DESCS_COUNT(descbits), \ }, \ /* the initial head and tail */ \ [_DESCS_COUNT(descbits) - 1] = { \ /* reports the first seq value during the bootstrap phase */ \ .seq = 0, \ }, \ }; \ static struct printk_ringbuffer name = { \ .desc_ring = { \ .count_bits = descbits, \ .descs = &_##name##_descs[0], \ .infos = &_##name##_infos[0], \ .head_id = ATOMIC_INIT(DESC0_ID(descbits)), \ .tail_id = ATOMIC_INIT(DESC0_ID(descbits)), \ }, \ .text_data_ring = { \ .size_bits = (avgtextbits) + (descbits), \ .data = text_buf, \ .head_lpos = ATOMIC_LONG_INIT(BLK0_LPOS((avgtextbits) + (descbits))), \ .tail_lpos = ATOMIC_LONG_INIT(BLK0_LPOS((avgtextbits) + (descbits))), \ }, \ .fail = ATOMIC_LONG_INIT(0), \ } /** * DEFINE_PRINTKRB() - Define a ringbuffer. * * @name: The name of the ringbuffer variable. * @descbits: The number of descriptors as a power-of-2 value. * @avgtextbits: The average text data size per record as a power-of-2 value. * * This is a macro for defining a ringbuffer and all internal structures * such that it is ready for immediate use. See _DEFINE_PRINTKRB() for a * variant where the text data buffer can be specified externally. */ #define DEFINE_PRINTKRB(name, descbits, avgtextbits) \ static char _##name##_text[1U << ((avgtextbits) + (descbits))] \ __aligned(__alignof__(unsigned long)); \ _DEFINE_PRINTKRB(name, descbits, avgtextbits, &_##name##_text[0]) /* Writer Interface */ /** * prb_rec_init_wd() - Initialize a buffer for writing records. * * @r: The record to initialize. * @text_buf_size: The needed text buffer size. */ static inline void prb_rec_init_wr(struct printk_record *r, unsigned int text_buf_size) { r->info = NULL; r->text_buf = NULL; r->text_buf_size = text_buf_size; } bool prb_reserve(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, struct printk_record *r); bool prb_reserve_in_last(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, struct printk_record *r, u32 caller_id, unsigned int max_size); void prb_commit(struct prb_reserved_entry *e); void prb_final_commit(struct prb_reserved_entry *e); void prb_init(struct printk_ringbuffer *rb, char *text_buf, unsigned int text_buf_size, struct prb_desc *descs, unsigned int descs_count_bits, struct printk_info *infos); unsigned int prb_record_text_space(struct prb_reserved_entry *e); /* Reader Interface */ /** * prb_rec_init_rd() - Initialize a buffer for reading records. * * @r: The record to initialize. * @info: A buffer to store record meta-data. * @text_buf: A buffer to store text data. * @text_buf_size: The size of @text_buf. * * Initialize all the fields that a reader is interested in. All arguments * (except @r) are optional. Only record data for arguments that are * non-NULL or non-zero will be read. */ static inline void prb_rec_init_rd(struct printk_record *r, struct printk_info *info, char *text_buf, unsigned int text_buf_size) { r->info = info; r->text_buf = text_buf; r->text_buf_size = text_buf_size; } /** * prb_for_each_record() - Iterate over the records of a ringbuffer. * * @from: The sequence number to begin with. * @rb: The ringbuffer to iterate over. * @s: A u64 to store the sequence number on each iteration. * @r: A printk_record to store the record on each iteration. * * This is a macro for conveniently iterating over a ringbuffer. * Note that @s may not be the sequence number of the record on each * iteration. For the sequence number, @r->info->seq should be checked. * * Context: Any context. */ #define prb_for_each_record(from, rb, s, r) \ for ((s) = from; prb_read_valid(rb, s, r); (s) = (r)->info->seq + 1) /** * prb_for_each_info() - Iterate over the meta data of a ringbuffer. * * @from: The sequence number to begin with. * @rb: The ringbuffer to iterate over. * @s: A u64 to store the sequence number on each iteration. * @i: A printk_info to store the record meta data on each iteration. * @lc: An unsigned int to store the text line count of each record. * * This is a macro for conveniently iterating over a ringbuffer. * Note that @s may not be the sequence number of the record on each * iteration. For the sequence number, @r->info->seq should be checked. * * Context: Any context. */ #define prb_for_each_info(from, rb, s, i, lc) \ for ((s) = from; prb_read_valid_info(rb, s, i, lc); (s) = (i)->seq + 1) bool prb_read_valid(struct printk_ringbuffer *rb, u64 seq, struct printk_record *r); bool prb_read_valid_info(struct printk_ringbuffer *rb, u64 seq, struct printk_info *info, unsigned int *line_count); u64 prb_first_valid_seq(struct printk_ringbuffer *rb); u64 prb_next_seq(struct printk_ringbuffer *rb); #endif /* _KERNEL_PRINTK_RINGBUFFER_H */
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NET_NEIGHBOUR_H #define _NET_NEIGHBOUR_H #include <linux/neighbour.h> /* * Generic neighbour manipulation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * * Changes: * * Harald Welte: <laforge@gnumonks.org> * - Add neighbour cache statistics like rtstat */ #include <linux/atomic.h> #include <linux/refcount.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/rcupdate.h> #include <linux/seq_file.h> #include <linux/bitmap.h> #include <linux/err.h> #include <linux/sysctl.h> #include <linux/workqueue.h> #include <net/rtnetlink.h> /* * NUD stands for "neighbor unreachability detection" */ #define NUD_IN_TIMER (NUD_INCOMPLETE|NUD_REACHABLE|NUD_DELAY|NUD_PROBE) #define NUD_VALID (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE|NUD_PROBE|NUD_STALE|NUD_DELAY) #define NUD_CONNECTED (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE) struct neighbour; enum { NEIGH_VAR_MCAST_PROBES, NEIGH_VAR_UCAST_PROBES, NEIGH_VAR_APP_PROBES, NEIGH_VAR_MCAST_REPROBES, NEIGH_VAR_RETRANS_TIME, NEIGH_VAR_BASE_REACHABLE_TIME, NEIGH_VAR_DELAY_PROBE_TIME, NEIGH_VAR_GC_STALETIME, NEIGH_VAR_QUEUE_LEN_BYTES, NEIGH_VAR_PROXY_QLEN, NEIGH_VAR_ANYCAST_DELAY, NEIGH_VAR_PROXY_DELAY, NEIGH_VAR_LOCKTIME, #define NEIGH_VAR_DATA_MAX (NEIGH_VAR_LOCKTIME + 1) /* Following are used as a second way to access one of the above */ NEIGH_VAR_QUEUE_LEN, /* same data as NEIGH_VAR_QUEUE_LEN_BYTES */ NEIGH_VAR_RETRANS_TIME_MS, /* same data as NEIGH_VAR_RETRANS_TIME */ NEIGH_VAR_BASE_REACHABLE_TIME_MS, /* same data as NEIGH_VAR_BASE_REACHABLE_TIME */ /* Following are used by "default" only */ NEIGH_VAR_GC_INTERVAL, NEIGH_VAR_GC_THRESH1, NEIGH_VAR_GC_THRESH2, NEIGH_VAR_GC_THRESH3, NEIGH_VAR_MAX }; struct neigh_parms { possible_net_t net; struct net_device *dev; struct list_head list; int (*neigh_setup)(struct neighbour *); struct neigh_table *tbl; void *sysctl_table; int dead; refcount_t refcnt; struct rcu_head rcu_head; int reachable_time; int data[NEIGH_VAR_DATA_MAX]; DECLARE_BITMAP(data_state, NEIGH_VAR_DATA_MAX); }; static inline void neigh_var_set(struct neigh_parms *p, int index, int val) { set_bit(index, p->data_state); p->data[index] = val; } #define NEIGH_VAR(p, attr) ((p)->data[NEIGH_VAR_ ## attr]) /* In ndo_neigh_setup, NEIGH_VAR_INIT should be used. * In other cases, NEIGH_VAR_SET should be used. */ #define NEIGH_VAR_INIT(p, attr, val) (NEIGH_VAR(p, attr) = val) #define NEIGH_VAR_SET(p, attr, val) neigh_var_set(p, NEIGH_VAR_ ## attr, val) static inline void neigh_parms_data_state_setall(struct neigh_parms *p) { bitmap_fill(p->data_state, NEIGH_VAR_DATA_MAX); } static inline void neigh_parms_data_state_cleanall(struct neigh_parms *p) { bitmap_zero(p->data_state, NEIGH_VAR_DATA_MAX); } struct neigh_statistics { unsigned long allocs; /* number of allocated neighs */ unsigned long destroys; /* number of destroyed neighs */ unsigned long hash_grows; /* number of hash resizes */ unsigned long res_failed; /* number of failed resolutions */ unsigned long lookups; /* number of lookups */ unsigned long hits; /* number of hits (among lookups) */ unsigned long rcv_probes_mcast; /* number of received mcast ipv6 */ unsigned long rcv_probes_ucast; /* number of received ucast ipv6 */ unsigned long periodic_gc_runs; /* number of periodic GC runs */ unsigned long forced_gc_runs; /* number of forced GC runs */ unsigned long unres_discards; /* number of unresolved drops */ unsigned long table_fulls; /* times even gc couldn't help */ }; #define NEIGH_CACHE_STAT_INC(tbl, field) this_cpu_inc((tbl)->stats->field) struct neighbour { struct neighbour __rcu *next; struct neigh_table *tbl; struct neigh_parms *parms; unsigned long confirmed; unsigned long updated; rwlock_t lock; refcount_t refcnt; unsigned int arp_queue_len_bytes; struct sk_buff_head arp_queue; struct timer_list timer; unsigned long used; atomic_t probes; __u8 flags; __u8 nud_state; __u8 type; __u8 dead; u8 protocol; seqlock_t ha_lock; unsigned char ha[ALIGN(MAX_ADDR_LEN, sizeof(unsigned long))] __aligned(8); struct hh_cache hh; int (*output)(struct neighbour *, struct sk_buff *); const struct neigh_ops *ops; struct list_head gc_list; struct rcu_head rcu; struct net_device *dev; u8 primary_key[0]; } __randomize_layout; struct neigh_ops { int family; void (*solicit)(struct neighbour *, struct sk_buff *); void (*error_report)(struct neighbour *, struct sk_buff *); int (*output)(struct neighbour *, struct sk_buff *); int (*connected_output)(struct neighbour *, struct sk_buff *); }; struct pneigh_entry { struct pneigh_entry *next; possible_net_t net; struct net_device *dev; u8 flags; u8 protocol; u8 key[]; }; /* * neighbour table manipulation */ #define NEIGH_NUM_HASH_RND 4 struct neigh_hash_table { struct neighbour __rcu **hash_buckets; unsigned int hash_shift; __u32 hash_rnd[NEIGH_NUM_HASH_RND]; struct rcu_head rcu; }; struct neigh_table { int family; unsigned int entry_size; unsigned int key_len; __be16 protocol; __u32 (*hash)(const void *pkey, const struct net_device *dev, __u32 *hash_rnd); bool (*key_eq)(const struct neighbour *, const void *pkey); int (*constructor)(struct neighbour *); int (*pconstructor)(struct pneigh_entry *); void (*pdestructor)(struct pneigh_entry *); void (*proxy_redo)(struct sk_buff *skb); int (*is_multicast)(const void *pkey); bool (*allow_add)(const struct net_device *dev, struct netlink_ext_ack *extack); char *id; struct neigh_parms parms; struct list_head parms_list; int gc_interval; int gc_thresh1; int gc_thresh2; int gc_thresh3; unsigned long last_flush; struct delayed_work gc_work; struct timer_list proxy_timer; struct sk_buff_head proxy_queue; atomic_t entries; atomic_t gc_entries; struct list_head gc_list; rwlock_t lock; unsigned long last_rand; struct neigh_statistics __percpu *stats; struct neigh_hash_table __rcu *nht; struct pneigh_entry **phash_buckets; }; enum { NEIGH_ARP_TABLE = 0, NEIGH_ND_TABLE = 1, NEIGH_DN_TABLE = 2, NEIGH_NR_TABLES, NEIGH_LINK_TABLE = NEIGH_NR_TABLES /* Pseudo table for neigh_xmit */ }; static inline int neigh_parms_family(struct neigh_parms *p) { return p->tbl->family; } #define NEIGH_PRIV_ALIGN sizeof(long long) #define NEIGH_ENTRY_SIZE(size) ALIGN((size), NEIGH_PRIV_ALIGN) static inline void *neighbour_priv(const struct neighbour *n) { return (char *)n + n->tbl->entry_size; } /* flags for neigh_update() */ #define NEIGH_UPDATE_F_OVERRIDE 0x00000001 #define NEIGH_UPDATE_F_WEAK_OVERRIDE 0x00000002 #define NEIGH_UPDATE_F_OVERRIDE_ISROUTER 0x00000004 #define NEIGH_UPDATE_F_USE 0x10000000 #define NEIGH_UPDATE_F_EXT_LEARNED 0x20000000 #define NEIGH_UPDATE_F_ISROUTER 0x40000000 #define NEIGH_UPDATE_F_ADMIN 0x80000000 extern const struct nla_policy nda_policy[]; static inline bool neigh_key_eq16(const struct neighbour *n, const void *pkey) { return *(const u16 *)n->primary_key == *(const u16 *)pkey; } static inline bool neigh_key_eq32(const struct neighbour *n, const void *pkey) { return *(const u32 *)n->primary_key == *(const u32 *)pkey; } static inline bool neigh_key_eq128(const struct neighbour *n, const void *pkey) { const u32 *n32 = (const u32 *)n->primary_key; const u32 *p32 = pkey; return ((n32[0] ^ p32[0]) | (n32[1] ^ p32[1]) | (n32[2] ^ p32[2]) | (n32[3] ^ p32[3])) == 0; } static inline struct neighbour *___neigh_lookup_noref( struct neigh_table *tbl, bool (*key_eq)(const struct neighbour *n, const void *pkey), __u32 (*hash)(const void *pkey, const struct net_device *dev, __u32 *hash_rnd), const void *pkey, struct net_device *dev) { struct neigh_hash_table *nht = rcu_dereference_bh(tbl->nht); struct neighbour *n; u32 hash_val; hash_val = hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift); for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); n != NULL; n = rcu_dereference_bh(n->next)) { if (n->dev == dev && key_eq(n, pkey)) return n; } return NULL; } static inline struct neighbour *__neigh_lookup_noref(struct neigh_table *tbl, const void *pkey, struct net_device *dev) { return ___neigh_lookup_noref(tbl, tbl->key_eq, tbl->hash, pkey, dev); } void neigh_table_init(int index, struct neigh_table *tbl); int neigh_table_clear(int index, struct neigh_table *tbl); struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, struct net_device *dev); struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net, const void *pkey); struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey, struct net_device *dev, bool want_ref); static inline struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey, struct net_device *dev) { return __neigh_create(tbl, pkey, dev, true); } void neigh_destroy(struct neighbour *neigh); int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb); int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid); void __neigh_set_probe_once(struct neighbour *neigh); bool neigh_remove_one(struct neighbour *ndel, struct neigh_table *tbl); void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev); int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev); int neigh_carrier_down(struct neigh_table *tbl, struct net_device *dev); int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb); int neigh_connected_output(struct neighbour *neigh, struct sk_buff *skb); int neigh_direct_output(struct neighbour *neigh, struct sk_buff *skb); struct neighbour *neigh_event_ns(struct neigh_table *tbl, u8 *lladdr, void *saddr, struct net_device *dev); struct neigh_parms *neigh_parms_alloc(struct net_device *dev, struct neigh_table *tbl); void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms); static inline struct net *neigh_parms_net(const struct neigh_parms *parms) { return read_pnet(&parms->net); } unsigned long neigh_rand_reach_time(unsigned long base); void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, struct sk_buff *skb); struct pneigh_entry *pneigh_lookup(struct neigh_table *tbl, struct net *net, const void *key, struct net_device *dev, int creat); struct pneigh_entry *__pneigh_lookup(struct neigh_table *tbl, struct net *net, const void *key, struct net_device *dev); int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *key, struct net_device *dev); static inline struct net *pneigh_net(const struct pneigh_entry *pneigh) { return read_pnet(&pneigh->net); } void neigh_app_ns(struct neighbour *n); void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void *), void *cookie); void __neigh_for_each_release(struct neigh_table *tbl, int (*cb)(struct neighbour *)); int neigh_xmit(int fam, struct net_device *, const void *, struct sk_buff *); void pneigh_for_each(struct neigh_table *tbl, void (*cb)(struct pneigh_entry *)); struct neigh_seq_state { struct seq_net_private p; struct neigh_table *tbl; struct neigh_hash_table *nht; void *(*neigh_sub_iter)(struct neigh_seq_state *state, struct neighbour *n, loff_t *pos); unsigned int bucket; unsigned int flags; #define NEIGH_SEQ_NEIGH_ONLY 0x00000001 #define NEIGH_SEQ_IS_PNEIGH 0x00000002 #define NEIGH_SEQ_SKIP_NOARP 0x00000004 }; void *neigh_seq_start(struct seq_file *, loff_t *, struct neigh_table *, unsigned int); void *neigh_seq_next(struct seq_file *, void *, loff_t *); void neigh_seq_stop(struct seq_file *, void *); int neigh_proc_dointvec(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); int neigh_proc_dointvec_jiffies(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); int neigh_proc_dointvec_ms_jiffies(struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, proc_handler *proc_handler); void neigh_sysctl_unregister(struct neigh_parms *p); static inline void __neigh_parms_put(struct neigh_parms *parms) { refcount_dec(&parms->refcnt); } static inline struct neigh_parms *neigh_parms_clone(struct neigh_parms *parms) { refcount_inc(&parms->refcnt); return parms; } /* * Neighbour references */ static inline void neigh_release(struct neighbour *neigh) { if (refcount_dec_and_test(&neigh->refcnt)) neigh_destroy(neigh); } static inline struct neighbour * neigh_clone(struct neighbour *neigh) { if (neigh) refcount_inc(&neigh->refcnt); return neigh; } #define neigh_hold(n) refcount_inc(&(n)->refcnt) static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) { unsigned long now = jiffies; if (READ_ONCE(neigh->used) != now) WRITE_ONCE(neigh->used, now); if (!(neigh->nud_state&(NUD_CONNECTED|NUD_DELAY|NUD_PROBE))) return __neigh_event_send(neigh, skb); return 0; } #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb) { unsigned int seq, hh_alen; do { seq = read_seqbegin(&hh->hh_lock); hh_alen = HH_DATA_ALIGN(ETH_HLEN); memcpy(skb->data - hh_alen, hh->hh_data, ETH_ALEN + hh_alen - ETH_HLEN); } while (read_seqretry(&hh->hh_lock, seq)); return 0; } #endif static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb) { unsigned int hh_alen = 0; unsigned int seq; unsigned int hh_len; do { seq = read_seqbegin(&hh->hh_lock); hh_len = READ_ONCE(hh->hh_len); if (likely(hh_len <= HH_DATA_MOD)) { hh_alen = HH_DATA_MOD; /* skb_push() would proceed silently if we have room for * the unaligned size but not for the aligned size: * check headroom explicitly. */ if (likely(skb_headroom(skb) >= HH_DATA_MOD)) { /* this is inlined by gcc */ memcpy(skb->data - HH_DATA_MOD, hh->hh_data, HH_DATA_MOD); } } else { hh_alen = HH_DATA_ALIGN(hh_len); if (likely(skb_headroom(skb) >= hh_alen)) { memcpy(skb->data - hh_alen, hh->hh_data, hh_alen); } } } while (read_seqretry(&hh->hh_lock, seq)); if (WARN_ON_ONCE(skb_headroom(skb) < hh_alen)) { kfree_skb(skb); return NET_XMIT_DROP; } __skb_push(skb, hh_len); return dev_queue_xmit(skb); } static inline int neigh_output(struct neighbour *n, struct sk_buff *skb, bool skip_cache) { const struct hh_cache *hh = &n->hh; /* n->nud_state and hh->hh_len could be changed under us. * neigh_hh_output() is taking care of the race later. */ if (!skip_cache && (READ_ONCE(n->nud_state) & NUD_CONNECTED) && READ_ONCE(hh->hh_len)) return neigh_hh_output(hh, skb); return n->output(n, skb); } static inline struct neighbour * __neigh_lookup(struct neigh_table *tbl, const void *pkey, struct net_device *dev, int creat) { struct neighbour *n = neigh_lookup(tbl, pkey, dev); if (n || !creat) return n; n = neigh_create(tbl, pkey, dev); return IS_ERR(n) ? NULL : n; } static inline struct neighbour * __neigh_lookup_errno(struct neigh_table *tbl, const void *pkey, struct net_device *dev) { struct neighbour *n = neigh_lookup(tbl, pkey, dev); if (n) return n; return neigh_create(tbl, pkey, dev); } struct neighbour_cb { unsigned long sched_next; unsigned int flags; }; #define LOCALLY_ENQUEUED 0x1 #define NEIGH_CB(skb) ((struct neighbour_cb *)(skb)->cb) static inline void neigh_ha_snapshot(char *dst, const struct neighbour *n, const struct net_device *dev) { unsigned int seq; do { seq = read_seqbegin(&n->ha_lock); memcpy(dst, n->ha, dev->addr_len); } while (read_seqretry(&n->ha_lock, seq)); } static inline void neigh_update_is_router(struct neighbour *neigh, u32 flags, int *notify) { u8 ndm_flags = 0; ndm_flags |= (flags & NEIGH_UPDATE_F_ISROUTER) ? NTF_ROUTER : 0; if ((neigh->flags ^ ndm_flags) & NTF_ROUTER) { if (ndm_flags & NTF_ROUTER) neigh->flags |= NTF_ROUTER; else neigh->flags &= ~NTF_ROUTER; *notify = 1; } } #endif
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __IEEE802154_CORE_H #define __IEEE802154_CORE_H #include <net/cfg802154.h> struct cfg802154_registered_device { const struct cfg802154_ops *ops; struct list_head list; /* wpan_phy index, internal only */ int wpan_phy_idx; /* also protected by devlist_mtx */ int opencount; wait_queue_head_t dev_wait; /* protected by RTNL only */ int num_running_ifaces; /* associated wpan interfaces, protected by rtnl or RCU */ struct list_head wpan_dev_list; int devlist_generation, wpan_dev_id; /* must be last because of the way we do wpan_phy_priv(), * and it should at least be aligned to NETDEV_ALIGN */ struct wpan_phy wpan_phy __aligned(NETDEV_ALIGN); }; static inline struct cfg802154_registered_device * wpan_phy_to_rdev(struct wpan_phy *wpan_phy) { BUG_ON(!wpan_phy); return container_of(wpan_phy, struct cfg802154_registered_device, wpan_phy); } extern struct list_head cfg802154_rdev_list; extern int cfg802154_rdev_list_generation; int cfg802154_switch_netns(struct cfg802154_registered_device *rdev, struct net *net); /* free object */ void cfg802154_dev_free(struct cfg802154_registered_device *rdev); struct cfg802154_registered_device * cfg802154_rdev_by_wpan_phy_idx(int wpan_phy_idx); struct wpan_phy *wpan_phy_idx_to_wpan_phy(int wpan_phy_idx); #endif /* __IEEE802154_CORE_H */
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 /* SPDX-License-Identifier: GPL-2.0 */ /* * Common header file for generic dynamic events. */ #ifndef _TRACE_DYNEVENT_H #define _TRACE_DYNEVENT_H #include <linux/kernel.h> #include <linux/list.h> #include <linux/mutex.h> #include <linux/seq_file.h> #include "trace.h" struct dyn_event; /** * struct dyn_event_operations - Methods for each type of dynamic events * * These methods must be set for each type, since there is no default method. * Before using this for dyn_event_init(), it must be registered by * dyn_event_register(). * * @create: Parse and create event method. This is invoked when user passes * a event definition to dynamic_events interface. This must not destruct * the arguments and return -ECANCELED if given arguments doesn't match its * command prefix. * @show: Showing method. This is invoked when user reads the event definitions * via dynamic_events interface. * @is_busy: Check whether given event is busy so that it can not be deleted. * Return true if it is busy, otherwides false. * @free: Delete the given event. Return 0 if success, otherwides error. * @match: Check whether given event and system name match this event. The argc * and argv is used for exact match. Return true if it matches, otherwides * false. * * Except for @create, these methods are called under holding event_mutex. */ struct dyn_event_operations { struct list_head list; int (*create)(int argc, const char *argv[]); int (*show)(struct seq_file *m, struct dyn_event *ev); bool (*is_busy)(struct dyn_event *ev); int (*free)(struct dyn_event *ev); bool (*match)(const char *system, const char *event, int argc, const char **argv, struct dyn_event *ev); }; /* Register new dyn_event type -- must be called at first */ int dyn_event_register(struct dyn_event_operations *ops); /** * struct dyn_event - Dynamic event list header * * The dyn_event structure encapsulates a list and a pointer to the operators * for making a global list of dynamic events. * User must includes this in each event structure, so that those events can * be added/removed via dynamic_events interface. */ struct dyn_event { struct list_head list; struct dyn_event_operations *ops; }; extern struct list_head dyn_event_list; static inline int dyn_event_init(struct dyn_event *ev, struct dyn_event_operations *ops) { if (!ev || !ops) return -EINVAL; INIT_LIST_HEAD(&ev->list); ev->ops = ops; return 0; } static inline int dyn_event_add(struct dyn_event *ev) { lockdep_assert_held(&event_mutex); if (!ev || !ev->ops) return -EINVAL; list_add_tail(&ev->list, &dyn_event_list); return 0; } static inline void dyn_event_remove(struct dyn_event *ev) { lockdep_assert_held(&event_mutex); list_del_init(&ev->list); } void *dyn_event_seq_start(struct seq_file *m, loff_t *pos); void *dyn_event_seq_next(struct seq_file *m, void *v, loff_t *pos); void dyn_event_seq_stop(struct seq_file *m, void *v); int dyn_events_release_all(struct dyn_event_operations *type); int dyn_event_release(int argc, char **argv, struct dyn_event_operations *type); /* * for_each_dyn_event - iterate over the dyn_event list * @pos: the struct dyn_event * to use as a loop cursor * * This is just a basement of for_each macro. Wrap this for * each actual event structure with ops filtering. */ #define for_each_dyn_event(pos) \ list_for_each_entry(pos, &dyn_event_list, list) /* * for_each_dyn_event - iterate over the dyn_event list safely * @pos: the struct dyn_event * to use as a loop cursor * @n: the struct dyn_event * to use as temporary storage */ #define for_each_dyn_event_safe(pos, n) \ list_for_each_entry_safe(pos, n, &dyn_event_list, list) extern void dynevent_cmd_init(struct dynevent_cmd *cmd, char *buf, int maxlen, enum dynevent_type type, dynevent_create_fn_t run_command); typedef int (*dynevent_check_arg_fn_t)(void *data); struct dynevent_arg { const char *str; char separator; /* e.g. ';', ',', or nothing */ }; extern void dynevent_arg_init(struct dynevent_arg *arg, char separator); extern int dynevent_arg_add(struct dynevent_cmd *cmd, struct dynevent_arg *arg, dynevent_check_arg_fn_t check_arg); struct dynevent_arg_pair { const char *lhs; const char *rhs; char operator; /* e.g. '=' or nothing */ char separator; /* e.g. ';', ',', or nothing */ }; extern void dynevent_arg_pair_init(struct dynevent_arg_pair *arg_pair, char operator, char separator); extern int dynevent_arg_pair_add(struct dynevent_cmd *cmd, struct dynevent_arg_pair *arg_pair, dynevent_check_arg_fn_t check_arg); extern int dynevent_str_add(struct dynevent_cmd *cmd, const char *str); #endif
1 1 1 1 1 1 1 1 1 1 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 1994, Karl Keyte: Added support for disk statistics * Elevator latency, (C) 2000 Andrea Arcangeli <andrea@suse.de> SuSE * Queue request tables / lock, selectable elevator, Jens Axboe <axboe@suse.de> * kernel-doc documentation started by NeilBrown <neilb@cse.unsw.edu.au> * - July2000 * bio rewrite, highmem i/o, etc, Jens Axboe <axboe@suse.de> - may 2001 */ /* * This handles all read/write requests to block devices */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/backing-dev.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/blk-mq.h> #include <linux/blk-pm.h> #include <linux/highmem.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/kernel_stat.h> #include <linux/string.h> #include <linux/init.h> #include <linux/completion.h> #include <linux/slab.h> #include <linux/swap.h> #include <linux/writeback.h> #include <linux/task_io_accounting_ops.h> #include <linux/fault-inject.h> #include <linux/list_sort.h> #include <linux/delay.h> #include <linux/ratelimit.h> #include <linux/pm_runtime.h> #include <linux/blk-cgroup.h> #include <linux/t10-pi.h> #include <linux/debugfs.h> #include <linux/bpf.h> #include <linux/psi.h> #include <linux/sched/sysctl.h> #include <linux/blk-crypto.h> #define CREATE_TRACE_POINTS #include <trace/events/block.h> #include "blk.h" #include "blk-mq.h" #include "blk-mq-sched.h" #include "blk-pm.h" #include "blk-rq-qos.h" struct dentry *blk_debugfs_root; EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap); EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap); EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_complete); EXPORT_TRACEPOINT_SYMBOL_GPL(block_split); EXPORT_TRACEPOINT_SYMBOL_GPL(block_unplug); DEFINE_IDA(blk_queue_ida); /* * For queue allocation */ struct kmem_cache *blk_requestq_cachep; /* * Controlling structure to kblockd */ static struct workqueue_struct *kblockd_workqueue; /** * blk_queue_flag_set - atomically set a queue flag * @flag: flag to be set * @q: request queue */ void blk_queue_flag_set(unsigned int flag, struct request_queue *q) { set_bit(flag, &q->queue_flags); } EXPORT_SYMBOL(blk_queue_flag_set); /** * blk_queue_flag_clear - atomically clear a queue flag * @flag: flag to be cleared * @q: request queue */ void blk_queue_flag_clear(unsigned int flag, struct request_queue *q) { clear_bit(flag, &q->queue_flags); } EXPORT_SYMBOL(blk_queue_flag_clear); /** * blk_queue_flag_test_and_set - atomically test and set a queue flag * @flag: flag to be set * @q: request queue * * Returns the previous value of @flag - 0 if the flag was not set and 1 if * the flag was already set. */ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q) { return test_and_set_bit(flag, &q->queue_flags); } EXPORT_SYMBOL_GPL(blk_queue_flag_test_and_set); void blk_rq_init(struct request_queue *q, struct request *rq) { memset(rq, 0, sizeof(*rq)); INIT_LIST_HEAD(&rq->queuelist); rq->q = q; rq->__sector = (sector_t) -1; INIT_HLIST_NODE(&rq->hash); RB_CLEAR_NODE(&rq->rb_node); rq->tag = BLK_MQ_NO_TAG; rq->internal_tag = BLK_MQ_NO_TAG; rq->start_time_ns = ktime_get_ns(); rq->part = NULL; blk_crypto_rq_set_defaults(rq); } EXPORT_SYMBOL(blk_rq_init); #define REQ_OP_NAME(name) [REQ_OP_##name] = #name static const char *const blk_op_name[] = { REQ_OP_NAME(READ), REQ_OP_NAME(WRITE), REQ_OP_NAME(FLUSH), REQ_OP_NAME(DISCARD), REQ_OP_NAME(SECURE_ERASE), REQ_OP_NAME(ZONE_RESET), REQ_OP_NAME(ZONE_RESET_ALL), REQ_OP_NAME(ZONE_OPEN), REQ_OP_NAME(ZONE_CLOSE), REQ_OP_NAME(ZONE_FINISH), REQ_OP_NAME(ZONE_APPEND), REQ_OP_NAME(WRITE_SAME), REQ_OP_NAME(WRITE_ZEROES), REQ_OP_NAME(SCSI_IN), REQ_OP_NAME(SCSI_OUT), REQ_OP_NAME(DRV_IN), REQ_OP_NAME(DRV_OUT), }; #undef REQ_OP_NAME /** * blk_op_str - Return string XXX in the REQ_OP_XXX. * @op: REQ_OP_XXX. * * Description: Centralize block layer function to convert REQ_OP_XXX into * string format. Useful in the debugging and tracing bio or request. For * invalid REQ_OP_XXX it returns string "UNKNOWN". */ inline const char *blk_op_str(unsigned int op) { const char *op_str = "UNKNOWN"; if (op < ARRAY_SIZE(blk_op_name) && blk_op_name[op]) op_str = blk_op_name[op]; return op_str; } EXPORT_SYMBOL_GPL(blk_op_str); static const struct { int errno; const char *name; } blk_errors[] = { [BLK_STS_OK] = { 0, "" }, [BLK_STS_NOTSUPP] = { -EOPNOTSUPP, "operation not supported" }, [BLK_STS_TIMEOUT] = { -ETIMEDOUT, "timeout" }, [BLK_STS_NOSPC] = { -ENOSPC, "critical space allocation" }, [BLK_STS_TRANSPORT] = { -ENOLINK, "recoverable transport" }, [BLK_STS_TARGET] = { -EREMOTEIO, "critical target" }, [BLK_STS_NEXUS] = { -EBADE, "critical nexus" }, [BLK_STS_MEDIUM] = { -ENODATA, "critical medium" }, [BLK_STS_PROTECTION] = { -EILSEQ, "protection" }, [BLK_STS_RESOURCE] = { -ENOMEM, "kernel resource" }, [BLK_STS_DEV_RESOURCE] = { -EBUSY, "device resource" }, [BLK_STS_AGAIN] = { -EAGAIN, "nonblocking retry" }, /* device mapper special case, should not leak out: */ [BLK_STS_DM_REQUEUE] = { -EREMCHG, "dm internal retry" }, /* zone device specific errors */ [BLK_STS_ZONE_OPEN_RESOURCE] = { -ETOOMANYREFS, "open zones exceeded" }, [BLK_STS_ZONE_ACTIVE_RESOURCE] = { -EOVERFLOW, "active zones exceeded" }, /* everything else not covered above: */ [BLK_STS_IOERR] = { -EIO, "I/O" }, }; blk_status_t errno_to_blk_status(int errno) { int i; for (i = 0; i < ARRAY_SIZE(blk_errors); i++) { if (blk_errors[i].errno == errno) return (__force blk_status_t)i; } return BLK_STS_IOERR; } EXPORT_SYMBOL_GPL(errno_to_blk_status); int blk_status_to_errno(blk_status_t status) { int idx = (__force int)status; if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors))) return -EIO; return blk_errors[idx].errno; } EXPORT_SYMBOL_GPL(blk_status_to_errno); static void print_req_error(struct request *req, blk_status_t status, const char *caller) { int idx = (__force int)status; if (WARN_ON_ONCE(idx >= ARRAY_SIZE(blk_errors))) return; printk_ratelimited(KERN_ERR "%s: %s error, dev %s, sector %llu op 0x%x:(%s) flags 0x%x " "phys_seg %u prio class %u\n", caller, blk_errors[idx].name, req->rq_disk ? req->rq_disk->disk_name : "?", blk_rq_pos(req), req_op(req), blk_op_str(req_op(req)), req->cmd_flags & ~REQ_OP_MASK, req->nr_phys_segments, IOPRIO_PRIO_CLASS(req->ioprio)); } static void req_bio_endio(struct request *rq, struct bio *bio, unsigned int nbytes, blk_status_t error) { if (error) bio->bi_status = error; if (unlikely(rq->rq_flags & RQF_QUIET)) bio_set_flag(bio, BIO_QUIET); bio_advance(bio, nbytes); if (req_op(rq) == REQ_OP_ZONE_APPEND && error == BLK_STS_OK) { /* * Partial zone append completions cannot be supported as the * BIO fragments may end up not being written sequentially. */ if (bio->bi_iter.bi_size) bio->bi_status = BLK_STS_IOERR; else bio->bi_iter.bi_sector = rq->__sector; } /* don't actually finish bio if it's part of flush sequence */ if (bio->bi_iter.bi_size == 0 && !(rq->rq_flags & RQF_FLUSH_SEQ)) bio_endio(bio); } void blk_dump_rq_flags(struct request *rq, char *msg) { printk(KERN_INFO "%s: dev %s: flags=%llx\n", msg, rq->rq_disk ? rq->rq_disk->disk_name : "?", (unsigned long long) rq->cmd_flags); printk(KERN_INFO " sector %llu, nr/cnr %u/%u\n", (unsigned long long)blk_rq_pos(rq), blk_rq_sectors(rq), blk_rq_cur_sectors(rq)); printk(KERN_INFO " bio %p, biotail %p, len %u\n", rq->bio, rq->biotail, blk_rq_bytes(rq)); } EXPORT_SYMBOL(blk_dump_rq_flags); /** * blk_sync_queue - cancel any pending callbacks on a queue * @q: the queue * * Description: * The block layer may perform asynchronous callback activity * on a queue, such as calling the unplug function after a timeout. * A block device may call blk_sync_queue to ensure that any * such activity is cancelled, thus allowing it to release resources * that the callbacks might use. The caller must already have made sure * that its ->submit_bio will not re-add plugging prior to calling * this function. * * This function does not cancel any asynchronous activity arising * out of elevator or throttling code. That would require elevator_exit() * and blkcg_exit_queue() to be called with queue lock initialized. * */ void blk_sync_queue(struct request_queue *q) { del_timer_sync(&q->timeout); cancel_work_sync(&q->timeout_work); } EXPORT_SYMBOL(blk_sync_queue); /** * blk_set_pm_only - increment pm_only counter * @q: request queue pointer */ void blk_set_pm_only(struct request_queue *q) { atomic_inc(&q->pm_only); } EXPORT_SYMBOL_GPL(blk_set_pm_only); void blk_clear_pm_only(struct request_queue *q) { int pm_only; pm_only = atomic_dec_return(&q->pm_only); WARN_ON_ONCE(pm_only < 0); if (pm_only == 0) wake_up_all(&q->mq_freeze_wq); } EXPORT_SYMBOL_GPL(blk_clear_pm_only); /** * blk_put_queue - decrement the request_queue refcount * @q: the request_queue structure to decrement the refcount for * * Decrements the refcount of the request_queue kobject. When this reaches 0 * we'll have blk_release_queue() called. * * Context: Any context, but the last reference must not be dropped from * atomic context. */ void blk_put_queue(struct request_queue *q) { kobject_put(&q->kobj); } EXPORT_SYMBOL(blk_put_queue); void blk_set_queue_dying(struct request_queue *q) { blk_queue_flag_set(QUEUE_FLAG_DYING, q); /* * When queue DYING flag is set, we need to block new req * entering queue, so we call blk_freeze_queue_start() to * prevent I/O from crossing blk_queue_enter(). */ blk_freeze_queue_start(q); if (queue_is_mq(q)) blk_mq_wake_waiters(q); /* Make blk_queue_enter() reexamine the DYING flag. */ wake_up_all(&q->mq_freeze_wq); } EXPORT_SYMBOL_GPL(blk_set_queue_dying); /** * blk_cleanup_queue - shutdown a request queue * @q: request queue to shutdown * * Mark @q DYING, drain all pending requests, mark @q DEAD, destroy and * put it. All future requests will be failed immediately with -ENODEV. * * Context: can sleep */ void blk_cleanup_queue(struct request_queue *q) { /* cannot be called from atomic context */ might_sleep(); WARN_ON_ONCE(blk_queue_registered(q)); /* mark @q DYING, no new request or merges will be allowed afterwards */ blk_set_queue_dying(q); blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q); blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q); /* * Drain all requests queued before DYING marking. Set DEAD flag to * prevent that blk_mq_run_hw_queues() accesses the hardware queues * after draining finished. */ blk_freeze_queue(q); rq_qos_exit(q); blk_queue_flag_set(QUEUE_FLAG_DEAD, q); /* for synchronous bio-based driver finish in-flight integrity i/o */ blk_flush_integrity(); /* @q won't process any more request, flush async actions */ del_timer_sync(&q->backing_dev_info->laptop_mode_wb_timer); blk_sync_queue(q); if (queue_is_mq(q)) blk_mq_exit_queue(q); /* * In theory, request pool of sched_tags belongs to request queue. * However, the current implementation requires tag_set for freeing * requests, so free the pool now. * * Queue has become frozen, there can't be any in-queue requests, so * it is safe to free requests now. */ mutex_lock(&q->sysfs_lock); if (q->elevator) blk_mq_sched_free_requests(q); mutex_unlock(&q->sysfs_lock); percpu_ref_exit(&q->q_usage_counter); /* @q is and will stay empty, shutdown and put */ blk_put_queue(q); } EXPORT_SYMBOL(blk_cleanup_queue); /** * blk_queue_enter() - try to increase q->q_usage_counter * @q: request queue pointer * @flags: BLK_MQ_REQ_NOWAIT and/or BLK_MQ_REQ_PM */ int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags) { const bool pm = flags & BLK_MQ_REQ_PM; while (true) { bool success = false; rcu_read_lock(); if (percpu_ref_tryget_live(&q->q_usage_counter)) { /* * The code that increments the pm_only counter is * responsible for ensuring that that counter is * globally visible before the queue is unfrozen. */ if ((pm && queue_rpm_status(q) != RPM_SUSPENDED) || !blk_queue_pm_only(q)) { success = true; } else { percpu_ref_put(&q->q_usage_counter); } } rcu_read_unlock(); if (success) return 0; if (flags & BLK_MQ_REQ_NOWAIT) return -EBUSY; /* * read pair of barrier in blk_freeze_queue_start(), * we need to order reading __PERCPU_REF_DEAD flag of * .q_usage_counter and reading .mq_freeze_depth or * queue dying flag, otherwise the following wait may * never return if the two reads are reordered. */ smp_rmb(); wait_event(q->mq_freeze_wq, (!q->mq_freeze_depth && blk_pm_resume_queue(pm, q)) || blk_queue_dying(q)); if (blk_queue_dying(q)) return -ENODEV; } } static inline int bio_queue_enter(struct bio *bio) { struct request_queue *q = bio->bi_disk->queue; bool nowait = bio->bi_opf & REQ_NOWAIT; int ret; ret = blk_queue_enter(q, nowait ? BLK_MQ_REQ_NOWAIT : 0); if (unlikely(ret)) { if (nowait && !blk_queue_dying(q)) bio_wouldblock_error(bio); else bio_io_error(bio); } return ret; } void blk_queue_exit(struct request_queue *q) { percpu_ref_put(&q->q_usage_counter); } static void blk_queue_usage_counter_release(struct percpu_ref *ref) { struct request_queue *q = container_of(ref, struct request_queue, q_usage_counter); wake_up_all(&q->mq_freeze_wq); } static void blk_rq_timed_out_timer(struct timer_list *t) { struct request_queue *q = from_timer(q, t, timeout); kblockd_schedule_work(&q->timeout_work); } static void blk_timeout_work(struct work_struct *work) { } struct request_queue *blk_alloc_queue(int node_id) { struct request_queue *q; int ret; q = kmem_cache_alloc_node(blk_requestq_cachep, GFP_KERNEL | __GFP_ZERO, node_id); if (!q) return NULL; q->last_merge = NULL; q->id = ida_simple_get(&blk_queue_ida, 0, 0, GFP_KERNEL); if (q->id < 0) goto fail_q; ret = bioset_init(&q->bio_split, BIO_POOL_SIZE, 0, BIOSET_NEED_BVECS); if (ret) goto fail_id; q->backing_dev_info = bdi_alloc(node_id); if (!q->backing_dev_info) goto fail_split; q->stats = blk_alloc_queue_stats(); if (!q->stats) goto fail_stats; q->node = node_id; atomic_set(&q->nr_active_requests_shared_sbitmap, 0); timer_setup(&q->backing_dev_info->laptop_mode_wb_timer, laptop_mode_timer_fn, 0); timer_setup(&q->timeout, blk_rq_timed_out_timer, 0); INIT_WORK(&q->timeout_work, blk_timeout_work); INIT_LIST_HEAD(&q->icq_list); #ifdef CONFIG_BLK_CGROUP INIT_LIST_HEAD(&q->blkg_list); #endif kobject_init(&q->kobj, &blk_queue_ktype); mutex_init(&q->debugfs_mutex); mutex_init(&q->sysfs_lock); mutex_init(&q->sysfs_dir_lock); spin_lock_init(&q->queue_lock); init_waitqueue_head(&q->mq_freeze_wq); mutex_init(&q->mq_freeze_lock); /* * Init percpu_ref in atomic mode so that it's faster to shutdown. * See blk_register_queue() for details. */ if (percpu_ref_init(&q->q_usage_counter, blk_queue_usage_counter_release, PERCPU_REF_INIT_ATOMIC, GFP_KERNEL)) goto fail_bdi; if (blkcg_init_queue(q)) goto fail_ref; blk_queue_dma_alignment(q, 511); blk_set_default_limits(&q->limits); q->nr_requests = BLKDEV_MAX_RQ; return q; fail_ref: percpu_ref_exit(&q->q_usage_counter); fail_bdi: blk_free_queue_stats(q->stats); fail_stats: bdi_put(q->backing_dev_info); fail_split: bioset_exit(&q->bio_split); fail_id: ida_simple_remove(&blk_queue_ida, q->id); fail_q: kmem_cache_free(blk_requestq_cachep, q); return NULL; } EXPORT_SYMBOL(blk_alloc_queue); /** * blk_get_queue - increment the request_queue refcount * @q: the request_queue structure to increment the refcount for * * Increment