diff options
Diffstat (limited to 'kernel')
37 files changed, 2084 insertions, 1042 deletions
diff --git a/kernel/audit.c b/kernel/audit.c index c71bd26631a2..8296aa516c5a 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -407,7 +407,7 @@ static void kauditd_send_skb(struct sk_buff *skb) audit_hold_skb(skb); } else /* drop the extra reference if sent ok */ - kfree_skb(skb); + consume_skb(skb); } static int kauditd_thread(void *dummy) diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 3ac6f5b0a64b..a8ce09954404 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1788,6 +1788,29 @@ out: return retval; } +/** + * cgroup_attach_task_current_cg - attach task 'tsk' to current task's cgroup + * @tsk: the task to be attached + */ +int cgroup_attach_task_current_cg(struct task_struct *tsk) +{ + struct cgroupfs_root *root; + struct cgroup *cur_cg; + int retval = 0; + + cgroup_lock(); + for_each_active_root(root) { + cur_cg = task_cgroup_from_root(current, root); + retval = cgroup_attach_task(cur_cg, tsk); + if (retval) + break; + } + cgroup_unlock(); + + return retval; +} +EXPORT_SYMBOL_GPL(cgroup_attach_task_current_cg); + /* * Attach task with pid 'pid' to cgroup 'cgrp'. Call with cgroup_mutex * held. May take task_lock of task diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 02b9611eadde..7cb37d86a005 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -105,7 +105,7 @@ struct cpuset { /* for custom sched domain */ int relax_domain_level; - /* used for walking a cpuset heirarchy */ + /* used for walking a cpuset hierarchy */ struct list_head stack_list; }; diff --git a/kernel/cred.c b/kernel/cred.c index a2d5504fbcc2..60bc8b1e32e6 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -209,6 +209,31 @@ void exit_creds(struct task_struct *tsk) } } +/** + * get_task_cred - Get another task's objective credentials + * @task: The task to query + * + * Get the objective credentials of a task, pinning them so that they can't go + * away. Accessing a task's credentials directly is not permitted. + * + * The caller must also make sure task doesn't get deleted, either by holding a + * ref on task or by holding tasklist_lock to prevent it from being unlinked. + */ +const struct cred *get_task_cred(struct task_struct *task) +{ + const struct cred *cred; + + rcu_read_lock(); + + do { + cred = __task_cred((task)); + BUG_ON(!cred); + } while (!atomic_inc_not_zero(&((struct cred *)cred)->usage)); + + rcu_read_unlock(); + return cred; +} + /* * Allocate blank credentials, such that the credentials can be filled in at a * later date without risk of ENOMEM. diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 5cb7cd1de10c..3c2d4972d235 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -6,7 +6,7 @@ * Copyright (C) 2000-2001 VERITAS Software Corporation. * Copyright (C) 2002-2004 Timesys Corporation * Copyright (C) 2003-2004 Amit S. Kale <amitkale@linsyssoft.com> - * Copyright (C) 2004 Pavel Machek <pavel@suse.cz> + * Copyright (C) 2004 Pavel Machek <pavel@ucw.cz> * Copyright (C) 2004-2006 Tom Rini <trini@kernel.crashing.org> * Copyright (C) 2004-2006 LinSysSoft Technologies Pvt. Ltd. * Copyright (C) 2005-2009 Wind River Systems, Inc. @@ -605,13 +605,15 @@ cpu_master_loop: if (dbg_kdb_mode) { kgdb_connected = 1; error = kdb_stub(ks); + if (error == -1) + continue; + kgdb_connected = 0; } else { error = gdb_serial_stub(ks); } if (error == DBG_PASS_EVENT) { dbg_kdb_mode = !dbg_kdb_mode; - kgdb_connected = 0; } else if (error == DBG_SWITCH_CPU_EVENT) { dbg_cpu_switch(cpu, dbg_switch_cpu); goto cpu_loop; diff --git a/kernel/debug/gdbstub.c b/kernel/debug/gdbstub.c index 4b17b3269525..481a7bd2dfe7 100644 --- a/kernel/debug/gdbstub.c +++ b/kernel/debug/gdbstub.c @@ -6,7 +6,7 @@ * Copyright (C) 2000-2001 VERITAS Software Corporation. * Copyright (C) 2002-2004 Timesys Corporation * Copyright (C) 2003-2004 Amit S. Kale <amitkale@linsyssoft.com> - * Copyright (C) 2004 Pavel Machek <pavel@suse.cz> + * Copyright (C) 2004 Pavel Machek <pavel@ucw.cz> * Copyright (C) 2004-2006 Tom Rini <trini@kernel.crashing.org> * Copyright (C) 2004-2006 LinSysSoft Technologies Pvt. Ltd. * Copyright (C) 2005-2009 Wind River Systems, Inc. @@ -52,17 +52,6 @@ static unsigned long gdb_regs[(NUMREGBYTES + * GDB remote protocol parser: */ -static int hex(char ch) -{ - if ((ch >= 'a') && (ch <= 'f')) - return ch - 'a' + 10; - if ((ch >= '0') && (ch <= '9')) - return ch - '0'; - if ((ch >= 'A') && (ch <= 'F')) - return ch - 'A' + 10; - return -1; -} - #ifdef CONFIG_KGDB_KDB static int gdbstub_read_wait(void) { @@ -123,8 +112,8 @@ static void get_packet(char *buffer) buffer[count] = 0; if (ch == '#') { - xmitcsum = hex(gdbstub_read_wait()) << 4; - xmitcsum += hex(gdbstub_read_wait()); + xmitcsum = hex_to_bin(gdbstub_read_wait()) << 4; + xmitcsum += hex_to_bin(gdbstub_read_wait()); if (checksum != xmitcsum) /* failed checksum */ @@ -236,7 +225,7 @@ void gdbstub_msg_write(const char *s, int len) * buf. Return a pointer to the last char put in buf (null). May * return an error. */ -int kgdb_mem2hex(char *mem, char *buf, int count) +char *kgdb_mem2hex(char *mem, char *buf, int count) { char *tmp; int err; @@ -248,17 +237,16 @@ int kgdb_mem2hex(char *mem, char *buf, int count) tmp = buf + count; err = probe_kernel_read(tmp, mem, count); - if (!err) { - while (count > 0) { - buf = pack_hex_byte(buf, *tmp); - tmp++; - count--; - } - - *buf = 0; + if (err) + return NULL; + while (count > 0) { + buf = pack_hex_byte(buf, *tmp); + tmp++; + count--; } + *buf = 0; - return err; + return buf; } /* @@ -280,8 +268,8 @@ int kgdb_hex2mem(char *buf, char *mem, int count) tmp_hex = tmp_raw - 1; while (tmp_hex >= buf) { tmp_raw--; - *tmp_raw = hex(*tmp_hex--); - *tmp_raw |= hex(*tmp_hex--) << 4; + *tmp_raw = hex_to_bin(*tmp_hex--); + *tmp_raw |= hex_to_bin(*tmp_hex--) << 4; } return probe_kernel_write(mem, tmp_raw, count); @@ -304,7 +292,7 @@ int kgdb_hex2long(char **ptr, unsigned long *long_val) (*ptr)++; } while (**ptr) { - hex_val = hex(**ptr); + hex_val = hex_to_bin(**ptr); if (hex_val < 0) break; @@ -339,6 +327,32 @@ static int kgdb_ebin2mem(char *buf, char *mem, int count) return probe_kernel_write(mem, c, size); } +#if DBG_MAX_REG_NUM > 0 +void pt_regs_to_gdb_regs(unsigned long *gdb_regs, struct pt_regs *regs) +{ + int i; + int idx = 0; + char *ptr = (char *)gdb_regs; + + for (i = 0; i < DBG_MAX_REG_NUM; i++) { + dbg_get_reg(i, ptr + idx, regs); + idx += dbg_reg_def[i].size; + } +} + +void gdb_regs_to_pt_regs(unsigned long *gdb_regs, struct pt_regs *regs) +{ + int i; + int idx = 0; + char *ptr = (char *)gdb_regs; + + for (i = 0; i < DBG_MAX_REG_NUM; i++) { + dbg_set_reg(i, ptr + idx, regs); + idx += dbg_reg_def[i].size; + } +} +#endif /* DBG_MAX_REG_NUM > 0 */ + /* Write memory due to an 'M' or 'X' packet. */ static int write_mem_msg(int binary) { @@ -378,28 +392,31 @@ static void error_packet(char *pkt, int error) * remapped to negative TIDs. */ -#define BUF_THREAD_ID_SIZE 16 +#define BUF_THREAD_ID_SIZE 8 static char *pack_threadid(char *pkt, unsigned char *id) { - char *limit; + unsigned char *limit; + int lzero = 1; + + limit = id + (BUF_THREAD_ID_SIZE / 2); + while (id < limit) { + if (!lzero || *id != 0) { + pkt = pack_hex_byte(pkt, *id); + lzero = 0; + } + id++; + } - limit = pkt + BUF_THREAD_ID_SIZE; - while (pkt < limit) - pkt = pack_hex_byte(pkt, *id++); + if (lzero) + pkt = pack_hex_byte(pkt, 0); return pkt; } static void int_to_threadref(unsigned char *id, int value) { - unsigned char *scan; - int i = 4; - - scan = (unsigned char *)id; - while (i--) - *scan++ = 0; - put_unaligned_be32(value, scan); + put_unaligned_be32(value, id); } static struct task_struct *getthread(struct pt_regs *regs, int tid) @@ -463,8 +480,7 @@ static void gdb_cmd_status(struct kgdb_state *ks) pack_hex_byte(&remcom_out_buffer[1], ks->signo); } -/* Handle the 'g' get registers request */ -static void gdb_cmd_getregs(struct kgdb_state *ks) +static void gdb_get_regs_helper(struct kgdb_state *ks) { struct task_struct *thread; void *local_debuggerinfo; @@ -505,6 +521,12 @@ static void gdb_cmd_getregs(struct kgdb_state *ks) */ sleeping_thread_to_gdb_regs(gdb_regs, thread); } +} + +/* Handle the 'g' get registers request */ +static void gdb_cmd_getregs(struct kgdb_state *ks) +{ + gdb_get_regs_helper(ks); kgdb_mem2hex((char *)gdb_regs, remcom_out_buffer, NUMREGBYTES); } @@ -527,13 +549,13 @@ static void gdb_cmd_memread(struct kgdb_state *ks) char *ptr = &remcom_in_buffer[1]; unsigned long length; unsigned long addr; - int err; + char *err; if (kgdb_hex2long(&ptr, &addr) > 0 && *ptr++ == ',' && kgdb_hex2long(&ptr, &length) > 0) { err = kgdb_mem2hex((char *)addr, remcom_out_buffer, length); - if (err) - error_packet(remcom_out_buffer, err); + if (!err) + error_packet(remcom_out_buffer, -EINVAL); } else { error_packet(remcom_out_buffer, -EINVAL); } @@ -550,6 +572,60 @@ static void gdb_cmd_memwrite(struct kgdb_state *ks) strcpy(remcom_out_buffer, "OK"); } +#if DBG_MAX_REG_NUM > 0 +static char *gdb_hex_reg_helper(int regnum, char *out) +{ + int i; + int offset = 0; + + for (i = 0; i < regnum; i++) + offset += dbg_reg_def[i].size; + return kgdb_mem2hex((char *)gdb_regs + offset, out, + dbg_reg_def[i].size); +} + +/* Handle the 'p' individual regster get */ +static void gdb_cmd_reg_get(struct kgdb_state *ks) +{ + unsigned long regnum; + char *ptr = &remcom_in_buffer[1]; + + kgdb_hex2long(&ptr, ®num); + if (regnum >= DBG_MAX_REG_NUM) { + error_packet(remcom_out_buffer, -EINVAL); + return; + } + gdb_get_regs_helper(ks); + gdb_hex_reg_helper(regnum, remcom_out_buffer); +} + +/* Handle the 'P' individual regster set */ +static void gdb_cmd_reg_set(struct kgdb_state *ks) +{ + unsigned long regnum; + char *ptr = &remcom_in_buffer[1]; + int i = 0; + + kgdb_hex2long(&ptr, ®num); + if (*ptr++ != '=' || + !(!kgdb_usethread || kgdb_usethread == current) || + !dbg_get_reg(regnum, gdb_regs, ks->linux_regs)) { + error_packet(remcom_out_buffer, -EINVAL); + return; + } + memset(gdb_regs, 0, sizeof(gdb_regs)); + while (i < sizeof(gdb_regs) * 2) + if (hex_to_bin(ptr[i]) >= 0) + i++; + else + break; + i = i / 2; + kgdb_hex2mem(ptr, (char *)gdb_regs, i); + dbg_set_reg(regnum, gdb_regs, ks->linux_regs); + strcpy(remcom_out_buffer, "OK"); +} +#endif /* DBG_MAX_REG_NUM > 0 */ + /* Handle the 'X' memory binary write bytes */ static void gdb_cmd_binwrite(struct kgdb_state *ks) { @@ -612,7 +688,7 @@ static void gdb_cmd_query(struct kgdb_state *ks) { struct task_struct *g; struct task_struct *p; - unsigned char thref[8]; + unsigned char thref[BUF_THREAD_ID_SIZE]; char *ptr; int i; int cpu; @@ -621,10 +697,8 @@ static void gdb_cmd_query(struct kgdb_state *ks) switch (remcom_in_buffer[1]) { case 's': case 'f': - if (memcmp(remcom_in_buffer + 2, "ThreadInfo", 10)) { - error_packet(remcom_out_buffer, -EINVAL); + if (memcmp(remcom_in_buffer + 2, "ThreadInfo", 10)) break; - } i = 0; remcom_out_buffer[0] = 'm'; @@ -634,8 +708,7 @@ static void gdb_cmd_query(struct kgdb_state *ks) for_each_online_cpu(cpu) { ks->thr_query = 0; int_to_threadref(thref, -cpu - 2); - pack_threadid(ptr, thref); - ptr += BUF_THREAD_ID_SIZE; + ptr = pack_threadid(ptr, thref); *(ptr++) = ','; i++; } @@ -644,8 +717,7 @@ static void gdb_cmd_query(struct kgdb_state *ks) do_each_thread(g, p) { if (i >= ks->thr_query && !finished) { int_to_threadref(thref, p->pid); - pack_threadid(ptr, thref); - ptr += BUF_THREAD_ID_SIZE; + ptr = pack_threadid(ptr, thref); *(ptr++) = ','; ks->thr_query++; if (ks->thr_query % KGDB_MAX_THREAD_QUERY == 0) @@ -665,10 +737,9 @@ static void gdb_cmd_query(struct kgdb_state *ks) pack_threadid(remcom_out_buffer + 2, thref); break; case 'T': - if (memcmp(remcom_in_buffer + 1, "ThreadExtraInfo,", 16)) { - error_packet(remcom_out_buffer, -EINVAL); + if (memcmp(remcom_in_buffer + 1, "ThreadExtraInfo,", 16)) break; - } + ks->threadid = 0; ptr = remcom_in_buffer + 17; kgdb_hex2long(&ptr, &ks->threadid); @@ -861,11 +932,14 @@ int gdb_serial_stub(struct kgdb_state *ks) int error = 0; int tmp; - /* Clear the out buffer. */ + /* Initialize comm buffer and globals. */ memset(remcom_out_buffer, 0, sizeof(remcom_out_buffer)); + kgdb_usethread = kgdb_info[ks->cpu].task; + ks->kgdb_usethreadid = shadow_pid(kgdb_info[ks->cpu].task->pid); + ks->pass_exception = 0; if (kgdb_connected) { - unsigned char thref[8]; + unsigned char thref[BUF_THREAD_ID_SIZE]; char *ptr; /* Reply to host that an exception has occurred */ @@ -879,10 +953,6 @@ int gdb_serial_stub(struct kgdb_state *ks) put_packet(remcom_out_buffer); } - kgdb_usethread = kgdb_info[ks->cpu].task; - ks->kgdb_usethreadid = shadow_pid(kgdb_info[ks->cpu].task->pid); - ks->pass_exception = 0; - while (1) { error = 0; @@ -907,6 +977,14 @@ int gdb_serial_stub(struct kgdb_state *ks) case 'M': /* MAA..AA,LLLL: Write LLLL bytes at address AA..AA */ gdb_cmd_memwrite(ks); break; +#if DBG_MAX_REG_NUM > 0 + case 'p': /* pXX Return gdb register XX (in hex) */ + gdb_cmd_reg_get(ks); + break; + case 'P': /* PXX=aaaa Set gdb register XX to aaaa (in hex) */ + gdb_cmd_reg_set(ks); + break; +#endif /* DBG_MAX_REG_NUM > 0 */ case 'X': /* XAA..AA,LLLL: Write LLLL bytes at address AA..AA */ gdb_cmd_binwrite(ks); break; diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 184cd8209c36..8577e45a9a58 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -312,7 +312,7 @@ int kdbgetularg(const char *arg, unsigned long *value) if (endp == arg) { /* - * Try base 16, for us folks too lazy to type the + * Also try base 16, for us folks too lazy to type the * leading 0x... */ val = simple_strtoul(arg, &endp, 16); @@ -325,6 +325,25 @@ int kdbgetularg(const char *arg, unsigned long *value) return 0; } +int kdbgetu64arg(const char *arg, u64 *value) +{ + char *endp; + u64 val; + + val = simple_strtoull(arg, &endp, 0); + + if (endp == arg) { + + val = simple_strtoull(arg, &endp, 16); + if (endp == arg) + return KDB_BADINT; + } + + *value = val; + + return 0; +} + /* * kdb_set - This function implements the 'set' command. Alter an * existing environment variable or create a new one. @@ -1770,11 +1789,65 @@ static int kdb_go(int argc, const char **argv) */ static int kdb_rd(int argc, const char **argv) { - int diag = kdb_check_regs(); - if (diag) - return diag; + int len = kdb_check_regs(); +#if DBG_MAX_REG_NUM > 0 + int i; + char *rname; + int rsize; + u64 reg64; + u32 reg32; + u16 reg16; + u8 reg8; + + if (len) + return len; + + for (i = 0; i < DBG_MAX_REG_NUM; i++) { + rsize = dbg_reg_def[i].size * 2; + if (rsize > 16) + rsize = 2; + if (len + strlen(dbg_reg_def[i].name) + 4 + rsize > 80) { + len = 0; + kdb_printf("\n"); + } + if (len) + len += kdb_printf(" "); + switch(dbg_reg_def[i].size * 8) { + case 8: + rname = dbg_get_reg(i, ®8, kdb_current_regs); + if (!rname) + break; + len += kdb_printf("%s: %02x", rname, reg8); + break; + case 16: + rname = dbg_get_reg(i, ®16, kdb_current_regs); + if (!rname) + break; + len += kdb_printf("%s: %04x", rname, reg16); + break; + case 32: + rname = dbg_get_reg(i, ®32, kdb_current_regs); + if (!rname) + break; + len += kdb_printf("%s: %08x", rname, reg32); + break; + case 64: + rname = dbg_get_reg(i, ®64, kdb_current_regs); + if (!rname) + break; + len += kdb_printf("%s: %016llx", rname, reg64); + break; + default: + len += kdb_printf("%s: ??", dbg_reg_def[i].name); + } + } + kdb_printf("\n"); +#else + if (len) + return len; kdb_dumpregs(kdb_current_regs); +#endif return 0; } @@ -1782,32 +1855,67 @@ static int kdb_rd(int argc, const char **argv) * kdb_rm - This function implements the 'rm' (register modify) command. * rm register-name new-contents * Remarks: - * Currently doesn't allow modification of control or - * debug registers. + * Allows register modification with the same restrictions as gdb */ static int kdb_rm(int argc, const char **argv) { +#if DBG_MAX_REG_NUM > 0 int diag; - int ind = 0; - unsigned long contents; + const char *rname; + int i; + u64 reg64; + u32 reg32; + u16 reg16; + u8 reg8; if (argc != 2) return KDB_ARGCOUNT; /* * Allow presence or absence of leading '%' symbol. */ - if (argv[1][0] == '%') - ind = 1; + rname = argv[1]; + if (*rname == '%') + rname++; - diag = kdbgetularg(argv[2], &contents); + diag = kdbgetu64arg(argv[2], ®64); if (diag) return diag; diag = kdb_check_regs(); if (diag) return diag; + + diag = KDB_BADREG; + for (i = 0; i < DBG_MAX_REG_NUM; i++) { + if (strcmp(rname, dbg_reg_def[i].name) == 0) { + diag = 0; + break; + } + } + if (!diag) { + switch(dbg_reg_def[i].size * 8) { + case 8: + reg8 = reg64; + dbg_set_reg(i, ®8, kdb_current_regs); + break; + case 16: + reg16 = reg64; + dbg_set_reg(i, ®16, kdb_current_regs); + break; + case 32: + reg32 = reg64; + dbg_set_reg(i, ®32, kdb_current_regs); + break; + case 64: + dbg_set_reg(i, ®64, kdb_current_regs); + break; + } + } + return diag; +#else kdb_printf("ERROR: Register set currently not implemented\n"); - return 0; + return 0; +#endif } #if defined(CONFIG_MAGIC_SYSRQ) @@ -1820,9 +1928,8 @@ static int kdb_sr(int argc, const char **argv) { if (argc != 1) return KDB_ARGCOUNT; - sysrq_toggle_support(1); kdb_trap_printk++; - handle_sysrq(*argv[1], NULL); + __handle_sysrq(*argv[1], NULL, 0); kdb_trap_printk--; return 0; @@ -1883,6 +1990,7 @@ static int kdb_lsmod(int argc, const char **argv) kdb_printf(" (Loading)"); else kdb_printf(" (Live)"); + kdb_printf(" 0x%p", mod->module_core); #ifdef CONFIG_MODULE_UNLOAD { @@ -2291,6 +2399,9 @@ static int kdb_ll(int argc, const char **argv) while (va) { char buf[80]; + if (KDB_FLAG(CMD_INTERRUPT)) + return 0; + sprintf(buf, "%s " kdb_machreg_fmt "\n", command, va); diag = kdb_parse(buf); if (diag) diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h index 97d3ba69775d..c438f545a321 100644 --- a/kernel/debug/kdb/kdb_private.h +++ b/kernel/debug/kdb/kdb_private.h @@ -144,9 +144,7 @@ extern int kdb_getword(unsigned long *, unsigned long, size_t); extern int kdb_putword(unsigned long, unsigned long, size_t); extern int kdbgetularg(const char *, unsigned long *); -extern int kdb_set(int, const char **); extern char *kdbgetenv(const char *); -extern int kdbgetintenv(const char *, int *); extern int kdbgetaddrarg(int, const char **, int*, unsigned long *, long *, char **); extern int kdbgetsymval(const char *, kdb_symtab_t *); diff --git a/kernel/early_res.c b/kernel/early_res.c index 31aa9332ef3f..7bfae887f211 100644 --- a/kernel/early_res.c +++ b/kernel/early_res.c @@ -7,6 +7,8 @@ #include <linux/bootmem.h> #include <linux/mm.h> #include <linux/early_res.h> +#include <linux/slab.h> +#include <linux/kmemleak.h> /* * Early reserved memory areas. @@ -319,6 +321,8 @@ void __init free_early(u64 start, u64 end) struct