diff options
author | Jiri Kosina <jkosina@suse.cz> | 2012-10-28 19:28:52 +0100 |
---|---|---|
committer | Jiri Kosina <jkosina@suse.cz> | 2012-10-28 19:29:19 +0100 |
commit | 3bd7bf1f0fe14f591c089ae61bbfa9bd356f178a (patch) | |
tree | 0058693cc9e70b7461dae551f8a19aff2efd13ca /kernel | |
parent | f16f84937d769c893492160b1a8c3672e3992beb (diff) | |
parent | e657e078d3dfa9f96976db7a2b5fd7d7c9f1f1a6 (diff) | |
download | linux-3bd7bf1f0fe14f591c089ae61bbfa9bd356f178a.tar.bz2 |
Merge branch 'master' into for-next
Sync up with Linus' tree to be able to apply Cesar's patch
against newer version of the code.
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Diffstat (limited to 'kernel')
98 files changed, 6499 insertions, 4151 deletions
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks index 2251882daf53..44511d100eaa 100644 --- a/kernel/Kconfig.locks +++ b/kernel/Kconfig.locks @@ -87,6 +87,9 @@ config ARCH_INLINE_WRITE_UNLOCK_IRQ config ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE bool +config UNINLINE_SPIN_UNLOCK + bool + # # lock_* functions are inlined when: # - DEBUG_SPINLOCK=n and GENERIC_LOCKBREAK=n and ARCH_INLINE_*LOCK=y @@ -103,100 +106,120 @@ config ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE # - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y # +if !DEBUG_SPINLOCK + config INLINE_SPIN_TRYLOCK - def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_TRYLOCK + def_bool y + depends on ARCH_INLINE_SPIN_TRYLOCK config INLINE_SPIN_TRYLOCK_BH - def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_TRYLOCK_BH + def_bool y + depends on ARCH_INLINE_SPIN_TRYLOCK_BH config INLINE_SPIN_LOCK - def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK config INLINE_SPIN_LOCK_BH - def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ - ARCH_INLINE_SPIN_LOCK_BH + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK_BH config INLINE_SPIN_LOCK_IRQ - def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ - ARCH_INLINE_SPIN_LOCK_IRQ + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK_IRQ config INLINE_SPIN_LOCK_IRQSAVE - def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ - ARCH_INLINE_SPIN_LOCK_IRQSAVE - -config UNINLINE_SPIN_UNLOCK - bool + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_SPIN_LOCK_IRQSAVE config INLINE_SPIN_UNLOCK_BH - def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_UNLOCK_BH + def_bool y + depends on ARCH_INLINE_SPIN_UNLOCK_BH config INLINE_SPIN_UNLOCK_IRQ - def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_SPIN_UNLOCK_BH) + def_bool y + depends on !PREEMPT || ARCH_INLINE_SPIN_UNLOCK_BH config INLINE_SPIN_UNLOCK_IRQRESTORE - def_bool !DEBUG_SPINLOCK && ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE + def_bool y + depends on ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE config INLINE_READ_TRYLOCK - def_bool !DEBUG_SPINLOCK && ARCH_INLINE_READ_TRYLOCK + def_bool y + depends on ARCH_INLINE_READ_TRYLOCK config INLINE_READ_LOCK - def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK config INLINE_READ_LOCK_BH - def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ - ARCH_INLINE_READ_LOCK_BH + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK_BH config INLINE_READ_LOCK_IRQ - def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ - ARCH_INLINE_READ_LOCK_IRQ + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK_IRQ config INLINE_READ_LOCK_IRQSAVE - def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ - ARCH_INLINE_READ_LOCK_IRQSAVE + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_READ_LOCK_IRQSAVE config INLINE_READ_UNLOCK - def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_READ_UNLOCK) + def_bool y + depends on !PREEMPT || ARCH_INLINE_READ_UNLOCK config INLINE_READ_UNLOCK_BH - def_bool !DEBUG_SPINLOCK && ARCH_INLINE_READ_UNLOCK_BH + def_bool y + depends on ARCH_INLINE_READ_UNLOCK_BH config INLINE_READ_UNLOCK_IRQ - def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_READ_UNLOCK_BH) + def_bool y + depends on !PREEMPT || ARCH_INLINE_READ_UNLOCK_BH config INLINE_READ_UNLOCK_IRQRESTORE - def_bool !DEBUG_SPINLOCK && ARCH_INLINE_READ_UNLOCK_IRQRESTORE + def_bool y + depends on ARCH_INLINE_READ_UNLOCK_IRQRESTORE config INLINE_WRITE_TRYLOCK - def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_TRYLOCK + def_bool y + depends on ARCH_INLINE_WRITE_TRYLOCK config INLINE_WRITE_LOCK - def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK config INLINE_WRITE_LOCK_BH - def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ - ARCH_INLINE_WRITE_LOCK_BH + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK_BH config INLINE_WRITE_LOCK_IRQ - def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ - ARCH_INLINE_WRITE_LOCK_IRQ + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK_IRQ config INLINE_WRITE_LOCK_IRQSAVE - def_bool !DEBUG_SPINLOCK && !GENERIC_LOCKBREAK && \ - ARCH_INLINE_WRITE_LOCK_IRQSAVE + def_bool y + depends on !GENERIC_LOCKBREAK && ARCH_INLINE_WRITE_LOCK_IRQSAVE config INLINE_WRITE_UNLOCK - def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_WRITE_UNLOCK) + def_bool y + depends on !PREEMPT || ARCH_INLINE_WRITE_UNLOCK config INLINE_WRITE_UNLOCK_BH - def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_UNLOCK_BH + def_bool y + depends on ARCH_INLINE_WRITE_UNLOCK_BH config INLINE_WRITE_UNLOCK_IRQ - def_bool !DEBUG_SPINLOCK && (!PREEMPT || ARCH_INLINE_WRITE_UNLOCK_BH) + def_bool y + depends on !PREEMPT || ARCH_INLINE_WRITE_UNLOCK_BH config INLINE_WRITE_UNLOCK_IRQRESTORE - def_bool !DEBUG_SPINLOCK && ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE + def_bool y + depends on ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE + +endif config MUTEX_SPIN_ON_OWNER - def_bool SMP && !DEBUG_MUTEXES + def_bool y + depends on SMP && !DEBUG_MUTEXES diff --git a/kernel/Makefile b/kernel/Makefile index c0cc67ad764c..86e3285ae7e5 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -10,7 +10,7 @@ obj-y = fork.o exec_domain.o panic.o printk.o \ kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \ hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ notifier.o ksysfs.o cred.o \ - async.o range.o groups.o lglock.o + async.o range.o groups.o lglock.o smpboot.o ifdef CONFIG_FUNCTION_TRACER # Do not trace debug files and internal ftrace files @@ -46,7 +46,6 @@ obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o obj-$(CONFIG_SMP) += smp.o -obj-$(CONFIG_SMP) += smpboot.o ifneq ($(CONFIG_SMP),y) obj-y += up.o endif @@ -55,6 +54,7 @@ obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o obj-$(CONFIG_PROVE_LOCKING) += spinlock.o obj-$(CONFIG_UID16) += uid16.o obj-$(CONFIG_MODULES) += module.o +obj-$(CONFIG_MODULE_SIG) += module_signing.o modsign_pubkey.o obj-$(CONFIG_KALLSYMS) += kallsyms.o obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o obj-$(CONFIG_KEXEC) += kexec.o @@ -98,7 +98,7 @@ obj-$(CONFIG_COMPAT_BINFMT_ELF) += elfcore.o obj-$(CONFIG_BINFMT_ELF_FDPIC) += elfcore.o obj-$(CONFIG_FUNCTION_TRACER) += trace/ obj-$(CONFIG_TRACING) += trace/ -obj-$(CONFIG_X86_DS) += trace/ +obj-$(CONFIG_TRACE_CLOCK) += trace/ obj-$(CONFIG_RING_BUFFER) += trace/ obj-$(CONFIG_TRACEPOINTS) += trace/ obj-$(CONFIG_IRQ_WORK) += irq_work.o @@ -131,3 +131,77 @@ quiet_cmd_timeconst = TIMEC $@ targets += timeconst.h $(obj)/timeconst.h: $(src)/timeconst.pl FORCE $(call if_changed,timeconst) + +ifeq ($(CONFIG_MODULE_SIG),y) +# +# Pull the signing certificate and any extra certificates into the kernel +# +extra_certificates: + touch $@ + +kernel/modsign_pubkey.o: signing_key.x509 extra_certificates + +############################################################################### +# +# If module signing is requested, say by allyesconfig, but a key has not been +# supplied, then one will need to be generated to make sure the build does not +# fail and that the kernel may be used afterwards. +# +############################################################################### +sign_key_with_hash := +ifeq ($(CONFIG_MODULE_SIG_SHA1),y) +sign_key_with_hash := -sha1 +endif +ifeq ($(CONFIG_MODULE_SIG_SHA224),y) +sign_key_with_hash := -sha224 +endif +ifeq ($(CONFIG_MODULE_SIG_SHA256),y) +sign_key_with_hash := -sha256 +endif +ifeq ($(CONFIG_MODULE_SIG_SHA384),y) +sign_key_with_hash := -sha384 +endif +ifeq ($(CONFIG_MODULE_SIG_SHA512),y) +sign_key_with_hash := -sha512 +endif +ifeq ($(sign_key_with_hash),) +$(error Could not determine digest type to use from kernel config) +endif + +signing_key.priv signing_key.x509: x509.genkey + @echo "###" + @echo "### Now generating an X.509 key pair to be used for signing modules." + @echo "###" + @echo "### If this takes a long time, you might wish to run rngd in the" + @echo "### background to keep the supply of entropy topped up. It" + @echo "### needs to be run as root, and uses a hardware random" + @echo "### number generator if one is available." + @echo "###" + openssl req -new -nodes -utf8 $(sign_key_with_hash) -days 36500 -batch \ + -x509 -config x509.genkey \ + -outform DER -out signing_key.x509 \ + -keyout signing_key.priv + @echo "###" + @echo "### Key pair generated." + @echo "###" + +x509.genkey: + @echo Generating X.509 key generation config + @echo >x509.genkey "[ req ]" + @echo >>x509.genkey "default_bits = 4096" + @echo >>x509.genkey "distinguished_name = req_distinguished_name" + @echo >>x509.genkey "prompt = no" + @echo >>x509.genkey "string_mask = utf8only" + @echo >>x509.genkey "x509_extensions = myexts" + @echo >>x509.genkey + @echo >>x509.genkey "[ req_distinguished_name ]" + @echo >>x509.genkey "O = Magrathea" + @echo >>x509.genkey "CN = Glacier signing key" + @echo >>x509.genkey "emailAddress = slartibartfast@magrathea.h2g2" + @echo >>x509.genkey + @echo >>x509.genkey "[ myexts ]" + @echo >>x509.genkey "basicConstraints=critical,CA:FALSE" + @echo >>x509.genkey "keyUsage=digitalSignature" + @echo >>x509.genkey "subjectKeyIdentifier=hash" + @echo >>x509.genkey "authorityKeyIdentifier=keyid" +endif diff --git a/kernel/acct.c b/kernel/acct.c index 02e6167a53b0..051e071a06e7 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -193,7 +193,7 @@ static void acct_file_reopen(struct bsd_acct_struct *acct, struct file *file, } } -static int acct_on(char *name) +static int acct_on(struct filename *pathname) { struct file *file; struct vfsmount *mnt; @@ -201,7 +201,7 @@ static int acct_on(char *name) struct bsd_acct_struct *acct = NULL; /* Difference from BSD - they don't do O_APPEND */ - file = filp_open(name, O_WRONLY|O_APPEND|O_LARGEFILE, 0); + file = file_open_name(pathname, O_WRONLY|O_APPEND|O_LARGEFILE, 0); if (IS_ERR(file)) return PTR_ERR(file); @@ -260,7 +260,7 @@ SYSCALL_DEFINE1(acct, const char __user *, name) return -EPERM; if (name) { - char *tmp = getname(name); + struct filename *tmp = getname(name); if (IS_ERR(tmp)) return (PTR_ERR(tmp)); error = acct_on(tmp); @@ -507,8 +507,8 @@ static void do_acct_process(struct bsd_acct_struct *acct, do_div(elapsed, AHZ); ac.ac_btime = get_seconds() - elapsed; /* we really need to bite the bullet and change layout */ - ac.ac_uid = orig_cred->uid; - ac.ac_gid = orig_cred->gid; + ac.ac_uid = from_kuid_munged(file->f_cred->user_ns, orig_cred->uid); + ac.ac_gid = from_kgid_munged(file->f_cred->user_ns, orig_cred->gid); #if ACCT_VERSION==2 ac.ac_ahz = AHZ; #endif diff --git a/kernel/audit.c b/kernel/audit.c index ea3b7b6191c7..40414e9143db 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -61,6 +61,7 @@ #include <linux/netlink.h> #include <linux/freezer.h> #include <linux/tty.h> +#include <linux/pid_namespace.h> #include "audit.h" @@ -87,11 +88,11 @@ static int audit_failure = AUDIT_FAIL_PRINTK; /* * If audit records are to be written to the netlink socket, audit_pid - * contains the pid of the auditd process and audit_nlk_pid contains - * the pid to use to send netlink messages to that process. + * contains the pid of the auditd process and audit_nlk_portid contains + * the portid to use to send netlink messages to that process. */ int audit_pid; -static int audit_nlk_pid; +static int audit_nlk_portid; /* If audit_rate_limit is non-zero, limit the rate of sending audit records * to that number per second. This prevents DoS attacks, but results in @@ -104,7 +105,7 @@ static int audit_backlog_wait_time = 60 * HZ; static int audit_backlog_wait_overflow = 0; /* The identity of the user shutting down the audit system. */ -uid_t audit_sig_uid = -1; +kuid_t audit_sig_uid = INVALID_UID; pid_t audit_sig_pid = -1; u32 audit_sig_sid = 0; @@ -264,7 +265,7 @@ void audit_log_lost(const char *message) } static int audit_log_config_change(char *function_name, int new, int old, - uid_t loginuid, u32 sessionid, u32 sid, + kuid_t loginuid, u32 sessionid, u32 sid, int allow_changes) { struct audit_buffer *ab; @@ -272,7 +273,7 @@ static int audit_log_config_change(char *function_name, int new, int old, ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE); audit_log_format(ab, "%s=%d old=%d auid=%u ses=%u", function_name, new, - old, loginuid, sessionid); + old, from_kuid(&init_user_ns, loginuid), sessionid); if (sid) { char *ctx = NULL; u32 len; @@ -292,7 +293,7 @@ static int audit_log_config_change(char *function_name, int new, int old, } static int audit_do_config_change(char *function_name, int *to_change, - int new, uid_t loginuid, u32 sessionid, + int new, kuid_t loginuid, u32 sessionid, u32 sid) { int allow_changes, rc = 0, old = *to_change; @@ -319,21 +320,21 @@ static int audit_do_config_change(char *function_name, int *to_change, return rc; } -static int audit_set_rate_limit(int limit, uid_t loginuid, u32 sessionid, +static int audit_set_rate_limit(int limit, kuid_t loginuid, u32 sessionid, u32 sid) { return audit_do_config_change("audit_rate_limit", &audit_rate_limit, limit, loginuid, sessionid, sid); } -static int audit_set_backlog_limit(int limit, uid_t loginuid, u32 sessionid, +static int audit_set_backlog_limit(int limit, kuid_t loginuid, u32 sessionid, u32 sid) { return audit_do_config_change("audit_backlog_limit", &audit_backlog_limit, limit, loginuid, sessionid, sid); } -static int audit_set_enabled(int state, uid_t loginuid, u32 sessionid, u32 sid) +static int audit_set_enabled(int state, kuid_t loginuid, u32 sessionid, u32 sid) { int rc; if (state < AUDIT_OFF || state > AUDIT_LOCKED) @@ -348,7 +349,7 @@ static int audit_set_enabled(int state, uid_t loginuid, u32 sessionid, u32 sid) return rc; } -static int audit_set_failure(int state, uid_t loginuid, u32 sessionid, u32 sid) +static int audit_set_failure(int state, kuid_t loginuid, u32 sessionid, u32 sid) { if (state != AUDIT_FAIL_SILENT && state != AUDIT_FAIL_PRINTK @@ -401,7 +402,7 @@ static void kauditd_send_skb(struct sk_buff *skb) int err; /* take a reference in case we can't send it and we want to hold it */ skb_get(skb); - err = netlink_unicast(audit_sock, skb, audit_nlk_pid, 0); + err = netlink_unicast(audit_sock, skb, audit_nlk_portid, 0); if (err < 0) { BUG_ON(err != -ECONNREFUSED); /* Shouldn't happen */ printk(KERN_ERR "audit: *NO* daemon at audit_pid=%d\n", audit_pid); @@ -467,24 +468,6 @@ static int kauditd_thread(void *dummy) return 0; } -static int audit_prepare_user_tty(pid_t pid, uid_t loginuid, u32 sessionid) -{ - struct task_struct *tsk; - int err; - - rcu_read_lock(); - tsk = find_task_by_vpid(pid); - if (!tsk) { - rcu_read_unlock(); - return -ESRCH; - } - get_task_struct(tsk); - rcu_read_unlock(); - err = tty_audit_push_task(tsk, loginuid, sessionid); - put_task_struct(tsk); - return err; -} - int audit_send_list(void *_dest) { struct audit_netlink_list *dest = _dest; @@ -588,6 +571,11 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type) { int err = 0; + /* Only support the initial namespaces for now. */ + if ((current_user_ns() != &init_user_ns) || + (task_active_pid_ns(current) != &init_pid_ns)) + return -EPERM; + switch (msg_type) { case AUDIT_GET: case AUDIT_LIST: @@ -619,8 +607,7 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type) } static int audit_log_common_recv_msg(struct audit_buffer **ab, u16 msg_type, - u32 pid, u32 uid, uid_t auid, u32 ses, - u32 sid) + kuid_t auid, u32 ses, u32 sid) { int rc = 0; char *ctx = NULL; @@ -633,7 +620,9 @@ static int audit_log_common_recv_msg(struct audit_buffer **ab, u16 msg_type, *ab = audit_log_start(NULL, GFP_KERNEL, msg_type); audit_log_format(*ab, "pid=%d uid=%u auid=%u ses=%u", - pid, uid, auid, ses); + task_tgid_vnr(current), + from_kuid(&init_user_ns, current_uid()), + from_kuid(&init_user_ns, auid), ses); if (sid) { rc = security_secid_to_secctx(sid, &ctx, &len); if (rc) @@ -649,13 +638,13 @@ static int audit_log_common_recv_msg(struct audit_buffer **ab, u16 msg_type, static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) { - u32 uid, pid, seq, sid; + u32 seq, sid; void *data; struct audit_status *status_get, status_set; int err; struct audit_buffer *ab; u16 msg_type = nlh->nlmsg_type; - uid_t loginuid; /* loginuid of sender */ + kuid_t loginuid; /* loginuid of sender */ u32 sessionid; struct audit_sig_info *sig_data; char *ctx = NULL; @@ -675,8 +664,6 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) return err; } - pid = NETLINK_CREDS(skb)->pid; - uid = NETLINK_CREDS(skb)->uid; loginuid = audit_get_loginuid(current); sessionid = audit_get_sessionid(current); security_task_getsecid(current, &sid); @@ -692,7 +679,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) status_set.backlog_limit = audit_backlog_limit; status_set.lost = atomic_read(&audit_lost); status_set.backlog = skb_queue_len(&audit_skb_queue); - audit_send_reply(NETLINK_CB(skb).pid, seq, AUDIT_GET, 0, 0, + audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_GET, 0, 0, &status_set, sizeof(status_set)); break; case AUDIT_SET: @@ -720,7 +707,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) sessionid, sid, 1); audit_pid = new_pid; - audit_nlk_pid = NETLINK_CB(skb).pid; + audit_nlk_portid = NETLINK_CB(skb).portid; } if (status_get->mask & AUDIT_STATUS_RATE_LIMIT) { err = audit_set_rate_limit(status_get->rate_limit, @@ -738,16 +725,16 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (!audit_enabled && msg_type != AUDIT_USER_AVC) return 0; - err = audit_filter_user(&NETLINK_CB(skb)); + err = audit_filter_user(); if (err == 1) { err = 0; if (msg_type == AUDIT_USER_TTY) { - err = audit_prepare_user_tty(pid, loginuid, + err = tty_audit_push_task(current, loginuid, sessionid); if (err) break; } - audit_log_common_recv_msg(&ab, msg_type, pid, uid, + audit_log_common_recv_msg(&ab, msg_type, loginuid, sessionid, sid); if (msg_type != AUDIT_USER_TTY) @@ -763,7 +750,7 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) size--; audit_log_n_untrustedstring(ab, data, size); } - audit_set_pid(ab, pid); + audit_set_pid(ab, NETLINK_CB(skb).portid); audit_log_end(ab); } break; @@ -772,8 +759,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (nlmsg_len(nlh) < sizeof(struct audit_rule)) return -EINVAL; if (audit_enabled == AUDIT_LOCKED) { - audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE, pid, - uid, loginuid, sessionid, sid); + audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE, + loginuid, sessionid, sid); audit_log_format(ab, " audit_enabled=%d res=0", audit_enabled); @@ -782,8 +769,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) } /* fallthrough */ case AUDIT_LIST: - err = audit_receive_filter(msg_type, NETLINK_CB(skb).pid, - uid, seq, data, nlmsg_len(nlh), + err = audit_receive_filter(msg_type, NETLINK_CB(skb).portid, + seq, data, nlmsg_len(nlh), loginuid, sessionid, sid); break; case AUDIT_ADD_RULE: @@ -791,8 +778,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (nlmsg_len(nlh) < sizeof(struct audit_rule_data)) return -EINVAL; if (audit_enabled == AUDIT_LOCKED) { - audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE, pid, - uid, loginuid, sessionid, sid); + audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE, + loginuid, sessionid, sid); audit_log_format(ab, " audit_enabled=%d res=0", audit_enabled); @@ -801,15 +788,15 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) } /* fallthrough */ case AUDIT_LIST_RULES: - err = audit_receive_filter(msg_type, NETLINK_CB(skb).pid, - uid, seq, data, nlmsg_len(nlh), + err = audit_receive_filter(msg_type, NETLINK_CB(skb).portid, + seq, data, nlmsg_len(nlh), loginuid, sessionid, sid); break; case AUDIT_TRIM: audit_trim_trees(); - audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE, pid, - uid, loginuid, sessionid, sid); + audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE, + loginuid, sessionid, sid); audit_log_format(ab, " op=trim res=1"); audit_log_end(ab); @@ -840,8 +827,8 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) /* OK, here comes... */ err = audit_tag_tree(old, new); - audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE, pid, - uid, loginuid, sessionid, sid); + audit_log_common_recv_msg(&ab, AUDIT_CONFIG_CHANGE, + loginuid, sessionid, sid); audit_log_format(ab, " op=make_equiv old="); audit_log_untrustedstring(ab, old); @@ -866,53 +853,41 @@ static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh) security_release_secctx(ctx, len); return -ENOMEM; } - sig_data->uid = audit_sig_uid; + sig_data->uid = from_kuid(&init_user_ns, audit_sig_uid); sig_data->pid = audit_sig_pid; if (audit_sig_sid) { memcpy(sig_data->ctx, ctx, len); security_release_secctx(ctx, len); } - audit_send_reply(NETLINK_CB(skb).pid, seq, AUDIT_SIGNAL_INFO, + audit_send_reply(NETLINK_CB(skb).portid, seq, AUDIT_SIGNAL_INFO, 0, 0, sig_data, sizeof(*sig_data) + len); kfree(sig_data); break; case AUDIT_TTY_GET: { struct audit_tty_status s; - struct task_struct *tsk; - unsigned long flags; - - rcu_read_lock(); - tsk = find_task_by_vpid(pid); - if (tsk && lock_task_sighand(tsk, &flags)) { - s.enabled = tsk->signal->audit_tty != 0; - unlock_task_sighand(tsk, &flags); - } else - err = -ESRCH; - rcu_read_unlock(); - - if (!err) - audit_send_reply(NETLINK_CB(skb).pid, seq, - AUDIT_TTY_GET, 0, 0, &s, sizeof(s)); + struct task_struct *tsk = current; + + spin_lock_irq(&tsk->sighand->siglock); + s.enabled = tsk->signal->audit_tty != 0; + spin_unlock_irq(&tsk->sighand->siglock); + + audit_send_reply(NETLINK_CB(skb).portid, seq, + AUDIT_TTY_GET, 0, 0, &s, sizeof(s)); break; } case AUDIT_TTY_SET: { struct audit_tty_status *s; - struct task_struct *tsk; - unsigned long flags; + struct task_struct *tsk = current; if (nlh->nlmsg_len < sizeof(struct audit_tty_status)) return -EINVAL; s = data; if (s->enabled != 0 && s->enabled != 1) return -EINVAL; - rcu_read_lock(); - tsk = find_task_by_vpid(pid); - if (tsk && lock_task_sighand(tsk, &flags)) { - tsk->signal->audit_tty = s->enabled != 0; - unlock_task_sighand(tsk, &flags); - } else - err = -ESRCH; - rcu_read_unlock(); + + spin_lock_irq(&tsk->sighand->siglock); + tsk->signal->audit_tty = s->enabled != 0; + spin_unlock_irq(&tsk->sighand->siglock); break; } default: @@ -971,8 +946,7 @@ static int __init audit_init(void) printk(KERN_INFO "audit: initializing netlink socket (%s)\n", audit_default ? "enabled" : "disabled"); - audit_sock = netlink_kernel_create(&init_net, NETLINK_AUDIT, - THIS_MODULE, &cfg); + audit_sock = netlink_kernel_create(&init_net, NETLINK_AUDIT, &cfg); if (!audit_sock) audit_panic("cannot initialize netlink socket"); else @@ -1466,6 +1440,8 @@ void audit_log_link_denied(const char *operation, struct path *link) ab = audit_log_start(current->audit_context, GFP_KERNEL, AUDIT_ANOM_LINK); + if (!ab) + return; audit_log_format(ab, "op=%s action=denied", operation); audit_log_format(ab, " pid=%d comm=", current->pid); audit_log_untrustedstring(ab, current->comm); diff --git a/kernel/audit.h b/kernel/audit.h index 816766803371..d51cba868e1b 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -74,10 +74,15 @@ static inline int audit_hash_ino(u32 ino) return (ino & (AUDIT_INODE_BUCKETS-1)); } +/* Indicates that audit should log the full pathname. */ +#define AUDIT_NAME_FULL -1 + extern int audit_match_class(int class, unsigned syscall); extern int audit_comparator(const u32 left, const u32 op, const u32 right); -extern int audit_compare_dname_path(const char *dname, const char *path, - int *dirlen); +extern int audit_uid_comparator(kuid_t left, u32 op, kuid_t right); +extern int audit_gid_comparator(kgid_t left, u32 op, kgid_t right); +extern int parent_len(const char *path); +extern int audit_compare_dname_path(const char *dname, const char *path, int plen); extern struct sk_buff * audit_make_reply(int pid, int seq, int type, int done, int multi, const void *payload, int size); @@ -144,7 +149,7 @@ extern void audit_kill_trees(struct list_head *); extern char *audit_unpack_string(void **, size_t *, size_t); extern pid_t audit_sig_pid; -extern uid_t audit_sig_uid; +extern kuid_t audit_sig_uid; extern u32 audit_sig_sid; #ifdef CONFIG_AUDITSYSCALL diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 3823281401b5..9a9ae6e3d290 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -241,7 +241,7 @@ static void audit_watch_log_rule_change(struct audit_krule *r, struct audit_watc struct audit_buffer *ab; ab = audit_log_start(NULL, GFP_NOFS, AUDIT_CONFIG_CHANGE); audit_log_format(ab, "auid=%u ses=%u op=", - audit_get_loginuid(current), + from_kuid(&init_user_ns, audit_get_loginuid(current)), audit_get_sessionid(current)); audit_log_string(ab, op); audit_log_format(ab, " path="); @@ -265,7 +265,8 @@ static void audit_update_watch(struct audit_parent *parent, /* Run all of the watches on this parent looking for the one that * matches the given dname */ list_for_each_entry_safe(owatch, nextw, &parent->watches, wlist) { - if (audit_compare_dname_path(dname, owatch->path, NULL)) + if (audit_compare_dname_path(dname, owatch->path, + AUDIT_NAME_FULL)) continue; /* If the update involves invalidating rules, do the inode-based diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index a6c3f1abd206..7f19f23d38a3 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -342,6 +342,8 @@ static struct audit_entry *audit_rule_to_entry(struct audit_rule *rule) f->type = rule->fields[i] & ~(AUDIT_NEGATE|AUDIT_OPERATORS); f->val = rule->values[i]; + f->uid = INVALID_UID; + f->gid = INVALID_GID; err = -EINVAL; if (f->op == Audit_bad) @@ -350,16 +352,32 @@ static struct audit_entry *audit_rule_to_entry(struct audit_rule *rule) switch(f->type) { default: goto exit_free; - case AUDIT_PID: case AUDIT_UID: case AUDIT_EUID: case AUDIT_SUID: case AUDIT_FSUID: + case AUDIT_LOGINUID: + /* bit ops not implemented for uid comparisons */ + if (f->op == Audit_bitmask || f->op == Audit_bittest) + goto exit_free; + + f->uid = make_kuid(current_user_ns(), f->val); + if (!uid_valid(f->uid)) + goto exit_free; + break; case AUDIT_GID: case AUDIT_EGID: case AUDIT_SGID: case AUDIT_FSGID: - case AUDIT_LOGINUID: + /* bit ops not implemented for gid comparisons */ + if (f->op == Audit_bitmask || f->op == Audit_bittest) + goto exit_free; + + f->gid = make_kgid(current_user_ns(), f->val); + if (!gid_valid(f->gid)) + goto exit_free; + break; + case AUDIT_PID: case AUDIT_PERS: case AUDIT_MSGTYPE: case AUDIT_PPID: @@ -437,19 +455,39 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, f->type = data->fields[i]; f->val = data->values[i]; + f->uid = INVALID_UID; + f->gid = INVALID_GID; f->lsm_str = NULL; f->lsm_rule = NULL; switch(f->type) { - case AUDIT_PID: case AUDIT_UID: case AUDIT_EUID: case AUDIT_SUID: case AUDIT_FSUID: + case AUDIT_LOGINUID: + case AUDIT_OBJ_UID: + /* bit ops not implemented for uid comparisons */ + if (f->op == Audit_bitmask || f->op == Audit_bittest) + goto exit_free; + + f->uid = make_kuid(current_user_ns(), f->val); + if (!uid_valid(f->uid)) + goto exit_free; + break; case AUDIT_GID: case AUDIT_EGID: case AUDIT_SGID: case AUDIT_FSGID: - case AUDIT_LOGINUID: + case AUDIT_OBJ_GID: + /* bit ops not implemented for gid comparisons */ + if (f->op == Audit_bitmask || f->op == Audit_bittest) + goto exit_free; + + f->gid = make_kgid(current_user_ns(), f->val); + if (!gid_valid(f->gid)) + goto exit_free; + break; + case AUDIT_PID: case AUDIT_PERS: case AUDIT_MSGTYPE: case AUDIT_PPID: @@ -461,8 +499,6 @@ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, case AUDIT_ARG1: case AUDIT_ARG2: case AUDIT_ARG3: - case AUDIT_OBJ_UID: - case AUDIT_OBJ_GID: break; case AUDIT_ARCH: entry->rule.arch_f = f; @@ -707,6 +743,23 @@ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b) if (strcmp(a->filterkey, b->filterkey)) return 1; break; + case AUDIT_UID: + case AUDIT_EUID: + case AUDIT_SUID: + case AUDIT_FSUID: + case AUDIT_LOGINUID: + case AUDIT_OBJ_UID: + if (!uid_eq(a->fields[i].uid, b->fields[i].uid)) + return 1; + break; + case AUDIT_GID: + case AUDIT_EGID: + case AUDIT_SGID: + case AUDIT_FSGID: + case AUDIT_OBJ_GID: + if (!gid_eq(a->fields[i].gid, b->fields[i].gid)) + return 1; + break; default: if (a->fields[i].val != b->fields[i].val) return 1; @@ -1056,7 +1109,7 @@ static void audit_list_rules(int pid, int seq, struct sk_buff_head *q) } /* Log rule additions and removals */ -static void audit_log_rule_change(uid_t loginuid, u32 sessionid, u32 sid, +static void audit_log_rule_change(kuid_t loginuid, u32 sessionid, u32 sid, char *action, struct audit_krule *rule, int res) { @@ -1068,7 +1121,8 @@ static void audit_log_rule_change(uid_t loginuid, u32 sessionid, u32 sid, ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE); if (!ab) return; - audit_log_format(ab, "auid=%u ses=%u", loginuid, sessionid); + audit_log_format(ab, "auid=%u ses=%u", + from_kuid(&init_user_ns, loginuid), sessionid); if (sid) { char *ctx = NULL; u32 len; @@ -1098,8 +1152,8 @@ static void audit_log_rule_change(uid_t loginuid, u32 sessionid, u32 sid, * @sessionid: sessionid for netlink audit message * @sid: SE Linux Security ID of sender */ -int audit_receive_filter(int type, int pid, int uid, int seq, void *data, - size_t datasz, uid_t loginuid, u32 sessionid, u32 sid) +int audit_receive_filter(int type, int pid, int seq, void *data, + size_t datasz, kuid_t loginuid, u32 sessionid, u32 sid) { struct task_struct *tsk; struct audit_netlink_list *dest; @@ -1198,46 +1252,110 @@ int audit_comparator(u32 left, u32 op, u32 right) } } -/* Compare given dentry name with last component in given path, - * return of 0 indicates a match. */ -int audit_compare_dname_path(const char *dname, const char *path, - int *dirlen) +int audit_uid_comparator(kuid_t left, u32 op, kuid_t right) { - int dlen, plen; - const char *p; + switch (op) { + case Audit_equal: + return uid_eq(left, right); + case Audit_not_equal: + return !uid_eq(left, right); + case Audit_lt: + return uid_lt(left, right); + case Audit_le: + return uid_lte(left, right); + case Audit_gt: + return uid_gt(left, right); + case Audit_ge: + return uid_gte(left, right); + case Audit_bitmask: + case Audit_bittest: + default: + BUG(); + return 0; + } +} - if (!dname || !path) - return 1; +int audit_gid_comparator(kgid_t left, u32 op, kgid_t right) +{ + switch (op) { + case Audit_equal: + return gid_eq(left, right); + case Audit_not_equal: + return !gid_eq(left, right); + case Audit_lt: + return gid_lt(left, right); + case Audit_le: + return gid_lte(left, right); + case Audit_gt: + return gid_gt(left, right); + case Audit_ge: + return gid_gte(left, right); + case Audit_bitmask: + case Audit_bittest: + default: + BUG(); + return 0; + } +} + +/** + * parent_len - find the length of the parent portion of a pathname + * @path: pathname of which to determine length + */ +int parent_len(const char *path) +{ + int plen; + const char *p; - dlen = strlen(dname); plen = strlen(path); - if (plen < dlen) - return 1; + + if (plen == 0) + return plen; /* disregard trailing slashes */ p = path + plen - 1; while ((*p == '/') && (p > path)) p--; - /* find last path component */ - p = p - dlen + 1; - if (p < path) + /* walk backward until we find the next slash or hit beginning */ + while ((*p != '/') && (p > path)) + p--; + + /* did we find a slash? Then increment to include it in path */ + if (*p == '/') + p++; + + return p - path; +} + +/** + * audit_compare_dname_path - compare given dentry name with last component in + * given path. Return of 0 indicates a match. + * @dname: dentry name that we're comparing + * @path: full pathname that we're comparing + * @parentlen: length of the parent if known. Passing in AUDIT_NAME_FULL + * here indicates that we must compute this value. + */ +int audit_compare_dname_path(const char *dname, const char *path, int parentlen) +{ + int dlen, pathlen; + const char *p; + + dlen = strlen(dname); + pathlen = strlen(path); + if (pathlen < dlen) return 1; - else if (p > path) { - if (*--p != '/') - return 1; - else - p++; - } - /* return length of path's directory component */ - if (dirlen) - *dirlen = p - path; + parentlen = parentlen == AUDIT_NAME_FULL ? parent_len(path) : parentlen; + if (pathlen - parentlen != dlen) + return 1; + + p = path + parentlen; + return strncmp(p, dname, dlen); } -static int audit_filter_user_rules(struct netlink_skb_parms *cb, - struct audit_krule *rule, +static int audit_filter_user_rules(struct audit_krule *rule, enum audit_state *state) { int i; @@ -1249,17 +1367,17 @@ static int audit_filter_user_rules(struct netlink_skb_parms *cb, switch (f->type) { case AUDIT_PID: - result = audit_comparator(cb->creds.pid, f->op, f->val); + result = audit_comparator(task_pid_vnr(current), f->op, f->val); break; case AUDIT_UID: - result = audit_comparator(cb->creds.uid, f->op, f->val); + result = audit_uid_comparator(current_uid(), f->op, f->uid); break; case AUDIT_GID: - result = audit_comparator(cb->creds.gid, f->op, f->val); + result = audit_gid_comparator(current_gid(), f->op, f->gid); break; case AUDIT_LOGINUID: - result = audit_comparator(audit_get_loginuid(current), - f->op, f->val); + result = audit_uid_comparator(audit_get_loginuid(current), + f->op, f->uid); break; case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: @@ -1287,7 +1405,7 @@ static int audit_filter_user_rules(struct netlink_skb_parms *cb, return 1; } -int audit_filter_user(struct netlink_skb_parms *cb) +int audit_filter_user(void) { enum audit_state state = AUDIT_DISABLED; struct audit_entry *e; @@ -1295,7 +1413,7 @@ int audit_filter_user(struct netlink_skb_parms *cb) rcu_read_lock(); list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_USER], list) { - if (audit_filter_user_rules(cb, &e->rule, &state)) { + if (audit_filter_user_rules(&e->rule, &state)) { if (state == AUDIT_DISABLED) ret = 0; break; diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 4b96415527b8..2f186ed80c40 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -81,9 +81,6 @@ * a name dynamically and also add those to the list anchored by names_list. */ #define AUDIT_NAMES 5 -/* Indicates that audit should log the full pathname. */ -#define AUDIT_NAME_FULL -1 - /* no execve audit message should be longer than this (userspace limits) */ #define MAX_EXECVE_AUDIT_LEN 7500 @@ -106,27 +103,29 @@ struct audit_cap_data { * we don't let putname() free it (instead we free all of the saved * pointers at syscall exit time). * - * Further, in fs/namei.c:path_lookup() we store the inode and device. */ + * Further, in fs/namei.c:path_lookup() we store the inode and device. + */ struct audit_names { - struct list_head list; /* audit_context->names_list */ - const char *name; - unsigned long ino; - dev_t dev; - umode_t mode; - uid_t uid; - gid_t gid; - dev_t rdev; - u32 osid; - struct audit_cap_data fcap; - unsigned int fcap_ver; - int name_len; /* number of name's characters to log */ - bool name_put; /* call __putname() for this name */ + struct list_head list; /* audit_context->names_list */ + struct filename *name; + unsigned long ino; + dev_t dev; + umode_t mode; + kuid_t uid; + kgid_t gid; + dev_t rdev; + u32 osid; + struct audit_cap_data fcap; + unsigned int fcap_ver; + int name_len; /* number of name's characters to log */ + unsigned char type; /* record type */ + bool name_put; /* call __putname() for this name */ /* * This was an allocated audit_names and not from the array of * names allocated in the task audit context. Thus this name * should be freed on syscall exit */ - bool should_free; + bool should_free; }; struct audit_aux_data { @@ -149,8 +148,8 @@ struct audit_aux_data_execve { struct audit_aux_data_pids { struct audit_aux_data d; pid_t target_pid[AUDIT_AUX_PIDS]; - uid_t target_auid[AUDIT_AUX_PIDS]; - uid_t target_uid[AUDIT_AUX_PIDS]; + kuid_t target_auid[AUDIT_AUX_PIDS]; + kuid_t target_uid[AUDIT_AUX_PIDS]; unsigned int target_sessionid[AUDIT_AUX_PIDS]; u32 target_sid[AUDIT_AUX_PIDS]; char target_comm[AUDIT_AUX_PIDS][TASK_COMM_LEN]; @@ -208,14 +207,14 @@ struct audit_context { size_t sockaddr_len; /* Save things to print about task_struct */ pid_t pid, ppid; - uid_t uid, euid, suid, fsuid; - gid_t gid, egid, sgid, fsgid; + kuid_t uid, euid, suid, fsuid; + kgid_t gid, egid, sgid, fsgid; unsigned long personality; int arch; pid_t target_pid; - uid_t target_auid; - uid_t target_uid; + kuid_t target_auid; + kuid_t target_uid; unsigned int target_sessionid; u32 target_sid; char target_comm[TASK_COMM_LEN]; @@ -231,8 +230,8 @@ struct audit_context { long args[6]; } socketcall; struct { - uid_t uid; - gid_t gid; + kuid_t uid; + kgid_t gid; umode_t mode; u32 osid; int has_perm; @@ -464,37 +463,47 @@ static int match_tree_refs(struct audit_context *ctx, struct audit_tree *tree) return 0; } -static int audit_compare_id(uid_t uid1, - struct audit_names *name, - unsigned long name_offset, - struct audit_field *f, - struct audit_context *ctx) +static int audit_compare_uid(kuid_t uid, + struct audit_names *name, + struct audit_field *f, + struct audit_context *ctx) { struct audit_names *n; - unsigned long addr; - uid_t uid2; int rc; - - BUILD_BUG_ON(sizeof(uid_t) != sizeof(gid_t)); - + if (name) { - addr = (unsigned long)name; - addr += name_offset; - - uid2 = *(uid_t *)addr; - rc = audit_comparator(uid1, f->op, uid2); + rc = audit_uid_comparator(uid, f->op, name->uid); if (rc) return rc; } - + if (ctx) { list_for_each_entry(n, &ctx->names_list, list) { - addr = (unsigned long)n; - addr += name_offset; - - uid2 = *(uid_t *)addr; + rc = audit_uid_comparator(uid, f->op, n->uid); + if (rc) + return rc; + } + } + return 0; +} - rc = audit_comparator(uid1, f->op, uid2); +static int audit_compare_gid(kgid_t gid, + struct audit_names *name, + struct audit_field *f, + struct audit_context *ctx) +{ + struct audit_names *n; + int rc; + + if (name) { + rc = audit_gid_comparator(gid, f->op, name->gid); + if (rc) + return rc; + } + + if (ctx) { + list_for_each_entry(n, &ctx->names_list, list) { + rc = audit_gid_comparator(gid, f->op, n->gid); if (rc) return rc; } @@ -511,80 +520,62 @@ static int audit_field_compare(struct task_struct *tsk, switch (f->val) { /* process to file object comparisons */ case AUDIT_COMPARE_UID_TO_OBJ_UID: - return audit_compare_id(cred->uid, - name, offsetof(struct audit_names, uid), - f, ctx); + return audit_compare_uid(cred->uid, name, f, ctx); case AUDIT_COMPARE_GID_TO_OBJ_GID: - return audit_compare_id(cred->gid, - name, offsetof(struct audit_names, gid), - f, ctx); + return audit_compare_gid(cred->gid, name, f, ctx); case AUDIT_COMPARE_EUID_TO_OBJ_UID: - return audit_compare_id(cred->euid, - name, offsetof(struct audit_names, uid), - f, ctx); + return audit_compare_uid(cred->euid, name, f, ctx); case AUDIT_COMPARE_EGID_TO_OBJ_GID: - return audit_compare_id(cred->egid, - name, offsetof(struct audit_names, gid), - f, ctx); + return audit_compare_gid(cred->egid, name, f, ctx); case AUDIT_COMPARE_AUID_TO_OBJ_UID: - return audit_compare_id(tsk->loginuid, - name, offsetof(struct audit_names, uid), - f, ctx); + return audit_compare_uid(tsk->loginuid, name, f, ctx); case AUDIT_COMPARE_SUID_TO_OBJ_UID: - return audit_compare_id(cred->suid, - name, offsetof(struct audit_names, uid), - f, ctx); + return audit_compare_uid(cred->suid, name, f, ctx); case AUDIT_COMPARE_SGID_TO_OBJ_GID: - return audit_compare_id(cred->sgid, - name, offsetof(struct audit_names, gid), - f, ctx); + return audit_compare_gid(cred->sgid, name, f, ctx); case AUDIT_COMPARE_FSUID_TO_OBJ_UID: - return audit_compare_id(cred->fsuid, - name, offsetof(struct audit_names, uid), - f, ctx); + return audit_compare_uid(cred->fsuid, name, f, ctx); case AUDIT_COMPARE_FSGID_TO_OBJ_GID: - return audit_compare_id(cred->fsgid, - name, offsetof(struct audit_names, gid), - f, ctx); + return audit_compare_gid(cred->fsgid, name, f, ctx); /* uid comparisons */ case AUDIT_COMPARE_UID_TO_AUID: - return audit_comparator(cred->uid, f->op, tsk->loginuid); + return audit_uid_comparator(cred->uid, f->op, tsk->loginuid); case AUDIT_COMPARE_UID_TO_EUID: - return audit_comparator(cred->uid, f->op, cred->euid); + return audit_uid_comparator(cred->uid, f->op, cred->euid); case AUDIT_COMPARE_UID_TO_SUID: - return audit_comparator(cred->uid, f->op, cred->suid); + return audit_uid_comparator(cred->uid, f->op, cred->suid); case AUDIT_COMPARE_UID_TO_FSUID: - return audit_comparator(cred->uid, f->op, cred->fsuid); + return audit_uid_comparator(cred->uid, f->op, cred->fsuid); /* auid comparisons */ case AUDIT_COMPARE_AUID_TO_EUID: - return audit_comparator(tsk->loginuid, f->op, cred->euid); + return audit_uid_comparator(tsk->loginuid, f->op, cred->euid); case AUDIT_COMPARE_AUID_TO_SUID: - return audit_comparator(tsk->loginuid, f->op, cred->suid); + return audit_uid_comparator(tsk->loginuid, f->op, cred->suid); case AUDIT_COMPARE_AUID_TO_FSUID: - return audit_comparator(tsk->loginuid, f->op, cred->fsuid); + return audit_uid_comparator(tsk->loginuid, f->op, cred->fsuid); /* euid comparisons */ case AUDIT_COMPARE_EUID_TO_SUID: - return audit_comparator(cred->euid, f->op, cred->suid); + return audit_uid_comparator(cred->euid, f->op, cred->suid); case AUDIT_COMPARE_EUID_TO_FSUID: - return audit_comparator(cred->euid, f->op, cred->fsuid); + return audit_uid_comparator(cred->euid, f->op, cred->fsuid); /* suid comparisons */ case AUDIT_COMPARE_SUID_TO_FSUID: - return audit_comparator(cred->suid, f->op, cred->fsuid); + return audit_uid_comparator(cred->suid, f->op, cred->fsuid); /* gid comparisons */ case AUDIT_COMPARE_GID_TO_EGID: - return audit_comparator(cred->gid, f->op, cred->egid); + return audit_gid_comparator(cred->gid, f->op, cred->egid); case AUDIT_COMPARE_GID_TO_SGID: - return audit_comparator(cred->gid, f->op, cred->sgid); + return audit_gid_comparator(cred->gid, f->op, cred->sgid); case AUDIT_COMPARE_GID_TO_FSGID: - return audit_comparator(cred->gid, f->op, cred->fsgid); + return audit_gid_comparator(cred->gid, f->op, cred->fsgid); /* egid comparisons */ case AUDIT_COMPARE_EGID_TO_SGID: - return audit_comparator(cred->egid, f->op, cred->sgid); + return audit_gid_comparator(cred->egid, f->op, cred->sgid); case AUDIT_COMPARE_EGID_TO_FSGID: - return audit_comparator(cred->egid, f->op, cred->fsgid); + return audit_gid_comparator(cred->egid, f->op, cred->fsgid); /* sgid comparison */ case AUDIT_COMPARE_SGID_TO_FSGID: - return audit_comparator(cred->sgid, f->op, cred->fsgid); + return audit_gid_comparator(cred->sgid, f->op, cred->fsgid); default: WARN(1, "Missing AUDIT_COMPARE define. Report as a bug\n"); return 0; @@ -630,28 +621,28 @@ static int audit_filter_rules(struct task_struct *tsk, } break; case AUDIT_UID: - result = audit_comparator(cred->uid, f->op, f->val); + result = audit_uid_comparator(cred->uid, f->op, f->uid); break; case AUDIT_EUID: - result = audit_comparator(cred->euid, f->op, f->val); + result = audit_uid_comparator(cred->euid, f->op, f->uid); break; case AUDIT_SUID: - result = audit_comparator(cred->suid, f->op, f->val); + result = audit_uid_comparator(cred->suid, f->op, f->uid); break; case AUDIT_FSUID: - result = audit_comparator(cred->fsuid, f->op, f->val); + result = audit_uid_comparator(cred->fsuid, f->op, f->uid); break; case AUDIT_GID: - result = audit_comparator(cred->gid, f->op, f->val); + result = audit_gid_comparator(cred->gid, f->op, f->gid); break; case AUDIT_EGID: - result = audit_comparator(cred->egid, f->op, f->val); + result = audit_gid_comparator(cred->egid, f->op, f->gid); break; case AUDIT_SGID: - result = audit_comparator(cred->sgid, f->op, f->val); + result = audit_gid_comparator(cred->sgid, f->op, f->gid); break; case AUDIT_FSGID: - result = audit_comparator(cred->fsgid, f->op, f->val); + result = audit_gid_comparator(cred->fsgid, f->op, f->gid); break; case AUDIT_PERS: result = audit_comparator(tsk->personality, f->op, f->val); @@ -717,10 +708,10 @@ static int audit_filter_rules(struct task_struct *tsk, break; case AUDIT_OBJ_UID: if (name) { - result = audit_comparator(name->uid, f->op, f->val); + result = audit_uid_comparator(name->uid, f->op, f->uid); } else if (ctx) { list_for_each_entry(n, &ctx->names_list, list) { - if (audit_comparator(n->uid, f->op, f->val)) { + if (audit_uid_comparator(n->uid, f->op, f->uid)) { ++result; break; } @@ -729,10 +720,10 @@ static int audit_filter_rules(struct task_struct *tsk, break; case AUDIT_OBJ_GID: if (name) { - result = audit_comparator(name->gid, f->op, f->val); + result = audit_gid_comparator(name->gid, f->op, f->gid); } else if (ctx) { list_for_each_entry(n, &ctx->names_list, list) { - if (audit_comparator(n->gid, f->op, f->val)) { + if (audit_gid_comparator(n->gid, f->op, f->gid)) { ++result; break; } @@ -750,7 +741,7 @@ static int audit_filter_rules(struct task_struct *tsk, case AUDIT_LOGINUID: result = 0; if (ctx) - result = audit_comparator(tsk->loginuid, f->op, f->val); + result = audit_uid_comparator(tsk->loginuid, f->op, f->uid); break; case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: @@ -1006,7 +997,7 @@ static inline void audit_free_names(struct audit_context *context) context->ino_count); list_for_each_entry(n, &context->names_list, list) { printk(KERN_ERR "names[%d] = %p = %s\n", i, - n->name, n->name ?: "(null)"); + n->name, n->name->name ?: "(null)"); } dump_stack(); return; @@ -1154,13 +1145,43 @@ error_path: EXPORT_SYMBOL(audit_log_task_context); -static void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk) +void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk) { + const struct cred *cred; char name[sizeof(tsk->comm)]; struct mm_struct *mm = tsk->mm; - struct vm_area_struct *vma; + char *tty; + + if (!ab) + return; /* tsk == current */ + cred = current_cred(); + + spin_lock_irq(&tsk->sighand->siglock); + if (tsk->signal && tsk->signal->tty && tsk->signal->tty->name) + tty = tsk->signal->tty->name; + else + tty = "(none)"; + spin_unlock_irq(&tsk->sighand->siglock); + + + audit_log_format(ab, + " ppid=%ld pid=%d auid=%u uid=%u gid=%u" + " euid=%u suid=%u fsuid=%u" + " egid=%u sgid=%u fsgid=%u ses=%u tty=%s", + sys_getppid(), + tsk->pid, + from_kuid(&init_user_ns, tsk->loginuid), + from_kuid(&init_user_ns, cred->uid), + from_kgid(&init_user_ns, cred->gid), + from_kuid(&init_user_ns, cred->euid), + from_kuid(&init_user_ns, cred->suid), + from_kuid(&init_user_ns, cred->fsuid), + from_kgid(&init_user_ns, cred->egid), + from_kgid(&init_user_ns, cred->sgid), + from_kgid(&init_user_ns, cred->fsgid), + tsk->sessionid, tty); get_task_comm(name, tsk); audit_log_format(ab, " comm="); @@ -1168,23 +1189,17 @@ static void audit_log_task_info(struct audit_buffer *ab, struct task_struct *tsk if (mm) { down_read(&mm->mmap_sem); - vma = mm->mmap; - while (vma) { - if ((vma->vm_flags & VM_EXECUTABLE) && - vma->vm_file) { - audit_log_d_path(ab, " exe=", - &vma->vm_file->f_path); - break; - } - vma = vma->vm_next; - } + if (mm->exe_file) + audit_log_d_path(ab, " exe=", &mm->exe_file->f_path); up_read(&mm->mmap_sem); } audit_log_task_context(ab); } +EXPORT_SYMBOL(audit_log_task_info); + static int audit_log_pid_context(struct audit_context *context, pid_t pid, - uid_t auid, uid_t uid, unsigned int sessionid, + kuid_t auid, kuid_t uid, unsigned int sessionid, u32 sid, char *comm) { struct audit_buffer *ab; @@ -1196,8 +1211,9 @@ static int audit_log_pid_context(struct audit_context *context, pid_t pid, if (!ab) return rc; - audit_log_format(ab, "opid=%d oauid=%d ouid=%d oses=%d", pid, auid, - uid, sessionid); + audit_log_format(ab, "opid=%d oauid=%d ouid=%d oses=%d", pid, + from_kuid(&init_user_ns, auid), + from_kuid(&init_user_ns, uid), sessionid); if (security_secid_to_secctx(sid, &ctx, &len)) { audit_log_format(ab, " obj=(none)"); rc = 1; @@ -1447,7 +1463,9 @@ static void show_special(struct audit_context *context, int *call_panic) u32 osid = context->ipc.osid; audit_log_format(ab, "ouid=%u ogid=%u mode=%#ho", - context->ipc.uid, context->ipc.gid, context->ipc.mode); + from_kuid(&init_user_ns, context->ipc.uid), + from_kgid(&init_user_ns, context->ipc.gid), + context->ipc.mode); if (osid) { char *ctx = NULL; u32 len; @@ -1536,7 +1554,7 @@ static void audit_log_name(struct audit_context *context, struct audit_names *n, case AUDIT_NAME_FULL: /* log the full path */ audit_log_format(ab, " name="); - audit_log_untrustedstring(ab, n->name); + audit_log_untrustedstring(ab, n->name->name); break; case 0: /* name was specified as a relative path and the @@ -1546,7 +1564,7 @@ static void audit_log_name(struct audit_context *context, struct audit_names *n, default: /* log the name's directory component */ audit_log_format(ab, " name="); - audit_log_n_untrustedstring(ab, n->name, + audit_log_n_untrustedstring(ab, n->name->name, n->name_len); } } else @@ -1560,8 +1578,8 @@ static void audit_log_name(struct audit_context *context, struct audit_names *n, MAJOR(n->dev), MINOR(n->dev), n->mode, - n->uid, - n->gid, + from_kuid(&init_user_ns, n->uid), + from_kgid(&init_user_ns, n->gid), MAJOR(n->rdev), MINOR(n->rdev)); } @@ -1585,26 +1603,12 @@ static void audit_log_name(struct audit_context *context, struct audit_names *n, static void audit_log_exit(struct audit_context *context, struct task_struct *tsk) { - const struct cred *cred; int i, call_panic = 0; struct audit_buffer *ab; struct audit_aux_data *aux; - const char *tty; struct audit_names *n; /* tsk == current */ - context->pid = tsk->pid; - if (!context->ppid) - context->ppid = sys_getppid(); - cred = current_cred(); - context->uid = cred->uid; - context->gid = cred->gid; - context->euid = cred->euid; - context->suid = cred->suid; - context->fsuid = cred->fsuid; - context->egid = cred->egid; - context->sgid = cred->sgid; - context->fsgid = cred->fsgid; context->personality = tsk->personality; ab = audit_log_start(context, GFP_KERNEL, AUDIT_SYSCALL); @@ -1619,32 +1623,13 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts (context->return_valid==AUDITSC_SUCCESS)?"yes":"no", context->return_code); - spin_lock_irq(&tsk->sighand->siglock); - if (tsk->signal && tsk->signal->tty && tsk->signal->tty->name) - tty = tsk->signal->tty->name; - else - tty = "(none)"; - spin_unlock_irq(&tsk->sighand->siglock); - audit_log_format(ab, - " a0=%lx a1=%lx a2=%lx a3=%lx items=%d" - " ppid=%d pid=%d auid=%u uid=%u gid=%u" - " euid=%u suid=%u fsuid=%u" - " egid=%u sgid=%u fsgid=%u tty=%s ses=%u", - context->argv[0], - context->argv[1], - context->argv[2], - context->argv[3], - context->name_count, - context->ppid, - context->pid, - tsk->loginuid, - context->uid, - context->gid, - context->euid, context->suid, context->fsuid, - context->egid, context->sgid, context->fsgid, tty, - tsk->sessionid); - + " a0=%lx a1=%lx a2=%lx a3=%lx items=%d", + context->argv[0], + context->argv[1], + context->argv[2], + context->argv[3], + context->name_count); audit_log_task_info(ab, tsk); audit_log_key(ab, context->filterkey); @@ -2009,7 +1994,8 @@ retry: #endif } -static struct audit_names *audit_alloc_name(struct audit_context *context) +static struct audit_names *audit_alloc_name(struct audit_context *context, + unsigned char type) { struct audit_names *aname; @@ -2024,6 +2010,7 @@ static struct audit_names *audit_alloc_name(struct audit_context *context) } aname->ino = (unsigned long)-1; + aname->type = type; list_add_tail(&aname->list, &context->names_list); context->name_count++; @@ -2034,13 +2021,36 @@ static struct audit_names *audit_alloc_name(struct audit_context *context) } /** + * audit_reusename - fill out filename with info from existing entry + * @uptr: userland ptr to pathname + * + * Search the audit_names list for the current audit context. If there is an + * existing entry with a matching "uptr" then return the filename + * associated with that audit_name. If not, return NULL. + */ +struct filename * +__audit_reusename(const __user char *uptr) +{ + struct audit_context *context = current->audit_context; + struct audit_names *n; + + list_for_each_entry(n, &context->names_list, list) { + if (!n->name) + continue; + if (n->name->uptr == uptr) + return n->name; + } + return NULL; +} + +/** * audit_getname - add a name to the list * @name: name to add * * Add a name to the list of audit names for this context. * Called from fs/namei.c:getname(). */ -void __audit_getname(const char *name) +void __audit_getname(struct filename *name) { struct audit_context *context = current->audit_context; struct audit_names *n; @@ -2054,13 +2064,19 @@ void __audit_getname(const char *name) return; } - n = audit_alloc_name(context); +#if AUDIT_DEBUG + /* The filename _must_ have a populated ->name */ + BUG_ON(!name->name); +#endif + + n = audit_alloc_name(context, AUDIT_TYPE_UNKNOWN); if (!n) return; n->name = name; n->name_len = AUDIT_NAME_FULL; n->name_put = true; + name->aname = n; if (!context->pwd.dentry) get_fs_pwd(current->fs, &context->pwd); @@ -2073,7 +2089,7 @@ void __audit_getname(const char *name) * then we delay the putname until syscall exit. * Called from include/linux/fs.h:putname(). */ -void audit_putname(const char *name) +void audit_putname(struct filename *name) { struct audit_context *context = current->audit_context; @@ -2088,7 +2104,7 @@ void audit_putname(const char *name) list_for_each_entry(n, &context->names_list, list) printk(KERN_ERR "name[%d] = %p = %s\n", i, - n->name, n->name ?: "(null)"); + n->name, n->name->name ?: "(null)"); } #endif __putname(name); @@ -2102,8 +2118,8 @@ void audit_putname(const char *name) " put_count=%d\n", __FILE__, __LINE__, context->serial, context->major, - context->in_syscall, name, context->name_count, - context->put_count); + context->in_syscall, name->name, + context->name_count, context->put_count); dump_stack(); } } @@ -2146,13 +2162,13 @@ static void audit_copy_inode(struct audit_names *name, const struct dentry *dent } /** - * audit_inode - store the inode and device from a lookup + * __audit_inode - store the inode and device from a lookup * @name: name being audited * @dentry: dentry being audited - * - * Called from fs/namei.c:path_lookup(). + * @parent: does this dentry represent the parent? */ -void __audit_inode(const char *name, const struct dentry *dentry) +void __audit_inode(struct filename *name, const struct dentry *dentry, + unsigned int parent) { struct audit_context *context = current->audit_context; const struct inode *inode = dentry->d_inode; @@ -2161,24 +2177,69 @@ void __audit_inode(const char *name, const struct dentry *dentry) if (!context->in_syscall) return; + if (!name) + goto out_alloc; + +#if AUDIT_DEBUG + /* The struct filename _must_ have a populated ->name */ + BUG_ON(!name->name); +#endif + /* + * If we have a pointer to an audit_names entry already, then we can + * just use it directly if the type is correct. + */ + n = name->aname; + if (n) { + if (parent) { + if (n->type == AUDIT_TYPE_PARENT || + n->type == AUDIT_TYPE_UNKNOWN) + goto out; + } else { + if (n->type != AUDIT_TYPE_PARENT) + goto out; + } + } + list_for_each_entry_reverse(n, &context->names_list, list) { - if (n->name && (n->name == name)) - goto out; + /* does the name pointer match? */ + if (!n->name || n->name->name != name->name) + continue; + + /* match the correct record type */ + if (parent) { + if (n->type == AUDIT_TYPE_PARENT || + n->type == AUDIT_TYPE_UNKNOWN) + goto out; + } else { + if (n->type != AUDIT_TYPE_PARENT) + goto out; + } } - /* unable to find the name from a previous getname() */ - n = audit_alloc_name(context); +out_alloc: + /* unable to find the name from a previous getname(). Allocate a new + * anonymous entry. + */ + n = audit_alloc_name(context, AUDIT_TYPE_NORMAL); if (!n) return; out: + if (parent) { + n->name_len = n->name ? parent_len(n->name->name) : AUDIT_NAME_FULL; + n->type = AUDIT_TYPE_PARENT; + } else { + n->name_len = AUDIT_NAME_FULL; + n->type = AUDIT_TYPE_NORMAL; + } handle_path(dentry); audit_copy_inode(n, dentry, inode); } /** - * audit_inode_child - collect inode info for created/removed objects - * @dentry: dentry being audited + * __audit_inode_child - collect inode info for created/removed objects * @parent: inode of dentry parent + * @dentry: dentry being audited + * @type: AUDIT_TYPE_* value that we're looking for * * For syscalls that create or remove filesystem objects, audit_inode * can only collect information for the filesystem object's parent. @@ -2188,15 +2249,14 @@ out: * must be hooked prior, in order to capture the target inode during * unsuccessful attempts. */ -void __audit_inode_child(const struct dentry *dentry, - const struct inode *parent) +void __audit_inode_child(const struct inode *parent, + const struct dentry *dentry, + const unsigned char type) { struct audit_context *context = current->audit_context; - const char *found_parent = NULL, *found_child = NULL; const struct inode *inode = dentry->d_inode; const char *dname = dentry->d_name.name; - struct audit_names *n; - int dirlen = 0; + struct audit_names *n, *found_parent = NULL, *found_child = NULL; if (!context->in_syscall) return; @@ -2204,62 +2264,65 @@ void __audit_inode_child(const struct dentry *dentry, if (inode) handle_one(inode); - /* parent is more likely, look for it first */ + /* look for a parent entry first */ list_for_each_entry(n, &context->names_list, list) { - if (!n->name) + if (!n->name || n->type != AUDIT_TYPE_PARENT) continue; if (n->ino == parent->i_ino && - !audit_compare_dname_path(dname, n->name, &dirlen)) { - n->name_len = dirlen; /* update parent data in place */ - found_parent = n->name; - goto add_names; + !audit_compare_dname_path(dname, n->name->name, n->name_len)) { + found_parent = n; + break; } } - /* no matching parent, look for matching child */ + /* is there a matching child entry? */ list_for_each_entry(n, &context->names_list, list) { - if (!n->name) + /* can only match entries that have a name */ + if (!n->name || n->type != type) continue; - /* strcmp() is the more likely scenario */ - if (!strcmp(dname, n->name) || - !audit_compare_dname_path(dname, n->name, &dirlen)) { - if (inode) - audit_copy_inode(n, NULL, inode); - else - n->ino = (unsigned long)-1; - found_child = n->name; - goto add_names; + /* if we found a parent, make sure this one is a child of it */ + if (found_parent && (n->name != found_parent->name)) + continue; + + if (!strcmp(dname, n->name->name) || + !audit_compare_dname_path(dname, n->name->name, + found_parent ? + found_parent->name_len : + AUDIT_NAME_FULL)) { + found_child = n; + break; } } -add_names: if (!found_parent) { - n = audit_alloc_name(context); + /* create a new, "anonymous" parent record */ + n = audit_alloc_name(context, AUDIT_TYPE_PARENT); if (!n) return; audit_copy_inode(n, NULL, parent); } if (!found_child) { - n = audit_alloc_name(context); - if (!n) + found_child = audit_alloc_name(context, type); + if (!found_child) return; /* Re-use the name belonging to the slot for a matching parent * directory. All names for this context are relinquished in * audit_free_names() */ if (found_parent) { - n->name = found_parent; - n->name_len = AUDIT_NAME_FULL; + found_child->name = found_parent->name; + found_child->name_len = AUDIT_NAME_FULL; /* don't call __putname() */ - n->name_put = false; + found_child->name_put = false; } - - if (inode) - audit_copy_inode(n, NULL, inode); } + if (inode) + audit_copy_inode(found_child, dentry, inode); + else + found_child->ino = (unsigned long)-1; } EXPORT_SYMBOL_GPL(__audit_inode_child); @@ -2299,14 +2362,14 @@ static atomic_t session_id = ATOMIC_INIT(0); * * Called (set) from fs/proc/base.c::proc_loginuid_write(). */ -int audit_set_loginuid(uid_t loginuid) +int audit_set_loginuid(kuid_t loginuid) { struct task_struct *task = current; struct audit_context *context = task->audit_context; unsigned int sessionid; #ifdef CONFIG_AUDIT_LOGINUID_IMMUTABLE - if (task->loginuid != -1) + if (uid_valid(task->loginuid)) return -EPERM; #else /* CONFIG_AUDIT_LOGINUID_IMMUTABLE */ if (!capable(CAP_AUDIT_CONTROL)) @@ -2322,8 +2385,10 @@ int audit_set_loginuid(uid_t loginuid) audit_log_format(ab, "login pid=%d uid=%u " "old auid=%u new auid=%u" " old ses=%u new ses=%u", - task->pid, task_uid(task), - task->loginuid, loginuid, + task->pid, + from_kuid(&init_user_ns, task_uid(task)), + from_kuid(&init_user_ns, task->loginuid), + from_kuid(&init_user_ns, loginuid), task->sessionid, sessionid); audit_log_end(ab); } @@ -2546,12 +2611,12 @@ int __audit_signal_info(int sig, struct task_struct *t) struct audit_aux_data_pids *axp; struct task_struct *tsk = current; struct audit_context *ctx = tsk->audit_context; - uid_t uid = current_uid(), t_uid = task_uid(t); + kuid_t uid = current_uid(), t_uid = task_uid(t); if (audit_pid && t->tgid == audit_pid) { if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2) { audit_sig_pid = tsk->pid; - if (tsk->loginuid != -1) + if (uid_valid(tsk->loginuid)) audit_sig_uid = tsk->loginuid; else audit_sig_uid = uid; @@ -2672,8 +2737,8 @@ void __audit_mmap_fd(int fd, int flags) static void audit_log_abend(struct audit_buffer *ab, char *reason, long signr) { - uid_t auid, uid; - gid_t gid; + kuid_t auid, uid; + kgid_t gid; unsigned int sessionid; auid = audit_get_loginuid(current); @@ -2681,7 +2746,10 @@ static void audit_log_abend(struct audit_buffer *ab, char *reason, long signr) current_uid_gid(&uid, &gid); audit_log_format(ab, "auid=%u uid=%u gid=%u ses=%u", - auid, uid, gid, sessionid); + from_kuid(&init_user_ns, auid), + from_kuid(&init_user_ns, uid), + from_kgid(&init_user_ns, gid), + sessionid); audit_log_task_context(ab); audit_log_format(ab, " pid=%d comm=", current->pid); audit_log_untrustedstring(ab, current->comm); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 79818507e444..f24f724620dd 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -88,11 +88,12 @@ static DEFINE_MUTEX(cgroup_root_mutex); /* * Generate an array of cgroup subsystem pointers. At boot time, this is - * populated up to CGROUP_BUILTIN_SUBSYS_COUNT, and modular subsystems are + * populated with the built in subsystems, and modular subsystems are * registered after that. The mutable section of this array is protected by * cgroup_mutex. */ -#define SUBSYS(_x) &_x ## _subsys, +#define SUBSYS(_x) [_x ## _subsys_id] = &_x ## _subsys, +#define IS_SUBSYS_ENABLED(option) IS_BUILTIN(option) static struct cgroup_subsys *subsys[CGROUP_SUBSYS_COUNT] = { #include <linux/cgroup_subsys.h> }; @@ -111,13 +112,13 @@ struct cgroupfs_root { * The bitmask of subsystems intended to be attached to this * hierarchy */ - unsigned long subsys_bits; + unsigned long subsys_mask; /* Unique id for this hierarchy. */ int hierarchy_id; /* The bitmask of subsystems currently attached to this hierarchy */ - unsigned long actual_subsys_bits; + unsigned long actual_subsys_mask; /* A list running through the attached subsystems */ struct list_head subsys_list; @@ -276,7 +277,8 @@ inline int cgroup_is_removed(const struct cgroup *cgrp) /* bits in struct cgroupfs_root flags field */ enum { - ROOT_NOPREFIX, /* mounted subsystems have no named prefix */ + ROOT_NOPREFIX, /* mounted subsystems have no named prefix */ + ROOT_XATTR, /* supports extended attributes */ }; static int cgroup_is_releasable(const struct cgroup *cgrp) @@ -556,7 +558,7 @@ static struct css_set *find_existing_css_set( * won't change, so no need for locking. */ for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { - if (root->subsys_bits & (1UL << i)) { + if (root->subsys_mask & (1UL << i)) { /* Subsystem is in this hierarchy. So we want * the subsystem state from the new * cgroup */ @@ -824,7 +826,8 @@ EXPORT_SYMBOL_GPL(cgroup_unlock); static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode); static struct dentry *cgroup_lookup(struct inode *, struct dentry *, unsigned int); static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry); -static int cgroup_populate_dir(struct cgroup *cgrp); +static int cgroup_populate_dir(struct cgroup *cgrp, bool base_files, + unsigned long subsys_mask); static const struct inode_operations cgroup_dir_inode_operations; static const struct file_operations proc_cgroupstats_operations; @@ -912,15 +915,19 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode) */ BUG_ON(!list_empty(&cgrp->pidlists)); + simple_xattrs_free(&cgrp->xattrs); + kfree_rcu(cgrp, rcu_head); } else { struct cfent *cfe = __d_cfe(dentry); struct cgroup *cgrp = dentry->d_parent->d_fsdata; + struct cftype *cft = cfe->type; WARN_ONCE(!list_empty(&cfe->node) && cgrp != &cgrp->root->top_cgroup, "cfe still linked for %s\n", cfe->type->name); kfree(cfe); + simple_xattrs_free(&cft->xattrs); } iput(inode); } @@ -963,12 +970,29 @@ static int cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) return -ENOENT; } -static void cgroup_clear_directory(struct dentry *dir) +/** + * cgroup_clear_directory - selective removal of base and subsystem files + * @dir: directory containing the files + * @base_files: true if the base files should be removed + * @subsys_mask: mask of the subsystem ids whose files should be removed + */ +static void cgroup_clear_directory(struct dentry *dir, bool base_files, + unsigned long subsys_mask) { struct cgroup *cgrp = __d_cgrp(dir); + struct cgroup_subsys *ss; - while (!list_empty(&cgrp->files)) - cgroup_rm_file(cgrp, NULL); + for_each_subsys(cgrp->root, ss) { + struct cftype_set *set; + if (!test_bit(ss->subsys_id, &subsys_mask)) + continue; + list_for_each_entry(set, &ss->cftsets, node) + cgroup_rm_file(cgrp, set->cfts); + } + if (base_files) { + while (!list_empty(&cgrp->files)) + cgroup_rm_file(cgrp, NULL); + } } /* @@ -977,8 +1001,9 @@ static void cgroup_clear_directory(struct dentry *dir) static void cgroup_d_remove_dir(struct dentry *dentry) { struct dentry *parent; + struct cgroupfs_root *root = dentry->d_sb->s_fs_info; - cgroup_clear_directory(dentry); + cgroup_clear_directory(dentry, true, root->subsys_mask); parent = dentry->d_parent; spin_lock(&parent->d_lock); @@ -1022,22 +1047,22 @@ void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css) * returns an error, no reference counts are touched. */ static int rebind_subsystems(struct cgroupfs_root *root, - unsigned long final_bits) + unsigned long final_subsys_mask) { - unsigned long added_bits, removed_bits; + unsigned long added_mask, removed_mask; struct cgroup *cgrp = &root->top_cgroup; int i; BUG_ON(!mutex_is_locked(&cgroup_mutex)); BUG_ON(!mutex_is_locked(&cgroup_root_mutex)); - removed_bits = root->actual_subsys_bits & ~final_bits; - added_bits = final_bits & ~root->actual_subsys_bits; + removed_mask = root->actual_subsys_mask & ~final_subsys_mask; + added_mask = final_subsys_mask & ~root->actual_subsys_mask; /* Check that any added subsystems are currently free */ for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { unsigned long bit = 1UL << i; struct cgroup_subsys *ss = subsys[i]; - if (!(bit & added_bits)) + if (!(bit & added_mask)) continue; /* * Nobody should tell us to do a subsys that doesn't exist: @@ -1062,7 +1087,7 @@ static int rebind_subsystems(struct cgroupfs_root *root, for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { struct cgroup_subsys *ss = subsys[i]; unsigned long bit = 1UL << i; - if (bit & added_bits) { + if (bit & added_mask) { /* We're binding this subsystem to this hierarchy */ BUG_ON(ss == NULL); BUG_ON(cgrp->subsys[i]); @@ -1075,7 +1100,7 @@ static int rebind_subsystems(struct cgroupfs_root *root, if (ss->bind) ss->bind(cgrp); /* refcount was already taken, and we're keeping it */ - } else if (bit & removed_bits) { + } else if (bit & removed_mask) { /* We're removing this subsystem */ BUG_ON(ss == NULL); BUG_ON(cgrp->subsys[i] != dummytop->subsys[i]); @@ -1088,7 +1113,7 @@ static int rebind_subsystems(struct cgroupfs_root *root, list_move(&ss->sibling, &rootnode.subsys_list); /* subsystem is now free - drop reference on module */ module_put(ss->module); - } else if (bit & final_bits) { + } else if (bit & final_subsys_mask) { /* Subsystem state should already exist */ BUG_ON(ss == NULL); BUG_ON(!cgrp->subsys[i]); @@ -1105,7 +1130,7 @@ static int rebind_subsystems(struct cgroupfs_root *root, BUG_ON(cgrp->subsys[i]); } } - root->subsys_bits = root->actual_subsys_bits = final_bits; + root->subsys_mask = root->actual_subsys_mask = final_subsys_mask; synchronize_rcu(); return 0; @@ -1121,6 +1146,8 @@ static int cgroup_show_options(struct seq_file *seq, struct dentry *dentry) seq_printf(seq, ",%s", ss->name); if (test_bit(ROOT_NOPREFIX, &root->flags)) seq_puts(seq, ",noprefix"); + if (test_bit(ROOT_XATTR, &root->flags)) + seq_puts(seq, ",xattr"); if (strlen(root->release_agent_path)) seq_printf(seq, ",release_agent=%s", root->release_agent_path); if (clone_children(&root->top_cgroup)) @@ -1132,7 +1159,7 @@ static int cgroup_show_options(struct seq_file *seq, struct dentry *dentry) } struct cgroup_sb_opts { - unsigned long subsys_bits; + unsigned long subsys_mask; unsigned long flags; char *release_agent; bool clone_children; @@ -1189,6 +1216,10 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) opts->clone_children = true; continue; } + if (!strcmp(token, "xattr")) { + set_bit(ROOT_XATTR, &opts->flags); + continue; + } if (!strncmp(token, "release_agent=", 14)) { /* Specifying two release agents is forbidden */ if (opts->release_agent) @@ -1237,7 +1268,7 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) /* Mutually exclusive option 'all' + subsystem name */ if (all_ss) return -EINVAL; - set_bit(i, &opts->subsys_bits); + set_bit(i, &opts->subsys_mask); one_ss = true; break; @@ -1258,7 +1289,7 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) continue; if (ss->disabled) continue; - set_bit(i, &opts->subsys_bits); + set_bit(i, &opts->subsys_mask); } } @@ -1270,19 +1301,19 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) * the cpuset subsystem. */ if (test_bit(ROOT_NOPREFIX, &opts->flags) && - (opts->subsys_bits & mask)) + (opts->subsys_mask & mask)) return -EINVAL; /* Can't specify "none" and some subsystems */ - if (opts->subsys_bits && opts->none) + if (opts->subsys_mask && opts->none) return -EINVAL; /* * We either have to specify by name or by subsystems. (So all * empty hierarchies must have a name). */ - if (!opts->subsys_bits && !opts->name) + if (!opts->subsys_mask && !opts->name) return -EINVAL; /* @@ -1291,10 +1322,10 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) * take duplicate reference counts on a subsystem that's already used, * but rebind_subsystems handles this case. */ - for (i = CGROUP_BUILTIN_SUBSYS_COUNT; i < CGROUP_SUBSYS_COUNT; i++) { + for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { unsigned long bit = 1UL << i; - if (!