the refcount of the request_queue kobject. * * Context: Any context. */ bool blk_get_queue(struct request_queue *q) { if (likely(!blk_queue_dying(q))) { __blk_get_queue(q); return true; } return false; } EXPORT_SYMBOL(blk_get_queue); /** * blk_get_request - allocate a request * @q: request queue to allocate a request for * @op: operation (REQ_OP_*) and REQ_* flags, e.g. REQ_SYNC. * @flags: BLK_MQ_REQ_* flags, e.g. BLK_MQ_REQ_NOWAIT. */ struct request *blk_get_request(struct request_queue *q, unsigned int op, blk_mq_req_flags_t flags) { struct request *req; WARN_ON_ONCE(op & REQ_NOWAIT); WARN_ON_ONCE(flags & ~(BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_PM)); req = blk_mq_alloc_request(q, op, flags); if (!IS_ERR(req) && q->mq_ops->initialize_rq_fn) q->mq_ops->initialize_rq_fn(req); return req; } EXPORT_SYMBOL(blk_get_request); void blk_put_request(struct request *req) { blk_mq_free_request(req); } EXPORT_SYMBOL(blk_put_request); static void handle_bad_sector(struct bio *bio, sector_t maxsector) { char b[BDEVNAME_SIZE]; pr_info_ratelimited("attempt to access beyond end of device\n" "%s: rw=%d, want=%llu, limit=%llu\n", bio_devname(bio, b), bio->bi_opf, bio_end_sector(bio), maxsector); } #ifdef CONFIG_FAIL_MAKE_REQUEST static DECLARE_FAULT_ATTR(fail_make_request); static int __init setup_fail_make_request(char *str) { return setup_fault_attr(&fail_make_request, str); } __setup("fail_make_request=", setup_fail_make_request); static bool should_fail_request(struct hd_struct *part, unsigned int bytes) { return part->make_it_fail && should_fail(&fail_make_request, bytes); } static int __init fail_make_request_debugfs(void) { struct dentry *dir = fault_create_debugfs_attr("fail_make_request", NULL, &fail_make_request); return PTR_ERR_OR_ZERO(dir); } late_initcall(fail_make_request_debugfs); #else /* CONFIG_FAIL_MAKE_REQUEST */ static inline bool should_fail_request(struct hd_struct *part, unsigned int bytes) { return false; } #endif /* CONFIG_FAIL_MAKE_REQUEST */ static inline bool bio_check_ro(struct bio *bio, struct hd_struct *part) { const int op = bio_op(bio); if (part->policy && op_is_write(op)) { char b[BDEVNAME_SIZE]; if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) return false; WARN_ONCE(1, "Trying to write to read-only block-device %s (partno %d)\n", bio_devname(bio, b), part->partno); /* Older lvm-tools actually trigger this */ return false; } return false; } static noinline int should_fail_bio(struct bio *bio) { if (should_fail_request(&bio->bi_disk->part0, bio->bi_iter.bi_size)) return -EIO; return 0; } ALLOW_ERROR_INJECTION(should_fail_bio, ERRNO); /* * Check whether this bio extends beyond the end of the device or partition. * This may well happen - the kernel calls bread() without checking the size of * the device, e.g., when mounting a file system. */ static inline int bio_check_eod(struct bio *bio, sector_t maxsector) { unsigned int nr_sectors = bio_sectors(bio); if (nr_sectors && maxsector && (nr_sectors > maxsector || bio->bi_iter.bi_sector > maxsector - nr_sectors)) { handle_bad_sector(bio, maxsector); return -EIO; } return 0; } /* * Remap block n of partition p to block n+start(p) of the disk. */ static inline int blk_partition_remap(struct bio *bio) { struct hd_struct *p; int ret = -EIO; rcu_read_lock(); p = __disk_get_part(bio->bi_disk, bio->bi_partno); if (unlikely(!p)) goto out; if (unlikely(should_fail_request(p, bio->bi_iter.bi_size))) goto out; if (unlikely(bio_check_ro(bio, p))) goto out; if (bio_sectors(bio)) { if (bio_check_eod(bio, part_nr_sects_read(p))) goto out; bio->bi_iter.bi_sector += p->start_sect; trace_block_bio_remap(bio->bi_disk->queue, bio, part_devt(p), bio->bi_iter.bi_sector - p->start_sect); } bio->bi_partno = 0; ret = 0; out: rcu_read_unlock(); return ret; } /* * Check write append to a zoned block device. */ static inline blk_status_t blk_check_zone_append(struct request_queue *q, struct bio *bio) { sector_t pos = bio->bi_iter.bi_sector; int nr_sectors = bio_sectors(bio); /* Only applicable to zoned block devices */ if (!blk_queue_is_zoned(q)) return BLK_STS_NOTSUPP; /* The bio sector must point to the start of a sequential zone */ if (pos & (blk_queue_zone_sectors(q) - 1) || !blk_queue_zone_is_seq(q, pos)) return BLK_STS_IOERR; /* * Not allowed to cross zone boundaries. Otherwise, the BIO will be * split and could result in non-contiguous sectors being written in * different zones. */ if (nr_sectors > q->limits.chunk_sectors) return BLK_STS_IOERR; /* Make sure the BIO is small enough and will not get split */ if (nr_sectors > q->limits.max_zone_append_sectors) return BLK_STS_IOERR; bio->bi_opf |= REQ_NOMERGE; return BLK_STS_OK; } static noinline_for_stack bool submit_bio_checks(struct bio *bio) { struct request_queue *q = bio->bi_disk->queue; blk_status_t status = BLK_STS_IOERR; struct blk_plug *plug; might_sleep(); plug = blk_mq_plug(q, bio); if (plug && plug->nowait) bio->bi_opf |= REQ_NOWAIT; /* * For a REQ_NOWAIT based request, return -EOPNOTSUPP * if queue does not support NOWAIT. */ if ((bio->bi_opf & REQ_NOWAIT) && !blk_queue_nowait(q)) goto not_supported; if (should_fail_bio(bio)) goto end_io; if (bio->bi_partno) { if (unlikely(blk_partition_remap(bio))) goto end_io; } else { if (unlikely(bio_check_ro(bio, &bio->bi_disk->part0))) goto end_io; if (unlikely(bio_check_eod(bio, get_capacity(bio->bi_disk)))) goto end_io; } /* * Filter flush bio's early so that bio based drivers without flush * support don't have to worry about them. */ if (op_is_flush(bio->bi_opf) && !test_bit(QUEUE_FLAG_WC, &q->queue_flags)) { bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA); if (!bio_sectors(bio)) { status = BLK_STS_OK; goto end_io; } } if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags)) bio->bi_opf &= ~REQ_HIPRI; switch (bio_op(bio)) { case REQ_OP_DISCARD: if (!blk_queue_discard(q)) goto not_supported; break; case REQ_OP_SECURE_ERASE: if (!blk_queue_secure_erase(q)) goto not_supported; break; case REQ_OP_WRITE_SAME: if (!q->limits.max_write_same_sectors) goto not_supported; break; case REQ_OP_ZONE_APPEND: status = blk_check_zone_append(q, bio); if (status != BLK_STS_OK) goto end_io; break; case REQ_OP_ZONE_RESET: case REQ_OP_ZONE_OPEN: case REQ_OP_ZONE_CLOSE: case REQ_OP_ZONE_FINISH: if (!blk_queue_is_zoned(q)) goto not_supported; break; case REQ_OP_ZONE_RESET_ALL: if (!blk_queue_is_zoned(q) || !blk_queue_zone_resetall(q)) goto not_supported; break; case REQ_OP_WRITE_ZEROES: if (!q->limits.max_write_zeroes_sectors) goto not_supported; break; default: break; } /* * Various block parts want %current->io_context, so allocate it up * front rather than dealing with lots of pain to allocate it only * where needed. This may fail and the block layer knows how to live * with it. */ if (unlikely(!current->io_context)) create_task_io_context(current, GFP_ATOMIC, q->node); if (blk_throtl_bio(bio)) return false; blk_cgroup_bio_start(bio); blkcg_bio_issue_init(bio); if (!bio_flagged(bio, BIO_TRACE_COMPLETION)) { trace_block_bio_queue(q, bio); /* Now that enqueuing has been traced, we need to trace * completion as well. */ bio_set_flag(bio, BIO_TRACE_COMPLETION); } return true; not_supported: status = BLK_STS_NOTSUPP; end_io: bio->bi_status = status; bio_endio(bio); return false; } static blk_qc_t __submit_bio(struct bio *bio) { struct gendisk *disk = bio->bi_disk; blk_qc_t ret = BLK_QC_T_NONE; if (blk_crypto_bio_prep(&bio)) { if (!disk->fops->submit_bio) return blk_mq_submit_bio(bio); ret = disk->fops->submit_bio(bio); } blk_queue_exit(disk->queue); return ret; } /* * The loop in this function may be a bit non-obvious, and so deserves some * explanation: * * - Before entering the loop, bio->bi_next is NULL (as all callers ensure * that), so we have a list with a single bio. * - We pretend that we have just taken it off a longer list, so we assign * bio_list to a pointer to the bio_list_on_stack, thus initialising the * bio_list of new bios to be added. ->submit_bio() may indeed add some more * bios through a recursive call to submit_bio_noacct. If it did, we find a * non-NULL value in bio_list and re-enter the loop from the top. * - In this case we really did just take the bio of the top of the list (no * pretending) and so remove it from bio_list, and call into ->submit_bio() * again. * * bio_list_on_stack[0] contains bios submitted by the current ->submit_bio. * bio_list_on_stack[1] contains bios that were submitted before the current * ->submit_bio_bio, but that haven't been processed yet. */ static blk_qc_t __submit_bio_noacct(struct bio *bio) { struct bio_list bio_list_on_stack[2]; blk_qc_t ret = BLK_QC_T_NONE; BUG_ON(bio->bi_next); bio_list_init(&bio_list_on_stack[0]); current->bio_list = bio_list_on_stack; do { struct request_queue *q = bio->bi_disk->queue; struct bio_list lower, same; if (unlikely(bio_queue_enter(bio) != 0)) continue; /* * Create a fresh bio_list for all subordinate requests. */ bio_list_on_stack[1] = bio_list_on_stack[0]; bio_list_init(&bio_list_on_stack[0]); ret = __submit_bio(bio); /* * Sort new bios into those for a lower level and those for the * same level. */ bio_list_init(&lower); bio_list_init(&same); while ((bio = bio_list_pop(&bio_list_on_stack[0])) != NULL) if (q == bio->bi_disk->queue) bio_list_add(&same, bio); else bio_list_add(&lower, bio); /* * Now assemble so we handle the lowest level first. */ bio_list_merge(&bio_list_on_stack[0], &lower); bio_list_merge(&bio_list_on_stack[0], &same); bio_list_merge(&bio_list_on_stack[0], &bio_list_on_stack[1]); } while ((bio = bio_list_pop(&bio_list_on_stack[0]))); current->bio_list = NULL; return ret; } static blk_qc_t __submit_bio_noacct_mq(struct bio *bio) { struct bio_list bio_list[2] = { }; blk_qc_t ret = BLK_QC_T_NONE; current->bio_list = bio_list; do { struct gendisk *disk = bio->bi_disk; if (unlikely(bio_queue_enter(bio) != 0)) continue; if (!blk_crypto_bio_prep(&bio)) { blk_queue_exit(disk->queue); ret = BLK_QC_T_NONE; continue; } ret = blk_mq_submit_bio(bio); } while ((bio = bio_list_pop(&bio_list[0]))); current->bio_list = NULL; return ret; } /** * submit_bio_noacct - re-submit a bio to the block device layer for I/O * @bio: The bio describing the location in memory and on the device. * * This is a version of submit_bio() that shall only be used for I/O that is * resubmitted to lower level drivers by stacking block drivers. All file * systems and other upper level users of the block layer should use * submit_bio() instead. */ blk_qc_t submit_bio_noacct(struct bio *bio) { if (!submit_bio_checks(bio)) return BLK_QC_T_NONE; /* * We only want one ->submit_bio to be active at a time, else stack * usage with stacked devices could be a problem. Use current->bio_list * to collect a list of requests submited by a ->submit_bio method while * it is active, and then process them after it returned. */ if (current->bio_list) { bio_list_add(&current->bio_list[0], bio); return BLK_QC_T_NONE; } if (!bio->bi_disk->fops->submit_bio) return __submit_bio_noacct_mq(bio); return __submit_bio_noacct(bio); } EXPORT_SYMBOL(submit_bio_noacct); /** * submit_bio - submit a bio to the block device layer for I/O * @bio: The &struct bio which describes the I/O * * submit_bio() is used to submit I/O requests to block devices. It is passed a * fully set up &struct bio that describes the I/O that needs to be done. The * bio will be send to the device described by the bi_disk and bi_partno fields. * * The success/failure status of the request, along with notification of * completion, is delivered asynchronously through the ->bi_end_io() callback * in @bio. The bio must NOT be touched by thecaller until ->bi_end_io() has * been called. */ blk_qc_t submit_bio(struct bio *bio) { if (blkcg_punt_bio_submit(bio)) return BLK_QC_T_NONE; /* * If it's a regular read/write or a barrier with data attached, * go through the normal accounting stuff before submission. */ if (bio_has_data(bio)) { unsigned int count; if (unlikely(bio_op(bio) == REQ_OP_WRITE_SAME)) count = queue_logical_block_size(bio->bi_disk->queue) >> 9; else count = bio_sectors(bio); if (op_is_write(bio_op(bio))) { count_vm_events(PGPGOUT, count); } else { task_io_account_read(bio->bi_iter.bi_size); count_vm_events(PGPGIN, count); } if (unlikely(block_dump)) { char b[BDEVNAME_SIZE]; printk(KERN_DEBUG "%s(%d): %s block %Lu on %s (%u sectors)\n", current->comm, task_pid_nr(current), op_is_write(bio_op(bio)) ? "WRITE" : "READ", (unsigned long long)bio->bi_iter.bi_sector, bio_devname(bio, b), count); } } /* * If we're reading data that is part of the userspace workingset, count * submission time as memory stall. When the device is congested, or * the submitting cgroup IO-throttled, submission can be a significant * part of overall IO time. */ if (unlikely(bio_op(bio) == REQ_OP_READ && bio_flagged(bio, BIO_WORKINGSET))) { unsigned long pflags; blk_qc_t ret; psi_memstall_enter(&pflags); ret = submit_bio_noacct(bio); psi_memstall_leave(&pflags); return ret; } return submit_bio_noacct(bio); } EXPORT_SYMBOL(submit_bio); /** * blk_cloned_rq_check_limits - Helper function to check a cloned request * for the new queue limits * @q: the queue * @rq: the request being checked * * Description: * @rq may have been made based on weaker limitations of upper-level queues * in request stacking drivers, and it may violate the limitation of @q. * Since the block layer and the underlying device driver trust @rq * after it is inserted to @q, it should be checked against @q before * the insertion using this generic function. * * Request stacking drivers like request-based dm may change the queue * limits when retrying requests on other queues. Those requests need * to be checked against the new queue limits again during dispatch. */ static blk_status_t blk_cloned_rq_check_limits(struct request_queue *q, struct request *rq) { unsigned int max_sectors = blk_queue_get_max_sectors(q, req_op(rq)); if (blk_rq_sectors(rq) > max_sectors) { /* * SCSI device does not have a good way to return if * Write Same/Zero is actually supported. If a device rejects * a non-read/write command (discard, write same,etc.) the * low-level device driver will set the relevant queue limit to * 0 to prevent blk-lib from issuing more of the offending * operations. Commands queued prior to the queue limit being * reset need to be completed with BLK_STS_NOTSUPP to avoid I/O * errors being propagated to upper layers. */ if (max_sectors == 0) return BLK_STS_NOTSUPP; printk(KERN_ERR "%s: over max size limit. (%u > %u)\n", __func__, blk_rq_sectors(rq), max_sectors); return BLK_STS_IOERR; } /* * queue's settings related to segment counting like q->bounce_pfn * may differ from that of other stacking queues. * Recalculate it to check the request correctly on this queue's * limitation. */ rq->nr_phys_segments = blk_recalc_rq_segments(rq); if (rq->nr_phys_segments > queue_max_segments(q)) { printk(KERN_ERR "%s: over max segments limit. (%hu > %hu)\n", __func__, rq->nr_phys_segments, queue_max_segments(q)); return BLK_STS_IOERR; } return BLK_STS_OK; } /** * blk_insert_cloned_request - Helper for stacking drivers to submit a request * @q: the queue to submit the request * @rq: the request being queued */ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq) { blk_status_t ret; ret = blk_cloned_rq_check_limits(q, rq); if (ret != BLK_STS_OK) return ret; if (rq->rq_disk && should_fail_request(&rq->rq_disk->part0, blk_rq_bytes(rq))) return BLK_STS_IOERR; if (blk_crypto_insert_cloned_request(rq)) return BLK_STS_IOERR; if (blk_queue_io_stat(q)) blk_account_io_start(rq); /* * Since we have a scheduler attached on the top device, * bypass a potential scheduler on the bottom device for * insert. */ return blk_mq_request_issue_directly(rq, true); } EXPORT_SYMBOL_GPL(blk_insert_cloned_request); /** * blk_rq_err_bytes - determine number of bytes till the next failure boundary * @rq: request to examine * * Description: * A request could be merge of IOs which require different failure * handling. This function determines the number of bytes which * can be failed from the beginning of the request without * crossing into area which need to be retried further. * * Return: * The number of bytes to fail. */ unsigned int blk_rq_err_bytes(const struct request *rq) { unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK; unsigned int bytes = 0; struct bio *bio; if (!(rq->rq_flags & RQF_MIXED_MERGE)) return blk_rq_bytes(rq); /* * Currently the only 'mixing' which can happen is between * different fastfail types. We can safely fail portions * which have all the failfast bits that the first one has - * the ones which are at least as eager to fail as the first * one. */ for (bio = rq->bio; bio; bio = bio->bi_next) { if ((bio->bi_opf & ff) != ff) break; bytes += bio->bi_iter.bi_size; } /* this could lead to infinite loop */ BUG_ON(blk_rq_bytes(rq) && !bytes); return bytes; } EXPORT_SYMBOL_GPL(blk_rq_err_bytes); static void update_io_ticks(struct hd_struct *part, unsigned long now, bool end) { unsigned long stamp; again: stamp = READ_ONCE(part->stamp); if (unlikely(stamp != now)) { if (likely(cmpxchg(&part->stamp, stamp, now) == stamp)) __part_stat_add(part, io_ticks, end ? now - stamp : 1); } if (part->partno) { part = &part_to_disk(part)->part0; goto again; } } static void blk_account_io_completion(struct request *req, unsigned int bytes) { if (req->part && blk_do_io_stat(req)) { const int sgrp = op_stat_group(req_op(req)); struct hd_struct *part; part_stat_lock(); part = req->part; part_stat_add(part, sectors[sgrp], bytes >> 9); part_stat_unlock(); } } void blk_account_io_done(struct request *req, u64 now) { /* * Account IO completion. flush_rq isn't accounted as a * normal IO on queueing nor completion. Accounting the * containing request is enough. */ if (req->part && blk_do_io_stat(req) && !(req->rq_flags & RQF_FLUSH_SEQ)) { const int sgrp = op_stat_group(req_op(req)); struct hd_struct *part; part_stat_lock(); part = req->part; update_io_ticks(part, jiffies, true); part_stat_inc(part, ios[sgrp]); part_stat_add(part, nsecs[sgrp], now - req->start_time_ns); part_stat_unlock(); hd_struct_put(part); } } void blk_account_io_start(struct request *rq) { if (!blk_do_io_stat(rq)) return; rq->part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq)); part_stat_lock(); update_io_ticks(rq->part, jiffies, false); part_stat_unlock(); } static unsigned long __part_start_io_acct(struct hd_struct *part, unsigned int sectors, unsigned int op) { const int sgrp = op_stat_group(op); unsigned long now = READ_ONCE(jiffies); part_stat_lock(); update_io_ticks(part, now, false); part_stat_inc(part, ios[sgrp]); part_stat_add(part, sectors[sgrp], sectors); part_stat_local_inc(part, in_flight[op_is_write(op)]); part_stat_unlock(); return now; } unsigned long part_start_io_acct(struct gendisk *disk, struct hd_struct **part, struct bio *bio) { *part = disk_map_sector_rcu(disk, bio->bi_iter.bi_sector); return __part_start_io_acct(*part, bio_sectors(bio), bio_op(bio)); } EXPORT_SYMBOL_GPL(part_start_io_acct); unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, unsigned int op) { return __part_start_io_acct(&disk->part0, sectors, op); } EXPORT_SYMBOL(disk_start_io_acct); static void __part_end_io_acct(struct hd_struct *part, unsigned int op, unsigned long start_time) { const int sgrp = op_stat_group(op); unsigned long now = READ_ONCE(jiffies); unsigned long duration = now - start_time; part_stat_lock(); update_io_ticks(part, now, true); part_stat_add(part, nsecs[sgrp], jiffies_to_nsecs(duration)); part_stat_local_dec(part, in_flight[op_is_write(op)]); part_stat_unlock(); } void part_end_io_acct(struct hd_struct *part, struct bio *bio, unsigned long start_time) { __part_end_io_acct(part, bio_op(bio), start_time); hd_struct_put(part); } EXPORT_SYMBOL_GPL(part_end_io_acct); void disk_end_io_acct(struct gendisk *disk, unsigned int op, unsigned long start_time) { __part_end_io_acct(&disk->part0, op, start_time); } EXPORT_SYMBOL(disk_end_io_acct); /* * Steal bios from a request and add them to a bio list. * The request must not have been partially completed before. */ void blk_steal_bios(struct bio_list *list, struct request *rq) { if (rq->bio) { if (list->tail) list->tail->bi_next = rq->bio; else list->head = rq->bio; list->tail = rq->biotail; rq->bio = NULL; rq->biotail = NULL; } rq->__data_len = 0; } EXPORT_SYMBOL_GPL(blk_steal_bios); /** * blk_update_request - Special helper function for request stacking drivers * @req: the request being processed * @error: block status code * @nr_bytes: number of bytes to complete @req * * Description: * Ends I/O on a number of bytes attached to @req, but doesn't complete * the request structure even if @req doesn't have leftover. * If @req has leftover, sets it up for the next range of segments. * * This special helper function is only for request stacking drivers * (e.g. request-based dm) so that they can handle partial completion. * Actual device drivers should use blk_mq_end_request instead. * * Passing the result of blk_rq_bytes() as @nr_bytes guarantees * %false return from this function. * * Note: * The RQF_SPECIAL_PAYLOAD flag is ignored on purpose in both * blk_rq_bytes() and in blk_update_request(). * * Return: * %false - this request doesn't have any more data * %true - this request has more data **/ bool blk_update_request(struct request *req, blk_status_t error, unsigned int nr_bytes) { int total_bytes; trace_block_rq_complete(req, blk_status_to_errno(error), nr_bytes); if (!req->bio) return false; #ifdef CONFIG_BLK_DEV_INTEGRITY if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ && error == BLK_STS_OK) req->q->integrity.profile->complete_fn(req, nr_bytes); #endif if (unlikely(error && !blk_rq_is_passthrough(req) && !(req->rq_flags & RQF_QUIET))) print_req_error(req, error, __func__); blk_account_io_completion(req, nr_bytes); total_bytes = 0; while (req->bio) { struct bio *bio = req->bio; unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes); if (bio_bytes == bio->bi_iter.bi_size) req->bio = bio->bi_next; /* Completion has already been traced */ bio_clear_flag(bio, BIO_TRACE_COMPLETION); req_bio_endio(req, bio, bio_bytes, error); total_bytes += bio_bytes; nr_bytes -= bio_bytes; if (!nr_bytes) break; } /* * completely done */ if (!req->bio) { /* * Reset counters so that the request stacking driver * can find how many bytes remain in the request * later. */ req->__data_len = 0; return false; } req->__data_len -= total_bytes; /* update sector only for requests with clear definition of sector */ if (!blk_rq_is_passthrough(req)) req->__sector += total_bytes >> 9; /* mixed attributes always follow the first bio */ if (req->rq_flags & RQF_MIXED_MERGE) { req->cmd_flags &= ~REQ_FAILFAST_MASK; req->cmd_flags |= req->bio->bi_opf & REQ_FAILFAST_MASK; } if (!(req->rq_flags & RQF_SPECIAL_PAYLOAD)) { /* * If total number of sectors is less than the first segment * size, something has gone terribly wrong. */ if (blk_rq_bytes(req) < blk_rq_cur_bytes(req)) { blk_dump_rq_flags(req, "request botched"); req->__data_len = blk_rq_cur_bytes(req); } /* recalculate the number of segments */ req->nr_phys_segments = blk_recalc_rq_segments(req); } return true; } EXPORT_SYMBOL_GPL(blk_update_request); #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE /** * rq_flush_dcache_pages - Helper function to flush all pages in a request * @rq: the request to be flushed * * Description: * Flush all pages in @rq. */ void rq_flush_dcache_pages(struct request *rq) { struct req_iterator iter; struct bio_vec bvec; rq_for_each_segment(bvec, rq, iter) flush_dcache_page(bvec.bv_page); } EXPORT_SYMBOL_GPL(rq_flush_dcache_pages); #endif /** * blk_lld_busy - Check if underlying low-level drivers of a device are busy * @q : the queue of the device being checked * * Description: * Check if underlying low-level drivers of a device are busy. * If the drivers want to export their busy state, they must set own * exporting function using blk_queue_lld_busy() first. * * Basically, this function is used only by request stacking drivers * to stop dispatching requests to underlying devices when underlying * devices are busy. This behavior helps more I/O merging on the queue * of the request stacking driver and prevents I/O throughput regression * on burst I/O load. * * Return: * 0 - Not busy (The request stacking driver should dispatch request) * 1 - Busy (The request stacking driver should stop dispatching request) */ int blk_lld_busy(struct request_queue *q) { if (queue_is_mq(q) && q->mq_ops->busy) return q->mq_ops->busy(q); return 0; } EXPORT_SYMBOL_GPL(blk_lld_busy); /** * blk_rq_unprep_clone - Helper function to free all bios in a cloned request * @rq: the clone request to be cleaned up * * Description: * Free all bios in @rq for a cloned request. */ void blk_rq_unprep_clone(struct request *rq) { struct bio *bio; while ((bio = rq->bio) != NULL) { rq->bio = bio->bi_next; bio_put(bio); } } EXPORT_SYMBOL_GPL(blk_rq_unprep_clone); /** * blk_rq_prep_clone - Helper function to setup clone request * @rq: the request to be setup * @rq_src: original request to be cloned * @bs: bio_set that bios for clone are allocated from * @gfp_mask: memory allocation mask for bio * @bio_ctr: setup function to be called for each clone bio. * Returns %0 for success, non %0 for failure. * @data: private data to be passed to @bio_ctr * * Description: * Clones bios in @rq_src to @rq, and copies attributes of @rq_src to @rq. * Also, pages which the original bios are pointing to are not copied * and the cloned bios just point same pages. * So cloned bios must be completed before original bios, which means * the caller must complete @rq before @rq_src. */ int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio_set *bs, gfp_t gfp_mask, int (*bio_ctr)(struct bio *, struct bio *, void *), void *data) { struct bio *bio, *bio_src; if (!bs) bs = &fs_bio_set; __rq_for_each_bio(bio_src, rq_src) { bio = bio_clone_fast(bio_src, gfp_mask, bs); if (!bio) goto free_and_out; if (bio_ctr && bio_ctr(bio, bio_src, data)) goto free_and_out; if (rq->bio) { rq->biotail->bi_next = bio; rq->biotail = bio; } else { rq->bio = rq->biotail = bio; } bio = NULL; } /* Copy attributes of the original request to the clone request. */ rq->__sector = blk_rq_pos(rq_src); rq->__data_len = blk_rq_bytes(rq_src); if (rq_src->rq_flags & RQF_SPECIAL_PAYLOAD) { rq->rq_flags |= RQF_SPECIAL_PAYLOAD; rq->special_vec = rq_src->special_vec; } rq->nr_phys_segments = rq_src->nr_phys_segments; rq->ioprio = rq_src->ioprio; if (rq->bio && blk_crypto_rq_bio_prep(rq, rq->bio, gfp_mask) < 0) goto free_and_out; return 0; free_and_out: if (bio) bio_put(bio); blk_rq_unprep_clone(rq); return -ENOMEM; } EXPORT_SYMBOL_GPL(blk_rq_prep_clone); int kblockd_schedule_work(struct work_struct *work) { return queue_work(kblockd_workqueue, work); } EXPORT_SYMBOL(kblockd_schedule_work); int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay) { return mod_delayed_work_on(cpu, kblockd_workqueue, dwork, delay); } EXPORT_SYMBOL(kblockd_mod_delayed_work_on); /** * blk_start_plug - initialize blk_plug and track it inside the task_struct * @plug: The &struct blk_plug that needs to be initialized * * Description: * blk_start_plug() indicates to the block layer an intent by the caller * to submit multiple I/O requests in a batch. The block layer may use * this hint to defer submitting I/Os from the caller until blk_finish_plug() * is called. However, the block layer may choose to submit requests * before a call to blk_finish_plug() if the number of queued I/Os * exceeds %BLK_MAX_REQUEST_COUNT, or if the size of the I/O is larger than * %BLK_PLUG_FLUSH_SIZE. The queued I/Os may also be submitted early if * the task schedules (see below). * * Tracking blk_plug inside the task_struct will help with auto-flushing the * pending I/O should the task end up blocking between blk_start_plug() and * blk_finish_plug(). This is important from a performance perspective, but * also ensures that we don't deadlock. For instance, if the task is blocking * for a memory allocation, memory reclaim could end up wanting to free a * page belonging to that request that is currently residing in our private * plug. By flushing the pending I/O when the process goes to sleep, we avoid * this kind of deadlock. */ void blk_start_plug(struct blk_plug *plug) { struct task_struct *tsk = current; /* * If this is a nested plug, don't actually assign it. */ if (tsk->plug) return; INIT_LIST_HEAD(&plug->mq_list); INIT_LIST_HEAD(&plug->cb_list); plug->rq_count = 0; plug->multiple_queues = false; plug->nowait = false; /* * Store ordering should not be needed here, since a potential * preempt will imply a full memory barrier */ tsk->plug = plug; } EXPORT_SYMBOL(blk_start_plug); static void flush_plug_callbacks(struct blk_plug *plug, bool from_schedule) { LIST_HEAD(callbacks); while (!list_empty(&plug->cb_list)) { list_splice_init(&plug->cb_list, &callbacks); while (!list_empty(&callbacks)) { struct blk_plug_cb *cb = list_first_entry(&callbacks, struct blk_plug_cb, list); list_del(&cb->list); cb->callback(cb, from_schedule); } } } struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, void *data, int size) { struct blk_plug *plug = current->plug; struct blk_plug_cb *cb; if (!plug) return NULL; list_for_each_entry(cb, &plug->cb_list, list) if (cb->callback == unplug && cb->data == data) return cb; /* Not currently on the callback list */ BUG_ON(size < sizeof(*cb)); cb = kzalloc(size, GFP_ATOMIC); if (cb) { cb->data = data; cb->callback = unplug; list_add(&cb->list, &plug->cb_list); } return cb; } EXPORT_SYMBOL(blk_check_plugged); void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) { flush_plug_callbacks(plug, from_schedule); if (!list_empty(&plug->mq_list)) blk_mq_flush_plug_list(plug, from_schedule); } /** * blk_finish_plug - mark the end of a batch of submitted I/O * @plug: The &struct blk_plug passed to blk_start_plug() * * Description: * Indicate that a batch of I/O submissions is complete. This function * must be paired with an initial call to blk_start_plug(). The intent * is to allow the block layer to optimize I/O submission. See the * documentation for blk_start_plug() for more information. */ void blk_finish_plug(struct blk_plug *plug) { if (plug != current->plug) return; blk_flush_plug_list(plug, false); current->plug = NULL; } EXPORT_SYMBOL(blk_finish_plug); void blk_io_schedule(void) { /* Prevent hang_check timer from firing at us during very long I/O */ unsigned long timeout = sysctl_hung_task_timeout_secs * HZ / 2; if (timeout) io_schedule_timeout(timeout); else io_schedule(); } EXPORT_SYMBOL_GPL(blk_io_schedule); int __init blk_dev_init(void) { BUILD_BUG_ON(REQ_OP_LAST >= (1 << REQ_OP_BITS)); BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * sizeof_field(struct request, cmd_flags)); BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * sizeof_field(struct bio, bi_opf)); /* used for unplugging and affects IO latency/throughput - HIGHPRI */ kblockd_workqueue = alloc_workqueue("kblockd", WQ_MEM_RECLAIM | WQ_HIGHPRI, 0); if (!kblockd_workqueue) panic("Failed to create kblockd\n"); blk_requestq_cachep = kmem_cache_create("request_queue", sizeof(struct request_queue), 0, SLAB_PANIC, NULL); blk_debugfs_root = debugfs_create_dir("block", NULL); return 0; }
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 // SPDX-License-Identifier: GPL-2.0 /* File: fs/ext4/acl.h (C) 2001 Andreas Gruenbacher, <a.gruenbacher@computer.org> */ #include <linux/posix_acl_xattr.h> #define EXT4_ACL_VERSION 0x0001 typedef struct { __le16 e_tag; __le16 e_perm; __le32 e_id; } ext4_acl_entry; typedef struct { __le16 e_tag; __le16 e_perm; } ext4_acl_entry_short; typedef struct { __le32 a_version; } ext4_acl_header; static inline size_t ext4_acl_size(int count) { if (count <= 4) { return sizeof(ext4_acl_header) + count * sizeof(ext4_acl_entry_short); } else { return sizeof(ext4_acl_header) + 4 * sizeof(ext4_acl_entry_short) + (count - 4) * sizeof(ext4_acl_entry); } } static inline int ext4_acl_count(size_t size) { ssize_t s; size -= sizeof(ext4_acl_header); s = size - 4 * sizeof(ext4_acl_entry_short); if (s < 0) { if (size % sizeof(ext4_acl_entry_short)) return -1; return size / sizeof(ext4_acl_entry_short); } else { if (s % sizeof(ext4_acl_entry)) return -1; return s / sizeof(ext4_acl_entry) + 4; } } #ifdef CONFIG_EXT4_FS_POSIX_ACL /* acl.c */ struct posix_acl *ext4_get_acl(struct inode *inode, int type); int ext4_set_acl(struct inode *inode, struct posix_acl *acl, int type); extern int ext4_init_acl(handle_t *, struct inode *, struct inode *); #else /* CONFIG_EXT4_FS_POSIX_ACL */ #include <linux/sched.h> #define ext4_get_acl NULL #define ext4_set_acl NULL static inline int ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir) { return 0; } #endif /* CONFIG_EXT4_FS_POSIX_ACL */
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 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM fib6 #if !defined(_TRACE_FIB6_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_FIB6_H #include <linux/in6.h> #include <net/flow.h> #include <net/ip6_fib.h> #include <linux/tracepoint.h> TRACE_EVENT(fib6_table_lookup, TP_PROTO(const struct net *net, const struct fib6_result *res, struct fib6_table *table, const struct flowi6 *flp), TP_ARGS(net, res, table, flp), TP_STRUCT__entry( __field( u32, tb_id ) __field( int, err ) __field( int, oif ) __field( int, iif ) __field( __u8, tos ) __field( __u8, scope ) __field( __u8, flags ) __array( __u8, src, 16 ) __array( __u8, dst, 16 ) __field( u16, sport ) __field( u16, dport ) __field( u8, proto ) __field( u8, rt_type ) __dynamic_array( char, name, IFNAMSIZ ) __array( __u8, gw, 16 ) ), TP_fast_assign( struct in6_addr *in6; __entry->tb_id = table->tb6_id; __entry->err = ip6_rt_type_to_error(res->fib6_type); __entry->oif = flp->flowi6_oif; __entry->iif = flp->flowi6_iif; __entry->tos = ip6_tclass(flp->flowlabel); __entry->scope = flp->flowi6_scope; __entry->flags = flp->flowi6_flags; in6 = (struct in6_addr *)__entry->src; *in6 = flp->saddr; in6 = (struct in6_addr *)__entry->dst; *in6 = flp->daddr; __entry->proto = flp->flowi6_proto; if (__entry->proto == IPPROTO_TCP || __entry->proto == IPPROTO_UDP) { __entry->sport = ntohs(flp->fl6_sport); __entry->dport = ntohs(flp->fl6_dport); } else { __entry->sport = 0; __entry->dport = 0; } if (res->nh && res->nh->fib_nh_dev) { __assign_str(name, res->nh->fib_nh_dev); } else { __assign_str(name, "-"); } if (res->f6i == net->ipv6.fib6_null_entry) { struct in6_addr in6_zero = {}; in6 = (struct in6_addr *)__entry->gw; *in6 = in6_zero; } else if (res->nh) { in6 = (struct in6_addr *)__entry->gw; *in6 = res->nh->fib_nh_gw6; } ), TP_printk("table %3u oif %d iif %d proto %u %pI6c/%u -> %pI6c/%u tos %d scope %d flags %x ==> dev %s gw %pI6c err %d", __entry->tb_id, __entry->oif, __entry->iif, __entry->proto, __entry->src, __entry->sport, __entry->dst, __entry->dport, __entry->tos, __entry->scope, __entry->flags, __get_str(name), __entry->gw, __entry->err) ); #endif /* _TRACE_FIB6_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_FUTEX_H #define _ASM_X86_FUTEX_H #ifdef __KERNEL__ #include <linux/futex.h> #include <linux/uaccess.h> #include <asm/asm.h> #include <asm/errno.h> #include <asm/processor.h> #include <asm/smap.h> #define unsafe_atomic_op1(insn, oval, uaddr, oparg, label) \ do { \ int oldval = 0, ret; \ asm volatile("1:\t" insn "\n" \ "2:\n" \ "\t.section .fixup,\"ax\"\n" \ "3:\tmov\t%3, %1\n" \ "\tjmp\t2b\n" \ "\t.previous\n" \ _ASM_EXTABLE_UA(1b, 3b) \ : "=r" (oldval), "=r" (ret), "+m" (*uaddr) \ : "i" (-EFAULT), "0" (oparg), "1" (0)); \ if (ret) \ goto label; \ *oval = oldval; \ } while(0) #define unsafe_atomic_op2(insn, oval, uaddr, oparg, label) \ do { \ int oldval = 0, ret, tem; \ asm volatile("1:\tmovl %2, %0\n" \ "2:\tmovl\t%0, %3\n" \ "\t" insn "\n" \ "3:\t" LOCK_PREFIX "cmpxchgl %3, %2\n" \ "\tjnz\t2b\n" \ "4:\n" \ "\t.section .fixup,\"ax\"\n" \ "5:\tmov\t%5, %1\n" \ "\tjmp\t4b\n" \ "\t.previous\n" \ _ASM_EXTABLE_UA(1b, 5b) \ _ASM_EXTABLE_UA(3b, 5b) \ : "=&a" (oldval), "=&r" (ret), \ "+m" (*uaddr), "=&r" (tem) \ : "r" (oparg), "i" (-EFAULT), "1" (0)); \ if (ret) \ goto label; \ *oval = oldval; \ } while(0) static __always_inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) { if (!user_access_begin(uaddr, sizeof(u32))) return -EFAULT; switch (op) { case FUTEX_OP_SET: unsafe_atomic_op1("xchgl %0, %2", oval, uaddr, oparg, Efault); break; case FUTEX_OP_ADD: unsafe_atomic_op1(LOCK_PREFIX "xaddl %0, %2", oval, uaddr, oparg, Efault); break; case FUTEX_OP_OR: unsafe_atomic_op2("orl %4, %3", oval, uaddr, oparg, Efault); break; case FUTEX_OP_ANDN: unsafe_atomic_op2("andl %4, %3", oval, uaddr, ~oparg, Efault); break; case FUTEX_OP_XOR: unsafe_atomic_op2("xorl %4, %3", oval, uaddr, oparg, Efault); break; default: user_access_end(); return -ENOSYS; } user_access_end(); return 0; Efault: user_access_end(); return -EFAULT; } static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newval) { int ret = 0; if (!user_access_begin(uaddr, sizeof(u32))) return -EFAULT; asm volatile("\n" "1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n" "2:\n" "\t.section .fixup, \"ax\"\n" "3:\tmov %3, %0\n" "\tjmp 2b\n" "\t.previous\n" _ASM_EXTABLE_UA(1b, 3b) : "+r" (ret), "=a" (oldval), "+m" (*uaddr) : "i" (-EFAULT), "r" (newval), "1" (oldval) : "memory" ); user_access_end(); *uval = oldval; return ret; } #endif #endif /* _ASM_X86_FUTEX_H */
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _INET_COMMON_H #define _INET_COMMON_H #include <linux/indirect_call_wrapper.h> extern const struct proto_ops inet_stream_ops; extern const struct proto_ops inet_dgram_ops; /* * INET4 prototypes used by INET6 */ struct msghdr; struct sock; struct sockaddr; struct socket; int inet_release(struct socket *sock); int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags); int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags, int is_sendmsg); int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags); int inet_accept(struct socket *sock, struct socket *newsock, int flags, bool kern); int inet_send_prepare(struct sock *sk); int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size); ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags); int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags); int inet_shutdown(struct socket *sock, int how); int inet_listen(struct socket *sock, int backlog); void inet_sock_destruct(struct sock *sk); int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); /* Don't allocate port at this moment, defer to connect. */ #define BIND_FORCE_ADDRESS_NO_PORT (1 << 0) /* Grab and release socket lock. */ #define BIND_WITH_LOCK (1 << 1) /* Called from BPF program. */ #define BIND_FROM_BPF (1 << 2) int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, u32 flags); int inet_getname(struct socket *sock, struct sockaddr *uaddr, int peer); int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int inet_ctl_sock_create(struct sock **sk, unsigned short family, unsigned short type, unsigned char protocol, struct net *net); int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len); struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb); int inet_gro_complete(struct sk_buff *skb, int nhoff); struct sk_buff *inet_gso_segment(struct sk_buff *skb, netdev_features_t features); static inline void inet_ctl_sock_destroy(struct sock *sk) { if (sk) sock_release(sk->sk_socket); } #define indirect_call_gro_receive(f2, f1, cb, head, skb) \ ({ \ unlikely(gro_recursion_inc_test(skb)) ? \ NAPI_GRO_CB(skb)->flush |= 1, NULL : \ INDIRECT_CALL_2(cb, f2, f1, head, skb); \ }) #endif
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NF_CONNTRACK_ZONES_H #define _NF_CONNTRACK_ZONES_H #include <linux/netfilter/nf_conntrack_zones_common.h> #include <net/netfilter/nf_conntrack.h> static inline const struct nf_conntrack_zone * nf_ct_zone(const struct nf_conn *ct) { #ifdef CONFIG_NF_CONNTRACK_ZONES return &ct->zone; #else return &nf_ct_zone_dflt; #endif } static inline const struct nf_conntrack_zone * nf_ct_zone_init(struct nf_conntrack_zone *zone, u16 id, u8 dir, u8 flags) { zone->id = id; zone->flags = flags; zone->dir = dir; return zone; } static inline const struct nf_conntrack_zone * nf_ct_zone_tmpl(const struct nf_conn *tmpl, const struct sk_buff *skb, struct nf_conntrack_zone *tmp) { #ifdef CONFIG_NF_CONNTRACK_ZONES if (!tmpl) return &nf_ct_zone_dflt; if (tmpl->zone.flags & NF_CT_FLAG_MARK) return nf_ct_zone_init(tmp, skb->mark, tmpl->zone.dir, 0); #endif return nf_ct_zone(tmpl); } static inline void nf_ct_zone_add(struct nf_conn *ct, const struct nf_conntrack_zone *zone) { #ifdef CONFIG_NF_CONNTRACK_ZONES ct->zone = *zone; #endif } static inline bool nf_ct_zone_matches_dir(const struct nf_conntrack_zone *zone, enum ip_conntrack_dir dir) { return zone->dir & (1 << dir); } static inline u16 nf_ct_zone_id(const struct nf_conntrack_zone *zone, enum ip_conntrack_dir dir) { #ifdef CONFIG_NF_CONNTRACK_ZONES return nf_ct_zone_matches_dir(zone, dir) ? zone->id : NF_CT_DEFAULT_ZONE_ID; #else return NF_CT_DEFAULT_ZONE_ID; #endif } static inline bool nf_ct_zone_equal(const struct nf_conn *a, const struct nf_conntrack_zone *b, enum ip_conntrack_dir dir) { #ifdef CONFIG_NF_CONNTRACK_ZONES return nf_ct_zone_id(nf_ct_zone(a), dir) == nf_ct_zone_id(b, dir); #else return true; #endif } static inline bool nf_ct_zone_equal_any(const struct nf_conn *a, const struct nf_conntrack_zone *b) { #ifdef CONFIG_NF_CONNTRACK_ZONES return nf_ct_zone(a)->id == b->id; #else return true; #endif } #endif /* _NF_CONNTRACK_ZONES_H */