early_res *r; int i; + kmemleak_free_part(__va(start), end - start); + i = find_overlapped_early(start, end); r = &early_res[i]; if (i >= max_early_res || r->end != end || r->start != start) @@ -333,6 +337,8 @@ void __init free_early_partial(u64 start, u64 end) struct early_res *r; int i; + kmemleak_free_part(__va(start), end - start); + if (start == end) return; diff --git a/kernel/futex.c b/kernel/futex.c index e7a35f1039e7..6a3a5fa1526d 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -429,20 +429,11 @@ static void free_pi_state(struct futex_pi_state *pi_state) static struct task_struct * futex_find_get_task(pid_t pid) { struct task_struct *p; - const struct cred *cred = current_cred(), *pcred; rcu_read_lock(); p = find_task_by_vpid(pid); - if (!p) { - p = ERR_PTR(-ESRCH); - } else { - pcred = __task_cred(p); - if (cred->euid != pcred->euid && - cred->euid != pcred->uid) - p = ERR_PTR(-ESRCH); - else - get_task_struct(p); - } + if (p) + get_task_struct(p); rcu_read_unlock(); @@ -564,8 +555,8 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, if (!pid) return -ESRCH; p = futex_find_get_task(pid); - if (IS_ERR(p)) - return PTR_ERR(p); + if (!p) + return -ESRCH; /* * We need to look at the task state flags to figure out, diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c index 7a56b22e0602..71ed3ce29e12 100644 --- a/kernel/hw_breakpoint.c +++ b/kernel/hw_breakpoint.c @@ -242,6 +242,17 @@ toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type, } /* + * Function to perform processor-specific cleanup during unregistration + */ +__weak void arch_unregister_hw_breakpoint(struct perf_event *bp) +{ + /* + * A weak stub function here for those archs that don't define + * it inside arch/.../kernel/hw_breakpoint.c + */ +} + +/* * Contraints to check before allowing this new breakpoint counter: * * == Non-pinned counter == (Considered as pinned for now) @@ -339,6 +350,7 @@ void release_bp_slot(struct perf_event *bp) { mutex_lock(&nr_bp_mutex); + arch_unregister_hw_breakpoint(bp); __release_bp_slot(bp); mutex_unlock(&nr_bp_mutex); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 3164ba7ce151..e1497481fe8a 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -456,6 +456,9 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq, /* note that IRQF_TRIGGER_MASK == IRQ_TYPE_SENSE_MASK */ desc->status &= ~(IRQ_LEVEL | IRQ_TYPE_SENSE_MASK); desc->status |= flags; + + if (chip != desc->chip) + irq_chip_set_defaults(desc->chip); } return ret; diff --git a/kernel/kexec.c b/kernel/kexec.c index 474a84715eac..131b1703936f 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -1089,9 +1089,10 @@ void crash_kexec(struct pt_regs *regs) size_t crash_get_memory_size(void) { - size_t size; + size_t size = 0; mutex_lock(&kexec_mutex); - size = crashk_res.end - crashk_res.start + 1; + if (crashk_res.end != crashk_res.start) + size = crashk_res.end - crashk_res.start + 1; mutex_unlock(&kexec_mutex); return size; } @@ -1134,7 +1135,7 @@ int crash_shrink_memory(unsigned long new_size) free_reserved_phys_range(end, crashk_res.end); - if (start == end) + if ((start == end) && (crashk_res.parent != NULL)) release_resource(&crashk_res); crashk_res.end = end - 1; diff --git a/kernel/module.c b/kernel/module.c index 8c6b42840dd1..d0b5f8db11b4 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1,6 +1,6 @@ /* Copyright (C) 2002 Richard Henderson - Copyright (C) 2001 Rusty Russell, 2002 Rusty Russell IBM. + Copyright (C) 2001 Rusty Russell, 2002, 2010 Rusty Russell IBM. This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by @@ -110,6 +110,20 @@ int unregister_module_notifier(struct notifier_block * nb) } EXPORT_SYMBOL(unregister_module_notifier); +struct load_info { + Elf_Ehdr *hdr; + unsigned long len; + Elf_Shdr *sechdrs; + char *secstrings, *strtab; + unsigned long *strmap; + unsigned long symoffs, stroffs; + struct _ddebug *debug; + unsigned int num_debug; + struct { + unsigned int sym, str, mod, vers, info, pcpu; + } index; +}; + /* We require a truly strong try_module_get(): 0 means failure due to ongoing or failed initialization etc. */ static inline int strong_try_module_get(struct module *mod) @@ -140,42 +154,38 @@ void __module_put_and_exit(struct module *mod, long code) EXPORT_SYMBOL(__module_put_and_exit); /* Find a module section: 0 means not found. */ -static unsigned int find_sec(Elf_Ehdr *hdr, - Elf_Shdr *sechdrs, - const char *secstrings, - const char *name) +static unsigned int find_sec(const struct load_info *info, const char *name) { unsigned int i; - for (i = 1; i < hdr->e_shnum; i++) + for (i = 1; i < info->hdr->e_shnum; i++) { + Elf_Shdr *shdr = &info->sechdrs[i]; /* Alloc bit cleared means "ignore it." */ - if ((sechdrs[i].sh_flags & SHF_ALLOC) - && strcmp(secstrings+sechdrs[i].sh_name, name) == 0) + if ((shdr->sh_flags & SHF_ALLOC) + && strcmp(info->secstrings + shdr->sh_name, name) == 0) return i; + } return 0; } /* Find a module section, or NULL. */ -static void *section_addr(Elf_Ehdr *hdr, Elf_Shdr *shdrs, - const char *secstrings, const char *name) +static void *section_addr(const struct load_info *info, const char *name) { /* Section 0 has sh_addr 0. */ - return (void *)shdrs[find_sec(hdr, shdrs, secstrings, name)].sh_addr; + return (void *)info->sechdrs[find_sec(info, name)].sh_addr; } /* Find a module section, or NULL. Fill in number of "objects" in section. */ -static void *section_objs(Elf_Ehdr *hdr, - Elf_Shdr *sechdrs, - const char *secstrings, +static void *section_objs(const struct load_info *info, const char *name, size_t object_size, unsigned int *num) { - unsigned int sec = find_sec(hdr, sechdrs, secstrings, name); + unsigned int sec = find_sec(info, name); /* Section 0 has sh_addr 0 and sh_size 0. */ - *num = sechdrs[sec].sh_size / object_size; - return (void *)sechdrs[sec].sh_addr; + *num = info->sechdrs[sec].sh_size / object_size; + return (void *)info->sechdrs[sec].sh_addr; } /* Provided by the linker */ @@ -227,7 +237,7 @@ bool each_symbol(bool (*fn)(const struct symsearch *arr, struct module *owner, unsigned int symnum, void *data), void *data) { struct module *mod; - const struct symsearch arr[] = { + static const struct symsearch arr[] = { { __start___ksymtab, __stop___ksymtab, __start___kcrctab, NOT_GPL_ONLY, false }, { __start___ksymtab_gpl, __stop___ksymtab_gpl, @@ -392,7 +402,8 @@ static int percpu_modalloc(struct module *mod, mod->percpu = __alloc_reserved_percpu(size, align); if (!mod->percpu) { printk(KERN_WARNING - "Could not allocate %lu bytes percpu data\n", size); + "%s: Could not allocate %lu bytes percpu data\n", + mod->name, size); return -ENOMEM; } mod->percpu_size = size; @@ -404,11 +415,9 @@ static void percpu_modfree(struct module *mod) free_percpu(mod->percpu); } -static unsigned int find_pcpusec(Elf_Ehdr *hdr, - Elf_Shdr *sechdrs, - const char *secstrings) +static unsigned int find_pcpusec(struct load_info *info) { - return find_sec(hdr, sechdrs, secstrings, ".data..percpu"); + return find_sec(info, ".data..percpu"); } static void percpu_modcopy(struct module *mod, @@ -468,9 +477,7 @@ static inline int percpu_modalloc(struct module *mod, static inline void percpu_modfree(struct module *mod) { } -static inline unsigned int find_pcpusec(Elf_Ehdr *hdr, - Elf_Shdr *sechdrs, - const char *secstrings) +static unsigned int find_pcpusec(struct load_info *info) { return 0; } @@ -524,21 +531,21 @@ static char last_unloaded_module[MODULE_NAME_LEN+1]; EXPORT_TRACEPOINT_SYMBOL(module_get); /* Init the unload section of the module. */ -static void module_unload_init(struct module *mod) +static int module_unload_init(struct module *mod) { - int cpu; + mod->refptr = alloc_percpu(struct module_ref); + if (!mod->refptr) + return -ENOMEM; INIT_LIST_HEAD(&mod->source_list); INIT_LIST_HEAD(&mod->target_list); - for_each_possible_cpu(cpu) { - per_cpu_ptr(mod->refptr, cpu)->incs = 0; - per_cpu_ptr(mod->refptr, cpu)->decs = 0; - } /* Hold reference count during initialization. */ __this_cpu_write(mod->refptr->incs, 1); /* Backwards compatibility macros put refcount during init. */ mod->waiter = current; + + return 0; } /* Does a already use b? */ @@ -618,6 +625,8 @@ static void module_unload_free(struct module *mod) kfree(use); } mutex_unlock(&module_mutex); + + free_percpu(mod->refptr); } #ifdef CONFIG_MODULE_FORCE_UNLOAD @@ -787,7 +796,6 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, /* Store the name of the last unloaded module for diagnostic purposes */ strlcpy(last_unloaded_module, mod->name, sizeof(last_unloaded_module)); - ddebug_remove_module(mod->name); free_module(mod); return 0; @@ -892,8 +900,9 @@ int ref_module(struct module *a, struct module *b) } EXPORT_SYMBOL_GPL(ref_module); -static inline void module_unload_init(struct module *mod) +static inline int module_unload_init(struct module *mod) { + return 0; } #endif /* CONFIG_MODULE_UNLOAD */ @@ -1052,10 +1061,9 @@ static inline int same_magic(const char *amagic, const char *bmagic, #endif /* CONFIG_MODVERSIONS */ /* Resolve a symbol for this module. I.e. if we find one, record usage. */ -static const struct kernel_symbol *resolve_symbol(Elf_Shdr *sechdrs, - unsigned int versindex, +static const struct kernel_symbol *resolve_symbol(struct module *mod, + const struct load_info *info, const char *name, - struct module *mod, char ownername[]) { struct module *owner; @@ -1069,7 +1077,8 @@ static const struct kernel_symbol *resolve_symbol(Elf_Shdr *sechdrs, if (!sym) goto unlock; - if (!check_version(sechdrs, versindex, name, mod, crc, owner)) { + if (!check_version(info->sechdrs, info->index.vers, name, mod, crc, + owner)) { sym = ERR_PTR(-EINVAL); goto getname; } @@ -1088,21 +1097,20 @@ unlock: return sym; } -static const struct kernel_symbol *resolve_symbol_wait(Elf_Shdr *sechdrs, - unsigned int versindex, - const char *name, - struct module *mod) +static const struct kernel_symbol * +resolve_symbol_wait(struct module *mod, + const struct load_info *info, + const char *name) { const struct kernel_symbol *ksym; - char ownername[MODULE_NAME_LEN]; + char owner[MODULE_NAME_LEN]; if (wait_event_interruptible_timeout(module_wq, - !IS_ERR(ksym = resolve_symbol(sechdrs, versindex, name, - mod, ownername)) || - PTR_ERR(ksym) != -EBUSY, + !IS_ERR(ksym = resolve_symbol(mod, info, name, owner)) + || PTR_ERR(ksym) != -EBUSY, 30 * HZ) <= 0) { printk(KERN_WARNING "%s: gave up waiting for init of module %s.\n", - mod->name, ownername); + mod->name, owner); } return ksym; } @@ -1111,8 +1119,9 @@ static const struct kernel_symbol *resolve_symbol_wait(Elf_Shdr *sechdrs, * /sys/module/foo/sections stuff * J. Corbet <corbet@lwn.net> */ -#if defined(CONFIG_KALLSYMS) && defined(CONFIG_SYSFS) +#ifdef CONFIG_SYSFS +#ifdef CONFIG_KALLSYMS static inline bool sect_empty(const Elf_Shdr *sect) { return !(sect->sh_flags & SHF_ALLOC) || sect->sh_size == 0; @@ -1149,8 +1158,7 @@ static void free_sect_attrs(struct module_sect_attrs *sect_attrs) kfree(sect_attrs); } -static void add_sect_attrs(struct module *mod, unsigned int nsect, - char *secstrings, Elf_Shdr *sechdrs) +static void add_sect_attrs(struct module *mod, const struct load_info *info) { unsigned int nloaded = 0, i, size[2]; struct module_sect_attrs *sect_attrs; @@ -1158,8 +1166,8 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect, struct attribute **gattr; /* Count loaded sections and allocate structures */ - for (i = 0; i < nsect; i++) - if (!sect_empty(&sechdrs[i])) + for (i = 0; i < info->hdr->e_shnum; i++) + if (!sect_empty(&info->sechdrs[i])) nloaded++; size[0] = ALIGN(sizeof(*sect_attrs) + nloaded * sizeof(sect_attrs->attrs[0]), @@ -1176,11 +1184,12 @@ static void add_sect_attrs(struct module *mod, unsigned int nsect, sect_attrs->nsections = 0; sattr = §_attrs->attrs[0]; gattr = §_attrs->grp.attrs[0]; - for (i = 0; i < nsect; i++) { - if (sect_empty(&sechdrs[i])) + for (i = 0; i < info->hdr->e_shnum; i++) { + Elf_Shdr *sec = &info->sechdrs[i]; + if (sect_empty(sec)) continue; - sattr->address = sechdrs[i].sh_addr; - sattr->name = kstrdup(secstrings + sechdrs[i].sh_name, + sattr->address = sec->sh_addr; + sattr->name = kstrdup(info->secstrings + sec->sh_name, GFP_KERNEL); if (sattr->name == NULL) goto out; @@ -1248,8 +1257,7 @@ static void free_notes_attrs(struct module_notes_attrs *notes_attrs, kfree(notes_attrs); } -static void add_notes_attrs(struct module *mod, unsigned int nsect, - char *secstrings, Elf_Shdr *sechdrs) +static void add_notes_attrs(struct module *mod, const struct load_info *info) { unsigned int notes, loaded, i; struct module_notes_attrs *notes_attrs; @@ -1261,9 +1269,9 @@ static void add_notes_attrs(struct module *mod, unsigned int nsect, /* Count notes sections and allocate structures. */ notes = 0; - for (i = 0; i < nsect; i++) - if (!sect_empty(&sechdrs[i]) && - (sechdrs[i].sh_type == SHT_NOTE)) + for (i = 0; i < info->hdr->e_shnum; i++) + if (!sect_empty(&info->sechdrs[i]) && + (info->sechdrs[i].sh_type == SHT_NOTE)) ++notes; if (notes == 0) @@ -1277,15 +1285,15 @@ static void add_notes_attrs(struct module *mod, unsigned int nsect, notes_attrs->notes = notes; nattr = ¬es_attrs->attrs[0]; - for (loaded = i = 0; i < nsect; ++i) { - if (sect_empty(&sechdrs[i])) + for (loaded = i = 0; i < info->hdr->e_shnum; ++i) { + if (sect_empty(&info->sechdrs[i])) continue; - if (sechdrs[i].sh_type == SHT_NOTE) { + if (info->sechdrs[i].sh_type == SHT_NOTE) { sysfs_bin_attr_init(nattr); nattr->attr.name = mod->sect_attrs->attrs[loaded].name; nattr->attr.mode = S_IRUGO; - nattr->size = sechdrs[i].sh_size; - nattr->private = (void *) sechdrs[i].sh_addr; + nattr->size = info->sechdrs[i].sh_size; + nattr->private = (void *) info->sechdrs[i].sh_addr; nattr->read = module_notes_read; ++nattr; } @@ -1316,8 +1324,8 @@ static void remove_notes_attrs(struct module *mod) #else -static inline void add_sect_attrs(struct module *mod, unsigned int nsect, - char *sectstrings, Elf_Shdr *sechdrs) +static inline void add_sect_attrs(struct module *mod, + const struct load_info *info) { } @@ -1325,17 +1333,16 @@ static inline void remove_sect_attrs(struct module *mod) { } -static inline void add_notes_attrs(struct module *mod, unsigned int nsect, - char *sectstrings, Elf_Shdr *sechdrs) +static inline void add_notes_attrs(struct module *mod, + const struct load_info *info) { } static inline void remove_notes_attrs(struct module *mod) { } -#endif +#endif /* CONFIG_KALLSYMS */ -#ifdef CONFIG_SYSFS static void add_usage_links(struct module *mod) { #ifdef CONFIG_MODULE_UNLOAD @@ -1440,6 +1447,7 @@ out: } static int mod_sysfs_setup(struct module *mod, + const struct load_info *info, struct kernel_param *kparam, unsigned int num_params) { @@ -1464,6 +1472,8 @@ static int mod_sysfs_setup(struct module *mod, goto out_unreg_param; add_usage_links(mod); + add_sect_attrs(mod, info); + add_notes_attrs(mod, info); kobject_uevent(&mod->mkobj.kobj, KOBJ_ADD); return 0; @@ -1480,33 +1490,26 @@ out: static void mod_sysfs_fini(struct module *mod) { + remove_notes_attrs(mod); + remove_sect_attrs(mod); kobject_put(&mod->mkobj.kobj); } -#else /* CONFIG_SYSFS */ - -static inline int mod_sysfs_init(struct module *mod) -{ - return 0; -} +#else /* !CONFIG_SYSFS */ -static inline int mod_sysfs_setup(struct module *mod, +static int mod_sysfs_setup(struct module *mod, + const struct load_info *info, struct kernel_param *kparam, unsigned int num_params) { return 0; } -static inline int module_add_modinfo_attrs(struct module *mod) -{ - return 0; -} - -static inline void module_remove_modinfo_attrs(struct module *mod) +static void mod_sysfs_fini(struct module *mod) { } -static void mod_sysfs_fini(struct module *mod) +static void module_remove_modinfo_attrs(struct module *mod) { } @@ -1516,7 +1519,7 @@ static void del_usage_links(struct module *mod) #endif /* CONFIG_SYSFS */ -static void mod_kobject_remove(struct module *mod) +static void mod_sysfs_teardown(struct module *mod) { del_usage_links(mod); module_remove_modinfo_attrs(mod); @@ -1546,9 +1549,10 @@ static void free_module(struct module *mod) mutex_lock(&module_mutex); stop_machine(__unlink_module, mod, NULL); mutex_unlock(&module_mutex); - remove_notes_attrs(mod); - remove_sect_attrs(mod); - mod_kobject_remove(mod); + mod_sysfs_teardown(mod); + + /* Remove dynamic debug info */ + ddebug_remove_module(mod->name); /* Arch-specific cleanup. */ module_arch_cleanup(mod); @@ -1563,10 +1567,7 @@ static void free_module(struct module *mod) module_free(mod, mod->module_init); kfree(mod->args); percpu_modfree(mod); -#if defined(CONFIG_MODULE_UNLOAD) - if (mod->refptr) - free_percpu(mod->refptr); -#endif + /* Free lock-classes: */ lockdep_free_key_range(mod->module_core, mod->core_size); @@ -1632,25 +1633,23 @@ static int verify_export_symbols(struct module *mod) } /* Change all symbols so that st_value encodes the pointer directly. */ -static int simplify_symbols(Elf_Shdr *sechdrs, - unsigned int symindex, - const char *strtab, - unsigned int versindex, - unsigned int pcpuindex, - struct module *mod) -{ - Elf_Sym *sym = (void *)sechdrs[symindex].sh_addr; +static int simplify_symbols(struct module *mod, const struct load_info *info) +{ + Elf_Shdr *symsec = &info->sechdrs[info->index.sym]; + Elf_Sym *sym = (void *)symsec->sh_addr; unsigned long secbase; - unsigned int i, n = sechdrs[symindex].sh_size / sizeof(Elf_Sym); + unsigned int i; int ret = 0; const struct kernel_symbol *ksym; - for (i = 1; i < n; i++) { + for (i = 1; i < symsec->sh_size / sizeof(Elf_Sym); i++) { + const char *name = info->strtab + sym[i].st_name; + switch (sym[i].st_shndx) { case SHN_COMMON: /* We compiled with -fno-common. These are not supposed to happen. */ - DEBUGP("Common symbol: %s\n", strtab + sym[i].st_name); + DEBUGP("Common symbol: %s\n", name); printk("%s: please compile with -fno-common\n", mod->name); ret = -ENOEXEC; @@ -1663,9 +1662,7 @@ static int simplify_symbols(Elf_Shdr *sechdrs, break; case SHN_UNDEF: - ksym = resolve_symbol_wait(sechdrs, versindex, - strtab + sym[i].st_name, - mod); + ksym = resolve_symbol_wait(mod, info, name); /* Ok if resolved. */ if (ksym && !IS_ERR(ksym)) { sym[i].st_value = ksym->value; @@ -1677,17 +1674,16 @@ static int simplify_symbols(Elf_Shdr *sechdrs, break; printk(KERN_WARNING "%s: Unknown symbol %s (err %li)\n", - mod->name, strtab + sym[i].st_name, - PTR_ERR(ksym)); + mod->name, name, PTR_ERR(ksym)); ret = PTR_ERR(ksym) ?: -ENOENT; break; default: /* Divert to percpu allocation if a percpu var. */ - if (sym[i].st_shndx == pcpuindex) + if (sym[i].st_shndx == info->index.pcpu) secbase = (unsigned long)mod_percpu(mod); else - secbase = sechdrs[sym[i].st_shndx].sh_addr; + secbase = info->sechdrs[sym[i].st_shndx].sh_addr; sym[i].st_value += secbase; break; } @@ -1696,6 +1692,35 @@ static int simplify_symbols(Elf_Shdr *sechdrs, return ret; } +static int apply_relocations(struct module *mod, const struct load_info *info) +{ + unsigned int i; + int err = 0; + + /* Now do relocations. */ + for (i = 1; i < info->hdr->e_shnum; i++) { + unsigned int infosec = info->sechdrs[i].sh_info; + + /* Not a valid relocation section? */ + if (infosec >= info->hdr->e_shnum) + continue; + + /* Don't bother with non-allocated sections */ + if (!