(bit & opts->subsys_bits)) + if (!(bit & opts->subsys_mask)) continue; if (!try_module_get(subsys[i]->module)) { module_pin_failed = true; @@ -1307,11 +1338,11 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) * raced with a module_delete call, and to the user this is * essentially a "subsystem doesn't exist" case. */ - for (i--; i >= CGROUP_BUILTIN_SUBSYS_COUNT; i--) { + for (i--; i >= 0; i--) { /* drop refcounts only on the ones we took */ unsigned long bit = 1UL << i; - if (!(bit & opts->subsys_bits)) + if (!(bit & opts->subsys_mask)) continue; module_put(subsys[i]->module); } @@ -1321,13 +1352,13 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) return 0; } -static void drop_parsed_module_refcounts(unsigned long subsys_bits) +static void drop_parsed_module_refcounts(unsigned long subsys_mask) { int i; - for (i = CGROUP_BUILTIN_SUBSYS_COUNT; i < CGROUP_SUBSYS_COUNT; i++) { + for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { unsigned long bit = 1UL << i; - if (!(bit & subsys_bits)) + if (!(bit & subsys_mask)) continue; module_put(subsys[i]->module); } @@ -1339,6 +1370,7 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data) struct cgroupfs_root *root = sb->s_fs_info; struct cgroup *cgrp = &root->top_cgroup; struct cgroup_sb_opts opts; + unsigned long added_mask, removed_mask; mutex_lock(&cgrp->dentry->d_inode->i_mutex); mutex_lock(&cgroup_mutex); @@ -1350,27 +1382,31 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data) goto out_unlock; /* See feature-removal-schedule.txt */ - if (opts.subsys_bits != root->actual_subsys_bits || opts.release_agent) + if (opts.subsys_mask != root->actual_subsys_mask || opts.release_agent) pr_warning("cgroup: option changes via remount are deprecated (pid=%d comm=%s)\n", task_tgid_nr(current), current->comm); + added_mask = opts.subsys_mask & ~root->subsys_mask; + removed_mask = root->subsys_mask & ~opts.subsys_mask; + /* Don't allow flags or name to change at remount */ if (opts.flags != root->flags || (opts.name && strcmp(opts.name, root->name))) { ret = -EINVAL; - drop_parsed_module_refcounts(opts.subsys_bits); + drop_parsed_module_refcounts(opts.subsys_mask); goto out_unlock; } - ret = rebind_subsystems(root, opts.subsys_bits); + ret = rebind_subsystems(root, opts.subsys_mask); if (ret) { - drop_parsed_module_refcounts(opts.subsys_bits); + drop_parsed_module_refcounts(opts.subsys_mask); goto out_unlock; } /* clear out any existing files and repopulate subsystem files */ - cgroup_clear_directory(cgrp->dentry); - cgroup_populate_dir(cgrp); + cgroup_clear_directory(cgrp->dentry, false, removed_mask); + /* re-populate subsystem files */ + cgroup_populate_dir(cgrp, false, added_mask); if (opts.release_agent) strcpy(root->release_agent_path, opts.release_agent); @@ -1401,6 +1437,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp) mutex_init(&cgrp->pidlist_mutex); INIT_LIST_HEAD(&cgrp->event_list); spin_lock_init(&cgrp->event_list_lock); + simple_xattrs_init(&cgrp->xattrs); } static void init_cgroup_root(struct cgroupfs_root *root) @@ -1455,8 +1492,8 @@ static int cgroup_test_super(struct super_block *sb, void *data) * If we asked for subsystems (or explicitly for no * subsystems) then they must match */ - if ((opts->subsys_bits || opts->none) - && (opts->subsys_bits != root->subsys_bits)) + if ((opts->subsys_mask || opts->none) + && (opts->subsys_mask != root->subsys_mask)) return 0; return 1; @@ -1466,7 +1503,7 @@ static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts) { struct cgroupfs_root *root; - if (!opts->subsys_bits && !opts->none) + if (!opts->subsys_mask && !opts->none) return NULL; root = kzalloc(sizeof(*root), GFP_KERNEL); @@ -1479,7 +1516,7 @@ static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts) } init_cgroup_root(root); - root->subsys_bits = opts->subsys_bits; + root->subsys_mask = opts->subsys_mask; root->flags = opts->flags; if (opts->release_agent) strcpy(root->release_agent_path, opts->release_agent); @@ -1511,7 +1548,7 @@ static int cgroup_set_super(struct super_block *sb, void *data) if (!opts->new_root) return -EINVAL; - BUG_ON(!opts->subsys_bits && !opts->none); + BUG_ON(!opts->subsys_mask && !opts->none); ret = set_anon_super(sb, NULL); if (ret) @@ -1629,7 +1666,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, if (ret) goto unlock_drop; - ret = rebind_subsystems(root, root->subsys_bits); + ret = rebind_subsystems(root, root->subsys_mask); if (ret == -EBUSY) { free_cg_links(&tmp_cg_links); goto unlock_drop; @@ -1669,7 +1706,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, BUG_ON(root->number_of_cgroups != 1); cred = override_creds(&init_cred); - cgroup_populate_dir(root_cgrp); + cgroup_populate_dir(root_cgrp, true, root->subsys_mask); revert_creds(cred); mutex_unlock(&cgroup_root_mutex); mutex_unlock(&cgroup_mutex); @@ -1681,7 +1718,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, */ cgroup_drop_root(opts.new_root); /* no subsys rebinding, so refcounts don't change */ - drop_parsed_module_refcounts(opts.subsys_bits); + drop_parsed_module_refcounts(opts.subsys_mask); } kfree(opts.release_agent); @@ -1695,7 +1732,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, drop_new_super: deactivate_locked_super(sb); drop_modules: - drop_parsed_module_refcounts(opts.subsys_bits); + drop_parsed_module_refcounts(opts.subsys_mask); out_err: kfree(opts.release_agent); kfree(opts.name); @@ -1745,6 +1782,8 @@ static void cgroup_kill_sb(struct super_block *sb) { mutex_unlock(&cgroup_root_mutex); mutex_unlock(&cgroup_mutex); + simple_xattrs_free(&cgrp->xattrs); + kill_litter_super(sb); cgroup_drop_root(root); } @@ -1923,9 +1962,8 @@ static void cgroup_task_migrate(struct cgroup *cgrp, struct cgroup *oldcgrp, * trading it for newcg is protected by cgroup_mutex, we're safe to drop * it here; it will be freed under RCU. */ - put_css_set(oldcg); - set_bit(CGRP_RELEASABLE, &oldcgrp->flags); + put_css_set(oldcg); } /** @@ -2551,6 +2589,64 @@ static int cgroup_rename(struct inode *old_dir, struct dentry *old_dentry, return simple_rename(old_dir, old_dentry, new_dir, new_dentry); } +static struct simple_xattrs *__d_xattrs(struct dentry *dentry) +{ + if (S_ISDIR(dentry->d_inode->i_mode)) + return &__d_cgrp(dentry)->xattrs; + else + return &__d_cft(dentry)->xattrs; +} + +static inline int xattr_enabled(struct dentry *dentry) +{ + struct cgroupfs_root *root = dentry->d_sb->s_fs_info; + return test_bit(ROOT_XATTR, &root->flags); +} + +static bool is_valid_xattr(const char *name) +{ + if (!strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) || + !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) + return true; + return false; +} + +static int cgroup_setxattr(struct dentry *dentry, const char *name, + const void *val, size_t size, int flags) +{ + if (!xattr_enabled(dentry)) + return -EOPNOTSUPP; + if (!is_valid_xattr(name)) + return -EINVAL; + return simple_xattr_set(__d_xattrs(dentry), name, val, size, flags); +} + +static int cgroup_removexattr(struct dentry *dentry, const char *name) +{ + if (!xattr_enabled(dentry)) + return -EOPNOTSUPP; + if (!is_valid_xattr(name)) + return -EINVAL; + return simple_xattr_remove(__d_xattrs(dentry), name); +} + +static ssize_t cgroup_getxattr(struct dentry *dentry, const char *name, + void *buf, size_t size) +{ + if (!xattr_enabled(dentry)) + return -EOPNOTSUPP; + if (!is_valid_xattr(name)) + return -EINVAL; + return simple_xattr_get(__d_xattrs(dentry), name, buf, size); +} + +static ssize_t cgroup_listxattr(struct dentry *dentry, char *buf, size_t size) +{ + if (!xattr_enabled(dentry)) + return -EOPNOTSUPP; + return simple_xattr_list(__d_xattrs(dentry), buf, size); +} + static const struct file_operations cgroup_file_operations = { .read = cgroup_file_read, .write = cgroup_file_write, @@ -2559,11 +2655,22 @@ static const struct file_operations cgroup_file_operations = { .release = cgroup_file_release, }; +static const struct inode_operations cgroup_file_inode_operations = { + .setxattr = cgroup_setxattr, + .getxattr = cgroup_getxattr, + .listxattr = cgroup_listxattr, + .removexattr = cgroup_removexattr, +}; + static const struct inode_operations cgroup_dir_inode_operations = { .lookup = cgroup_lookup, .mkdir = cgroup_mkdir, .rmdir = cgroup_rmdir, .rename = cgroup_rename, + .setxattr = cgroup_setxattr, + .getxattr = cgroup_getxattr, + .listxattr = cgroup_listxattr, + .removexattr = cgroup_removexattr, }; static struct dentry *cgroup_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) @@ -2611,6 +2718,7 @@ static int cgroup_create_file(struct dentry *dentry, umode_t mode, } else if (S_ISREG(mode)) { inode->i_size = 0; inode->i_fop = &cgroup_file_operations; + inode->i_op = &cgroup_file_inode_operations; } d_instantiate(dentry, inode); dget(dentry); /* Extra count - pin the dentry in core */ @@ -2671,7 +2779,7 @@ static umode_t cgroup_file_mode(const struct cftype *cft) } static int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys, - const struct cftype *cft) + struct cftype *cft) { struct dentry *dir = cgrp->dentry; struct cgroup *parent = __d_cgrp(dir); @@ -2681,6 +2789,8 @@ static int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys, umode_t mode; char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 }; + simple_xattrs_init(&cft->xattrs); + /* does @cft->flags tell us to skip creation on @cgrp? */ if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgrp->parent) return 0; @@ -2721,9 +2831,9 @@ out: } static int cgroup_addrm_files(struct cgroup *cgrp, struct cgroup_subsys *subsys, - const struct cftype cfts[], bool is_add) + struct cftype cfts[], bool is_add) { - const struct cftype *cft; + struct cftype *cft; int err, ret = 0; for (cft = cfts; cft->name[0] != '\0'; cft++) { @@ -2757,7 +2867,7 @@ static void cgroup_cfts_prepare(void) } static void cgroup_cfts_commit(struct cgroup_subsys *ss, - const struct cftype *cfts, bool is_add) + struct cftype *cfts, bool is_add) __releases(&cgroup_mutex) __releases(&cgroup_cft_mutex) { LIST_HEAD(pending); @@ -2808,7 +2918,7 @@ static void cgroup_cfts_commit(struct cgroup_subsys *ss, * function currently returns 0 as long as @cfts registration is successful * even if some file creation attempts on existing cgroups fail. */ -int cgroup_add_cftypes(struct cgroup_subsys *ss, const struct cftype *cfts) +int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { struct cftype_set *set; @@ -2838,7 +2948,7 @@ EXPORT_SYMBOL_GPL(cgroup_add_cftypes); * Returns 0 on successful unregistration, -ENOENT if @cfts is not * registered with @ss. */ -int cgroup_rm_cftypes(struct cgroup_subsys *ss, const struct cftype *cfts) +int cgroup_rm_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { struct cftype_set *set; @@ -3843,18 +3953,29 @@ static struct cftype files[] = { { } /* terminate */ }; -static int cgroup_populate_dir(struct cgroup *cgrp) +/** + * cgroup_populate_dir - selectively creation of files in a directory + * @cgrp: target cgroup + * @base_files: true if the base files should be added + * @subsys_mask: mask of the subsystem ids whose files should be added + */ +static int cgroup_populate_dir(struct cgroup *cgrp, bool base_files, + unsigned long subsys_mask) { int err; struct cgroup_subsys *ss; - err = cgroup_addrm_files(cgrp, NULL, files, true); - if (err < 0) - return err; + if (base_files) { + err = cgroup_addrm_files(cgrp, NULL, files, true); + if (err < 0) + return err; + } /* process cftsets of each subsystem */ for_each_subsys(cgrp->root, ss) { struct cftype_set *set; + if (!test_bit(ss->subsys_id, &subsys_mask)) + continue; list_for_each_entry(set, &ss->cftsets, node) cgroup_addrm_files(cgrp, ss, set->cfts, true); @@ -3954,8 +4075,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags); for_each_subsys(root, ss) { - struct cgroup_subsys_state *css = ss->create(cgrp); + struct cgroup_subsys_state *css; + css = ss->create(cgrp); if (IS_ERR(css)) { err = PTR_ERR(css); goto err_destroy; @@ -3969,6 +4091,15 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, /* At error, ->destroy() callback has to free assigned ID. */ if (clone_children(parent) && ss->post_clone) ss->post_clone(cgrp); + + if (ss->broken_hierarchy && !ss->warned_broken_hierarchy && + parent->parent) { + pr_warning("cgroup: %s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n", + current->comm, current->pid, ss->name); + if (!strcmp(ss->name, "memory")) + pr_warning("cgroup: \"memory\" requires setting use_hierarchy to 1 on the root.\n"); + ss->warned_broken_hierarchy = true; + } } list_add(&cgrp->sibling, &cgrp->parent->children); @@ -3988,7 +4119,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, list_add_tail(&cgrp->allcg_node, &root->allcg_list); - err = cgroup_populate_dir(cgrp); + err = cgroup_populate_dir(cgrp, true, root->subsys_mask); /* If err < 0, we have a half-filled directory - oh well ;) */ mutex_unlock(&cgroup_mutex); @@ -4321,8 +4452,7 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss) * since cgroup_init_subsys will have already taken care of it. */ if (ss->module == NULL) { - /* a few sanity checks */ - BUG_ON(ss->subsys_id >= CGROUP_BUILTIN_SUBSYS_COUNT); + /* a sanity check */ BUG_ON(subsys[ss->subsys_id] != ss); return 0; } @@ -4330,24 +4460,8 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss) /* init base cftset */ cgroup_init_cftsets(ss); - /* - * need to register a subsys id before anything else - for example, - * init_cgroup_css needs it. - */ mutex_lock(&cgroup_mutex); - /* find the first empty slot in the array */ - for (i = CGROUP_BUILTIN_SUBSYS_COUNT; i < CGROUP_SUBSYS_COUNT; i++) { - if (subsys[i] == NULL) - break; - } - if (i == CGROUP_SUBSYS_COUNT) { - /* maximum number of subsystems already registered! */ - mutex_unlock(&cgroup_mutex); - return -EBUSY; - } - /* assign ourselves the subsys_id */ - ss->subsys_id = i; - subsys[i] = ss; + subsys[ss->subsys_id] = ss; /* * no ss->create seems to need anything important in the ss struct, so @@ -4356,7 +4470,7 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss) css = ss->create(dummytop); if (IS_ERR(css)) { /* failure case - need to deassign the subsys[] slot. */ - subsys[i] = NULL; + subsys[ss->subsys_id] = NULL; mutex_unlock(&cgroup_mutex); return PTR_ERR(css); } @@ -4372,7 +4486,7 @@ int __init_or_module cgroup_load_subsys(struct cgroup_subsys *ss) if (ret) { dummytop->subsys[ss->subsys_id] = NULL; ss->destroy(dummytop); - subsys[i] = NULL; + subsys[ss->subsys_id] = NULL; mutex_unlock(&cgroup_mutex); return ret; } @@ -4439,7 +4553,6 @@ void cgroup_unload_subsys(struct cgroup_subsys *ss) mutex_lock(&cgroup_mutex); /* deassign the subsys_id */ - BUG_ON(ss->subsys_id < CGROUP_BUILTIN_SUBSYS_COUNT); subsys[ss->subsys_id] = NULL; /* remove subsystem from rootnode's list of subsystems */ @@ -4502,10 +4615,13 @@ int __init cgroup_init_early(void) for (i = 0; i < CSS_SET_TABLE_SIZE; i++) INIT_HLIST_HEAD(&css_set_table[i]); - /* at bootup time, we don't worry about modular subsystems */ - for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) { + for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { struct cgroup_subsys *ss = subsys[i]; + /* at bootup time, we don't worry about modular subsystems */ + if (!ss || ss->module) + continue; + BUG_ON(!ss->name); BUG_ON(strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN); BUG_ON(!ss->create); @@ -4538,9 +4654,12 @@ int __init cgroup_init(void) if (err) return err; - /* at bootup time, we don't worry about modular subsystems */ - for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) { + for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { struct cgroup_subsys *ss = subsys[i]; + + /* at bootup time, we don't worry about modular subsystems */ + if (!ss || ss->module) + continue; if (!ss->early_init) cgroup_init_subsys(ss); if (ss->use_id) @@ -4695,31 +4814,20 @@ static const struct file_operations proc_cgroupstats_operations = { * * A pointer to the shared css_set was automatically copied in * fork.c by dup_task_struct(). However, we ignore that copy, since - * it was not made under the protection of RCU, cgroup_mutex or - * threadgroup_change_begin(), so it might no longer be a valid - * cgroup pointer. cgroup_attach_task() might have already changed - * current->cgroups, allowing the previously referenced cgroup - * group to be removed and freed. - * - * Outside the pointer validity we also need to process the css_set - * inheritance between threadgoup_change_begin() and - * threadgoup_change_end(), this way there is no leak in any process - * wide migration performed by cgroup_attach_proc() that could otherwise - * miss a thread because it is too early or too late in the fork stage. + * it was not made under the protection of RCU or cgroup_mutex, so + * might no longer be a valid cgroup pointer. cgroup_attach_task() might + * have already changed current->cgroups, allowing the previously + * referenced cgroup group to be removed and freed. * * At the point that cgroup_fork() is called, 'current' is the parent * task, and the passed argument 'child' points to the child task. */ void cgroup_fork(struct task_struct *child) { - /* - * We don't need to task_lock() current because current->cgroups - * can't be changed concurrently here. The parent obviously hasn't - * exited and called cgroup_exit(), and we are synchronized against - * cgroup migration through threadgroup_change_begin(). - */ + task_lock(current); child->cgroups = current->cgroups; get_css_set(child->cgroups); + task_unlock(current); INIT_LIST_HEAD(&child->cg_list); } @@ -4735,13 +4843,16 @@ void cgroup_fork_callbacks(struct task_struct *child) { if (need_forkexit_callback) { int i; - /* - * forkexit callbacks are only supported for builtin - * subsystems, and the builtin section of the subsys array is - * immutable, so we don't need to lock the subsys array here. - */ - for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) { + for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { struct cgroup_subsys *ss = subsys[i]; + + /* + * forkexit callbacks are only supported for + * builtin subsystems. + */ + if (!ss || ss->module) + continue; + if (ss->fork) ss->fork(child); } @@ -4772,19 +4883,10 @@ void cgroup_post_fork(struct task_struct *child) */ if (use_task_css_set_links) { write_lock(&css_set_lock); - if (list_empty(&child->cg_list)) { - /* - * It's safe to use child->cgroups without task_lock() - * here because we are protected through - * threadgroup_change_begin() against concurrent - * css_set change in cgroup_task_migrate(). Also - * the task can't exit at that point until - * wake_up_new_task() is called, so we are protected - * against cgroup_exit() setting child->cgroup to - * init_css_set. - */ + task_lock(child); + if (list_empty(&child->cg_list)) list_add(&child->cg_list, &child->cgroups->tasks); - } + task_unlock(child); write_unlock(&css_set_lock); } } @@ -4846,12 +4948,13 @@ void cgroup_exit(struct task_struct *tsk, int run_callbacks) tsk->cgroups = &init_css_set; if (run_callbacks && need_forkexit_callback) { - /* - * modular subsystems can't use callbacks, so no need to lock - * the subsys array - */ - for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) { + for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { struct cgroup_subsys *ss = subsys[i]; + + /* modular subsystems can't use callbacks */ + if (!ss || ss->module) + continue; + if (ss->exit) { struct cgroup *old_cgrp = rcu_dereference_raw(cg->subsys[i])->cgroup; @@ -5037,13 +5140,17 @@ static int __init cgroup_disable(char *str) while ((token = strsep(&str, ",")) != NULL) { if (!*token) continue; - /* - * cgroup_disable, being at boot time, can't know about module - * subsystems, so we don't worry about them. - */ - for (i = 0; i < CGROUP_BUILTIN_SUBSYS_COUNT; i++) { + for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { struct cgroup_subsys *ss = subsys[i]; + /* + * cgroup_disable, being at boot time, can't + * know about module subsystems, so we don't + * worry about them. + */ + if (!ss || ss->module) + continue; + if (!strcmp(token, ss->name)) { ss->disabled = 1; printk(KERN_INFO "Disabling %s control group" diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index 3649fc6b3eaa..b1724ce98981 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -373,4 +373,12 @@ struct cgroup_subsys freezer_subsys = { .can_attach = freezer_can_attach, .fork = freezer_fork, .base_cftypes = files, + + /* + * freezer subsys doesn't handle hierarchy at all. Frozen state + * should be inherited through the hierarchy - if a parent is + * frozen, all its children should be frozen. Fix it and remove + * the following. + */ + .broken_hierarchy = true, }; diff --git a/kernel/cpu.c b/kernel/cpu.c index 14d32588cccd..42bd331ee0ab 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -80,6 +80,10 @@ void put_online_cpus(void) if (cpu_hotplug.active_writer == current) return; mutex_lock(&cpu_hotplug.lock); + + if (WARN_ON(!cpu_hotplug.refcount)) + cpu_hotplug.refcount++; /* try to fix things up */ + if (!