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_TASK_H #define _LINUX_SCHED_TASK_H /* * Interface between the scheduler and various task lifetime (fork()/exit()) * functionality: */ #include <linux/sched.h> #include <linux/uaccess.h> struct task_struct; struct rusage; union thread_union; struct css_set; /* All the bits taken by the old clone syscall. */ #define CLONE_LEGACY_FLAGS 0xffffffffULL struct kernel_clone_args { u64 flags; int __user *pidfd; int __user *child_tid; int __user *parent_tid; int exit_signal; unsigned long stack; unsigned long stack_size; unsigned long tls; pid_t *set_tid; /* Number of elements in *set_tid */ size_t set_tid_size; int cgroup; struct cgroup *cgrp; struct css_set *cset; }; /* * This serializes "schedule()" and also protects * the run-queue from deletions/modifications (but * _adding_ to the beginning of the run-queue has * a separate lock). */ extern rwlock_t tasklist_lock; extern spinlock_t mmlist_lock; extern union thread_union init_thread_union; extern struct task_struct init_task; #ifdef CONFIG_PROVE_RCU extern int lockdep_tasklist_lock_is_held(void); #endif /* #ifdef CONFIG_PROVE_RCU */ extern asmlinkage void schedule_tail(struct task_struct *prev); extern void init_idle(struct task_struct *idle, int cpu); extern int sched_fork(unsigned long clone_flags, struct task_struct *p); extern void sched_post_fork(struct task_struct *p, struct kernel_clone_args *kargs); extern void sched_dead(struct task_struct *p); void __noreturn do_task_dead(void); extern void proc_caches_init(void); extern void fork_init(void); extern void release_task(struct task_struct * p); extern int copy_thread(unsigned long, unsigned long, unsigned long, struct task_struct *, unsigned long); extern void flush_thread(void); #ifdef CONFIG_HAVE_EXIT_THREAD extern void exit_thread(struct task_struct *tsk); #else static inline void exit_thread(struct task_struct *tsk) { } #endif extern void do_group_exit(int); extern void exit_files(struct task_struct *); extern void exit_itimers(struct signal_struct *); extern pid_t kernel_clone(struct kernel_clone_args *kargs); struct task_struct *fork_idle(int); struct mm_struct *copy_init_mm(void); extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags); extern long kernel_wait4(pid_t, int __user *, int, struct rusage *); int kernel_wait(pid_t pid, int *stat); extern void free_task(struct task_struct *tsk); /* sched_exec is called by processes performing an exec */ #ifdef CONFIG_SMP extern void sched_exec(void); #else #define sched_exec() {} #endif static inline struct task_struct *get_task_struct(struct task_struct *t) { refcount_inc(&t->usage); return t; } extern void __put_task_struct(struct task_struct *t); static inline void put_task_struct(struct task_struct *t) { if (refcount_dec_and_test(&t->usage)) __put_task_struct(t); } static inline void put_task_struct_many(struct task_struct *t, int nr) { if (refcount_sub_and_test(nr, &t->usage)) __put_task_struct(t); } void put_task_struct_rcu_user(struct task_struct *task); #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT extern int arch_task_struct_size __read_mostly; #else # define arch_task_struct_size (sizeof(struct task_struct)) #endif #ifndef CONFIG_HAVE_ARCH_THREAD_STRUCT_WHITELIST /* * If an architecture has not declared a thread_struct whitelist we * must assume something there may need to be copied to userspace. */ static inline void arch_thread_struct_whitelist(unsigned long *offset, unsigned long *size) { *offset = 0; /* Handle dynamically sized thread_struct. */ *size = arch_task_struct_size - offsetof(struct task_struct, thread); } #endif #ifdef CONFIG_VMAP_STACK static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) { return t->stack_vm_area; } #else static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) { return NULL; } #endif /* * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring * subscriptions and synchronises with wait4(). Also used in procfs. Also * pins the final release of task.io_context. Also protects ->cpuset and * ->cgroup.subsys[]. And ->vfork_done. And ->sysvshm.shm_clist. * * Nests both inside and outside of read_lock(&tasklist_lock). * It must not be nested with write_lock_irq(&tasklist_lock), * neither inside nor outside. */ static inline void task_lock(struct task_struct *p) { spin_lock(&p->alloc_lock); } static inline void task_unlock(struct task_struct *p) { spin_unlock(&p->alloc_lock); } #endif /* _LINUX_SCHED_TASK_H */
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 /* SPDX-License-Identifier: GPL-2.0-only */ /* * This file is part of the Linux kernel. * * Copyright (c) 2011-2014, Intel Corporation * Authors: Fenghua Yu <fenghua.yu@intel.com>, * H. Peter Anvin <hpa@linux.intel.com> */ #ifndef ASM_X86_ARCHRANDOM_H #define ASM_X86_ARCHRANDOM_H #include <asm/processor.h> #include <asm/cpufeature.h> #define RDRAND_RETRY_LOOPS 10 /* Unconditional execution of RDRAND and RDSEED */ static inline bool __must_check rdrand_long(unsigned long *v) { bool ok; unsigned int retry = RDRAND_RETRY_LOOPS; do { asm volatile("rdrand %[out]" CC_SET(c) : CC_OUT(c) (ok), [out] "=r" (*v)); if (ok) return true; } while (--retry); return false; } static inline bool __must_check rdrand_int(unsigned int *v) { bool ok; unsigned int retry = RDRAND_RETRY_LOOPS; do { asm volatile("rdrand %[out]" CC_SET(c) : CC_OUT(c) (ok), [out] "=r" (*v)); if (ok) return true; } while (--retry); return false; } static inline bool __must_check rdseed_long(unsigned long *v) { bool ok; asm volatile("rdseed %[out]" CC_SET(c) : CC_OUT(c) (ok), [out] "=r" (*v)); return ok; } static inline bool __must_check rdseed_int(unsigned int *v) { bool ok; asm volatile("rdseed %[out]" CC_SET(c) : CC_OUT(c) (ok), [out] "=r" (*v)); return ok; } /* * These are the generic interfaces; they must not be declared if the * stubs in <linux/random.h> are to be invoked, * i.e. CONFIG_ARCH_RANDOM is not defined. */ #ifdef CONFIG_ARCH_RANDOM static inline bool __must_check arch_get_random_long(unsigned long *v) { return static_cpu_has(X86_FEATURE_RDRAND) ? rdrand_long(v) : false; } static inline bool __must_check arch_get_random_int(unsigned int *v) { return static_cpu_has(X86_FEATURE_RDRAND) ? rdrand_int(v) : false; } static inline bool __must_check arch_get_random_seed_long(unsigned long *v) { return static_cpu_has(X86_FEATURE_RDSEED) ? rdseed_long(v) : false; } static inline bool __must_check arch_get_random_seed_int(unsigned int *v) { return static_cpu_has(X86_FEATURE_RDSEED) ? rdseed_int(v) : false; } extern void x86_init_rdrand(struct cpuinfo_x86 *c); #else /* !CONFIG_ARCH_RANDOM */ static inline void x86_init_rdrand(struct cpuinfo_x86 *c) { } #endif /* !CONFIG_ARCH_RANDOM */ #endif /* ASM_X86_ARCHRANDOM_H */
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TIME64_H #define _LINUX_TIME64_H #include <linux/math64.h> #include <vdso/time64.h> typedef __s64 time64_t; typedef __u64 timeu64_t; #include <uapi/linux/time.h> struct timespec64 { time64_t tv_sec; /* seconds */ long tv_nsec; /* nanoseconds */ }; struct itimerspec64 { struct timespec64 it_interval; struct timespec64 it_value; }; /* Located here for timespec[64]_valid_strict */ #define TIME64_MAX ((s64)~((u64)1 << 63)) #define TIME64_MIN (-TIME64_MAX - 1) #define KTIME_MAX ((s64)~((u64)1 << 63)) #define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) /* * Limits for settimeofday(): * * To prevent setting the time close to the wraparound point time setting * is limited so a reasonable uptime can be accomodated. Uptime of 30 years * should be really sufficient, which means the cutoff is 2232. At that * point the cutoff is just a small part of the larger problem. */ #define TIME_UPTIME_SEC_MAX (30LL * 365 * 24 *3600) #define TIME_SETTOD_SEC_MAX (KTIME_SEC_MAX - TIME_UPTIME_SEC_MAX) static inline int timespec64_equal(const struct timespec64 *a, const struct timespec64 *b) { return (a->tv_sec == b->tv_sec) && (a->tv_nsec == b->tv_nsec); } /* * lhs < rhs: return <0 * lhs == rhs: return 0 * lhs > rhs: return >0 */ static inline int timespec64_compare(const struct timespec64 *lhs, const struct timespec64 *rhs) { if (lhs->tv_sec < rhs->tv_sec) return -1; if (lhs->tv_sec > rhs->tv_sec) return 1; return lhs->tv_nsec - rhs->tv_nsec; } extern void set_normalized_timespec64(struct timespec64 *ts, time64_t sec, s64 nsec); static inline struct timespec64 timespec64_add(struct timespec64 lhs, struct timespec64 rhs) { struct timespec64 ts_delta; set_normalized_timespec64(&ts_delta, lhs.tv_sec + rhs.tv_sec, lhs.tv_nsec + rhs.tv_nsec); return ts_delta; } /* * sub = lhs - rhs, in normalized form */ static inline struct timespec64 timespec64_sub(struct timespec64 lhs, struct timespec64 rhs) { struct timespec64 ts_delta; set_normalized_timespec64(&ts_delta, lhs.tv_sec - rhs.tv_sec, lhs.tv_nsec - rhs.tv_nsec); return ts_delta; } /* * Returns true if the timespec64 is norm, false if denorm: */ static inline bool timespec64_valid(const struct timespec64 *ts) { /* Dates before 1970 are bogus */ if (ts->tv_sec < 0) return false; /* Can't have more nanoseconds then a second */ if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC) return false; return true; } static inline bool timespec64_valid_strict(const struct timespec64 *ts) { if (!timespec64_valid(ts)) return false; /* Disallow values that could overflow ktime_t */ if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) return false; return true; } static inline bool timespec64_valid_settod(const struct timespec64 *ts) { if (!timespec64_valid(ts)) return false; /* Disallow values which cause overflow issues vs. CLOCK_REALTIME */ if ((unsigned long long)ts->tv_sec >= TIME_SETTOD_SEC_MAX) return false; return true; } /** * timespec64_to_ns - Convert timespec64 to nanoseconds * @ts: pointer to the timespec64 variable to be converted * * Returns the scalar nanosecond representation of the timespec64 * parameter. */ static inline s64 timespec64_to_ns(const struct timespec64 *ts) { /* Prevent multiplication overflow */ if ((unsigned long long)ts->tv_sec >= KTIME_SEC_MAX) return KTIME_MAX; return ((s64) ts->tv_sec * NSEC_PER_SEC) + ts->tv_nsec; } /** * ns_to_timespec64 - Convert nanoseconds to timespec64 * @nsec: the nanoseconds value to be converted * * Returns the timespec64 representation of the nsec parameter. */ extern struct timespec64 ns_to_timespec64(const s64 nsec); /** * timespec64_add_ns - Adds nanoseconds to a timespec64 * @a: pointer to timespec64 to be incremented * @ns: unsigned nanoseconds value to be added * * This must always be inlined because its used from the x86-64 vdso, * which cannot call other kernel functions. */ static __always_inline void timespec64_add_ns(struct timespec64 *a, u64 ns) { a->tv_sec += __iter_div_u64_rem(a->tv_nsec + ns, NSEC_PER_SEC, &ns); a->tv_nsec = ns; } /* * timespec64_add_safe assumes both values are positive and checks for * overflow. It will return TIME64_MAX in case of overflow. */ extern struct timespec64 timespec64_add_safe(const struct timespec64 lhs, const struct timespec64 rhs); #endif /* _LINUX_TIME64_H */
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 /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * SR-IPv6 implementation * * Author: * David Lebrun <david.lebrun@uclouvain.be> */ #ifndef _NET_SEG6_H #define _NET_SEG6_H #include <linux/net.h> #include <linux/ipv6.h> #include <linux/seg6.h> #include <linux/rhashtable-types.h> static inline void update_csum_diff4(struct sk_buff *skb, __be32 from, __be32 to) { __be32 diff[] = { ~from, to }; skb->csum = ~csum_partial((char *)diff, sizeof(diff), ~skb->csum); } static inline void update_csum_diff16(struct sk_buff *skb, __be32 *from, __be32 *to) { __be32 diff[] = { ~from[0], ~from[1], ~from[2], ~from[3], to[0], to[1], to[2], to[3], }; skb->csum = ~csum_partial((char *)diff, sizeof(diff), ~skb->csum); } struct seg6_pernet_data { struct mutex lock; struct in6_addr __rcu *tun_src; #ifdef CONFIG_IPV6_SEG6_HMAC struct rhashtable hmac_infos; #endif }; static inline struct seg6_pernet_data *seg6_pernet(struct net *net) { #if IS_ENABLED(CONFIG_IPV6) return net->ipv6.seg6_data; #else return NULL; #endif } extern int seg6_init(void); extern void seg6_exit(void); extern int seg6_iptunnel_init(void); extern void seg6_iptunnel_exit(void); extern int seg6_local_init(void); extern void seg6_local_exit(void); extern bool seg6_validate_srh(struct ipv6_sr_hdr *srh, int len, bool reduced); extern int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto); extern int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh); extern int seg6_lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr, u32 tbl_id); #endif
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM jbd2 #if !defined(_TRACE_JBD2_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_JBD2_H #include <linux/jbd2.h> #include <linux/tracepoint.h> struct transaction_chp_stats_s; struct transaction_run_stats_s; TRACE_EVENT(jbd2_checkpoint, TP_PROTO(journal_t *journal, int result), TP_ARGS(journal, result), TP_STRUCT__entry( __field( dev_t, dev ) __field( int, result ) ), TP_fast_assign( __entry->dev = journal->j_fs_dev->bd_dev; __entry->result = result; ), TP_printk("dev %d,%d result %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->result) ); DECLARE_EVENT_CLASS(jbd2_commit, TP_PROTO(journal_t *journal, transaction_t *commit_transaction), TP_ARGS(journal, commit_transaction), TP_STRUCT__entry( __field( dev_t, dev ) __field( char, sync_commit ) __field( int, transaction ) ), TP_fast_assign( __entry->dev = journal->j_fs_dev->bd_dev; __entry->sync_commit = commit_transaction->t_synchronous_commit; __entry->transaction = commit_transaction->t_tid; ), TP_printk("dev %d,%d transaction %d sync %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->transaction, __entry->sync_commit) ); DEFINE_EVENT(jbd2_commit, jbd2_start_commit, TP_PROTO(journal_t *journal, transaction_t *commit_transaction), TP_ARGS(journal, commit_transaction) ); DEFINE_EVENT(jbd2_commit, jbd2_commit_locking, TP_PROTO(journal_t *journal, transaction_t *commit_transaction), TP_ARGS(journal, commit_transaction) ); DEFINE_EVENT(jbd2_commit, jbd2_commit_flushing, TP_PROTO(journal_t *journal, transaction_t *commit_transaction), TP_ARGS(journal, commit_transaction) ); DEFINE_EVENT(jbd2_commit, jbd2_commit_logging, TP_PROTO(journal_t *journal, transaction_t *commit_transaction), TP_ARGS(journal, commit_transaction) ); DEFINE_EVENT(jbd2_commit, jbd2_drop_transaction, TP_PROTO(journal_t *journal, transaction_t *commit_transaction), TP_ARGS(journal, commit_transaction) ); TRACE_EVENT(jbd2_end_commit, TP_PROTO(journal_t *journal, transaction_t *commit_transaction), TP_ARGS(journal, commit_transaction), TP_STRUCT__entry( __field( dev_t, dev ) __field( char, sync_commit ) __field( int, transaction ) __field( int, head ) ), TP_fast_assign( __entry->dev = journal->j_fs_dev->bd_dev; __entry->sync_commit = commit_transaction->t_synchronous_commit; __entry->transaction = commit_transaction->t_tid; __entry->head = journal->j_tail_sequence; ), TP_printk("dev %d,%d transaction %d sync %d head %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->transaction, __entry->sync_commit, __entry->head) ); TRACE_EVENT(jbd2_submit_inode_data, TP_PROTO(struct inode *inode), TP_ARGS(inode), TP_STRUCT__entry( __field( dev_t, dev ) __field( ino_t, ino ) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; ), TP_printk("dev %d,%d ino %lu", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long) __entry->ino) ); DECLARE_EVENT_CLASS(jbd2_handle_start_class, TP_PROTO(dev_t dev, unsigned long tid, unsigned int type, unsigned int line_no, int requested_blocks), TP_ARGS(dev, tid, type, line_no, requested_blocks), TP_STRUCT__entry( __field( dev_t, dev ) __field( unsigned long, tid ) __field( unsigned int, type ) __field( unsigned int, line_no ) __field( int, requested_blocks) ), TP_fast_assign( __entry->dev = dev; __entry->tid = tid; __entry->type = type; __entry->line_no = line_no; __entry->requested_blocks = requested_blocks; ), TP_printk("dev %d,%d tid %lu type %u line_no %u " "requested_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid, __entry->type, __entry->line_no, __entry->requested_blocks) ); DEFINE_EVENT(jbd2_handle_start_class, jbd2_handle_start, TP_PROTO(dev_t dev, unsigned long tid, unsigned int type, unsigned int line_no, int requested_blocks), TP_ARGS(dev, tid, type, line_no, requested_blocks) ); DEFINE_EVENT(jbd2_handle_start_class, jbd2_handle_restart, TP_PROTO(dev_t dev, unsigned long tid, unsigned int type, unsigned int line_no, int requested_blocks), TP_ARGS(dev, tid, type, line_no, requested_blocks) ); TRACE_EVENT(jbd2_handle_extend, TP_PROTO(dev_t dev, unsigned long tid, unsigned int type, unsigned int line_no, int buffer_credits, int requested_blocks), TP_ARGS(dev, tid, type, line_no, buffer_credits, requested_blocks), TP_STRUCT__entry( __field( dev_t, dev ) __field( unsigned long, tid ) __field( unsigned int, type ) __field( unsigned int, line_no ) __field( int, buffer_credits ) __field( int, requested_blocks) ), TP_fast_assign( __entry->dev = dev; __entry->tid = tid; __entry->type = type; __entry->line_no = line_no; __entry->buffer_credits = buffer_credits; __entry->requested_blocks = requested_blocks; ), TP_printk("dev %d,%d tid %lu type %u line_no %u " "buffer_credits %d requested_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid, __entry->type, __entry->line_no, __entry->buffer_credits, __entry->requested_blocks) ); TRACE_EVENT(jbd2_handle_stats, TP_PROTO(dev_t dev, unsigned long tid, unsigned int type, unsigned int line_no, int interval, int sync, int requested_blocks, int dirtied_blocks), TP_ARGS(dev, tid, type, line_no, interval, sync, requested_blocks, dirtied_blocks), TP_STRUCT__entry( __field( dev_t, dev ) __field( unsigned long, tid ) __field( unsigned int, type ) __field( unsigned int, line_no ) __field( int, interval ) __field( int, sync ) __field( int, requested_blocks) __field( int, dirtied_blocks ) ), TP_fast_assign( __entry->dev = dev; __entry->tid = tid; __entry->type = type; __entry->line_no = line_no; __entry->interval = interval; __entry->sync = sync; __entry->requested_blocks = requested_blocks; __entry->dirtied_blocks = dirtied_blocks; ), TP_printk("dev %d,%d tid %lu type %u line_no %u interval %d " "sync %d requested_blocks %d dirtied_blocks %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid, __entry->type, __entry->line_no, __entry->interval, __entry->sync, __entry->requested_blocks, __entry->dirtied_blocks) ); TRACE_EVENT(jbd2_run_stats, TP_PROTO(dev_t dev, unsigned long tid, struct transaction_run_stats_s *stats), TP_ARGS(dev, tid, stats), TP_STRUCT__entry( __field( dev_t, dev ) __field( unsigned long, tid ) __field( unsigned long, wait ) __field( unsigned long, request_delay ) __field( unsigned long, running ) __field( unsigned long, locked ) __field( unsigned long, flushing ) __field( unsigned long, logging ) __field( __u32, handle_count ) __field( __u32, blocks ) __field( __u32, blocks_logged ) ), TP_fast_assign( __entry->dev = dev; __entry->tid = tid; __entry->wait = stats->rs_wait; __entry->request_delay = stats->rs_request_delay; __entry->running = stats->rs_running; __entry->locked = stats->rs_locked; __entry->flushing = stats->rs_flushing; __entry->logging = stats->rs_logging; __entry->handle_count = stats->rs_handle_count; __entry->blocks = stats->rs_blocks; __entry->blocks_logged = stats->rs_blocks_logged; ), TP_printk("dev %d,%d tid %lu wait %u request_delay %u running %u " "locked %u flushing %u logging %u handle_count %u " "blocks %u blocks_logged %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid, jiffies_to_msecs(__entry->wait), jiffies_to_msecs(__entry->request_delay), jiffies_to_msecs(__entry->running), jiffies_to_msecs(__entry->locked), jiffies_to_msecs(__entry->flushing), jiffies_to_msecs(__entry->logging), __entry->handle_count, __entry->blocks, __entry->blocks_logged) ); TRACE_EVENT(jbd2_checkpoint_stats, TP_PROTO(dev_t dev, unsigned long tid, struct transaction_chp_stats_s *stats), TP_ARGS(dev, tid, stats), TP_STRUCT__entry( __field( dev_t, dev ) __field( unsigned long, tid ) __field( unsigned long, chp_time ) __field( __u32, forced_to_close ) __field( __u32, written ) __field( __u32, dropped ) ), TP_fast_assign( __entry->dev = dev; __entry->tid = tid; __entry->chp_time = stats->cs_chp_time; __entry->forced_to_close= stats->cs_forced_to_close; __entry->written = stats->cs_written; __entry->dropped = stats->cs_dropped; ), TP_printk("dev %d,%d tid %lu chp_time %u forced_to_close %u " "written %u dropped %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid, jiffies_to_msecs(__entry->chp_time), __entry->forced_to_close, __entry->written, __entry->dropped) ); TRACE_EVENT(jbd2_update_log_tail, TP_PROTO(journal_t *journal, tid_t first_tid, unsigned long block_nr, unsigned long freed), TP_ARGS(journal, first_tid, block_nr, freed), TP_STRUCT__entry( __field( dev_t, dev ) __field( tid_t, tail_sequence ) __field( tid_t, first_tid ) __field(unsigned long, block_nr ) __field(unsigned long, freed ) ), TP_fast_assign( __entry->dev = journal->j_fs_dev->bd_dev; __entry->tail_sequence = journal->j_tail_sequence; __entry->first_tid = first_tid; __entry->block_nr = block_nr; __entry->freed = freed; ), TP_printk("dev %d,%d from %u to %u offset %lu freed %lu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tail_sequence, __entry->first_tid, __entry->block_nr, __entry->freed) ); TRACE_EVENT(jbd2_write_superblock, TP_PROTO(journal_t *journal, int write_op), TP_ARGS(journal, write_op), TP_STRUCT__entry( __field( dev_t, dev ) __field( int, write_op ) ), TP_fast_assign( __entry->dev = journal->j_fs_dev->bd_dev; __entry->write_op = write_op; ), TP_printk("dev %d,%d write_op %x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->write_op) ); TRACE_EVENT(jbd2_lock_buffer_stall, TP_PROTO(dev_t dev, unsigned long stall_ms), TP_ARGS(dev, stall_ms), TP_STRUCT__entry( __field( dev_t, dev ) __field(unsigned long, stall_ms ) ), TP_fast_assign( __entry->dev = dev; __entry->stall_ms = stall_ms; ), TP_printk("dev %d,%d stall_ms %lu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->stall_ms) ); #endif /* _TRACE_JBD2_H */ /* This part must be outside protection */ #include <trace/define_trace.h>
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NET_XFRM_H #define _NET_XFRM_H #include <linux/compiler.h> #include <linux/xfrm.h> #include <linux/spinlock.h> #include <linux/list.h> #include <linux/skbuff.h> #include <linux/socket.h> #include <linux/pfkeyv2.h> #include <linux/ipsec.h> #include <linux/in6.h> #include <linux/mutex.h> #include <linux/audit.h> #include <linux/slab.h> #include <linux/refcount.h> #include <linux/sockptr.h> #include <net/sock.h> #include <net/dst.h> #include <net/ip.h> #include <net/route.h> #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/flow.h> #include <net/gro_cells.h> #include <linux/interrupt.h> #ifdef CONFIG_XFRM_STATISTICS #include <net/snmp.h> #endif #define XFRM_PROTO_ESP 50 #define XFRM_PROTO_AH 51 #define XFRM_PROTO_COMP 108 #define XFRM_PROTO_IPIP 4 #define XFRM_PROTO_IPV6 41 #define XFRM_PROTO_ROUTING IPPROTO_ROUTING #define XFRM_PROTO_DSTOPTS IPPROTO_DSTOPTS #define XFRM_ALIGN4(len) (((len) + 3) & ~3) #define XFRM_ALIGN8(len) (((len) + 7) & ~7) #define MODULE_ALIAS_XFRM_MODE(family, encap) \ MODULE_ALIAS("xfrm-mode-" __stringify(family) "-" __stringify(encap)) #define MODULE_ALIAS_XFRM_TYPE(family, proto) \ MODULE_ALIAS("xfrm-type-" __stringify(family) "-" __stringify(proto)) #define MODULE_ALIAS_XFRM_OFFLOAD_TYPE(family, proto) \ MODULE_ALIAS("xfrm-offload-" __stringify(family) "-" __stringify(proto)) #ifdef CONFIG_XFRM_STATISTICS #define XFRM_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.xfrm_statistics, field) #else #define XFRM_INC_STATS(net, field) ((void)(net)) #endif /* Organization of SPD aka "XFRM rules" ------------------------------------ Basic objects: - policy rule, struct xfrm_policy (=SPD entry) - bundle of transformations, struct dst_entry == struct xfrm_dst (=SA bundle) - instance of a transformer, struct xfrm_state (=SA) - template to clone xfrm_state, struct xfrm_tmpl SPD is plain linear list of xfrm_policy rules, ordered by priority. (To be compatible with existing pfkeyv2 implementations, many rules with priority of 0x7fffffff are allowed to exist and such rules are ordered in an unpredictable way, thanks to bsd folks.) Lookup is plain linear search until the first match with selector. If "action" is "block", then we prohibit the flow, otherwise: if "xfrms_nr" is zero, the flow passes untransformed. Otherwise, policy entry has list of up to XFRM_MAX_DEPTH transformations, described by templates xfrm_tmpl. Each template is resolved to a complete xfrm_state (see below) and we pack bundle of transformations to a dst_entry returned to requestor. dst -. xfrm .-> xfrm_state #1 |---. child .-> dst -. xfrm .-> xfrm_state #2 |---. child .-> dst -. xfrm .-> xfrm_state #3 |---. child .-> NULL Bundles are cached at xrfm_policy struct (field ->bundles). Resolution of xrfm_tmpl ----------------------- Template contains: 1. ->mode Mode: transport or tunnel 2. ->id.proto Protocol: AH/ESP/IPCOMP 3. ->id.daddr Remote tunnel endpoint, ignored for transport mode. Q: allow to resolve security gateway? 4. ->id.spi If not zero, static SPI. 5. ->saddr Local tunnel endpoint, ignored for transport mode. 6. ->algos List of allowed algos. Plain bitmask now. Q: ealgos, aalgos, calgos. What a mess... 7. ->share Sharing mode. Q: how to implement private sharing mode? To add struct sock* to flow id? Having this template we search through SAD searching for entries with appropriate mode/proto/algo, permitted by selector. If no appropriate entry found, it is requested from key manager. PROBLEMS: Q: How to find all the bundles referring to a physical path for PMTU discovery? Seems, dst should contain list of all parents... and enter to infinite locking hierarchy disaster. No! It is easier, we will not search for them, let them find us. We add genid to each dst plus pointer to genid of raw IP route, pmtu disc will update pmtu on raw IP route and increase its genid. dst_check() will see this for top level and trigger resyncing metrics. Plus, it will be made via sk->sk_dst_cache. Solved. */ struct xfrm_state_walk { struct list_head all; u8 state; u8 dying; u8 proto; u32 seq; struct xfrm_address_filter *filter; }; struct xfrm_state_offload { struct net_device *dev; struct net_device *real_dev; unsigned long offload_handle; unsigned int num_exthdrs; u8 flags; }; struct xfrm_mode { u8 encap; u8 family; u8 flags; }; /* Flags for xfrm_mode. */ enum { XFRM_MODE_FLAG_TUNNEL = 1, }; /* Full description of state of transformer. */ struct xfrm_state { possible_net_t xs_net; union { struct hlist_node gclist; struct hlist_node bydst; }; struct hlist_node bysrc; struct hlist_node byspi; refcount_t refcnt; spinlock_t lock; struct xfrm_id id; struct xfrm_selector sel; struct xfrm_mark mark; u32 if_id; u32 tfcpad; u32 genid; /* Key manager bits */ struct xfrm_state_walk km; /* Parameters of this state. */ struct { u32 reqid; u8 mode; u8 replay_window; u8 aalgo, ealgo, calgo; u8 flags; u16 family; xfrm_address_t saddr; int header_len; int trailer_len; u32 extra_flags; struct xfrm_mark smark; } props; struct xfrm_lifetime_cfg lft; /* Data for transformer */ struct xfrm_algo_auth *aalg; struct xfrm_algo *ealg; struct xfrm_algo *calg; struct xfrm_algo_aead *aead; const char *geniv; /* Data for encapsulator */ struct xfrm_encap_tmpl *encap; struct sock __rcu *encap_sk; /* Data for care-of address */ xfrm_address_t *coaddr; /* IPComp needs an IPIP tunnel for handling uncompressed packets */ struct xfrm_state *tunnel; /* If a tunnel, number of users + 1 */ atomic_t tunnel_users; /* State for replay detection */ struct xfrm_replay_state replay; struct xfrm_replay_state_esn *replay_esn; /* Replay detection state at the time we sent the last notification */ struct xfrm_replay_state preplay; struct xfrm_replay_state_esn *preplay_esn; /* The functions for replay detection. */ const struct xfrm_replay *repl; /* internal flag that only holds state for delayed aevent at the * moment */ u32 xflags; /* Replay detection notification settings */ u32 replay_maxage; u32 replay_maxdiff; /* Replay detection notification timer */ struct timer_list rtimer; /* Statistics */ struct xfrm_stats stats; struct xfrm_lifetime_cur curlft; struct hrtimer mtimer; struct xfrm_state_offload xso; /* used to fix curlft->add_time when changing date */ long saved_tmo; /* Last used time */ time64_t lastused; struct page_frag xfrag; /* Reference to data common to all the instances of this * transformer. */ const struct xfrm_type *type; struct xfrm_mode inner_mode; struct xfrm_mode inner_mode_iaf; struct xfrm_mode outer_mode; const struct xfrm_type_offload *type_offload; /* Security context */ struct xfrm_sec_ctx *security; /* Private data of this transformer, format is opaque, * interpreted by xfrm_type methods. */ void *data; }; static inline struct net *xs_net(struct xfrm_state *x) { return read_pnet(&x->xs_net); } /* xflags - make enum if more show up */ #define XFRM_TIME_DEFER 1 #define XFRM_SOFT_EXPIRE 2 enum { XFRM_STATE_VOID, XFRM_STATE_ACQ, XFRM_STATE_VALID, XFRM_STATE_ERROR, XFRM_STATE_EXPIRED, XFRM_STATE_DEAD }; /* callback structure passed from either netlink or pfkey */ struct km_event { union { u32 hard; u32 proto; u32 byid; u32 aevent; u32 type; } data; u32 seq; u32 portid; u32 event; struct net *net; }; struct xfrm_replay { void (*advance)(struct xfrm_state *x, __be32 net_seq); int (*check)(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq); int (*recheck)(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq); void (*notify)(struct xfrm_state *x, int event); int (*overflow)(struct xfrm_state *x, struct sk_buff *skb); }; struct xfrm_if_cb { struct xfrm_if *(*decode_session)(struct sk_buff *skb, unsigned short family); }; void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb); void xfrm_if_unregister_cb(void); struct net_device; struct xfrm_type; struct xfrm_dst; struct xfrm_policy_afinfo { struct dst_ops *dst_ops; struct dst_entry *(*dst_lookup)(struct net *net, int tos, int oif, const xfrm_address_t *saddr, const xfrm_address_t *daddr, u32 mark); int (*get_saddr)(struct net *net, int oif, xfrm_address_t *saddr, xfrm_address_t *daddr, u32 mark); int (*fill_dst)(struct xfrm_dst *xdst, struct net_device *dev, const struct flowi *fl); struct dst_entry *(*blackhole_route)(struct net *net, struct dst_entry *orig); }; int xfrm_policy_register_afinfo(const struct xfrm_policy_afinfo *afinfo, int family); void xfrm_policy_unregister_afinfo(const struct xfrm_policy_afinfo *afinfo); void km_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c); void km_state_notify(struct xfrm_state *x, const struct km_event *c); struct xfrm_tmpl; int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol); void km_state_expired(struct xfrm_state *x, int hard, u32 portid); int __xfrm_state_delete(struct xfrm_state *x); struct xfrm_state_afinfo { u8 family; u8 proto; const struct xfrm_type_offload *type_offload_esp; const struct xfrm_type *type_esp; const struct xfrm_type *type_ipip; const struct xfrm_type *type_ipip6; const struct xfrm_type *type_comp; const struct xfrm_type *type_ah; const struct xfrm_type *type_routing; const struct xfrm_type *type_dstopts; int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*transport_finish)(struct sk_buff *skb, int async); void (*local_error)(struct sk_buff *skb, u32 mtu); }; int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo); int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo); struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family); struct xfrm_state_afinfo *xfrm_state_afinfo_get_rcu(unsigned int family); struct xfrm_input_afinfo { u8 family; bool is_ipip; int (*callback)(struct sk_buff *skb, u8 protocol, int err); }; int xfrm_input_register_afinfo(const struct xfrm_input_afinfo *afinfo); int xfrm_input_unregister_afinfo(const struct xfrm_input_afinfo *afinfo); void xfrm_flush_gc(void); void xfrm_state_delete_tunnel(struct xfrm_state *x); struct xfrm_type { char *description; struct module *owner; u8 proto; u8 flags; #define XFRM_TYPE_NON_FRAGMENT 1 #define XFRM_TYPE_REPLAY_PROT 2 #define XFRM_TYPE_LOCAL_COADDR 4 #define XFRM_TYPE_REMOTE_COADDR 8 int (*init_state)(struct xfrm_state *x); void (*destructor)(struct xfrm_state *); int (*input)(struct xfrm_state *, struct sk_buff *skb); int (*output)(struct xfrm_state *, struct sk_buff *pskb); int (*reject)(struct xfrm_state *, struct sk_buff *, const struct flowi *); int (*hdr_offset)(struct xfrm_state *, struct sk_buff *, u8 **); }; int xfrm_register_type(const struct xfrm_type *type, unsigned short family); void xfrm_unregister_type(const struct xfrm_type *type, unsigned short family); struct xfrm_type_offload { char *description; struct module *owner; u8 proto; void (*encap)(struct xfrm_state *, struct sk_buff *pskb); int (*input_tail)(struct xfrm_state *x, struct sk_buff *skb); int (*xmit)(struct xfrm_state *, struct sk_buff *pskb, netdev_features_t features); }; int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family); void xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family); static inline int xfrm_af2proto(unsigned int family) { switch(family) { case AF_INET: return IPPROTO_IPIP; case AF_INET6: return IPPROTO_IPV6; default: return 0; } } static inline const struct xfrm_mode *xfrm_ip2inner_mode(struct xfrm_state *x, int ipproto) { if ((ipproto == IPPROTO_IPIP && x->props.family == AF_INET) || (ipproto == IPPROTO_IPV6 && x->props.family == AF_INET6)) return &x->inner_mode; else return &x->inner_mode_iaf; } struct xfrm_tmpl { /* id in template is interpreted as: * daddr - destination of tunnel, may be zero for transport mode. * spi - zero to acquire spi. Not zero if spi is static, then * daddr must be fixed too. * proto - AH/ESP/IPCOMP */ struct xfrm_id id; /* Source address of tunnel. Ignored, if it is not a tunnel. */ xfrm_address_t saddr; unsigned short encap_family; u32 reqid; /* Mode: transport, tunnel etc. */ u8 mode; /* Sharing mode: unique, this session only, this user only etc. */ u8 share; /* May skip this transfomration if no SA is found */ u8 optional; /* Skip aalgos/ealgos/calgos checks. */ u8 allalgs; /* Bit mask of algos allowed for acquisition */ u32 aalgos; u32 ealgos; u32 calgos; }; #define XFRM_MAX_DEPTH 6 #define XFRM_MAX_OFFLOAD_DEPTH 1 struct xfrm_policy_walk_entry { struct list_head all; u8 dead; }; struct xfrm_policy_walk { struct xfrm_policy_walk_entry walk; u8 type; u32 seq; }; struct xfrm_policy_queue { struct sk_buff_head hold_queue; struct timer_list hold_timer; unsigned long timeout; }; struct xfrm_policy { possible_net_t xp_net; struct hlist_node bydst; struct hlist_node byidx; /* This lock only affects elements except for entry. */ rwlock_t lock; refcount_t refcnt; u32 pos; struct timer_list timer; atomic_t genid; u32 priority; u32 index; u32 if_id; struct xfrm_mark mark; struct xfrm_selector selector; struct xfrm_lifetime_cfg lft; struct xfrm_lifetime_cur curlft; struct xfrm_policy_walk_entry walk; struct xfrm_policy_queue polq; bool bydst_reinsert; u8 type; u8 action; u8 flags; u8 xfrm_nr; u16 family; struct xfrm_sec_ctx *security; struct xfrm_tmpl xfrm_vec[XFRM_MAX_DEPTH]; struct hlist_node bydst_inexact_list; struct rcu_head rcu; }; static inline struct net *xp_net(const struct xfrm_policy *xp) { return read_pnet(&xp->xp_net); } struct xfrm_kmaddress { xfrm_address_t local; xfrm_address_t remote; u32 reserved; u16 family; }; struct xfrm_migrate { xfrm_address_t old_daddr; xfrm_address_t old_saddr; xfrm_address_t new_daddr; xfrm_address_t new_saddr; u8 proto; u8 mode; u16 reserved; u32 reqid; u16 old_family; u16 new_family; }; #define XFRM_KM_TIMEOUT 30 /* what happened */ #define XFRM_REPLAY_UPDATE XFRM_AE_CR #define XFRM_REPLAY_TIMEOUT XFRM_AE_CE /* default aevent timeout in units of 100ms */ #define XFRM_AE_ETIME 10 /* Async Event timer multiplier */ #define XFRM_AE_ETH_M 10 /* default seq threshold size */ #define XFRM_AE_SEQT_SIZE 2 struct xfrm_mgr { struct list_head list; int (*notify)(struct xfrm_state *x, const struct km_event *c); int (*acquire)(struct xfrm_state *x, struct xfrm_tmpl *, struct xfrm_policy *xp); struct xfrm_policy *(*compile_policy)(struct sock *sk, int opt, u8 *data, int len, int *dir); int (*new_mapping)(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport); int (*notify_policy)(struct xfrm_policy *x, int dir, const struct km_event *c); int (*report)(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr); int (*migrate)(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_bundles, const struct xfrm_kmaddress *k, const struct xfrm_encap_tmpl *encap); bool (*is_alive)(const struct km_event *c); }; int xfrm_register_km(struct xfrm_mgr *km); int xfrm_unregister_km(struct xfrm_mgr *km); struct xfrm_tunnel_skb_cb { union { struct inet_skb_parm h4; struct inet6_skb_parm h6; } header; union { struct ip_tunnel *ip4; struct ip6_tnl *ip6; } tunnel; }; #define XFRM_TUNNEL_SKB_CB(__skb) ((struct xfrm_tunnel_skb_cb *)&((__skb)->cb[0])) /* * This structure is used for the duration where packets are being * transformed by IPsec. As soon as the packet leaves IPsec the * area beyond the generic IP part may be overwritten. */ struct xfrm_skb_cb { struct xfrm_tunnel_skb_cb header; /* Sequence number for replay protection. */ union { struct { __u32 low; __u32 hi; } output; struct { __be32 low; __be32 hi; } input; } seq; }; #define XFRM_SKB_CB(__skb) ((struct xfrm_skb_cb *)&((__skb)->cb[0])) /* * This structure is used by the afinfo prepare_input/prepare_output functions * to transmit header information to the mode input/output functions. */ struct xfrm_mode_skb_cb { struct xfrm_tunnel_skb_cb header; /* Copied from header for IPv4, always set to zero and DF for IPv6. */ __be16 id; __be16 frag_off; /* IP header length (excluding options or extension headers). */ u8 ihl; /* TOS for IPv4, class for IPv6. */ u8 tos; /* TTL for IPv4, hop limitfor IPv6. */ u8 ttl; /* Protocol for IPv4, NH for IPv6. */ u8 protocol; /* Option length for IPv4, zero for IPv6. */ u8 optlen; /* Used by IPv6 only, zero for IPv4. */ u8 flow_lbl[3]; }; #define XFRM_MODE_SKB_CB(__skb) ((struct xfrm_mode_skb_cb *)&((__skb)->cb[0])) /* * This structure is used by the input processing to locate the SPI and * related information. */ struct xfrm_spi_skb_cb { struct xfrm_tunnel_skb_cb header; unsigned int daddroff; unsigned int family; __be32 seq; }; #define XFRM_SPI_SKB_CB(__skb) ((struct xfrm_spi_skb_cb *)&((__skb)->cb[0])) #ifdef CONFIG_AUDITSYSCALL static inline struct audit_buffer *xfrm_audit_start(const char *op) { struct audit_buffer *audit_buf = NULL; if (audit_enabled == AUDIT_OFF) return NULL; audit_buf = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_MAC_IPSEC_EVENT); if (audit_buf == NULL) return NULL; audit_log_format(audit_buf, "op=%s", op); return audit_buf; } static inline void xfrm_audit_helper_usrinfo(bool task_valid, struct audit_buffer *audit_buf) { const unsigned int auid = from_kuid(&init_user_ns, task_valid ? audit_get_loginuid(current) : INVALID_UID); const unsigned int ses = task_valid ? audit_get_sessionid(current) : AUDIT_SID_UNSET; audit_log_format(audit_buf, " auid=%u ses=%u", auid, ses); audit_log_task_context(audit_buf); } void xfrm_audit_policy_add(struct xfrm_policy *xp, int result, bool task_valid); void xfrm_audit_policy_delete(struct xfrm_policy *xp, int result, bool task_valid); void xfrm_audit_state_add(struct xfrm_state *x, int result, bool task_valid); void xfrm_audit_state_delete(struct xfrm_state *x, int result, bool task_valid); void xfrm_audit_state_replay_overflow(struct xfrm_state *x, struct sk_buff *skb); void xfrm_audit_state_replay(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq); void xfrm_audit_state_notfound_simple(struct sk_buff *skb, u16 family); void xfrm_audit_state_notfound(struct sk_buff *skb, u16 family, __be32 net_spi, __be32 net_seq); void xfrm_audit_state_icvfail(struct xfrm_state *x, struct sk_buff *skb, u8 proto); #else static inline void xfrm_audit_policy_add(struct xfrm_policy *xp, int result, bool task_valid) { } static inline void xfrm_audit_policy_delete(struct xfrm_policy *xp, int result, bool task_valid) { } static inline void xfrm_audit_state_add(struct xfrm_state *x, int result, bool task_valid) { } static inline void xfrm_audit_state_delete(struct xfrm_state *x, int result, bool task_valid) { } static inline void xfrm_audit_state_replay_overflow(struct xfrm_state *x, struct sk_buff *skb) { } static inline void xfrm_audit_state_replay(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq) { } static inline void xfrm_audit_state_notfound_simple(struct sk_buff *skb, u16 family) { } static inline void xfrm_audit_state_notfound(struct sk_buff *skb, u16 family, __be32 net_spi, __be32 net_seq) { } static inline void xfrm_audit_state_icvfail(struct xfrm_state *x, struct sk_buff *skb, u8 proto) { } #endif /* CONFIG_AUDITSYSCALL */ static inline void xfrm_pol_hold(struct xfrm_policy *policy) { if (likely(policy != NULL)) refcount_inc(&policy->refcnt); } void xfrm_policy_destroy(struct xfrm_policy *policy); static inline void xfrm_pol_put(struct xfrm_policy *policy) { if (refcount_dec_and_test(&policy->refcnt)) xfrm_policy_destroy(policy); } static inline void xfrm_pols_put(struct xfrm_policy **pols, int npols) { int i; for (i = npols - 1; i >= 0; --i) xfrm_pol_put(pols[i]); } void __xfrm_state_destroy(struct xfrm_state *, bool); static inline void __xfrm_state_put(struct xfrm_state *x) { refcount_dec(&x->refcnt); } static inline void xfrm_state_put(struct xfrm_state *x) { if (refcount_dec_and_test(&x->refcnt)) __xfrm_state_destroy(x, false); } static inline void xfrm_state_put_sync(struct xfrm_state *x) { if (refcount_dec_and_test(&x->refcnt)) __xfrm_state_destroy(x, true); } static inline void xfrm_state_hold(struct xfrm_state *x) { refcount_inc(&x->refcnt); } static inline bool addr_match(const void *token1, const void *token2, unsigned int prefixlen) { const __be32 *a1 = token1; const __be32 *a2 = token2; unsigned int pdw; unsigned int pbi; pdw = prefixlen >> 5; /* num of whole u32 in prefix */ pbi = prefixlen & 0x1f; /* num of bits in incomplete u32 in prefix */ if (pdw) if (memcmp(a1, a2, pdw << 2)) return false; if (pbi) { __be32 mask; mask = htonl((0xffffffff) << (32 - pbi)); if ((a1[pdw] ^ a2[pdw]) & mask) return false; } return true; } static inline bool addr4_match(__be32 a1, __be32 a2, u8 prefixlen) { /* C99 6.5.7 (3): u32 << 32 is undefined behaviour */ if (sizeof(long) == 4 && prefixlen == 0) return true; return !