(info->sechdrs[infosec].sh_flags & SHF_ALLOC)) + continue; + + if (info->sechdrs[i].sh_type == SHT_REL) + err = apply_relocate(info->sechdrs, info->strtab, + info->index.sym, i, mod); + else if (info->sechdrs[i].sh_type == SHT_RELA) + err = apply_relocate_add(info->sechdrs, info->strtab, + info->index.sym, i, mod); + if (err < 0) + break; + } + return err; +} + /* Additional bytes needed by arch in front of individual sections */ unsigned int __weak arch_mod_section_prepend(struct module *mod, unsigned int section) @@ -1720,10 +1745,7 @@ static long get_offset(struct module *mod, unsigned int *size, might -- code, read-only data, read-write data, small data. Tally sizes, and place the offsets into sh_entsize fields: high bit means it belongs in init. */ -static void layout_sections(struct module *mod, - const Elf_Ehdr *hdr, - Elf_Shdr *sechdrs, - const char *secstrings) +static void layout_sections(struct module *mod, struct load_info *info) { static unsigned long const masks[][2] = { /* NOTE: all executable code must be the first section @@ -1736,21 +1758,22 @@ static void layout_sections(struct module *mod, }; unsigned int m, i; - for (i = 0; i < hdr->e_shnum; i++) - sechdrs[i].sh_entsize = ~0UL; + for (i = 0; i < info->hdr->e_shnum; i++) + info->sechdrs[i].sh_entsize = ~0UL; DEBUGP("Core section allocation order:\n"); for (m = 0; m < ARRAY_SIZE(masks); ++m) { - for (i = 0; i < hdr->e_shnum; ++i) { - Elf_Shdr *s = &sechdrs[i]; + for (i = 0; i < info->hdr->e_shnum; ++i) { + Elf_Shdr *s = &info->sechdrs[i]; + const char *sname = info->secstrings + s->sh_name; if ((s->sh_flags & masks[m][0]) != masks[m][0] || (s->sh_flags & masks[m][1]) || s->sh_entsize != ~0UL - || strstarts(secstrings + s->sh_name, ".init")) + || strstarts(sname, ".init")) continue; s->sh_entsize = get_offset(mod, &mod->core_size, s, i); - DEBUGP("\t%s\n", secstrings + s->sh_name); + DEBUGP("\t%s\n", name); } if (m == 0) mod->core_text_size = mod->core_size; @@ -1758,17 +1781,18 @@ static void layout_sections(struct module *mod, DEBUGP("Init section allocation order:\n"); for (m = 0; m < ARRAY_SIZE(masks); ++m) { - for (i = 0; i < hdr->e_shnum; ++i) { - Elf_Shdr *s = &sechdrs[i]; + for (i = 0; i < info->hdr->e_shnum; ++i) { + Elf_Shdr *s = &info->sechdrs[i]; + const char *sname = info->secstrings + s->sh_name; if ((s->sh_flags & masks[m][0]) != masks[m][0] || (s->sh_flags & masks[m][1]) || s->sh_entsize != ~0UL - || !strstarts(secstrings + s->sh_name, ".init")) + || !strstarts(sname, ".init")) continue; s->sh_entsize = (get_offset(mod, &mod->init_size, s, i) | INIT_OFFSET_MASK); - DEBUGP("\t%s\n", secstrings + s->sh_name); + DEBUGP("\t%s\n", sname); } if (m == 0) mod->init_text_size = mod->init_size; @@ -1807,33 +1831,28 @@ static char *next_string(char *string, unsigned long *secsize) return string; } -static char *get_modinfo(Elf_Shdr *sechdrs, - unsigned int info, - const char *tag) +static char *get_modinfo(struct load_info *info, const char *tag) { char *p; unsigned int taglen = strlen(tag); - unsigned long size = sechdrs[info].sh_size; + Elf_Shdr *infosec = &info->sechdrs[info->index.info]; + unsigned long size = infosec->sh_size; - for (p = (char *)sechdrs[info].sh_addr; p; p = next_string(p, &size)) { + for (p = (char *)infosec->sh_addr; p; p = next_string(p, &size)) { if (strncmp(p, tag, taglen) == 0 && p[taglen] == '=') return p + taglen + 1; } return NULL; } -static void setup_modinfo(struct module *mod, Elf_Shdr *sechdrs, - unsigned int infoindex) +static void setup_modinfo(struct module *mod, struct load_info *info) { struct module_attribute *attr; int i; for (i = 0; (attr = modinfo_attrs[i]); i++) { if (attr->setup) - attr->setup(mod, - get_modinfo(sechdrs, - infoindex, - attr->attr.name)); + attr->setup(mod, get_modinfo(info, attr->attr.name)); } } @@ -1874,11 +1893,10 @@ static int is_exported(const char *name, unsigned long value, } /* As per nm */ -static char elf_type(const Elf_Sym *sym, - Elf_Shdr *sechdrs, - const char *secstrings, - struct module *mod) +static char elf_type(const Elf_Sym *sym, const struct load_info *info) { + const Elf_Shdr *sechdrs = info->sechdrs; + if (ELF_ST_BIND(sym->st_info) == STB_WEAK) { if (ELF_ST_TYPE(sym->st_info) == STT_OBJECT) return 'v'; @@ -1908,8 +1926,10 @@ static char elf_type(const Elf_Sym *sym, else return 'b'; } - if (strstarts(secstrings + sechdrs[sym->st_shndx].sh_name, ".debug")) + if (strstarts(info->secstrings + sechdrs[sym->st_shndx].sh_name, + ".debug")) { return 'n'; + } return '?'; } @@ -1934,127 +1954,96 @@ static bool is_core_symbol(const Elf_Sym *src, const Elf_Shdr *sechdrs, return true; } -static unsigned long layout_symtab(struct module *mod, - Elf_Shdr *sechdrs, - unsigned int symindex, - unsigned int strindex, - const Elf_Ehdr *hdr, - const char *secstrings, - unsigned long *pstroffs, - unsigned long *strmap) +static void layout_symtab(struct module *mod, struct load_info *info) { - unsigned long symoffs; - Elf_Shdr *symsect = sechdrs + symindex; - Elf_Shdr *strsect = sechdrs + strindex; + Elf_Shdr *symsect = info->sechdrs + info->index.sym; + Elf_Shdr *strsect = info->sechdrs + info->index.str; const Elf_Sym *src; - const char *strtab; unsigned int i, nsrc, ndst; /* Put symbol section at end of init part of module. */ symsect->sh_flags |= SHF_ALLOC; symsect->sh_entsize = get_offset(mod, &mod->init_size, symsect, - symindex) | INIT_OFFSET_MASK; - DEBUGP("\t%s\n", secstrings + symsect->sh_name); + info->index.sym) | INIT_OFFSET_MASK; + DEBUGP("\t%s\n", info->secstrings + symsect->sh_name); - src = (void *)hdr + symsect->sh_offset; + src = (void *)info->hdr + symsect->sh_offset; nsrc = symsect->sh_size / sizeof(*src); - strtab = (void *)hdr + strsect->sh_offset; for (ndst = i = 1; i < nsrc; ++i, ++src) - if (is_core_symbol(src, sechdrs, hdr->e_shnum)) { + if (is_core_symbol(src, info->sechdrs, info->hdr->e_shnum)) { unsigned int j = src->st_name; - while(!__test_and_set_bit(j, strmap) && strtab[j]) + while (!__test_and_set_bit(j, info->strmap) + && info->strtab[j]) ++j; ++ndst; } /* Append room for core symbols at end of core part. */ - symoffs = ALIGN(mod->core_size, symsect->sh_addralign ?: 1); - mod->core_size = symoffs + ndst * sizeof(Elf_Sym); + info->symoffs = ALIGN(mod->core_size, symsect->sh_addralign ?: 1); + mod->core_size = info->symoffs + ndst * sizeof(Elf_Sym); /* Put string table section at end of init part of module. */ strsect->sh_flags |= SHF_ALLOC; strsect->sh_entsize = get_offset(mod, &mod->init_size, strsect, - strindex) | INIT_OFFSET_MASK; - DEBUGP("\t%s\n", secstrings + strsect->sh_name); + info->index.str) | INIT_OFFSET_MASK; + DEBUGP("\t%s\n", info->secstrings + strsect->sh_name); /* Append room for core symbols' strings at end of core part. */ - *pstroffs = mod->core_size; - __set_bit(0, strmap); - mod->core_size += bitmap_weight(strmap, strsect->sh_size); - - return symoffs; + info->stroffs = mod->core_size; + __set_bit(0, info->strmap); + mod->core_size += bitmap_weight(info->strmap, strsect->sh_size); } -static void add_kallsyms(struct module *mod, - Elf_Shdr *sechdrs, - unsigned int shnum, - unsigned int symindex, - unsigned int strindex, - unsigned long symoffs, - unsigned long stroffs, - const char *secstrings, - unsigned long *strmap) +static void add_kallsyms(struct module *mod, const struct load_info *info) { unsigned int i, ndst; const Elf_Sym *src; Elf_Sym *dst; char *s; + Elf_Shdr *symsec = &info->sechdrs[info->index.sym]; - mod->symtab = (void *)sechdrs[symindex].sh_addr; - mod->num_symtab = sechdrs[symindex].sh_size / sizeof(Elf_Sym); - mod->strtab = (void *)sechdrs[strindex].sh_addr; + mod->symtab = (void *)symsec->sh_addr; + mod->num_symtab = symsec->sh_size / sizeof(Elf_Sym); + /* Make sure we get permanent strtab: don't use info->strtab. */ + mod->strtab = (void *)info->sechdrs[info->index.str].sh_addr; /* Set types up while we still have access to sections. */ for (i = 0; i < mod->num_symtab; i++) - mod->symtab[i].st_info - = elf_type(&mod->symtab[i], sechdrs, secstrings, mod); + mod->symtab[i].st_info = elf_type(&mod->symtab[i], info); - mod->core_symtab = dst = mod->module_core + symoffs; + mod->core_symtab = dst = mod->module_core + info->symoffs; src = mod->symtab; *dst = *src; for (ndst = i = 1; i < mod->num_symtab; ++i, ++src) { - if (!is_core_symbol(src, sechdrs, shnum)) + if (!is_core_symbol(src, info->sechdrs, info->hdr->e_shnum)) continue; dst[ndst] = *src; - dst[ndst].st_name = bitmap_weight(strmap, dst[ndst].st_name); + dst[ndst].st_name = bitmap_weight(info->strmap, + dst[ndst].st_name); ++ndst; } mod->core_num_syms = ndst; - mod->core_strtab = s = mod->module_core + stroffs; - for (*s = 0, i = 1; i < sechdrs[strindex].sh_size; ++i) - if (test_bit(i, strmap)) + mod->core_strtab = s = mod->module_core + info->stroffs; + for (*s = 0, i = 1; i < info->sechdrs[info->index.str].sh_size; ++i) + if (test_bit(i, info->strmap)) *++s = mod->strtab[i]; } #else -static inline unsigned long layout_symtab(struct module *mod, - Elf_Shdr *sechdrs, - unsigned int symindex, - unsigned int strindex, - const Elf_Ehdr *hdr, - const char *secstrings, - unsigned long *pstroffs, - unsigned long *strmap) +static inline void layout_symtab(struct module *mod, struct load_info *info) { - return 0; } -static inline void add_kallsyms(struct module *mod, - Elf_Shdr *sechdrs, - unsigned int shnum, - unsigned int symindex, - unsigned int strindex, - unsigned long symoffs, - unsigned long stroffs, - const char *secstrings, - const unsigned long *strmap) +static void add_kallsyms(struct module *mod, struct load_info *info) { } #endif /* CONFIG_KALLSYMS */ static void dynamic_debug_setup(struct _ddebug *debug, unsigned int num) { + if (!debug) + return; #ifdef CONFIG_DYNAMIC_DEBUG if (ddebug_add_module(debug, num, debug->modname)) printk(KERN_ERR "dynamic debug error adding module: %s\n", @@ -2062,6 +2051,12 @@ static void dynamic_debug_setup(struct _ddebug *debug, unsigned int num) #endif } +static void dynamic_debug_remove(struct _ddebug *debug) +{ + if (debug) + ddebug_remove_module(debug->modname); +} + static void *module_alloc_update_bounds(unsigned long size) { void *ret = module_alloc(size); @@ -2079,63 +2074,47 @@ static void *module_alloc_update_bounds(unsigned long size) } #ifdef CONFIG_DEBUG_KMEMLEAK -static void kmemleak_load_module(struct module *mod, Elf_Ehdr *hdr, - Elf_Shdr *sechdrs, char *secstrings) +static void kmemleak_load_module(const struct module *mod, + const struct load_info *info) { unsigned int i; /* only scan the sections containing data */ kmemleak_scan_area(mod, sizeof(struct module), GFP_KERNEL); - for (i = 1; i < hdr->e_shnum; i++) { - if (!(sechdrs[i].sh_flags & SHF_ALLOC)) + for (i = 1; i < info->hdr->e_shnum; i++) { + const char *name = info->secstrings + info->sechdrs[i].sh_name; + if (!(info->sechdrs[i].sh_flags & SHF_ALLOC)) continue; - if (strncmp(secstrings + sechdrs[i].sh_name, ".data", 5) != 0 - && strncmp(secstrings + sechdrs[i].sh_name, ".bss", 4) != 0) + if (!strstarts(name, ".data") && !strstarts(name, ".bss")) continue; - kmemleak_scan_area((void *)sechdrs[i].sh_addr, - sechdrs[i].sh_size, GFP_KERNEL); + kmemleak_scan_area((void *)info->sechdrs[i].sh_addr, + info->sechdrs[i].sh_size, GFP_KERNEL); } } #else -static inline void kmemleak_load_module(struct module *mod, Elf_Ehdr *hdr, - Elf_Shdr *sechdrs, char *secstrings) +static inline void kmemleak_load_module(const struct module *mod, + const struct load_info *info) { } #endif -/* Allocate and load the module: note that size of section 0 is always - zero, and we rely on this for optional sections. */ -static noinline struct module *load_module(void __user *umod, - unsigned long len, - const char __user *uargs) +/* Sets info->hdr and info->len. */ +static int copy_and_check(struct load_info *info, + const void __user *umod, unsigned long len, + const char __user *uargs) { + int err; Elf_Ehdr *hdr; - Elf_Shdr *sechdrs; - char *secstrings, *args, *modmagic, *strtab = NULL; - char *staging; - unsigned int i; - unsigned int symindex = 0; - unsigned int strindex = 0; - unsigned int modindex, versindex, infoindex, pcpuindex; - struct module *mod; - long err = 0; - void *ptr = NULL; /* Stops spurious gcc warning */ - unsigned long symoffs, stroffs, *strmap; - void __percpu *percpu; - - mm_segment_t old_fs; - DEBUGP("load_module: umod=%p, len=%lu, uargs=%p\n", - umod, len, uargs); if (len < sizeof(*hdr)) - return ERR_PTR(-ENOEXEC); + return -ENOEXEC; /* Suck in entire file: we'll want most of it. */ /* vmalloc barfs on "unusual" numbers. Check here */ if (len > 64 * 1024 * 1024 || (hdr = vmalloc(len)) == NULL) - return ERR_PTR(-ENOMEM); + return -ENOMEM; if (copy_from_user(hdr, umod, len) != 0) { err = -EFAULT; @@ -2143,135 +2122,225 @@ static noinline struct module *load_module(void __user *umod, } /* Sanity checks against insmoding binaries or wrong arch, - weird elf version */ + weird elf version */ if (memcmp(hdr->e_ident, ELFMAG, SELFMAG) != 0 || hdr->e_type != ET_REL || !elf_check_arch(hdr) - || hdr->e_shentsize != sizeof(*sechdrs)) { + || hdr->e_shentsize != sizeof(Elf_Shdr)) { + err = -ENOEXEC; + goto free_hdr; + } + + if (len < hdr->e_shoff + hdr->e_shnum * sizeof(Elf_Shdr)) { err = -ENOEXEC; goto free_hdr; } - if (len < hdr->e_shoff + hdr->e_shnum * sizeof(Elf_Shdr)) - goto truncated; + info->hdr = hdr; + info->len = len; + return 0; + +free_hdr: + vfree(hdr); + return err; +} + +static void free_copy(struct load_info *info) +{ + vfree(info->hdr); +} + +static int rewrite_section_headers(struct load_info *info) +{ + unsigned int i; - /* Convenience variables */ - sechdrs = (void *)hdr + hdr->e_shoff; - secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; - sechdrs[0].sh_addr = 0; + /* This should always be true, but let's be sure. */ + info->sechdrs[0].sh_addr = 0; - for (i = 1; i < hdr->e_shnum; i++) { - if (sechdrs[i].sh_type != SHT_NOBITS - && len < sechdrs[i].sh_offset + sechdrs[i].sh_size) - goto truncated; + for (i = 1; i < info->hdr->e_shnum; i++) { + Elf_Shdr *shdr = &info->sechdrs[i]; + if (shdr->sh_type != SHT_NOBITS + && info->len < shdr->sh_offset + shdr->sh_size) { + printk(KERN_ERR "Module len %lu truncated\n", + info->len); + return -ENOEXEC; + } /* Mark all sections sh_addr with their address in the temporary image. */ - sechdrs[i].sh_addr = (size_t)hdr + sechdrs[i].sh_offset; + shdr->sh_addr = (size_t)info->hdr + shdr->sh_offset; - /* Internal symbols and strings. */ - if (sechdrs[i].sh_type == SHT_SYMTAB) { - symindex = i; - strindex = sechdrs[i].sh_link; - strtab = (char *)hdr + sechdrs[strindex].sh_offset; - } #ifndef CONFIG_MODULE_UNLOAD /* Don't load .exit sections */ - if (strstarts(secstrings+sechdrs[i].sh_name, ".exit")) - sechdrs[i].sh_flags &= ~(unsigned long)SHF_ALLOC; + if (strstarts(info->secstrings+shdr->sh_name, ".exit")) + shdr->sh_flags &= ~(unsigned long)SHF_ALLOC; #endif } - modindex = find_sec(hdr, sechdrs, secstrings, - ".gnu.linkonce.this_module"); - if (!modindex) { + /* Track but don't keep modinfo and version sections. */ + info->index.vers = find_sec(info, "__versions"); + info->index.info = find_sec(info, ".modinfo"); + info->sechdrs[info->index.info].sh_flags &= ~(unsigned long)SHF_ALLOC; + info->sechdrs[info->index.vers].sh_flags &= ~(unsigned long)SHF_ALLOC; + return 0; +} + +/* + * Set up our basic convenience variables (pointers to section headers, + * search for module section index etc), and do some basic section + * verification. + * + * Return the temporary module pointer (we'll replace it with the final + * one when we move the module sections around). + */ +static struct module *setup_load_info(struct load_info *info) +{ + unsigned int i; + int err; + struct module *mod; + + /* Set up the convenience variables */ + info->sechdrs = (void *)info->hdr + info->hdr->e_shoff; + info->secstrings = (void *)info->hdr + + info->sechdrs[info->hdr->e_shstrndx].sh_offset; + + err = rewrite_section_headers(info); + if (err) + return ERR_PTR(err); + + /* Find internal symbols and strings. */ + for (i = 1; i < info->hdr->e_shnum; i++) { + if (info->sechdrs[i].sh_type == SHT_SYMTAB) { + info->index.sym = i; + info->index.str = info->sechdrs[i].sh_link; + info->strtab = (char *)info->hdr + + info->sechdrs[info->index.str].sh_offset; + break; + } + } + + info->index.mod = find_sec(info, ".gnu.linkonce.this_module"); + if (!info->index.mod) { printk(KERN_WARNING "No module found in object\n"); - err = -ENOEXEC; - goto free_hdr; + return ERR_PTR(-ENOEXEC); } /* This is temporary: point mod into copy of data. */ - mod = (void *)sechdrs[modindex].sh_addr; + mod = (void *)info->sechdrs[info->index.mod].sh_addr; - if (symindex == 0) { + if (info->index.sym == 0) { printk(KERN_WARNING "%s: module has no symbols (stripped?)\n", mod->name); - err = -ENOEXEC; - goto free_hdr; + return ERR_PTR(-ENOEXEC); } - versindex = find_sec(hdr, sechdrs, secstrings, "__versions"); - infoindex = find_sec(hdr, sechdrs, secstrings, ".modinfo"); - pcpuindex = find_pcpusec(hdr, sechdrs, secstrings); - - /* Don't keep modinfo and version sections. */ - sechdrs[infoindex].sh_flags &= ~(unsigned long)SHF_ALLOC; - sechdrs[versindex].sh_flags &= ~(unsigned long)SHF_ALLOC; + info->index.pcpu = find_pcpusec(info); /* Check module struct version now, before we try to use module. */ - if (!check_modstruct_version(sechdrs, versindex, mod)) { - err = -ENOEXEC; - goto free_hdr; - } + if (!check_modstruct_version(info->sechdrs, info->index.vers, mod)) + return ERR_PTR(-ENOEXEC); + + return mod; +} + +static int check_modinfo(struct module *mod, struct load_info *info) +{ + const char *modmagic = get_modinfo(info, "vermagic"); + int err; - modmagic = get_modinfo(sechdrs, infoindex, "vermagic"); /* This is allowed: modprobe --force will invalidate it. */ if (!modmagic) { err = try_to_force_load(mod, "bad vermagic"); if (err) - goto free_hdr; - } else if (!same_magic(modmagic, vermagic, versindex)) { + return err; + } else if (!same_magic(modmagic, vermagic, info->index.vers)) { printk(KERN_ERR "%s: version magic '%s' should be '%s'\n", mod->name, modmagic, vermagic); - err = -ENOEXEC; - goto free_hdr; + return -ENOEXEC; } - staging = get_modinfo(sechdrs, infoindex, "staging"); - if (staging) { + if (get_modinfo(info, "staging")) { add_taint_module(mod, TAINT_CRAP); printk(KERN_WARNING "%s: module is from the staging directory," " the quality is unknown, you have been warned.