--cpu_hotplug.refcount && unlikely(cpu_hotplug.active_writer)) wake_up_process(cpu_hotplug.active_writer); mutex_unlock(&cpu_hotplug.lock); @@ -280,12 +284,13 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) __func__, cpu); goto out_release; } + smpboot_park_threads(cpu); err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu)); if (err) { /* CPU didn't die: tell everyone. Can't complain. */ + smpboot_unpark_threads(cpu); cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu); - goto out_release; } BUG_ON(cpu_online(cpu)); @@ -354,6 +359,10 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen) goto out; } + ret = smpboot_create_threads(cpu); + if (ret) + goto out; + ret = __cpu_notify(CPU_UP_PREPARE | mod, hcpu, -1, &nr_calls); if (ret) { nr_calls--; @@ -368,6 +377,9 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen) goto out_notify; BUG_ON(!cpu_online(cpu)); + /* Wake the per cpu threads */ + smpboot_unpark_threads(cpu); + /* Now call notifier in preparation. */ cpu_notify(CPU_ONLINE | mod, hcpu); @@ -439,14 +451,6 @@ EXPORT_SYMBOL_GPL(cpu_up); #ifdef CONFIG_PM_SLEEP_SMP static cpumask_var_t frozen_cpus; -void __weak arch_disable_nonboot_cpus_begin(void) -{ -} - -void __weak arch_disable_nonboot_cpus_end(void) -{ -} - int disable_nonboot_cpus(void) { int cpu, first_cpu, error = 0; @@ -458,7 +462,6 @@ int disable_nonboot_cpus(void) * with the userspace trying to use the CPU hotplug at the same time */ cpumask_clear(frozen_cpus); - arch_disable_nonboot_cpus_begin(); printk("Disabling non-boot CPUs ...\n"); for_each_online_cpu(cpu) { @@ -474,8 +477,6 @@ int disable_nonboot_cpus(void) } } - arch_disable_nonboot_cpus_end(); - if (!error) { BUG_ON(num_online_cpus() > 1); /* Make sure the CPUs won't be enabled by someone else */ diff --git a/kernel/cred.c b/kernel/cred.c index de728ac50d82..48cea3da6d05 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -799,9 +799,15 @@ static void dump_invalid_creds(const struct cred *cred, const char *label, atomic_read(&cred->usage), read_cred_subscribers(cred)); printk(KERN_ERR "CRED: ->*uid = { %d,%d,%d,%d }\n", - cred->uid, cred->euid, cred->suid, cred->fsuid); + from_kuid_munged(&init_user_ns, cred->uid), + from_kuid_munged(&init_user_ns, cred->euid), + from_kuid_munged(&init_user_ns, cred->suid), + from_kuid_munged(&init_user_ns, cred->fsuid)); printk(KERN_ERR "CRED: ->*gid = { %d,%d,%d,%d }\n", - cred->gid, cred->egid, cred->sgid, cred->fsgid); + from_kgid_munged(&init_user_ns, cred->gid), + from_kgid_munged(&init_user_ns, cred->egid), + from_kgid_munged(&init_user_ns, cred->sgid), + from_kgid_munged(&init_user_ns, cred->fsgid)); #ifdef CONFIG_SECURITY printk(KERN_ERR "CRED: ->security is %p\n", cred->security); if ((unsigned long) cred->security >= PAGE_SIZE && diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 0557f24c6bca..9a61738cefc8 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -672,6 +672,10 @@ kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs) { struct kgdb_state kgdb_var; struct kgdb_state *ks = &kgdb_var; + int ret = 0; + + if (arch_kgdb_ops.enable_nmi) + arch_kgdb_ops.enable_nmi(0); ks->cpu = raw_smp_processor_id(); ks->ex_vector = evector; @@ -681,13 +685,33 @@ kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs) ks->linux_regs = regs; if (kgdb_reenter_check(ks)) - return 0; /* Ouch, double exception ! */ + goto out; /* Ouch, double exception ! */ if (kgdb_info[ks->cpu].enter_kgdb != 0) - return 0; + goto out; - return kgdb_cpu_enter(ks, regs, DCPU_WANT_MASTER); + ret = kgdb_cpu_enter(ks, regs, DCPU_WANT_MASTER); +out: + if (arch_kgdb_ops.enable_nmi) + arch_kgdb_ops.enable_nmi(1); + return ret; } +/* + * GDB places a breakpoint at this function to know dynamically + * loaded objects. It's not defined static so that only one instance with this + * name exists in the kernel. + */ + +static int module_event(struct notifier_block *self, unsigned long val, + void *data) +{ + return 0; +} + +static struct notifier_block dbg_module_load_nb = { + .notifier_call = module_event, +}; + int kgdb_nmicallback(int cpu, void *regs) { #ifdef CONFIG_SMP @@ -816,6 +840,7 @@ static void kgdb_register_callbacks(void) kgdb_arch_init(); if (!dbg_is_early) kgdb_arch_late(); + register_module_notifier(&dbg_module_load_nb); register_reboot_notifier(&dbg_reboot_notifier); atomic_notifier_chain_register(&panic_notifier_list, &kgdb_panic_event_nb); @@ -839,6 +864,7 @@ static void kgdb_unregister_callbacks(void) if (kgdb_io_module_registered) { kgdb_io_module_registered = 0; unregister_reboot_notifier(&dbg_reboot_notifier); + unregister_module_notifier(&dbg_module_load_nb); atomic_notifier_chain_unregister(&panic_notifier_list, &kgdb_panic_event_nb); kgdb_arch_exit(); diff --git a/kernel/debug/kdb/kdb_bt.c b/kernel/debug/kdb/kdb_bt.c index 07c9bbb94a0b..b03e0e814e43 100644 --- a/kernel/debug/kdb/kdb_bt.c +++ b/kernel/debug/kdb/kdb_bt.c @@ -129,6 +129,8 @@ kdb_bt(int argc, const char **argv) } /* Now the inactive tasks */ kdb_do_each_thread(g, p) { + if (KDB_FLAG(CMD_INTERRUPT)) + return 0; if (task_curr(p)) continue; if (kdb_bt1(p, mask, argcount, btaprompt)) diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c index 0a69d2adc4f3..14ff4849262c 100644 --- a/kernel/debug/kdb/kdb_io.c +++ b/kernel/debug/kdb/kdb_io.c @@ -552,6 +552,7 @@ int vkdb_printf(const char *fmt, va_list ap) { int diag; int linecount; + int colcount; int logging, saved_loglevel = 0; int saved_trap_printk; int got_printf_lock = 0; @@ -584,6 +585,10 @@ int vkdb_printf(const char *fmt, va_list ap) if (diag || linecount <= 1) linecount = 24; + diag = kdbgetintenv("COLUMNS", &colcount); + if (diag || colcount <= 1) + colcount = 80; + diag = kdbgetintenv("LOGGING", &logging); if (diag) logging = 0; @@ -690,7 +695,7 @@ kdb_printit: gdbstub_msg_write(kdb_buffer, retlen); } else { if (dbg_io_ops && !dbg_io_ops->is_console) { - len = strlen(kdb_buffer); + len = retlen; cp = kdb_buffer; while (len--) { dbg_io_ops->write_char(*cp); @@ -709,11 +714,29 @@ kdb_printit: printk(KERN_INFO "%s", kdb_buffer); } - if (KDB_STATE(PAGER) && strchr(kdb_buffer, '\n')) - kdb_nextline++; + if (KDB_STATE(PAGER)) { + /* + * Check printed string to decide how to bump the + * kdb_nextline to control when the more prompt should + * show up. + */ + int got = 0; + len = retlen; + while (len--) { + if (kdb_buffer[len] == '\n') { + kdb_nextline++; + got = 0; + } else if (kdb_buffer[len] == '\r') { + got = 0; + } else { + got++; + } + } + kdb_nextline += got / (colcount + 1); + } /* check for having reached the LINES number of printed lines */ - if (kdb_nextline == linecount) { + if (kdb_nextline >= linecount) { char buf1[16] = ""; /* Watch out for recursion here. Any routine that calls @@ -765,7 +788,7 @@ kdb_printit: kdb_grepping_flag = 0; kdb_printf("\n"); } else if (buf1[0] == ' ') { - kdb_printf("\n"); + kdb_printf("\r"); suspend_grep = 1; /* for this recursion */ } else if (buf1[0] == '\n') { kdb_nextline = linecount - 1; diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 31df1706b9a9..4d5f8d5612f3 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -21,6 +21,7 @@ #include <linux/smp.h> #include <linux/utsname.h> #include <linux/vmalloc.h> +#include <linux/atomic.h> #include <linux/module.h> #include <linux/mm.h> #include <linux/init.h> @@ -2100,6 +2101,8 @@ static int kdb_dmesg(int argc, const char **argv) } if (!lines--) break; + if (KDB_FLAG(CMD_INTERRUPT)) + return 0; kdb_printf("%.*s\n", (int)len - 1, buf); } @@ -2107,6 +2110,32 @@ static int kdb_dmesg(int argc, const char **argv) return 0; } #endif /* CONFIG_PRINTK */ + +/* Make sure we balance enable/disable calls, must disable first. */ +static atomic_t kdb_nmi_disabled; + +static int kdb_disable_nmi(int argc, const char *argv[]) +{ + if (atomic_read(&kdb_nmi_disabled)) + return 0; + atomic_set(&kdb_nmi_disabled, 1); + arch_kgdb_ops.enable_nmi(0); + return 0; +} + +static int kdb_param_enable_nmi(const char *val, const struct kernel_param *kp) +{ + if (!atomic_add_unless(&kdb_nmi_disabled, -1, 0)) + return -EINVAL; + arch_kgdb_ops.enable_nmi(1); + return 0; +} + +static const struct kernel_param_ops kdb_param_ops_enable_nmi = { + .set = kdb_param_enable_nmi, +}; +module_param_cb(enable_nmi, &kdb_param_ops_enable_nmi, NULL, 0600); + /* * kdb_cpu - This function implements the 'cpu' command. * cpu [<cpunum>] @@ -2851,6 +2880,10 @@ static void __init kdb_inittab(void) kdb_register_repeat("dmesg", kdb_dmesg, "[lines]", "Display syslog buffer", 0, KDB_REPEAT_NONE); #endif + if (arch_kgdb_ops.enable_nmi) { + kdb_register_repeat("disable_nmi", kdb_disable_nmi, "", + "Disable NMI entry to KDB", 0, KDB_REPEAT_NONE); + } kdb_register_repeat("defcmd", kdb_defcmd, "name \"usage\" \"help\"", "Define a set of commands, down to endefcmd", 0, KDB_REPEAT_NONE); kdb_register_repeat("kill", kdb_kill, "<-signal> <pid>", diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c index 98d4597f43d6..c77206184b8b 100644 --- a/kernel/events/callchain.c +++ b/kernel/events/callchain.c @@ -159,6 +159,11 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs) int rctx; struct perf_callchain_entry *entry; + int kernel = !event->attr.exclude_callchain_kernel; + int user = !event->attr.exclude_callchain_user; + + if (!kernel && !user) + return NULL; entry = get_callchain_entry(&rctx); if (rctx == -1) @@ -169,24 +174,29 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs) entry->nr = 0; - if (!user_mode(regs)) { + if (kernel && !user_mode(regs)) { perf_callchain_store(entry, PERF_CONTEXT_KERNEL); perf_callchain_kernel(entry, regs); - if (current->mm) - regs = task_pt_regs(current); - else - regs = NULL; } - if (regs) { - /* - * Disallow cross-task user callchains. - */ - if (event->ctx->task && event->ctx->task != current) - goto exit_put; - - perf_callchain_store(entry, PERF_CONTEXT_USER); - perf_callchain_user(entry, regs); + if (user) { + if (!user_mode(regs)) { + if (current->mm) + regs = task_pt_regs(current); + else + regs = NULL; + } + + if (regs) { + /* + * Disallow cross-task user callchains. + */ + if (event->ctx->task && event->ctx->task != current) + goto exit_put; + + perf_callchain_store(entry, PERF_CONTEXT_USER); + perf_callchain_user(entry, regs); + } } exit_put: diff --git a/kernel/events/core.c b/kernel/events/core.c index 7fee567153f0..dbccf83c134d 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -36,6 +36,7 @@ #include <linux/perf_event.h> #include <linux/ftrace_event.h> #include <linux/hw_breakpoint.h> +#include <linux/mm_types.h> #include "internal.h" @@ -371,6 +372,8 @@ void perf_cgroup_switch(struct task_struct *task, int mode) list_for_each_entry_rcu(pmu, &pmus, entry) { cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); + if (cpuctx->unique_pmu != pmu) + continue; /* ensure we process each cpuctx once */ /* * perf_cgroup_events says at least one @@ -394,9 +397,10 @@ void perf_cgroup_switch(struct task_struct *task, int mode) if (mode & PERF_CGROUP_SWIN) { WARN_ON_ONCE(cpuctx->cgrp); - /* set cgrp before ctxsw in to - * allow event_filter_match() to not - * have to pass task around + /* + * set cgrp before ctxsw in to allow + * event_filter_match() to not have to pass + * task around */ cpuctx->cgrp = perf_cgroup_from_task(task); cpu_ctx_sched_in(cpuctx, EVENT_ALL, task); @@ -467,14 +471,13 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event, { struct perf_cgroup *cgrp; struct cgroup_subsys_state *css; - struct file *file; - int ret = 0, fput_needed; + struct fd f = fdget(fd); + int ret = 0; - file = fget_light(fd, &fput_needed); - if (!file) + if (!f.file) return -EBADF; - css = cgroup_css_from_dir(file, perf_subsys_id); + css = cgroup_css_from_dir(f.file, perf_subsys_id); if (IS_ERR(css)) { ret = PTR_ERR(css); goto out; @@ -500,7 +503,7 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event, ret = -EINVAL; } out: - fput_light(file, fput_needed); + fdput(f); return ret; } @@ -3233,21 +3236,18 @@ unlock: static const struct file_operations perf_fops; -static struct file *perf_fget_light(int fd, int *fput_needed) +static inline int perf_fget_light(int fd, struct fd *p) { - struct file *file; - - file = fget_light(fd, fput_needed); - if (!file) - return ERR_PTR(-EBADF); + struct fd f = fdget(fd); + if (!f.file) + return -EBADF; - if (file->f_op != &perf_fops) { - fput_light(file, *fput_needed); - *fput_needed = 0; - return ERR_PTR(-EBADF); + if (f.file->f_op != &perf_fops) { + fdput(f); + return -EBADF; } - - return file; + *p = f; + return 0; } static int perf_event_set_output(struct perf_event *event, @@ -3279,22 +3279,19 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case PERF_EVENT_IOC_SET_OUTPUT: { - struct file *output_file = NULL; - struct perf_event *output_event = NULL; - int fput_needed = 0; int ret; - if (arg != -1) { - output_file = perf_fget_light(arg, &fput_needed); - if (IS_ERR(output_file)) - return PTR_ERR(output_file); - output_event = output_file->private_data; + struct perf_event *output_event; + struct fd output; + ret = perf_fget_light(arg, &output); + if (ret) + return ret; + output_event = output.file->private_data; + ret = perf_event_set_output(event, output_event); + fdput(output); + } else { + ret = perf_event_set_output(event, NULL); } - - ret = perf_event_set_output(event, output_event); - if (output_event) - fput_light(output_file, fput_needed); - return ret; } @@ -3677,7 +3674,7 @@ unlock: atomic_inc(&event->mmap_count); mutex_unlock(&event->mmap_mutex); - vma->vm_flags |= VM_RESERVED; + vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; vma->vm_ops = &perf_mmap_vmops; return ret; @@ -3764,6 +3761,132 @@ int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs) } EXPORT_SYMBOL_GPL(perf_unregister_guest_info_callbacks); +static void +perf_output_sample_regs(struct perf_output_handle *handle, + struct pt_regs *regs, u64 mask) +{ + int bit; + + for_each_set_bit(bit, (const unsigned long *) &mask, + sizeof(mask) * BITS_PER_BYTE) { + u64 val; + + val = perf_reg_value(regs, bit); + perf_output_put(handle, val); + } +} + +static void perf_sample_regs_user(struct perf_regs_user *regs_user, + struct pt_regs *regs) +{ + if (!user_mode(regs)) { + if (current->mm) + regs = task_pt_regs(current); + else + regs = NULL; + } + + if (regs) { + regs_user->regs = regs; + regs_user->abi = perf_reg_abi(current); + } +} + +/* + * Get remaining task size from user stack pointer. + * + * It'd be better to take stack vma map and limit this more + * precisly, but there's no way to get it safely under interrupt, + * so using TASK_SIZE as limit. + */ +static u64 perf_ustack_task_size(struct pt_regs *regs) +{ + unsigned long addr = perf_user_stack_pointer(regs); + + if (!addr || addr >= TASK_SIZE) + return 0; + + return TASK_SIZE - addr; +} + +static u16 +perf_sample_ustack_size(u16 stack_size, u16 header_size, + struct pt_regs *regs) +{ + u64 task_size; + + /* No regs, no stack pointer, no dump. */ + if (!regs) + return 0; + + /* + * Check if we fit in with the requested stack size into the: + * - TASK_SIZE + * If we don't, we limit the size to the TASK_SIZE. + * + * - remaining sample size + * If we don't, we customize the stack size to + * fit in to the remaining sample size. + */ + + task_size = min((u64) USHRT_MAX, perf_ustack_task_size(regs)); + stack_size = min(stack_size, (u16) task_size); + + /* Current header size plus static size and dynamic size. */ + header_size += 2 * sizeof(u64); + + /* Do we fit in with the current stack dump size? */ + if ((u16) (header_size + stack_size) < header_size) { + /* + * If we overflow the maximum size for the sample, + * we customize the stack dump size to fit in. + */ + stack_size = USHRT_MAX - header_size - sizeof(u64); + stack_size = round_up(stack_size, sizeof(u64)); + } + + return stack_size; +} + +static void +perf_output_sample_ustack(struct perf_output_handle *handle, u64 dump_size, + struct pt_regs *regs) +{ + /* Case of a kernel thread, nothing to dump */ + if (!regs) { + u64 size = 0; + perf_output_put(handle, size); + } else { + unsigned long sp; + unsigned int rem; + u64 dyn_size; + + /* + * We dump: + * static size + * - the size requested by user or the best one we can fit + * in to the sample max size + * data + * - user stack dump data + * dynamic size + * - the actual dumped size + */ + + /* Static size. */ + perf_output_put(handle, dump_size); + + /* Data. */ + sp = perf_user_stack_pointer(regs); + rem = __output_copy_user(handle, (void *) sp, dump_size); + dyn_size = dump_size - rem; + + perf_output_skip(handle, rem); + + /* Dynamic size. */ + perf_output_put(handle, dyn_size); + } +} + static void __perf_event_header__init_id(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event) @@ -4024,6 +4147,28 @@ void perf_output_sample(struct perf_output_handle *handle, perf_output_put(handle, nr); } } + + if (sample_type & PERF_SAMPLE_REGS_USER) { + u64 abi = data->regs_user.abi; + + /* + * If there are no regs to dump, notice it through + * first u64 being zero (PERF_SAMPLE_REGS_ABI_NONE). + */ + perf_output_put(handle, abi); + + if (abi) { + u64 mask = event->attr.sample_regs_user; + perf_output_sample_regs(handle, + data->regs_user.regs, + mask); + } + } + + if (sample_type & PERF_SAMPLE_STACK_USER) + perf_output_sample_ustack(handle, + data->stack_user_size, + data->regs_user.regs); } void perf_prepare_sample(struct perf_event_header *header, @@ -4075,6 +4220,49 @@ void perf_prepare_sample(struct perf_event_header *header, } header->size += size; } + + if (sample_type & PERF_SAMPLE_REGS_USER) { + /* regs dump ABI info */ + int size = sizeof(u64); + + perf_sample_regs_user(&data->regs_user, regs); + + if (data->regs_user.regs) { + u64 mask = event->attr.sample_regs_user; + size += hweight64(mask) * sizeof(u64); + } + + header->size += size; + } + + if (sample_type & PERF_SAMPLE_STACK_USER) { + /* + * Either we need PERF_SAMPLE_STACK_USER bit to be allways + * processed as the last one or have additional check added + * in case new sample type is added, because we could eat + * up the rest of the sample size. + */ + struct perf_regs_user *uregs = &data->regs_user; + u16 stack_size = event->attr.sample_stack_user; + u16 size = sizeof(u64); + + if (!uregs->abi) + perf_sample_regs_user(uregs, regs); + + stack_size = perf_sample_ustack_size(stack_size, header->size, + uregs->regs); + + /* + * If there is something to dump, add space for the dump + * itself and for the field that tells the dynamic size, + * which is how many have been actually dumped. + */ + if (stack_size) + size += sizeof(u64) + stack_size; + + data->stack_user_size = stack_size; + header->size += size; + } } static void perf_event_output(struct perf_event *event, @@ -4227,7 +4415,7 @@ static void perf_event_task_event(struct perf_task_event *task_event) rcu_read_lock(); list_for_each_entry_rcu(pmu, &pmus, entry) { cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); - if (cpuctx->active_pmu != pmu) + if (cpuctx->unique_pmu != pmu) goto next; perf_event_task_ctx(&cpuctx->ctx, task_event); @@ -4373,7 +4561,7 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event) rcu_read_lock(); list_for_each_entry_rcu(pmu, &pmus, entry) { cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); - if (cpuctx->active_pmu != pmu) + if (cpuctx->unique_pmu != pmu) goto next; perf_event_comm_ctx(&cpuctx->ctx, comm_event); @@ -4569,7 +4757,7 @@ got_name: rcu_read_lock(); list_for_each_entry_rcu(pmu, &pmus, entry) { cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); - if (cpuctx->active_pmu != pmu) + if (cpuctx->unique_pmu != pmu) goto next; perf_event_mmap_ctx(&cpuctx->ctx, mmap_event, vma->vm_flags & VM_EXEC); @@ -5670,8 +5858,8 @@ static void update_pmu_context(struct pmu *pmu, struct pmu *old_pmu) cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu); - if (cpuctx->active_pmu == old_pmu) - cpuctx->active_pmu = pmu; + if (cpuctx->unique_pmu == old_pmu) + cpuctx->unique_pmu = pmu; } } @@ -5806,7 +5994,7 @@ skip_type: cpuctx->ctx.pmu = pmu; cpuctx->jiffies_interval = 1; INIT_LIST_HEAD(&cpuctx->rotation_list); - cpuctx->active_pmu = pmu; + cpuctx->unique_pmu = pmu; } got_cpu_context: @@ -6151,6 +6339,28 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr, attr->branch_sample_type = mask; } } + + if (attr->sample_type & PERF_SAMPLE_REGS_USER) { + ret = perf_reg_validate(attr->sample_regs_user); + if (ret) + return ret; + } + + if (attr->sample_type & PERF_SAMPLE_STACK_USER) { + if (!arch_perf_have_user_stack_dump()) + return -ENOSYS; + + /* + * We have __u32 type for the size, but so far + * we can only use __u16 as maximum due to the + * __u16 sample size limit. + */ + if (attr->sample_stack_user >= USHRT_MAX) + ret = -EINVAL; + else if (!IS_ALIGNED(attr->sample_stack_user, sizeof(u64))) + ret = -EINVAL; + } + out: return ret; @@ -6229,12 +6439,11 @@ SYSCALL_DEFINE5(perf_event_open, struct perf_event_attr attr; struct perf_event_context *ctx; struct file *event_file = NULL; - struct file *group_file = NULL; + struct fd group = {NULL, 0}; struct task_struct *task = NULL; struct pmu *pmu; int event_fd; int move_group = 0; - int fput_needed = 0; int err; /* for future expandability... */ @@ -6264,17 +6473,15 @@ SYSCALL_DEFINE5(perf_event_open, if ((flags & PERF_FLAG_PID_CGROUP) && (pid == -1 || cpu == -1)) return -EINVAL; - event_fd = get_unused_fd_flags(O_RDWR); + event_fd = get_unused_fd(); if (event_fd < 0) return event_fd; if (group_fd != -1) { - group_file = perf_fget_light(group_fd, &fput_needed); - if (IS_ERR(group_file)) { - err = PTR_ERR(group_file); + err = perf_fget_light(group_fd, &group); + if (err) goto err_fd; - } - group_leader = group_file->private_data; + group_leader = group.file->private_data; if (flags & PERF_FLAG_FD_OUTPUT) output_event = group_leader; if (flags & PERF_FLAG_FD_NO_GROUP) @@ -6450,7 +6657,7 @@ SYSCALL_DEFINE5(perf_event_open, * of the group leader will find the pointer to itself in * perf_group_detach(). */ - fput_light(group_file, fput_needed); + fdput(group); fd_install(event_fd, event_file); return event_fd; @@ -6464,7 +6671,7 @@ err_task: if (task) put_task_struct(task); err_group_fd: - fput_light(group_file, fput_needed); + fdput(group); err_fd: put_unused_fd(event_fd); return err; @@ -7289,5 +7496,12 @@ struct cgroup_subsys perf_subsys = { .destroy = perf_cgroup_destroy, .exit = perf_cgroup_exit, .attach = perf_cgroup_attach, + + /* + * perf_event cgroup doesn't handle nesting correctly. + * ctx->nr_cgroups adjustments should be propagated through the + * cgroup hierarchy. Fix it and remove the following. + */ + .broken_hierarchy = true, }; #endif /* CONFIG_CGROUP_PERF */ diff --git a/kernel/events/internal.h b/kernel/events/internal.h index a096c19f2c2a..d56a64c99a8b 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -2,6 +2,7 @@ #define _KERNEL_EVENTS_INTERNAL_H #include <linux/hardirq.h> +#include <linux/uaccess.h> /* Buffer handling */ @@ -76,30 +77,53 @@ static inline unsigned long perf_data_size(struct ring_buffer *rb) return rb->nr_pages << (PAGE_SHIFT + page_order(rb)); } -static inline void -__output_copy(struct perf_output_handle *handle, - const void *buf, unsigned int len) +#define DEFINE_OUTPUT_COPY(func_name, memcpy_func) \ +static inline unsigned int \ +func_name(struct perf_output_handle *handle, \ + const void *buf, unsigned int len) \ +{ \ + unsigned long size, written; \ + \ + do { \ + size = min_t(unsigned long, handle->size, len); \ + \ + written = memcpy_func(handle->addr, buf, size); \ + \ + len -= written; \ + handle->addr += written; \ + buf += written; \ + handle->size -= written; \ + if (!handle->size) { \ + struct ring_buffer *rb = handle->rb; \ + \ + handle->page++; \ + handle->page &= rb->nr_pages - 1; \ + handle->addr = rb->data_pages[handle->page]; \ + handle->size = PAGE_SIZE << page_order(rb); \ + } \ + } while (len && written == size); \ + \ + return len; \ +} + +static inline int memcpy_common(void *dst, const void *src, size_t n) { - do { - unsigned long size = min_t(unsigned long, handle->size, len); - - memcpy(handle->addr, buf, size); - - len -= size; - handle->addr += size; - buf += size; - handle->size -= size; - if (!handle->size) { - struct ring_buffer *rb = handle->rb; - - handle->page++; - handle->page &= rb->nr_pages - 1; - handle->addr = rb->data_pages[handle->page]; - handle->size = PAGE_SIZE << page_order(rb); - } - } while (len); + memcpy(dst, src, n); + return n; } +DEFINE_OUTPUT_COPY(__output_copy, memcpy_common) + +#define MEMCPY_SKIP(dst, src, n) (n) + +DEFINE_OUTPUT_COPY(__output_skip, MEMCPY_SKIP) + +#ifndef arch_perf_out_copy_user +#define arch_perf_out_copy_user __copy_from_user_inatomic +#endif + +DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user) + /* Callchain handling */ extern struct perf_callchain_entry * perf_callchain(struct perf_event *event, struct pt_regs *regs); @@ -134,4 +158,20 @@ static inline void put_recursion_context(int *recursion, int rctx) recursion[rctx]--; } +#ifdef CONFIG_HAVE_PERF_USER_STACK_DUMP +static inline bool arch_perf_have_user_stack_dump(void) +{ + return true; +} + +#define perf_user_stack_pointer(regs) user_stack_pointer(regs) +#else +static inline bool arch_perf_have_user_stack_dump(void) +{ + return false; +} + +#define perf_user_stack_pointer(regs) 0 +#endif /* CONFIG_HAVE_PERF_USER_STACK_DUMP */ + #endif /* _KERNEL_EVENTS_INTERNAL_H */ diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 6ddaba43fb7a..23cb34ff3973 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -182,10 +182,16 @@ out: return -ENOSPC; } -void perf_output_copy(struct perf_output_handle *handle, +unsigned int perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len) { - __output_copy(handle, buf, len); + return __output_copy(handle, buf, len); +} + +unsigned int perf_output_skip(struct perf_output_handle *handle, + unsigned int len) +{ + return __output_skip(handle, NULL, len); } void perf_output_end(struct perf_output_handle *handle) diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index c08a22d02f72..5cc4e7e42e68 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -78,15 +78,23 @@ static struct mutex uprobes_mmap_mutex[UPROBES_HASH_SZ]; */ static atomic_t uprobe_events = ATOMIC_INIT(0); +/* Have a copy of original instruction */ +#define UPROBE_COPY_INSN 0 +/* Dont run handlers when first register/ last unregister in progress*/ +#define UPROBE_RUN_HANDLER 1 +/* Can skip singlestep */ +#define UPROBE_SKIP_SSTEP 2 + struct uprobe { struct rb_node rb_node; /* node in the rb tree */ atomic_t ref; struct rw_semaphore consumer_rwsem; + struct mutex copy_mutex; /* TODO: kill me and UPROBE_COPY_INSN */ struct list_head pending_list; struct uprobe_consumer *consumers; struct inode *inode; /* Also hold a ref to inode */ loff_t offset; - int flags; + unsigned long flags; struct arch_uprobe arch; }; @@ -100,17 +108,12 @@ struct uprobe { */ static bool valid_vma(struct vm_area_struct *vma, bool is_register) { - if (!vma->vm_file) - return false; + vm_flags_t flags = VM_HUGETLB | VM_MAYEXEC | VM_SHARED; - if (!is_register) - return true; + if (is_register) + flags |= VM_WRITE; - if ((vma->vm_flags & (VM_HUGETLB|VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)) - == (VM_READ|VM_EXEC)) - return true; - - return false; + return vma->vm_file && (vma->vm_flags & flags) == VM_MAYEXEC; } static unsigned long offset_to_vaddr(struct vm_area_struct *vma, loff_t offset) @@ -141,10 +144,14 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, spinlock_t *ptl; pte_t *ptep; int err; + /* For mmu_notifiers */ + const unsigned long mmun_start = addr; + const unsigned long mmun_end = addr + PAGE_SIZE; /* For try_to_free_swap() and munlock_vma_page() below */ lock_page(page); + mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); err = -EAGAIN; ptep = page_check_address(page, mm, addr, &ptl, 0); if (!ptep) @@ -173,6 +180,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, err = 0; unlock: + mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); unlock_page(page); return err; } @@ -188,19 +196,44 @@ bool __weak is_swbp_insn(uprobe_opcode_t *insn) return *insn == UPROBE_SWBP_INSN; } +static void copy_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t *opcode) +{ + void *kaddr = kmap_atomic(page); + memcpy(opcode, kaddr + (vaddr & ~PAGE_MASK), UPROBE_SWBP_INSN_SIZE); + kunmap_atomic(kaddr); +} + +static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t *new_opcode) +{ + uprobe_opcode_t old_opcode; + bool is_swbp; + + copy_opcode(page, vaddr, &old_opcode); + is_swbp = is_swbp_insn(&old_opcode); + + if (is_swbp_insn(new_opcode)) { + if (is_swbp) /* register: already installed? */ + return 0; + } else { + if (!is_swbp) /* unregister: was it changed by us? */ + return 0; + } + + return 1; +} + /* * NOTE: * Expect the breakpoint instruction to be the smallest size instruction for * the architecture. If an arch has variable length instruction and the * breakpoint instruction is not of the smallest length instruction - * supported by that architecture then we need to modify read_opcode / + * supported by that architecture then we need to modify is_swbp_at_addr and * write_opcode accordingly. This would never be a problem for archs that * have fixed length instructions. */ /* * write_opcode - write the opcode at a given virtual address. - * @auprobe: arch breakpointing information. * @mm: the probed process address space. * @vaddr: the virtual address to store the opcode. * @opcode: opcode to be written at @vaddr. @@ -211,8 +244,8 @@ bool __weak is_swbp_insn(uprobe_opcode_t *insn) * For mm @mm, write the opcode at @vaddr. * Return 0 (success) or a negative errno. */ -static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, - unsigned long vaddr, uprobe_opcode_t opcode) +static int write_opcode(struct mm_struct *mm, unsigned long vaddr, + uprobe_opcode_t opcode) { struct page *old_page, *new_page; void *vaddr_old, *vaddr_new; @@ -221,10 +254,14 @@ static int write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, retry: /* Read the page with vaddr into memory */ - ret = get_user_pages(NULL, mm, vaddr, 1, 0, 0, &old_page, &vma); + ret = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &old_page, &vma); if (ret <= 0) return ret; + ret = verify_opcode(old_page, vaddr, &opcode); + if (ret <= 0) + goto put_old; + ret = -ENOMEM; new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr); if (!new_page) @@ -259,65 +296,6 @@ put_old: } /** - * read_opcode - read the opcode at a given virtual address. - * @mm: the probed process address space. - * @vaddr: the virtual address to read the opcode. - * @opcode: location to store the read opcode. - * - * Called with mm->mmap_sem held (for read and with a reference to - * mm. - * - * For mm @mm, read the opcode at @vaddr and store it in @opcode. - * Return 0 (success) or a negative errno. - */ -static int read_opcode(struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t *opcode) -{ - struct page *page; - void *vaddr_new; - int ret; - - ret = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &page, NULL); - if (ret <= 0) - return ret; - - lock_page(page); - vaddr_new = kmap_atomic(page); - vaddr &= ~PAGE_MASK; - memcpy(opcode, vaddr_new + vaddr, UPROBE_SWBP_INSN_SIZE); - kunmap_atomic(vaddr_new); - unlock_page(page); - - put_page(page); - - return 0; -} - -static int is_swbp_at_addr(struct mm_struct *mm, unsigned long vaddr) -{ - uprobe_opcode_t opcode; - int result; - - if (current->mm == mm) { - pagefault_disable(); - result = __copy_from_user_inatomic(&opcode, (void __user*)vaddr, - sizeof(opcode)); - pagefault_enable(); - - if (likely(result == 0)) - goto out; - } - - result = read_opcode(mm, vaddr, &opcode); - if (result) - return result; -out: - if (is_swbp_insn(&opcode)) - return 1; - - return 0; -} - -/** * set_swbp - store breakpoint at a given address. * @auprobe: arch specific probepoint information. * @mm: the probed process address space. @@ -328,18 +306,7 @@ out: */ int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr) { - int result; - /* - * See the comment near uprobes_hash(). - */ - result = is_swbp_at_addr(mm, vaddr); - if (result == 1) - return -EEXIST; - - if (result) - return result; - - return write_opcode(auprobe, mm, vaddr, UPROBE_SWBP_INSN); + return write_opcode(mm, vaddr, UPROBE_SWBP_INSN); } /** @@ -347,25 +314,14 @@ int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned * @mm: the probed process address space. * @auprobe: arch specific probepoint information. * @vaddr: the virtual address to insert the opcode. - * @verify: if true, verify existance of breakpoint instruction. * * For mm @mm, restore the original opcode (opcode) at @vaddr. * Return 0 (success) or a negative errno. */ int __weak -set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, bool verify) +set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr) { - if (verify) { - int result; - - result = is_swbp_at_addr(mm, vaddr); - if (!result) - return -EINVAL; - - if (result != 1) - return result; - } - return write_opcode(auprobe, mm, vaddr, *(uprobe_opcode_t *)auprobe->insn); + return write_opcode(mm, vaddr, *(uprobe_opcode_t *)auprobe->insn); } static int match_uprobe(struct uprobe *l, struct uprobe *r) @@ -415,11 +371,10 @@ static struct uprobe *__find_uprobe(struct inode *inode, loff_t offset) static struct uprobe *find_uprobe(struct inode *inode, loff_t offset) { struct uprobe *uprobe; - unsigned long flags; - spin_lock_irqsave(&uprobes_treelock, flags); + spin_lock(&uprobes_treelock); uprobe = __find_uprobe(inode, offset); - spin_unlock_irqrestore(&uprobes_treelock, flags); + spin_unlock(&uprobes_treelock); return uprobe; } @@ -466,15 +421,14 @@ static struct uprobe *__insert_uprobe(struct uprobe *uprobe) */ static struct uprobe *insert_uprobe(struct uprobe *uprobe) { - unsigned long flags; struct uprobe *u; - spin_lock_irqsave(&uprobes_treelock, flags); + spin_lock(&uprobes_treelock); u = __insert_uprobe(uprobe); - spin_unlock_irqrestore(&uprobes_treelock, flags); + spin_unlock(&uprobes_treelock); /* For now assume that the instruction need not be single-stepped */ - uprobe->flags |= UPROBE_SKIP_SSTEP; + __set_bit(UPROBE_SKIP_SSTEP, &uprobe->flags); return u; } @@ -496,6 +450,7 @@ static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset) uprobe->inode = igrab(inode); uprobe->offset = offset; init_rwsem(&uprobe->consumer_rwsem); + mutex_init(&uprobe->copy_mutex); /* add to uprobes_tree, sorted on inode:offset */ cur_uprobe = insert_uprobe(uprobe); @@ -516,7 +471,7 @@ static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs) { struct uprobe_consumer *uc; - if (!(uprobe->flags & UPROBE_RUN_HANDLER)) + if (!test_bit(UPROBE_RUN_HANDLER, &uprobe->flags)) return; down_read(&uprobe->consumer_rwsem); @@ -622,33 +577,48 @@ static int copy_insn(struct uprobe *uprobe, struct file *filp) return __copy_insn(mapping, filp, uprobe->arch.insn, bytes, uprobe->offset); } -/* - * How mm->uprobes_state.count gets updated - * uprobe_mmap() increments the count if - * - it successfully adds a breakpoint. - * - it cannot add a breakpoint, but sees that there is a underlying - * breakpoint (via a is_swbp_at_addr()). - * - * uprobe_munmap() decrements the count if - * - it sees a underlying breakpoint, (via is_swbp_at_addr) - * (Subsequent uprobe_unregister wouldnt find the breakpoint - * unless a uprobe_mmap kicks in, since the old vma would be - * dropped just after uprobe_munmap.) - * - * uprobe_register increments the count if: - * - it successfully adds a breakpoint. - * - * uprobe_unregister decrements the count if: - * - it sees a underlying breakpoint and removes successfully. - * (via is_swbp_at_addr) - * (Subsequent uprobe_munmap wouldnt find the breakpoint - * since there is no underlying breakpoint after the - * breakpoint removal.) - */ +static int prepare_uprobe(struct uprobe *uprobe, struct file *file, + struct mm_struct *mm, unsigned long vaddr) +{ + int ret = 0; + + if (test_bit(UPROBE_COPY_INSN, &uprobe->flags)) + return ret; + + mutex_lock(&uprobe->copy_mutex); + if (test_bit(UPROBE_COPY_INSN, &uprobe->flags)) + goto out; + + ret = copy_insn(uprobe, file); + if (ret) + goto out; + + ret = -ENOTSUPP; + if (is_swbp_insn((uprobe_opcode_t *)uprobe->arch.insn)) + goto out; + + ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr); + if (ret) + goto out; + + /* write_opcode() assumes we don't cross page boundary */ + BUG_ON((uprobe->offset & ~PAGE_MASK) + + UPROBE_SWBP_INSN_SIZE > PAGE_SIZE); + + smp_wmb(); /* pairs with rmb() in find_active_uprobe() */ + set_bit(UPROBE_COPY_INSN, &uprobe->flags); + + out: + mutex_unlock(&uprobe->copy_mutex); + + return ret; +} + static int install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, struct vm_area_struct *vma, unsigned long vaddr) { + bool first_uprobe; int ret; /* @@ -659,48 +629,38 @@ install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, * Hence behave as if probe already existed. */ if (!uprobe->consumers) - return -EEXIST; - - if (!(uprobe->flags & UPROBE_COPY_INSN)) { - ret = copy_insn(uprobe, vma->vm_file); - if (ret) - return ret; - - if (is_swbp_insn((uprobe_opcode_t *)uprobe->arch.insn)) - return -ENOTSUPP; - - ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr); - if (ret) - return ret; - - /* write_opcode() assumes we don't cross page boundary */ - BUG_ON((uprobe->offset & ~PAGE_MASK) + - UPROBE_SWBP_INSN_SIZE > PAGE_SIZE); + return 0; - uprobe->flags |= UPROBE_COPY_INSN; - } + ret = prepare_uprobe(uprobe, vma->vm_file, mm, vaddr); + if (ret) + return ret; /* - * Ideally, should be updating the probe count after the breakpoint - * has been successfully inserted. However a thread could hit the - * breakpoint we just inserted even before the probe count is - * incremented. If this is the first breakpoint placed, breakpoint - * notifier might ignore uprobes and pass the trap to the thread. - * Hence increment before and decrement on failure. + * set MMF_HAS_UPROBES in advance for uprobe_pre_sstep_notifier(), + * the task can hit this breakpoint right after __replace_page(). */ - atomic_inc(&mm->uprobes_state.count); + first_uprobe = !test_bit(MMF_HAS_UPROBES, &mm->flags); + if (first_uprobe) + set_bit(MMF_HAS_UPROBES, &mm->flags); + ret = set_swbp(&uprobe->arch, mm, vaddr); - if (ret) - atomic_dec(&mm->uprobes_state.count); + if (!ret) + clear_bit(MMF_RECALC_UPROBES, &mm->flags); + else if (first_uprobe) + clear_bit(MMF_HAS_UPROBES, &mm->flags); return ret; } -static void +static int remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr) { - if (!set_orig_insn(&uprobe->arch, mm, vaddr, true)) - atomic_dec(&mm->uprobes_state.count); + /* can happen if uprobe_register() fails */ + if (!test_bit(MMF_HAS_UPROBES, &mm->flags)) + return 0; + + set_bit(MMF_RECALC_UPROBES, &mm->flags); + return set_orig_insn(&uprobe->arch, mm, vaddr); } /* @@ -710,11 +670,9 @@ remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vad */ static void delete_uprobe(struct uprobe *uprobe) { - unsigned long flags; - - spin_lock_irqsave(&uprobes_treelock, flags); + spin_lock(&uprobes_treelock); rb_erase(&uprobe->rb_node, &uprobes_tree); - spin_unlock_irqrestore(&uprobes_treelock, flags); + spin_unlock(&uprobes_treelock); iput(uprobe->inode); put_uprobe(uprobe); atomic_dec(&uprobe_events); @@ -737,7 +695,6 @@ static struct map_info * build_map_info(struct address_space *mapping, loff_t offset, bool is_register) { unsigned long pgoff = offset >> PAGE_SHIFT; - struct prio_tree_iter iter; struct vm_area_struct *vma; struct map_info *curr = NULL; struct map_info *prev = NULL; @@ -746,7 +703,7 @@ build_map_info(struct address_space *mapping, loff_t offset, bool is_register) again: mutex_lock(&mapping->i_mmap_mutex); - vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) { + vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { if (!valid_vma(vma, is_register)) continue; @@ -818,7 +775,7 @@ static int register_for_each_vma(struct uprobe *uprobe, bool is_register) struct mm_struct *mm = info->mm; struct vm_area_struct *vma; - if (err) + if (err && is_register) goto free; down_write(&mm->mmap_sem); @@ -831,17 +788,11 @@ static int register_for_each_vma(struct uprobe *uprobe, bool is_register) vaddr_to_offset(vma, info->vaddr) != uprobe->offset) goto unlock; - if (is_register) { + if (is_register) err = install_breakpoint(uprobe, mm, vma, info->vaddr); - /* - * We can race against uprobe_mmap(), see the - * comment near uprobe_hash(). - */ - if (err == -EEXIST) - err = 0; - } else { - remove_breakpoint(uprobe, mm, info->vaddr); - } + else + err |= remove_breakpoint(uprobe, mm, info->vaddr); + unlock: up_write(&mm->mmap_sem); free: @@ -897,18 +848,21 @@ int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer * mutex_lock(uprobes_hash(inode)); uprobe = alloc_uprobe(inode, offset); - if (uprobe && !consumer_add(uprobe, uc)) { + if (!uprobe) { + ret = -ENOMEM; + } else if (!consumer_add(uprobe, uc)) { ret = __uprobe_register(uprobe); if (ret) { uprobe->consumers = NULL; __uprobe_unregister(uprobe); } else { - uprobe->flags |= UPROBE_RUN_HANDLER; + set_bit(UPROBE_RUN_HANDLER, &uprobe->flags); } } mutex_unlock(uprobes_hash(inode)); - put_uprobe(uprobe); + if (uprobe) + put_uprobe(uprobe); return ret; } @@ -935,7 +889,7 @@ void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consume if (consumer_del(uprobe, uc)) { if (!uprobe->consumers) { __uprobe_unregister(uprobe); - uprobe->flags &= ~UPROBE_RUN_HANDLER; + clear_bit(UPROBE_RUN_HANDLER, &uprobe->flags); } } @@ -978,7 +932,6 @@ static void build_probe_list(struct inode *inode, struct list_head *head) { loff_t min, max; - unsigned long flags; struct rb_node *n, *t; struct uprobe *u; @@ -986,7 +939,7 @@ static void build_probe_list(struct inode *inode, min = vaddr_to_offset(vma, start); max = min + (end - start) - 1; - spin_lock_irqsave(&uprobes_treelock, flags); + spin_lock(&uprobes_treelock); n = find_node_in_range(inode, min, max); if (n) { for (t = n; t; t = rb_prev(t)) { @@ -1004,27 +957,20 @@ static void build_probe_list(struct inode *inode, atomic_inc(&u->ref); } } - spin_unlock_irqrestore(&uprobes_treelock, flags); + spin_unlock(&uprobes_treelock); } /* - * Called from mmap_region. - * called with mm->mmap_sem acquired. - * - * Return -ve no if we fail to insert probes and we cannot - * bail-out. - * Return 0 otherwise. i.e: + * Called from mmap_region/vma_adjust with mm->mmap_sem acquired. * - * - successful insertion of probes - * - (or) no possible probes to be inserted. - * - (or) insertion of probes failed but we can bail-out. + * Currently we ignore all errors and always return 0, the callers + * can't handle the failure anyway. */ int uprobe_mmap(struct vm_area_struct *vma) { struct list_head tmp_list; struct uprobe *uprobe, *u; struct inode *inode; - int ret, count; if (!atomic_read(&uprobe_events) || !valid_vma(vma, true)) return 0; @@ -1036,44 +982,35 @@ int uprobe_mmap(struct vm_area_struct *vma) mutex_lock(uprobes_mmap_hash(inode)); build_probe_list(inode, vma, vma->vm_start, vma->vm_end, &tmp_list); - ret = 0; - count = 0; - list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) { - if (!ret) { + if (!fatal_signal_pending(current)) { unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset); - - ret = install_breakpoint(uprobe, vma->vm_mm, vma, vaddr); - /* - * We can race against uprobe_register(), see the - * comment near uprobe_hash(). - */ - if (ret == -EEXIST) { - ret = 0; - - if (!is_swbp_at_addr(vma->vm_mm, vaddr)) - continue; - - /* - * Unable to insert a breakpoint, but - * breakpoint lies underneath. Increment the - * probe count. - */ - atomic_inc(&vma->vm_mm->uprobes_state.count); - } - - if (!ret) - count++; + install_breakpoint(uprobe, vma->vm_mm, vma, vaddr); } put_uprobe(uprobe); } - mutex_unlock(uprobes_mmap_hash(inode)); - if (ret) - atomic_sub(count, &vma->vm_mm->uprobes_state.count); + return 0; +} - return ret; +static bool +vma_has_uprobes(struct vm_area_struct *vma, unsigned long start, unsigned long end) +{ + loff_t min, max; + struct inode *inode; + struct rb_node *n; + + inode = vma->vm_file->f_mapping->host; + + min = vaddr_to_offset(vma, start); + max = min + (end - start) - 1; + + spin_lock(&uprobes_treelock); + n = find_node_in_range(inode, min, max); + spin_unlock(&uprobes_treelock); + + return !!n; } /* @@ -1081,37 +1018,18 @@ int uprobe_mmap(struct vm_area_struct *vma) */ void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end) { - struct list_head tmp_list; - struct uprobe *uprobe, *u; - struct inode *inode; - if (!atomic_read(&uprobe_events) || !valid_vma(vma, false)) return; if (!atomic_read(&vma->vm_mm->mm_users)) /* called by mmput() ? */ return; - if (!atomic_read(&vma->vm_mm->uprobes_state.count)) - return; - - inode = vma->vm_file->f_mapping->host; - if (!inode) + if (!test_bit(MMF_HAS_UPROBES, &vma->vm_mm->flags) || + test_bit(MMF_RECALC_UPROBES, &vma->vm_mm->flags)) return; - mutex_lock(uprobes_mmap_hash(inode)); - build_probe_list(inode, vma, start, end, &tmp_list); - - list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) { - unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset); - /* - * An unregister could have removed the probe before - * unmap. So check before we decrement the count. - */ - if (is_swbp_at_addr(vma->vm_mm, vaddr) == 1) - atomic_dec(&vma->vm_mm->uprobes_state.count); - put_uprobe(uprobe); - } - mutex_unlock(uprobes_mmap_hash(inode)); + if (vma_has_uprobes(vma, start, end)) + set_bit(MMF_RECALC_UPROBES, &vma->vm_mm->flags); } /* Slot allocation for XOL */ @@ -1213,13 +1131,15 @@ void uprobe_clear_state(struct mm_struct *mm) kfree(area); } -/* - * uprobe_reset_state - Free the area allocated for slots. - */ -void uprobe_reset_state(struct mm_struct *mm) +void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm) { - mm->uprobes_state.xol_area = NULL; - atomic_set(&mm->uprobes_state.count, 0); + newmm->uprobes_state.xol_area = NULL; + + if (test_bit(MMF_HAS_UPROBES, &oldmm->flags)) { + set_bit(MMF_HAS_UPROBES, &newmm->flags); + /* unconditionally, dup_mmap() skips VM_DONTCOPY vmas */ + set_bit(MMF_RECALC_UPROBES, &newmm->flags); + } } /* @@ -1430,13 +1350,57 @@ bool uprobe_deny_signal(void) */ static bool can_skip_sstep(struct uprobe *uprobe, struct pt_regs *regs) { - if (arch_uprobe_skip_sstep(&uprobe->arch, regs)) - return true; - - uprobe->flags &= ~UPROBE_SKIP_SSTEP; + if (test_bit(UPROBE_SKIP_SSTEP, &uprobe->flags)) { + if (arch_uprobe_skip_sstep(&uprobe->arch, regs)) + return true; + clear_bit(UPROBE_SKIP_SSTEP, &uprobe->flags); + } return false; } +static void mmf_recalc_uprobes(struct mm_struct *mm) +{ + struct vm_area_struct *vma; + + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (!valid_vma(vma, false)) + continue; + /* + * This is not strictly accurate, we can race with + * uprobe_unregister() and see the already removed + * uprobe if delete_uprobe() was not yet called. + */ + if (vma_has_uprobes(vma, vma->vm_start, vma->vm_end)) + return; + } + + clear_bit(MMF_HAS_UPROBES, &mm->flags); +} + +static int is_swbp_at_addr(struct mm_struct *mm, unsigned long vaddr) +{ + struct page *page; + uprobe_opcode_t opcode; + int result; + + pagefault_disable(); + result = __copy_from_user_inatomic(&opcode, (void __user*)vaddr, + sizeof(opcode)); + pagefault_enable(); + + if (likely(result == 0)) + goto out; + + result = get_user_pages(NULL, mm, vaddr, 1, 0, 1, &page, NULL); + if (result < 0) + return result; + + copy_opcode(page, vaddr, &opcode); + put_page(page); + out: + return is_swbp_insn(&opcode); +} + static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp) { struct mm_struct *mm = current->mm; @@ -1458,11 +1422,24 @@ static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp) } else { *is_swbp = -EFAULT; } + + if (!uprobe && test_and_clear_bit(MMF_RECALC_UPROBES, &mm->flags)) + mmf_recalc_uprobes(mm); up_read(&mm->mmap_sem); return uprobe; } +void __weak arch_uprobe_enable_step(struct arch_uprobe *arch) +{ + user_enable_single_step(current); +} + +void __weak arch_uprobe_disable_step(struct arch_uprobe *arch) +{ + user_disable_single_step(current); +} + /* * Run handler and ask thread to singlestep. * Ensure all non-fatal signals cannot interrupt thread while it singlesteps. @@ -1494,41 +1471,42 @@ static void handle_swbp(struct pt_regs *regs) } return; } + /* + * TODO: move copy_insn/etc into _register and remove this hack. + * After we hit the bp, _unregister + _register can install the + * new and not-yet-analyzed uprobe at the same address, restart. + */ + smp_rmb(); /* pairs with wmb() in install_breakpoint() */ + if (unlikely(!test_bit(UPROBE_COPY_INSN, &uprobe->flags))) + goto restart; utask = current->utask; if (!utask) { utask = add_utask(); /* Cannot allocate; re-execute the instruction. */ if (!utask) - goto cleanup_ret; + goto restart; } - utask->active_uprobe = uprobe; + handler_chain(uprobe, regs); - if (uprobe->flags & UPROBE_SKIP_SSTEP && can_skip_sstep(uprobe, regs)) - goto cleanup_ret; + if (can_skip_sstep(uprobe, regs)) + goto out; - utask->state = UTASK_SSTEP; if (!pre_ssout(uprobe, regs, bp_vaddr)) { - user_enable_single_step(current); + arch_uprobe_enable_step(&uprobe->arch); + utask->active_uprobe = uprobe; + utask->state = UTASK_SSTEP; return; } -cleanup_ret: - if (utask) { - utask->active_uprobe = NULL; - utask->state = UTASK_RUNNING; - } - if (uprobe) { - if (!