((a1 ^ a2) & htonl(~0UL << (32 - prefixlen))); } static __inline__ __be16 xfrm_flowi_sport(const struct flowi *fl, const union flowi_uli *uli) { __be16 port; switch(fl->flowi_proto) { case IPPROTO_TCP: case IPPROTO_UDP: case IPPROTO_UDPLITE: case IPPROTO_SCTP: port = uli->ports.sport; break; case IPPROTO_ICMP: case IPPROTO_ICMPV6: port = htons(uli->icmpt.type); break; case IPPROTO_MH: port = htons(uli->mht.type); break; case IPPROTO_GRE: port = htons(ntohl(uli->gre_key) >> 16); break; default: port = 0; /*XXX*/ } return port; } static __inline__ __be16 xfrm_flowi_dport(const struct flowi *fl, const union flowi_uli *uli) { __be16 port; switch(fl->flowi_proto) { case IPPROTO_TCP: case IPPROTO_UDP: case IPPROTO_UDPLITE: case IPPROTO_SCTP: port = uli->ports.dport; break; case IPPROTO_ICMP: case IPPROTO_ICMPV6: port = htons(uli->icmpt.code); break; case IPPROTO_GRE: port = htons(ntohl(uli->gre_key) & 0xffff); break; default: port = 0; /*XXX*/ } return port; } bool xfrm_selector_match(const struct xfrm_selector *sel, const struct flowi *fl, unsigned short family); #ifdef CONFIG_SECURITY_NETWORK_XFRM /* If neither has a context --> match * Otherwise, both must have a context and the sids, doi, alg must match */ static inline bool xfrm_sec_ctx_match(struct xfrm_sec_ctx *s1, struct xfrm_sec_ctx *s2) { return ((!s1 && !s2) || (s1 && s2 && (s1->ctx_sid == s2->ctx_sid) && (s1->ctx_doi == s2->ctx_doi) && (s1->ctx_alg == s2->ctx_alg))); } #else static inline bool xfrm_sec_ctx_match(struct xfrm_sec_ctx *s1, struct xfrm_sec_ctx *s2) { return true; } #endif /* A struct encoding bundle of transformations to apply to some set of flow. * * xdst->child points to the next element of bundle. * dst->xfrm points to an instanse of transformer. * * Due to unfortunate limitations of current routing cache, which we * have no time to fix, it mirrors struct rtable and bound to the same * routing key, including saddr,daddr. However, we can have many of * bundles differing by session id. All the bundles grow from a parent * policy rule. */ struct xfrm_dst { union { struct dst_entry dst; struct rtable rt; struct rt6_info rt6; } u; struct dst_entry *route; struct dst_entry *child; struct dst_entry *path; struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; int num_pols, num_xfrms; u32 xfrm_genid; u32 policy_genid; u32 route_mtu_cached; u32 child_mtu_cached; u32 route_cookie; u32 path_cookie; }; static inline struct dst_entry *xfrm_dst_path(const struct dst_entry *dst) { #ifdef CONFIG_XFRM if (dst->xfrm || (dst->flags & DST_XFRM_QUEUE)) { const struct xfrm_dst *xdst = (const struct xfrm_dst *) dst; return xdst->path; } #endif return (struct dst_entry *) dst; } static inline struct dst_entry *xfrm_dst_child(const struct dst_entry *dst) { #ifdef CONFIG_XFRM if (dst->xfrm || (dst->flags & DST_XFRM_QUEUE)) { struct xfrm_dst *xdst = (struct xfrm_dst *) dst; return xdst->child; } #endif return NULL; } #ifdef CONFIG_XFRM static inline void xfrm_dst_set_child(struct xfrm_dst *xdst, struct dst_entry *child) { xdst->child = child; } static inline void xfrm_dst_destroy(struct xfrm_dst *xdst) { xfrm_pols_put(xdst->pols, xdst->num_pols); dst_release(xdst->route); if (likely(xdst->u.dst.xfrm)) xfrm_state_put(xdst->u.dst.xfrm); } #endif void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev); struct xfrm_if_parms { int link; /* ifindex of underlying L2 interface */ u32 if_id; /* interface identifyer */ }; struct xfrm_if { struct xfrm_if __rcu *next; /* next interface in list */ struct net_device *dev; /* virtual device associated with interface */ struct net *net; /* netns for packet i/o */ struct xfrm_if_parms p; /* interface parms */ struct gro_cells gro_cells; }; struct xfrm_offload { /* Output sequence number for replay protection on offloading. */ struct { __u32 low; __u32 hi; } seq; __u32 flags; #define SA_DELETE_REQ 1 #define CRYPTO_DONE 2 #define CRYPTO_NEXT_DONE 4 #define CRYPTO_FALLBACK 8 #define XFRM_GSO_SEGMENT 16 #define XFRM_GRO 32 #define XFRM_ESP_NO_TRAILER 64 #define XFRM_DEV_RESUME 128 #define XFRM_XMIT 256 __u32 status; #define CRYPTO_SUCCESS 1 #define CRYPTO_GENERIC_ERROR 2 #define CRYPTO_TRANSPORT_AH_AUTH_FAILED 4 #define CRYPTO_TRANSPORT_ESP_AUTH_FAILED 8 #define CRYPTO_TUNNEL_AH_AUTH_FAILED 16 #define CRYPTO_TUNNEL_ESP_AUTH_FAILED 32 #define CRYPTO_INVALID_PACKET_SYNTAX 64 #define CRYPTO_INVALID_PROTOCOL 128 __u8 proto; }; struct sec_path { int len; int olen; struct xfrm_state *xvec[XFRM_MAX_DEPTH]; struct xfrm_offload ovec[XFRM_MAX_OFFLOAD_DEPTH]; }; struct sec_path *secpath_set(struct sk_buff *skb); static inline void secpath_reset(struct sk_buff *skb) { #ifdef CONFIG_XFRM skb_ext_del(skb, SKB_EXT_SEC_PATH); #endif } static inline int xfrm_addr_any(const xfrm_address_t *addr, unsigned short family) { switch (family) { case AF_INET: return addr->a4 == 0; case AF_INET6: return ipv6_addr_any(&addr->in6); } return 0; } static inline int __xfrm4_state_addr_cmp(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x) { return (tmpl->saddr.a4 && tmpl->saddr.a4 != x->props.saddr.a4); } static inline int __xfrm6_state_addr_cmp(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x) { return (!ipv6_addr_any((struct in6_addr*)&tmpl->saddr) && !ipv6_addr_equal((struct in6_addr *)&tmpl->saddr, (struct in6_addr*)&x->props.saddr)); } static inline int xfrm_state_addr_cmp(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, unsigned short family) { switch (family) { case AF_INET: return __xfrm4_state_addr_cmp(tmpl, x); case AF_INET6: return __xfrm6_state_addr_cmp(tmpl, x); } return !0; } #ifdef CONFIG_XFRM int __xfrm_policy_check(struct sock *, int dir, struct sk_buff *skb, unsigned short family); static inline int __xfrm_policy_check2(struct sock *sk, int dir, struct sk_buff *skb, unsigned int family, int reverse) { struct net *net = dev_net(skb->dev); int ndir = dir | (reverse ? XFRM_POLICY_MASK + 1 : 0); if (sk && sk->sk_policy[XFRM_POLICY_IN]) return __xfrm_policy_check(sk, ndir, skb, family); return (!net->xfrm.policy_count[dir] && !secpath_exists(skb)) || (skb_dst(skb) && (skb_dst(skb)->flags & DST_NOPOLICY)) || __xfrm_policy_check(sk, ndir, skb, family); } static inline int xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, unsigned short family) { return __xfrm_policy_check2(sk, dir, skb, family, 0); } static inline int xfrm4_policy_check(struct sock *sk, int dir, struct sk_buff *skb) { return xfrm_policy_check(sk, dir, skb, AF_INET); } static inline int xfrm6_policy_check(struct sock *sk, int dir, struct sk_buff *skb) { return xfrm_policy_check(sk, dir, skb, AF_INET6); } static inline int xfrm4_policy_check_reverse(struct sock *sk, int dir, struct sk_buff *skb) { return __xfrm_policy_check2(sk, dir, skb, AF_INET, 1); } static inline int xfrm6_policy_check_reverse(struct sock *sk, int dir, struct sk_buff *skb) { return __xfrm_policy_check2(sk, dir, skb, AF_INET6, 1); } int __xfrm_decode_session(struct sk_buff *skb, struct flowi *fl, unsigned int family, int reverse); static inline int xfrm_decode_session(struct sk_buff *skb, struct flowi *fl, unsigned int family) { return __xfrm_decode_session(skb, fl, family, 0); } static inline int xfrm_decode_session_reverse(struct sk_buff *skb, struct flowi *fl, unsigned int family) { return __xfrm_decode_session(skb, fl, family, 1); } int __xfrm_route_forward(struct sk_buff *skb, unsigned short family); static inline int xfrm_route_forward(struct sk_buff *skb, unsigned short family) { struct net *net = dev_net(skb->dev); return !net->xfrm.policy_count[XFRM_POLICY_OUT] || (skb_dst(skb)->flags & DST_NOXFRM) || __xfrm_route_forward(skb, family); } static inline int xfrm4_route_forward(struct sk_buff *skb) { return xfrm_route_forward(skb, AF_INET); } static inline int xfrm6_route_forward(struct sk_buff *skb) { return xfrm_route_forward(skb, AF_INET6); } int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk); static inline int xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { sk->sk_policy[0] = NULL; sk->sk_policy[1] = NULL; if (unlikely(osk->sk_policy[0] || osk->sk_policy[1])) return __xfrm_sk_clone_policy(sk, osk); return 0; } int xfrm_policy_delete(struct xfrm_policy *pol, int dir); static inline void xfrm_sk_free_policy(struct sock *sk) { struct xfrm_policy *pol; pol = rcu_dereference_protected(sk->sk_policy[0], 1); if (unlikely(pol != NULL)) { xfrm_policy_delete(pol, XFRM_POLICY_MAX); sk->sk_policy[0] = NULL; } pol = rcu_dereference_protected(sk->sk_policy[1], 1); if (unlikely(pol != NULL)) { xfrm_policy_delete(pol, XFRM_POLICY_MAX+1); sk->sk_policy[1] = NULL; } } #else static inline void xfrm_sk_free_policy(struct sock *sk) {} static inline int xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { return 0; } static inline int xfrm6_route_forward(struct sk_buff *skb) { return 1; } static inline int xfrm4_route_forward(struct sk_buff *skb) { return 1; } static inline int xfrm6_policy_check(struct sock *sk, int dir, struct sk_buff *skb) { return 1; } static inline int xfrm4_policy_check(struct sock *sk, int dir, struct sk_buff *skb) { return 1; } static inline int xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, unsigned short family) { return 1; } static inline int xfrm_decode_session_reverse(struct sk_buff *skb, struct flowi *fl, unsigned int family) { return -ENOSYS; } static inline int xfrm4_policy_check_reverse(struct sock *sk, int dir, struct sk_buff *skb) { return 1; } static inline int xfrm6_policy_check_reverse(struct sock *sk, int dir, struct sk_buff *skb) { return 1; } #endif static __inline__ xfrm_address_t *xfrm_flowi_daddr(const struct flowi *fl, unsigned short family) { switch (family){ case AF_INET: return (xfrm_address_t *)&fl->u.ip4.daddr; case AF_INET6: return (xfrm_address_t *)&fl->u.ip6.daddr; } return NULL; } static __inline__ xfrm_address_t *xfrm_flowi_saddr(const struct flowi *fl, unsigned short family) { switch (family){ case AF_INET: return (xfrm_address_t *)&fl->u.ip4.saddr; case AF_INET6: return (xfrm_address_t *)&fl->u.ip6.saddr; } return NULL; } static __inline__ void xfrm_flowi_addr_get(const struct flowi *fl, xfrm_address_t *saddr, xfrm_address_t *daddr, unsigned short family) { switch(family) { case AF_INET: memcpy(&saddr->a4, &fl->u.ip4.saddr, sizeof(saddr->a4)); memcpy(&daddr->a4, &fl->u.ip4.daddr, sizeof(daddr->a4)); break; case AF_INET6: saddr->in6 = fl->u.ip6.saddr; daddr->in6 = fl->u.ip6.daddr; break; } } static __inline__ int __xfrm4_state_addr_check(const struct xfrm_state *x, const xfrm_address_t *daddr, const xfrm_address_t *saddr) { if (daddr->a4 == x->id.daddr.a4 && (saddr->a4 == x->props.saddr.a4 || !saddr->a4 || !x->props.saddr.a4)) return 1; return 0; } static __inline__ int __xfrm6_state_addr_check(const struct xfrm_state *x, const xfrm_address_t *daddr, const xfrm_address_t *saddr) { if (ipv6_addr_equal((struct in6_addr *)daddr, (struct in6_addr *)&x->id.daddr) && (ipv6_addr_equal((struct in6_addr *)saddr, (struct in6_addr *)&x->props.saddr) || ipv6_addr_any((struct in6_addr *)saddr) || ipv6_addr_any((struct in6_addr *)&x->props.saddr))) return 1; return 0; } static __inline__ int xfrm_state_addr_check(const struct xfrm_state *x, const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family) { switch (family) { case AF_INET: return __xfrm4_state_addr_check(x, daddr, saddr); case AF_INET6: return __xfrm6_state_addr_check(x, daddr, saddr); } return 0; } static __inline__ int xfrm_state_addr_flow_check(const struct xfrm_state *x, const struct flowi *fl, unsigned short family) { switch (family) { case AF_INET: return __xfrm4_state_addr_check(x, (const xfrm_address_t *)&fl->u.ip4.daddr, (const xfrm_address_t *)&fl->u.ip4.saddr); case AF_INET6: return __xfrm6_state_addr_check(x, (const xfrm_address_t *)&fl->u.ip6.daddr, (const xfrm_address_t *)&fl->u.ip6.saddr); } return 0; } static inline int xfrm_state_kern(const struct xfrm_state *x) { return atomic_read(&x->tunnel_users); } static inline bool xfrm_id_proto_valid(u8 proto) { switch (proto) { case IPPROTO_AH: case IPPROTO_ESP: case IPPROTO_COMP: #if IS_ENABLED(CONFIG_IPV6) case IPPROTO_ROUTING: case IPPROTO_DSTOPTS: #endif return true; default: return false; } } /* IPSEC_PROTO_ANY only matches 3 IPsec protocols, 0 could match all. */ static inline int xfrm_id_proto_match(u8 proto, u8 userproto) { return (!userproto || proto == userproto || (userproto == IPSEC_PROTO_ANY && (proto == IPPROTO_AH || proto == IPPROTO_ESP || proto == IPPROTO_COMP))); } /* * xfrm algorithm information */ struct xfrm_algo_aead_info { char *geniv; u16 icv_truncbits; }; struct xfrm_algo_auth_info { u16 icv_truncbits; u16 icv_fullbits; }; struct xfrm_algo_encr_info { char *geniv; u16 blockbits; u16 defkeybits; }; struct xfrm_algo_comp_info { u16 threshold; }; struct xfrm_algo_desc { char *name; char *compat; u8 available:1; u8 pfkey_supported:1; union { struct xfrm_algo_aead_info aead; struct xfrm_algo_auth_info auth; struct xfrm_algo_encr_info encr; struct xfrm_algo_comp_info comp; } uinfo; struct sadb_alg desc; }; /* XFRM protocol handlers. */ struct xfrm4_protocol { int (*handler)(struct sk_buff *skb); int (*input_handler)(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); int (*cb_handler)(struct sk_buff *skb, int err); int (*err_handler)(struct sk_buff *skb, u32 info); struct xfrm4_protocol __rcu *next; int priority; }; struct xfrm6_protocol { int (*handler)(struct sk_buff *skb); int (*input_handler)(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); int (*cb_handler)(struct sk_buff *skb, int err); int (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info); struct xfrm6_protocol __rcu *next; int priority; }; /* XFRM tunnel handlers. */ struct xfrm_tunnel { int (*handler)(struct sk_buff *skb); int (*cb_handler)(struct sk_buff *skb, int err); int (*err_handler)(struct sk_buff *skb, u32 info); struct xfrm_tunnel __rcu *next; int priority; }; struct xfrm6_tunnel { int (*handler)(struct sk_buff *skb); int (*cb_handler)(struct sk_buff *skb, int err); int (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info); struct xfrm6_tunnel __rcu *next; int priority; }; void xfrm_init(void); void xfrm4_init(void); int xfrm_state_init(struct net *net); void xfrm_state_fini(struct net *net); void xfrm4_state_init(void); void xfrm4_protocol_init(void); #ifdef CONFIG_XFRM int xfrm6_init(void); void xfrm6_fini(void); int xfrm6_state_init(void); void xfrm6_state_fini(void); int xfrm6_protocol_init(void); void xfrm6_protocol_fini(void); #else static inline int xfrm6_init(void) { return 0; } static inline void xfrm6_fini(void) { ; } #endif #ifdef CONFIG_XFRM_STATISTICS int xfrm_proc_init(struct net *net); void xfrm_proc_fini(struct net *net); #endif int xfrm_sysctl_init(struct net *net); #ifdef CONFIG_SYSCTL void xfrm_sysctl_fini(struct net *net); #else static inline void xfrm_sysctl_fini(struct net *net) { } #endif void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto, struct xfrm_address_filter *filter); int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, int (*func)(struct xfrm_state *, int, void*), void *); void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net); struct xfrm_state *xfrm_state_alloc(struct net *net); void xfrm_state_free(struct xfrm_state *x); struct xfrm_state *xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, const struct flowi *fl, struct xfrm_tmpl *tmpl, struct xfrm_policy *pol, int *err, unsigned short family, u32 if_id); struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id, xfrm_address_t *daddr, xfrm_address_t *saddr, unsigned short family, u8 mode, u8 proto, u32 reqid); struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi, unsigned short family); int xfrm_state_check_expire(struct xfrm_state *x); void xfrm_state_insert(struct xfrm_state *x); int xfrm_state_add(struct xfrm_state *x); int xfrm_state_update(struct xfrm_state *x); struct xfrm_state *xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family); struct xfrm_state *xfrm_state_lookup_byaddr(struct net *net, u32 mark, const xfrm_address_t *daddr, const xfrm_address_t *saddr, u8 proto, unsigned short family); #ifdef CONFIG_XFRM_SUB_POLICY void xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n, unsigned short family); void xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n, unsigned short family); #else static inline void xfrm_tmpl_sort(struct xfrm_tmpl **d, struct xfrm_tmpl **s, int n, unsigned short family) { } static inline void xfrm_state_sort(struct xfrm_state **d, struct xfrm_state **s, int n, unsigned short family) { } #endif struct xfrmk_sadinfo { u32 sadhcnt; /* current hash bkts */ u32 sadhmcnt; /* max allowed hash bkts */ u32 sadcnt; /* current running count */ }; struct xfrmk_spdinfo { u32 incnt; u32 outcnt; u32 fwdcnt; u32 inscnt; u32 outscnt; u32 fwdscnt; u32 spdhcnt; u32 spdhmcnt; }; struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq); int xfrm_state_delete(struct xfrm_state *x); int xfrm_state_flush(struct net *net, u8 proto, bool task_valid, bool sync); int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid); void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si); void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si); u32 xfrm_replay_seqhi(struct xfrm_state *x, __be32 net_seq); int xfrm_init_replay(struct xfrm_state *x); u32 __xfrm_state_mtu(struct xfrm_state *x, int mtu); u32 xfrm_state_mtu(struct xfrm_state *x, int mtu); int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload); int xfrm_init_state(struct xfrm_state *x); int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); int xfrm_input_resume(struct sk_buff *skb, int nexthdr); int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb, int (*finish)(struct net *, struct sock *, struct sk_buff *)); int xfrm_trans_queue(struct sk_buff *skb, int (*finish)(struct net *, struct sock *, struct sk_buff *)); int xfrm_output_resume(struct sock *sk, struct sk_buff *skb, int err); int xfrm_output(struct sock *sk, struct sk_buff *skb); #if IS_ENABLED(CONFIG_NET_PKTGEN) int pktgen_xfrm_outer_mode_output(struct xfrm_state *x, struct sk_buff *skb); #endif void xfrm_local_error(struct sk_buff *skb, int mtu); int xfrm4_extract_input(struct xfrm_state *x, struct sk_buff *skb); int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); int xfrm4_transport_finish(struct sk_buff *skb, int async); int xfrm4_rcv(struct sk_buff *skb); int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq); static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi) { XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL; XFRM_SPI_SKB_CB(skb)->family = AF_INET; XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr); return xfrm_input(skb, nexthdr, spi, 0); } int xfrm4_output(struct net *net, struct sock *sk, struct sk_buff *skb); int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb); int xfrm4_protocol_register(struct xfrm4_protocol *handler, unsigned char protocol); int xfrm4_protocol_deregister(struct xfrm4_protocol *handler, unsigned char protocol); int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family); int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler, unsigned short family); void xfrm4_local_error(struct sk_buff *skb, u32 mtu); int xfrm6_extract_input(struct xfrm_state *x, struct sk_buff *skb); int xfrm6_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi, struct ip6_tnl *t); int xfrm6_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type); int xfrm6_transport_finish(struct sk_buff *skb, int async); int xfrm6_rcv_tnl(struct sk_buff *skb, struct ip6_tnl *t); int xfrm6_rcv(struct sk_buff *skb); int xfrm6_input_addr(struct sk_buff *skb, xfrm_address_t *daddr, xfrm_address_t *saddr, u8 proto); void xfrm6_local_error(struct sk_buff *skb, u32 mtu); int xfrm6_protocol_register(struct xfrm6_protocol *handler, unsigned char protocol); int xfrm6_protocol_deregister(struct xfrm6_protocol *handler, unsigned char protocol); int xfrm6_tunnel_register(struct xfrm6_tunnel *handler, unsigned short family); int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family); __be32 xfrm6_tunnel_alloc_spi(struct net *net, xfrm_address_t *saddr); __be32 xfrm6_tunnel_spi_lookup(struct net *net, const xfrm_address_t *saddr); int xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb); int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb); int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb, u8 **prevhdr); #ifdef CONFIG_XFRM void xfrm6_local_rxpmtu(struct sk_buff *skb, u32 mtu); int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb); int xfrm6_udp_encap_rcv(struct sock *sk, struct sk_buff *skb); int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen); #else static inline int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen) { return -ENOPROTOOPT; } #endif struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif, const xfrm_address_t *saddr, const xfrm_address_t *daddr, int family, u32 mark); struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp); void xfrm_policy_walk_init(struct xfrm_policy_walk *walk, u8 type); int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk, int (*func)(struct xfrm_policy *, int, int, void*), void *); void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net); int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl); struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, const struct xfrm_mark *mark, u32 if_id, u8 type, int dir, struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx, int delete, int *err); struct xfrm_policy *xfrm_policy_byid(struct net *net, const struct xfrm_mark *mark, u32 if_id, u8 type, int dir, u32 id, int delete, int *err); int xfrm_policy_flush(struct net *net, u8 type, bool task_valid); void xfrm_policy_hash_rebuild(struct net *net); u32 xfrm_get_acqseq(void); int verify_spi_info(u8 proto, u32 min, u32 max); int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi); struct xfrm_state *xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid, u32 if_id, u8 proto, const xfrm_address_t *daddr, const xfrm_address_t *saddr, int create, unsigned short family); int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol); #ifdef CONFIG_XFRM_MIGRATE int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_bundles, const struct xfrm_kmaddress *k, const struct xfrm_encap_tmpl *encap); struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net); struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, struct xfrm_migrate *m, struct xfrm_encap_tmpl *encap); int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_bundles, struct xfrm_kmaddress *k, struct net *net, struct xfrm_encap_tmpl *encap); #endif int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport); void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 portid); int km_report(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr); void xfrm_input_init(void); int xfrm_parse_spi(struct sk_buff *skb, u8 nexthdr, __be32 *spi, __be32 *seq); void xfrm_probe_algs(void); int xfrm_count_pfkey_auth_supported(void); int xfrm_count_pfkey_enc_supported(void); struct xfrm_algo_desc *xfrm_aalg_get_byidx(unsigned int idx); struct xfrm_algo_desc *xfrm_ealg_get_byidx(unsigned int idx); struct xfrm_algo_desc *xfrm_aalg_get_byid(int alg_id); struct xfrm_algo_desc *xfrm_ealg_get_byid(int alg_id); struct xfrm_algo_desc *xfrm_calg_get_byid(int alg_id); struct xfrm_algo_desc *xfrm_aalg_get_byname(const char *name, int probe); struct xfrm_algo_desc *xfrm_ealg_get_byname(const char *name, int probe); struct xfrm_algo_desc *xfrm_calg_get_byname(const char *name, int probe); struct xfrm_algo_desc *xfrm_aead_get_byname(const char *name, int icv_len, int probe); static inline bool xfrm6_addr_equal(const xfrm_address_t *a, const xfrm_address_t *b) { return ipv6_addr_equal((const struct in6_addr *)a, (const struct in6_addr *)b); } static inline bool xfrm_addr_equal(const xfrm_address_t *a, const xfrm_address_t *b, sa_family_t family) { switch (family) { default: case AF_INET: return ((__force u32)a->a4 ^ (__force u32)b->a4) == 0; case AF_INET6: return xfrm6_addr_equal(a, b); } } static inline int xfrm_policy_id2dir(u32 index) { return index & 7; } #ifdef CONFIG_XFRM static inline int xfrm_aevent_is_on(struct net *net) { struct sock *nlsk; int ret = 0; rcu_read_lock(); nlsk = rcu_dereference(net->xfrm.nlsk); if (nlsk) ret = netlink_has_listeners(nlsk, XFRMNLGRP_AEVENTS); rcu_read_unlock(); return ret; } static inline int xfrm_acquire_is_on(struct net *net) { struct sock *nlsk; int ret = 0; rcu_read_lock(); nlsk = rcu_dereference(net->xfrm.nlsk); if (nlsk) ret = netlink_has_listeners(nlsk, XFRMNLGRP_ACQUIRE); rcu_read_unlock(); return ret; } #endif static inline unsigned int aead_len(struct xfrm_algo_aead *alg) { return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); } static inline unsigned int xfrm_alg_len(const struct xfrm_algo *alg) { return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); } static inline unsigned int xfrm_alg_auth_len(const struct xfrm_algo_auth *alg) { return sizeof(*alg) + ((alg->alg_key_len + 7) / 8); } static inline unsigned int xfrm_replay_state_esn_len(struct xfrm_replay_state_esn *replay_esn) { return sizeof(*replay_esn) + replay_esn->bmp_len * sizeof(__u32); } #ifdef CONFIG_XFRM_MIGRATE static inline int xfrm_replay_clone(struct xfrm_state *x, struct xfrm_state *orig) { x->replay_esn = kmemdup(orig->replay_esn, xfrm_replay_state_esn_len(orig->replay_esn), GFP_KERNEL); if (!x->replay_esn) return -ENOMEM; x->preplay_esn = kmemdup(orig->preplay_esn, xfrm_replay_state_esn_len(orig->preplay_esn), GFP_KERNEL); if (!x->preplay_esn) return -ENOMEM; return 0; } static inline struct xfrm_algo_aead *xfrm_algo_aead_clone(struct xfrm_algo_aead *orig) { return kmemdup(orig, aead_len(orig), GFP_KERNEL); } static inline struct xfrm_algo *xfrm_algo_clone(struct xfrm_algo *orig) { return kmemdup(orig, xfrm_alg_len(orig), GFP_KERNEL); } static inline struct xfrm_algo_auth *xfrm_algo_auth_clone(struct xfrm_algo_auth *orig) { return kmemdup(orig, xfrm_alg_auth_len(orig), GFP_KERNEL); } static inline void xfrm_states_put(struct xfrm_state **states, int n) { int i; for (i = 0; i < n; i++) xfrm_state_put(*(states + i)); } static inline void xfrm_states_delete(struct xfrm_state **states, int n) { int i; for (i = 0; i < n; i++) xfrm_state_delete(*(states + i)); } #endif #ifdef CONFIG_XFRM static inline struct xfrm_state *xfrm_input_state(struct sk_buff *skb) { struct sec_path *sp = skb_sec_path(skb); return sp->xvec[sp->len - 1]; } #endif static inline struct xfrm_offload *xfrm_offload(struct sk_buff *skb) { #ifdef CONFIG_XFRM struct sec_path *sp = skb_sec_path(skb); if (!sp || !sp->olen || sp->len != sp->olen) return NULL; return &sp->ovec[sp->olen - 1]; #else return NULL; #endif } void __init xfrm_dev_init(void); #ifdef CONFIG_XFRM_OFFLOAD void xfrm_dev_resume(struct sk_buff *skb); void xfrm_dev_backlog(struct softnet_data *sd); struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features, bool *again); int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, struct xfrm_user_offload *xuo); bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x); static inline void xfrm_dev_state_advance_esn(struct xfrm_state *x) { struct xfrm_state_offload *xso = &x->xso; if (xso->dev && xso->dev->xfrmdev_ops->xdo_dev_state_advance_esn) xso->dev->xfrmdev_ops->xdo_dev_state_advance_esn(x); } static inline bool xfrm_dst_offload_ok(struct dst_entry *dst) { struct xfrm_state *x = dst->xfrm; struct xfrm_dst *xdst; if (!x || !x->type_offload) return false; xdst = (struct xfrm_dst *) dst; if (!x->xso.offload_handle && !xdst->child->xfrm) return true; if (x->xso.offload_handle && (x->xso.dev == xfrm_dst_path(dst)->dev) && !xdst->child->xfrm) return true; return false; } static inline void xfrm_dev_state_delete(struct xfrm_state *x) { struct xfrm_state_offload *xso = &x->xso; if (xso->dev) xso->dev->xfrmdev_ops->xdo_dev_state_delete(x); } static inline void xfrm_dev_state_free(struct xfrm_state *x) { struct xfrm_state_offload *xso = &x->xso; struct net_device *dev = xso->dev; if (dev && dev->xfrmdev_ops) { if (dev->xfrmdev_ops->xdo_dev_state_free) dev->xfrmdev_ops->xdo_dev_state_free(x); xso->dev = NULL; dev_put(dev); } } #else static inline void xfrm_dev_resume(struct sk_buff *skb) { } static inline void xfrm_dev_backlog(struct softnet_data *sd) { } static inline struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t features, bool *again) { return skb; } static inline int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, struct xfrm_user_offload *xuo) { return 0; } static inline void xfrm_dev_state_delete(struct xfrm_state *x) { } static inline void xfrm_dev_state_free(struct xfrm_state *x) { } static inline bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x) { return false; } static inline void xfrm_dev_state_advance_esn(struct xfrm_state *x) { } static inline bool xfrm_dst_offload_ok(struct dst_entry *dst) { return false; } #endif static inline int xfrm_mark_get(struct nlattr **attrs, struct xfrm_mark *m) { if (attrs[XFRMA_MARK]) memcpy(m, nla_data(attrs[XFRMA_MARK]), sizeof(struct xfrm_mark)); else m->v = m->m = 0; return m->v & m->m; } static inline int xfrm_mark_put(struct sk_buff *skb, const struct xfrm_mark *m) { int ret = 0; if (m->m | m->v) ret = nla_put(skb, XFRMA_MARK, sizeof(struct xfrm_mark), m); return ret; } static inline __u32 xfrm_smark_get(__u32 mark, struct xfrm_state *x) { struct xfrm_mark *m = &x->props.smark; return (m->v & m->m) | (mark & ~m->m); } static inline int xfrm_if_id_put(struct sk_buff *skb, __u32 if_id) { int ret = 0; if (if_id) ret = nla_put_u32(skb, XFRMA_IF_ID, if_id); return ret; } static inline int xfrm_tunnel_check(struct sk_buff *skb, struct xfrm_state *x, unsigned int family) { bool tunnel = false; switch(family) { case AF_INET: if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4) tunnel = true; break; case AF_INET6: if (XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6) tunnel = true; break; } if (tunnel && !(x->outer_mode.flags & XFRM_MODE_FLAG_TUNNEL)) return -EINVAL; return 0; } extern const int xfrm_msg_min[XFRM_NR_MSGTYPES]; extern const struct nla_policy xfrma_policy[XFRMA_MAX+1]; struct xfrm_translator { /* Allocate frag_list and put compat translation there */ int (*alloc_compat)(struct sk_buff *skb, const struct nlmsghdr *src); /* Allocate nlmsg with 64-bit translaton of received 32-bit message */ struct nlmsghdr *(*rcv_msg_compat)(const struct nlmsghdr *nlh, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack); /* Translate 32-bit user_policy from sockptr */ int (*xlate_user_policy_sockptr)(u8 **pdata32, int optlen); struct module *owner; }; #if IS_ENABLED(CONFIG_XFRM_USER_COMPAT) extern int xfrm_register_translator(struct xfrm_translator *xtr); extern int xfrm_unregister_translator(struct xfrm_translator *xtr); extern struct xfrm_translator *xfrm_get_translator(void); extern void xfrm_put_translator(struct xfrm_translator *xtr); #else static inline struct xfrm_translator *xfrm_get_translator(void) { return NULL; } static inline void xfrm_put_translator(struct xfrm_translator *xtr) { } #endif #if IS_ENABLED(CONFIG_IPV6) static inline bool xfrm6_local_dontfrag(const struct sock *sk) { int proto; if (!sk || sk->sk_family != AF_INET6) return false; proto = sk->sk_protocol; if (proto == IPPROTO_UDP || proto == IPPROTO_RAW) return inet6_sk(sk)->dontfrag; return false; } #endif #endif /* _NET_XFRM_H */
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __INCLUDE_LINUX_OOM_H #define __INCLUDE_LINUX_OOM_H #include <linux/sched/signal.h> #include <linux/types.h> #include <linux/nodemask.h> #include <uapi/linux/oom.h> #include <linux/sched/coredump.h> /* MMF_* */ #include <linux/mm.h> /* VM_FAULT* */ struct zonelist; struct notifier_block; struct mem_cgroup; struct task_struct; enum oom_constraint { CONSTRAINT_NONE, CONSTRAINT_CPUSET, CONSTRAINT_MEMORY_POLICY, CONSTRAINT_MEMCG, }; /* * Details of the page allocation that triggered the oom killer that are used to * determine what should be killed. */ struct oom_control { /* Used to determine cpuset */ struct zonelist *zonelist; /* Used to determine mempolicy */ nodemask_t *nodemask; /* Memory cgroup in which oom is invoked, or NULL for global oom */ struct mem_cgroup *memcg; /* Used to determine cpuset and node locality requirement */ const gfp_t gfp_mask; /* * order == -1 means the oom kill is required by sysrq, otherwise only * for display purposes. */ const int order; /* Used by oom implementation, do not set */ unsigned long totalpages; struct task_struct *chosen; long chosen_points; /* Used to print the constraint info. */ enum oom_constraint constraint; }; extern struct mutex oom_lock; extern struct mutex oom_adj_mutex; static inline void set_current_oom_origin(void) { current->signal->oom_flag_origin = true; } static inline void clear_current_oom_origin(void) { current->signal->oom_flag_origin = false; } static inline bool oom_task_origin(const struct task_struct *p) { return p->signal->oom_flag_origin; } static inline bool tsk_is_oom_victim(struct task_struct * tsk) { return tsk->signal->oom_mm; } /* * Use this helper if tsk->mm != mm and the victim mm needs a special * handling. This is guaranteed to stay true after once set. */ static inline bool mm_is_oom_victim(struct mm_struct *mm) { return test_bit(MMF_OOM_VICTIM, &mm->flags); } /* * Checks whether a page fault on the given mm is still reliable. * This is no longer true if the oom reaper started to reap the * address space which is reflected by MMF_UNSTABLE flag set in * the mm. At that moment any !shared mapping would lose the content * and could cause a memory corruption (zero pages instead of the * original content). * * User should call this before establishing a page table entry for * a !shared mapping and under the proper page table lock. * * Return 0 when the PF is safe VM_FAULT_SIGBUS otherwise. */ static inline vm_fault_t check_stable_address_space(struct mm_struct *mm) { if (unlikely(test_bit(MMF_UNSTABLE, &mm->flags))) return VM_FAULT_SIGBUS; return 0; } bool __oom_reap_task_mm(struct mm_struct *mm); long oom_badness(struct task_struct *p, unsigned long totalpages); extern bool out_of_memory(struct oom_control *oc); extern void exit_oom_victim(void); extern int register_oom_notifier(struct notifier_block *nb); extern int unregister_oom_notifier(struct notifier_block *nb); extern bool oom_killer_disable(signed long timeout); extern void oom_killer_enable(void); extern struct task_struct *find_lock_task_mm(struct task_struct *p); /* sysctls */ extern int sysctl_oom_dump_tasks; extern int sysctl_oom_kill_allocating_task; extern int sysctl_panic_on_oom; #endif /* _INCLUDE_LINUX_OOM_H */