\n", mod->name); } - /* Now copy in args */ - args = strndup_user(uargs, ~0UL >> 1); - if (IS_ERR(args)) { - err = PTR_ERR(args); - goto free_hdr; - } + /* Set up license info based on the info section */ + set_license(mod, get_modinfo(info, "license")); - strmap = kzalloc(BITS_TO_LONGS(sechdrs[strindex].sh_size) - * sizeof(long), GFP_KERNEL); - if (!strmap) { - err = -ENOMEM; - goto free_mod; - } + return 0; +} - mod->state = MODULE_STATE_COMING; +static void find_module_sections(struct module *mod, struct load_info *info) +{ + mod->kp = section_objs(info, "__param", + sizeof(*mod->kp), &mod->num_kp); + mod->syms = section_objs(info, "__ksymtab", + sizeof(*mod->syms), &mod->num_syms); + mod->crcs = section_addr(info, "__kcrctab"); + mod->gpl_syms = section_objs(info, "__ksymtab_gpl", + sizeof(*mod->gpl_syms), + &mod->num_gpl_syms); + mod->gpl_crcs = section_addr(info, "__kcrctab_gpl"); + mod->gpl_future_syms = section_objs(info, + "__ksymtab_gpl_future", + sizeof(*mod->gpl_future_syms), + &mod->num_gpl_future_syms); + mod->gpl_future_crcs = section_addr(info, "__kcrctab_gpl_future"); - /* Allow arches to frob section contents and sizes. */ - err = module_frob_arch_sections(hdr, sechdrs, secstrings, mod); - if (err < 0) - goto free_mod; +#ifdef CONFIG_UNUSED_SYMBOLS + mod->unused_syms = section_objs(info, "__ksymtab_unused", + sizeof(*mod->unused_syms), + &mod->num_unused_syms); + mod->unused_crcs = section_addr(info, "__kcrctab_unused"); + mod->unused_gpl_syms = section_objs(info, "__ksymtab_unused_gpl", + sizeof(*mod->unused_gpl_syms), + &mod->num_unused_gpl_syms); + mod->unused_gpl_crcs = section_addr(info, "__kcrctab_unused_gpl"); +#endif +#ifdef CONFIG_CONSTRUCTORS + mod->ctors = section_objs(info, ".ctors", + sizeof(*mod->ctors), &mod->num_ctors); +#endif - if (pcpuindex) { - /* We have a special allocation for this section. */ - err = percpu_modalloc(mod, sechdrs[pcpuindex].sh_size, - sechdrs[pcpuindex].sh_addralign); - if (err) - goto free_mod; - sechdrs[pcpuindex].sh_flags &= ~(unsigned long)SHF_ALLOC; - } - /* Keep this around for failure path. */ - percpu = mod_percpu(mod); +#ifdef CONFIG_TRACEPOINTS + mod->tracepoints = section_objs(info, "__tracepoints", + sizeof(*mod->tracepoints), + &mod->num_tracepoints); +#endif +#ifdef CONFIG_EVENT_TRACING + mod->trace_events = section_objs(info, "_ftrace_events", + sizeof(*mod->trace_events), + &mod->num_trace_events); + /* + * This section contains pointers to allocated objects in the trace + * code and not scanning it leads to false positives. + */ + kmemleak_scan_area(mod->trace_events, sizeof(*mod->trace_events) * + mod->num_trace_events, GFP_KERNEL); +#endif +#ifdef CONFIG_FTRACE_MCOUNT_RECORD + /* sechdrs[0].sh_size is always zero */ + mod->ftrace_callsites = section_objs(info, "__mcount_loc", + sizeof(*mod->ftrace_callsites), + &mod->num_ftrace_callsites); +#endif - /* Determine total sizes, and put offsets in sh_entsize. For now - this is done generically; there doesn't appear to be any - special cases for the architectures. */ - layout_sections(mod, hdr, sechdrs, secstrings); - symoffs = layout_symtab(mod, sechdrs, symindex, strindex, hdr, - secstrings, &stroffs, strmap); + mod->extable = section_objs(info, "__ex_table", + sizeof(*mod->extable), &mod->num_exentries); + + if (section_addr(info, "__obsparm")) + printk(KERN_WARNING "%s: Ignoring obsolete parameters\n", + mod->name); + + info->debug = section_objs(info, "__verbose", + sizeof(*info->debug), &info->num_debug); +} + +static int move_module(struct module *mod, struct load_info *info) +{ + int i; + void *ptr; /* Do the allocs. */ ptr = module_alloc_update_bounds(mod->core_size); @@ -2281,10 +2350,9 @@ static noinline struct module *load_module(void __user *umod, * leak. */ kmemleak_not_leak(ptr); - if (!ptr) { - err = -ENOMEM; - goto free_percpu; - } + if (!ptr) + return -ENOMEM; + memset(ptr, 0, mod->core_size); mod->module_core = ptr; @@ -2297,50 +2365,40 @@ static noinline struct module *load_module(void __user *umod, */ kmemleak_ignore(ptr); if (!ptr && mod->init_size) { - err = -ENOMEM; - goto free_core; + module_free(mod, mod->module_core); + return -ENOMEM; } memset(ptr, 0, mod->init_size); mod->module_init = ptr; /* Transfer each section which specifies SHF_ALLOC */ DEBUGP("final section addresses:\n"); - for (i = 0; i < hdr->e_shnum; i++) { + for (i = 0; i < info->hdr->e_shnum; i++) { void *dest; + Elf_Shdr *shdr = &info->sechdrs[i]; - if (!(sechdrs[i].sh_flags & SHF_ALLOC)) + if (!(shdr->sh_flags & SHF_ALLOC)) continue; - if (sechdrs[i].sh_entsize & INIT_OFFSET_MASK) + if (shdr->sh_entsize & INIT_OFFSET_MASK) dest = mod->module_init - + (sechdrs[i].sh_entsize & ~INIT_OFFSET_MASK); + + (shdr->sh_entsize & ~INIT_OFFSET_MASK); else - dest = mod->module_core + sechdrs[i].sh_entsize; + dest = mod->module_core + shdr->sh_entsize; - if (sechdrs[i].sh_type != SHT_NOBITS) - memcpy(dest, (void *)sechdrs[i].sh_addr, - sechdrs[i].sh_size); + if (shdr->sh_type != SHT_NOBITS) + memcpy(dest, (void *)shdr->sh_addr, shdr->sh_size); /* Update sh_addr to point to copy in image. */ - sechdrs[i].sh_addr = (unsigned long)dest; - DEBUGP("\t0x%lx %s\n", sechdrs[i].sh_addr, secstrings + sechdrs[i].sh_name); - } - /* Module has been moved. */ - mod = (void *)sechdrs[modindex].sh_addr; - kmemleak_load_module(mod, hdr, sechdrs, secstrings); - -#if defined(CONFIG_MODULE_UNLOAD) - mod->refptr = alloc_percpu(struct module_ref); - if (!mod->refptr) { - err = -ENOMEM; - goto free_init; + shdr->sh_addr = (unsigned long)dest; + DEBUGP("\t0x%lx %s\n", + shdr->sh_addr, info->secstrings + shdr->sh_name); } -#endif - /* Now we've moved module, initialize linked lists, etc. */ - module_unload_init(mod); - /* Set up license info based on the info section */ - set_license(mod, get_modinfo(sechdrs, infoindex, "license")); + return 0; +} +static int check_module_license_and_versions(struct module *mod) +{ /* * ndiswrapper is under GPL by itself, but loads proprietary modules. * Don't use add_taint_module(), as it would prevent ndiswrapper from @@ -2353,77 +2411,6 @@ static noinline struct module *load_module(void __user *umod, if (strcmp(mod->name, "driverloader") == 0) add_taint_module(mod, TAINT_PROPRIETARY_MODULE); - /* Set up MODINFO_ATTR fields */ - setup_modinfo(mod, sechdrs, infoindex); - - /* Fix up syms, so that st_value is a pointer to location. */ - err = simplify_symbols(sechdrs, symindex, strtab, versindex, pcpuindex, - mod); - if (err < 0) - goto cleanup; - - /* Now we've got everything in the final locations, we can - * find optional sections. */ - mod->kp = section_objs(hdr, sechdrs, secstrings, "__param", - sizeof(*mod->kp), &mod->num_kp); - mod->syms = section_objs(hdr, sechdrs, secstrings, "__ksymtab", - sizeof(*mod->syms), &mod->num_syms); - mod->crcs = section_addr(hdr, sechdrs, secstrings, "__kcrctab"); - mod->gpl_syms = section_objs(hdr, sechdrs, secstrings, "__ksymtab_gpl", - sizeof(*mod->gpl_syms), - &mod->num_gpl_syms); - mod->gpl_crcs = section_addr(hdr, sechdrs, secstrings, "__kcrctab_gpl"); - mod->gpl_future_syms = section_objs(hdr, sechdrs, secstrings, - "__ksymtab_gpl_future", - sizeof(*mod->gpl_future_syms), - &mod->num_gpl_future_syms); - mod->gpl_future_crcs = section_addr(hdr, sechdrs, secstrings, - "__kcrctab_gpl_future"); - -#ifdef CONFIG_UNUSED_SYMBOLS - mod->unused_syms = section_objs(hdr, sechdrs, secstrings, - "__ksymtab_unused", - sizeof(*mod->unused_syms), - &mod->num_unused_syms); - mod->unused_crcs = section_addr(hdr, sechdrs, secstrings, - "__kcrctab_unused"); - mod->unused_gpl_syms = section_objs(hdr, sechdrs, secstrings, - "__ksymtab_unused_gpl", - sizeof(*mod->unused_gpl_syms), - &mod->num_unused_gpl_syms); - mod->unused_gpl_crcs = section_addr(hdr, sechdrs, secstrings, - "__kcrctab_unused_gpl"); -#endif -#ifdef CONFIG_CONSTRUCTORS - mod->ctors = section_objs(hdr, sechdrs, secstrings, ".ctors", - sizeof(*mod->ctors), &mod->num_ctors); -#endif - -#ifdef CONFIG_TRACEPOINTS - mod->tracepoints = section_objs(hdr, sechdrs, secstrings, - "__tracepoints", - sizeof(*mod->tracepoints), - &mod->num_tracepoints); -#endif -#ifdef CONFIG_EVENT_TRACING - mod->trace_events = section_objs(hdr, sechdrs, secstrings, - "_ftrace_events", - sizeof(*mod->trace_events), - &mod->num_trace_events); - /* - * This section contains pointers to allocated objects in the trace - * code and not scanning it leads to false positives. - */ - kmemleak_scan_area(mod->trace_events, sizeof(*mod->trace_events) * - mod->num_trace_events, GFP_KERNEL); -#endif -#ifdef CONFIG_FTRACE_MCOUNT_RECORD - /* sechdrs[0].sh_size is always zero */ - mod->ftrace_callsites = section_objs(hdr, sechdrs, secstrings, - "__mcount_loc", - sizeof(*mod->ftrace_callsites), - &mod->num_ftrace_callsites); -#endif #ifdef CONFIG_MODVERSIONS if ((mod->num_syms && !mod->crcs) || (mod->num_gpl_syms && !mod->gpl_crcs) @@ -2433,62 +2420,16 @@ static noinline struct module *load_module(void __user *umod, || (mod->num_unused_gpl_syms && !mod->unused_gpl_crcs) #endif ) { - err = try_to_force_load(mod, - "no versions for exported symbols"); - if (err) - goto cleanup; + return try_to_force_load(mod, + "no versions for exported symbols"); } #endif + return 0; +} - /* Now do relocations. */ - for (i = 1; i < hdr->e_shnum; i++) { - const char *strtab = (char *)sechdrs[strindex].sh_addr; - unsigned int info = sechdrs[i].sh_info; - - /* Not a valid relocation section? */ - if (info >= hdr->e_shnum) - continue; - - /* Don't bother with non-allocated sections */ - if (!(sechdrs[info].sh_flags & SHF_ALLOC)) - continue; - - if (sechdrs[i].sh_type == SHT_REL) - err = apply_relocate(sechdrs, strtab, symindex, i,mod); - else if (sechdrs[i].sh_type == SHT_RELA) - err = apply_relocate_add(sechdrs, strtab, symindex, i, - mod); - if (err < 0) - goto cleanup; - } - - /* Set up and sort exception table */ - mod->extable = section_objs(hdr, sechdrs, secstrings, "__ex_table", - sizeof(*mod->extable), &mod->num_exentries); - sort_extable(mod->extable, mod->extable + mod->num_exentries); - - /* Finally, copy percpu area over. */ - percpu_modcopy(mod, (void *)sechdrs[pcpuindex].sh_addr, - sechdrs[pcpuindex].sh_size); - - add_kallsyms(mod, sechdrs, hdr->e_shnum, symindex, strindex, - symoffs, stroffs, secstrings, strmap); - kfree(strmap); - strmap = NULL; - - if (!mod->taints) { - struct _ddebug *debug; - unsigned int num_debug; - - debug = section_objs(hdr, sechdrs, secstrings, "__verbose", - sizeof(*debug), &num_debug); - if (debug) - dynamic_debug_setup(debug, num_debug); - } - - err = module_finalize(hdr, sechdrs, mod); - if (err < 0) - goto cleanup; +static void flush_module_icache(const struct module *mod) +{ + mm_segment_t old_fs; /* flush the icache in correct context */ old_fs = get_fs(); @@ -2507,11 +2448,160 @@ static noinline struct module *load_module(void __user *umod, (unsigned long)mod->module_core + mod->core_size); set_fs(old_fs); +} - mod->args = args; - if (section_addr(hdr, sechdrs, secstrings, "__obsparm")) - printk(KERN_WARNING "%s: Ignoring obsolete parameters\n", - mod->name); +static struct module *layout_and_allocate(struct load_info *info) +{ + /* Module within temporary copy. */ + struct module *mod; + Elf_Shdr *pcpusec; + int err; + + mod = setup_load_info(info); + if (IS_ERR(mod)) + return mod; + + err = check_modinfo(mod, info); + if (err) + return ERR_PTR(err); + + /* Allow arches to frob section contents and sizes. */ + err = module_frob_arch_sections(info->hdr, info->sechdrs, + info->secstrings, mod); + if (err < 0) + goto out; + + pcpusec = &info->sechdrs[info->index.pcpu]; + if (pcpusec->sh_size) { + /* We have a special allocation for this section. */ + err = percpu_modalloc(mod, + pcpusec->sh_size, pcpusec->sh_addralign); + if (err) + goto out; + pcpusec->sh_flags &= ~(unsigned long)SHF_ALLOC; + } + + /* Determine total sizes, and put offsets in sh_entsize. For now + this is done generically; there doesn't appear to be any + special cases for the architectures. */ + layout_sections(mod, info); + + info->strmap = kzalloc(BITS_TO_LONGS(info->sechdrs[info->index.str].sh_size) + * sizeof(long), GFP_KERNEL); + if (!info->strmap) { + err = -ENOMEM; + goto free_percpu; + } + layout_symtab(mod, info); + + /* Allocate and move to the final place */ + err = move_module(mod, info); + if (err) + goto free_strmap; + + /* Module has been copied to its final place now: return it. */ + mod = (void *)info->sechdrs[info->index.mod].sh_addr; + kmemleak_load_module(mod, info); + return mod; + +free_strmap: + kfree(info->strmap); +free_percpu: + percpu_modfree(mod); +out: + return ERR_PTR(err); +} + +/* mod is no longer valid after this! */ +static void module_deallocate(struct module *mod, struct load_info *info) +{ + kfree(info->strmap); + percpu_modfree(mod); + module_free(mod, mod->module_init); + module_free(mod, mod->module_core); +} + +static int post_relocation(struct module *mod, const struct load_info *info) +{ + /* Sort exception table now relocations are done. */ + sort_extable(mod->extable, mod->extable + mod->num_exentries); + + /* Copy relocated percpu area over. */ + percpu_modcopy(mod, (void *)info->sechdrs[info->index.pcpu].sh_addr, + info->sechdrs[info->index.pcpu].sh_size); + + /* Setup kallsyms-specific fields. */ + add_kallsyms(mod, info); + + /* Arch-specific module finalizing. */ + return module_finalize(info->hdr, info->sechdrs, mod); +} + +/* Allocate and load the module: note that size of section 0 is always + zero, and we rely on this for optional sections. */ +static struct module *load_module(void __user *umod, + unsigned long len, + const char __user *uargs) +{ + struct load_info info = { NULL, }; + struct module *mod; + long err; + + DEBUGP("load_module: umod=%p, len=%lu, uargs=%p\n", + umod, len, uargs); + + /* Copy in the blobs from userspace, check they are vaguely sane. */ + err = copy_and_check(&info, umod, len, uargs); + if (err) + return ERR_PTR(err); + + /* Figure out module layout, and allocate all the memory. */ + mod = layout_and_allocate(&info); + if (IS_ERR(mod)) { + err = PTR_ERR(mod); + goto free_copy; + } + + /* Now module is in final location, initialize linked lists, etc. */ + err = module_unload_init(mod); + if (err) + goto free_module; + + /* Now we've got everything in the final locations, we can + * find optional sections. */ + find_module_sections(mod, &info); + + err = check_module_license_and_versions(mod); + if (err) + goto free_unload; + + /* Set up MODINFO_ATTR fields */ + setup_modinfo(mod, &info); + + /* Fix up syms, so that st_value is a pointer to location. */ + err = simplify_symbols(mod, &info); + if (err < 0) + goto free_modinfo; + + err = apply_relocations(mod, &info); + if (err < 0) + goto free_modinfo; + + err = post_relocation(mod, &info); + if (err < 0) + goto free_modinfo; + + flush_module_icache(mod); + + /* Now copy in args */ + mod->args = strndup_user(uargs, ~0UL >> 1); + if (IS_ERR(mod->args)) { + err = PTR_ERR(mod->args); + goto free_arch_cleanup; + } + + /* Mark state as coming so strong_try_module_get() ignores us. */ + mod->state = MODULE_STATE_COMING; /* Now sew it into the lists so we can get lockdep and oops * info during argument parsing. Noone should access us, since @@ -2526,65 +2616,58 @@ static noinline struct module *load_module(void __user *umod, goto unlock; } + /* This has to be done once we're sure module name is unique. */ + if (!mod->taints) + dynamic_debug_setup(info.debug, info.num_debug); + /* Find duplicate symbols */ err = verify_export_symbols(mod); if (err < 0) - goto unlock; + goto ddebug; list_add_rcu(&mod->list, &modules); mutex_unlock(&module_mutex); + /* Module is ready to execute: parsing args may do that. */ err = parse_args(mod->name, mod->args, mod->kp, mod->num_kp, NULL); if (err < 0) goto unlink; - err = mod_sysfs_setup(mod, mod->kp, mod->num_kp); + /* Link in to syfs. */ + err = mod_sysfs_setup(mod, &info, mod->kp, mod->num_kp); if (err < 0) goto unlink; - add_sect_attrs(mod, hdr->e_shnum, secstrings, sechdrs); - add_notes_attrs(mod, hdr->e_shnum, secstrings, sechdrs); - - /* Get rid of temporary copy */ - vfree(hdr); - - trace_module_load(mod); + /* Get rid of temporary copy and strmap. */ + kfree(info.strmap); + free_copy(&info); /* Done! */ + trace_module_load(mod); return mod; unlink: mutex_lock(&module_mutex); /* Unlink carefully: kallsyms could be walking list. */ list_del_rcu(&mod->list); + ddebug: + if (!mod->taints) + dynamic_debug_remove(info.debug); unlock: mutex_unlock(&module_mutex); synchronize_sched(); + kfree(mod->args); + free_arch_cleanup: module_arch_cleanup(mod); - cleanup: + free_modinfo: free_modinfo(mod); + free_unload: module_unload_free(mod); -#if defined(CONFIG_MODULE_UNLOAD) - free_percpu(mod->refptr); - free_init: -#endif - module_free(mod, mod->module_init); - free_core: - module_free(mod, mod->module_core); - /* mod will be freed with core. Don't access it beyond this line! */ - free_percpu: - free_percpu(percpu); - free_mod: - kfree(args); - kfree(strmap); - free_hdr: - vfree(hdr); + free_module: + module_deallocate(mod, &info); + free_copy: + free_copy(&info); return ERR_PTR(err); - - truncated: - printk(KERN_ERR "Module len %lu truncated\n", len); - err = -ENOEXEC; - goto free_hdr; } /* Call module constructors. */ diff --git a/kernel/padata.c b/kernel/padata.c index fdd8ae609ce3..751019415d23 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -26,18 +26,19 @@ #include <linux/mutex.h> #include <linux/sched.h> #include <linux/slab.h> +#include <linux/sysfs.h> #include <linux/rcupdate.h> -#define MAX_SEQ_NR INT_MAX - NR_CPUS +#define MAX_SEQ_NR (INT_MAX - NR_CPUS) #define MAX_OBJ_NUM 1000 static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index) { int cpu, target_cpu; - target_cpu = cpumask_first(pd->cpumask); + target_cpu = cpumask_first(pd->cpumask.pcpu); for (cpu = 0; cpu < cpu_index; cpu++) - target_cpu = cpumask_next(target_cpu, pd->cpumask); + target_cpu = cpumask_next(target_cpu, pd->cpumask.pcpu); return target_cpu; } @@ -53,26 +54,27 @@ static int padata_cpu_hash(struct padata_priv *padata) * Hash the sequence numbers to the cpus by taking * seq_nr mod. number of cpus in use. */ - cpu_index = padata->seq_nr % cpumask_weight(pd->cpumask); + cpu_index = padata->seq_nr % cpumask_weight(pd->cpumask.pcpu); return padata_index_to_cpu(pd, cpu_index); } -static void padata_parallel_worker(struct work_struct *work) +static void padata_parallel_worker(struct work_struct *parallel_work) { - struct padata_queue *queue; + struct padata_parallel_queue *pqueue; struct parallel_data *pd; struct padata_instance *pinst; LIST_HEAD(local_list); local_bh_disable(); - queue = container_of(work, struct padata_queue, pwork); - pd = queue->pd; + pqueue = container_of(parallel_work, + struct padata_parallel_queue, work); + pd = pqueue->pd; pinst = pd->pinst; - spin_lock(&queue->parallel.lock); - list_replace_init(&queue->parallel.list, &local_list); - spin_unlock(&queue->parallel.lock); + spin_lock(&pqueue->parallel.lock); + list_replace_init(&pqueue->parallel.list, &local_list); + spin_unlock(&pqueue->parallel.lock); while (!list_empty(&local_list)) { struct padata_priv *padata; @@ -94,7 +96,7 @@ static void padata_parallel_worker(struct work_struct *work) * @pinst: padata instance * @padata: object to be parallelized * @cb_cpu: cpu the serialization callback function will run on, - * must be in the cpumask of padata. + * must be in the serial cpumask of padata(i.e. cpumask.cbcpu). * * The parallelization callback function will run with BHs off. * Note: Every object which is parallelized by padata_do_parallel @@ -104,15 +106,18 @@ int padata_do_parallel(struct padata_instance *pinst, struct padata_priv *padata, int cb_cpu) { int target_cpu, err; - struct padata_queue *queue; + struct padata_parallel_queue *queue; struct parallel_data *pd; rcu_read_lock_bh(); pd = rcu_dereference(pinst->pd); - err = 0; - if (!