(uprobe->flags & UPROBE_SKIP_SSTEP)) - - /* - * cannot singlestep; cannot skip instruction; - * re-execute the instruction. - */ - instruction_pointer_set(regs, bp_vaddr); - - put_uprobe(uprobe); - } +restart: + /* + * cannot singlestep; cannot skip instruction; + * re-execute the instruction. + */ + instruction_pointer_set(regs, bp_vaddr); +out: + put_uprobe(uprobe); } /* @@ -1547,10 +1525,10 @@ static void handle_singlestep(struct uprobe_task *utask, struct pt_regs *regs) else WARN_ON_ONCE(1); + arch_uprobe_disable_step(&uprobe->arch); put_uprobe(uprobe); utask->active_uprobe = NULL; utask->state = UTASK_RUNNING; - user_disable_single_step(current); xol_free_insn_slot(current); spin_lock_irq(¤t->sighand->siglock); @@ -1559,13 +1537,12 @@ static void handle_singlestep(struct uprobe_task *utask, struct pt_regs *regs) } /* - * On breakpoint hit, breakpoint notifier sets the TIF_UPROBE flag. (and on - * subsequent probe hits on the thread sets the state to UTASK_BP_HIT) and - * allows the thread to return from interrupt. + * On breakpoint hit, breakpoint notifier sets the TIF_UPROBE flag and + * allows the thread to return from interrupt. After that handle_swbp() + * sets utask->active_uprobe. * - * On singlestep exception, singlestep notifier sets the TIF_UPROBE flag and - * also sets the state to UTASK_SSTEP_ACK and allows the thread to return from - * interrupt. + * On singlestep exception, singlestep notifier sets the TIF_UPROBE flag + * and allows the thread to return from interrupt. * * While returning to userspace, thread notices the TIF_UPROBE flag and calls * uprobe_notify_resume(). @@ -1574,11 +1551,13 @@ void uprobe_notify_resume(struct pt_regs *regs) { struct uprobe_task *utask; + clear_thread_flag(TIF_UPROBE); + utask = current->utask; - if (!utask || utask->state == UTASK_BP_HIT) - handle_swbp(regs); - else + if (utask && utask->active_uprobe) handle_singlestep(utask, regs); + else + handle_swbp(regs); } /* @@ -1587,18 +1566,10 @@ void uprobe_notify_resume(struct pt_regs *regs) */ int uprobe_pre_sstep_notifier(struct pt_regs *regs) { - struct uprobe_task *utask; - - if (!current->mm || !atomic_read(¤t->mm->uprobes_state.count)) - /* task is currently not uprobed */ + if (!current->mm || !test_bit(MMF_HAS_UPROBES, ¤t->mm->flags)) return 0; - utask = current->utask; - if (utask) - utask->state = UTASK_BP_HIT; - set_thread_flag(TIF_UPROBE); - return 1; } diff --git a/kernel/exit.c b/kernel/exit.c index f65345f9e5bb..346616c0092c 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -457,108 +457,13 @@ void daemonize(const char *name, ...) /* Become as one with the init task */ daemonize_fs_struct(); - exit_files(current); - current->files = init_task.files; - atomic_inc(¤t->files->count); + daemonize_descriptors(); reparent_to_kthreadd(); } EXPORT_SYMBOL(daemonize); -static void close_files(struct files_struct * files) -{ - int i, j; - struct fdtable *fdt; - - j = 0; - - /* - * It is safe to dereference the fd table without RCU or - * ->file_lock because this is the last reference to the - * files structure. But use RCU to shut RCU-lockdep up. - */ - rcu_read_lock(); - fdt = files_fdtable(files); - rcu_read_unlock(); - for (;;) { - unsigned long set; - i = j * BITS_PER_LONG; - if (i >= fdt->max_fds) - break; - set = fdt->open_fds[j++]; - while (set) { - if (set & 1) { - struct file * file = xchg(&fdt->fd[i], NULL); - if (file) { - filp_close(file, files); - cond_resched(); - } - } - i++; - set >>= 1; - } - } -} - -struct files_struct *get_files_struct(struct task_struct *task) -{ - struct files_struct *files; - - task_lock(task); - files = task->files; - if (files) - atomic_inc(&files->count); - task_unlock(task); - - return files; -} - -void put_files_struct(struct files_struct *files) -{ - struct fdtable *fdt; - - if (atomic_dec_and_test(&files->count)) { - close_files(files); - /* - * Free the fd and fdset arrays if we expanded them. - * If the fdtable was embedded, pass files for freeing - * at the end of the RCU grace period. Otherwise, - * you can free files immediately. - */ - rcu_read_lock(); - fdt = files_fdtable(files); - if (fdt != &files->fdtab) - kmem_cache_free(files_cachep, files); - free_fdtable(fdt); - rcu_read_unlock(); - } -} - -void reset_files_struct(struct files_struct *files) -{ - struct task_struct *tsk = current; - struct files_struct *old; - - old = tsk->files; - task_lock(tsk); - tsk->files = files; - task_unlock(tsk); - put_files_struct(old); -} - -void exit_files(struct task_struct *tsk) -{ - struct files_struct * files = tsk->files; - - if (files) { - task_lock(tsk); - tsk->files = NULL; - task_unlock(tsk); - put_files_struct(files); - } -} - #ifdef CONFIG_MM_OWNER /* * A task is exiting. If it owned this mm, find a new owner for the mm. @@ -1046,6 +951,9 @@ void do_exit(long code) if (tsk->splice_pipe) __free_pipe_info(tsk->splice_pipe); + if (tsk->task_frag.page) + put_page(tsk->task_frag.page); + validate_creds_for_do_exit(tsk); preempt_disable(); diff --git a/kernel/fork.c b/kernel/fork.c index 2c8857e12855..8b20ab7d3aa2 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -330,6 +330,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig) tsk->btrace_seq = 0; #endif tsk->splice_pipe = NULL; + tsk->task_frag.page = NULL; account_kernel_stack(ti, 1); @@ -353,6 +354,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) down_write(&oldmm->mmap_sem); flush_cache_dup_mm(oldmm); + uprobe_dup_mmap(oldmm, mm); /* * Not linked in yet - no deadlock potential: */ @@ -421,7 +423,12 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) mapping->i_mmap_writable++; flush_dcache_mmap_lock(mapping); /* insert tmp into the share list, just after mpnt */ - vma_prio_tree_add(tmp, mpnt); + if (unlikely(tmp->vm_flags & VM_NONLINEAR)) + vma_nonlinear_insert(tmp, + &mapping->i_mmap_nonlinear); + else + vma_interval_tree_insert_after(tmp, mpnt, + &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); mutex_unlock(&mapping->i_mmap_mutex); } @@ -454,9 +461,6 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) if (retval) goto out; - - if (file) - uprobe_mmap(tmp); } /* a new mm has just been created */ arch_dup_mmap(oldmm, mm); @@ -623,26 +627,6 @@ void mmput(struct mm_struct *mm) } EXPORT_SYMBOL_GPL(mmput); -/* - * We added or removed a vma mapping the executable. The vmas are only mapped - * during exec and are not mapped with the mmap system call. - * Callers must hold down_write() on the mm's mmap_sem for these - */ -void added_exe_file_vma(struct mm_struct *mm) -{ - mm->num_exe_file_vmas++; -} - -void removed_exe_file_vma(struct mm_struct *mm) -{ - mm->num_exe_file_vmas--; - if ((mm->num_exe_file_vmas == 0) && mm->exe_file) { - fput(mm->exe_file); - mm->exe_file = NULL; - } - -} - void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) { if (new_exe_file) @@ -650,15 +634,13 @@ void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) if (mm->exe_file) fput(mm->exe_file); mm->exe_file = new_exe_file; - mm->num_exe_file_vmas = 0; } struct file *get_mm_exe_file(struct mm_struct *mm) { struct file *exe_file; - /* We need mmap_sem to protect against races with removal of - * VM_EXECUTABLE vmas */ + /* We need mmap_sem to protect against races with removal of exe_file */ down_read(&mm->mmap_sem); exe_file = mm->exe_file; if (exe_file) @@ -839,8 +821,6 @@ struct mm_struct *dup_mm(struct task_struct *tsk) #ifdef CONFIG_TRANSPARENT_HUGEPAGE mm->pmd_huge_pte = NULL; #endif - uprobe_reset_state(mm); - if (!mm_init(mm, tsk)) goto fail_nomem; @@ -1081,7 +1061,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) init_rwsem(&sig->group_rwsem); #endif - sig->oom_adj = current->signal->oom_adj; sig->oom_score_adj = current->signal->oom_score_adj; sig->oom_score_adj_min = current->signal->oom_score_adj_min; @@ -1280,11 +1259,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, #endif #ifdef CONFIG_TRACE_IRQFLAGS p->irq_events = 0; -#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW - p->hardirqs_enabled = 1; -#else p->hardirqs_enabled = 0; -#endif p->hardirq_enable_ip = 0; p->hardirq_enable_event = 0; p->hardirq_disable_ip = _THIS_IP_; @@ -1609,7 +1584,7 @@ long do_fork(unsigned long clone_flags, * requested, no event is reported; otherwise, report if the event * for the type of forking is enabled. */ - if (likely(user_mode(regs)) && !(clone_flags & CLONE_UNTRACED)) { + if (!(clone_flags & CLONE_UNTRACED) && likely(user_mode(regs))) { if (clone_flags & CLONE_VFORK) trace = PTRACE_EVENT_VFORK; else if ((clone_flags & CSIGNAL) != SIGCHLD) @@ -1659,6 +1634,17 @@ long do_fork(unsigned long clone_flags, return nr; } +#ifdef CONFIG_GENERIC_KERNEL_THREAD +/* + * Create a kernel thread. + */ +pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags) +{ + return do_fork(flags|CLONE_VM|CLONE_UNTRACED, (unsigned long)fn, NULL, + (unsigned long)arg, NULL, NULL); +} +#endif + #ifndef ARCH_MIN_MMSTRUCT_ALIGN #define ARCH_MIN_MMSTRUCT_ALIGN 0 #endif diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index eebd6d5cfb44..57d86d07221e 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -671,6 +671,7 @@ irq_set_chip_and_handler_name(unsigned int irq, struct irq_chip *chip, irq_set_chip(irq, chip); __irq_set_handler(irq, handle, 0, name); } +EXPORT_SYMBOL_GPL(irq_set_chip_and_handler_name); void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set) { diff --git a/kernel/irq/dummychip.c b/kernel/irq/dummychip.c index b5fcd96c7102..988dc58e8847 100644 --- a/kernel/irq/dummychip.c +++ b/kernel/irq/dummychip.c @@ -6,6 +6,7 @@ */ #include <linux/interrupt.h> #include <linux/irq.h> +#include <linux/export.h> #include "internals.h" @@ -57,3 +58,4 @@ struct irq_chip dummy_irq_chip = { .irq_mask = noop, .irq_unmask = noop, }; +EXPORT_SYMBOL_GPL(dummy_irq_chip); diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 49a77727db42..4e69e24d3d7d 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -148,7 +148,8 @@ static unsigned int irq_domain_legacy_revmap(struct irq_domain *domain, * @host_data: Controller private data pointer * * Allocates a legacy irq_domain if irq_base is positive or a linear - * domain otherwise. + * domain otherwise. For the legacy domain, IRQ descriptors will also + * be allocated. * * This is intended to implement the expected behaviour for most * interrupt controllers which is that a linear mapping should @@ -162,11 +163,33 @@ struct irq_domain *irq_domain_add_simple(struct device_node *of_node, const struct irq_domain_ops *ops, void *host_data) { - if (first_irq > 0) - return irq_domain_add_legacy(of_node, size, first_irq, 0, + if (first_irq > 0) { + int irq_base; + + if (IS_ENABLED(CONFIG_SPARSE_IRQ)) { + /* + * Set the descriptor allocator to search for a + * 1-to-1 mapping, such as irq_alloc_desc_at(). + * Use of_node_to_nid() which is defined to + * numa_node_id() on platforms that have no custom + * implementation. + */ + irq_base = irq_alloc_descs(first_irq, first_irq, size, + of_node_to_nid(of_node)); + if (irq_base < 0) { + WARN(1, "Cannot allocate irq_descs @ IRQ%d, assuming pre-allocated\n", + first_irq); + irq_base = first_irq; + } + } else + irq_base = first_irq; + + return irq_domain_add_legacy(of_node, size, irq_base, 0, ops, host_data); - else - return irq_domain_add_linear(of_node, size, ops, host_data); + } + + /* A linear domain is the default */ + return irq_domain_add_linear(of_node, size, ops, host_data); } /** diff --git a/kernel/jump_label.c b/kernel/jump_label.c index 43049192b5ec..60f48fa0fd0d 100644 --- a/kernel/jump_label.c +++ b/kernel/jump_label.c @@ -118,6 +118,7 @@ void jump_label_rate_limit(struct static_key_deferred *key, key->timeout = rl; INIT_DELAYED_WORK(&key->work, jump_label_update_timeout); } +EXPORT_SYMBOL_GPL(jump_label_rate_limit); static int addr_conflict(struct jump_entry *entry, void *start, void *end) { diff --git a/kernel/kexec.c b/kernel/kexec.c index 0668d58d6413..5e4bd7864c5d 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -21,7 +21,6 @@ #include <linux/hardirq.h> #include <linux/elf.h> #include <linux/elfcore.h> -#include <generated/utsrelease.h> #include <linux/utsname.h> #include <linux/numa.h> #include <linux/suspend.h> diff --git a/kernel/kmod.c b/kernel/kmod.c index 6f99aead66c6..1c317e386831 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -37,6 +37,7 @@ #include <linux/notifier.h> #include <linux/suspend.h> #include <linux/rwsem.h> +#include <linux/ptrace.h> #include <asm/uaccess.h> #include <trace/events/module.h> @@ -221,11 +222,13 @@ static int ____call_usermodehelper(void *data) retval = kernel_execve(sub_info->path, (const char *const *)sub_info->argv, (const char *const *)sub_info->envp); + if (!retval) + return 0; /* Exec failed? */ fail: sub_info->retval = retval; - return 0; + do_exit(0); } static int call_helper(void *data) @@ -292,7 +295,7 @@ static int wait_for_helper(void *data) } umh_complete(sub_info); - return 0; + do_exit(0); } /* This is run by khelper thread */ diff --git a/kernel/kprobes.c b/kernel/kprobes.c index c62b8546cc90..098f396aa409 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -561,9 +561,9 @@ static __kprobes void kprobe_optimizer(struct work_struct *work) { LIST_HEAD(free_list); + mutex_lock(&kprobe_mutex); /* Lock modules while optimizing kprobes */ mutex_lock(&module_mutex); - mutex_lock(&kprobe_mutex); /* * Step 1: Unoptimize kprobes and collect cleaned (unused and disarmed) @@ -586,8 +586,8 @@ static __kprobes void kprobe_optimizer(struct work_struct *work) /* Step 4: Free cleaned kprobes after quiesence period */ do_free_cleaned_kprobes(&free_list); - mutex_unlock(&kprobe_mutex); mutex_unlock(&module_mutex); + mutex_unlock(&kprobe_mutex); /* Step 5: Kick optimizer again if needed */ if (!list_empty(&optimizing_list) || !list_empty(&unoptimizing_list)) @@ -759,20 +759,32 @@ static __kprobes void try_to_optimize_kprobe(struct kprobe *p) struct kprobe *ap; struct optimized_kprobe *op; + /* Impossible to optimize ftrace-based kprobe */ + if (kprobe_ftrace(p)) + return; + + /* For preparing optimization, jump_label_text_reserved() is called */ + jump_label_lock(); + mutex_lock(&text_mutex); + ap = alloc_aggr_kprobe(p); if (!ap) - return; + goto out; op = container_of(ap, struct optimized_kprobe, kp); if (!arch_prepared_optinsn(&op->optinsn)) { /* If failed to setup optimizing, fallback to kprobe */ arch_remove_optimized_kprobe(op); kfree(op); - return; + goto out; } init_aggr_kprobe(ap, p); - optimize_kprobe(ap); + optimize_kprobe(ap); /* This just kicks optimizer thread */ + +out: + mutex_unlock(&text_mutex); + jump_label_unlock(); } #ifdef CONFIG_SYSCTL @@ -907,9 +919,64 @@ static __kprobes struct kprobe *alloc_aggr_kprobe(struct kprobe *p) } #endif /* CONFIG_OPTPROBES */ +#ifdef KPROBES_CAN_USE_FTRACE +static struct ftrace_ops kprobe_ftrace_ops __read_mostly = { + .func = kprobe_ftrace_handler, + .flags = FTRACE_OPS_FL_SAVE_REGS, +}; +static int kprobe_ftrace_enabled; + +/* Must ensure p->addr is really on ftrace */ +static int __kprobes prepare_kprobe(struct kprobe *p) +{ + if (!kprobe_ftrace(p)) + return arch_prepare_kprobe(p); + + return arch_prepare_kprobe_ftrace(p); +} + +/* Caller must lock kprobe_mutex */ +static void __kprobes arm_kprobe_ftrace(struct kprobe *p) +{ + int ret; + + ret = ftrace_set_filter_ip(&kprobe_ftrace_ops, + (unsigned long)p->addr, 0, 0); + WARN(ret < 0, "Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret); + kprobe_ftrace_enabled++; + if (kprobe_ftrace_enabled == 1) { + ret = register_ftrace_function(&kprobe_ftrace_ops); + WARN(ret < 0, "Failed to init kprobe-ftrace (%d)\n", ret); + } +} + +/* Caller must lock kprobe_mutex */ +static void __kprobes disarm_kprobe_ftrace(struct kprobe *p) +{ + int ret; + + kprobe_ftrace_enabled--; + if (kprobe_ftrace_enabled == 0) { + ret = unregister_ftrace_function(&kprobe_ftrace_ops); + WARN(ret < 0, "Failed to init kprobe-ftrace (%d)\n", ret); + } + ret = ftrace_set_filter_ip(&kprobe_ftrace_ops, + (unsigned long)p->addr, 1, 0); + WARN(ret < 0, "Failed to disarm kprobe-ftrace at %p (%d)\n", p->addr, ret); +} +#else /* !KPROBES_CAN_USE_FTRACE */ +#define prepare_kprobe(p) arch_prepare_kprobe(p) +#define arm_kprobe_ftrace(p) do {} while (0) +#define disarm_kprobe_ftrace(p) do {} while (0) +#endif + /* Arm a kprobe with text_mutex */ static void __kprobes arm_kprobe(struct kprobe *kp) { + if (unlikely(kprobe_ftrace(kp))) { + arm_kprobe_ftrace(kp); + return; + } /* * Here, since __arm_kprobe() doesn't use stop_machine(), * this doesn't cause deadlock on text_mutex. So, we don't @@ -921,11 +988,15 @@ static void __kprobes arm_kprobe(struct kprobe *kp) } /* Disarm a kprobe with text_mutex */ -static void __kprobes disarm_kprobe(struct kprobe *kp) +static void __kprobes disarm_kprobe(struct kprobe *kp, bool reopt) { + if (unlikely(kprobe_ftrace(kp))) { + disarm_kprobe_ftrace(kp); + return; + } /* Ditto */ mutex_lock(&text_mutex); - __disarm_kprobe(kp, true); + __disarm_kprobe(kp, reopt); mutex_unlock(&text_mutex); } @@ -1144,12 +1215,6 @@ static int __kprobes add_new_kprobe(struct kprobe *ap, struct kprobe *p) if (p->post_handler && !ap->post_handler) ap->post_handler = aggr_post_handler; - if (kprobe_disabled(ap) && !kprobe_disabled(p)) { - ap->flags &= ~KPROBE_FLAG_DISABLED; - if (!kprobes_all_disarmed) - /* Arm the breakpoint again. */ - __arm_kprobe(ap); - } return 0; } @@ -1189,11 +1254,22 @@ static int __kprobes register_aggr_kprobe(struct kprobe *orig_p, int ret = 0; struct kprobe *ap = orig_p; + /* For preparing optimization, jump_label_text_reserved() is called */ + jump_label_lock(); + /* + * Get online CPUs to avoid text_mutex deadlock.with stop machine, + * which is invoked by unoptimize_kprobe() in add_new_kprobe() + */ + get_online_cpus(); + mutex_lock(&text_mutex); + if (!kprobe_aggrprobe(orig_p)) { /* If orig_p is not an aggr_kprobe, create new aggr_kprobe. */ ap = alloc_aggr_kprobe(orig_p); - if (!ap) - return -ENOMEM; + if (!ap) { + ret = -ENOMEM; + goto out; + } init_aggr_kprobe(ap, orig_p); } else if (kprobe_unused(ap)) /* This probe is going to die. Rescue it */ @@ -1213,7 +1289,7 @@ static int __kprobes register_aggr_kprobe(struct kprobe *orig_p, * free aggr_probe. It will be used next time, or * freed by unregister_kprobe. */ - return ret; + goto out; /* Prepare optimized instructions if possible. */ prepare_optimized_kprobe(ap); @@ -1228,7 +1304,20 @@ static int __kprobes register_aggr_kprobe(struct kprobe *orig_p, /* Copy ap's insn slot to p */ copy_kprobe(ap, p); - return add_new_kprobe(ap, p); + ret = add_new_kprobe(ap, p); + +out: + mutex_unlock(&text_mutex); + put_online_cpus(); + jump_label_unlock(); + + if (ret == 0 && kprobe_disabled(ap) && !kprobe_disabled(p)) { + ap->flags &= ~KPROBE_FLAG_DISABLED; + if (!kprobes_all_disarmed) + /* Arm the breakpoint again. */ + arm_kprobe(ap); + } + return ret; } static int __kprobes in_kprobes_functions(unsigned long addr) @@ -1313,71 +1402,96 @@ static inline int check_kprobe_rereg(struct kprobe *p) return ret; } -int __kprobes register_kprobe(struct kprobe *p) +static __kprobes int check_kprobe_address_safe(struct kprobe *p, + struct module **probed_mod) { int ret = 0; - struct kprobe *old_p; - struct module *probed_mod; - kprobe_opcode_t *addr; - - addr = kprobe_addr(p); - if (IS_ERR(addr)) - return PTR_ERR(addr); - p->addr = addr; + unsigned long ftrace_addr; - ret = check_kprobe_rereg(p); - if (ret) - return ret; + /* + * If the address is located on a ftrace nop, set the + * breakpoint to the following instruction. + */ + ftrace_addr = ftrace_location((unsigned long)p->addr); + if (ftrace_addr) { +#ifdef KPROBES_CAN_USE_FTRACE + /* Given address is not on the instruction boundary */ + if ((unsigned long)p->addr != ftrace_addr) + return -EILSEQ; + p->flags |= KPROBE_FLAG_FTRACE; +#else /* !KPROBES_CAN_USE_FTRACE */ + return -EINVAL; +#endif + } jump_label_lock(); preempt_disable(); + + /* Ensure it is not in reserved area nor out of text */ if (!kernel_text_address((unsigned long) p->addr) || in_kprobes_functions((unsigned long) p->addr) || - ftrace_text_reserved(p->addr, p->addr) || jump_label_text_reserved(p->addr, p->addr)) { ret = -EINVAL; - goto cannot_probe; + goto out; } - /* User can pass only KPROBE_FLAG_DISABLED to register_kprobe */ - p->flags &= KPROBE_FLAG_DISABLED; - - /* - * Check if are we probing a module. - */ - probed_mod = __module_text_address((unsigned long) p->addr); - if (probed_mod) { - /* Return -ENOENT if fail. */ - ret = -ENOENT; + /* Check if are we probing a module */ + *probed_mod = __module_text_address((unsigned long) p->addr); + if (*probed_mod) { /* * We must hold a refcount of the probed module while updating * its code to prohibit