1 1 1 1 1 1 1 1 1 1 1 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 // SPDX-License-Identifier: GPL-2.0-or-later /* * libata-core.c - helper library for ATA * * Copyright 2003-2004 Red Hat, Inc. All rights reserved. * Copyright 2003-2004 Jeff Garzik * * libata documentation is available via 'make {ps|pdf}docs', * as Documentation/driver-api/libata.rst * * Hardware documentation available from http://www.t13.org/ and * http://www.sata-io.org/ * * Standards documents from: * http://www.t13.org (ATA standards, PCI DMA IDE spec) * http://www.t10.org (SCSI MMC - for ATAPI MMC) * http://www.sata-io.org (SATA) * http://www.compactflash.org (CF) * http://www.qic.org (QIC157 - Tape and DSC) * http://www.ce-ata.org (CE-ATA: not supported) * * libata is essentially a library of internal helper functions for * low-level ATA host controller drivers. As such, the API/ABI is * likely to change as new drivers are added and updated. * Do not depend on ABI/API stability. */ #include <linux/kernel.h> #include <linux/module.h> #include <linux/pci.h> #include <linux/init.h> #include <linux/list.h> #include <linux/mm.h> #include <linux/spinlock.h> #include <linux/blkdev.h> #include <linux/delay.h> #include <linux/timer.h> #include <linux/time.h> #include <linux/interrupt.h> #include <linux/completion.h> #include <linux/suspend.h> #include <linux/workqueue.h> #include <linux/scatterlist.h> #include <linux/io.h> #include <linux/log2.h> #include <linux/slab.h> #include <linux/glob.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> #include <scsi/scsi_host.h> #include <linux/libata.h> #include <asm/byteorder.h> #include <asm/unaligned.h> #include <linux/cdrom.h> #include <linux/ratelimit.h> #include <linux/leds.h> #include <linux/pm_runtime.h> #include <linux/platform_device.h> #include <asm/setup.h> #define CREATE_TRACE_POINTS #include <trace/events/libata.h> #include "libata.h" #include "libata-transport.h" const struct ata_port_operations ata_base_port_ops = { .prereset = ata_std_prereset, .postreset = ata_std_postreset, .error_handler = ata_std_error_handler, .sched_eh = ata_std_sched_eh, .end_eh = ata_std_end_eh, }; const struct ata_port_operations sata_port_ops = { .inherits = &ata_base_port_ops, .qc_defer = ata_std_qc_defer, .hardreset = sata_std_hardreset, }; EXPORT_SYMBOL_GPL(sata_port_ops); static unsigned int ata_dev_init_params(struct ata_device *dev, u16 heads, u16 sectors); static unsigned int ata_dev_set_xfermode(struct ata_device *dev); static void ata_dev_xfermask(struct ata_device *dev); static unsigned long ata_dev_blacklisted(const struct ata_device *dev); atomic_t ata_print_id = ATOMIC_INIT(0); #ifdef CONFIG_ATA_FORCE struct ata_force_param { const char *name; u8 cbl; u8 spd_limit; unsigned long xfer_mask; unsigned int horkage_on; unsigned int horkage_off; u16 lflags; }; struct ata_force_ent { int port; int device; struct ata_force_param param; }; static struct ata_force_ent *ata_force_tbl; static int ata_force_tbl_size; static char ata_force_param_buf[COMMAND_LINE_SIZE] __initdata; /* param_buf is thrown away after initialization, disallow read */ module_param_string(force, ata_force_param_buf, sizeof(ata_force_param_buf), 0); MODULE_PARM_DESC(force, "Force ATA configurations including cable type, link speed and transfer mode (see Documentation/admin-guide/kernel-parameters.rst for details)"); #endif static int atapi_enabled = 1; module_param(atapi_enabled, int, 0444); MODULE_PARM_DESC(atapi_enabled, "Enable discovery of ATAPI devices (0=off, 1=on [default])"); static int atapi_dmadir = 0; module_param(atapi_dmadir, int, 0444); MODULE_PARM_DESC(atapi_dmadir, "Enable ATAPI DMADIR bridge support (0=off [default], 1=on)"); int atapi_passthru16 = 1; module_param(atapi_passthru16, int, 0444); MODULE_PARM_DESC(atapi_passthru16, "Enable ATA_16 passthru for ATAPI devices (0=off, 1=on [default])"); int libata_fua = 0; module_param_named(fua, libata_fua, int, 0444); MODULE_PARM_DESC(fua, "FUA support (0=off [default], 1=on)"); static int ata_ignore_hpa; module_param_named(ignore_hpa, ata_ignore_hpa, int, 0644); MODULE_PARM_DESC(ignore_hpa, "Ignore HPA limit (0=keep BIOS limits, 1=ignore limits, using full disk)"); static int libata_dma_mask = ATA_DMA_MASK_ATA|ATA_DMA_MASK_ATAPI|ATA_DMA_MASK_CFA; module_param_named(dma, libata_dma_mask, int, 0444); MODULE_PARM_DESC(dma, "DMA enable/disable (0x1==ATA, 0x2==ATAPI, 0x4==CF)"); static int ata_probe_timeout; module_param(ata_probe_timeout, int, 0444); MODULE_PARM_DESC(ata_probe_timeout, "Set ATA probing timeout (seconds)"); int libata_noacpi = 0; module_param_named(noacpi, libata_noacpi, int, 0444); MODULE_PARM_DESC(noacpi, "Disable the use of ACPI in probe/suspend/resume (0=off [default], 1=on)"); int libata_allow_tpm = 0; module_param_named(allow_tpm, libata_allow_tpm, int, 0444); MODULE_PARM_DESC(allow_tpm, "Permit the use of TPM commands (0=off [default], 1=on)"); static int atapi_an; module_param(atapi_an, int, 0444); MODULE_PARM_DESC(atapi_an, "Enable ATAPI AN media presence notification (0=0ff [default], 1=on)"); MODULE_AUTHOR("Jeff Garzik"); MODULE_DESCRIPTION("Library module for ATA devices"); MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_VERSION); static bool ata_sstatus_online(u32 sstatus) { return (sstatus & 0xf) == 0x3; } /** * ata_link_next - link iteration helper * @link: the previous link, NULL to start * @ap: ATA port containing links to iterate * @mode: iteration mode, one of ATA_LITER_* * * LOCKING: * Host lock or EH context. * * RETURNS: * Pointer to the next link. */ struct ata_link *ata_link_next(struct ata_link *link, struct ata_port *ap, enum ata_link_iter_mode mode) { BUG_ON(mode != ATA_LITER_EDGE && mode != ATA_LITER_PMP_FIRST && mode != ATA_LITER_HOST_FIRST); /* NULL link indicates start of iteration */ if (!link) switch (mode) { case ATA_LITER_EDGE: case ATA_LITER_PMP_FIRST: if (sata_pmp_attached(ap)) return ap->pmp_link; fallthrough; case ATA_LITER_HOST_FIRST: return &ap->link; } /* we just iterated over the host link, what's next? */ if (link == &ap->link) switch (mode) { case ATA_LITER_HOST_FIRST: if (sata_pmp_attached(ap)) return ap->pmp_link; fallthrough; case ATA_LITER_PMP_FIRST: if (unlikely(ap->slave_link)) return ap->slave_link; fallthrough; case ATA_LITER_EDGE: return NULL; } /* slave_link excludes PMP */ if (unlikely(link == ap->slave_link)) return NULL; /* we were over a PMP link */ if (++link < ap->pmp_link + ap->nr_pmp_links) return link; if (mode == ATA_LITER_PMP_FIRST) return &ap->link; return NULL; } EXPORT_SYMBOL_GPL(ata_link_next); /** * ata_dev_next - device iteration helper * @dev: the previous device, NULL to start * @link: ATA link containing devices to iterate * @mode: iteration mode, one of ATA_DITER_* * * LOCKING: * Host lock or EH context. * * RETURNS: * Pointer to the next device. */ struct ata_device *ata_dev_next(struct ata_device *dev, struct ata_link *link, enum ata_dev_iter_mode mode) { BUG_ON(mode != ATA_DITER_ENABLED && mode != ATA_DITER_ENABLED_REVERSE && mode != ATA_DITER_ALL && mode != ATA_DITER_ALL_REVERSE); /* NULL dev indicates start of iteration */ if (!dev) switch (mode) { case ATA_DITER_ENABLED: case ATA_DITER_ALL: dev = link->device; goto check; case ATA_DITER_ENABLED_REVERSE: case ATA_DITER_ALL_REVERSE: dev = link->device + ata_link_max_devices(link) - 1; goto check; } next: /* move to the next one */ switch (mode) { case ATA_DITER_ENABLED: case ATA_DITER_ALL: if (++dev < link->device + ata_link_max_devices(link)) goto check; return NULL; case ATA_DITER_ENABLED_REVERSE: case ATA_DITER_ALL_REVERSE: if (--dev >= link->device) goto check; return NULL; } check: if ((mode == ATA_DITER_ENABLED || mode == ATA_DITER_ENABLED_REVERSE) && !ata_dev_enabled(dev)) goto next; return dev; } EXPORT_SYMBOL_GPL(ata_dev_next); /** * ata_dev_phys_link - find physical link for a device * @dev: ATA device to look up physical link for * * Look up physical link which @dev is attached to. Note that * this is different from @dev->link only when @dev is on slave * link. For all other cases, it's the same as @dev->link. * * LOCKING: * Don't care. * * RETURNS: * Pointer to the found physical link. */ struct ata_link *ata_dev_phys_link(struct ata_device *dev) { struct ata_port *ap = dev->link->ap; if (!ap->slave_link) return dev->link; if (!dev->devno) return &ap->link; return ap->slave_link; } #ifdef CONFIG_ATA_FORCE /** * ata_force_cbl - force cable type according to libata.force * @ap: ATA port of interest * * Force cable type according to libata.force and whine about it. * The last entry which has matching port number is used, so it * can be specified as part of device force parameters. For * example, both "a:40c,1.00:udma4" and "1.00:40c,udma4" have the * same effect. * * LOCKING: * EH context. */ void ata_force_cbl(struct ata_port *ap) { int i; for (i = ata_force_tbl_size - 1; i >= 0; i--) { const struct ata_force_ent *fe = &ata_force_tbl[i]; if (fe->port != -1 && fe->port != ap->print_id) continue; if (fe->param.cbl == ATA_CBL_NONE) continue; ap->cbl = fe->param.cbl; ata_port_notice(ap, "FORCE: cable set to %s\n", fe->param.name); return; } } /** * ata_force_link_limits - force link limits according to libata.force * @link: ATA link of interest * * Force link flags and SATA spd limit according to libata.force * and whine about it. When only the port part is specified * (e.g. 1:), the limit applies to all links connected to both * the host link and all fan-out ports connected via PMP. If the * device part is specified as 0 (e.g. 1.00:), it specifies the * first fan-out link not the host link. Device number 15 always * points to the host link whether PMP is attached or not. If the * controller has slave link, device number 16 points to it. * * LOCKING: * EH context. */ static void ata_force_link_limits(struct ata_link *link) { bool did_spd = false; int linkno = link->pmp; int i; if (ata_is_host_link(link)) linkno += 15; for (i = ata_force_tbl_size - 1; i >= 0; i--) { const struct ata_force_ent *fe = &ata_force_tbl[i]; if (fe->port != -1 && fe->port != link->ap->print_id) continue; if (fe->device != -1 && fe->device != linkno) continue; /* only honor the first spd limit */ if (!did_spd && fe->param.spd_limit) { link->hw_sata_spd_limit = (1 << fe->param.spd_limit) - 1; ata_link_notice(link, "FORCE: PHY spd limit set to %s\n", fe->param.name); did_spd = true; } /* let lflags stack */ if (fe->param.lflags) { link->flags |= fe->param.lflags; ata_link_notice(link, "FORCE: link flag 0x%x forced -> 0x%x\n", fe->param.lflags, link->flags); } } } /** * ata_force_xfermask - force xfermask according to libata.force * @dev: ATA device of interest * * Force xfer_mask according to libata.force and whine about it. * For consistency with link selection, device number 15 selects * the first device connected to the host link. * * LOCKING: * EH context. */ static void ata_force_xfermask(struct ata_device *dev) { int devno = dev->link->pmp + dev->devno; int alt_devno = devno; int i; /* allow n.15/16 for devices attached to host port */ if (ata_is_host_link(dev->link)) alt_devno += 15; for (i = ata_force_tbl_size - 1; i >= 0; i--) { const struct ata_force_ent *fe = &ata_force_tbl[i]; unsigned long pio_mask, mwdma_mask, udma_mask; if (fe->port != -1 && fe->port != dev->link->ap->print_id) continue; if (fe->device != -1 && fe->device != devno && fe->device != alt_devno) continue; if (!fe->param.xfer_mask) continue; ata_unpack_xfermask(fe->param.xfer_mask, &pio_mask, &mwdma_mask, &udma_mask); if (udma_mask) dev->udma_mask = udma_mask; else if (mwdma_mask) { dev->udma_mask = 0; dev->mwdma_mask = mwdma_mask; } else { dev->udma_mask = 0; dev->mwdma_mask = 0; dev->pio_mask = pio_mask; } ata_dev_notice(dev, "FORCE: xfer_mask set to %s\n", fe->param.name); return; } } /** * ata_force_horkage - force horkage according to libata.force * @dev: ATA device of interest * * Force horkage according to libata.force and whine about it. * For consistency with link selection, device number 15 selects * the first device connected to the host link. * * LOCKING: * EH context. */ static void ata_force_horkage(struct ata_device *dev) { int devno = dev->link->pmp + dev->devno; int alt_devno = devno; int i; /* allow n.15/16 for devices attached to host port */ if (ata_is_host_link(dev->link)) alt_devno += 15; for (i = 0; i < ata_force_tbl_size; i++) { const struct ata_force_ent *fe = &ata_force_tbl[i]; if (fe->port != -1 && fe->port != dev->link->ap->print_id) continue; if (fe->device != -1 && fe->device != devno && fe->device != alt_devno) continue; if (!(~dev->horkage & fe->param.horkage_on) && !(dev->horkage & fe->param.horkage_off)) continue; dev->horkage |= fe->param.horkage_on; dev->horkage &= ~fe->param.horkage_off; ata_dev_notice(dev, "FORCE: horkage modified (%s)\n", fe->param.name); } } #else static inline void ata_force_link_limits(struct ata_link *link) { } static inline void ata_force_xfermask(struct ata_device *dev) { } static inline void ata_force_horkage(struct ata_device *dev) { } #endif /** * atapi_cmd_type - Determine ATAPI command type from SCSI opcode * @opcode: SCSI opcode * * Determine ATAPI command type from @opcode. * * LOCKING: * None. * * RETURNS: * ATAPI_{READ|WRITE|READ_CD|PASS_THRU|MISC} */ int atapi_cmd_type(u8 opcode) { switch (opcode) { case GPCMD_READ_10: case GPCMD_READ_12: return ATAPI_READ; case GPCMD_WRITE_10: case GPCMD_WRITE_12: case GPCMD_WRITE_AND_VERIFY_10: return ATAPI_WRITE; case GPCMD_READ_CD: case GPCMD_READ_CD_MSF: return ATAPI_READ_CD; case ATA_16: case ATA_12: if (atapi_passthru16) return ATAPI_PASS_THRU; fallthrough; default: return ATAPI_MISC; } } EXPORT_SYMBOL_GPL(atapi_cmd_type); static const u8 ata_rw_cmds[] = { /* pio multi */ ATA_CMD_READ_MULTI, ATA_CMD_WRITE_MULTI, ATA_CMD_READ_MULTI_EXT, ATA_CMD_WRITE_MULTI_EXT, 0, 0, 0, ATA_CMD_WRITE_MULTI_FUA_EXT, /* pio */ ATA_CMD_PIO_READ, ATA_CMD_PIO_WRITE, ATA_CMD_PIO_READ_EXT, ATA_CMD_PIO_WRITE_EXT, 0, 0, 0, 0, /* dma */ ATA_CMD_READ, ATA_CMD_WRITE, ATA_CMD_READ_EXT, ATA_CMD_WRITE_EXT, 0, 0, 0, ATA_CMD_WRITE_FUA_EXT }; /** * ata_rwcmd_protocol - set taskfile r/w commands and protocol * @tf: command to examine and configure * @dev: device tf belongs to * * Examine the device configuration and tf->flags to calculate * the proper read/write commands and protocol to use. * * LOCKING: * caller. */ static int ata_rwcmd_protocol(struct ata_taskfile *tf, struct ata_device *dev) { u8 cmd; int index, fua, lba48, write; fua = (tf->flags & ATA_TFLAG_FUA) ? 4 : 0; lba48 = (tf->flags & ATA_TFLAG_LBA48) ? 2 : 0; write = (tf->flags & ATA_TFLAG_WRITE) ? 1 : 0; if (dev->flags & ATA_DFLAG_PIO) { tf->protocol = ATA_PROT_PIO; index = dev->multi_count ? 0 : 8; } else if (lba48 && (dev->link->ap->flags & ATA_FLAG_PIO_LBA48)) { /* Unable to use DMA due to host limitation */ tf->protocol = ATA_PROT_PIO; index = dev->multi_count ? 0 : 8; } else { tf->protocol = ATA_PROT_DMA; index = 16; } cmd = ata_rw_cmds[index + fua + lba48 + write]; if (cmd) { tf->command = cmd; return 0; } return -1; } /** * ata_tf_read_block - Read block address from ATA taskfile * @tf: ATA taskfile of interest * @dev: ATA device @tf belongs to * * LOCKING: * None. * * Read block address from @tf. This function can handle all * three address formats - LBA, LBA48 and CHS. tf->protocol and * flags select the address format to use. * * RETURNS: * Block address read from @tf. */ u64 ata_tf_read_block(const struct ata_taskfile *tf, struct ata_device *dev) { u64 block = 0; if (tf->flags & ATA_TFLAG_LBA) { if (tf->flags & ATA_TFLAG_LBA48) { block |= (u64)tf->hob_lbah << 40; block |= (u64)tf->hob_lbam << 32; block |= (u64)tf->hob_lbal << 24; } else block |= (tf->device & 0xf) << 24; block |= tf->lbah << 16; block |= tf->lbam << 8; block |= tf->lbal; } else { u32 cyl, head, sect; cyl = tf->lbam | (tf->lbah << 8); head = tf->device & 0xf; sect = tf->lbal; if (!sect) { ata_dev_warn(dev, "device reported invalid CHS sector 0\n"); return U64_MAX; } block = (cyl * dev->heads + head) * dev->sectors + sect - 1; } return block; } /** * ata_build_rw_tf - Build ATA taskfile for given read/write request * @tf: Target ATA taskfile * @dev: ATA device @tf belongs to * @block: Block address * @n_block: Number of blocks * @tf_flags: RW/FUA etc... * @tag: tag * @class: IO priority class * * LOCKING: * None. * * Build ATA taskfile @tf for read/write request described by * @block, @n_block, @tf_flags and @tag on @dev. * * RETURNS: * * 0 on success, -ERANGE if the request is too large for @dev, * -EINVAL if the request is invalid. */ int ata_build_rw_tf(struct ata_taskfile *tf, struct ata_device *dev, u64 block, u32 n_block, unsigned int tf_flags, unsigned int tag, int class) { tf->flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE; tf->flags |= tf_flags; if (ata_ncq_enabled(dev) && !ata_tag_internal(tag)) { /* yay, NCQ */ if (!lba_48_ok(block, n_block)) return -ERANGE; tf->protocol = ATA_PROT_NCQ; tf->flags |= ATA_TFLAG_LBA | ATA_TFLAG_LBA48; if (tf->flags & ATA_TFLAG_WRITE) tf->command = ATA_CMD_FPDMA_WRITE; else tf->command = ATA_CMD_FPDMA_READ; tf->nsect = tag << 3; tf->hob_feature = (n_block >> 8) & 0xff; tf->feature = n_block & 0xff; tf->hob_lbah = (block >> 40) & 0xff; tf->hob_lbam = (block >> 32) & 0xff; tf->hob_lbal = (block >> 24) & 0xff; tf->lbah = (block >> 16) & 0xff; tf->lbam = (block >> 8) & 0xff; tf->lbal = block & 0xff; tf->device = ATA_LBA; if (tf->flags & ATA_TFLAG_FUA) tf->device |= 1 << 7; if (dev->flags & ATA_DFLAG_NCQ_PRIO) { if (class == IOPRIO_CLASS_RT) tf->hob_nsect |= ATA_PRIO_HIGH << ATA_SHIFT_PRIO; } } else if (dev->flags & ATA_DFLAG_LBA) { tf->flags |= ATA_TFLAG_LBA; if (lba_28_ok(block, n_block)) { /* use LBA28 */ tf->device |= (block >> 24) & 0xf; } else if (lba_48_ok(block, n_block)) { if (!(dev->flags & ATA_DFLAG_LBA48)) return -ERANGE; /* use LBA48 */ tf->flags |= ATA_TFLAG_LBA48; tf->hob_nsect = (n_block >> 8) & 0xff; tf->hob_lbah = (block >> 40) & 0xff; tf->hob_lbam = (block >> 32) & 0xff; tf->hob_lbal = (block >> 24) & 0xff; } else /* request too large even for LBA48 */ return -ERANGE; if (unlikely(ata_rwcmd_protocol(tf, dev) < 0)) return -EINVAL; tf->nsect = n_block & 0xff; tf->lbah = (block >> 16) & 0xff; tf->lbam = (block >> 8) & 0xff; tf->lbal = block & 0xff; tf->device |= ATA_LBA; } else { /* CHS */ u32 sect, head, cyl, track; /* The request -may- be too large for CHS addressing. */ if (!lba_28_ok(block, n_block)) return -ERANGE; if (unlikely(ata_rwcmd_protocol(tf, dev) < 0)) return -EINVAL; /* Convert LBA to CHS */ track = (u32)block / dev->sectors; cyl = track / dev->heads; head = track % dev->heads; sect = (u32)block % dev->sectors + 1; DPRINTK("block %u track %u cyl %u head %u sect %u\n", (u32)block, track, cyl, head, sect); /* Check whether the converted CHS can fit. Cylinder: 0-65535 Head: 0-15 Sector: 1-255*/ if ((cyl >> 16) || (head >> 4) || (sect >> 8) || (!sect)) return -ERANGE; tf->nsect = n_block & 0xff; /* Sector count 0 means 256 sectors */ tf->lbal = sect; tf->lbam = cyl; tf->lbah = cyl >> 8; tf->device |= head; } return 0; } /** * ata_pack_xfermask - Pack pio, mwdma and udma masks into xfer_mask * @pio_mask: pio_mask * @mwdma_mask: mwdma_mask * @udma_mask: udma_mask * * Pack @pio_mask, @mwdma_mask and @udma_mask into a single * unsigned int xfer_mask. * * LOCKING: * None. * * RETURNS: * Packed xfer_mask. */ unsigned long ata_pack_xfermask(unsigned long pio_mask, unsigned long mwdma_mask, unsigned long udma_mask) { return ((pio_mask << ATA_SHIFT_PIO) & ATA_MASK_PIO) | ((mwdma_mask << ATA_SHIFT_MWDMA) & ATA_MASK_MWDMA) | ((udma_mask << ATA_SHIFT_UDMA) & ATA_MASK_UDMA); } EXPORT_SYMBOL_GPL(ata_pack_xfermask); /** * ata_unpack_xfermask - Unpack xfer_mask into pio, mwdma and udma masks * @xfer_mask: xfer_mask to unpack * @pio_mask: resulting pio_mask * @mwdma_mask: resulting mwdma_mask * @udma_mask: resulting udma_mask * * Unpack @xfer_mask into @pio_mask, @mwdma_mask and @udma_mask. * Any NULL destination masks will be ignored. */ void ata_unpack_xfermask(unsigned long xfer_mask, unsigned long *pio_mask, unsigned long *mwdma_mask, unsigned long *udma_mask) { if (pio_mask) *pio_mask = (xfer_mask & ATA_MASK_PIO) >> ATA_SHIFT_PIO; if (mwdma_mask) *mwdma_mask = (xfer_mask & ATA_MASK_MWDMA) >> ATA_SHIFT_MWDMA; if (udma_mask) *udma_mask = (xfer_mask & ATA_MASK_UDMA) >> ATA_SHIFT_UDMA; } static const struct ata_xfer_ent { int shift, bits; u8 base; } ata_xfer_tbl[] = { { ATA_SHIFT_PIO, ATA_NR_PIO_MODES, XFER_PIO_0 }, { ATA_SHIFT_MWDMA, ATA_NR_MWDMA_MODES, XFER_MW_DMA_0 }, { ATA_SHIFT_UDMA, ATA_NR_UDMA_MODES, XFER_UDMA_0 }, { -1, }, }; /** * ata_xfer_mask2mode - Find matching XFER_* for the given xfer_mask * @xfer_mask: xfer_mask of interest * * Return matching XFER_* value for @xfer_mask. Only the highest * bit of @xfer_mask is considered. * * LOCKING: * None. * * RETURNS: * Matching XFER_* value, 0xff if no match found. */ u8 ata_xfer_mask2mode(unsigned long xfer_mask) { int highbit = fls(xfer_mask) - 1; const struct ata_xfer_ent *ent; for (ent = ata_xfer_tbl; ent->shift >= 0; ent++) if (highbit >= ent->shift && highbit < ent->shift + ent->bits) return ent->base + highbit - ent->shift; return 0xff; } EXPORT_SYMBOL_GPL(ata_xfer_mask2mode); /** * ata_xfer_mode2mask - Find matching xfer_mask for XFER_* * @xfer_mode: XFER_* of interest * * Return matching xfer_mask for @xfer_mode. * * LOCKING: * None. * * RETURNS: * Matching xfer_mask, 0 if no match found. */ unsigned long ata_xfer_mode2mask(u8 xfer_mode) { const struct ata_xfer_ent *ent; for (ent = ata_xfer_tbl; ent->shift >= 0; ent++) if (xfer_mode >= ent->base && xfer_mode < ent->base + ent->bits) return ((2 << (ent->shift + xfer_mode - ent->base)) - 1) & ~((1 << ent->shift) - 1); return 0; } EXPORT_SYMBOL_GPL(ata_xfer_mode2mask); /** * ata_xfer_mode2shift - Find matching xfer_shift for XFER_* * @xfer_mode: XFER_* of interest * * Return matching xfer_shift for @xfer_mode. * * LOCKING: * None. * * RETURNS: * Matching xfer_shift, -1 if no match found. */ int ata_xfer_mode2shift(unsigned long xfer_mode) { const struct ata_xfer_ent *ent; for (ent = ata_xfer_tbl; ent->shift >= 0; ent++) if (xfer_mode >= ent->base && xfer_mode < ent->base + ent->bits) return ent->shift; return -1; } EXPORT_SYMBOL_GPL(ata_xfer_mode2shift); /** * ata_mode_string - convert xfer_mask to string * @xfer_mask: mask of bits supported; only highest bit counts. * * Determine string which represents the highest speed * (highest bit in @modemask). * * LOCKING: * None. * * RETURNS: * Constant C string representing highest speed listed in * @mode_mask, or the constant C string "<n/a>". */ const char *ata_mode_string(unsigned long xfer_mask) { static const char * const xfer_mode_str[] = { "PIO0", "PIO1", "PIO2", "PIO3", "PIO4", "PIO5", "PIO6", "MWDMA0", "MWDMA1", "MWDMA2", "MWDMA3", "MWDMA4", "UDMA/16", "UDMA/25", "UDMA/33", "UDMA/44", "UDMA/66", "UDMA/100", "UDMA/133", "UDMA7", }; int highbit; highbit = fls(xfer_mask) - 1; if (highbit >= 0 && highbit < ARRAY_SIZE(xfer_mode_str)) return xfer_mode_str[highbit]; return "<n/a>"; } EXPORT_SYMBOL_GPL(ata_mode_string); const char *sata_spd_string(unsigned int spd) { static const char * const spd_str[] = { "1.5 Gbps", "3.0 Gbps", "6.0 Gbps", }; if (spd == 0 || (spd - 1) >= ARRAY_SIZE(spd_str)) return "<unknown>"; return spd_str[spd - 1]; } /** * ata_dev_classify - determine device type based on ATA-spec signature * @tf: ATA taskfile register set for device to be identified * * Determine from taskfile register contents whether a device is * ATA or ATAPI, as per "Signature and persistence" section * of ATA/PI spec (volume 1, sect 5.14). * * LOCKING: * None. * * RETURNS: * Device type, %ATA_DEV_ATA, %ATA_DEV_ATAPI, %ATA_DEV_PMP, * %ATA_DEV_ZAC, or %ATA_DEV_UNKNOWN the event of failure. */ unsigned int ata_dev_classify(const struct ata_taskfile *tf) { /* Apple's open source Darwin code hints that some devices only * put a proper signature into the LBA mid/high registers, * So, we only check those. It's sufficient for uniqueness. * * ATA/ATAPI-7 (d1532v1r1: Feb. 19, 2003) specified separate * signatures for ATA and ATAPI devices attached on SerialATA, * 0x3c/0xc3 and 0x69/0x96 respectively. However, SerialATA * spec has never mentioned about using different signatures * for ATA/ATAPI devices. Then, Serial ATA II: Port * Multiplier specification began to use 0x69/0x96 to identify * port multpliers and 0x3c/0xc3 to identify SEMB device. * ATA/ATAPI-7 dropped descriptions about 0x3c/0xc3 and * 0x69/0x96 shortly and described them as reserved for * SerialATA. * * We follow the current spec and consider that 0x69/0x96 * identifies a port multiplier and 0x3c/0xc3 a SEMB device. * Unfortunately, WDC WD1600JS-62MHB5 (a hard drive) reports * SEMB signature. This is worked around in * ata_dev_read_id(). */ if ((tf->lbam == 0) && (tf->lbah == 0)) { DPRINTK("found ATA device by sig\n"); return ATA_DEV_ATA; } if ((tf->lbam == 0x14) && (tf->lbah == 0xeb)) { DPRINTK("found ATAPI device by sig\n"); return ATA_DEV_ATAPI; } if ((tf->lbam == 0x69) && (tf->lbah == 0x96)) { DPRINTK("found PMP device by sig\n"); return ATA_DEV_PMP; } if ((tf->lbam == 0x3c) && (tf->lbah == 0xc3)) { DPRINTK("found SEMB device by sig (could be ATA device)\n"); return ATA_DEV_SEMB; } if ((tf->lbam == 0xcd) && (tf->lbah == 0xab)) { DPRINTK("found ZAC device by sig\n"); return ATA_DEV_ZAC; } DPRINTK("unknown device\n"); return ATA_DEV_UNKNOWN; } EXPORT_SYMBOL_GPL(ata_dev_classify); /** * ata_id_string - Convert IDENTIFY DEVICE page into string * @id: IDENTIFY DEVICE results we will examine * @s: string into which data is output * @ofs: offset into identify device page * @len: length of string to return. must be an even number. * * The strings in the IDENTIFY DEVICE page are broken up into * 16-bit chunks. Run through the string, and output each * 8-bit chunk linearly, regardless of platform. * * LOCKING: * caller. */ void ata_id_string(const u16 *id, unsigned char *s, unsigned int ofs, unsigned int len) { unsigned int c; BUG_ON(len & 1); while (len > 0) { c = id[ofs] >> 8; *s = c; s++; c = id[ofs] & 0xff; *s = c; s++; ofs++; len -= 2; } } EXPORT_SYMBOL_GPL(ata_id_string); /** * ata_id_c_string - Convert IDENTIFY DEVICE page into C string * @id: IDENTIFY DEVICE results we will examine * @s: string into which data is output * @ofs: offset into identify device page * @len: length of string to return. must be an odd number. * * This function is identical to ata_id_string except that it * trims trailing spaces and terminates the resulting string with * null. @len must be actual maximum length (even number) + 1. * * LOCKING: * caller. */ void ata_id_c_string(const u16 *id, unsigned char *s, unsigned int ofs, unsigned int len) { unsigned char *p; ata_id_string(id, s, ofs, len - 1); p = s + strnlen(s, len - 1); while (p > s && p[-1] == ' ') p--; *p = '\0'; } EXPORT_SYMBOL_GPL(ata_id_c_string); static u64 ata_id_n_sectors(const u16 *id) { if (ata_id_has_lba(id)) { if (ata_id_has_lba48(id)) return ata_id_u64(id, ATA_ID_LBA_CAPACITY_2); else return ata_id_u32(id, ATA_ID_LBA_CAPACITY); } else { if (ata_id_current_chs_valid(id)) return id[ATA_ID_CUR_CYLS] * id[ATA_ID_CUR_HEADS] * id[ATA_ID_CUR_SECTORS]; else return id[ATA_ID_CYLS] * id[ATA_ID_HEADS] * id[ATA_ID_SECTORS]; } } u64 ata_tf_to_lba48(const struct ata_taskfile *tf) { u64 sectors = 0; sectors |= ((u64)(tf->hob_lbah & 0xff)) << 40; sectors |= ((u64)(tf->hob_lbam & 0xff)) << 32; sectors |= ((u64)(tf->hob_lbal & 0xff)) << 24; sectors |= (tf->lbah & 0xff) << 16; sectors |= (tf->lbam & 0xff) << 8; sectors |= (tf->lbal & 0xff); return sectors; } u64 ata_tf_to_lba(const struct ata_taskfile *tf) { u64 sectors = 0; sectors |= (tf->device & 0x0f) << 24; sectors |= (tf->lbah & 0xff) << 16; sectors |= (tf->lbam & 0xff) << 8; sectors |= (tf->lbal & 0xff); return sectors; } /** * ata_read_native_max_address - Read native max address * @dev: target device * @max_sectors: out parameter for the result native max address * * Perform an LBA48 or LBA28 native size query upon the device in * question. * * RETURNS: * 0 on success, -EACCES if command is aborted by the drive. * -EIO on other errors. */ static int ata_read_native_max_address(struct ata_device *dev, u64 *max_sectors) { unsigned int err_mask; struct ata_taskfile tf; int lba48 = ata_id_has_lba48(dev->id); ata_tf_init(dev, &tf); /* always clear all address registers */ tf.flags |= ATA_TFLAG_DEVICE | ATA_TFLAG_ISADDR; if (lba48) { tf.command = ATA_CMD_READ_NATIVE_MAX_EXT; tf.flags |= ATA_TFLAG_LBA48; } else tf.command = ATA_CMD_READ_NATIVE_MAX; tf.protocol = ATA_PROT_NODATA; tf.device |= ATA_LBA; err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0); if (err_mask) { ata_dev_warn(dev, "failed to read native max address (err_mask=0x%x)\n", err_mask); if (err_mask == AC_ERR_DEV && (tf.feature & ATA_ABORTED)) return -EACCES; return -EIO; } if (lba48) *max_sectors = ata_tf_to_lba48(&tf) + 1; else *max_sectors = ata_tf_to_lba(&tf) + 1; if (dev->horkage & ATA_HORKAGE_HPA_SIZE) (*max_sectors)--; return 0; } /** * ata_set_max_sectors - Set max sectors * @dev: target device * @new_sectors: new max sectors value to set for the device * * Set max sectors of @dev to @new_sectors. * * RETURNS: * 0 on success, -EACCES if command is aborted or denied (due to * previous non-volatile SET_MAX) by the drive. -EIO on other * errors. */ static int ata_set_max_sectors(struct ata_device *dev, u64 new_sectors) { unsigned int err_mask; struct ata_taskfile tf; int lba48 = ata_id_has_lba48(dev->id); new_sectors--; ata_tf_init(dev, &tf); tf.flags |= ATA_TFLAG_DEVICE | ATA_TFLAG_ISADDR; if (lba48) { tf.command = ATA_CMD_SET_MAX_EXT; tf.flags |= ATA_TFLAG_LBA48; tf.hob_lbal = (new_sectors >> 24) & 0xff; tf.hob_lbam = (new_sectors >> 32) & 0xff; tf.hob_lbah = (new_sectors >> 40) & 0xff; } else { tf.command = ATA_CMD_SET_MAX; tf.device |= (new_sectors >> 24) & 0xf; } tf.protocol = ATA_PROT_NODATA; tf.device |= ATA_LBA; tf.lbal = (new_sectors >> 0) & 0xff; tf.lbam = (new_sectors >> 8) & 0xff; tf.lbah = (new_sectors >> 16) & 0xff; err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0); if (err_mask) { ata_dev_warn(dev, "failed to set max address (err_mask=0x%x)\n", err_mask); if (err_mask == AC_ERR_DEV && (tf.feature & (ATA_ABORTED | ATA_IDNF))) return -EACCES; return -EIO; } return 0; } /** * ata_hpa_resize - Resize a device with an HPA set * @dev: Device to resize * * Read the size of an LBA28 or LBA48 disk with HPA features and resize * it if required to the full size of the media. The caller must check * the drive has the HPA feature set enabled. * * RETURNS: * 0 on success, -errno on failure. */ static int ata_hpa_resize(struct ata_device *dev) { struct ata_eh_context *ehc = &dev->link->eh_context; int print_info = ehc->i.flags & ATA_EHI_PRINTINFO; bool unlock_hpa = ata_ignore_hpa || dev->flags & ATA_DFLAG_UNLOCK_HPA; u64 sectors = ata_id_n_sectors(dev->id); u64 native_sectors; int rc; /* do we need to do it? */ if ((dev->class != ATA_DEV_ATA && dev->class != ATA_DEV_ZAC) || !ata_id_has_lba(dev->id) || !ata_id_hpa_enabled(dev->id) || (dev->horkage & ATA_HORKAGE_BROKEN_HPA)) return 0; /* read native max address */ rc = ata_read_native_max_address(dev, &native_sectors); if (rc) { /* If device aborted the command or HPA isn't going to * be unlocked, skip HPA resizing. */ if (rc == -EACCES || !unlock_hpa) { ata_dev_warn(dev, "HPA support seems broken, skipping HPA handling\n"); dev->horkage |= ATA_HORKAGE_BROKEN_HPA; /* we can continue if device aborted the command */ if (rc == -EACCES) rc = 0; } return rc; } dev->n_native_sectors = native_sectors; /* nothing to do? */ if (native_sectors <= sectors || !unlock_hpa) { if (!print_info || native_sectors == sectors) return 0; if (native_sectors > sectors) ata_dev_info(dev, "HPA detected: current %llu, native %llu\n", (unsigned long long)sectors, (unsigned long long)native_sectors); else if (native_sectors < sectors) ata_dev_warn(dev, "native sectors (%llu) is smaller than sectors (%llu)\n", (unsigned long long)native_sectors, (unsigned long long)sectors); return 0; } /* let's unlock HPA */ rc = ata_set_max_sectors(dev, native_sectors); if (rc == -EACCES) { /* if device aborted the command, skip HPA resizing */ ata_dev_warn(dev, "device aborted resize (%llu -> %llu), skipping HPA handling\n", (unsigned long long)sectors, (unsigned long long)native_sectors); dev->horkage |= ATA_HORKAGE_BROKEN_HPA; return 0; } else if (rc) return rc; /* re-read IDENTIFY data */ rc = ata_dev_reread_id(dev, 0); if (rc) { ata_dev_err(dev, "failed to re-read IDENTIFY data after HPA resizing\n"); return rc; } if (print_info) { u64 new_sectors = ata_id_n_sectors(dev->id); ata_dev_info(dev, "HPA unlocked: %llu -> %llu, native %llu\n", (unsigned long long)sectors, (unsigned long long)new_sectors, (unsigned long long)native_sectors); } return 0; } /** * ata_dump_id - IDENTIFY DEVICE info debugging output * @id: IDENTIFY DEVICE page to dump * * Dump selected 16-bit words from the given IDENTIFY DEVICE * page. * * LOCKING: * caller. */ static inline void ata_dump_id(const u16 *id) { DPRINTK("49==0x%04x " "53==0x%04x " "63==0x%04x " "64==0x%04x " "75==0x%04x \n", id[49], id[53], id[63], id[64], id[75]); DPRINTK("80==0x%04x " "81==0x%04x " "82==0x%04x " "83==0x%04x " "84==0x%04x \n", id[80], id[81], id[82], id[83], id[84]); DPRINTK("88==0x%04x " "93==0x%04x\n", id[88], id[93]); } /** * ata_id_xfermask - Compute xfermask from the given IDENTIFY data * @id: IDENTIFY data to compute xfer mask from * * Compute the xfermask for this device. This is not as trivial * as it seems if we must consider early devices correctly. * * FIXME: pre IDE drive timing (do we care ?). * * LOCKING: * None. * * RETURNS: * Computed xfermask */ unsigned long ata_id_xfermask(const u16 *id) { unsigned long pio_mask, mwdma_mask, udma_mask; /* Usual case. Word 53 indicates word 64 is valid */ if (id[ATA_ID_FIELD_VALID] & (1 << 1)) { pio_mask = id[ATA_ID_PIO_MODES] & 0x03; pio_mask <<= 3; pio_mask |= 0x7; } else { /* If word 64 isn't valid then Word 51 high byte holds * the PIO timing number for the maximum. Turn it into * a mask. */ u8 mode = (id[ATA_ID_OLD_PIO_MODES] >> 8) & 0xFF; if (mode < 5) /* Valid PIO range */ pio_mask = (2 << mode) - 1; else pio_mask = 1; /* But wait.. there's more. Design your standards by * committee and you too can get a free iordy field to * process. However its the speeds not the modes that * are supported... Note drivers using the timing API * will get this right anyway */ } mwdma_mask = id[ATA_ID_MWDMA_MODES] & 0x07; if (ata_id_is_cfa(id)) { /* * Process compact flash extended modes */ int pio = (id[ATA_ID_CFA_MODES] >> 0) & 0x7; int dma = (id[ATA_ID_CFA_MODES] >> 3) & 0x7; if (pio) pio_mask |= (1 << 5); if (pio > 1) pio_mask |= (1 << 6); if (dma) mwdma_mask |= (1 << 3); if (dma > 1) mwdma_mask |= (1 << 4); } udma_mask = 0; if (id[ATA_ID_FIELD_VALID] & (1 << 2)) udma_mask = id[ATA_ID_UDMA_MODES] & 0xff; return ata_pack_xfermask(pio_mask, mwdma_mask, udma_mask); } EXPORT_SYMBOL_GPL(ata_id_xfermask); static void ata_qc_complete_internal(struct ata_queued_cmd *qc) { struct completion *waiting = qc->private_data; complete(waiting); } /** * ata_exec_internal_sg - execute libata internal command * @dev: Device to which the command is sent * @tf: Taskfile registers for the command and the result * @cdb: CDB for packet command * @dma_dir: Data transfer direction of the command * @sgl: sg list for the data buffer of the command * @n_elem: Number of sg entries * @timeout: Timeout in msecs (0 for default) * * Executes libata internal command with timeout. @tf contains * command on entry and result on return. Timeout and error * conditions are reported via return value. No recovery action * is taken after a command times out. It's caller's duty to * clean up after timeout. * * LOCKING: * None. Should be called with kernel context, might sleep. * * RETURNS: * Zero on success, AC_ERR_* mask on failure */ unsigned ata_exec_internal_sg(struct ata_device *dev, struct ata_taskfile *tf, const u8 *cdb, int dma_dir, struct scatterlist *sgl, unsigned int n_elem, unsigned long timeout) { struct ata_link *link = dev->link; struct ata_port *ap = link->ap; u8 command = tf->command; int auto_timeout = 0; struct ata_queued_cmd *qc; unsigned int preempted_tag; u32 preempted_sactive; u64 preempted_qc_active; int preempted_nr_active_links; DECLARE_COMPLETION_ONSTACK(wait); unsigned long flags; unsigned int err_mask; int rc; spin_lock_irqsave(ap->lock, flags); /* no internal command while frozen */ if (ap->pflags & ATA_PFLAG_FROZEN) { spin_unlock_irqrestore(ap->lock, flags); return AC_ERR_SYSTEM; } /* initialize internal qc */ qc = __ata_qc_from_tag(ap, ATA_TAG_INTERNAL); qc->tag = ATA_TAG_INTERNAL; qc->hw_tag = 0; qc->scsicmd = NULL; qc->ap = ap; qc->dev = dev; ata_qc_reinit(qc); preempted_tag = link->active_tag; preempted_sactive = link->sactive; preempted_qc_active = ap->qc_active; preempted_nr_active_links = ap->nr_active_links; link->active_tag = ATA_TAG_POISON; link->sactive = 0; ap->qc_active = 0; ap->nr_active_links = 0; /* prepare & issue qc */ qc->tf = *tf; if (cdb) memcpy(qc->cdb, cdb, ATAPI_CDB_LEN); /* some SATA bridges need us to indicate data xfer direction */ if (tf->protocol == ATAPI_PROT_DMA && (dev->flags & ATA_DFLAG_DMADIR) && dma_dir == DMA_FROM_DEVICE) qc->tf.feature |= ATAPI_DMADIR; qc->flags |= ATA_QCFLAG_RESULT_TF; qc->dma_dir = dma_dir; if (dma_dir != DMA_NONE) { unsigned int i, buflen = 0; struct scatterlist *sg; for_each_sg(sgl, sg, n_elem, i) buflen += sg->length; ata_sg_init(qc, sgl, n_elem); qc->nbytes = buflen; } qc->private_data = &wait; qc->complete_fn = ata_qc_complete_internal; ata_qc_issue(qc); spin_unlock_irqrestore(ap->lock, flags); if (!timeout) { if (ata_probe_timeout) timeout = ata_probe_timeout * 1000; else { timeout = ata_internal_cmd_timeout(dev, command); auto_timeout = 1; } } if (ap->ops->error_handler) ata_eh_release(ap); rc = wait_for_completion_timeout(&wait, msecs_to_jiffies(timeout)); if (ap->ops->error_handler) ata_eh_acquire(ap); ata_sff_flush_pio_task(ap); if (!rc) { spin_lock_irqsave(ap->lock, flags); /* We're racing with irq here. If we lose, the * following test prevents us from completing the qc * twice. If we win, the port is frozen and will be * cleaned up by ->post_internal_cmd(). */ if (qc->flags & ATA_QCFLAG_ACTIVE) { qc->err_mask |= AC_ERR_TIMEOUT; if (ap->ops->error_handler) ata_port_freeze(ap); else ata_qc_complete(qc); if (ata_msg_warn(ap)) ata_dev_warn(dev, "qc timeout (cmd 0x%x)\n", command); } spin_unlock_irqrestore(ap->lock, flags); } /* do post_internal_cmd */ if (ap->ops->post_internal_cmd) ap->ops->post_internal_cmd(qc); /* perform minimal error analysis */ if (qc->flags & ATA_QCFLAG_FAILED) { if (qc->result_tf.command & (ATA_ERR | ATA_DF)) qc->err_mask |= AC_ERR_DEV; if (!qc->err_mask) qc->err_mask |= AC_ERR_OTHER; if (qc->err_mask & ~AC_ERR_OTHER) qc->err_mask &= ~AC_ERR_OTHER; } else if (qc->tf.command == ATA_CMD_REQ_SENSE_DATA) { qc->result_tf.command |= ATA_SENSE; } /* finish up */ spin_lock_irqsave(ap->lock, flags); *tf = qc->result_tf; err_mask = qc->err_mask; ata_qc_free(qc); link->active_tag = preempted_tag; link->sactive = preempted_sactive; ap->qc_active = preempted_qc_active; ap->nr_active_links = preempted_nr_active_links; spin_unlock_irqrestore(ap->lock, flags); if ((err_mask & AC_ERR_TIMEOUT) && auto_timeout) ata_internal_cmd_timed_out(dev, command); return err_mask; } /** * ata_exec_internal - execute libata internal command * @dev: Device to which the command is sent * @tf: Taskfile registers for the command and the result * @cdb: CDB for packet command * @dma_dir: Data transfer direction of the command * @buf: Data buffer of the command * @buflen: Length of data buffer * @timeout: Timeout in msecs (0 for default) * * Wrapper around ata_exec_internal_sg() which takes simple * buffer instead of sg list. * * LOCKING: * None. Should be called with kernel context, might sleep. * * RETURNS: * Zero on success, AC_ERR_* mask on failure */ unsigned ata_exec_internal(struct ata_device *dev, struct ata_taskfile *tf, const u8 *cdb, int dma_dir, void *buf, unsigned int buflen, unsigned long timeout) { struct scatterlist *psg = NULL, sg; unsigned int n_elem = 0; if (dma_dir != DMA_NONE) { WARN_ON(!buf); sg_init_one(&sg, buf, buflen); psg = &sg; n_elem++; } return ata_exec_internal_sg(dev, tf, cdb, dma_dir, psg, n_elem, timeout); } /** * ata_pio_need_iordy - check if iordy needed * @adev: ATA device * * Check if the current speed of the device requires IORDY. Used * by various controllers for chip configuration. */ unsigned int ata_pio_need_iordy(const struct ata_device *adev) { /* Don't set IORDY if we're preparing for reset. IORDY may * lead to controller lock up on certain controllers if the * port is not occupied. See bko#11703 for details. */ if (adev->link->ap->pflags & ATA_PFLAG_RESETTING) return 0; /* Controller doesn't support IORDY. Probably a pointless * check as the caller should know this. */ if (adev->link->ap->flags & ATA_FLAG_NO_IORDY) return 0; /* CF spec. r4.1 Table 22 says no iordy on PIO5 and PIO6. */ if (ata_id_is_cfa(adev->id) && (adev->pio_mode == XFER_PIO_5 || adev->pio_mode == XFER_PIO_6)) return 0; /* PIO3 and higher it is mandatory */ if (adev->pio_mode > XFER_PIO_2) return 1; /* We turn it on when possible */ if (ata_id_has_iordy(adev->id)) return 1; return 0; } EXPORT_SYMBOL_GPL(ata_pio_need_iordy); /** * ata_pio_mask_no_iordy - Return the non IORDY mask * @adev: ATA device * * Compute the highest mode possible if we are not using iordy. Return * -1 if no iordy mode is available. */ static u32 ata_pio_mask_no_iordy(const struct ata_device *adev) { /* If we have no drive specific rule, then PIO 2 is non IORDY */ if (adev->id[ATA_ID_FIELD_VALID] & 2) { /* EIDE */ u16 pio = adev->id[ATA_ID_EIDE_PIO]; /* Is the speed faster than the drive allows non IORDY ? */ if (pio) { /* This is cycle times not frequency - watch the logic! */ if (pio > 240) /* PIO2 is 240nS per cycle */ return 3 << ATA_SHIFT_PIO; return 7 << ATA_SHIFT_PIO; } } return 3 << ATA_SHIFT_PIO; } /** * ata_do_dev_read_id - default ID read method * @dev: device * @tf: proposed taskfile * @id: data buffer * * Issue the identify taskfile and hand back the buffer containing * identify data. For some RAID controllers and for pre ATA devices * this function is wrapped or replaced by the driver */ unsigned int ata_do_dev_read_id(struct ata_device *dev, struct ata_taskfile *tf, u16 *id) { return ata_exec_internal(dev, tf, NULL, DMA_FROM_DEVICE, id, sizeof(id[0]) * ATA_ID_WORDS, 0); } EXPORT_SYMBOL_GPL(ata_do_dev_read_id); /** * ata_dev_read_id - Read ID data from the specified device * @dev: target device * @p_class: pointer to class of the target device (may be changed) * @flags: ATA_READID_* flags * @id: buffer to read IDENTIFY data into * * Read ID data from the specified device. ATA_CMD_ID_ATA is * performed on ATA devices and ATA_CMD_ID_ATAPI on ATAPI * devices. This function also issues ATA_CMD_INIT_DEV_PARAMS * for pre-ATA4 drives. * * FIXME: ATA_CMD_ID_ATA is optional for early drives and right * now we abort if we hit that case. * * LOCKING: * Kernel thread context (may sleep) * * RETURNS: * 0 on success, -errno otherwise. */ int ata_dev_read_id(struct ata_device *dev, unsigned int *p_class, unsigned int flags, u16 *id) { struct ata_port *ap = dev->link->ap; unsigned int class = *p_class; struct ata_taskfile tf; unsigned int err_mask = 0; const char *reason; bool is_semb = class == ATA_DEV_SEMB; int may_fallback = 1, tried_spinup = 0; int rc; if (ata_msg_ctl(ap)) ata_dev_dbg(dev, "%s: ENTER\n", __func__); retry: ata_tf_init(dev, &tf); switch (class) { case ATA_DEV_SEMB: class = ATA_DEV_ATA; /* some hard drives report SEMB sig */ fallthrough; case ATA_DEV_ATA: case ATA_DEV_ZAC: tf.command = ATA_CMD_ID_ATA; break; case ATA_DEV_ATAPI: tf.command = ATA_CMD_ID_ATAPI; break; default: rc = -ENODEV; reason = "unsupported class"; goto err_out; } tf.protocol = ATA_PROT_PIO; /* Some devices choke if TF registers contain garbage. Make * sure those are properly initialized. */ tf.flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE; /* Device presence detection is unreliable on some * controllers. Always poll IDENTIFY if available. */ tf.flags |= ATA_TFLAG_POLLING; if (ap->ops->read_id) err_mask = ap->ops->read_id(dev, &tf, id); else err_mask = ata_do_dev_read_id(dev, &tf, id); if (err_mask) { if (err_mask & AC_ERR_NODEV_HINT) { ata_dev_dbg(dev, "NODEV after polling detection\n"); return -ENOENT; } if (is_semb) { ata_dev_info(dev, "IDENTIFY failed on device w/ SEMB sig, disabled\n"); /* SEMB is not supported yet */ *p_class = ATA_DEV_SEMB_UNSUP; return 0; } if ((err_mask == AC_ERR_DEV) && (tf.feature & ATA_ABORTED)) { /* Device or controller might have reported * the wrong device class. Give a shot at the * other IDENTIFY if the current one is * aborted by the device. */ if (may_fallback) { may_fallback = 0; if (class == ATA_DEV_ATA) class = ATA_DEV_ATAPI; else class = ATA_DEV_ATA; goto retry; } /* Control reaches here iff the device aborted * both flavors of IDENTIFYs which happens * sometimes with phantom devices. */ ata_dev_dbg(dev, "both IDENTIFYs aborted, assuming NODEV\n"); return -ENOENT; } rc = -EIO; reason = "I/O error"; goto err_out; } if (dev->horkage & ATA_HORKAGE_DUMP_ID) { ata_dev_dbg(dev, "dumping IDENTIFY data, " "class=%d may_fallback=%d tried_spinup=%d\n", class, may_fallback, tried_spinup); print_hex_dump(KERN_DEBUG, "", DUMP_PREFIX_OFFSET, 16, 2, id, ATA_ID_WORDS * sizeof(*id), true); } /* Falling back doesn't make sense if ID data was read * successfully at least once. */ may_fallback = 0; swap_buf_le16(id, ATA_ID_WORDS); /* sanity check */ rc = -EINVAL; reason = "device reports invalid type"; if (class == ATA_DEV_ATA || class == ATA_DEV_ZAC) { if (!ata_id_is_ata(id) && !ata_id_is_cfa(id)) goto err_out; if (ap->host->flags & ATA_HOST_IGNORE_ATA && ata_id_is_ata(id)) { ata_dev_dbg(dev, "host indicates ignore ATA devices, ignored\n"); return -ENOENT; } } else { if (ata_id_is_ata(id)) goto err_out; } if (!tried_spinup && (id[2] == 0x37c8 || id[2] == 0x738c)) { tried_spinup = 1; /* * Drive powered-up in standby mode, and requires a specific * SET_FEATURES spin-up subcommand before it will accept * anything other than the original IDENTIFY command. */ err_mask = ata_dev_set_feature(dev, SETFEATURES_SPINUP, 0); if (err_mask && id[2] != 0x738c) { rc = -EIO; reason = "SPINUP failed"; goto err_out; } /* * If the drive initially returned incomplete IDENTIFY info, * we now must reissue the IDENTIFY command. */ if (id[2] == 0x37c8) goto retry; } if ((flags & ATA_READID_POSTRESET) && (class == ATA_DEV_ATA || class == ATA_DEV_ZAC)) { /* * The exact sequence expected by certain pre-ATA4 drives is: * SRST RESET * IDENTIFY (optional in early ATA) * INITIALIZE DEVICE PARAMETERS (later IDE and ATA) * anything else.. * Some drives were very specific about that exact sequence. * * Note that ATA4 says lba is mandatory so the second check * should never trigger. */ if (ata_id_major_version(id) < 4 || !ata_id_has_lba(id)) { err_mask = ata_dev_init_params(dev, id[3], id[6]); if (err_mask) { rc = -EIO; reason = "INIT_DEV_PARAMS failed"; goto err_out; } /* current CHS translation info (id[53-58]) might be * changed. reread the identify device info. */ flags &= ~ATA_READID_POSTRESET; goto retry; } } *p_class = class; return 0; err_out: if (ata_msg_warn(ap)) ata_dev_warn(dev, "failed to IDENTIFY (%s, err_mask=0x%x)\n", reason, err_mask); return rc; } /** * ata_read_log_page - read a specific log page * @dev: target device * @log: log to read * @page: page to read * @buf: buffer to store read page * @sectors: number of sectors to read * * Read log page using READ_LOG_EXT command. * * LOCKING: * Kernel thread context (may sleep). * * RETURNS: * 0 on success, AC_ERR_* mask otherwise. */ unsigned int ata_read_log_page(struct ata_device *dev, u8 log, u8 page, void *buf, unsigned int sectors) { unsigned long ap_flags = dev->link->ap->flags; struct ata_taskfile tf; unsigned int err_mask; bool dma = false; DPRINTK("read log page - log 0x%x, page 0x%x\n", log, page); /* * Return error without actually issuing the command on controllers * which e.g. lockup on a read log page. */ if (ap_flags & ATA_FLAG_NO_LOG_PAGE) return AC_ERR_DEV; retry: ata_tf_init(dev, &tf); if (ata_dma_enabled(dev) && ata_id_has_read_log_dma_ext(dev->id) && !