(pinst->flags & PADATA_INIT)) + err = -EINVAL; + if (!(pinst->flags & PADATA_INIT) || pinst->flags & PADATA_INVALID) + goto out; + + if (!cpumask_test_cpu(cb_cpu, pd->cpumask.cbcpu)) goto out; err = -EBUSY; @@ -122,11 +127,7 @@ int padata_do_parallel(struct padata_instance *pinst, if (atomic_read(&pd->refcnt) >= MAX_OBJ_NUM) goto out; - err = -EINVAL; - if (!cpumask_test_cpu(cb_cpu, pd->cpumask)) - goto out; - - err = -EINPROGRESS; + err = 0; atomic_inc(&pd->refcnt); padata->pd = pd; padata->cb_cpu = cb_cpu; @@ -137,13 +138,13 @@ int padata_do_parallel(struct padata_instance *pinst, padata->seq_nr = atomic_inc_return(&pd->seq_nr); target_cpu = padata_cpu_hash(padata); - queue = per_cpu_ptr(pd->queue, target_cpu); + queue = per_cpu_ptr(pd->pqueue, target_cpu); spin_lock(&queue->parallel.lock); list_add_tail(&padata->list, &queue->parallel.list); spin_unlock(&queue->parallel.lock); - queue_work_on(target_cpu, pinst->wq, &queue->pwork); + queue_work_on(target_cpu, pinst->wq, &queue->work); out: rcu_read_unlock_bh(); @@ -171,84 +172,52 @@ EXPORT_SYMBOL(padata_do_parallel); */ static struct padata_priv *padata_get_next(struct parallel_data *pd) { - int cpu, num_cpus, empty, calc_seq_nr; - int seq_nr, next_nr, overrun, next_overrun; - struct padata_queue *queue, *next_queue; + int cpu, num_cpus; + int next_nr, next_index; + struct padata_parallel_queue *queue, *next_queue; struct padata_priv *padata; struct padata_list *reorder; - empty = 0; - next_nr = -1; - next_overrun = 0; - next_queue = NULL; - - num_cpus = cpumask_weight(pd->cpumask); - - for_each_cpu(cpu, pd->cpumask) { - queue = per_cpu_ptr(pd->queue, cpu); - reorder = &queue->reorder; - - /* - * Calculate the seq_nr of the object that should be - * next in this reorder queue. - */ - overrun = 0; - calc_seq_nr = (atomic_read(&queue->num_obj) * num_cpus) - + queue->cpu_index; + num_cpus = cpumask_weight(pd->cpumask.pcpu); - if (unlikely(calc_seq_nr > pd->max_seq_nr)) { - calc_seq_nr = calc_seq_nr - pd->max_seq_nr - 1; - overrun = 1; - } - - if (!list_empty(&reorder->list)) { - padata = list_entry(reorder->list.next, - struct padata_priv, list); - - seq_nr = padata->seq_nr; - BUG_ON(calc_seq_nr != seq_nr); - } else { - seq_nr = calc_seq_nr; - empty++; - } - - if (next_nr < 0 || seq_nr < next_nr - || (next_overrun && !overrun)) { - next_nr = seq_nr; - next_overrun = overrun; - next_queue = queue; - } + /* + * Calculate the percpu reorder queue and the sequence + * number of the next object. + */ + next_nr = pd->processed; + next_index = next_nr % num_cpus; + cpu = padata_index_to_cpu(pd, next_index); + next_queue = per_cpu_ptr(pd->pqueue, cpu); + + if (unlikely(next_nr > pd->max_seq_nr)) { + next_nr = next_nr - pd->max_seq_nr - 1; + next_index = next_nr % num_cpus; + cpu = padata_index_to_cpu(pd, next_index); + next_queue = per_cpu_ptr(pd->pqueue, cpu); + pd->processed = 0; } padata = NULL; - if (empty == num_cpus) - goto out; - reorder = &next_queue->reorder; if (!list_empty(&reorder->list)) { padata = list_entry(reorder->list.next, struct padata_priv, list); - if (unlikely(next_overrun)) { - for_each_cpu(cpu, pd->cpumask) { - queue = per_cpu_ptr(pd->queue, cpu); - atomic_set(&queue->num_obj, 0); - } - } + BUG_ON(next_nr != padata->seq_nr); spin_lock(&reorder->lock); list_del_init(&padata->list); atomic_dec(&pd->reorder_objects); spin_unlock(&reorder->lock); - atomic_inc(&next_queue->num_obj); + pd->processed++; goto out; } - queue = per_cpu_ptr(pd->queue, smp_processor_id()); + queue = per_cpu_ptr(pd->pqueue, smp_processor_id()); if (queue->cpu_index == next_queue->cpu_index) { padata = ERR_PTR(-ENODATA); goto out; @@ -262,7 +231,7 @@ out: static void padata_reorder(struct parallel_data *pd) { struct padata_priv *padata; - struct padata_queue *queue; + struct padata_serial_queue *squeue; struct padata_instance *pinst = pd->pinst; /* @@ -301,13 +270,13 @@ static void padata_reorder(struct parallel_data *pd) return; } - queue = per_cpu_ptr(pd->queue, padata->cb_cpu); + squeue = per_cpu_ptr(pd->squeue, padata->cb_cpu); - spin_lock(&queue->serial.lock); - list_add_tail(&padata->list, &queue->serial.list); - spin_unlock(&queue->serial.lock); + spin_lock(&squeue->serial.lock); + list_add_tail(&padata->list, &squeue->serial.list); + spin_unlock(&squeue->serial.lock); - queue_work_on(padata->cb_cpu, pinst->wq, &queue->swork); + queue_work_on(padata->cb_cpu, pinst->wq, &squeue->work); } spin_unlock_bh(&pd->lock); @@ -333,19 +302,19 @@ static void padata_reorder_timer(unsigned long arg) padata_reorder(pd); } -static void padata_serial_worker(struct work_struct *work) +static void padata_serial_worker(struct work_struct *serial_work) { - struct padata_queue *queue; + struct padata_serial_queue *squeue; struct parallel_data *pd; LIST_HEAD(local_list); local_bh_disable(); - queue = container_of(work, struct padata_queue, swork); - pd = queue->pd; + squeue = container_of(serial_work, struct padata_serial_queue, work); + pd = squeue->pd; - spin_lock(&queue->serial.lock); - list_replace_init(&queue->serial.list, &local_list); - spin_unlock(&queue->serial.lock); + spin_lock(&squeue->serial.lock); + list_replace_init(&squeue->serial.list, &local_list); + spin_unlock(&squeue->serial.lock); while (!list_empty(&local_list)) { struct padata_priv *padata; @@ -372,18 +341,18 @@ static void padata_serial_worker(struct work_struct *work) void padata_do_serial(struct padata_priv *padata) { int cpu; - struct padata_queue *queue; + struct padata_parallel_queue *pqueue; struct parallel_data *pd; pd = padata->pd; cpu = get_cpu(); - queue = per_cpu_ptr(pd->queue, cpu); + pqueue = per_cpu_ptr(pd->pqueue, cpu); - spin_lock(&queue->reorder.lock); + spin_lock(&pqueue->reorder.lock); atomic_inc(&pd->reorder_objects); - list_add_tail(&padata->list, &queue->reorder.list); - spin_unlock(&queue->reorder.lock); + list_add_tail(&padata->list, &pqueue->reorder.list); + spin_unlock(&pqueue->reorder.lock); put_cpu(); @@ -391,52 +360,89 @@ void padata_do_serial(struct padata_priv *padata) } EXPORT_SYMBOL(padata_do_serial); -/* Allocate and initialize the internal cpumask dependend resources. */ -static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst, - const struct cpumask *cpumask) +static int padata_setup_cpumasks(struct parallel_data *pd, + const struct cpumask *pcpumask, + const struct cpumask *cbcpumask) { - int cpu, cpu_index, num_cpus; - struct padata_queue *queue; - struct parallel_data *pd; - - cpu_index = 0; + if (!alloc_cpumask_var(&pd->cpumask.pcpu, GFP_KERNEL)) + return -ENOMEM; - pd = kzalloc(sizeof(struct parallel_data), GFP_KERNEL); - if (!pd) - goto err; + cpumask_and(pd->cpumask.pcpu, pcpumask, cpu_active_mask); + if (!alloc_cpumask_var(&pd->cpumask.cbcpu, GFP_KERNEL)) { + free_cpumask_var(pd->cpumask.cbcpu); + return -ENOMEM; + } - pd->queue = alloc_percpu(struct padata_queue); - if (!pd->queue) - goto err_free_pd; + cpumask_and(pd->cpumask.cbcpu, cbcpumask, cpu_active_mask); + return 0; +} - if (!alloc_cpumask_var(&pd->cpumask, GFP_KERNEL)) - goto err_free_queue; +static void __padata_list_init(struct padata_list *pd_list) +{ + INIT_LIST_HEAD(&pd_list->list); + spin_lock_init(&pd_list->lock); +} - cpumask_and(pd->cpumask, cpumask, cpu_active_mask); +/* Initialize all percpu queues used by serial workers */ +static void padata_init_squeues(struct parallel_data *pd) +{ + int cpu; + struct padata_serial_queue *squeue; - for_each_cpu(cpu, pd->cpumask) { - queue = per_cpu_ptr(pd->queue, cpu); + for_each_cpu(cpu, pd->cpumask.cbcpu) { + squeue = per_cpu_ptr(pd->squeue, cpu); + squeue->pd = pd; + __padata_list_init(&squeue->serial); + INIT_WORK(&squeue->work, padata_serial_worker); + } +} - queue->pd = pd; +/* Initialize all percpu queues used by parallel workers */ +static void padata_init_pqueues(struct parallel_data *pd) +{ + int cpu_index, num_cpus, cpu; + struct padata_parallel_queue *pqueue; - queue->cpu_index = cpu_index; + cpu_index = 0; + for_each_cpu(cpu, pd->cpumask.pcpu) { + pqueue = per_cpu_ptr(pd->pqueue, cpu); + pqueue->pd = pd; + pqueue->cpu_index = cpu_index; cpu_index++; - INIT_LIST_HEAD(&queue->reorder.list); - INIT_LIST_HEAD(&queue->parallel.list); - INIT_LIST_HEAD(&queue->serial.list); - spin_lock_init(&queue->reorder.lock); - spin_lock_init(&queue->parallel.lock); - spin_lock_init(&queue->serial.lock); - - INIT_WORK(&queue->pwork, padata_parallel_worker); - INIT_WORK(&queue->swork, padata_serial_worker); - atomic_set(&queue->num_obj, 0); + __padata_list_init(&pqueue->reorder); + __padata_list_init(&pqueue->parallel); + INIT_WORK(&pqueue->work, padata_parallel_worker); + atomic_set(&pqueue->num_obj, 0); } - num_cpus = cpumask_weight(pd->cpumask); - pd->max_seq_nr = (MAX_SEQ_NR / num_cpus) * num_cpus - 1; + num_cpus = cpumask_weight(pd->cpumask.pcpu); + pd->max_seq_nr = num_cpus ? (MAX_SEQ_NR / num_cpus) * num_cpus - 1 : 0; +} + +/* Allocate and initialize the internal cpumask dependend resources. */ +static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst, + const struct cpumask *pcpumask, + const struct cpumask *cbcpumask) +{ + struct parallel_data *pd; + pd = kzalloc(sizeof(struct parallel_data), GFP_KERNEL); + if (!pd) + goto err; + + pd->pqueue = alloc_percpu(struct padata_parallel_queue); + if (!pd->pqueue) + goto err_free_pd; + + pd->squeue = alloc_percpu(struct padata_serial_queue); + if (!pd->squeue) + goto err_free_pqueue; + if (padata_setup_cpumasks(pd, pcpumask, cbcpumask) < 0) + goto err_free_squeue; + + padata_init_pqueues(pd); + padata_init_squeues(pd); setup_timer(&pd->timer, padata_reorder_timer, (unsigned long)pd); atomic_set(&pd->seq_nr, -1); atomic_set(&pd->reorder_objects, 0); @@ -446,8 +452,10 @@ static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst, return pd; -err_free_queue: - free_percpu(pd->queue); +err_free_squeue: + free_percpu(pd->squeue); +err_free_pqueue: + free_percpu(pd->pqueue); err_free_pd: kfree(pd); err: @@ -456,8 +464,10 @@ err: static void padata_free_pd(struct parallel_data *pd) { - free_cpumask_var(pd->cpumask); - free_percpu(pd->queue); + free_cpumask_var(pd->cpumask.pcpu); + free_cpumask_var(pd->cpumask.cbcpu); + free_percpu(pd->pqueue); + free_percpu(pd->squeue); kfree(pd); } @@ -465,11 +475,12 @@ static void padata_free_pd(struct parallel_data *pd) static void padata_flush_queues(struct parallel_data *pd) { int cpu; - struct padata_queue *queue; + struct padata_parallel_queue *pqueue; + struct padata_serial_queue *squeue; - for_each_cpu(cpu, pd->cpumask) { - queue = per_cpu_ptr(pd->queue, cpu); - flush_work(&queue->pwork); + for_each_cpu(cpu, pd->cpumask.pcpu) { + pqueue = per_cpu_ptr(pd->pqueue, cpu); + flush_work(&pqueue->work); } del_timer_sync(&pd->timer); @@ -477,19 +488,39 @@ static void padata_flush_queues(struct parallel_data *pd) if (atomic_read(&pd->reorder_objects)) padata_reorder(pd); - for_each_cpu(cpu, pd->cpumask) { - queue = per_cpu_ptr(pd->queue, cpu); - flush_work(&queue->swork); + for_each_cpu(cpu, pd->cpumask.cbcpu) { + squeue = per_cpu_ptr(pd->squeue, cpu); + flush_work(&squeue->work); } BUG_ON(atomic_read(&pd->refcnt) != 0); } +static void __padata_start(struct padata_instance *pinst) +{ + pinst->flags |= PADATA_INIT; +} + +static void __padata_stop(struct padata_instance *pinst) +{ + if (!(pinst->flags & PADATA_INIT)) + return; + + pinst->flags &= ~PADATA_INIT; + + synchronize_rcu(); + + get_online_cpus(); + padata_flush_queues(pinst->pd); + put_online_cpus(); +} + /* Replace the internal control stucture with a new one. */ static void padata_replace(struct padata_instance *pinst, struct parallel_data *pd_new) { struct parallel_data *pd_old = pinst->pd; + int notification_mask = 0; pinst->flags |= PADATA_RESET; @@ -497,41 +528,162 @@ static void padata_replace(struct padata_instance *pinst, synchronize_rcu(); + if (!cpumask_equal(pd_old->cpumask.pcpu, pd_new->cpumask.pcpu)) + notification_mask |= PADATA_CPU_PARALLEL; + if (!cpumask_equal(pd_old->cpumask.cbcpu, pd_new->cpumask.cbcpu)) + notification_mask |= PADATA_CPU_SERIAL; + padata_flush_queues(pd_old); padata_free_pd(pd_old); + if (notification_mask) + blocking_notifier_call_chain(&pinst->cpumask_change_notifier, + notification_mask, + &pd_new->cpumask); + pinst->flags &= ~PADATA_RESET; } /** - * padata_set_cpumask - set the cpumask that padata should use + * padata_register_cpumask_notifier - Registers a notifier that will be called + * if either pcpu or cbcpu or both cpumasks change. * - * @pinst: padata instance - * @cpumask: the cpumask to use + * @pinst: A poineter to padata instance + * @nblock: A pointer to notifier block. */ -int padata_set_cpumask(struct padata_instance *pinst, - cpumask_var_t cpumask) +int padata_register_cpumask_notifier(struct padata_instance *pinst, + struct notifier_block *nblock) { + return blocking_notifier_chain_register(&pinst->cpumask_change_notifier, + nblock); +} +EXPORT_SYMBOL(padata_register_cpumask_notifier); + +/** + * padata_unregister_cpumask_notifier - Unregisters cpumask notifier + * registered earlier using padata_register_cpumask_notifier + * + * @pinst: A pointer to data instance. + * @nlock: A pointer to notifier block. + */ +int padata_unregister_cpumask_notifier(struct padata_instance *pinst, + struct notifier_block *nblock) +{ + return blocking_notifier_chain_unregister( + &pinst->cpumask_change_notifier, + nblock); +} +EXPORT_SYMBOL(padata_unregister_cpumask_notifier); + + +/* If cpumask contains no active cpu, we mark the instance as invalid. */ +static bool padata_validate_cpumask(struct padata_instance *pinst, + const struct cpumask *cpumask) +{ + if (!cpumask_intersects(cpumask, cpu_active_mask)) { + pinst->flags |= PADATA_INVALID; + return false; + } + + pinst->flags &= ~PADATA_INVALID; + return true; +} + +static int __padata_set_cpumasks(struct padata_instance *pinst, + cpumask_var_t pcpumask, + cpumask_var_t cbcpumask) +{ + int valid; struct parallel_data *pd; - int err = 0; + + valid = padata_validate_cpumask(pinst, pcpumask); + if (!valid) { + __padata_stop(pinst); + goto out_replace; + } + + valid = padata_validate_cpumask(pinst, cbcpumask); + if (!valid) + __padata_stop(pinst); + +out_replace: + pd = padata_alloc_pd(pinst, pcpumask, cbcpumask); + if (!pd) + return -ENOMEM; + + cpumask_copy(pinst->cpumask.pcpu, pcpumask); + cpumask_copy(pinst->cpumask.cbcpu, cbcpumask); + + padata_replace(pinst, pd); + + if (valid) + __padata_start(pinst); + + return 0; +} + +/** + * padata_set_cpumasks - Set both parallel and serial cpumasks. The first + * one is used by parallel workers and the second one + * by the wokers doing serialization. + * + * @pinst: padata instance + * @pcpumask: the cpumask to use for parallel workers + * @cbcpumask: the cpumsak to use for serial workers + */ +int padata_set_cpumasks(struct padata_instance *pinst, cpumask_var_t pcpumask, + cpumask_var_t cbcpumask) +{ + int err; mutex_lock(&pinst->lock); + get_online_cpus(); + err = __padata_set_cpumasks(pinst, pcpumask, cbcpumask); + + put_online_cpus(); + mutex_unlock(&pinst->lock); + + return err; + +} +EXPORT_SYMBOL(padata_set_cpumasks); + +/** + * padata_set_cpumask: Sets specified by @cpumask_type cpumask to the value + * equivalent to @cpumask. + * + * @pinst: padata instance + * @cpumask_type: PADATA_CPU_SERIAL or PADATA_CPU_PARALLEL corresponding + * to parallel and serial cpumasks respectively. + * @cpumask: the cpumask to use + */ +int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type, + cpumask_var_t cpumask) +{ + struct cpumask *serial_mask, *parallel_mask; + int err = -EINVAL; + + mutex_lock(&pinst->lock); get_online_cpus(); - pd = padata_alloc_pd(pinst, cpumask); - if (!pd) { - err = -ENOMEM; - goto out; + switch (cpumask_type) { + case PADATA_CPU_PARALLEL: + serial_mask = pinst->cpumask.cbcpu; + parallel_mask = cpumask; + break; + case PADATA_CPU_SERIAL: + parallel_mask = pinst->cpumask.pcpu; + serial_mask = cpumask; + break; + default: + goto out; } - cpumask_copy(pinst->cpumask, cpumask); - - padata_replace(pinst, pd); + err = __padata_set_cpumasks(pinst, parallel_mask, serial_mask); out: put_online_cpus(); - mutex_unlock(&pinst->lock); return err; @@ -543,30 +695,48 @@ static int __padata_add_cpu(struct padata_instance *pinst, int cpu) struct parallel_data *pd; if (cpumask_test_cpu(cpu, cpu_active_mask)) { - pd = padata_alloc_pd(pinst, pinst->cpumask); + pd = padata_alloc_pd(pinst, pinst->cpumask.pcpu, + pinst->cpumask.cbcpu); if (!pd) return -ENOMEM; padata_replace(pinst, pd); + + if (padata_validate_cpumask(pinst, pinst->cpumask.pcpu) && + padata_validate_cpumask(pinst, pinst->cpumask.cbcpu)) + __padata_start(pinst); } return 0; } -/** - * padata_add_cpu - add a cpu to the padata cpumask + /** + * padata_add_cpu - add a cpu to one or both(parallel and serial) + * padata cpumasks. * * @pinst: padata instance * @cpu: cpu to add + * @mask: bitmask of flags specifying to which cpumask @cpu shuld be added. + * The @mask may be any combination of the following flags: + * PADATA_CPU_SERIAL - serial cpumask + * PADATA_CPU_PARALLEL - parallel cpumask */ -int padata_add_cpu(struct padata_instance *pinst, int cpu) + +int padata_add_cpu(struct padata_instance *pinst, int cpu, int mask) { int err; + if (!