(dev->horkage & ATA_HORKAGE_NO_DMA_LOG)) { tf.command = ATA_CMD_READ_LOG_DMA_EXT; tf.protocol = ATA_PROT_DMA; dma = true; } else { tf.command = ATA_CMD_READ_LOG_EXT; tf.protocol = ATA_PROT_PIO; dma = false; } tf.lbal = log; tf.lbam = page; tf.nsect = sectors; tf.hob_nsect = sectors >> 8; tf.flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_LBA48 | ATA_TFLAG_DEVICE; err_mask = ata_exec_internal(dev, &tf, NULL, DMA_FROM_DEVICE, buf, sectors * ATA_SECT_SIZE, 0); if (err_mask && dma) { dev->horkage |= ATA_HORKAGE_NO_DMA_LOG; ata_dev_warn(dev, "READ LOG DMA EXT failed, trying PIO\n"); goto retry; } DPRINTK("EXIT, err_mask=%x\n", err_mask); return err_mask; } static bool ata_log_supported(struct ata_device *dev, u8 log) { struct ata_port *ap = dev->link->ap; if (ata_read_log_page(dev, ATA_LOG_DIRECTORY, 0, ap->sector_buf, 1)) return false; return get_unaligned_le16(&ap->sector_buf[log * 2]) ? true : false; } static bool ata_identify_page_supported(struct ata_device *dev, u8 page) { struct ata_port *ap = dev->link->ap; unsigned int err, i; if (!ata_log_supported(dev, ATA_LOG_IDENTIFY_DEVICE)) { ata_dev_warn(dev, "ATA Identify Device Log not supported\n"); return false; } /* * Read IDENTIFY DEVICE data log, page 0, to figure out if the page is * supported. */ err = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE, 0, ap->sector_buf, 1); if (err) { ata_dev_info(dev, "failed to get Device Identify Log Emask 0x%x\n", err); return false; } for (i = 0; i < ap->sector_buf[8]; i++) { if (ap->sector_buf[9 + i] == page) return true; } return false; } static int ata_do_link_spd_horkage(struct ata_device *dev) { struct ata_link *plink = ata_dev_phys_link(dev); u32 target, target_limit; if (!sata_scr_valid(plink)) return 0; if (dev->horkage & ATA_HORKAGE_1_5_GBPS) target = 1; else return 0; target_limit = (1 << target) - 1; /* if already on stricter limit, no need to push further */ if (plink->sata_spd_limit <= target_limit) return 0; plink->sata_spd_limit = target_limit; /* Request another EH round by returning -EAGAIN if link is * going faster than the target speed. Forward progress is * guaranteed by setting sata_spd_limit to target_limit above. */ if (plink->sata_spd > target) { ata_dev_info(dev, "applying link speed limit horkage to %s\n", sata_spd_string(target)); return -EAGAIN; } return 0; } static inline u8 ata_dev_knobble(struct ata_device *dev) { struct ata_port *ap = dev->link->ap; if (ata_dev_blacklisted(dev) & ATA_HORKAGE_BRIDGE_OK) return 0; return ((ap->cbl == ATA_CBL_SATA) && (!ata_id_is_sata(dev->id))); } static void ata_dev_config_ncq_send_recv(struct ata_device *dev) { struct ata_port *ap = dev->link->ap; unsigned int err_mask; if (!ata_log_supported(dev, ATA_LOG_NCQ_SEND_RECV)) { ata_dev_warn(dev, "NCQ Send/Recv Log not supported\n"); return; } err_mask = ata_read_log_page(dev, ATA_LOG_NCQ_SEND_RECV, 0, ap->sector_buf, 1); if (err_mask) { ata_dev_dbg(dev, "failed to get NCQ Send/Recv Log Emask 0x%x\n", err_mask); } else { u8 *cmds = dev->ncq_send_recv_cmds; dev->flags |= ATA_DFLAG_NCQ_SEND_RECV; memcpy(cmds, ap->sector_buf, ATA_LOG_NCQ_SEND_RECV_SIZE); if (dev->horkage & ATA_HORKAGE_NO_NCQ_TRIM) { ata_dev_dbg(dev, "disabling queued TRIM support\n"); cmds[ATA_LOG_NCQ_SEND_RECV_DSM_OFFSET] &= ~ATA_LOG_NCQ_SEND_RECV_DSM_TRIM; } } } static void ata_dev_config_ncq_non_data(struct ata_device *dev) { struct ata_port *ap = dev->link->ap; unsigned int err_mask; if (!ata_log_supported(dev, ATA_LOG_NCQ_NON_DATA)) { ata_dev_warn(dev, "NCQ Send/Recv Log not supported\n"); return; } err_mask = ata_read_log_page(dev, ATA_LOG_NCQ_NON_DATA, 0, ap->sector_buf, 1); if (err_mask) { ata_dev_dbg(dev, "failed to get NCQ Non-Data Log Emask 0x%x\n", err_mask); } else { u8 *cmds = dev->ncq_non_data_cmds; memcpy(cmds, ap->sector_buf, ATA_LOG_NCQ_NON_DATA_SIZE); } } static void ata_dev_config_ncq_prio(struct ata_device *dev) { struct ata_port *ap = dev->link->ap; unsigned int err_mask; if (!(dev->flags & ATA_DFLAG_NCQ_PRIO_ENABLE)) { dev->flags &= ~ATA_DFLAG_NCQ_PRIO; return; } err_mask = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE, ATA_LOG_SATA_SETTINGS, ap->sector_buf, 1); if (err_mask) { ata_dev_dbg(dev, "failed to get Identify Device data, Emask 0x%x\n", err_mask); return; } if (ap->sector_buf[ATA_LOG_NCQ_PRIO_OFFSET] & BIT(3)) { dev->flags |= ATA_DFLAG_NCQ_PRIO; } else { dev->flags &= ~ATA_DFLAG_NCQ_PRIO; ata_dev_dbg(dev, "SATA page does not support priority\n"); } } static bool ata_dev_check_adapter(struct ata_device *dev, unsigned short vendor_id) { struct pci_dev *pcidev = NULL; struct device *parent_dev = NULL; for (parent_dev = dev->tdev.parent; parent_dev != NULL; parent_dev = parent_dev->parent) { if (dev_is_pci(parent_dev)) { pcidev = to_pci_dev(parent_dev); if (pcidev->vendor == vendor_id) return true; break; } } return false; } static int ata_dev_config_ncq(struct ata_device *dev, char *desc, size_t desc_sz) { struct ata_port *ap = dev->link->ap; int hdepth = 0, ddepth = ata_id_queue_depth(dev->id); unsigned int err_mask; char *aa_desc = ""; if (!ata_id_has_ncq(dev->id)) { desc[0] = '\0'; return 0; } if (!IS_ENABLED(CONFIG_SATA_HOST)) return 0; if (dev->horkage & ATA_HORKAGE_NONCQ) { snprintf(desc, desc_sz, "NCQ (not used)"); return 0; } if (dev->horkage & ATA_HORKAGE_NO_NCQ_ON_ATI && ata_dev_check_adapter(dev, PCI_VENDOR_ID_ATI)) { snprintf(desc, desc_sz, "NCQ (not used)"); return 0; } if (ap->flags & ATA_FLAG_NCQ) { hdepth = min(ap->scsi_host->can_queue, ATA_MAX_QUEUE); dev->flags |= ATA_DFLAG_NCQ; } if (!(dev->horkage & ATA_HORKAGE_BROKEN_FPDMA_AA) && (ap->flags & ATA_FLAG_FPDMA_AA) && ata_id_has_fpdma_aa(dev->id)) { err_mask = ata_dev_set_feature(dev, SETFEATURES_SATA_ENABLE, SATA_FPDMA_AA); if (err_mask) { ata_dev_err(dev, "failed to enable AA (error_mask=0x%x)\n", err_mask); if (err_mask != AC_ERR_DEV) { dev->horkage |= ATA_HORKAGE_BROKEN_FPDMA_AA; return -EIO; } } else aa_desc = ", AA"; } if (hdepth >= ddepth) snprintf(desc, desc_sz, "NCQ (depth %d)%s", ddepth, aa_desc); else snprintf(desc, desc_sz, "NCQ (depth %d/%d)%s", hdepth, ddepth, aa_desc); if ((ap->flags & ATA_FLAG_FPDMA_AUX)) { if (ata_id_has_ncq_send_and_recv(dev->id)) ata_dev_config_ncq_send_recv(dev); if (ata_id_has_ncq_non_data(dev->id)) ata_dev_config_ncq_non_data(dev); if (ata_id_has_ncq_prio(dev->id)) ata_dev_config_ncq_prio(dev); } return 0; } static void ata_dev_config_sense_reporting(struct ata_device *dev) { unsigned int err_mask; if (!ata_id_has_sense_reporting(dev->id)) return; if (ata_id_sense_reporting_enabled(dev->id)) return; err_mask = ata_dev_set_feature(dev, SETFEATURE_SENSE_DATA, 0x1); if (err_mask) { ata_dev_dbg(dev, "failed to enable Sense Data Reporting, Emask 0x%x\n", err_mask); } } static void ata_dev_config_zac(struct ata_device *dev) { struct ata_port *ap = dev->link->ap; unsigned int err_mask; u8 *identify_buf = ap->sector_buf; dev->zac_zones_optimal_open = U32_MAX; dev->zac_zones_optimal_nonseq = U32_MAX; dev->zac_zones_max_open = U32_MAX; /* * Always set the 'ZAC' flag for Host-managed devices. */ if (dev->class == ATA_DEV_ZAC) dev->flags |= ATA_DFLAG_ZAC; else if (ata_id_zoned_cap(dev->id) == 0x01) /* * Check for host-aware devices. */ dev->flags |= ATA_DFLAG_ZAC; if (!(dev->flags & ATA_DFLAG_ZAC)) return; if (!ata_identify_page_supported(dev, ATA_LOG_ZONED_INFORMATION)) { ata_dev_warn(dev, "ATA Zoned Information Log not supported\n"); return; } /* * Read IDENTIFY DEVICE data log, page 9 (Zoned-device information) */ err_mask = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE, ATA_LOG_ZONED_INFORMATION, identify_buf, 1); if (!err_mask) { u64 zoned_cap, opt_open, opt_nonseq, max_open; zoned_cap = get_unaligned_le64(&identify_buf[8]); if ((zoned_cap >> 63)) dev->zac_zoned_cap = (zoned_cap & 1); opt_open = get_unaligned_le64(&identify_buf[24]); if ((opt_open >> 63)) dev->zac_zones_optimal_open = (u32)opt_open; opt_nonseq = get_unaligned_le64(&identify_buf[32]); if ((opt_nonseq >> 63)) dev->zac_zones_optimal_nonseq = (u32)opt_nonseq; max_open = get_unaligned_le64(&identify_buf[40]); if ((max_open >> 63)) dev->zac_zones_max_open = (u32)max_open; } } static void ata_dev_config_trusted(struct ata_device *dev) { struct ata_port *ap = dev->link->ap; u64 trusted_cap; unsigned int err; if (!ata_id_has_trusted(dev->id)) return; if (!ata_identify_page_supported(dev, ATA_LOG_SECURITY)) { ata_dev_warn(dev, "Security Log not supported\n"); return; } err = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE, ATA_LOG_SECURITY, ap->sector_buf, 1); if (err) { ata_dev_dbg(dev, "failed to read Security Log, Emask 0x%x\n", err); return; } trusted_cap = get_unaligned_le64(&ap->sector_buf[40]); if (!(trusted_cap & (1ULL << 63))) { ata_dev_dbg(dev, "Trusted Computing capability qword not valid!\n"); return; } if (trusted_cap & (1 << 0)) dev->flags |= ATA_DFLAG_TRUSTED; } /** * ata_dev_configure - Configure the specified ATA/ATAPI device * @dev: Target device to configure * * Configure @dev according to @dev->id. Generic and low-level * driver specific fixups are also applied. * * LOCKING: * Kernel thread context (may sleep) * * RETURNS: * 0 on success, -errno otherwise */ int ata_dev_configure(struct ata_device *dev) { struct ata_port *ap = dev->link->ap; struct ata_eh_context *ehc = &dev->link->eh_context; int print_info = ehc->i.flags & ATA_EHI_PRINTINFO; const u16 *id = dev->id; unsigned long xfer_mask; unsigned int err_mask; char revbuf[7]; /* XYZ-99\0 */ char fwrevbuf[ATA_ID_FW_REV_LEN+1]; char modelbuf[ATA_ID_PROD_LEN+1]; int rc; if (!ata_dev_enabled(dev) && ata_msg_info(ap)) { ata_dev_info(dev, "%s: ENTER/EXIT -- nodev\n", __func__); return 0; } if (ata_msg_probe(ap)) ata_dev_dbg(dev, "%s: ENTER\n", __func__); /* set horkage */ dev->horkage |= ata_dev_blacklisted(dev); ata_force_horkage(dev); if (dev->horkage & ATA_HORKAGE_DISABLE) { ata_dev_info(dev, "unsupported device, disabling\n"); ata_dev_disable(dev); return 0; } if ((!atapi_enabled || (ap->flags & ATA_FLAG_NO_ATAPI)) && dev->class == ATA_DEV_ATAPI) { ata_dev_warn(dev, "WARNING: ATAPI is %s, device ignored\n", atapi_enabled ? "not supported with this driver" : "disabled"); ata_dev_disable(dev); return 0; } rc = ata_do_link_spd_horkage(dev); if (rc) return rc; /* some WD SATA-1 drives have issues with LPM, turn on NOLPM for them */ if ((dev->horkage & ATA_HORKAGE_WD_BROKEN_LPM) && (id[ATA_ID_SATA_CAPABILITY] & 0xe) == 0x2) dev->horkage |= ATA_HORKAGE_NOLPM; if (ap->flags & ATA_FLAG_NO_LPM) dev->horkage |= ATA_HORKAGE_NOLPM; if (dev->horkage & ATA_HORKAGE_NOLPM) { ata_dev_warn(dev, "LPM support broken, forcing max_power\n"); dev->link->ap->target_lpm_policy = ATA_LPM_MAX_POWER; } /* let ACPI work its magic */ rc = ata_acpi_on_devcfg(dev); if (rc) return rc; /* massage HPA, do it early as it might change IDENTIFY data */ rc = ata_hpa_resize(dev); if (rc) return rc; /* print device capabilities */ if (ata_msg_probe(ap)) ata_dev_dbg(dev, "%s: cfg 49:%04x 82:%04x 83:%04x 84:%04x " "85:%04x 86:%04x 87:%04x 88:%04x\n", __func__, id[49], id[82], id[83], id[84], id[85], id[86], id[87], id[88]); /* initialize to-be-configured parameters */ dev->flags &= ~ATA_DFLAG_CFG_MASK; dev->max_sectors = 0; dev->cdb_len = 0; dev->n_sectors = 0; dev->cylinders = 0; dev->heads = 0; dev->sectors = 0; dev->multi_count = 0; /* * common ATA, ATAPI feature tests */ /* find max transfer mode; for printk only */ xfer_mask = ata_id_xfermask(id); if (ata_msg_probe(ap)) ata_dump_id(id); /* SCSI only uses 4-char revisions, dump full 8 chars from ATA */ ata_id_c_string(dev->id, fwrevbuf, ATA_ID_FW_REV, sizeof(fwrevbuf)); ata_id_c_string(dev->id, modelbuf, ATA_ID_PROD, sizeof(modelbuf)); /* ATA-specific feature tests */ if (dev->class == ATA_DEV_ATA || dev->class == ATA_DEV_ZAC) { if (ata_id_is_cfa(id)) { /* CPRM may make this media unusable */ if (id[ATA_ID_CFA_KEY_MGMT] & 1) ata_dev_warn(dev, "supports DRM functions and may not be fully accessible\n"); snprintf(revbuf, 7, "CFA"); } else { snprintf(revbuf, 7, "ATA-%d", ata_id_major_version(id)); /* Warn the user if the device has TPM extensions */ if (ata_id_has_tpm(id)) ata_dev_warn(dev, "supports DRM functions and may not be fully accessible\n"); } dev->n_sectors = ata_id_n_sectors(id); /* get current R/W Multiple count setting */ if ((dev->id[47] >> 8) == 0x80 && (dev->id[59] & 0x100)) { unsigned int max = dev->id[47] & 0xff; unsigned int cnt = dev->id[59] & 0xff; /* only recognize/allow powers of two here */ if (is_power_of_2(max) && is_power_of_2(cnt)) if (cnt <= max) dev->multi_count = cnt; } if (ata_id_has_lba(id)) { const char *lba_desc; char ncq_desc[24]; lba_desc = "LBA"; dev->flags |= ATA_DFLAG_LBA; if (ata_id_has_lba48(id)) { dev->flags |= ATA_DFLAG_LBA48; lba_desc = "LBA48"; if (dev->n_sectors >= (1UL << 28) && ata_id_has_flush_ext(id)) dev->flags |= ATA_DFLAG_FLUSH_EXT; } /* config NCQ */ rc = ata_dev_config_ncq(dev, ncq_desc, sizeof(ncq_desc)); if (rc) return rc; /* print device info to dmesg */ if (ata_msg_drv(ap) && print_info) { ata_dev_info(dev, "%s: %s, %s, max %s\n", revbuf, modelbuf, fwrevbuf, ata_mode_string(xfer_mask)); ata_dev_info(dev, "%llu sectors, multi %u: %s %s\n", (unsigned long long)dev->n_sectors, dev->multi_count, lba_desc, ncq_desc); } } else { /* CHS */ /* Default translation */ dev->cylinders = id[1]; dev->heads = id[3]; dev->sectors = id[6]; if (ata_id_current_chs_valid(id)) { /* Current CHS translation is valid. */ dev->cylinders = id[54]; dev->heads = id[55]; dev->sectors = id[56]; } /* print device info to dmesg */ if (ata_msg_drv(ap) && print_info) { ata_dev_info(dev, "%s: %s, %s, max %s\n", revbuf, modelbuf, fwrevbuf, ata_mode_string(xfer_mask)); ata_dev_info(dev, "%llu sectors, multi %u, CHS %u/%u/%u\n", (unsigned long long)dev->n_sectors, dev->multi_count, dev->cylinders, dev->heads, dev->sectors); } } /* Check and mark DevSlp capability. Get DevSlp timing variables * from SATA Settings page of Identify Device Data Log. */ if (ata_id_has_devslp(dev->id)) { u8 *sata_setting = ap->sector_buf; int i, j; dev->flags |= ATA_DFLAG_DEVSLP; err_mask = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE, ATA_LOG_SATA_SETTINGS, sata_setting, 1); if (err_mask) ata_dev_dbg(dev, "failed to get Identify Device Data, Emask 0x%x\n", err_mask); else for (i = 0; i < ATA_LOG_DEVSLP_SIZE; i++) { j = ATA_LOG_DEVSLP_OFFSET + i; dev->devslp_timing[i] = sata_setting[j]; } } ata_dev_config_sense_reporting(dev); ata_dev_config_zac(dev); ata_dev_config_trusted(dev); dev->cdb_len = 32; } /* ATAPI-specific feature tests */ else if (dev->class == ATA_DEV_ATAPI) { const char *cdb_intr_string = ""; const char *atapi_an_string = ""; const char *dma_dir_string = ""; u32 sntf; rc = atapi_cdb_len(id); if ((rc < 12) || (rc > ATAPI_CDB_LEN)) { if (ata_msg_warn(ap)) ata_dev_warn(dev, "unsupported CDB len\n"); rc = -EINVAL; goto err_out_nosup; } dev->cdb_len = (unsigned int) rc; /* Enable ATAPI AN if both the host and device have * the support. If PMP is attached, SNTF is required * to enable ATAPI AN to discern between PHY status * changed notifications and ATAPI ANs. */ if (atapi_an && (ap->flags & ATA_FLAG_AN) && ata_id_has_atapi_AN(id) && (!sata_pmp_attached(ap) || sata_scr_read(&ap->link, SCR_NOTIFICATION, &sntf) == 0)) { /* issue SET feature command to turn this on */ err_mask = ata_dev_set_feature(dev, SETFEATURES_SATA_ENABLE, SATA_AN); if (err_mask) ata_dev_err(dev, "failed to enable ATAPI AN (err_mask=0x%x)\n", err_mask); else { dev->flags |= ATA_DFLAG_AN; atapi_an_string = ", ATAPI AN"; } } if (ata_id_cdb_intr(dev->id)) { dev->flags |= ATA_DFLAG_CDB_INTR; cdb_intr_string = ", CDB intr"; } if (atapi_dmadir || (dev->horkage & ATA_HORKAGE_ATAPI_DMADIR) || atapi_id_dmadir(dev->id)) { dev->flags |= ATA_DFLAG_DMADIR; dma_dir_string = ", DMADIR"; } if (ata_id_has_da(dev->id)) { dev->flags |= ATA_DFLAG_DA; zpodd_init(dev); } /* print device info to dmesg */ if (ata_msg_drv(ap) && print_info) ata_dev_info(dev, "ATAPI: %s, %s, max %s%s%s%s\n", modelbuf, fwrevbuf, ata_mode_string(xfer_mask), cdb_intr_string, atapi_an_string, dma_dir_string); } /* determine max_sectors */ dev->max_sectors = ATA_MAX_SECTORS; if (dev->flags & ATA_DFLAG_LBA48) dev->max_sectors = ATA_MAX_SECTORS_LBA48; /* Limit PATA drive on SATA cable bridge transfers to udma5, 200 sectors */ if (ata_dev_knobble(dev)) { if (ata_msg_drv(ap) && print_info) ata_dev_info(dev, "applying bridge limits\n"); dev->udma_mask &= ATA_UDMA5; dev->max_sectors = ATA_MAX_SECTORS; } if ((dev->class == ATA_DEV_ATAPI) && (atapi_command_packet_set(id) == TYPE_TAPE)) { dev->max_sectors = ATA_MAX_SECTORS_TAPE; dev->horkage |= ATA_HORKAGE_STUCK_ERR; } if (dev->horkage & ATA_HORKAGE_MAX_SEC_128) dev->max_sectors = min_t(unsigned int, ATA_MAX_SECTORS_128, dev->max_sectors); if (dev->horkage & ATA_HORKAGE_MAX_SEC_1024) dev->max_sectors = min_t(unsigned int, ATA_MAX_SECTORS_1024, dev->max_sectors); if (dev->horkage & ATA_HORKAGE_MAX_SEC_LBA48) dev->max_sectors = ATA_MAX_SECTORS_LBA48; if (ap->ops->dev_config) ap->ops->dev_config(dev); if (dev->horkage & ATA_HORKAGE_DIAGNOSTIC) { /* Let the user know. We don't want to disallow opens for rescue purposes, or in case the vendor is just a blithering idiot. Do this after the dev_config call as some controllers with buggy firmware may want to avoid reporting false device bugs */ if (print_info) { ata_dev_warn(dev, "Drive reports diagnostics failure. This may indicate a drive\n"); ata_dev_warn(dev, "fault or invalid emulation. Contact drive vendor for information.\n"); } } if ((dev->horkage & ATA_HORKAGE_FIRMWARE_WARN) && print_info) { ata_dev_warn(dev, "WARNING: device requires firmware update to be fully functional\n"); ata_dev_warn(dev, " contact the vendor or visit http://ata.wiki.kernel.org\n"); } return 0; err_out_nosup: if (ata_msg_probe(ap)) ata_dev_dbg(dev, "%s: EXIT, err\n", __func__); return rc; } /** * ata_cable_40wire - return 40 wire cable type * @ap: port * * Helper method for drivers which want to hardwire 40 wire cable * detection. */ int ata_cable_40wire(struct ata_port *ap) { return ATA_CBL_PATA40; } EXPORT_SYMBOL_GPL(ata_cable_40wire); /** * ata_cable_80wire - return 80 wire cable type * @ap: port * * Helper method for drivers which want to hardwire 80 wire cable * detection. */ int ata_cable_80wire(struct ata_port *ap) { return ATA_CBL_PATA80; } EXPORT_SYMBOL_GPL(ata_cable_80wire); /** * ata_cable_unknown - return unknown PATA cable. * @ap: port * * Helper method for drivers which have no PATA cable detection. */ int ata_cable_unknown(struct ata_port *ap) { return ATA_CBL_PATA_UNK; } EXPORT_SYMBOL_GPL(ata_cable_unknown); /** * ata_cable_ignore - return ignored PATA cable. * @ap: port * * Helper method for drivers which don't use cable type to limit * transfer mode. */ int ata_cable_ignore(struct ata_port *ap) { return ATA_CBL_PATA_IGN; } EXPORT_SYMBOL_GPL(ata_cable_ignore); /** * ata_cable_sata - return SATA cable type * @ap: port * * Helper method for drivers which have SATA cables */ int ata_cable_sata(struct ata_port *ap) { return ATA_CBL_SATA; } EXPORT_SYMBOL_GPL(ata_cable_sata); /** * ata_bus_probe - Reset and probe ATA bus * @ap: Bus to probe * * Master ATA bus probing function. Initiates a hardware-dependent * bus reset, then attempts to identify any devices found on * the bus. * * LOCKING: * PCI/etc. bus probe sem. * * RETURNS: * Zero on success, negative errno otherwise. */ int ata_bus_probe(struct ata_port *ap) { unsigned int classes[ATA_MAX_DEVICES]; int tries[ATA_MAX_DEVICES]; int rc; struct ata_device *dev; ata_for_each_dev(dev, &ap->link, ALL) tries[dev->devno] = ATA_PROBE_MAX_TRIES; retry: ata_for_each_dev(dev, &ap->link, ALL) { /* If we issue an SRST then an ATA drive (not ATAPI) * may change configuration and be in PIO0 timing. If * we do a hard reset (or are coming from power on) * this is true for ATA or ATAPI. Until we've set a * suitable controller mode we should not touch the * bus as we may be talking too fast. */ dev->pio_mode = XFER_PIO_0; dev->dma_mode = 0xff; /* If the controller has a pio mode setup function * then use it to set the chipset to rights. Don't * touch the DMA setup as that will be dealt with when * configuring devices. */ if (ap->ops->set_piomode) ap->ops->set_piomode(ap, dev); } /* reset and determine device classes */ ap->ops->phy_reset(ap); ata_for_each_dev(dev, &ap->link, ALL) { if (dev->class != ATA_DEV_UNKNOWN) classes[dev->devno] = dev->class; else classes[dev->devno] = ATA_DEV_NONE; dev->class = ATA_DEV_UNKNOWN; } /* read IDENTIFY page and configure devices. We have to do the identify specific sequence bass-ackwards so that PDIAG- is released by the slave device */ ata_for_each_dev(dev, &ap->link, ALL_REVERSE) { if (tries[dev->devno]) dev->class = classes[dev->devno]; if (!ata_dev_enabled(dev)) continue; rc = ata_dev_read_id(dev, &dev->class, ATA_READID_POSTRESET, dev->id); if (rc) goto fail; } /* Now ask for the cable type as PDIAG- should have been released */ if (ap->ops->cable_detect) ap->cbl = ap->ops->cable_detect(ap); /* We may have SATA bridge glue hiding here irrespective of * the reported cable types and sensed types. When SATA * drives indicate we have a bridge, we don't know which end * of the link the bridge is which is a problem. */ ata_for_each_dev(dev, &ap->link, ENABLED) if (ata_id_is_sata(dev->id)) ap->cbl = ATA_CBL_SATA; /* After the identify sequence we can now set up the devices. We do this in the normal order so that the user doesn't get confused */ ata_for_each_dev(dev, &ap->link, ENABLED) { ap->link.eh_context.i.flags |= ATA_EHI_PRINTINFO; rc = ata_dev_configure(dev); ap->link.eh_context.i.flags &= ~ATA_EHI_PRINTINFO; if (rc) goto fail; } /* configure transfer mode */ rc = ata_set_mode(&ap->link, &dev); if (rc) goto fail; ata_for_each_dev(dev, &ap->link, ENABLED) return 0; return -ENODEV; fail: tries[dev->devno]--; switch (rc) { case -EINVAL: /* eeek, something went very wrong, give up */ tries[dev->devno] = 0; break; case -ENODEV: /* give it just one more chance */ tries[dev->devno] = min(tries[dev->devno], 1); fallthrough; case -EIO: if (tries[dev->devno] == 1) { /* This is the last chance, better to slow * down than lose it. */ sata_down_spd_limit(&ap->link, 0); ata_down_xfermask_limit(dev, ATA_DNXFER_PIO); } } if (!tries[dev->devno]) ata_dev_disable(dev); goto retry; } /** * sata_print_link_status - Print SATA link status * @link: SATA link to printk link status about * * This function prints link speed and status of a SATA link. * * LOCKING: * None. */ static void sata_print_link_status(struct ata_link *link) { u32 sstatus, scontrol, tmp; if (sata_scr_read(link, SCR_STATUS, &sstatus)) return; sata_scr_read(link, SCR_CONTROL, &scontrol); if (ata_phys_link_online(link)) { tmp = (sstatus >> 4) & 0xf; ata_link_info(link, "SATA link up %s (SStatus %X SControl %X)\n", sata_spd_string(tmp), sstatus, scontrol); } else { ata_link_info(link, "SATA link down (SStatus %X SControl %X)\n", sstatus, scontrol); } } /** * ata_dev_pair - return other device on cable * @adev: device * * Obtain the other device on the same cable, or if none is * present NULL is returned */ struct ata_device *ata_dev_pair(struct ata_device *adev) { struct ata_link *link = adev->link; struct ata_device *pair = &link->device[1 - adev->devno]; if (!ata_dev_enabled(pair)) return NULL; return pair; } EXPORT_SYMBOL_GPL(ata_dev_pair); /** * sata_down_spd_limit - adjust SATA spd limit downward * @link: Link to adjust SATA spd limit for * @spd_limit: Additional limit * * Adjust SATA spd limit of @link downward. Note that this * function only adjusts the limit. The change must be applied * using sata_set_spd(). * * If @spd_limit is non-zero, the speed is limited to equal to or * lower than @spd_limit if such speed is supported. If * @spd_limit is slower than any supported speed, only the lowest * supported speed is allowed. * * LOCKING: * Inherited from caller. * * RETURNS: * 0 on success, negative errno on failure */ int sata_down_spd_limit(struct ata_link *link, u32 spd_limit) { u32 sstatus, spd, mask; int rc, bit; if (!sata_scr_valid(link)) return -EOPNOTSUPP; /* If SCR can be read, use it to determine the current SPD. * If not, use cached value in link->sata_spd. */ rc = sata_scr_read(link, SCR_STATUS, &sstatus); if (rc == 0 && ata_sstatus_online(sstatus)) spd = (sstatus >> 4) & 0xf; else spd = link->sata_spd; mask = link->sata_spd_limit; if (mask <= 1) return -EINVAL; /* unconditionally mask off the highest bit */ bit = fls(mask) - 1; mask &= ~(1 << bit); /* * Mask off all speeds higher than or equal to the current one. At * this point, if current SPD is not available and we previously * recorded the link speed from SStatus, the driver has already * masked off the highest bit so mask should already be 1 or 0. * Otherwise, we should not force 1.5Gbps on a link where we have * not previously recorded speed from SStatus. Just return in this * case. */ if (spd > 1) mask &= (1 << (spd - 1)) - 1; else return -EINVAL; /* were we already at the bottom? */ if (!mask) return -EINVAL; if (spd_limit) { if (mask & ((1 << spd_limit) - 1)) mask &= (1 << spd_limit) - 1; else { bit = ffs(mask) - 1; mask = 1 << bit; } } link->sata_spd_limit = mask; ata_link_warn(link, "limiting SATA link speed to %s\n", sata_spd_string(fls(mask))); return 0; } #ifdef CONFIG_ATA_ACPI /** * ata_timing_cycle2mode - find xfer mode for the specified cycle duration * @xfer_shift: ATA_SHIFT_* value for transfer type to examine. * @cycle: cycle duration in ns * * Return matching xfer mode for @cycle. The returned mode is of * the transfer type specified by @xfer_shift. If @cycle is too * slow for @xfer_shift, 0xff is returned. If @cycle is faster * than the fastest known mode, the fasted mode is returned. * * LOCKING: * None. * * RETURNS: * Matching xfer_mode, 0xff if no match found. */ u8 ata_timing_cycle2mode(unsigned int xfer_shift, int cycle) { u8 base_mode = 0xff, last_mode = 0xff; const struct ata_xfer_ent *ent; const struct ata_timing *t; for (ent = ata_xfer_tbl; ent->shift >= 0; ent++) if (ent->shift == xfer_shift) base_mode = ent->base; for (t = ata_timing_find_mode(base_mode); t && ata_xfer_mode2shift(t->mode) == xfer_shift; t++) { unsigned short this_cycle; switch (xfer_shift) { case ATA_SHIFT_PIO: case ATA_SHIFT_MWDMA: this_cycle = t->cycle; break; case ATA_SHIFT_UDMA: this_cycle = t->udma; break; default: return 0xff; } if (cycle > this_cycle) break; last_mode = t->mode; } return last_mode; } #endif /** * ata_down_xfermask_limit - adjust dev xfer masks downward * @dev: Device to adjust xfer masks * @sel: ATA_DNXFER_* selector * * Adjust xfer masks of @dev downward. Note that this function * does not apply the change. Invoking ata_set_mode() afterwards * will apply the limit. * * LOCKING: * Inherited from caller. * * RETURNS: * 0 on success, negative errno on failure */ int ata_down_xfermask_limit(struct ata_device *dev, unsigned int sel) { char buf[32]; unsigned long orig_mask, xfer_mask; unsigned long pio_mask, mwdma_mask, udma_mask; int quiet, highbit; quiet = !!(sel & ATA_DNXFER_QUIET); sel &= ~ATA_DNXFER_QUIET; xfer_mask = orig_mask = ata_pack_xfermask(dev->pio_mask, dev->mwdma_mask, dev->udma_mask); ata_unpack_xfermask(xfer_mask, &pio_mask, &mwdma_mask, &udma_mask); switch (sel) { case ATA_DNXFER_PIO: highbit = fls(pio_mask) - 1; pio_mask &= ~(1 << highbit); break; case ATA_DNXFER_DMA: if (udma_mask) { highbit = fls(udma_mask) - 1; udma_mask &= ~(1 << highbit); if (!udma_mask) return -ENOENT; } else if (mwdma_mask) { highbit = fls(mwdma_mask) - 1; mwdma_mask &= ~(1 << highbit); if (!mwdma_mask) return -ENOENT; } break; case ATA_DNXFER_40C: udma_mask &= ATA_UDMA_MASK_40C; break; case ATA_DNXFER_FORCE_PIO0: pio_mask &= 1; fallthrough; case ATA_DNXFER_FORCE_PIO: mwdma_mask = 0; udma_mask = 0; break; default: BUG(); } xfer_mask &= ata_pack_xfermask(pio_mask, mwdma_mask, udma_mask); if (!(xfer_mask & ATA_MASK_PIO) || xfer_mask == orig_mask) return -ENOENT; if (!quiet) { if (xfer_mask & (ATA_MASK_MWDMA | ATA_MASK_UDMA)) snprintf(buf, sizeof(buf), "%s:%s", ata_mode_string(xfer_mask), ata_mode_string(xfer_mask & ATA_MASK_PIO)); else snprintf(buf, sizeof(buf), "%s", ata_mode_string(xfer_mask)); ata_dev_warn(dev, "limiting speed to %s\n", buf); } ata_unpack_xfermask(xfer_mask, &dev->pio_mask, &dev->mwdma_mask, &dev->udma_mask); return 0; } static int ata_dev_set_mode(struct ata_device *dev) { struct ata_port *ap = dev->link->ap; struct ata_eh_context *ehc = &dev->link->eh_context; const bool nosetxfer = dev->horkage & ATA_HORKAGE_NOSETXFER; const char *dev_err_whine = ""; int ign_dev_err = 0; unsigned int err_mask = 0; int rc; dev->flags &= ~ATA_DFLAG_PIO; if (dev->xfer_shift == ATA_SHIFT_PIO) dev->flags |= ATA_DFLAG_PIO; if (nosetxfer && ap->flags & ATA_FLAG_SATA && ata_id_is_sata(dev->id)) dev_err_whine = " (SET_XFERMODE skipped)"; else { if (nosetxfer) ata_dev_warn(dev, "NOSETXFER but PATA detected - can't " "skip SETXFER, might malfunction\n"); err_mask = ata_dev_set_xfermode(dev); } if (err_mask & ~AC_ERR_DEV) goto fail; /* revalidate */ ehc->i.flags |= ATA_EHI_POST_SETMODE; rc = ata_dev_revalidate(dev, ATA_DEV_UNKNOWN, 0); ehc->i.flags &= ~ATA_EHI_POST_SETMODE; if (rc) return rc; if (dev->xfer_shift == ATA_SHIFT_PIO) { /* Old CFA may refuse this command, which is just fine */ if (ata_id_is_cfa(dev->id)) ign_dev_err = 1; /* Catch several broken garbage emulations plus some pre ATA devices */ if (ata_id_major_version(dev->id) == 0 && dev->pio_mode <= XFER_PIO_2) ign_dev_err = 1; /* Some very old devices and some bad newer ones fail any kind of SET_XFERMODE request but support PIO0-2 timings and no IORDY */ if (!ata_id_has_iordy(dev->id) && dev->pio_mode <= XFER_PIO_2) ign_dev_err = 1; } /* Early MWDMA devices do DMA but don't allow DMA mode setting. Don't fail an MWDMA0 set IFF the device indicates it is in MWDMA0 */ if (dev->xfer_shift == ATA_SHIFT_MWDMA && dev->dma_mode == XFER_MW_DMA_0 && (dev->id[63] >> 8) & 1) ign_dev_err = 1; /* if the device is actually configured correctly, ignore dev err */ if (dev->xfer_mode == ata_xfer_mask2mode(ata_id_xfermask(dev->id))) ign_dev_err = 1; if (err_mask & AC_ERR_DEV) { if (!ign_dev_err) goto fail; else dev_err_whine = " (device error ignored)"; } DPRINTK("xfer_shift=%u, xfer_mode=0x%x\n", dev->xfer_shift, (int)dev->xfer_mode); if (!(ehc->i.flags & ATA_EHI_QUIET) || ehc->i.flags & ATA_EHI_DID_HARDRESET) ata_dev_info(dev, "configured for %s%s\n", ata_mode_string(ata_xfer_mode2mask(dev->xfer_mode)), dev_err_whine); return 0; fail: ata_dev_err(dev, "failed to set xfermode (err_mask=0x%x)\n", err_mask); return -EIO; } /** * ata_do_set_mode - Program timings and issue SET FEATURES - XFER * @link: link on which timings will be programmed * @r_failed_dev: out parameter for failed device * * Standard implementation of the function used to tune and set * ATA device disk transfer mode (PIO3, UDMA6, etc.). If * ata_dev_set_mode() fails, pointer to the failing device is * returned in @r_failed_dev. * * LOCKING: * PCI/etc. bus probe sem. * * RETURNS: * 0 on success, negative errno otherwise */ int ata_do_set_mode(struct ata_link *link, struct ata_device **r_failed_dev) { struct ata_port *ap = link->ap; struct ata_device *dev; int rc = 0, used_dma = 0, found = 0; /* step 1: calculate xfer_mask */ ata_for_each_dev(dev, link, ENABLED) { unsigned long pio_mask, dma_mask; unsigned int mode_mask; mode_mask = ATA_DMA_MASK_ATA; if (dev->class == ATA_DEV_ATAPI) mode_mask = ATA_DMA_MASK_ATAPI; else if (ata_id_is_cfa(dev->id)) mode_mask = ATA_DMA_MASK_CFA; ata_dev_xfermask(dev); ata_force_xfermask(dev); pio_mask = ata_pack_xfermask(dev->pio_mask, 0, 0); if (libata_dma_mask & mode_mask) dma_mask = ata_pack_xfermask(0, dev->mwdma_mask, dev->udma_mask); else dma_mask = 0; dev->pio_mode = ata_xfer_mask2mode(pio_mask); dev->dma_mode = ata_xfer_mask2mode(dma_mask); found = 1; if (ata_dma_enabled(dev)) used_dma = 1; } if (!found) goto out; /* step 2: always set host PIO timings */ ata_for_each_dev(dev, link, ENABLED) { if (dev->pio_mode == 0xff) { ata_dev_warn(dev, "no PIO support\n"); rc = -EINVAL; goto out; } dev->xfer_mode = dev->pio_mode; dev->xfer_shift = ATA_SHIFT_PIO; if (ap->ops->set_piomode) ap->ops->set_piomode(ap, dev); } /* step 3: set host DMA timings */ ata_for_each_dev(dev, link, ENABLED) { if (!ata_dma_enabled(dev)) continue; dev->xfer_mode = dev->dma_mode; dev->xfer_shift = ata_xfer_mode2shift(dev->dma_mode); if (ap->ops->set_dmamode) ap->ops->set_dmamode(ap, dev); } /* step 4: update devices' xfer mode */ ata_for_each_dev(dev, link, ENABLED) { rc = ata_dev_set_mode(dev); if (rc) goto out; } /* Record simplex status. If we selected DMA then the other * host channels are not permitted to do so. */ if (used_dma && (ap->host->flags & ATA_HOST_SIMPLEX)) ap->host->simplex_claimed = ap; out: if (rc) *r_failed_dev = dev; return rc; } EXPORT_SYMBOL_GPL(ata_do_set_mode); /** * ata_wait_ready - wait for link to become ready * @link: link to be waited on * @deadline: deadline jiffies for the operation * @check_ready: callback to check link readiness * * Wait for @link to become ready. @check_ready should return * positive number if @link is ready, 0 if it isn't, -ENODEV if * link doesn't seem to be occupied, other errno for other error * conditions. * * Transient -ENODEV conditions are allowed for * ATA_TMOUT_FF_WAIT. * * LOCKING: * EH context. * * RETURNS: * 0 if @link is ready before @deadline; otherwise, -errno. */ int ata_wait_ready(struct ata_link *link, unsigned long deadline, int (*check_ready)(struct ata_link *link)) { unsigned long start = jiffies; unsigned long nodev_deadline; int warned = 0; /* choose which 0xff timeout to use, read comment in libata.h */ if (link->ap->host->flags & ATA_HOST_PARALLEL_SCAN) nodev_deadline = ata_deadline(start, ATA_TMOUT_FF_WAIT_LONG); else nodev_deadline = ata_deadline(start, ATA_TMOUT_FF_WAIT); /* Slave readiness can't be tested separately from master. On * M/S emulation configuration, this function should be called * only on the master and it will handle both master and slave. */ WARN_ON(link == link->ap->slave_link); if (time_after(nodev_deadline, deadline)) nodev_deadline = deadline; while (1) { unsigned long now = jiffies; int ready, tmp; ready = tmp = check_ready(link); if (ready > 0) return 0; /* * -ENODEV could be transient. Ignore -ENODEV if link * is online. Also, some SATA devices take a long * time to clear 0xff after reset. Wait for * ATA_TMOUT_FF_WAIT[_LONG] on -ENODEV if link isn't * offline. * * Note that some PATA controllers (pata_ali) explode * if status register is read more than once when * there's no device attached. */ if (ready == -ENODEV) { if (ata_link_online(link)) ready = 0; else if ((link->ap->flags & ATA_FLAG_SATA) && !ata_link_offline(link) && time_before(now, nodev_deadline)) ready = 0; } if (ready) return ready; if (time_after(now, deadline)) return -EBUSY; if (!warned && time_after(now, start + 5 * HZ) && (deadline - now > 3 * HZ)) { ata_link_warn(link, "link is slow to respond, please be patient " "(ready=%d)\n", tmp); warned = 1; } ata_msleep(link->ap, 50); } } /** * ata_wait_after_reset - wait for link to become ready after reset * @link: link to be waited on * @deadline: deadline jiffies for the operation * @check_ready: callback to check link readiness * * Wait for @link to become ready after reset. * * LOCKING: * EH context. * * RETURNS: * 0 if @link is ready before @deadline; otherwise, -errno. */ int ata_wait_after_reset(struct ata_link *link, unsigned long deadline, int (*check_ready)(struct ata_link *link)) { ata_msleep(link->ap, ATA_WAIT_AFTER_RESET); return ata_wait_ready(link, deadline, check_ready); } EXPORT_SYMBOL_GPL(ata_wait_after_reset); /** * ata_std_prereset - prepare for reset * @link: ATA link to be reset * @deadline: deadline jiffies for the operation * * @link is about to be reset. Initialize it. Failure from * prereset makes libata abort whole reset sequence and give up * that port, so prereset should be best-effort. It does its * best to prepare for reset sequence but if things go wrong, it * should just whine, not fail. * * LOCKING: * Kernel thread context (may sleep) * * RETURNS: * 0 on success, -errno otherwise. */ int ata_std_prereset(struct ata_link *link, unsigned long deadline) { struct ata_port *ap = link->ap; struct ata_eh_context *ehc = &link->eh_context; const unsigned long *timing = sata_ehc_deb_timing(ehc); int rc; /* if we're about to do hardreset, nothing more to do */ if (ehc->i.action & ATA_EH_HARDRESET) return 0; /* if SATA, resume link */ if (ap->flags & ATA_FLAG_SATA) { rc = sata_link_resume(link, timing, deadline); /* whine about phy resume failure but proceed */ if (rc && rc != -EOPNOTSUPP) ata_link_warn(link, "failed to resume link for reset (errno=%d)\n", rc); } /* no point in trying softreset on offline link */ if (ata_phys_link_offline(link)) ehc->i.action &= ~ATA_EH_SOFTRESET; return 0; } EXPORT_SYMBOL_GPL(ata_std_prereset); /** * sata_std_hardreset - COMRESET w/o waiting or classification * @link: link to reset * @class: resulting class of attached device * @deadline: deadline jiffies for the operation * * Standard SATA COMRESET w/o waiting or classification. * * LOCKING: * Kernel thread context (may sleep) * * RETURNS: * 0 if link offline, -EAGAIN if link online, -errno on errors. */ int sata_std_hardreset(struct ata_link *link, unsigned int *class, unsigned long deadline) { const unsigned long *timing = sata_ehc_deb_timing(&link->eh_context); bool online; int rc; /* do hardreset */ rc = sata_link_hardreset(link, timing, deadline, &online, NULL); return online ? -EAGAIN : rc; } EXPORT_SYMBOL_GPL(sata_std_hardreset); /** * ata_std_postreset - standard postreset callback * @link: the target ata_link * @classes: classes of attached devices * * This function is invoked after a successful reset. Note that * the device might have been reset more than once using * different reset methods before postreset is invoked. * * LOCKING: * Kernel thread context (may sleep) */ void ata_std_postreset(struct ata_link *link, unsigned int *classes) { u32 serror; DPRINTK("ENTER\n"); /* reset complete, clear SError */ if (!sata_scr_read(link, SCR_ERROR, &serror)) sata_scr_write(link, SCR_ERROR, serror); /* print link status */ sata_print_link_status(link); DPRINTK("EXIT\n"); } EXPORT_SYMBOL_GPL(ata_std_postreset); /** * ata_dev_same_device - Determine whether new ID matches configured device * @dev: device to compare against * @new_class: class of the new device * @new_id: IDENTIFY page of the new device * * Compare @new_class and @new_id against @dev and determine * whether @dev is the device indicated by @new_class and * @new_id. * * LOCKING: * None. * * RETURNS: * 1 if @dev matches @new_class and @new_id, 0 otherwise. */ static int ata_dev_same_device(struct ata_device *dev, unsigned int new_class, const u16 *new_id) { const u16 *old_id = dev->id; unsigned char model[2][ATA_ID_PROD_LEN + 1]; unsigned char serial[2][ATA_ID_SERNO_LEN + 1]; if (dev->class != new_class) { ata_dev_info(dev, "class mismatch %d != %d\n", dev->class, new_class); return 0; } ata_id_c_string(old_id, model[0], ATA_ID_PROD, sizeof(model[0])); ata_id_c_string(new_id, model[1], ATA_ID_PROD, sizeof(model[1])); ata_id_c_string(old_id, serial[0], ATA_ID_SERNO, sizeof(serial[0])); ata_id_c_string(new_id, serial[1], ATA_ID_SERNO, sizeof(serial[1])); if (strcmp(model[0], model[1])) { ata_dev_info(dev, "model number mismatch '%s' != '%s'\n", model[0], model[1]); return 0; } if (strcmp(serial[0], serial[1])) { ata_dev_info(dev, "serial number mismatch '%s' != '%s'\n", serial[0], serial[1]); return 0; } return 1; } /** * ata_dev_reread_id - Re-read IDENTIFY data * @dev: target ATA device * @readid_flags: read ID flags * * Re-read IDENTIFY page and make sure @dev is still attached to * the port. * * LOCKING: * Kernel thread context (may sleep) * * RETURNS: * 0 on success, negative errno otherwise */ int ata_dev_reread_id(struct ata_device *dev, unsigned int readid_flags) { unsigned int class = dev->class; u16 *id = (void *)dev->link->ap->sector_buf; int rc; /* read ID data */ rc = ata_dev_read_id(dev, &class, readid_flags, id); if (rc) return rc; /* is the device still there? */ if (!ata_dev_same_device(dev, class, id)) return -ENODEV; memcpy(dev->id, id, sizeof(id[0]) * ATA_ID_WORDS); return 0; } /** * ata_dev_revalidate - Revalidate ATA device * @dev: device to revalidate * @new_class: new class code * @readid_flags: read ID flags * * Re-read IDENTIFY page, make sure @dev is still attached to the * port and reconfigure it according to the new IDENTIFY page. * * LOCKING: * Kernel thread context (may sleep) * * RETURNS: * 0 on success, negative errno otherwise */ int ata_dev_revalidate(struct ata_device *dev, unsigned int new_class, unsigned int readid_flags) { u64 n_sectors = dev->n_sectors; u64 n_native_sectors = dev->n_native_sectors; int rc; if (!ata_dev_enabled(dev)) return -ENODEV; /* fail early if !ATA && !ATAPI to avoid issuing [P]IDENTIFY to PMP */ if (ata_class_enabled(new_class) && new_class != ATA_DEV_ATA && new_class != ATA_DEV_ATAPI && new_class != ATA_DEV_ZAC && new_class != ATA_DEV_SEMB) { ata_dev_info(dev, "class mismatch %u != %u\n", dev->class, new_class); rc = -ENODEV; goto fail; } /* re-read ID */ rc = ata_dev_reread_id(dev, readid_flags); if (rc) goto fail; /* configure device according to the new ID */ rc = ata_dev_configure(dev); if (rc) goto fail; /* verify n_sectors hasn't changed */ if (dev->class != ATA_DEV_ATA || !n_sectors || dev->n_sectors == n_sectors) return 0; /* n_sectors has changed */ ata_dev_warn(dev, "n_sectors mismatch %llu != %llu\n", (unsigned long long)n_sectors, (unsigned long long)dev->n_sectors); /* * Something could have caused HPA to be unlocked * involuntarily. If n_native_sectors hasn't changed and the * new size matches it, keep the device. */ if (dev->n_native_sectors == n_native_sectors && dev->n_sectors > n_sectors && dev->n_sectors == n_native_sectors) { ata_dev_warn(dev, "new n_sectors matches native, probably " "late HPA unlock, n_sectors updated\n"); /* use the larger n_sectors */ return 0; } /* * Some BIOSes boot w/o HPA but resume w/ HPA locked. Try * unlocking HPA in those cases. * * https://bugzilla.kernel.org/show_bug.cgi?id=15396 */ if (dev->n_native_sectors == n_native_sectors && dev->n_sectors < n_sectors && n_sectors == n_native_sectors && !(dev->horkage & ATA_HORKAGE_BROKEN_HPA)) { ata_dev_warn(dev, "old n_sectors matches native, probably " "late HPA lock, will try to unlock HPA\n"); /* try unlocking HPA */ dev->flags |= ATA_DFLAG_UNLOCK_HPA; rc = -EIO; } else rc = -ENODEV; /* restore original n_[native_]sectors and fail */ dev->n_native_sectors = n_native_sectors; dev->n_sectors = n_sectors; fail: ata_dev_err(dev, "revalidation failed (errno=%d)\n", rc); return rc; } struct ata_blacklist_entry { const char *model_num; const char *model_rev; unsigned long horkage; }; static const struct ata_blacklist_entry ata_device_blacklist [] = { /* Devices with DMA related problems under Linux */ { "WDC AC11000H", NULL, ATA_HORKAGE_NODMA }, { "WDC AC22100H", NULL, ATA_HORKAGE_NODMA }, { "WDC AC32500H", NULL, ATA_HORKAGE_NODMA }, { "WDC AC33100H", NULL, ATA_HORKAGE_NODMA }, { "WDC AC31600H", NULL, ATA_HORKAGE_NODMA }, { "WDC AC32100H", "24.09P07", ATA_HORKAGE_NODMA }, { "WDC AC23200L", "21.10N21", ATA_HORKAGE_NODMA }, { "Compaq CRD-8241B", NULL, ATA_HORKAGE_NODMA }, { "CRD-8400B", NULL, ATA_HORKAGE_NODMA }, { "CRD-848[02]B", NULL, ATA_HORKAGE_NODMA }, { "CRD-84", NULL, ATA_HORKAGE_NODMA }, { "SanDisk SDP3B", NULL, ATA_HORKAGE_NODMA }, { "SanDisk SDP3B-64", NULL, ATA_HORKAGE_NODMA }, { "SANYO CD-ROM CRD", NULL, ATA_HORKAGE_NODMA }, { "HITACHI CDR-8", NULL, ATA_HORKAGE_NODMA }, { "HITACHI CDR-8[34]35",NULL, ATA_HORKAGE_NODMA }, { "Toshiba CD-ROM XM-6202B", NULL, ATA_HORKAGE_NODMA }, { "TOSHIBA CD-ROM XM-1702BC", NULL, ATA_HORKAGE_NODMA }, { "CD-532E-A", NULL, ATA_HORKAGE_NODMA }, { "E-IDE CD-ROM CR-840",NULL, ATA_HORKAGE_NODMA }, { "CD-ROM Drive/F5A", NULL, ATA_HORKAGE_NODMA }, { "WPI CDD-820", NULL, ATA_HORKAGE_NODMA }, { "SAMSUNG CD-ROM SC-148C", NULL, ATA_HORKAGE_NODMA }, { "SAMSUNG CD-ROM SC", NULL, ATA_HORKAGE_NODMA }, { "ATAPI CD-ROM DRIVE 40X MAXIMUM",NULL,ATA_HORKAGE_NODMA }, { "_NEC DV5800A", NULL, ATA_HORKAGE_NODMA }, { "SAMSUNG CD-ROM SN-124", "N001", ATA_HORKAGE_NODMA }, { "Seagate STT20000A", NULL, ATA_HORKAGE_NODMA }, { " 2GB ATA Flash Disk", "ADMA428M", ATA_HORKAGE_NODMA }, { "VRFDFC22048UCHC-TE*", NULL, ATA_HORKAGE_NODMA }, /* Odd clown on sil3726/4726 PMPs */ { "Config Disk", NULL, ATA_HORKAGE_DISABLE }, /* Similar story with ASMedia 1092 */ { "ASMT109x- Config", NULL, ATA_HORKAGE_DISABLE }, /* Weird ATAPI devices */ { "TORiSAN DVD-ROM DRD-N216", NULL, ATA_HORKAGE_MAX_SEC_128 }, { "QUANTUM DAT DAT72-000", NULL, ATA_HORKAGE_ATAPI_MOD16_DMA }, { "Slimtype DVD A DS8A8SH", NULL, ATA_HORKAGE_MAX_SEC_LBA48 }, { "Slimtype DVD A DS8A9SH", NULL, ATA_HORKAGE_MAX_SEC_LBA48 }, /* * Causes silent data corruption with higher max sects. * http://lkml.kernel.org/g/x49wpy40ysk.fsf@segfault.boston.devel.redhat.com */ { "ST380013AS", "3.20", ATA_HORKAGE_MAX_SEC_1024 }, /* * These devices time out with higher max sects. * https://bugzilla.kernel.org/show_bug.cgi?id=121671 */ { "LITEON CX1-JB*-HP", NULL, ATA_HORKAGE_MAX_SEC_1024 }, { "LITEON EP1-*", NULL, ATA_HORKAGE_MAX_SEC_1024 }, /* Devices we expect to fail diagnostics */ /* Devices where NCQ should be avoided */ /* NCQ is slow */ { "WDC WD740ADFD-00", NULL, ATA_HORKAGE_NONCQ }, { "WDC WD740ADFD-00NLR1", NULL, ATA_HORKAGE_NONCQ, }, /* http://thread.gmane.org/gmane.linux.ide/14907 */ { "FUJITSU MHT2060BH", NULL, ATA_HORKAGE_NONCQ }, /* NCQ is broken */ { "Maxtor *", "BANC*", ATA_HORKAGE_NONCQ }, { "Maxtor 7V300F0", "VA111630", ATA_HORKAGE_NONCQ }, { "ST380817AS", "3.42", ATA_HORKAGE_NONCQ }, { "ST3160023AS", "3.42", ATA_HORKAGE_NONCQ }, { "OCZ CORE_SSD", "02.10104", ATA_HORKAGE_NONCQ }, /* Seagate NCQ + FLUSH CACHE firmware bug */ { "ST31500341AS", "SD1[5-9]", ATA_HORKAGE_NONCQ | ATA_HORKAGE_FIRMWARE_WARN }, { "ST31000333AS", "SD1[5-9]", ATA_HORKAGE_NONCQ | ATA_HORKAGE_FIRMWARE_WARN }, { "ST3640[36]23AS", "SD1[5-9]", ATA_HORKAGE_NONCQ | ATA_HORKAGE_FIRMWARE_WARN }, { "ST3320[68]13AS", "SD1[5-9]", ATA_HORKAGE_NONCQ | ATA_HORKAGE_FIRMWARE_WARN }, /* drives which fail FPDMA_AA activation (some may freeze afterwards) the ST disks also have LPM issues */ { "ST1000LM024 HN-M101MBB", NULL, ATA_HORKAGE_BROKEN_FPDMA_AA | ATA_HORKAGE_NOLPM, }, { "VB0250EAVER", "HPG7", ATA_HORKAGE_BROKEN_FPDMA_AA }, /* Blacklist entries taken from Silicon Image 3124/3132 Windows driver .inf file - also several Linux problem reports */ { "HTS541060G9SA00", "MB3OC60D", ATA_HORKAGE_NONCQ, }, { "HTS541080G9SA00", "MB4OC60D", ATA_HORKAGE_NONCQ, }, { "HTS541010G9SA00", "MBZOC60D", ATA_HORKAGE_NONCQ, }, /* https://bugzilla.kernel.org/show_bug.cgi?id=15573 */ { "C300-CTFDDAC128MAG", "0001", ATA_HORKAGE_NONCQ, }, /* Sandisk SD7/8/9s lock up hard on large trims */ { "SanDisk SD[789]*", NULL, ATA_HORKAGE_MAX_TRIM_128M, }, /* devices which puke on READ_NATIVE_MAX */ { "HDS724040KLSA80", "KFAOA20N", ATA_HORKAGE_BROKEN_HPA, }, { "WDC WD3200JD-00KLB0", "WD-WCAMR1130137", ATA_HORKAGE_BROKEN_HPA }, { "WDC WD2500JD-00HBB0", "WD-WMAL71490727", ATA_HORKAGE_BROKEN_HPA }, { "MAXTOR 6L080L4", "A93.0500", ATA_HORKAGE_BROKEN_HPA }, /* this one allows HPA unlocking but fails IOs on the area */ { "OCZ-VERTEX", "1.30", ATA_HORKAGE_BROKEN_HPA }, /* Devices which report 1 sector over size HPA */ { "ST340823A", NULL, ATA_HORKAGE_HPA_SIZE, }, { "ST320413A", NULL, ATA_HORKAGE_HPA_SIZE, }, { "ST310211A", NULL, ATA_HORKAGE_HPA_SIZE, }, /* Devices which get the IVB wrong */ { "QUANTUM FIREBALLlct10 05", "A03.0900", ATA_HORKAGE_IVB, }, /* Maybe we should just blacklist TSSTcorp... */ { "TSSTcorp CDDVDW SH-S202[HJN]", "SB0[01]", ATA_HORKAGE_IVB, }, /* Devices that do not need bridging limits applied */ { "MTRON MSP-SATA*", NULL, ATA_HORKAGE_BRIDGE_OK, }, { "BUFFALO HD-QSU2/R5", NULL, ATA_HORKAGE_BRIDGE_OK, }, /* Devices which aren't very happy with higher link speeds */ { "WD My Book", NULL, ATA_HORKAGE_1_5_GBPS, }, { "Seagate FreeAgent GoFlex", NULL, ATA_HORKAGE_1_5_GBPS, }, /* * Devices which choke on SETXFER. Applies only if both the * device and controller are SATA. */ { "PIONEER DVD-RW DVRTD08", NULL, ATA_HORKAGE_NOSETXFER }, { "PIONEER DVD-RW DVRTD08A", NULL, ATA_HORKAGE_NOSETXFER }, { "PIONEER DVD-RW DVR-215", NULL, ATA_HORKAGE_NOSETXFER }, { "PIONEER DVD-RW DVR-212D", NULL, ATA_HORKAGE_NOSETXFER }, { "PIONEER DVD-RW DVR-216D", NULL, ATA_HORKAGE_NOSETXFER }, /* Crucial BX100 SSD 500GB has broken LPM support */ { "CT500BX100SSD1", NULL, ATA_HORKAGE_NOLPM }, /* 512GB MX100 with MU01 firmware has both queued TRIM and LPM issues */ { "Crucial_CT512MX100*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM | ATA_HORKAGE_NOLPM, }, /* 512GB MX100 with newer firmware has only LPM issues */ { "Crucial_CT512MX100*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM | ATA_HORKAGE_NOLPM, }, /* 480GB+ M500 SSDs have both queued TRIM and LPM issues */ { "Crucial_CT480M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM | ATA_HORKAGE_NOLPM, }, { "Crucial_CT960M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM | ATA_HORKAGE_NOLPM, }, /* These specific Samsung models/firmware-revs do not handle LPM well */ { "SAMSUNG MZMPC128HBFU-000MV", "CXM14M1Q", ATA_HORKAGE_NOLPM, }, { "SAMSUNG SSD PM830 mSATA *", "CXM13D1Q", ATA_HORKAGE_NOLPM, }, { "SAMSUNG MZ7TD256HAFV-000L9", NULL, ATA_HORKAGE_NOLPM, }, { "SAMSUNG MZ7TE512HMHP-000L1", "EXT06L0Q", ATA_HORKAGE_NOLPM, }, /* devices that don't properly handle queued TRIM commands */ { "Micron_M500IT_*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Micron_M500_*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Crucial_CT*M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Micron_M5[15]0_*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Crucial_CT*M550*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Crucial_CT*MX100*", "MU01", ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Samsung SSD 840*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Samsung SSD 850*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Samsung SSD 860*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM | ATA_HORKAGE_NO_NCQ_ON_ATI, }, { "Samsung SSD 870*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM | ATA_HORKAGE_NO_NCQ_ON_ATI, }, { "FCCT*M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM | ATA_HORKAGE_ZERO_AFTER_TRIM, }, /* devices that don't properly handle TRIM commands */ { "SuperSSpeed S238*", NULL, ATA_HORKAGE_NOTRIM, }, /* * As defined, the DRAT (Deterministic Read After Trim) and RZAT * (Return Zero After Trim) flags in the ATA Command Set are * unreliable in the sense that they only define what happens if * the device successfully executed the DSM TRIM command. TRIM * is only advisory, however, and the device is free to silently * ignore all or parts of the request. * * Whitelist drives that are known to reliably return zeroes * after TRIM. */ /* * The intel 510 drive has buggy DRAT/RZAT. Explicitly exclude * that model before whitelisting all other intel SSDs. */ { "INTEL*SSDSC2MH*", NULL, 0, }, { "Micron*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Crucial*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "INTEL*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "SSD*INTEL*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "Samsung*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "SAMSUNG*SSD*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "SAMSUNG*MZ7KM*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, { "ST[1248][0248]0[FH]*", NULL, ATA_HORKAGE_ZERO_AFTER_TRIM, }, /* * Some WD SATA-I drives spin up and down erratically when the link * is put into the slumber mode. We don't have full list of the * affected devices. Disable LPM if the device matches one of the * known prefixes and is SATA-1. As a side effect LPM partial is * lost too. * * https://bugzilla.kernel.org/show_bug.cgi?id=57211 */ { "WDC WD800JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM }, { "WDC WD1200JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM }, { "WDC WD1600JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM }, { "WDC WD2000JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM }, { "WDC WD2500JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM }, { "WDC WD3000JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM }, { "WDC WD3200JD-*", NULL, ATA_HORKAGE_WD_BROKEN_LPM }, /* End Marker */ { } }; static unsigned long ata_dev_blacklisted(const struct ata_device *dev) { unsigned char model_num[ATA_ID_PROD_LEN + 1]; unsigned char model_rev[ATA_ID_FW_REV_LEN + 1]; const struct ata_blacklist_entry *ad = ata_device_blacklist; ata_id_c_string(dev->id, model_num, ATA_ID_PROD, sizeof(model_num)); ata_id_c_string(dev->id, model_rev, ATA_ID_FW_REV, sizeof(model_rev)); while (ad->model_num) { if (glob_match(ad->model_num, model_num)) { if (ad->model_rev == NULL) return ad->horkage; if (glob_match(ad->model_rev, model_rev)) return ad->horkage; } ad++; } return 0; } static int ata_dma_blacklisted(const struct ata_device *dev) { /* We don't support polling DMA. * DMA blacklist those ATAPI devices with CDB-intr (and use PIO) * if the LLDD handles only interrupts in the HSM_ST_LAST state. */ if ((dev->link->ap->flags & ATA_FLAG_PIO_POLLING) && (dev->flags & ATA_DFLAG_CDB_INTR)) return 1; return (dev->horkage & ATA_HORKAGE_NODMA) ? 1 : 0; } /** * ata_is_40wire - check drive side detection * @dev: device * * Perform drive side detection decoding, allowing for device vendors * who can't follow the documentation. */ static int ata_is_40wire(struct ata_device *dev) { if (dev->horkage & ATA_HORKAGE_IVB) return ata_drive_40wire_relaxed(dev->id); return ata_drive_40wire(dev->id); } /** * cable_is_40wire - 40/80/SATA decider * @ap: port to consider * * This function encapsulates the policy for speed management * in one place. At the moment we don't cache the result but * there is a good case for setting ap->cbl to the result when * we are called with unknown cables (and figuring out if it * impacts hotplug at all). * * Return 1 if the cable appears to be 40 wire. */ static int cable_is_40wire(struct ata_port *ap) { struct ata_link *link; struct ata_device *dev; /* If the controller thinks we are 40 wire, we are. */ if (ap->cbl == ATA_CBL_PATA40) return 1; /* If the controller thinks we are 80 wire, we are. */ if (ap->cbl == ATA_CBL_PATA80 || ap->cbl == ATA_CBL_SATA) return 0; /* If the system is known to be 40 wire short cable (eg * laptop), then we allow 80 wire modes even if the drive * isn't sure. */ if (ap->cbl == ATA_CBL_PATA40_SHORT) return 0; /* If the controller doesn't know, we scan. * * Note: We look for all 40 wire detects at this point. Any * 80 wire detect is taken to be 80 wire cable because * - in many setups only the one drive (slave if present) will * give a valid detect * - if you have a non detect capable drive you don't want it * to colour the choice */ ata_for_each_link(link, ap, EDGE) { ata_for_each_dev(dev, link, ENABLED) { if (!ata_is_40wire(dev)) return 0; } } return 1; } /** * ata_dev_xfermask - Compute supported xfermask of the given device * @dev: Device to compute xfermask for * * Compute supported xfermask of @dev and store it in * dev->*_mask. This function is responsible for applying all * known limits including host controller limits, device * blacklist, etc... * * LOCKING: * None. */ static void ata_dev_xfermask(struct ata_device *dev) { struct ata_link *link = dev->link; struct ata_port *ap = link->ap; struct ata_host *host = ap->host; unsigned long xfer_mask; /* controller modes available */ xfer_mask = ata_pack_xfermask(ap->pio_mask, ap->mwdma_mask, ap->udma_mask); /* drive modes available */ xfer_mask &= ata_pack_xfermask(dev->pio_mask, dev->mwdma_mask, dev->udma_mask); xfer_mask &= ata_id_xfermask(dev->id); /* * CFA Advanced TrueIDE timings are not allowed on a shared * cable */ if (ata_dev_pair(dev)) { /* No PIO5 or PIO6 */ xfer_mask &= ~(0x03 << (ATA_SHIFT_PIO + 5)); /* No MWDMA3 or MWDMA 4 */ xfer_mask &= ~(0x03 << (ATA_SHIFT_MWDMA + 3)); } if (ata_dma_blacklisted(dev)) { xfer_mask &= ~(ATA_MASK_MWDMA | ATA_MASK_UDMA); ata_dev_warn(dev, "device is on DMA blacklist, disabling DMA\n"); } if ((host->flags & ATA_HOST_SIMPLEX) && host->simplex_claimed && host->simplex_claimed != ap) { xfer_mask &= ~(ATA_MASK_MWDMA | ATA_MASK_UDMA); ata_dev_warn(dev, "simplex DMA is claimed by other device, disabling DMA\n"); } if (ap->flags & ATA_FLAG_NO_IORDY) xfer_mask &= ata_pio_mask_no_iordy(dev); if (ap->ops->mode_filter) xfer_mask = ap->ops->mode_filter(dev, xfer_mask); /* Apply cable rule here. Don't apply it early because when * we handle hot plug the cable type can itself change. * Check this last so that we know if the transfer rate was * solely limited by the cable. * Unknown or 80 wire cables reported host side are checked * drive side as well. Cases where we know a 40wire cable * is used safely for 80 are not checked here. */ if (xfer_mask & (0xF8 << ATA_SHIFT_UDMA)) /* UDMA/44 or higher would be available */ if (cable_is_40wire(ap)) { ata_dev_warn(dev, "limited to UDMA/33 due to 40-wire cable\n"); xfer_mask &= ~(0xF8 << ATA_SHIFT_UDMA); } ata_unpack_xfermask(xfer_mask, &dev->pio_mask, &dev->mwdma_mask, &dev->udma_mask); } /** * ata_dev_set_xfermode - Issue SET FEATURES - XFER MODE command * @dev: Device to which command will be sent * * Issue SET FEATURES - XFER MODE command to device @dev * on port @ap. * * LOCKING: * PCI/etc. bus probe sem. * * RETURNS: * 0 on success, AC_ERR_* mask otherwise. */ static unsigned int ata_dev_set_xfermode(struct ata_device *dev) { struct ata_taskfile tf; unsigned int err_mask; /* set up set-features taskfile */ DPRINTK("set features - xfer mode\n"); /* Some controllers and ATAPI devices show flaky interrupt * behavior after setting xfer mode. Use polling instead. */ ata_tf_init(dev, &tf); tf.command = ATA_CMD_SET_FEATURES; tf.feature = SETFEATURES_XFER; tf.flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE | ATA_TFLAG_POLLING; tf.protocol = ATA_PROT_NODATA; /* If we are using IORDY we must send the mode setting command */ if (ata_pio_need_iordy(dev)) tf.nsect = dev->xfer_mode; /* If the device has IORDY and the controller does not - turn it off */ else if (ata_id_has_iordy(dev->id)) tf.nsect = 0x01; else /* In the ancient relic department - skip all of this */ return 0; /* On some disks, this command causes spin-up, so we need longer timeout */ err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 15000); DPRINTK("EXIT, err_mask=%x\n", err_mask); return err_mask; } /** * ata_dev_set_feature - Issue SET FEATURES - SATA FEATURES * @dev: Device to which command will be sent * @enable: Whether to enable or disable the feature * @feature: The sector count represents the feature to set * * Issue SET FEATURES - SATA FEATURES command to device @dev * on port @ap with sector count * * LOCKING: * PCI/etc. bus probe sem. * * RETURNS: * 0 on success, AC_ERR_* mask otherwise. */ unsigned int ata_dev_set_feature(struct ata_device *dev, u8 enable, u8 feature) { struct ata_taskfile tf; unsigned int err_mask; unsigned long timeout = 0; /* set up set-features taskfile */ DPRINTK("set features - SATA features\n"); ata_tf_init(dev, &tf); tf.command = ATA_CMD_SET_FEATURES; tf.feature = enable; tf.flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE; tf.protocol = ATA_PROT_NODATA; tf.nsect = feature; if (enable == SETFEATURES_SPINUP) timeout = ata_probe_timeout ? ata_probe_timeout * 1000 : SETFEATURES_SPINUP_TIMEOUT; err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, timeout); DPRINTK("EXIT, err_mask=%x\n", err_mask); return err_mask; } EXPORT_SYMBOL_GPL(ata_dev_set_feature); /** * ata_dev_init_params - Issue INIT DEV PARAMS command * @dev: Device to which command will be sent * @heads: Number of heads (taskfile parameter) * @sectors: Number of sectors (taskfile parameter) * * LOCKING: * Kernel thread context (may sleep) * * RETURNS: * 0 on success, AC_ERR_* mask otherwise. */ static unsigned int ata_dev_init_params(struct ata_device *dev, u16 heads, u16 sectors) { struct ata_taskfile tf; unsigned int err_mask; /* Number of sectors per track 1-255. Number of heads 1-16 */ if (sectors < 1 || sectors > 255 || heads < 1 || heads > 16) return AC_ERR_INVALID; /* set up init dev params taskfile */ DPRINTK("init dev params \n"); ata_tf_init(dev, &tf); tf.command = ATA_CMD_INIT_DEV_PARAMS; tf.flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE; tf.protocol = ATA_PROT_NODATA; tf.nsect = sectors; tf.device |= (heads - 1) & 0x0f; /* max head = num. of heads - 1 */ err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0); /* A clean abort indicates an original or just out of spec drive and we should continue as we issue the setup based on the drive reported working geometry */ if (err_mask == AC_ERR_DEV && (tf.feature & ATA_ABORTED)) err_mask = 0; DPRINTK("EXIT, err_mask=%x\n", err_mask); return err_mask; } /** * atapi_check_dma - Check whether ATAPI DMA can be supported * @qc: Metadata associated with taskfile to check * * Allow low-level driver to filter ATA PACKET commands, returning * a status indicating whether or not it is OK to use DMA for the * supplied PACKET command. * * LOCKING: * spin_lock_irqsave(host lock) * * RETURNS: 0 when ATAPI DMA can be used * nonzero otherwise */ int atapi_check_dma(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; /* Don't allow DMA if it isn't multiple of 16 bytes. Quite a * few ATAPI devices choke on such DMA requests. */ if (!(qc->dev->horkage & ATA_HORKAGE_ATAPI_MOD16_DMA) && unlikely(qc->nbytes & 15)) return 1; if (ap->ops->check_atapi_dma) return ap->ops->check_atapi_dma(qc); return 0; } /** * ata_std_qc_defer - Check whether a qc needs to be deferred * @qc: ATA command in question * * Non-NCQ commands cannot run with any other command, NCQ or * not. As upper layer only knows the queue depth, we are * responsible for maintaining exclusion. This function checks * whether a new command @qc can be issued. * * LOCKING: * spin_lock_irqsave(host lock) * * RETURNS: * ATA_DEFER_* if deferring is needed, 0 otherwise. */ int ata_std_qc_defer(struct ata_queued_cmd *qc) { struct ata_link *link = qc->dev->link; if (ata_is_ncq(qc->tf.protocol)) { if (!ata_tag_valid(link->active_tag)) return 0; } else { if (!ata_tag_valid(link->active_tag) && !link->sactive) return 0; } return ATA_DEFER_LINK; } EXPORT_SYMBOL_GPL(ata_std_qc_defer); enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc) { return AC_ERR_OK; } EXPORT_SYMBOL_GPL(ata_noop_qc_prep); /** * ata_sg_init - Associate command with scatter-gather table. * @qc: Command to be associated * @sg: Scatter-gather table. * @n_elem: Number of elements in s/g table. * * Initialize the data-related elements of queued_cmd @qc * to point to a scatter-gather table @sg, containing @n_elem * elements. * * LOCKING: * spin_lock_irqsave(host lock) */ void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg, unsigned int n_elem) { qc->sg = sg; qc->n_elem = n_elem; qc->cursg = qc->sg; } #ifdef CONFIG_HAS_DMA /** * ata_sg_clean - Unmap DMA memory associated with command * @qc: Command containing DMA memory to be released * * Unmap all mapped DMA memory associated with this command. * * LOCKING: * spin_lock_irqsave(host lock) */ static void ata_sg_clean(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct scatterlist *sg = qc->sg; int dir = qc->dma_dir; WARN_ON_ONCE(sg == NULL); VPRINTK("unmapping %u sg elements\n", qc->n_elem); if (qc->n_elem) dma_unmap_sg(ap->dev, sg, qc->orig_n_elem, dir); qc->flags &= ~ATA_QCFLAG_DMAMAP; qc->sg = NULL; } /** * ata_sg_setup - DMA-map the scatter-gather table associated with a command. * @qc: Command with scatter-gather table to be mapped. * * DMA-map the scatter-gather table associated with queued_cmd @qc. * * LOCKING: * spin_lock_irqsave(host lock) * * RETURNS: * Zero on success, negative on error. * */ static int ata_sg_setup(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; unsigned int n_elem; VPRINTK("ENTER, ata%u\n", ap->print_id); n_elem = dma_map_sg(ap->dev, qc->sg, qc->n_elem, qc->dma_dir); if (n_elem < 1) return -1; VPRINTK("%d sg elements mapped\n", n_elem); qc->orig_n_elem = qc->n_elem; qc->n_elem = n_elem; qc->flags |= ATA_QCFLAG_DMAMAP; return 0; } #else /* !CONFIG_HAS_DMA */ static inline void ata_sg_clean(struct ata_queued_cmd *qc) {} static inline int ata_sg_setup(struct ata_queued_cmd *qc) { return -1; } #endif /* !CONFIG_HAS_DMA */ /** * swap_buf_le16 - swap halves of 16-bit words in place * @buf: Buffer to swap * @buf_words: Number of 16-bit words in buffer. * * Swap halves of 16-bit words if needed to convert from * little-endian byte order to native cpu byte order, or * vice-versa. * * LOCKING: * Inherited from caller. */ void swap_buf_le16(u16 *buf, unsigned int buf_words) { #ifdef __BIG_ENDIAN unsigned int i; for (i = 0; i < buf_words; i++) buf[i] = le16_to_cpu(buf[i]); #endif /* __BIG_ENDIAN */ } /** * ata_qc_new_init - Request an available ATA command, and initialize it * @dev: Device from whom we request an available command structure * @tag: tag * * LOCKING: * None. */ struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev, int tag) { struct ata_port *ap = dev->link->ap; struct ata_queued_cmd *qc; /* no command while frozen */ if (unlikely(ap->pflags & ATA_PFLAG_FROZEN)) return NULL; /* libsas case */ if (ap->flags & ATA_FLAG_SAS_HOST) { tag = ata_sas_allocate_tag(ap); if (tag < 0) return NULL; } qc = __ata_qc_from_tag(ap, tag); qc->tag = qc->hw_tag = tag; qc->scsicmd = NULL; qc->ap = ap; qc->dev = dev; ata_qc_reinit(qc); return qc; } /** * ata_qc_free - free unused ata_queued_cmd * @qc: Command to complete * * Designed to free unused ata_queued_cmd object * in case something prevents using it. * * LOCKING: * spin_lock_irqsave(host lock) */ void ata_qc_free(struct ata_queued_cmd *qc) { struct ata_port *ap; unsigned int tag; WARN_ON_ONCE(qc == NULL); /* ata_qc_from_tag _might_ return NULL */ ap = qc->ap; qc->flags = 0; tag = qc->tag; if (ata_tag_valid(tag)) { qc->tag = ATA_TAG_POISON; if (ap->flags & ATA_FLAG_SAS_HOST) ata_sas_free_tag(tag, ap); } } void __ata_qc_complete(struct ata_queued_cmd *qc) { struct ata_port *ap; struct ata_link *link; WARN_ON_ONCE(qc == NULL); /* ata_qc_from_tag _might_ return NULL */ WARN_ON_ONCE(!(qc->flags & ATA_QCFLAG_ACTIVE)); ap = qc->ap; link = qc->dev->link; if (likely(qc->flags & ATA_QCFLAG_DMAMAP)) ata_sg_clean(qc); /* command should be marked inactive atomically with qc completion */ if (ata_is_ncq(qc->tf.protocol)) { link->sactive &= ~(1 << qc->hw_tag); if (!link->sactive) ap->nr_active_links--; } else { link->active_tag = ATA_TAG_POISON; ap->nr_active_links--; } /* clear exclusive status */ if (unlikely(qc->flags & ATA_QCFLAG_CLEAR_EXCL && ap->excl_link == link)) ap->excl_link = NULL; /* atapi: mark qc as inactive to prevent the interrupt handler * from completing the command twice later, before the error handler * is called. (when rc != 0 and atapi request sense is needed) */ qc->flags &= ~ATA_QCFLAG_ACTIVE; ap->qc_active &= ~(1ULL << qc->tag); /* call completion callback */ qc->complete_fn(qc); } static void fill_result_tf(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; qc->result_tf.flags = qc->tf.flags; ap->ops->qc_fill_rtf(qc); } static void ata_verify_xfer(struct ata_queued_cmd *qc) { struct ata_device *dev = qc->dev; if (!ata_is_data(qc->tf.protocol)) return; if ((dev->mwdma_mask || dev->udma_mask) && ata_is_pio(qc->tf.protocol)) return; dev->flags &= ~ATA_DFLAG_DUBIOUS_XFER; } /** * ata_qc_complete - Complete an active ATA command * @qc: Command to complete * * Indicate to the mid and upper layers that an ATA command has * completed, with either an ok or not-ok status. * * Refrain from calling this function multiple times when * successfully completing multiple NCQ commands. * ata_qc_complete_multiple() should be used instead, which will * properly update IRQ expect state. * * LOCKING: * spin_lock_irqsave(host lock) */ void ata_qc_complete(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; /* Trigger the LED (if available) */ ledtrig_disk_activity(!!(qc->tf.flags & ATA_TFLAG_WRITE)); /* XXX: New EH and old EH use different mechanisms to * synchronize EH with regular execution path. * * In new EH, a failed qc is marked with ATA_QCFLAG_FAILED. * Normal execution path is responsible for not accessing a * failed qc. libata core enforces the rule by returning NULL * from ata_qc_from_tag() for failed qcs. * * Old EH depends on ata_qc_complete() nullifying completion * requests if ATA_QCFLAG_EH_SCHEDULED is set. Old EH does * not synchronize with interrupt handler. Only PIO task is * taken care of. */ if (ap->ops->error_handler) { struct ata_device *dev = qc->dev; struct ata_eh_info *ehi = &dev->link->eh_info; if (unlikely(qc->err_mask)) qc->flags |= ATA_QCFLAG_FAILED; /* * Finish internal commands without any further processing * and always with the result TF filled. */ if (unlikely(ata_tag_internal(qc->tag))) { fill_result_tf(qc); trace_ata_qc_complete_internal(qc); __ata_qc_complete(qc); return; } /* * Non-internal qc has failed. Fill the result TF and * summon EH. */ if (unlikely(qc->flags & ATA_QCFLAG_FAILED)) { fill_result_tf(qc); trace_ata_qc_complete_failed(qc); ata_qc_schedule_eh(qc); return; } WARN_ON_ONCE(ap->pflags & ATA_PFLAG_FROZEN); /* read result TF if requested */ if (qc->flags & ATA_QCFLAG_RESULT_TF) fill_result_tf(qc); trace_ata_qc_complete_done(qc); /* Some commands need post-processing after successful * completion. */ switch (qc->tf.command) { case ATA_CMD_SET_FEATURES: if (qc->tf.feature != SETFEATURES_WC_ON && qc->tf.feature != SETFEATURES_WC_OFF && qc->tf.feature != SETFEATURES_RA_ON && qc->tf.feature != SETFEATURES_RA_OFF) break; fallthrough; case ATA_CMD_INIT_DEV_PARAMS: /* CHS translation changed */ case ATA_CMD_SET_MULTI: /* multi_count changed */ /* revalidate device */ ehi->dev_action[dev->devno] |= ATA_EH_REVALIDATE; ata_port_schedule_eh(ap); break; case ATA_CMD_SLEEP: dev->flags |= ATA_DFLAG_SLEEPING; break; } if (unlikely(dev->flags & ATA_DFLAG_DUBIOUS_XFER)) ata_verify_xfer(qc); __ata_qc_complete(qc); } else { if (qc->flags & ATA_QCFLAG_EH_SCHEDULED) return; /* read result TF if failed or requested */ if (qc->err_mask || qc->flags & ATA_QCFLAG_RESULT_TF) fill_result_tf(qc); __ata_qc_complete(qc); } } EXPORT_SYMBOL_GPL(ata_qc_complete); /** * ata_qc_get_active - get bitmask of active qcs * @ap: port in question * * LOCKING: * spin_lock_irqsave(host lock) * * RETURNS: * Bitmask of active qcs */ u64 ata_qc_get_active(struct ata_port *ap) { u64 qc_active = ap->qc_active; /* ATA_TAG_INTERNAL is sent to hw as tag 0 */ if (qc_active & (1ULL << ATA_TAG_INTERNAL)) { qc_active |= (1 << 0); qc_active &= ~(1ULL << ATA_TAG_INTERNAL); } return qc_active; } EXPORT_SYMBOL_GPL(ata_qc_get_active); /** * ata_qc_issue - issue taskfile to device * @qc: command to issue to device * * Prepare an ATA command to submission to device. * This includes mapping the data into a DMA-able * area, filling in the S/G table, and finally * writing the taskfile to hardware, starting the command. * * LOCKING: * spin_lock_irqsave(host lock) */ void ata_qc_issue(struct ata_queued_cmd *qc) { struct ata_port *ap = qc->ap; struct ata_link *link = qc->dev->link; u8 prot = qc->tf.protocol; /* Make sure only one non-NCQ command is outstanding. The * check is skipped for old EH because it reuses active qc to * request ATAPI sense. */ WARN_ON_ONCE(ap->ops->error_handler && ata_tag_valid(link->active_tag)); if (ata_is_ncq(prot)) { WARN_ON_ONCE(link->sactive & (1 << qc->hw_tag)); if (!link->sactive) ap->nr_active_links++; link->sactive |= 1 << qc->hw_tag; } else { WARN_ON_ONCE(link->sactive); ap->nr_active_links++; link->active_tag = qc->tag; } qc->flags |= ATA_QCFLAG_ACTIVE; ap->qc_active |= 1ULL << qc->tag; /* * We guarantee to LLDs that they will have at least one * non-zero sg if the command is a data command. */ if (ata_is_data(prot) && (!qc->sg || !qc->n_elem || !qc->nbytes)) goto sys_err; if (ata_is_dma(prot) || (ata_is_pio(prot) && (ap->flags & ATA_FLAG_PIO_DMA))) if (ata_sg_setup(qc)) goto sys_err; /* if device is sleeping, schedule reset and abort the link */ if (unlikely(qc->dev->flags & ATA_DFLAG_SLEEPING)) { link->eh_info.action |= ATA_EH_RESET; ata_ehi_push_desc(&link->eh_info, "waking up from sleep"); ata_link_abort(link); return; } qc->err_mask |= ap->ops->qc_prep(qc); if (unlikely(qc->err_mask)) goto err; trace_ata_qc_issue(qc); qc->err_mask |= ap->ops->qc_issue(qc); if (unlikely(qc->err_mask)) goto err; return; sys_err: qc->err_mask |= AC_ERR_SYSTEM; err: ata_qc_complete(qc); } /** * ata_phys_link_online - test whether the given link is online * @link: ATA link to test * * Test whether @link is online. Note that this function returns * 0 if online status of @link cannot be obtained, so * ata_link_online(link) != !ata_link_offline(link). * * LOCKING: * None. * * RETURNS: * True if the port online status is available and online. */ bool ata_phys_link_online(struct ata_link *link) { u32 sstatus; if (sata_scr_read(link, SCR_STATUS, &sstatus) == 0 && ata_sstatus_online(sstatus)) return true; return false; } /** * ata_phys_link_offline - test whether the given link is offline * @link: ATA link to test * * Test whether @link is offline. Note that this function * returns 0 if offline status of @link cannot be obtained, so * ata_link_online(link) != !ata_link_offline(link). * * LOCKING: * None. * * RETURNS: * True if the port offline status is available and offline. */ bool ata_phys_link_offline(struct ata_link *link) { u32 sstatus; if (sata_scr_read(link, SCR_STATUS, &sstatus) == 0 && !ata_sstatus_online(sstatus)) return true; return false; } /** * ata_link_online - test whether the given link is online * @link: ATA link to test * * Test whether @link is online. This is identical to * ata_phys_link_online() when there's no slave link. When * there's a slave link, this function should only be called on * the master link and will return true if any of M/S links is * online. * * LOCKING: * None. * * RETURNS: * True if the port online status is available and online. */ bool ata_link_online(struct ata_link *link) { struct ata_link *slave = link->ap->slave_link; WARN_ON(link == slave); /* shouldn't be called on slave link */ return ata_phys_link_online(link) || (slave && ata_phys_link_online(slave)); } EXPORT_SYMBOL_GPL(ata_link_online); /** * ata_link_offline - test whether the given link is offline * @link: ATA link to test * * Test whether @link is offline. This is identical to * ata_phys_link_offline() when there's no slave link. When * there's a slave link, this function should only be called on * the master link and will return true if both M/S links are * offline. * * LOCKING: * None. * * RETURNS: * True if the port offline status is available and offline. */ bool ata_link_offline(struct ata_link *link) { struct ata_link *slave = link->ap->slave_link; WARN_ON(link == slave); /* shouldn't be called on slave link */ return ata_phys_link_offline(link) && (!slave || ata_phys_link_offline(slave)); } EXPORT_SYMBOL_GPL(ata_link_offline); #ifdef CONFIG_PM static void ata_port_request_pm(struct ata_port *ap, pm_message_t mesg, unsigned int action, unsigned int ehi_flags, bool async) { struct ata_link *link; unsigned long flags; /* Previous resume operation might still be in * progress. Wait for PM_PENDING to clear. */ if (ap->pflags & ATA_PFLAG_PM_PENDING) { ata_port_wait_eh(ap); WARN_ON(ap->pflags & ATA_PFLAG_PM_PENDING); } /* request PM ops to EH */ spin_lock_irqsave(ap->lock, flags); ap->pm_mesg = mesg; ap->pflags |= ATA_PFLAG_PM_PENDING; ata_for_each_link(link, ap, HOST_FIRST) { link->eh_info.action |= action; link->eh_info.flags |= ehi_flags; } ata_port_schedule_eh(ap); spin_unlock_irqrestore(ap->lock, flags); if (!async) { ata_port_wait_eh(ap); WARN_ON(ap->pflags & ATA_PFLAG_PM_PENDING); } } /* * On some hardware, device fails to respond after spun down for suspend. As * the device won't be used before being resumed, we don't need to touch the * device. Ask EH to skip the usual stuff and proceed directly to suspend. * * http://thread.gmane.org/gmane.linux.ide/46764 */ static const unsigned int ata_port_suspend_ehi = ATA_EHI_QUIET | ATA_EHI_NO_AUTOPSY | ATA_EHI_NO_RECOVERY; static void ata_port_suspend(struct ata_port *ap, pm_message_t mesg) { ata_port_request_pm(ap, mesg, 0, ata_port_suspend_ehi, false); } static void ata_port_suspend_async(struct ata_port *ap, pm_message_t mesg) { ata_port_request_pm(ap, mesg, 0, ata_port_suspend_ehi, true); } static int ata_port_pm_suspend(struct device *dev) { struct ata_port *ap = to_ata_port(dev); if (pm_runtime_suspended(dev)) return 0; ata_port_suspend(ap, PMSG_SUSPEND); return 0; } static int ata_port_pm_freeze(struct device *dev) { struct ata_port *ap = to_ata_port(dev); if (pm_runtime_suspended(dev)) return 0; ata_port_suspend(ap, PMSG_FREEZE); return 0; } static int ata_port_pm_poweroff(struct device *dev) { ata_port_suspend(to_ata_port(dev), PMSG_HIBERNATE); return 0; } static const unsigned int ata_port_resume_ehi = ATA_EHI_NO_AUTOPSY | ATA_EHI_QUIET; static void ata_port_resume(struct ata_port *ap, pm_message_t mesg) { ata_port_request_pm(ap, mesg, ATA_EH_RESET, ata_port_resume_ehi, false); } static void ata_port_resume_async(struct ata_port *ap, pm_message_t mesg) { ata_port_request_pm(ap, mesg, ATA_EH_RESET, ata_port_resume_ehi, true); } static