(mask & (PADATA_CPU_SERIAL | PADATA_CPU_PARALLEL))) + return -EINVAL; + mutex_lock(&pinst->lock); get_online_cpus(); - cpumask_set_cpu(cpu, pinst->cpumask); + if (mask & PADATA_CPU_SERIAL) + cpumask_set_cpu(cpu, pinst->cpumask.cbcpu); + if (mask & PADATA_CPU_PARALLEL) + cpumask_set_cpu(cpu, pinst->cpumask.pcpu); + err = __padata_add_cpu(pinst, cpu); put_online_cpus(); @@ -578,10 +748,16 @@ EXPORT_SYMBOL(padata_add_cpu); static int __padata_remove_cpu(struct padata_instance *pinst, int cpu) { - struct parallel_data *pd; + struct parallel_data *pd = NULL; if (cpumask_test_cpu(cpu, cpu_online_mask)) { - pd = padata_alloc_pd(pinst, pinst->cpumask); + + if (!padata_validate_cpumask(pinst, pinst->cpumask.pcpu) || + !padata_validate_cpumask(pinst, pinst->cpumask.cbcpu)) + __padata_stop(pinst); + + pd = padata_alloc_pd(pinst, pinst->cpumask.pcpu, + pinst->cpumask.cbcpu); if (!pd) return -ENOMEM; @@ -591,20 +767,32 @@ static int __padata_remove_cpu(struct padata_instance *pinst, int cpu) return 0; } -/** - * padata_remove_cpu - remove a cpu from the padata cpumask + /** + * padata_remove_cpu - remove a cpu from the one or both(serial and paralell) + * padata cpumasks. * * @pinst: padata instance * @cpu: cpu to remove + * @mask: bitmask specifying from which cpumask @cpu should be removed + * The @mask may be any combination of the following flags: + * PADATA_CPU_SERIAL - serial cpumask + * PADATA_CPU_PARALLEL - parallel cpumask */ -int padata_remove_cpu(struct padata_instance *pinst, int cpu) +int padata_remove_cpu(struct padata_instance *pinst, int cpu, int mask) { int err; + if (!(mask & (PADATA_CPU_SERIAL | PADATA_CPU_PARALLEL))) + return -EINVAL; + mutex_lock(&pinst->lock); get_online_cpus(); - cpumask_clear_cpu(cpu, pinst->cpumask); + if (mask & PADATA_CPU_SERIAL) + cpumask_clear_cpu(cpu, pinst->cpumask.cbcpu); + if (mask & PADATA_CPU_PARALLEL) + cpumask_clear_cpu(cpu, pinst->cpumask.pcpu); + err = __padata_remove_cpu(pinst, cpu); put_online_cpus(); @@ -619,11 +807,20 @@ EXPORT_SYMBOL(padata_remove_cpu); * * @pinst: padata instance to start */ -void padata_start(struct padata_instance *pinst) +int padata_start(struct padata_instance *pinst) { + int err = 0; + mutex_lock(&pinst->lock); - pinst->flags |= PADATA_INIT; + + if (pinst->flags & PADATA_INVALID) + err =-EINVAL; + + __padata_start(pinst); + mutex_unlock(&pinst->lock); + + return err; } EXPORT_SYMBOL(padata_start); @@ -635,12 +832,20 @@ EXPORT_SYMBOL(padata_start); void padata_stop(struct padata_instance *pinst) { mutex_lock(&pinst->lock); - pinst->flags &= ~PADATA_INIT; + __padata_stop(pinst); mutex_unlock(&pinst->lock); } EXPORT_SYMBOL(padata_stop); #ifdef CONFIG_HOTPLUG_CPU + +static inline int pinst_has_cpu(struct padata_instance *pinst, int cpu) +{ + return cpumask_test_cpu(cpu, pinst->cpumask.pcpu) || + cpumask_test_cpu(cpu, pinst->cpumask.cbcpu); +} + + static int padata_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { @@ -653,7 +858,7 @@ static int padata_cpu_callback(struct notifier_block *nfb, switch (action) { case CPU_ONLINE: case CPU_ONLINE_FROZEN: - if (!cpumask_test_cpu(cpu, pinst->cpumask)) + if (!pinst_has_cpu(pinst, cpu)) break; mutex_lock(&pinst->lock); err = __padata_add_cpu(pinst, cpu); @@ -664,7 +869,7 @@ static int padata_cpu_callback(struct notifier_block *nfb, case CPU_DOWN_PREPARE: case CPU_DOWN_PREPARE_FROZEN: - if (!cpumask_test_cpu(cpu, pinst->cpumask)) + if (!pinst_has_cpu(pinst, cpu)) break; mutex_lock(&pinst->lock); err = __padata_remove_cpu(pinst, cpu); @@ -675,7 +880,7 @@ static int padata_cpu_callback(struct notifier_block *nfb, case CPU_UP_CANCELED: case CPU_UP_CANCELED_FROZEN: - if (!cpumask_test_cpu(cpu, pinst->cpumask)) + if (!pinst_has_cpu(pinst, cpu)) break; mutex_lock(&pinst->lock); __padata_remove_cpu(pinst, cpu); @@ -683,7 +888,7 @@ static int padata_cpu_callback(struct notifier_block *nfb, case CPU_DOWN_FAILED: case CPU_DOWN_FAILED_FROZEN: - if (!cpumask_test_cpu(cpu, pinst->cpumask)) + if (!pinst_has_cpu(pinst, cpu)) break; mutex_lock(&pinst->lock); __padata_add_cpu(pinst, cpu); @@ -694,36 +899,202 @@ static int padata_cpu_callback(struct notifier_block *nfb, } #endif +static void __padata_free(struct padata_instance *pinst) +{ +#ifdef CONFIG_HOTPLUG_CPU + unregister_hotcpu_notifier(&pinst->cpu_notifier); +#endif + + padata_stop(pinst); + padata_free_pd(pinst->pd); + free_cpumask_var(pinst->cpumask.pcpu); + free_cpumask_var(pinst->cpumask.cbcpu); + kfree(pinst); +} + +#define kobj2pinst(_kobj) \ + container_of(_kobj, struct padata_instance, kobj) +#define attr2pentry(_attr) \ + container_of(_attr, struct padata_sysfs_entry, attr) + +static void padata_sysfs_release(struct kobject *kobj) +{ + struct padata_instance *pinst = kobj2pinst(kobj); + __padata_free(pinst); +} + +struct padata_sysfs_entry { + struct attribute attr; + ssize_t (*show)(struct padata_instance *, struct attribute *, char *); + ssize_t (*store)(struct padata_instance *, struct attribute *, + const char *, size_t); +}; + +static ssize_t show_cpumask(struct padata_instance *pinst, + struct attribute *attr, char *buf) +{ + struct cpumask *cpumask; + ssize_t len; + + mutex_lock(&pinst->lock); + if (!strcmp(attr->name, "serial_cpumask")) + cpumask = pinst->cpumask.cbcpu; + else + cpumask = pinst->cpumask.pcpu; + + len = bitmap_scnprintf(buf, PAGE_SIZE, cpumask_bits(cpumask), + nr_cpu_ids); + if (PAGE_SIZE - len < 2) + len = -EINVAL; + else + len += sprintf(buf + len, "\n"); + + mutex_unlock(&pinst->lock); + return len; +} + +static ssize_t store_cpumask(struct padata_instance *pinst, + struct attribute *attr, + const char *buf, size_t count) +{ + cpumask_var_t new_cpumask; + ssize_t ret; + int mask_type; + + if (!alloc_cpumask_var(&new_cpumask, GFP_KERNEL)) + return -ENOMEM; + + ret = bitmap_parse(buf, count, cpumask_bits(new_cpumask), + nr_cpumask_bits); + if (ret < 0) + goto out; + + mask_type = !strcmp(attr->name, "serial_cpumask") ? + PADATA_CPU_SERIAL : PADATA_CPU_PARALLEL; + ret = padata_set_cpumask(pinst, mask_type, new_cpumask); + if (!ret) + ret = count; + +out: + free_cpumask_var(new_cpumask); + return ret; +} + +#define PADATA_ATTR_RW(_name, _show_name, _store_name) \ + static struct padata_sysfs_entry _name##_attr = \ + __ATTR(_name, 0644, _show_name, _store_name) +#define PADATA_ATTR_RO(_name, _show_name) \ + static struct padata_sysfs_entry _name##_attr = \ + __ATTR(_name, 0400, _show_name, NULL) + +PADATA_ATTR_RW(serial_cpumask, show_cpumask, store_cpumask); +PADATA_ATTR_RW(parallel_cpumask, show_cpumask, store_cpumask); + +/* + * Padata sysfs provides the following objects: + * serial_cpumask [RW] - cpumask for serial workers + * parallel_cpumask [RW] - cpumask for parallel workers + */ +static struct attribute *padata_default_attrs[] = { + &serial_cpumask_attr.attr, + ¶llel_cpumask_attr.attr, + NULL, +}; + +static ssize_t padata_sysfs_show(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + struct padata_instance *pinst; + struct padata_sysfs_entry *pentry; + ssize_t ret = -EIO; + + pinst = kobj2pinst(kobj); + pentry = attr2pentry(attr); + if (pentry->show) + ret = pentry->show(pinst, attr, buf); + + return ret; +} + +static ssize_t padata_sysfs_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t count) +{ + struct padata_instance *pinst; + struct padata_sysfs_entry *pentry; + ssize_t ret = -EIO; + + pinst = kobj2pinst(kobj); + pentry = attr2pentry(attr); + if (pentry->show) + ret = pentry->store(pinst, attr, buf, count); + + return ret; +} + +static const struct sysfs_ops padata_sysfs_ops = { + .show = padata_sysfs_show, + .store = padata_sysfs_store, +}; + +static struct kobj_type padata_attr_type = { + .sysfs_ops = &padata_sysfs_ops, + .default_attrs = padata_default_attrs, + .release = padata_sysfs_release, +}; + /** - * padata_alloc - allocate and initialize a padata instance + * padata_alloc_possible - Allocate and initialize padata instance. + * Use the cpu_possible_mask for serial and + * parallel workers. * - * @cpumask: cpumask that padata uses for parallelization * @wq: workqueue to use for the allocated padata instance */ -struct padata_instance *padata_alloc(const struct cpumask *cpumask, - struct workqueue_struct *wq) +struct padata_instance *padata_alloc_possible(struct workqueue_struct *wq) +{ + return padata_alloc(wq, cpu_possible_mask, cpu_possible_mask); +} +EXPORT_SYMBOL(padata_alloc_possible); + +/** + * padata_alloc - allocate and initialize a padata instance and specify + * cpumasks for serial and parallel workers. + * + * @wq: workqueue to use for the allocated padata instance + * @pcpumask: cpumask that will be used for padata parallelization + * @cbcpumask: cpumask that will be used for padata serialization + */ +struct padata_instance *padata_alloc(struct workqueue_struct *wq, + const struct cpumask *pcpumask, + const struct cpumask *cbcpumask) { struct padata_instance *pinst; - struct parallel_data *pd; + struct parallel_data *pd = NULL; pinst = kzalloc(sizeof(struct padata_instance), GFP_KERNEL); if (!pinst) goto err; get_online_cpus(); - - pd = padata_alloc_pd(pinst, cpumask); - if (!pd) + if (!alloc_cpumask_var(&pinst->cpumask.pcpu, GFP_KERNEL)) goto err_free_inst; + if (!alloc_cpumask_var(&pinst->cpumask.cbcpu, GFP_KERNEL)) { + free_cpumask_var(pinst->cpumask.pcpu); + goto err_free_inst; + } + if (!padata_validate_cpumask(pinst, pcpumask) || + !padata_validate_cpumask(pinst, cbcpumask)) + goto err_free_masks; - if (!alloc_cpumask_var(&pinst->cpumask, GFP_KERNEL)) - goto err_free_pd; + pd = padata_alloc_pd(pinst, pcpumask, cbcpumask); + if (!pd) + goto err_free_masks; rcu_assign_pointer(pinst->pd, pd); pinst->wq = wq; - cpumask_copy(pinst->cpumask, cpumask); + cpumask_copy(pinst->cpumask.pcpu, pcpumask); + cpumask_copy(pinst->cpumask.cbcpu, cbcpumask); pinst->flags = 0; @@ -735,12 +1106,15 @@ struct padata_instance *padata_alloc(const struct cpumask *cpumask, put_online_cpus(); + BLOCKING_INIT_NOTIFIER_HEAD(&pinst->cpumask_change_notifier); + kobject_init(&pinst->kobj, &padata_attr_type); mutex_init(&pinst->lock); return pinst; -err_free_pd: - padata_free_pd(pd); +err_free_masks: + free_cpumask_var(pinst->cpumask.pcpu); + free_cpumask_var(pinst->cpumask.cbcpu); err_free_inst: kfree(pinst); put_online_cpus(); @@ -756,19 +1130,6 @@ EXPORT_SYMBOL(padata_alloc); */ void padata_free(struct padata_instance *pinst) { - padata_stop(pinst); - - synchronize_rcu(); - -#ifdef CONFIG_HOTPLUG_CPU - unregister_hotcpu_notifier(&pinst->cpu_notifier); -#endif - get_online_cpus(); - padata_flush_queues(pinst->pd); - put_online_cpus(); - - padata_free_pd(pinst->pd); - free_cpumask_var(pinst->cpumask); - kfree(pinst); + kobject_put(&pinst->kobj); } EXPORT_SYMBOL(padata_free); diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c index f42d3f737a33..996a4dec5f96 100644 --- a/kernel/pm_qos_params.c +++ b/kernel/pm_qos_params.c @@ -48,59 +48,49 @@ * or pm_qos_object list and pm_qos_objects need to happen with pm_qos_lock * held, taken with _irqsave. One lock to rule them all */ -struct pm_qos_request_list { - struct list_head list; - union { - s32 value; - s32 usec; - s32 kbps; - }; - int pm_qos_class; +enum pm_qos_type { + PM_QOS_MAX, /* return the largest value */ + PM_QOS_MIN /* return the smallest value */ }; -static s32 max_compare(s32 v1, s32 v2); -static s32 min_compare(s32 v1, s32 v2); - struct pm_qos_object { - struct pm_qos_request_list requests; + struct plist_head requests; struct blocking_notifier_head *notifiers; struct miscdevice pm_qos_power_miscdev; char *name; s32 default_value; - atomic_t target_value; - s32 (*comparitor)(s32, s32); + enum pm_qos_type type; }; +static DEFINE_SPINLOCK(pm_qos_lock); + static struct pm_qos_object null_pm_qos; static BLOCKING_NOTIFIER_HEAD(cpu_dma_lat_notifier); static struct pm_qos_object cpu_dma_pm_qos = { - .requests = {LIST_HEAD_INIT(cpu_dma_pm_qos.requests.list)}, + .requests = PLIST_HEAD_INIT(cpu_dma_pm_qos.requests, pm_qos_lock), .notifiers = &cpu_dma_lat_notifier, .name = "cpu_dma_latency", .default_value = 2000 * USEC_PER_SEC, - .target_value = ATOMIC_INIT(2000 * USEC_PER_SEC), - .comparitor = min_compare + .type = PM_QOS_MIN, }; static BLOCKING_NOTIFIER_HEAD(network_lat_notifier); static struct pm_qos_object network_lat_pm_qos = { - .requests = {LIST_HEAD_INIT(network_lat_pm_qos.requests.list)}, + .requests = PLIST_HEAD_INIT(network_lat_pm_qos.requests, pm_qos_lock), .notifiers = &network_lat_notifier, .name = "network_latency", .default_value = 2000 * USEC_PER_SEC, - .target_value = ATOMIC_INIT(2000 * USEC_PER_SEC), - .comparitor = min_compare + .type = PM_QOS_MIN }; static BLOCKING_NOTIFIER_HEAD(network_throughput_notifier); static struct pm_qos_object network_throughput_pm_qos = { - .requests = {LIST_HEAD_INIT(network_throughput_pm_qos.requests.list)}, + .requests = PLIST_HEAD_INIT(network_throughput_pm_qos.requests, pm_qos_lock), .notifiers = &network_throughput_notifier, .name = "network_throughput", .default_value = 0, - .target_value = ATOMIC_INIT(0), - .comparitor = max_compare + .type = PM_QOS_MAX, }; @@ -111,8 +101,6 @@ static struct pm_qos_object *pm_qos_array[] = { &network_throughput_pm_qos }; -static DEFINE_SPINLOCK(pm_qos_lock); - static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf, size_t count, loff_t *f_pos); static int pm_qos_power_open(struct inode *inode, struct file *filp); @@ -124,46 +112,55 @@ static const struct file_operations pm_qos_power_fops = { .release = pm_qos_power_release, }; -/* static helper functions */ -static s32 max_compare(s32 v1, s32 v2) +/* unlocked internal variant */ +static inline int pm_qos_get_value(struct pm_qos_object *o) { - return max(v1, v2); -} + if (plist_head_empty(&o->requests)) + return o->default_value; -static s32 min_compare(s32 v1, s32 v2) -{ - return min(v1, v2); -} + switch (o->type) { + case PM_QOS_MIN: + return plist_last(&o->requests)->prio; + case PM_QOS_MAX: + return plist_first(&o->requests)->prio; -static void update_target(int pm_qos_class) + default: + /* runtime check for not using enum */ + BUG(); + } +} + +static void update_target(struct pm_qos_object *o, struct plist_node *node, + int del, int value) { - s32 extreme_value; - struct pm_qos_request_list *node; unsigned long flags; - int call_notifier = 0; + int prev_value, curr_value; spin_lock_irqsave(&pm_qos_lock, flags); - extreme_value = pm_qos_array[pm_qos_class]->default_value; - list_for_each_entry(node, - &pm_qos_array[pm_qos_class]->requests.list, list) { - extreme_value = pm_qos_array[pm_qos_class]->comparitor( - extreme_value, node->value); - } - if (atomic_read(&pm_qos_array[pm_qos_class]->target_value) != - extreme_value) { - call_notifier = 1; - atomic_set(&pm_qos_array[pm_qos_class]->target_value, - extreme_value); - pr_debug(KERN_ERR "new target for qos %d is %d\n", pm_qos_class, - atomic_read(&pm_qos_array[pm_qos_class]->target_value)); + prev_value = pm_qos_get_value(o); + /* PM_QOS_DEFAULT_VALUE is a signal that the value is unchanged */ + if (value != PM_QOS_DEFAULT_VALUE) { + /* + * to change the list, we atomically remove, reinit + * with new value and add, then see if the extremal + * changed + */ + plist_del(node, &o->requests); + plist_node_init(node, value); + plist_add(node, &o->requests); + } else if (del) { + plist_del(node, &o->requests); + } else { + plist_add(node, &o->requests); } + curr_value = pm_qos_get_value(o); spin_unlock_irqrestore(&pm_qos_lock, flags); - if (call_notifier) - blocking_notifier_call_chain( - pm_qos_array[pm_qos_class]->notifiers, - (unsigned long) extreme_value, NULL); + if (prev_value != curr_value) + blocking_notifier_call_chain(o->notifiers, + (unsigned long)curr_value, + NULL); } static int register_pm_qos_misc(struct pm_qos_object *qos) @@ -196,10 +193,23 @@ static int find_pm_qos_object_by_minor(int minor) */ int pm_qos_request(int pm_qos_class) { - return atomic_read(&pm_qos_array[pm_qos_class]->target_value); + unsigned long flags; + int value; + + spin_lock_irqsave(&pm_qos_lock, flags); + value = pm_qos_get_value(pm_qos_array[pm_qos_class]); + spin_unlock_irqrestore(&pm_qos_lock, flags); + + return value; } EXPORT_SYMBOL_GPL(pm_qos_request); +int pm_qos_request_active(struct pm_qos_request_list *req) +{ + return req->pm_qos_class != 0; +} +EXPORT_SYMBOL_GPL(pm_qos_request_active); + /** * pm_qos_add_request - inserts new qos request into the list * @pm_qos_class: identifies which list of qos request to us @@ -211,27 +221,23 @@ EXPORT_SYMBOL_GPL(pm_qos_request); * element as a handle for use in updating and removal. Call needs to save * this handle for later use. */ -struct pm_qos_request_list *pm_qos_add_request(int pm_qos_class, s32 value) +void pm_qos_add_request(struct pm_qos_request_list *dep, + int pm_qos_class, s32 value) { - struct pm_qos_request_list *dep; - unsigned long flags; + struct pm_qos_object *o = pm_qos_array[pm_qos_class]; + int new_value; - dep = kzalloc(sizeof(struct pm_qos_request_list), GFP_KERNEL); - if (dep) { - if (value == PM_QOS_DEFAULT_VALUE) - dep->value = pm_qos_array[pm_qos_class]->default_value; - else - dep->value = value; - dep->pm_qos_class = pm_qos_class; - - spin_lock_irqsave(&pm_qos_lock, flags); - list_add(&dep->list, - &pm_qos_array[pm_qos_class]->requests.list); - spin_unlock_irqrestore(&pm_qos_lock, flags); - update_target(pm_qos_class); + if (pm_qos_request_active(dep)) { + WARN(1, KERN_ERR "pm_qos_add_request() called for already added request\n"); + return; } - - return dep; + if (value == PM_QOS_DEFAULT_VALUE) + new_value = o->default_value; + else + new_value = value; + plist_node_init(&dep->list, new_value); + dep->pm_qos_class = pm_qos_class; + update_target(o, &dep->list, 0, PM_QOS_DEFAULT_VALUE); } EXPORT_SYMBOL_GPL(pm_qos_add_request); @@ -246,27 +252,28 @@ EXPORT_SYMBOL_GPL(pm_qos_add_request); * Attempts are made to make this code callable on hot code paths. */ void pm_qos_update_request(struct pm_qos_request_list *pm_qos_req, - s32 new_value) + s32 new_value) { - unsigned long flags; - int pending_update = 0; s32 temp; + struct pm_qos_object *o; + + if (!pm_qos_req) /*guard against callers passing in null */ + return; - if (pm_qos_req) { /*guard against callers passing in null */ - spin_lock_irqsave(&pm_qos_lock, flags); - if (new_value == PM_QOS_DEFAULT_VALUE) - temp = pm_qos_array[pm_qos_req->pm_qos_class]->default_value; - else - temp = new_value; - - if (temp != pm_qos_req->value) { - pending_update = 1; - pm_qos_req->value = temp; - } - spin_unlock_irqrestore(&pm_qos_lock, flags); - if (pending_update) - update_target(pm_qos_req->pm_qos_class); + if (!pm_qos_request_active(pm_qos_req)) { + WARN(1, KERN_ERR "pm_qos_update_request() called for unknown object\n"); + return; } + + o = pm_qos_array[pm_qos_req->pm_qos_class]; + + if (new_value == PM_QOS_DEFAULT_VALUE) + temp = o->default_value; + else + temp = new_value; + + if (temp != pm_qos_req->list.prio) + update_target(o, &pm_qos_req->list, 0, temp); } EXPORT_SYMBOL_GPL(pm_qos_update_request); @@ -280,19 +287,20 @@ EXPORT_SYMBOL_GPL(pm_qos_update_request); */ void pm_qos_remove_request(struct pm_qos_request_list *pm_qos_req) { - unsigned long flags; - int qos_class; + struct pm_qos_object *o; if (pm_qos_req == NULL) return; /* silent return to keep pcm code cleaner */ - qos_class = pm_qos_req->pm_qos_class; - spin_lock_irqsave(&pm_qos_lock, flags); - list_del(&pm_qos_req->list); - kfree(pm_qos_req); - spin_unlock_irqrestore(&pm_qos_lock, flags); - update_target(qos_class); + if (!pm_qos_request_active(pm_qos_req)) { + WARN(1, KERN_ERR "pm_qos_remove_request() called for unknown object\n"); + return; + } + + o = pm_qos_array[pm_qos_req->pm_qos_class]; + update_target(o, &pm_qos_req->list, 1, PM_QOS_DEFAULT_VALUE); + memset(pm_qos_req, 0, sizeof(*pm_qos_req)); } EXPORT_SYMBOL_GPL(pm_qos_remove_request); @@ -340,8 +348,12 @@ static int pm_qos_power_open(struct inode *inode, struct file *filp) pm_qos_class = find_pm_qos_object_by_minor(iminor(inode)); if (pm_qos_class >= 0) { - filp->private_data = (void *) pm_qos_add_request(pm_qos_class, - PM_QOS_DEFAULT_VALUE); + struct pm_qos_request_list *req = kzalloc(GFP_KERNEL, sizeof(*req)); + if (!req) + return -ENOMEM; + + pm_qos_add_request(req, pm_qos_class, PM_QOS_DEFAULT_VALUE); + filp->private_data = req; if (filp->private_data) return 0; @@ -353,8 +365,9 @@ static int pm_qos_power_release(struct inode *inode, struct file *filp) { struct pm_qos_request_list *req; - req = (struct pm_qos_request_list *)filp->private_data; + req = filp->private_data; pm_qos_remove_request(req); + kfree(req); return 0; } diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 5c36ea9d55d2..ca6066a6952e 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -99,9 +99,13 @@ config PM_SLEEP_ADVANCED_DEBUG depends on PM_ADVANCED_DEBUG default n +config SUSPEND_NVS + bool + config SUSPEND bool "Suspend to RAM and standby" depends on PM && ARCH_SUSPEND_POSSIBLE + select SUSPEND_NVS if HAS_IOMEM default y ---help--- Allow the system to enter sleep states in which main memory is @@ -130,13 +134,10 @@ config SUSPEND_FREEZER Turning OFF this setting is NOT recommended! If in doubt, say Y. -config HIBERNATION_NVS - bool - config HIBERNATION bool "Hibernation (aka 'suspend to disk')" depends on PM && SWAP && ARCH_HIBERNATION_POSSIBLE - select HIBERNATION_NVS if HAS_IOMEM + select SUSPEND_NVS if HAS_IOMEM ---help--- Enable the suspend to disk (STD) functionality, which is usually called "hibernation" in user interfaces. STD checkpoints the diff --git a/kernel/power/Makefile b/kernel/power/Makefile index 524e058dcf06..f9063c6b185d 100644 --- a/kernel/power/Makefile +++ b/kernel/power/Makefile @@ -10,6 +10,6 @@ obj-$(CONFIG_SUSPEND) += suspend.o obj-$(CONFIG_PM_TEST_SUSPEND) += suspend_test.o obj-$(CONFIG_HIBERNATION) += hibernate.o snapshot.o swap.o user.o \ block_io.o -obj-$(CONFIG_HIBERNATION_NVS) += hibernate_nvs.o +obj-$(CONFIG_SUSPEND_NVS) += nvs.o obj-$(CONFIG_MAGIC_SYSRQ) += poweroff.o diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index aa9e916da4d5..8dc31e02ae12 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -3,7 +3,7 @@ * * Copyright (c) 2003 Patrick Mochel * Copyright (c) 2003 Open Source Development Lab - * Copyright (c) 2004 Pavel Machek <pavel@suse.cz> + * Copyright (c) 2004 Pavel Machek <pavel@ucw.cz> * Copyright (c) 2009 Rafael J. Wysocki, Novell Inc. * * This file is released under the GPLv2. @@ -277,7 +277,7 @@ static int create_image(int platform_mode) goto Enable_irqs; } - if (hibernation_test(TEST_CORE)) + if (hibernation_test(TEST_CORE) || !pm_check_wakeup_events()) goto Power_up; in_suspend = 1; @@ -288,8 +288,10 @@ static int create_image(int platform_mode) error); /* Restore control flow magically appears here */ restore_processor_state(); - if (!in_suspend) + if (!in_suspend) { + events_check_enabled = false; platform_leave(platform_mode); + } Power_up: sysdev_resume(); @@ -328,7 +330,7 @@ int hibernation_snapshot(int platform_mode) error = platform_begin(platform_mode); if (error) - return error; + goto Close; /* Preallocate image memory before shutting down devices. */ error = hibernate_preallocate_memory(); @@ -511,18 +513,24 @@ int hibernation_platform_enter(void) local_irq_disable(); sysdev_suspend(PMSG_HIBERNATE); + if (!pm_check_wakeup_events()) { + error = -EAGAIN; + goto Power_up; + } + hibernation_ops->enter(); /* We should never get here */ while (1); - /* - * We don't need to reenable the nonboot CPUs or resume consoles, since - * the system is going to be halted anyway. - */ + Power_up: + sysdev_resume(); + local_irq_enable(); + enable_nonboot_cpus(); + Platform_finish: hibernation_ops->finish(); - dpm_suspend_noirq(PMSG_RESTORE); + dpm_resume_noirq(PMSG_RESTORE); Resume_devices: entering_platform_hibernation = false; diff --git a/kernel/power/main.c b/kernel/power/main.c index b58800b21fc0..62b0bc6e4983 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -204,6 +204,60 @@ static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr, power_attr(state); +#ifdef CONFIG_PM_SLEEP +/* + * The 'wakeup_count' attribute, along with the functions defined in + * drivers/base/power/wakeup.c, provides a means by which wakeup events can be + * handled in a non-racy way. + * + * If a wakeup event occurs when the system is in a sleep state, it simply is + * woken up. In turn, if an event that would wake the system up from a sleep + * state occurs when it is undergoing a transition to that sleep state, the + * transition should be aborted. Moreover, if such an event occurs when the + * system is in the working state, an attempt to start a transition to the + * given sleep state should fail during certain period after the detection of + * the event. Using the 'state' attribute alone is not sufficient to satisfy + * these requirements, because a wakeup event may occur exactly when 'state' + * is being written to and may be delivered to user space right before it is + * frozen, so the event will remain only partially processed until the system is + * woken up by another event. In particular, it won't cause the transition to + * a sleep state to be aborted. + * + * This difficulty may be overcome if user space uses 'wakeup_count' before + * writing to 'state'. It first should read from 'wakeup_count' and store + * the read value. Then, after carrying out its own preparations for the system + * transition to a sleep state, it should write the stored value to + * 'wakeup_count'. If that fails, at least one wakeup event has occured since + * 'wakeup_count' was read and 'state' should not be written to. Otherwise, it + * is allowed to write to 'state', but the transition will be aborted if there + * are any wakeup events detected after 'wakeup_count' was written to. + */ + +static ssize_t wakeup_count_show(struct kobject *kobj, + struct kobj_attribute *attr, + char *buf) +{ + unsigned long val; + + return pm_get_wakeup_count(&val) ? sprintf(buf, "%lu\n", val) : -EINTR; +} + +static ssize_t wakeup_count_store(struct kobject *kobj, + struct kobj_attribute *attr, + const char *buf, size_t n) +{ + unsigned long val; + + if (sscanf(buf, "%lu", &val) == 1) { + if (pm_save_wakeup_count(val)) + return n; + } + return -EINVAL; +} + +power_attr(wakeup_count); +#endif /* CONFIG_PM_SLEEP */ + #ifdef CONFIG_PM_TRACE int pm_trace_enabled; @@ -236,6 +290,7 @@ static struct attribute * g[] = { #endif #ifdef CONFIG_PM_SLEEP &pm_async_attr.attr, + &wakeup_count_attr.attr, #ifdef CONFIG_PM_DEBUG &pm_test_attr.attr, #endif diff --git a/kernel/power/hibernate_nvs.c b/kernel/power/nvs.c index fdcad9ed5a7b..1836db60bbb6 100644 --- a/kernel/power/hibernate_nvs.c +++ b/kernel/power/nvs.c @@ -15,7 +15,7 @@ /* * Platforms, like ACPI, may want us to save some memory used by them during - * hibernation and to restore the contents of this memory during the subsequent + * suspend and to restore the contents of this memory during the subsequent * resume. The code below implements a mechanism allowing us to do that. */ @@ -30,7 +30,7 @@ struct nvs_page { static LIST_HEAD(nvs_list); /** - * hibernate_nvs_register - register platform NVS memory region to save + * suspend_nvs_register - register platform NVS memory region to save * @start - physical address of the region * @size - size of the region * @@ -38,7 +38,7 @@ static LIST_HEAD(nvs_list); * things so that the data from page-aligned addresses in this region will * be copied into separate RAM pages. */ -int hibernate_nvs_register(unsigned long start, unsigned long size) +int suspend_nvs_register(unsigned long start, unsigned long size) { struct nvs_page *entry, *next; @@ -68,9 +68,9 @@ int hibernate_nvs_register(unsigned long start, unsigned long size) } /** - * hibernate_nvs_free - free data pages allocated for saving NVS regions + * suspend_nvs_free - free data pages allocated for saving NVS regions */ -void hibernate_nvs_free(void) +void suspend_nvs_free(void) { struct nvs_page *entry; @@ -86,16 +86,16 @@ void hibernate_nvs_free(void) } /** - * hibernate_nvs_alloc - allocate memory necessary for saving NVS regions + * suspend_nvs_alloc - allocate memory necessary for saving NVS regions */ -int hibernate_nvs_alloc(void) +int suspend_nvs_alloc(void) { struct nvs_page *entry; list_for_each_entry(entry, &nvs_list, node) { entry->data = (void *)__get_free_page(GFP_KERNEL); if (!entry->data) { - hibernate_nvs_free(); + suspend_nvs_free(); return -ENOMEM; } } @@ -103,9 +103,9 @@ int hibernate_nvs_alloc(void) } /** - * hibernate_nvs_save - save NVS memory regions + * suspend_nvs_save - save NVS memory regions */ -void hibernate_nvs_save(void) +void suspend_nvs_save(void) { struct nvs_page *entry; @@ -119,12 +119,12 @@ void hibernate_nvs_save(void) } /** - * hibernate_nvs_restore - restore NVS memory regions + * suspend_nvs_restore - restore NVS memory regions * * This function is going to be called with interrupts disabled, so it * cannot iounmap the virtual addresses used to access the NVS region. */ -void hibernate_nvs_restore(void) +void suspend_nvs_restore(void) { struct nvs_page *entry; diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 25ce010e9f8b..f6cd6faf84fd 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -3,7 +3,7 @@ * * This file provides system snapshot/restore functionality for swsusp. * - * Copyright (C) 1998-2005 Pavel Machek <pavel@suse.cz> + * Copyright (C) 1998-2005 Pavel Machek <pavel@ucw.cz> * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl> * * This file is released under the GPLv2. diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 56e7dbb8b996..7335952ee473 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -16,6 +16,12 @@ #include <linux/cpu.h> #include <linux/syscalls.h> #include <linux/gfp.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/list.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <linux/suspend.h> #include "power.h" @@ -130,19 +136,19 @@ static int suspend_enter(suspend_state_t state) if (suspend_ops->prepare) { error = suspend_ops->prepare(); if (error) - return error; + goto Platform_finish; } error = dpm_suspend_noirq(PMSG_SUSPEND); if (error) { printk(KERN_ERR "PM: Some devices failed to power down\n"); - goto Platfrom_finish; + goto Platform_finish; } if (suspend_ops->prepare_late) { error = suspend_ops->prepare_late(); if (error) - goto Power_up_devices; + goto Platform_wake; } if (suspend_test(TEST_PLATFORM)) @@ -157,8 +163,10 @@ static int suspend_enter(suspend_state_t state) error = sysdev_suspend(PMSG_SUSPEND); if (!error) { - if (!suspend_test(TEST_CORE)) + if (!suspend_test(TEST_CORE) && pm_check_wakeup_events()) { error = suspend_ops->enter(state); + events_check_enabled = false; + } sysdev_resume(); } @@ -172,10 +180,9 @@ static int suspend_enter(suspend_state_t state) if (suspend_ops->wake) suspend_ops->wake(); - Power_up_devices: dpm_resume_noirq(PMSG_RESUME); - Platfrom_finish: + Platform_finish: if (suspend_ops->finish) suspend_ops->finish(); diff --git a/kernel/power/swap.c b/kernel/power/swap.c index b0bb21778391..e6a5bdf61a37 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -4,7 +4,7 @@ * This file provides functions for reading the suspend image from * and writing it to a swap partition. * - * Copyright (C) 1998,2001-2005 Pavel Machek <pavel@suse.cz> + * Copyright (C) 1998,2001-2005 Pavel Machek <pavel@ucw.cz> * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl> * * This file is released under the GPLv2. @@ -32,7 +32,7 @@ /* * The swap map is a data structure used for keeping track of each page * written to a swap partition. It consists of many swap_map_page - * structures that contain each an array of MAP_PAGE_SIZE swap entries. + * structures that contain each an array of MAP_PAGE_ENTRIES swap entries. * These structures are stored on the swap and linked together with the * help of the .next_swap member. * @@ -148,7 +148,7 @@ sector_t alloc_swapdev_block(int swap) /** * free_all_swap_pages - free swap pages allocated for saving image data. - * It also frees the extents used to register which swap entres had been + * It also frees the extents used to register which swap entries had been * allocated. */ diff --git a/kernel/printk.c b/kernel/printk.c index 444b770c9595..4ab0164bcf84 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -37,6 +37,8 @@ #include <linux/ratelimit.h> #include <linux/kmsg_dump.h> #include <linux/syslog.h> +#include <linux/cpu.h> +#include <linux/notifier.h> #include <asm/uaccess.h> @@ -985,6 +987,32 @@ void resume_console(void) } /** + * console_cpu_notify - print deferred console messages after CPU hotplug + * @self: notifier struct + * @action: CPU hotplug event + * @hcpu: unused + * + * If printk() is called from a CPU that is not online yet, the messages + * will be spooled but will not show up on the console. This function is + * called when a new CPU comes online (or fails to come up), and ensures + * that any such output gets printed. + */ +static int __cpuinit console_cpu_notify(struct notifier_block *self, + unsigned long action, void *hcpu) +{ + switch (action) { + case CPU_ONLINE: + case CPU_DEAD: + case CPU_DYING: + case CPU_DOWN_FAILED: + case CPU_UP_CANCELED: + acquire_console_sem(); + release_console_sem(); + } + return NOTIFY_OK; +} + +/** * acquire_console_sem - lock the console system for exclusive use. * * Acquires a semaphore which guarantees that the caller has @@ -1371,7 +1399,7 @@ int unregister_console(struct console *console) } EXPORT_SYMBOL(unregister_console); -static int __init disable_boot_consoles(void) +static int __init printk_late_init(void) { struct console *con; @@ -1382,9 +1410,10 @@ static int __init disable_boot_consoles(void) unregister_console(con); } } + hotcpu_notifier(console_cpu_notify, 0); return 0; } -late_initcall(disable_boot_consoles); +late_initcall(printk_late_init); #if defined CONFIG_PRINTK diff --git a/kernel/sched.c b/kernel/sched.c index f8b8996228dd..f52a8801b7a2 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -306,52 +306,6 @@ static int init_task_group_load = INIT_TASK_GROUP_LOAD; */ struct task_group init_task_group; -/* return group to which a task belongs */ -static inline struct task_group *task_group(struct task_struct *p) -{ - struct task_group *tg; - -#ifdef CONFIG_CGROUP_SCHED - tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id), - struct task_group, css); -#else - tg = &init_task_group; -#endif - return tg; -} - -/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */ -static inline void set_task_rq(struct task_struct *p, unsigned int cpu) -{ - /* - * Strictly speaking this rcu_read_lock() is not needed since the - * task_group is tied to the cgroup, which in turn can never go away - * as long as there are tasks attached to it. - * - * However since task_group() uses task_subsys_state() which is an - * rcu_dereference() user, this quiets CONFIG_PROVE_RCU. - */ - rcu_read_lock(); -#ifdef CONFIG_FAIR_GROUP_SCHED - p->se.cfs_rq = task_group(p)->cfs_rq[cpu]; - p->se.parent = task_group(p)->se[cpu]; -#endif - -#ifdef CONFIG_RT_GROUP_SCHED - p->rt.rt_rq = task_group(p)->rt_rq[cpu]; - p->rt.parent = task_group(p)->rt_se[cpu]; -#endif - rcu_read_unlock(); -} - -#else - -static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { } -static inline struct task_group *task_group(struct task_struct *p) -{ - return NULL; -} - #endif /* CONFIG_CGROUP_SCHED */ /* CFS-related fields in a runqueue */ @@ -644,6 +598,49 @@ static inline int cpu_of(struct rq *rq) #define cpu_curr(cpu) (cpu_rq(cpu)->curr) #define raw_rq() (&__raw_get_cpu_var(runqueues)) +#ifdef CONFIG_CGROUP_SCHED + +/* + * Return the group to which this tasks belongs. + * + * We use task_subsys_state_check() and extend the RCU verification + * with lockdep_is_held(&task_rq(p)->lock) because cpu_cgroup_attach() + * holds that lock for each task it moves into the cgroup. Therefore + * by holding that lock, we pin the task to the current cgroup. + */ +static inline struct task_group *task_group(struct task_struct *p) +{ + struct cgroup_subsys_state *css; + + css = task_subsys_state_check(p, cpu_cgroup_subsys_id, + lockdep_is_held(&task_rq(p)->lock)); + return container_of(css, struct task_group, css); +} + +/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */ +static inline void set_task_rq(struct task_struct *p, unsigned int cpu) +{ +#ifdef CONFIG_FAIR_GROUP_SCHED + p->se.cfs_rq = task_group(p)->cfs_rq[cpu]; + p->se.parent = task_group(p)->se[cpu]; +#endif + +#ifdef CONFIG_RT_GROUP_SCHED + p->rt.rt_rq = task_group(p)->rt_rq[cpu]; + p->rt.parent = task_group(p)->rt_se[cpu]; +#endif +} + +#else /* CONFIG_CGROUP_SCHED */ + +static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { } +static inline struct task_group *task_group(struct task_struct *p) +{ + return NULL; +} + +#endif /* CONFIG_CGROUP_SCHED */ + inline void update_rq_clock(struct rq *rq) { if (!rq->skip_clock_update) @@ -1257,6 +1254,12 @@ static void sched_avg_update(struct rq *rq) s64 period = sched_avg_period(); while ((s64)(rq->clock - rq->age_stamp) > period) { + /* + * Inline assembly required to prevent the compiler + * optimising this loop into a divmod call. + * See __iter_div_u64_rem() for another example of this. + */ + asm("" : "+rm" (rq->age_stamp)); rq->age_stamp += period; rq->rt_avg /= 2; } @@ -1660,9 +1663,6 @@ static void update_shares(struct sched_domain *sd) static void update_h_load(long cpu) { - if (root_task_group_empty()) - return; - walk_tg_tree(tg_load_down, tg_nop, (void *)cpu); } @@ -2494,7 +2494,16 @@ void sched_fork(struct task_struct *p, int clone_flags) if (p->sched_class->task_fork) p->sched_class->task_fork(p); + /* + * The child is not yet in the pid-hash so no cgroup attach races, + * and the cgroup is pinned to this child due to cgroup_fork() + * is ran before sched_fork(). + * + * Silence PROVE_RCU. + */ + rcu_read_lock(); set_task_cpu(p, cpu); + rcu_read_unlock(); #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) if (likely(sched_info_on())) @@ -2864,9 +2873,9 @@ unsigned long nr_iowait(void) return sum; } -unsigned long nr_iowait_cpu(void) +unsigned long nr_iowait_cpu(int cpu) { - struct rq *this = this_rq(); + struct rq *this = cpu_rq(cpu); return atomic_read(&this->nr_iowait); } @@ -4465,16 +4474,6 @@ recheck: } if (user) { -#ifdef CONFIG_RT_GROUP_SCHED - /* - * Do not allow realtime tasks into groups that have no runtime - * assigned. - */ - if (rt_bandwidth_enabled() && rt_policy(policy) && - task_group(p)->rt_bandwidth.rt_runtime == 0) - return -EPERM; -#endif - retval = security_task_setscheduler(p, policy, param); if (retval) return retval; @@ -4490,6 +4489,22 @@ recheck: * runqueue lock must be held. */ rq = __task_rq_lock(p); + +#ifdef CONFIG_RT_GROUP_SCHED + if (user) { + /* + * Do not allow realtime tasks into groups that have no runtime + * assigned. + */ + if (rt_bandwidth_enabled() && rt_policy(policy) && + task_group(p)->rt_bandwidth.rt_runtime == 0) { + __task_rq_unlock(rq); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + return -EPERM; + } + } +#endif + /* recheck policy now with rq lock held */ if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { policy = oldpolicy = -1; diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index eed35eded602..a878b5332daa 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1240,6 +1240,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) * effect of the currently running task from the load * of the current CPU: */ + rcu_read_lock(); if (sync) { tg = task_group(current); weight = current->se.load.weight; @@ -1275,6 +1276,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) balanced = this_eff_load <= prev_eff_load; } else balanced = true; + rcu_read_unlock(); /* * If the currently running task will sleep within diff --git a/kernel/signal.c b/kernel/signal.c index 906ae5a1779c..bded65187780 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -637,7 +637,7 @@ static inline bool si_fromuser(const struct siginfo *info) /* * Bad permissions for sending the signal - * - the caller must hold at least the RCU read lock + * - the caller must hold the RCU read lock */ static int check_kill_permission(int sig, struct siginfo *info, struct task_struct *t) @@ -1127,11 +1127,14 @@ struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long /* * send signal info to all the members of a group - * - the caller must hold the RCU read lock at least */ int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p) { - int ret = check_kill_permission(sig, info, p); + int ret; + + rcu_read_lock(); + ret = check_kill_permission(sig, info, p); + rcu_read_unlock(); if (!ret && sig) ret = do_send_sig_info(sig, info, p, true); diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index b3bafd5fc66d..48b2761b5668 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -188,7 +188,7 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev) /* * Setup the next period for devices, which do not have * periodic mode. We read dev->next_event first and add to it - * when the event alrady expired. clockevents_program_event() + * when the event already expired. clockevents_program_event() * sets dev->next_event only when the event is really * programmed to the device. */ diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 1d7b9bc1c034..813993b5fb61 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -154,14 +154,14 @@ static void tick_nohz_update_jiffies(ktime_t now) * Updates the per cpu time idle statistics counters */ static void -update_ts_time_stats(struct tick_sched *ts, ktime_t now, u64 *last_update_time) +update_ts_time_stats(int cpu, struct tick_sched *ts, ktime_t now, u64 *last_update_time) { ktime_t delta; if (ts->idle_active) { delta = ktime_sub(now, ts->idle_entrytime); ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta); - if (nr_iowait_cpu() > 0) + if (nr_iowait_cpu(cpu) > 0) ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta); ts->idle_entrytime = now; } @@ -175,19 +175,19 @@ static void tick_nohz_stop_idle(int cpu, ktime_t now) { struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); - update_ts_time_stats(ts, now, NULL); + update_ts_time_stats(cpu, ts, now, NULL); ts->idle_active = 0; sched_clock_idle_wakeup_event(0); } -static ktime_t tick_nohz_start_idle(struct tick_sched *ts) +static ktime_t tick_nohz_start_idle(int cpu, struct tick_sched *ts) { ktime_t now; now = ktime_get(); - update_ts_time_stats(ts, now, NULL); + update_ts_time_stats(cpu, ts, now, NULL); ts->idle_entrytime = now; ts->idle_active = 1; @@ -216,7 +216,7 @@ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time) if (!tick_nohz_enabled) return -1; - update_ts_time_stats(ts, ktime_get(), last_update_time); + update_ts_time_stats(cpu, ts, ktime_get(), last_update_time); return ktime_to_us(ts->idle_sleeptime); } @@ -242,7 +242,7 @@ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time) if (!tick_nohz_enabled) return -1; - update_ts_time_stats(ts, ktime_get(), last_update_time); + update_ts_time_stats(cpu, ts, ktime_get(), last_update_time); return ktime_to_us(ts->iowait_sleeptime); } @@ -284,7 +284,7 @@ void tick_nohz_stop_sched_tick(int inidle) */ ts->inidle = 1; - now = tick_nohz_start_idle(ts); + now = tick_nohz_start_idle(cpu, ts); /* * If this cpu is offline and it is the one which updates @@ -315,9 +315,6 @@ void tick_nohz_stop_sched_tick(int inidle) goto end; } - if (nohz_ratelimit(cpu)) - goto end; - ts->idle_calls++; /* Read jiffies and the time when jiffies were updated last */ do { @@ -328,7 +325,7 @@ void tick_nohz_stop_sched_tick(int inidle) } while (read_seqretry(&xtime_lock, seq)); if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu) || - arch_needs_cpu(cpu)) { + arch_needs_cpu(cpu) || nohz_ratelimit(cpu)) { next_jiffies = last_jiffies + 1; delta_jiffies = 1; } else { diff --git a/kernel/timer.c b/kernel/timer.c index ee305c8d4e18..efde11e197c4 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -577,6 +577,19 @@ static void __init_timer(struct timer_list *timer, lockdep_init_map(&timer->lockdep_map, name, key, 0); } +void setup_deferrable_timer_on_stack_key(struct timer_list *timer, + const char *name, + struct lock_class_key *key, + void (*function)(unsigned long), + unsigned long data) +{ + timer->function = function; + timer->data = data; + init_timer_on_stack_key(timer, name, key); + timer_set_deferrable(timer); +} +EXPORT_SYMBOL_GPL(setup_deferrable_timer_on_stack_key); + /** * init_timer_key - initialize a timer * @timer: the timer to be initialized diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index ffb1a5b0550e..4215530b490b 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -57,5 +57,8 @@ obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o obj-$(CONFIG_KSYM_TRACER) += trace_ksym.o obj-$(CONFIG_EVENT_TRACING) += power-traces.o +ifeq ($(CONFIG_TRACING),y) +obj-$(CONFIG_KGDB_KDB) += trace_kdb.o +endif libftrace-y := ftrace.o diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 086d36316805..d6736b93dc2a 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -101,10 +101,7 @@ static inline void ftrace_enable_cpu(void) preempt_enable(); } -static cpumask_var_t __read_mostly tracing_buffer_mask; - -#define for_each_tracing_cpu(cpu) \ - for_each_cpu(cpu, tracing_buffer_mask) +cpumask_var_t __read_mostly tracing_buffer_mask; /* * ftrace_dump_on_oops - variable to dump ftrace buffer on oops @@ -1539,11 +1536,6 @@ int trace_vprintk(unsigned long ip, const char *fmt, va_list args) } EXPORT_SYMBOL_GPL(trace_vprintk); -enum trace_file_type { - TRACE_FILE_LAT_FMT = 1, - TRACE_FILE_ANNOTATE = 2, -}; - static void trace_iterator_increment(struct trace_iterator *iter) { /* Don't allow ftrace to trace into the ring buffers */ @@ -1641,7 +1633,7 @@ struct trace_entry *trace_find_next_entry(struct trace_iterator *iter, } /* Find the next real entry, and increment the iterator to the next entry */ -static void *find_next_entry_inc(struct trace_iterator *iter) +void *trace_find_next_entry_inc(struct trace_iterator *iter) { iter->ent = __find_next_entry(iter, &iter->cpu, &iter->lost_events, &iter->ts); @@ -1676,19 +1668,19 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos) return NULL; if (iter->idx < 0) - ent = find_next_entry_inc(iter); + ent = trace_find_next_entry_inc(iter); else ent = iter; while (ent && iter->idx < i) - ent = find_next_entry_inc(iter); + ent = trace_find_next_entry_inc(iter); iter->pos = *pos; return ent; } -static void tracing_iter_reset(struct trace_iterator *iter, int cpu) +void tracing_iter_reset(struct trace_iterator *iter, int cpu) { struct trace_array *tr = iter->tr; struct ring_buffer_event *event; @@ -2049,7 +2041,7 @@ int trace_empty(struct trace_iterator *iter) } /* Called with trace_event_read_lock() held. */ -static enum print_line_t print_trace_line(struct trace_iterator *iter) +enum print_line_t print_trace_line(struct trace_iterator *iter) { enum print_line_t ret; @@ -3211,7 +3203,7 @@ waitagain: trace_event_read_lock(); trace_access_lock(iter->cpu_file); - while (find_next_entry_inc(iter) != NULL) { + while (trace_find_next_entry_inc(iter) != NULL) { enum print_line_t ret; int len = iter->seq.len; @@ -3294,7 +3286,7 @@ tracing_fill_pipe_page(size_t rem, struct trace_iterator *iter) if (ret != TRACE_TYPE_NO_CONSUME) trace_consume(iter); rem -= count; - if (!find_next_entry_inc(iter)) { + if (!trace_find_next_entry_inc(iter)) { rem = 0; iter->ent = NULL; break; @@ -3350,7 +3342,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, if (ret <= 0) goto out_err; - if (!iter->ent && !find_next_entry_inc(iter)) { + if (!iter->ent && !trace_find_next_entry_inc(iter)) { ret = -EFAULT; goto out_err; } @@ -4414,7 +4406,7 @@ static struct notifier_block trace_die_notifier = { */ #define KERN_TRACE KERN_EMERG -static void +void trace_printk_seq(struct trace_seq *s) { /* Probably should print a warning here. */ @@ -4429,6 +4421,13 @@ trace_printk_seq(struct trace_seq *s) trace_seq_init(s); } +void trace_init_global_iter(struct trace_iterator *iter) +{ + iter->tr = &global_trace; + iter->trace = current_trace; + iter->cpu_file = TRACE_PIPE_ALL_CPU; +} + static void __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) { @@ -4454,8 +4453,10 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) if (disable_tracing) ftrace_kill(); + trace_init_global_iter(&iter); + for_each_tracing_cpu(cpu) { - atomic_inc(&global_trace.data[cpu]->disabled); + atomic_inc(&iter.tr->data[cpu]->disabled); } old_userobj = trace_flags & TRACE_ITER_SYM_USEROBJ; @@ -4504,7 +4505,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) iter.iter_flags |= TRACE_FILE_LAT_FMT; iter.pos = -1; - if (find_next_entry_inc(&iter) != NULL) { + if (trace_find_next_entry_inc(&iter) != NULL) { int ret; ret = print_trace_line(&iter); @@ -4526,7 +4527,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) trace_flags |= old_userobj; for_each_tracing_cpu(cpu) { - atomic_dec(&global_trace.data[cpu]->disabled); + atomic_dec(&iter.tr->data[cpu]->disabled); } tracing_on(); } diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 2cd96399463f..0605fc00c176 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -338,6 +338,14 @@ struct trace_entry *tracing_get_trace_entry(struct trace_array *tr, struct trace_entry *trace_find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts); +int trace_empty(struct trace_iterator *iter); + +void *trace_find_next_entry_inc(struct trace_iterator *iter); + +void trace_init_global_iter(struct trace_iterator *iter); + +void tracing_iter_reset(struct trace_iterator *iter, int cpu); + void default_wait_pipe(struct trace_iterator *iter); void poll_wait_pipe(struct trace_iterator *iter); @@ -380,6 +388,15 @@ void tracing_start_sched_switch_record(void); int register_tracer(struct tracer *type); void unregister_tracer(struct tracer *type); int is_tracing_stopped(void); +enum trace_file_type { + TRACE_FILE_LAT_FMT = 1, + TRACE_FILE_ANNOTATE = 2, +}; + +extern cpumask_var_t __read_mostly tracing_buffer_mask; + +#define for_each_tracing_cpu(cpu) \ + for_each_cpu(cpu, tracing_buffer_mask) extern int process_new_ksym_entry(char *ksymname, int op, unsigned long addr); @@ -471,6 +488,8 @@ trace_array_vprintk(struct trace_array *tr, unsigned long ip, const char *fmt, va_list args); int trace_array_printk(struct trace_array *tr, unsigned long ip, const char *fmt, ...); +void trace_printk_seq(struct trace_seq *s); +enum print_line_t print_trace_line(struct trace_iterator *iter); extern unsigned long trace_flags; diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index e6f65887842c..8a2b73f7c068 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -96,7 +96,9 @@ int perf_trace_init(struct perf_event *p_event) mutex_lock(&event_mutex); list_for_each_entry(tp_event, &ftrace_events, list) { if (tp_event->event.type == event_id && - tp_event->class && tp_event->class->perf_probe && + tp_event->class && + (tp_event->class->perf_probe || + tp_event->class->reg) && try_module_get(tp_event->mod)) { ret = perf_trace_event_init(tp_event, p_event); break; diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c new file mode 100644 index 000000000000..7b8ecd751d93 --- /dev/null +++ b/kernel/trace/trace_kdb.c @@ -0,0 +1,136 @@ +/* + * kdb helper for dumping the ftrace buffer + * + * Copyright (C) 2010 Jason Wessel <jason.wessel@windriver.com> + * + * ftrace_dump_buf based on ftrace_dump: + * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com> + * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com> + * + */ +#include <linux/init.h> +#include <linux/kgdb.h> +#include <linux/kdb.h> +#include <linux/ftrace.h> + +#include "../debug/kdb/kdb_private.h" +#include "trace.h" +#include "trace_output.h" + +static void ftrace_dump_buf(int skip_lines, long cpu_file) +{ + /* use static because iter can be a bit big for the stack */ + static struct trace_iterator iter; + unsigned int old_userobj; + int cnt = 0, cpu; + + trace_init_global_iter(&iter); + + for_each_tracing_cpu(cpu) { + atomic_inc(&iter.tr->data[cpu]->disabled); + } + + old_userobj = trace_flags; + + /* don't look at user memory in panic mode */ + trace_flags &= ~TRACE_ITER_SYM_USEROBJ; + + kdb_printf("Dumping ftrace buffer:\n"); + + /* reset all but tr, trace, and overruns */ + memset(&iter.seq, 0, + sizeof(struct trace_iterator) - + offsetof(struct trace_iterator, seq)); + iter.iter_flags |= TRACE_FILE_LAT_FMT; + iter.pos = -1; + + if (cpu_file == TRACE_PIPE_ALL_CPU) { + for_each_tracing_cpu(cpu) { + iter.buffer_iter[cpu] = + ring_buffer_read_prepare(iter.tr->buffer, cpu); + ring_buffer_read_start(iter.buffer_iter[cpu]); + tracing_iter_reset(&iter, cpu); + } + } else { + iter.cpu_file = cpu_file; + iter.buffer_iter[cpu_file] = + ring_buffer_read_prepare(iter.tr->buffer, cpu_file); + ring_buffer_read_start(iter.buffer_iter[cpu_file]); + tracing_iter_reset(&iter, cpu_file); + } + if (!trace_empty(&iter)) + trace_find_next_entry_inc(&iter); + while (!trace_empty(&iter)) { + if (!cnt) + kdb_printf("---------------------------------\n"); + cnt++; + + if (trace_find_next_entry_inc(&iter) != NULL && !skip_lines) + print_trace_line(&iter); + if (!skip_lines) + trace_printk_seq(&iter.seq); + else + skip_lines--; + if (KDB_FLAG(CMD_INTERRUPT)) + goto out; + } + + if (!cnt) + kdb_printf(" (ftrace buffer empty)\n"); + else + kdb_printf("---------------------------------\n"); + +out: + trace_flags = old_userobj; + + for_each_tracing_cpu(cpu) { + atomic_dec(&iter.tr->data[cpu]->disabled); + } + + for_each_tracing_cpu(cpu) + if (iter.buffer_iter[cpu]) + ring_buffer_read_finish(iter.buffer_iter[cpu]); +} + +/* + * kdb_ftdump - Dump the ftrace log buffer + */ +static int kdb_ftdump(int argc, const char **argv) +{ + int skip_lines = 0; + long cpu_file; + char *cp; + + if (argc > 2) + return KDB_ARGCOUNT; + + if (argc) { + skip_lines = simple_strtol(argv[1], &cp, 0); + if (*cp) + skip_lines = 0; + } + + if (argc == 2) { + cpu_file = simple_strtol(argv[2], &cp, 0); + if (*cp || cpu_file >= NR_CPUS || cpu_file < 0 || + !cpu_online(cpu_file)) + return KDB_BADINT; + } else { + cpu_file = TRACE_PIPE_ALL_CPU; + } + + kdb_trap_printk++; + ftrace_dump_buf(skip_lines, cpu_file); + kdb_trap_printk--; + + return 0; +} + +static __init int kdb_ftrace_register(void) +{ + kdb_register_repeat("ftdump", kdb_ftdump, "[skip_#lines] [cpu]", + "Dump ftrace log", 0, KDB_REPEAT_NONE); + return 0; +} + +late_initcall(kdb_ftrace_register); diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index b2d70d38dff4..25915832291a 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -9,6 +9,7 @@ #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/user_namespace.h> +#include <linux/highuid.h> #include <linux/cred.h> /* @@ -82,3 +83,46 @@ void free_user_ns(struct kref *kref) schedule_work(&ns->destroyer); } EXPORT_SYMBOL(free_user_ns); + +uid_t user_ns_map_uid(struct user_namespace *to, const struct cred *cred, uid_t uid) +{ + struct user_namespace *tmp; + + if (likely(to == cred->user->user_ns)) + return uid; + + + /* Is cred->user the creator of the target user_ns + * or the creator of one of it's parents? + */ + for ( tmp = to; tmp != &init_user_ns; + tmp = tmp->creator->user_ns ) { + if (cred->user == tmp->creator) { + return (uid_t)0; + } + } + + /* No useful relationship so no mapping */ + return overflowuid; +} + +gid_t user_ns_map_gid(struct user_namespace *to, const struct cred *cred, gid_t gid) +{ + struct user_namespace *tmp; + + if (likely(to == cred->user->user_ns)) + return gid; + + /* Is cred->user the creator of the target user_ns + * or the creator of one of it's parents? + */ + for ( tmp = to; tmp != &init_user_ns; + tmp = tmp->creator->user_ns ) { + if (cred->user == tmp->creator) { + return (gid_t)0; + } + } + + /* No useful relationship so no mapping */ + return overflowgid; +} |