int ata_port_pm_resume(struct device *dev) { ata_port_resume_async(to_ata_port(dev), PMSG_RESUME); pm_runtime_disable(dev); pm_runtime_set_active(dev); pm_runtime_enable(dev); return 0; } /* * For ODDs, the upper layer will poll for media change every few seconds, * which will make it enter and leave suspend state every few seconds. And * as each suspend will cause a hard/soft reset, the gain of runtime suspend * is very little and the ODD may malfunction after constantly being reset. * So the idle callback here will not proceed to suspend if a non-ZPODD capable * ODD is attached to the port. */ static int ata_port_runtime_idle(struct device *dev) { struct ata_port *ap = to_ata_port(dev); struct ata_link *link; struct ata_device *adev; ata_for_each_link(link, ap, HOST_FIRST) { ata_for_each_dev(adev, link, ENABLED) if (adev->class == ATA_DEV_ATAPI && !zpodd_dev_enabled(adev)) return -EBUSY; } return 0; } static int ata_port_runtime_suspend(struct device *dev) { ata_port_suspend(to_ata_port(dev), PMSG_AUTO_SUSPEND); return 0; } static int ata_port_runtime_resume(struct device *dev) { ata_port_resume(to_ata_port(dev), PMSG_AUTO_RESUME); return 0; } static const struct dev_pm_ops ata_port_pm_ops = { .suspend = ata_port_pm_suspend, .resume = ata_port_pm_resume, .freeze = ata_port_pm_freeze, .thaw = ata_port_pm_resume, .poweroff = ata_port_pm_poweroff, .restore = ata_port_pm_resume, .runtime_suspend = ata_port_runtime_suspend, .runtime_resume = ata_port_runtime_resume, .runtime_idle = ata_port_runtime_idle, }; /* sas ports don't participate in pm runtime management of ata_ports, * and need to resume ata devices at the domain level, not the per-port * level. sas suspend/resume is async to allow parallel port recovery * since sas has multiple ata_port instances per Scsi_Host. */ void ata_sas_port_suspend(struct ata_port *ap) { ata_port_suspend_async(ap, PMSG_SUSPEND); } EXPORT_SYMBOL_GPL(ata_sas_port_suspend); void ata_sas_port_resume(struct ata_port *ap) { ata_port_resume_async(ap, PMSG_RESUME); } EXPORT_SYMBOL_GPL(ata_sas_port_resume); /** * ata_host_suspend - suspend host * @host: host to suspend * @mesg: PM message * * Suspend @host. Actual operation is performed by port suspend. */ int ata_host_suspend(struct ata_host *host, pm_message_t mesg) { host->dev->power.power_state = mesg; return 0; } EXPORT_SYMBOL_GPL(ata_host_suspend); /** * ata_host_resume - resume host * @host: host to resume * * Resume @host. Actual operation is performed by port resume. */ void ata_host_resume(struct ata_host *host) { host->dev->power.power_state = PMSG_ON; } EXPORT_SYMBOL_GPL(ata_host_resume); #endif const struct device_type ata_port_type = { .name = "ata_port", #ifdef CONFIG_PM .pm = &ata_port_pm_ops, #endif }; /** * ata_dev_init - Initialize an ata_device structure * @dev: Device structure to initialize * * Initialize @dev in preparation for probing. * * LOCKING: * Inherited from caller. */ void ata_dev_init(struct ata_device *dev) { struct ata_link *link = ata_dev_phys_link(dev); struct ata_port *ap = link->ap; unsigned long flags; /* SATA spd limit is bound to the attached device, reset together */ link->sata_spd_limit = link->hw_sata_spd_limit; link->sata_spd = 0; /* High bits of dev->flags are used to record warm plug * requests which occur asynchronously. Synchronize using * host lock. */ spin_lock_irqsave(ap->lock, flags); dev->flags &= ~ATA_DFLAG_INIT_MASK; dev->horkage = 0; spin_unlock_irqrestore(ap->lock, flags); memset((void *)dev + ATA_DEVICE_CLEAR_BEGIN, 0, ATA_DEVICE_CLEAR_END - ATA_DEVICE_CLEAR_BEGIN); dev->pio_mask = UINT_MAX; dev->mwdma_mask = UINT_MAX; dev->udma_mask = UINT_MAX; } /** * ata_link_init - Initialize an ata_link structure * @ap: ATA port link is attached to * @link: Link structure to initialize * @pmp: Port multiplier port number * * Initialize @link. * * LOCKING: * Kernel thread context (may sleep) */ void ata_link_init(struct ata_port *ap, struct ata_link *link, int pmp) { int i; /* clear everything except for devices */ memset((void *)link + ATA_LINK_CLEAR_BEGIN, 0, ATA_LINK_CLEAR_END - ATA_LINK_CLEAR_BEGIN); link->ap = ap; link->pmp = pmp; link->active_tag = ATA_TAG_POISON; link->hw_sata_spd_limit = UINT_MAX; /* can't use iterator, ap isn't initialized yet */ for (i = 0; i < ATA_MAX_DEVICES; i++) { struct ata_device *dev = &link->device[i]; dev->link = link; dev->devno = dev - link->device; #ifdef CONFIG_ATA_ACPI dev->gtf_filter = ata_acpi_gtf_filter; #endif ata_dev_init(dev); } } /** * sata_link_init_spd - Initialize link->sata_spd_limit * @link: Link to configure sata_spd_limit for * * Initialize ``link->[hw_]sata_spd_limit`` to the currently * configured value. * * LOCKING: * Kernel thread context (may sleep). * * RETURNS: * 0 on success, -errno on failure. */ int sata_link_init_spd(struct ata_link *link) { u8 spd; int rc; rc = sata_scr_read(link, SCR_CONTROL, &link->saved_scontrol); if (rc) return rc; spd = (link->saved_scontrol >> 4) & 0xf; if (spd) link->hw_sata_spd_limit &= (1 << spd) - 1; ata_force_link_limits(link); link->sata_spd_limit = link->hw_sata_spd_limit; return 0; } /** * ata_port_alloc - allocate and initialize basic ATA port resources * @host: ATA host this allocated port belongs to * * Allocate and initialize basic ATA port resources. * * RETURNS: * Allocate ATA port on success, NULL on failure. * * LOCKING: * Inherited from calling layer (may sleep). */ struct ata_port *ata_port_alloc(struct ata_host *host) { struct ata_port *ap; DPRINTK("ENTER\n"); ap = kzalloc(sizeof(*ap), GFP_KERNEL); if (!ap) return NULL; ap->pflags |= ATA_PFLAG_INITIALIZING | ATA_PFLAG_FROZEN; ap->lock = &host->lock; ap->print_id = -1; ap->local_port_no = -1; ap->host = host; ap->dev = host->dev; #if defined(ATA_VERBOSE_DEBUG) /* turn on all debugging levels */ ap->msg_enable = 0x00FF; #elif defined(ATA_DEBUG) ap->msg_enable = ATA_MSG_DRV | ATA_MSG_INFO | ATA_MSG_CTL | ATA_MSG_WARN | ATA_MSG_ERR; #else ap->msg_enable = ATA_MSG_DRV | ATA_MSG_ERR | ATA_MSG_WARN; #endif mutex_init(&ap->scsi_scan_mutex); INIT_DELAYED_WORK(&ap->hotplug_task, ata_scsi_hotplug); INIT_WORK(&ap->scsi_rescan_task, ata_scsi_dev_rescan); INIT_LIST_HEAD(&ap->eh_done_q); init_waitqueue_head(&ap->eh_wait_q); init_completion(&ap->park_req_pending); timer_setup(&ap->fastdrain_timer, ata_eh_fastdrain_timerfn, TIMER_DEFERRABLE); ap->cbl = ATA_CBL_NONE; ata_link_init(ap, &ap->link, 0); #ifdef ATA_IRQ_TRAP ap->stats.unhandled_irq = 1; ap->stats.idle_irq = 1; #endif ata_sff_port_init(ap); return ap; } static void ata_devres_release(struct device *gendev, void *res) { struct ata_host *host = dev_get_drvdata(gendev); int i; for (i = 0; i < host->n_ports; i++) { struct ata_port *ap = host->ports[i]; if (!ap) continue; if (ap->scsi_host) scsi_host_put(ap->scsi_host); } dev_set_drvdata(gendev, NULL); ata_host_put(host); } static void ata_host_release(struct kref *kref) { struct ata_host *host = container_of(kref, struct ata_host, kref); int i; for (i = 0; i < host->n_ports; i++) { struct ata_port *ap = host->ports[i]; kfree(ap->pmp_link); kfree(ap->slave_link); kfree(ap); host->ports[i] = NULL; } kfree(host); } void ata_host_get(struct ata_host *host) { kref_get(&host->kref); } void ata_host_put(struct ata_host *host) { kref_put(&host->kref, ata_host_release); } EXPORT_SYMBOL_GPL(ata_host_put); /** * ata_host_alloc - allocate and init basic ATA host resources * @dev: generic device this host is associated with * @max_ports: maximum number of ATA ports associated with this host * * Allocate and initialize basic ATA host resources. LLD calls * this function to allocate a host, initializes it fully and * attaches it using ata_host_register(). * * @max_ports ports are allocated and host->n_ports is * initialized to @max_ports. The caller is allowed to decrease * host->n_ports before calling ata_host_register(). The unused * ports will be automatically freed on registration. * * RETURNS: * Allocate ATA host on success, NULL on failure. * * LOCKING: * Inherited from calling layer (may sleep). */ struct ata_host *ata_host_alloc(struct device *dev, int max_ports) { struct ata_host *host; size_t sz; int i; void *dr; DPRINTK("ENTER\n"); /* alloc a container for our list of ATA ports (buses) */ sz = sizeof(struct ata_host) + (max_ports + 1) * sizeof(void *); host = kzalloc(sz, GFP_KERNEL); if (!host) return NULL; if (!devres_open_group(dev, NULL, GFP_KERNEL)) goto err_free; dr = devres_alloc(ata_devres_release, 0, GFP_KERNEL); if (!dr) goto err_out; devres_add(dev, dr); dev_set_drvdata(dev, host); spin_lock_init(&host->lock); mutex_init(&host->eh_mutex); host->dev = dev; host->n_ports = max_ports; kref_init(&host->kref); /* allocate ports bound to this host */ for (i = 0; i < max_ports; i++) { struct ata_port *ap; ap = ata_port_alloc(host); if (!ap) goto err_out; ap->port_no = i; host->ports[i] = ap; } devres_remove_group(dev, NULL); return host; err_out: devres_release_group(dev, NULL); err_free: kfree(host); return NULL; } EXPORT_SYMBOL_GPL(ata_host_alloc); /** * ata_host_alloc_pinfo - alloc host and init with port_info array * @dev: generic device this host is associated with * @ppi: array of ATA port_info to initialize host with * @n_ports: number of ATA ports attached to this host * * Allocate ATA host and initialize with info from @ppi. If NULL * terminated, @ppi may contain fewer entries than @n_ports. The * last entry will be used for the remaining ports. * * RETURNS: * Allocate ATA host on success, NULL on failure. * * LOCKING: * Inherited from calling layer (may sleep). */ struct ata_host *ata_host_alloc_pinfo(struct device *dev, const struct ata_port_info * const * ppi, int n_ports) { const struct ata_port_info *pi; struct ata_host *host; int i, j; host = ata_host_alloc(dev, n_ports); if (!host) return NULL; for (i = 0, j = 0, pi = NULL; i < host->n_ports; i++) { struct ata_port *ap = host->ports[i]; if (ppi[j]) pi = ppi[j++]; ap->pio_mask = pi->pio_mask; ap->mwdma_mask = pi->mwdma_mask; ap->udma_mask = pi->udma_mask; ap->flags |= pi->flags; ap->link.flags |= pi->link_flags; ap->ops = pi->port_ops; if (!host->ops && (pi->port_ops != &ata_dummy_port_ops)) host->ops = pi->port_ops; } return host; } EXPORT_SYMBOL_GPL(ata_host_alloc_pinfo); static void ata_host_stop(struct device *gendev, void *res) { struct ata_host *host = dev_get_drvdata(gendev); int i; WARN_ON(!(host->flags & ATA_HOST_STARTED)); for (i = 0; i < host->n_ports; i++) { struct ata_port *ap = host->ports[i]; if (ap->ops->port_stop) ap->ops->port_stop(ap); } if (host->ops->host_stop) host->ops->host_stop(host); } /** * ata_finalize_port_ops - finalize ata_port_operations * @ops: ata_port_operations to finalize * * An ata_port_operations can inherit from another ops and that * ops can again inherit from another. This can go on as many * times as necessary as long as there is no loop in the * inheritance chain. * * Ops tables are finalized when the host is started. NULL or * unspecified entries are inherited from the closet ancestor * which has the method and the entry is populated with it. * After finalization, the ops table directly points to all the * methods and ->inherits is no longer necessary and cleared. * * Using ATA_OP_NULL, inheriting ops can force a method to NULL. * * LOCKING: * None. */ static void ata_finalize_port_ops(struct ata_port_operations *ops) { static DEFINE_SPINLOCK(lock); const struct ata_port_operations *cur; void **begin = (void **)ops; void **end = (void **)&ops->inherits; void **pp; if (!ops || !ops->inherits) return; spin_lock(&lock); for (cur = ops->inherits; cur; cur = cur->inherits) { void **inherit = (void **)cur; for (pp = begin; pp < end; pp++, inherit++) if (!*pp) *pp = *inherit; } for (pp = begin; pp < end; pp++) if (IS_ERR(*pp)) *pp = NULL; ops->inherits = NULL; spin_unlock(&lock); } /** * ata_host_start - start and freeze ports of an ATA host * @host: ATA host to start ports for * * Start and then freeze ports of @host. Started status is * recorded in host->flags, so this function can be called * multiple times. Ports are guaranteed to get started only * once. If host->ops isn't initialized yet, its set to the * first non-dummy port ops. * * LOCKING: * Inherited from calling layer (may sleep). * * RETURNS: * 0 if all ports are started successfully, -errno otherwise. */ int ata_host_start(struct ata_host *host) { int have_stop = 0; void *start_dr = NULL; int i, rc; if (host->flags & ATA_HOST_STARTED) return 0; ata_finalize_port_ops(host->ops); for (i = 0; i < host->n_ports; i++) { struct ata_port *ap = host->ports[i]; ata_finalize_port_ops(ap->ops); if (!host->ops && !ata_port_is_dummy(ap)) host->ops = ap->ops; if (ap->ops->port_stop) have_stop = 1; } if (host->ops && host->ops->host_stop) have_stop = 1; if (have_stop) { start_dr = devres_alloc(ata_host_stop, 0, GFP_KERNEL); if (!start_dr) return -ENOMEM; } for (i = 0; i < host->n_ports; i++) { struct ata_port *ap = host->ports[i]; if (ap->ops->port_start) { rc = ap->ops->port_start(ap); if (rc) { if (rc != -ENODEV) dev_err(host->dev, "failed to start port %d (errno=%d)\n", i, rc); goto err_out; } } ata_eh_freeze_port(ap); } if (start_dr) devres_add(host->dev, start_dr); host->flags |= ATA_HOST_STARTED; return 0; err_out: while (--i >= 0) { struct ata_port *ap = host->ports[i]; if (ap->ops->port_stop) ap->ops->port_stop(ap); } devres_free(start_dr); return rc; } EXPORT_SYMBOL_GPL(ata_host_start); /** * ata_host_init - Initialize a host struct for sas (ipr, libsas) * @host: host to initialize * @dev: device host is attached to * @ops: port_ops * */ void ata_host_init(struct ata_host *host, struct device *dev, struct ata_port_operations *ops) { spin_lock_init(&host->lock); mutex_init(&host->eh_mutex); host->n_tags = ATA_MAX_QUEUE; host->dev = dev; host->ops = ops; kref_init(&host->kref); } EXPORT_SYMBOL_GPL(ata_host_init); void __ata_port_probe(struct ata_port *ap) { struct ata_eh_info *ehi = &ap->link.eh_info; unsigned long flags; /* kick EH for boot probing */ spin_lock_irqsave(ap->lock, flags); ehi->probe_mask |= ATA_ALL_DEVICES; ehi->action |= ATA_EH_RESET; ehi->flags |= ATA_EHI_NO_AUTOPSY | ATA_EHI_QUIET; ap->pflags &= ~ATA_PFLAG_INITIALIZING; ap->pflags |= ATA_PFLAG_LOADING; ata_port_schedule_eh(ap); spin_unlock_irqrestore(ap->lock, flags); } int ata_port_probe(struct ata_port *ap) { int rc = 0; if (ap->ops->error_handler) { __ata_port_probe(ap); ata_port_wait_eh(ap); } else { DPRINTK("ata%u: bus probe begin\n", ap->print_id); rc = ata_bus_probe(ap); DPRINTK("ata%u: bus probe end\n", ap->print_id); } return rc; } static void async_port_probe(void *data, async_cookie_t cookie) { struct ata_port *ap = data; /* * If we're not allowed to scan this host in parallel, * we need to wait until all previous scans have completed * before going further. * Jeff Garzik says this is only within a controller, so we * don't need to wait for port 0, only for later ports. */ if (!(ap->host->flags & ATA_HOST_PARALLEL_SCAN) && ap->port_no != 0) async_synchronize_cookie(cookie); (void)ata_port_probe(ap); /* in order to keep device order, we need to synchronize at this point */ async_synchronize_cookie(cookie); ata_scsi_scan_host(ap, 1); } /** * ata_host_register - register initialized ATA host * @host: ATA host to register * @sht: template for SCSI host * * Register initialized ATA host. @host is allocated using * ata_host_alloc() and fully initialized by LLD. This function * starts ports, registers @host with ATA and SCSI layers and * probe registered devices. * * LOCKING: * Inherited from calling layer (may sleep). * * RETURNS: * 0 on success, -errno otherwise. */ int ata_host_register(struct ata_host *host, struct scsi_host_template *sht) { int i, rc; host->n_tags = clamp(sht->can_queue, 1, ATA_MAX_QUEUE); /* host must have been started */ if (!(host->flags & ATA_HOST_STARTED)) { dev_err(host->dev, "BUG: trying to register unstarted host\n"); WARN_ON(1); return -EINVAL; } /* Blow away unused ports. This happens when LLD can't * determine the exact number of ports to allocate at * allocation time. */ for (i = host->n_ports; host->ports[i]; i++) kfree(host->ports[i]); /* give ports names and add SCSI hosts */ for (i = 0; i < host->n_ports; i++) { host->ports[i]->print_id = atomic_inc_return(&ata_print_id); host->ports[i]->local_port_no = i + 1; } /* Create associated sysfs transport objects */ for (i = 0; i < host->n_ports; i++) { rc = ata_tport_add(host->dev,host->ports[i]); if (rc) { goto err_tadd; } } rc = ata_scsi_add_hosts(host, sht); if (rc) goto err_tadd; /* set cable, sata_spd_limit and report */ for (i = 0; i < host->n_ports; i++) { struct ata_port *ap = host->ports[i]; unsigned long xfer_mask; /* set SATA cable type if still unset */ if (ap->cbl == ATA_CBL_NONE && (ap->flags & ATA_FLAG_SATA)) ap->cbl = ATA_CBL_SATA; /* init sata_spd_limit to the current value */ sata_link_init_spd(&ap->link); if (ap->slave_link) sata_link_init_spd(ap->slave_link); /* print per-port info to dmesg */ xfer_mask = ata_pack_xfermask(ap->pio_mask, ap->mwdma_mask, ap->udma_mask); if (!ata_port_is_dummy(ap)) { ata_port_info(ap, "%cATA max %s %s\n", (ap->flags & ATA_FLAG_SATA) ? 'S' : 'P', ata_mode_string(xfer_mask), ap->link.eh_info.desc); ata_ehi_clear_desc(&ap->link.eh_info); } else ata_port_info(ap, "DUMMY\n"); } /* perform each probe asynchronously */ for (i = 0; i < host->n_ports; i++) { struct ata_port *ap = host->ports[i]; ap->cookie = async_schedule(async_port_probe, ap); } return 0; err_tadd: while (--i >= 0) { ata_tport_delete(host->ports[i]); } return rc; } EXPORT_SYMBOL_GPL(ata_host_register); /** * ata_host_activate - start host, request IRQ and register it * @host: target ATA host * @irq: IRQ to request * @irq_handler: irq_handler used when requesting IRQ * @irq_flags: irq_flags used when requesting IRQ * @sht: scsi_host_template to use when registering the host * * After allocating an ATA host and initializing it, most libata * LLDs perform three steps to activate the host - start host, * request IRQ and register it. This helper takes necessary * arguments and performs the three steps in one go. * * An invalid IRQ skips the IRQ registration and expects the host to * have set polling mode on the port. In this case, @irq_handler * should be NULL. * * LOCKING: * Inherited from calling layer (may sleep). * * RETURNS: * 0 on success, -errno otherwise. */ int ata_host_activate(struct ata_host *host, int irq, irq_handler_t irq_handler, unsigned long irq_flags, struct scsi_host_template *sht) { int i, rc; char *irq_desc; rc = ata_host_start(host); if (rc) return rc; /* Special case for polling mode */ if (!irq) { WARN_ON(irq_handler); return ata_host_register(host, sht); } irq_desc = devm_kasprintf(host->dev, GFP_KERNEL, "%s[%s]", dev_driver_string(host->dev), dev_name(host->dev)); if (!irq_desc) return -ENOMEM; rc = devm_request_irq(host->dev, irq, irq_handler, irq_flags, irq_desc, host); if (rc) return rc; for (i = 0; i < host->n_ports; i++) ata_port_desc(host->ports[i], "irq %d", irq); rc = ata_host_register(host, sht); /* if failed, just free the IRQ and leave ports alone */ if (rc) devm_free_irq(host->dev, irq, host); return rc; } EXPORT_SYMBOL_GPL(ata_host_activate); /** * ata_port_detach - Detach ATA port in preparation of device removal * @ap: ATA port to be detached * * Detach all ATA devices and the associated SCSI devices of @ap; * then, remove the associated SCSI host. @ap is guaranteed to * be quiescent on return from this function. * * LOCKING: * Kernel thread context (may sleep). */ static void ata_port_detach(struct ata_port *ap) { unsigned long flags; struct ata_link *link; struct ata_device *dev; if (!ap->ops->error_handler) goto skip_eh; /* tell EH we're leaving & flush EH */ spin_lock_irqsave(ap->lock, flags); ap->pflags |= ATA_PFLAG_UNLOADING; ata_port_schedule_eh(ap); spin_unlock_irqrestore(ap->lock, flags); /* wait till EH commits suicide */ ata_port_wait_eh(ap); /* it better be dead now */ WARN_ON(!(ap->pflags & ATA_PFLAG_UNLOADED)); cancel_delayed_work_sync(&ap->hotplug_task); skip_eh: /* clean up zpodd on port removal */ ata_for_each_link(link, ap, HOST_FIRST) { ata_for_each_dev(dev, link, ALL) { if (zpodd_dev_enabled(dev)) zpodd_exit(dev); } } if (ap->pmp_link) { int i; for (i = 0; i < SATA_PMP_MAX_PORTS; i++) ata_tlink_delete(&ap->pmp_link[i]); } /* remove the associated SCSI host */ scsi_remove_host(ap->scsi_host); ata_tport_delete(ap); } /** * ata_host_detach - Detach all ports of an ATA host * @host: Host to detach * * Detach all ports of @host. * * LOCKING: * Kernel thread context (may sleep). */ void ata_host_detach(struct ata_host *host) { int i; for (i = 0; i < host->n_ports; i++) { /* Ensure ata_port probe has completed */ async_synchronize_cookie(host->ports[i]->cookie + 1); ata_port_detach(host->ports[i]); } /* the host is dead now, dissociate ACPI */ ata_acpi_dissociate(host); } EXPORT_SYMBOL_GPL(ata_host_detach); #ifdef CONFIG_PCI /** * ata_pci_remove_one - PCI layer callback for device removal * @pdev: PCI device that was removed * * PCI layer indicates to libata via this hook that hot-unplug or * module unload event has occurred. Detach all ports. Resource * release is handled via devres. * * LOCKING: * Inherited from PCI layer (may sleep). */ void ata_pci_remove_one(struct pci_dev *pdev) { struct ata_host *host = pci_get_drvdata(pdev); ata_host_detach(host); } EXPORT_SYMBOL_GPL(ata_pci_remove_one); void ata_pci_shutdown_one(struct pci_dev *pdev) { struct ata_host *host = pci_get_drvdata(pdev); int i; for (i = 0; i < host->n_ports; i++) { struct ata_port *ap = host->ports[i]; ap->pflags |= ATA_PFLAG_FROZEN; /* Disable port interrupts */ if (ap->ops->freeze) ap->ops->freeze(ap); /* Stop the port DMA engines */ if (ap->ops->port_stop) ap->ops->port_stop(ap); } } EXPORT_SYMBOL_GPL(ata_pci_shutdown_one); /* move to PCI subsystem */ int pci_test_config_bits(struct pci_dev *pdev, const struct pci_bits *bits) { unsigned long tmp = 0; switch (bits->width) { case 1: { u8 tmp8 = 0; pci_read_config_byte(pdev, bits->reg, &tmp8); tmp = tmp8; break; } case 2: { u16 tmp16 = 0; pci_read_config_word(pdev, bits->reg, &tmp16); tmp = tmp16; break; } case 4: { u32 tmp32 = 0; pci_read_config_dword(pdev, bits->reg, &tmp32); tmp = tmp32; break; } default: return -EINVAL; } tmp &= bits->mask; return (tmp == bits->val) ? 1 : 0; } EXPORT_SYMBOL_GPL(pci_test_config_bits); #ifdef CONFIG_PM void ata_pci_device_do_suspend(struct pci_dev *pdev, pm_message_t mesg) { pci_save_state(pdev); pci_disable_device(pdev); if (mesg.event & PM_EVENT_SLEEP) pci_set_power_state(pdev, PCI_D3hot); } EXPORT_SYMBOL_GPL(ata_pci_device_do_suspend); int ata_pci_device_do_resume(struct pci_dev *pdev) { int rc; pci_set_power_state(pdev, PCI_D0); pci_restore_state(pdev); rc = pcim_enable_device(pdev); if (rc) { dev_err(&pdev->dev, "failed to enable device after resume (%d)\n", rc); return rc; } pci_set_master(pdev); return 0; } EXPORT_SYMBOL_GPL(ata_pci_device_do_resume); int ata_pci_device_suspend(struct pci_dev *pdev, pm_message_t mesg) { struct ata_host *host = pci_get_drvdata(pdev); int rc = 0; rc = ata_host_suspend(host, mesg); if (rc) return rc; ata_pci_device_do_suspend(pdev, mesg); return 0; } EXPORT_SYMBOL_GPL(ata_pci_device_suspend); int ata_pci_device_resume(struct pci_dev *pdev) { struct ata_host *host = pci_get_drvdata(pdev); int rc; rc = ata_pci_device_do_resume(pdev); if (rc == 0) ata_host_resume(host); return rc; } EXPORT_SYMBOL_GPL(ata_pci_device_resume); #endif /* CONFIG_PM */ #endif /* CONFIG_PCI */ /** * ata_platform_remove_one - Platform layer callback for device removal * @pdev: Platform device that was removed * * Platform layer indicates to libata via this hook that hot-unplug or * module unload event has occurred. Detach all ports. Resource * release is handled via devres. * * LOCKING: * Inherited from platform layer (may sleep). */ int ata_platform_remove_one(struct platform_device *pdev) { struct ata_host *host = platform_get_drvdata(pdev); ata_host_detach(host); return 0; } EXPORT_SYMBOL_GPL(ata_platform_remove_one); #ifdef CONFIG_ATA_FORCE static int __init ata_parse_force_one(char **cur, struct ata_force_ent *force_ent, const char **reason) { static const struct ata_force_param force_tbl[] __initconst = { { "40c", .cbl = ATA_CBL_PATA40 }, { "80c", .cbl = ATA_CBL_PATA80 }, { "short40c", .cbl = ATA_CBL_PATA40_SHORT }, { "unk", .cbl = ATA_CBL_PATA_UNK }, { "ign", .cbl = ATA_CBL_PATA_IGN }, { "sata", .cbl = ATA_CBL_SATA }, { "1.5Gbps", .spd_limit = 1 }, { "3.0Gbps", .spd_limit = 2 }, { "noncq", .horkage_on = ATA_HORKAGE_NONCQ }, { "ncq", .horkage_off = ATA_HORKAGE_NONCQ }, { "noncqtrim", .horkage_on = ATA_HORKAGE_NO_NCQ_TRIM }, { "ncqtrim", .horkage_off = ATA_HORKAGE_NO_NCQ_TRIM }, { "noncqati", .horkage_on = ATA_HORKAGE_NO_NCQ_ON_ATI }, { "ncqati", .horkage_off = ATA_HORKAGE_NO_NCQ_ON_ATI }, { "dump_id", .horkage_on = ATA_HORKAGE_DUMP_ID }, { "pio0", .xfer_mask = 1 << (ATA_SHIFT_PIO + 0) }, { "pio1", .xfer_mask = 1 << (ATA_SHIFT_PIO + 1) }, { "pio2", .xfer_mask = 1 << (ATA_SHIFT_PIO + 2) }, { "pio3", .xfer_mask = 1 << (ATA_SHIFT_PIO + 3) }, { "pio4", .xfer_mask = 1 << (ATA_SHIFT_PIO + 4) }, { "pio5", .xfer_mask = 1 << (ATA_SHIFT_PIO + 5) }, { "pio6", .xfer_mask = 1 << (ATA_SHIFT_PIO + 6) }, { "mwdma0", .xfer_mask = 1 << (ATA_SHIFT_MWDMA + 0) }, { "mwdma1", .xfer_mask = 1 << (ATA_SHIFT_MWDMA + 1) }, { "mwdma2", .xfer_mask = 1 << (ATA_SHIFT_MWDMA + 2) }, { "mwdma3", .xfer_mask = 1 << (ATA_SHIFT_MWDMA + 3) }, { "mwdma4", .xfer_mask = 1 << (ATA_SHIFT_MWDMA + 4) }, { "udma0", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 0) }, { "udma16", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 0) }, { "udma/16", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 0) }, { "udma1", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 1) }, { "udma25", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 1) }, { "udma/25", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 1) }, { "udma2", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 2) }, { "udma33", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 2) }, { "udma/33", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 2) }, { "udma3", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 3) }, { "udma44", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 3) }, { "udma/44", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 3) }, { "udma4", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 4) }, { "udma66", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 4) }, { "udma/66", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 4) }, { "udma5", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 5) }, { "udma100", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 5) }, { "udma/100", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 5) }, { "udma6", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 6) }, { "udma133", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 6) }, { "udma/133", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 6) }, { "udma7", .xfer_mask = 1 << (ATA_SHIFT_UDMA + 7) }, { "nohrst", .lflags = ATA_LFLAG_NO_HRST }, { "nosrst", .lflags = ATA_LFLAG_NO_SRST }, { "norst", .lflags = ATA_LFLAG_NO_HRST | ATA_LFLAG_NO_SRST }, { "rstonce", .lflags = ATA_LFLAG_RST_ONCE }, { "atapi_dmadir", .horkage_on = ATA_HORKAGE_ATAPI_DMADIR }, { "disable", .horkage_on = ATA_HORKAGE_DISABLE }, }; char *start = *cur, *p = *cur; char *id, *val, *endp; const struct ata_force_param *match_fp = NULL; int nr_matches = 0, i; /* find where this param ends and update *cur */ while (*p != '\0' && *p != ',') p++; if (*p == '\0') *cur = p; else *cur = p + 1; *p = '\0'; /* parse */ p = strchr(start, ':'); if (!p) { val = strstrip(start); goto parse_val; } *p = '\0'; id = strstrip(start); val = strstrip(p + 1); /* parse id */ p = strchr(id, '.'); if (p) { *p++ = '\0'; force_ent->device = simple_strtoul(p, &endp, 10); if (p == endp || *endp != '\0') { *reason = "invalid device"; return -EINVAL; } } force_ent->port = simple_strtoul(id, &endp, 10); if (id == endp || *endp != '\0') { *reason = "invalid port/link"; return -EINVAL; } parse_val: /* parse val, allow shortcuts so that both 1.5 and 1.5Gbps work */ for (i = 0; i < ARRAY_SIZE(force_tbl); i++) { const struct ata_force_param *fp = &force_tbl[i]; if (strncasecmp(val, fp->name, strlen(val))) continue; nr_matches++; match_fp = fp; if (strcasecmp(val, fp->name) == 0) { nr_matches = 1; break; } } if (!nr_matches) { *reason = "unknown value"; return -EINVAL; } if (nr_matches > 1) { *reason = "ambiguous value"; return -EINVAL; } force_ent->param = *match_fp; return 0; } static void __init ata_parse_force_param(void) { int idx = 0, size = 1; int last_port = -1, last_device = -1; char *p, *cur, *next; /* calculate maximum number of params and allocate force_tbl */ for (p = ata_force_param_buf; *p; p++) if (*p == ',') size++; ata_force_tbl = kcalloc(size, sizeof(ata_force_tbl[0]), GFP_KERNEL); if (!ata_force_tbl) { printk(KERN_WARNING "ata: failed to extend force table, " "libata.force ignored\n"); return; } /* parse and populate the table */ for (cur = ata_force_param_buf; *cur != '\0'; cur = next) { const char *reason = ""; struct ata_force_ent te = { .port = -1, .device = -1 }; next = cur; if (ata_parse_force_one(&next, &te, &reason)) { printk(KERN_WARNING "ata: failed to parse force " "parameter \"%s\" (%s)\n", cur, reason); continue; } if (te.port == -1) { te.port = last_port; te.device = last_device; } ata_force_tbl[idx++] = te; last_port = te.port; last_device = te.device; } ata_force_tbl_size = idx; } static void ata_free_force_param(void) { kfree(ata_force_tbl); } #else static inline void ata_parse_force_param(void) { } static inline void ata_free_force_param(void) { } #endif static int __init ata_init(void) { int rc; ata_parse_force_param(); rc = ata_sff_init(); if (rc) { ata_free_force_param(); return rc; } libata_transport_init(); ata_scsi_transport_template = ata_attach_transport(); if (!ata_scsi_transport_template) { ata_sff_exit(); rc = -ENOMEM; goto err_out; } printk(KERN_DEBUG "libata version " DRV_VERSION " loaded.\n"); return 0; err_out: return rc; } static void __exit ata_exit(void) { ata_release_transport(ata_scsi_transport_template); libata_transport_exit(); ata_sff_exit(); ata_free_force_param(); } subsys_initcall(ata_init); module_exit(ata_exit); static DEFINE_RATELIMIT_STATE(ratelimit, HZ / 5, 1); int ata_ratelimit(void) { return __ratelimit(&ratelimit); } EXPORT_SYMBOL_GPL(ata_ratelimit); /** * ata_msleep - ATA EH owner aware msleep * @ap: ATA port to attribute the sleep to * @msecs: duration to sleep in milliseconds * * Sleeps @msecs. If the current task is owner of @ap's EH, the * ownership is released before going to sleep and reacquired * after the sleep is complete. IOW, other ports sharing the * @ap->host will be allowed to own the EH while this task is * sleeping. * * LOCKING: * Might sleep. */ void ata_msleep(struct ata_port *ap, unsigned int msecs) { bool owns_eh = ap && ap->host->eh_owner == current; if (owns_eh) ata_eh_release(ap); if (msecs < 20) { unsigned long usecs = msecs * USEC_PER_MSEC; usleep_range(usecs, usecs + 50); } else { msleep(msecs); } if (owns_eh) ata_eh_acquire(ap); } EXPORT_SYMBOL_GPL(ata_msleep); /** * ata_wait_register - wait until register value changes * @ap: ATA port to wait register for, can be NULL * @reg: IO-mapped register * @mask: Mask to apply to read register value * @val: Wait condition * @interval: polling interval in milliseconds * @timeout: timeout in milliseconds * * Waiting for some bits of register to change is a common * operation for ATA controllers. This function reads 32bit LE * IO-mapped register @reg and tests for the following condition. * * (*@reg & mask) != val * * If the condition is met, it returns; otherwise, the process is * repeated after @interval_msec until timeout. * * LOCKING: * Kernel thread context (may sleep) * * RETURNS: * The final register value. */ u32 ata_wait_register(struct ata_port *ap, void __iomem *reg, u32 mask, u32 val, unsigned long interval, unsigned long timeout) { unsigned long deadline; u32 tmp; tmp = ioread32(reg); /* Calculate timeout _after_ the first read to make sure * preceding writes reach the controller before starting to * eat away the timeout. */ deadline = ata_deadline(jiffies, timeout); while ((tmp & mask) == val && time_before(jiffies, deadline)) { ata_msleep(ap, interval); tmp = ioread32(reg); } return tmp; } EXPORT_SYMBOL_GPL(ata_wait_register); /* * Dummy port_ops */ static unsigned int ata_dummy_qc_issue(struct ata_queued_cmd *qc) { return AC_ERR_SYSTEM; } static void ata_dummy_error_handler(struct ata_port *ap) { /* truly dummy */ } struct ata_port_operations ata_dummy_port_ops = { .qc_prep = ata_noop_qc_prep, .qc_issue = ata_dummy_qc_issue, .error_handler = ata_dummy_error_handler, .sched_eh = ata_std_sched_eh, .end_eh = ata_std_end_eh, }; EXPORT_SYMBOL_GPL(ata_dummy_port_ops); const struct ata_port_info ata_dummy_port_info = { .port_ops = &ata_dummy_port_ops, }; EXPORT_SYMBOL_GPL(ata_dummy_port_info); /* * Utility print functions */ void ata_port_printk(const struct ata_port *ap, const char *level, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk("%sata%u: %pV", level, ap->print_id, &vaf); va_end(args); } EXPORT_SYMBOL(ata_port_printk); void ata_link_printk(const struct ata_link *link, const char *level, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; if (sata_pmp_attached(link->ap) || link->ap->slave_link) printk("%sata%u.%02u: %pV", level, link->ap->print_id, link->pmp, &vaf); else printk("%sata%u: %pV", level, link->ap->print_id, &vaf); va_end(args); } EXPORT_SYMBOL(ata_link_printk); void ata_dev_printk(const struct ata_device *dev, const char *level, const char *fmt, ...) { struct va_format vaf; va_list args; va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; printk("%sata%u.%02u: %pV", level, dev->link->ap->print_id, dev->link->pmp + dev->devno, &vaf); va_end(args); } EXPORT_SYMBOL(ata_dev_printk); void ata_print_version(const struct device *dev, const char *version) { dev_printk(KERN_DEBUG, dev, "version %s\n", version); } EXPORT_SYMBOL(ata_print_version);
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 /* SPDX-License-Identifier: GPL-2.0 */ /* File: linux/posix_acl.h (C) 2002 Andreas Gruenbacher, <a.gruenbacher@computer.org> */ #ifndef __LINUX_POSIX_ACL_H #define __LINUX_POSIX_ACL_H #include <linux/bug.h> #include <linux/slab.h> #include <linux/rcupdate.h> #include <linux/refcount.h> #include <uapi/linux/posix_acl.h> struct posix_acl_entry { short e_tag; unsigned short e_perm; union { kuid_t e_uid; kgid_t e_gid; }; }; struct posix_acl { refcount_t a_refcount; struct rcu_head a_rcu; unsigned int a_count; struct posix_acl_entry a_entries[]; }; #define FOREACH_ACL_ENTRY(pa, acl, pe) \ for(pa=(acl)->a_entries, pe=pa+(acl)->a_count; pa<pe; pa++) /* * Duplicate an ACL handle. */ static inline struct posix_acl * posix_acl_dup(struct posix_acl *acl) { if (acl) refcount_inc(&acl->a_refcount); return acl; } /* * Free an ACL handle. */ static inline void posix_acl_release(struct posix_acl *acl) { if (acl && refcount_dec_and_test(&acl->a_refcount)) kfree_rcu(acl, a_rcu); } /* posix_acl.c */ extern void posix_acl_init(struct posix_acl *, int); extern struct posix_acl *posix_acl_alloc(int, gfp_t); extern int posix_acl_valid(struct user_namespace *, const struct posix_acl *); extern int posix_acl_permission(struct inode *, const struct posix_acl *, int); extern struct posix_acl *posix_acl_from_mode(umode_t, gfp_t); extern int posix_acl_equiv_mode(const struct posix_acl *, umode_t *); extern int __posix_acl_create(struct posix_acl **, gfp_t, umode_t *); extern int __posix_acl_chmod(struct posix_acl **, gfp_t, umode_t); extern struct posix_acl *get_posix_acl(struct inode *, int); extern int set_posix_acl(struct inode *, int, struct posix_acl *); #ifdef CONFIG_FS_POSIX_ACL extern int posix_acl_chmod(struct inode *, umode_t); extern int posix_acl_create(struct inode *, umode_t *, struct posix_acl **, struct posix_acl **); extern int posix_acl_update_mode(struct inode *, umode_t *, struct posix_acl **); extern int simple_set_acl(struct inode *, struct posix_acl *, int); extern int simple_acl_create(struct inode *, struct inode *); struct posix_acl *get_cached_acl(struct inode *inode, int type); struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type); void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl); void forget_cached_acl(struct inode *inode, int type); void forget_all_cached_acls(struct inode *inode); static inline void cache_no_acl(struct inode *inode) { inode->i_acl = NULL; inode->i_default_acl = NULL; } #else static inline int posix_acl_chmod(struct inode *inode, umode_t mode) { return 0; } #define simple_set_acl NULL static inline int simple_acl_create(struct inode *dir, struct inode *inode) { return 0; } static inline void cache_no_acl(struct inode *inode) { } static inline int posix_acl_create(struct inode *inode, umode_t *mode, struct posix_acl **default_acl, struct posix_acl **acl) { *default_acl = *acl = NULL; return 0; } static inline void forget_all_cached_acls(struct inode *inode) { } #endif /* CONFIG_FS_POSIX_ACL */ struct posix_acl *get_acl(struct inode *inode, int type); #endif /* __LINUX_POSIX_ACL_H */
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SECCOMP_H #define _LINUX_SECCOMP_H #include <uapi/linux/seccomp.h> #define SECCOMP_FILTER_FLAG_MASK (SECCOMP_FILTER_FLAG_TSYNC | \ SECCOMP_FILTER_FLAG_LOG | \ SECCOMP_FILTER_FLAG_SPEC_ALLOW | \ SECCOMP_FILTER_FLAG_NEW_LISTENER | \ SECCOMP_FILTER_FLAG_TSYNC_ESRCH) /* sizeof() the first published struct seccomp_notif_addfd */ #define SECCOMP_NOTIFY_ADDFD_SIZE_VER0 24 #define SECCOMP_NOTIFY_ADDFD_SIZE_LATEST SECCOMP_NOTIFY_ADDFD_SIZE_VER0 #ifdef CONFIG_SECCOMP #include <linux/thread_info.h> #include <linux/atomic.h> #include <asm/seccomp.h> struct seccomp_filter; /** * struct seccomp - the state of a seccomp'ed process * * @mode: indicates one of the valid values above for controlled * system calls available to a process. * @filter: must always point to a valid seccomp-filter or NULL as it is * accessed without locking during system call entry. * * @filter must only be accessed from the context of current as there * is no read locking. */ struct seccomp { int mode; atomic_t filter_count; struct seccomp_filter *filter; }; #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER extern int __secure_computing(const struct seccomp_data *sd); static inline int secure_computing(void) { if (unlikely(test_thread_flag(TIF_SECCOMP))) return __secure_computing(NULL); return 0; } #else extern void secure_computing_strict(int this_syscall); #endif extern long prctl_get_seccomp(void); extern long prctl_set_seccomp(unsigned long, void __user *); static inline int seccomp_mode(struct seccomp *s) { return s->mode; } #else /* CONFIG_SECCOMP */ #include <linux/errno.h> struct seccomp { }; struct seccomp_filter { }; struct seccomp_data; #ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER static inline int secure_computing(void) { return 0; } static inline int __secure_computing(const struct seccomp_data *sd) { return 0; } #else static inline void secure_computing_strict(int this_syscall) { return; } #endif static inline long prctl_get_seccomp(void) { return -EINVAL; } static inline long prctl_set_seccomp(unsigned long arg2, char __user *arg3) { return -EINVAL; } static inline int seccomp_mode(struct seccomp *s) { return SECCOMP_MODE_DISABLED; } #endif /* CONFIG_SECCOMP */ #ifdef CONFIG_SECCOMP_FILTER extern void seccomp_filter_release(struct task_struct *tsk); extern void get_seccomp_filter(struct task_struct *tsk); #else /* CONFIG_SECCOMP_FILTER */ static inline void seccomp_filter_release(struct task_struct *tsk) { return; } static inline void get_seccomp_filter(struct task_struct *tsk) { return; } #endif /* CONFIG_SECCOMP_FILTER */ #if defined(CONFIG_SECCOMP_FILTER) && defined(CONFIG_CHECKPOINT_RESTORE) extern long seccomp_get_filter(struct task_struct *task, unsigned long filter_off, void __user *data); extern long seccomp_get_metadata(struct task_struct *task, unsigned long filter_off, void __user *data); #else static inline long seccomp_get_filter(struct task_struct *task, unsigned long n, void __user *data) { return -EINVAL; } static inline long seccomp_get_metadata(struct task_struct *task, unsigned long filter_off, void __user *data) { return -EINVAL; } #endif /* CONFIG_SECCOMP_FILTER && CONFIG_CHECKPOINT_RESTORE */ #endif /* _LINUX_SECCOMP_H */
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 /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_X86_XSAVE_H #define __ASM_X86_XSAVE_H #include <linux/uaccess.h> #include <linux/types.h> #include <asm/processor.h> #include <asm/user.h> /* Bit 63 of XCR0 is reserved for futur