unexpected unloading. */ - if (unlikely(!try_module_get(probed_mod))) - goto cannot_probe; + if (unlikely(!try_module_get(*probed_mod))) { + ret = -ENOENT; + goto out; + } /* * If the module freed .init.text, we couldn't insert * kprobes in there. */ - if (within_module_init((unsigned long)p->addr, probed_mod) && - probed_mod->state != MODULE_STATE_COMING) { - module_put(probed_mod); - goto cannot_probe; + if (within_module_init((unsigned long)p->addr, *probed_mod) && + (*probed_mod)->state != MODULE_STATE_COMING) { + module_put(*probed_mod); + *probed_mod = NULL; + ret = -ENOENT; } - /* ret will be updated by following code */ } +out: preempt_enable(); jump_label_unlock(); + return ret; +} + +int __kprobes register_kprobe(struct kprobe *p) +{ + int ret; + struct kprobe *old_p; + struct module *probed_mod; + kprobe_opcode_t *addr; + + /* Adjust probe address from symbol */ + addr = kprobe_addr(p); + if (IS_ERR(addr)) + return PTR_ERR(addr); + p->addr = addr; + + ret = check_kprobe_rereg(p); + if (ret) + return ret; + + /* User can pass only KPROBE_FLAG_DISABLED to register_kprobe */ + p->flags &= KPROBE_FLAG_DISABLED; p->nmissed = 0; INIT_LIST_HEAD(&p->list); - mutex_lock(&kprobe_mutex); - jump_label_lock(); /* needed to call jump_label_text_reserved() */ + ret = check_kprobe_address_safe(p, &probed_mod); + if (ret) + return ret; - get_online_cpus(); /* For avoiding text_mutex deadlock. */ - mutex_lock(&text_mutex); + mutex_lock(&kprobe_mutex); old_p = get_kprobe(p->addr); if (old_p) { @@ -1386,7 +1500,9 @@ int __kprobes register_kprobe(struct kprobe *p) goto out; } - ret = arch_prepare_kprobe(p); + mutex_lock(&text_mutex); /* Avoiding text modification */ + ret = prepare_kprobe(p); + mutex_unlock(&text_mutex); if (ret) goto out; @@ -1395,26 +1511,18 @@ int __kprobes register_kprobe(struct kprobe *p) &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]); if (!kprobes_all_disarmed && !kprobe_disabled(p)) - __arm_kprobe(p); + arm_kprobe(p); /* Try to optimize kprobe */ try_to_optimize_kprobe(p); out: - mutex_unlock(&text_mutex); - put_online_cpus(); - jump_label_unlock(); mutex_unlock(&kprobe_mutex); if (probed_mod) module_put(probed_mod); return ret; - -cannot_probe: - preempt_enable(); - jump_label_unlock(); - return ret; } EXPORT_SYMBOL_GPL(register_kprobe); @@ -1451,7 +1559,7 @@ static struct kprobe *__kprobes __disable_kprobe(struct kprobe *p) /* Try to disarm and disable this/parent probe */ if (p == orig_p || aggr_kprobe_disabled(orig_p)) { - disarm_kprobe(orig_p); + disarm_kprobe(orig_p, true); orig_p->flags |= KPROBE_FLAG_DISABLED; } } @@ -2049,10 +2157,11 @@ static void __kprobes report_probe(struct seq_file *pi, struct kprobe *p, if (!pp) pp = p; - seq_printf(pi, "%s%s%s\n", + seq_printf(pi, "%s%s%s%s\n", (kprobe_gone(p) ? "[GONE]" : ""), ((kprobe_disabled(p) && !kprobe_gone(p)) ? "[DISABLED]" : ""), - (kprobe_optimized(pp) ? "[OPTIMIZED]" : "")); + (kprobe_optimized(pp) ? "[OPTIMIZED]" : ""), + (kprobe_ftrace(pp) ? "[FTRACE]" : "")); } static void __kprobes *kprobe_seq_start(struct seq_file *f, loff_t *pos) @@ -2131,14 +2240,12 @@ static void __kprobes arm_all_kprobes(void) goto already_enabled; /* Arming kprobes doesn't optimize kprobe itself */ - mutex_lock(&text_mutex); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry_rcu(p, node, head, hlist) if (!kprobe_disabled(p)) - __arm_kprobe(p); + arm_kprobe(p); } - mutex_unlock(&text_mutex); kprobes_all_disarmed = false; printk(KERN_INFO "Kprobes globally enabled\n"); @@ -2166,15 +2273,13 @@ static void __kprobes disarm_all_kprobes(void) kprobes_all_disarmed = true; printk(KERN_INFO "Kprobes globally disabled\n"); - mutex_lock(&text_mutex); for (i = 0; i < KPROBE_TABLE_SIZE; i++) { head = &kprobe_table[i]; hlist_for_each_entry_rcu(p, node, head, hlist) { if (!arch_trampoline_kprobe(p) && !kprobe_disabled(p)) - __disarm_kprobe(p, false); + disarm_kprobe(p, false); } } - mutex_unlock(&text_mutex); mutex_unlock(&kprobe_mutex); /* Wait for disarming all kprobes by optimizer */ diff --git a/kernel/kthread.c b/kernel/kthread.c index b579af57ea10..29fb60caecb5 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -16,6 +16,7 @@ #include <linux/mutex.h> #include <linux/slab.h> #include <linux/freezer.h> +#include <linux/ptrace.h> #include <trace/events/sched.h> static DEFINE_SPINLOCK(kthread_create_lock); @@ -37,11 +38,20 @@ struct kthread_create_info }; struct kthread { - int should_stop; + unsigned long flags; + unsigned int cpu; void *data; + struct completion parked; struct completion exited; }; +enum KTHREAD_BITS { + KTHREAD_IS_PER_CPU = 0, + KTHREAD_SHOULD_STOP, + KTHREAD_SHOULD_PARK, + KTHREAD_IS_PARKED, +}; + #define to_kthread(tsk) \ container_of((tsk)->vfork_done, struct kthread, exited) @@ -52,13 +62,29 @@ struct kthread { * and this will return true. You should then return, and your return * value will be passed through to kthread_stop(). */ -int kthread_should_stop(void) +bool kthread_should_stop(void) { - return to_kthread(current)->should_stop; + return test_bit(KTHREAD_SHOULD_STOP, &to_kthread(current)->flags); } EXPORT_SYMBOL(kthread_should_stop); /** + * kthread_should_park - should this kthread park now? + * + * When someone calls kthread_park() on your kthread, it will be woken + * and this will return true. You should then do the necessary + * cleanup and call kthread_parkme() + * + * Similar to kthread_should_stop(), but this keeps the thread alive + * and in a park position. kthread_unpark() "restarts" the thread and + * calls the thread function again. + */ +bool kthread_should_park(void) +{ + return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(current)->flags); +} + +/** * kthread_freezable_should_stop - should this freezable kthread return now? * @was_frozen: optional out parameter, indicates whether %current was frozen * @@ -96,6 +122,24 @@ void *kthread_data(struct task_struct *task) return to_kthread(task)->data; } +static void __kthread_parkme(struct kthread *self) +{ + __set_current_state(TASK_INTERRUPTIBLE); + while (test_bit(KTHREAD_SHOULD_PARK, &self->flags)) { + if (!test_and_set_bit(KTHREAD_IS_PARKED, &self->flags)) + complete(&self->parked); + schedule(); + __set_current_state(TASK_INTERRUPTIBLE); + } + clear_bit(KTHREAD_IS_PARKED, &self->flags); + __set_current_state(TASK_RUNNING); +} + +void kthread_parkme(void) +{ + __kthread_parkme(to_kthread(current)); +} + static int kthread(void *_create) { /* Copy data: it's on kthread's stack */ @@ -105,9 +149,10 @@ static int kthread(void *_create) struct kthread self; int ret; - self.should_stop = 0; + self.flags = 0; self.data = data; init_completion(&self.exited); + init_completion(&self.parked); current->vfork_done = &self.exited; /* OK, tell user we're spawned, wait for stop or wakeup */ @@ -117,9 +162,11 @@ static int kthread(void *_create) schedule(); ret = -EINTR; - if (!self.should_stop) - ret = threadfn(data); + if (!test_bit(KTHREAD_SHOULD_STOP, &self.flags)) { + __kthread_parkme(&self); + ret = threadfn(data); + } /* we can't just return, we must preserve "self" on stack */ do_exit(ret); } @@ -172,8 +219,7 @@ static void create_kthread(struct kthread_create_info *create) * Returns a task_struct or ERR_PTR(-ENOMEM). */ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), - void *data, - int node, + void *data, int node, const char namefmt[], ...) { @@ -210,6 +256,13 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), } EXPORT_SYMBOL(kthread_create_on_node); +static void __kthread_bind(struct task_struct *p, unsigned int cpu) +{ + /* It's safe because the task is inactive. */ + do_set_cpus_allowed(p, cpumask_of(cpu)); + p->flags |= PF_THREAD_BOUND; +} + /** * kthread_bind - bind a just-created kthread to a cpu. * @p: thread created by kthread_create(). @@ -226,14 +279,112 @@ void kthread_bind(struct task_struct *p, unsigned int cpu) WARN_ON(1); return; } - - /* It's safe because the task is inactive. */ - do_set_cpus_allowed(p, cpumask_of(cpu)); - p->flags |= PF_THREAD_BOUND; + __kthread_bind(p, cpu); } EXPORT_SYMBOL(kthread_bind); /** + * kthread_create_on_cpu - Create a cpu bound kthread + * @threadfn: the function to run until signal_pending(current). + * @data: data ptr for @threadfn. + * @cpu: The cpu on which the thread should be bound, + * @namefmt: printf-style name for the thread. Format is restricted + * to "name.*%u". Code fills in cpu number. + * + * Description: This helper function creates and names a kernel thread + * The thread will be woken and put into park mode. + */ +struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), + void *data, unsigned int cpu, + const char *namefmt) +{ + struct task_struct *p; + + p = kthread_create_on_node(threadfn, data, cpu_to_node(cpu), namefmt, + cpu); + if (IS_ERR(p)) + return p; + set_bit(KTHREAD_IS_PER_CPU, &to_kthread(p)->flags); + to_kthread(p)->cpu = cpu; + /* Park the thread to get it out of TASK_UNINTERRUPTIBLE state */ + kthread_park(p); + return p; +} + +static struct kthread *task_get_live_kthread(struct task_struct *k) +{ + struct kthread *kthread; + + get_task_struct(k); + kthread = to_kthread(k); + /* It might have exited */ + barrier(); + if (k->vfork_done != NULL) + return kthread; + return NULL; +} + +/** + * kthread_unpark - unpark a thread created by kthread_create(). + * @k: thread created by kthread_create(). + * + * Sets kthread_should_park() for @k to return false, wakes it, and + * waits for it to return. If the thread is marked percpu then its + * bound to the cpu again. + */ +void kthread_unpark(struct task_struct *k) +{ + struct kthread *kthread = task_get_live_kthread(k); + + if (kthread) { + clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags); + /* + * We clear the IS_PARKED bit here as we don't wait + * until the task has left the park code. So if we'd + * park before that happens we'd see the IS_PARKED bit + * which might be about to be cleared. + */ + if (test_and_clear_bit(KTHREAD_IS_PARKED, &kthread->flags)) { + if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags)) + __kthread_bind(k, kthread->cpu); + wake_up_process(k); + } + } + put_task_struct(k); +} + +/** + * kthread_park - park a thread created by kthread_create(). + * @k: thread created by kthread_create(). + * + * Sets kthread_should_park() for @k to return true, wakes it, and + * waits for it to return. This can also be called after kthread_create() + * instead of calling wake_up_process(): the thread will park without + * calling threadfn(). + * + * Returns 0 if the thread is parked, -ENOSYS if the thread exited. + * If called by the kthread itself just the park bit is set. + */ +int kthread_park(struct task_struct *k) +{ + struct kthread *kthread = task_get_live_kthread(k); + int ret = -ENOSYS; + + if (kthread) { + if (!test_bit(KTHREAD_IS_PARKED, &kthread->flags)) { + set_bit(KTHREAD_SHOULD_PARK, &kthread->flags); + if (k != current) { + wake_up_process(k); + wait_for_completion(&kthread->parked); + } + } + ret = 0; + } + put_task_struct(k); + return ret; +} + +/** * kthread_stop - stop a thread created by kthread_create(). * @k: thread created by kthread_create(). * @@ -250,16 +401,13 @@ EXPORT_SYMBOL(kthread_bind); */ int kthread_stop(struct task_struct *k) { - struct kthread *kthread; + struct kthread *kthread = task_get_live_kthread(k); int ret; trace_sched_kthread_stop(k); - get_task_struct(k); - - kthread = to_kthread(k); - barrier(); /* it might have exited */ - if (k->vfork_done != NULL) { - kthread->should_stop = 1; + if (kthread) { + set_bit(KTHREAD_SHOULD_STOP, &kthread->flags); + clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags); wake_up_process(k); wait_for_completion(&kthread->exited); } diff --git a/kernel/lockdep.c b/kernel/lockdep.c index ea9ee4518c35..7981e5b2350d 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -2998,6 +2998,42 @@ EXPORT_SYMBOL_GPL(lockdep_init_map); struct lock_class_key __lockdep_no_validate__; +static int +print_lock_nested_lock_not_held(struct task_struct *curr, + struct held_lock *hlock, + unsigned long ip) +{ + if (!debug_locks_off()) + return 0; + if (debug_locks_silent) + return 0; + + printk("\n"); + printk("==================================\n"); + printk("[ BUG: Nested lock was not taken ]\n"); + print_kernel_ident(); + printk("----------------------------------\n"); + + printk("%s/%d is trying to lock:\n", curr->comm, task_pid_nr(curr)); + print_lock(hlock); + + printk("\nbut this task is not holding:\n"); + printk("%s\n", hlock->nest_lock->name); + + printk("\nstack backtrace:\n"); + dump_stack(); + + printk("\nother info that might help us debug this:\n"); + lockdep_print_held_locks(curr); + + printk("\nstack backtrace:\n"); + dump_stack(); + + return 0; +} + +static int __lock_is_held(struct lockdep_map *lock); + /* * This gets called for every mutex_lock*()/spin_lock*() operation. * We maintain the dependency maps and validate the locking attempt: @@ -3139,6 +3175,9 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, } chain_key = iterate_chain_key(chain_key, id); + if (nest_lock && !__lock_is_held(nest_lock)) + return print_lock_nested_lock_not_held(curr, hlock, ip); + if (!validate_chain(curr, lock, hlock, chain_head, chain_key)) return 0; diff --git a/kernel/modsign_pubkey.c b/kernel/modsign_pubkey.c new file mode 100644 index 000000000000..4646eb2c3820 --- /dev/null +++ b/kernel/modsign_pubkey.c @@ -0,0 +1,113 @@ +/* Public keys for module signature verification + * + * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/sched.h> +#include <linux/cred.h> +#include <linux/err.h> +#include <keys/asymmetric-type.h> +#include "module-internal.h" + +struct key *modsign_keyring; + +extern __initdata const u8 modsign_certificate_list[]; +extern __initdata const u8 modsign_certificate_list_end[]; +asm(".section .init.data,\"aw\"\n" + "modsign_certificate_list:\n" + ".incbin \"signing_key.x509\"\n" + ".incbin \"extra_certificates\"\n" + "modsign_certificate_list_end:" + ); + +/* + * We need to make sure ccache doesn't cache the .o file as it doesn't notice + * if modsign.pub changes. + */ +static __initdata const char annoy_ccache[] = __TIME__ "foo"; + +/* + * Load the compiled-in keys + */ +static __init int module_verify_init(void) +{ + pr_notice("Initialise module verification\n"); + + modsign_keyring = key_alloc(&key_type_keyring, ".module_sign", + KUIDT_INIT(0), KGIDT_INIT(0), + current_cred(), + (KEY_POS_ALL & ~KEY_POS_SETATTR) | + KEY_USR_VIEW | KEY_USR_READ, + KEY_ALLOC_NOT_IN_QUOTA); + if (IS_ERR(modsign_keyring)) + panic("Can't allocate module signing keyring\n"); + + if (key_instantiate_and_link(modsign_keyring, NULL, 0, NULL, NULL) < 0) + panic("Can't instantiate module signing keyring\n"); + + return 0; +} + +/* + * Must be initialised before we try and load the keys into the keyring. + */ +device_initcall(module_verify_init); + +/* + * Load the compiled-in keys + */ +static __init int load_module_signing_keys(void) +{ + key_ref_t key; + const u8 *p, *end; + size_t plen; + + pr_notice("Loading module verification certificates\n"); + + end = modsign_certificate_list_end; + p = modsign_certificate_list; + while (p < end) { + /* Each cert begins with an ASN.1 SEQUENCE tag and must be more + * than 256 bytes in size. + */ + if (end - p < 4) + goto dodgy_cert; + if (p[0] != 0x30 && + p[1] != 0x82) + goto dodgy_cert; + plen = (p[2] << 8) | p[3]; + plen += 4; + if (plen > end - p) + goto dodgy_cert; + + key = key_create_or_update(make_key_ref(modsign_keyring, 1), + "asymmetric", + NULL, + p, + plen, + (KEY_POS_ALL & ~KEY_POS_SETATTR) | + KEY_USR_VIEW, + KEY_ALLOC_NOT_IN_QUOTA); + if (IS_ERR(key)) + pr_err("MODSIGN: Problem loading in-kernel X.509 certificate (%ld)\n", + PTR_ERR(key)); + else + pr_notice("MODSIGN: Loaded cert '%s'\n", + key_ref_to_ptr(key)->description); + p += plen; + } + + return 0; + +dodgy_cert: + pr_err("MODSIGN: Problem parsing in-kernel X.509 certificate list\n"); + return 0; +} +late_initcall(load_module_signing_keys); diff --git a/kernel/module-internal.h b/kernel/module-internal.h new file mode 100644 index 000000000000..24f9247b7d02 --- /dev/null +++ b/kernel/module-internal.h @@ -0,0 +1,14 @@ +/* Module internals + * + * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +extern struct key *modsign_keyring; + +extern int mod_verify_sig(const void *mod, unsigned long *_modlen); diff --git a/kernel/module.c b/kernel/module.c index 4edbd9c11aca..6085f5ef88ea 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -58,6 +58,8 @@ #include <linux/jump_label.h> #include <linux/pfn.h> #include <linux/bsearch.h> +#include <linux/fips.h> +#include "module-internal.h" #define CREATE_TRACE_POINTS #include <trace/events/module.h> @@ -102,6 +104,43 @@ static LIST_HEAD(modules); struct list_head *kdb_modules = &modules; /* kdb needs the list of modules */ #endif /* CONFIG_KGDB_KDB */ +#ifdef CONFIG_MODULE_SIG +#ifdef CONFIG_MODULE_SIG_FORCE +static bool sig_enforce = true; +#else +static bool sig_enforce = false; + +static int param_set_bool_enable_only(const char *val, + const struct kernel_param *kp) +{ + int err; + bool test; + struct kernel_param dummy_kp = *kp; + + dummy_kp.arg = &test; + + err = param_set_bool(val, &dummy_kp); + if (err) + return err; + + /* Don't let them unset it once it's set! */ + if (!test && sig_enforce) + return -EROFS; + + if (test) + sig_enforce = true; + return 0; +} + +static const struct kernel_param_ops param_ops_bool_enable_only = { + .set = param_set_bool_enable_only, + .get = param_get_bool, +}; +#define param_check_bool_enable_only param_check_bool + +module_param(sig_enforce, bool_enable_only, 0644); +#endif /* !CONFIG_MODULE_SIG_FORCE */ +#endif /* CONFIG_MODULE_SIG */ /* Block module loading/unloading? */ int modules_disabled = 0; @@ -136,6 +175,7 @@ struct load_info { unsigned long symoffs, stroffs; struct _ddebug *debug; unsigned int num_debug; + bool sig_ok; struct { unsigned int sym, str, mod, vers, info, pcpu; } index; @@ -1949,26 +1989,6 @@ static int simplify_symbols(struct module *mod, const struct load_info *info) return ret; } -int __weak apply_relocate(Elf_Shdr *sechdrs, - const char *strtab, - unsigned int symindex, - unsigned int relsec, - struct module *me) -{ - pr_err("module %s: REL relocation unsupported\n", me->name); - return -ENOEXEC; -} - -int __weak apply_relocate_add(Elf_Shdr *sechdrs, - const char *strtab, - unsigned int symindex, - unsigned int relsec, - struct module *me) -{ - pr_err("module %s: RELA relocation unsupported\n", me->name); - return -ENOEXEC; -} - static int apply_relocations(struct module *mod, const struct load_info *info) { unsigned int i; @@ -2399,7 +2419,44 @@ static inline void kmemleak_load_module(const struct module *mod, } #endif -/* Sets info->hdr and info->len. */ +#ifdef CONFIG_MODULE_SIG +static int module_sig_check(struct load_info *info, + const void *mod, unsigned long *_len) +{ + int err = -ENOKEY; + unsigned long markerlen = sizeof(MODULE_SIG_STRING) - 1; + unsigned long len = *_len; + + if (len > markerlen && + memcmp(mod + len - markerlen, MODULE_SIG_STRING, markerlen) == 0) { + /* We truncate the module to discard the signature */ + *_len -= markerlen; + err = mod_verify_sig(mod, _len); + } + + if (!err) { + info->sig_ok = true; + return 0; + } + + /* Not having a signature is only an error if we're strict. */ + if (err < 0 && fips_enabled) + panic("Module verification failed with error %d in FIPS mode\n", + err); + if (err == -ENOKEY && !sig_enforce) + err = 0; + + return err; +} +#else /* !CONFIG_MODULE_SIG */ +static int module_sig_check(struct load_info *info, + void *mod, unsigned long *len) +{ + return 0; +} +#endif /* !CONFIG_MODULE_SIG */ + +/* Sets info->hdr, info->len and info->sig_ok. */ static int copy_and_check(struct load_info *info, const void __user *umod, unsigned long len, const char __user *uargs) @@ -2419,6 +2476,10 @@ static int copy_and_check(struct load_info *info, goto free_hdr; } + err = module_sig_check(info, hdr, &len); + if (err) + goto free_hdr; + /* Sanity checks against insmoding binaries or wrong arch, weird elf version */ if (memcmp(hdr->e_ident, ELFMAG, SELFMAG) != 0 @@ -2730,6 +2791,10 @@ static int check_module_license_and_versions(struct module *mod) if (strcmp(mod->name, "driverloader") == 0) add_taint_module(mod, TAINT_PROPRIETARY_MODULE); + /* lve claims to be GPL but upstream won't provide source */ + if (strcmp(mod->name, "lve") == 0) + add_taint_module(mod, TAINT_PROPRIETARY_MODULE); + #ifdef CONFIG_MODVERSIONS if ((mod->num_syms && !mod->crcs) || (mod->num_gpl_syms && !mod->gpl_crcs) @@ -2861,6 +2926,20 @@ static int post_relocation(struct module *mod, const struct load_info *info) return module_finalize(info->hdr, info->sechdrs, mod); } +/* Is this module of this name done loading? No locks held. */ +static bool finished_loading(const char *name) +{ + struct module *mod; + bool ret; + + mutex_lock(&module_mutex); + mod = find_module(name); + ret = !mod || mod->state != MODULE_STATE_COMING; + mutex_unlock(&module_mutex); + + return ret; +} + /* 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, @@ -2868,7 +2947,7 @@ static struct module *load_module(void __user *umod, const char __user *uargs) { struct load_info info = { NULL, }; - struct module *mod; + struct module *mod, *old; long err; pr_debug("load_module: umod=%p, len=%lu, uargs=%p\n", @@ -2886,6 +2965,12 @@ static struct module *load_module(void __user *umod, goto free_copy; } +#ifdef CONFIG_MODULE_SIG + mod->sig_ok = info.sig_ok; + if (!mod->sig_ok) + add_taint_module(mod, TAINT_FORCED_MODULE); +#endif + /* Now module is in final location, initialize linked lists, etc. */ err = module_unload_init(mod); if (err) @@ -2934,8 +3019,18 @@ static struct module *load_module(void __user *umod, * function to insert in a way safe to concurrent readers. * The mutex protects against concurrent writers. */ +again: mutex_lock(&module_mutex); - if (find_module(mod->name)) { + if ((old = find_module(mod->name)) != NULL) { + if (old->state == MODULE_STATE_COMING) { + /* Wait in case it fails to load. */ + mutex_unlock(&module_mutex); + err = wait_event_interruptible(module_wq, + finished_loading(mod->name)); + if (err) + goto free_arch_cleanup; + goto again; + } err = -EEXIST; goto unlock; } @@ -2975,7 +3070,7 @@ static struct module *load_module(void __user *umod, /* Unlink carefully: kallsyms could be walking list. */ list_del_rcu(&mod->list); module_bug_cleanup(mod); - + wake_up_all(&module_wq); ddebug: dynamic_debug_remove(info.debug); unlock: @@ -3050,7 +3145,7 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_GOING, mod); free_module(mod); - wake_up(&module_wq); + wake_up_all(&module_wq); return ret; } if (ret > 0) { @@ -3062,9 +3157,8 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, dump_stack(); } - /* Now it's a first class citizen! Wake up anyone waiting for it. */ + /* Now it's a first class citizen! */ mod->state = MODULE_STATE_LIVE; - wake_up(&module_wq); blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_LIVE, mod); @@ -3087,6 +3181,7 @@ SYSCALL_DEFINE3(init_module, void __user *, umod, mod->init_ro_size = 0; mod->init_text_size = 0; mutex_unlock(&module_mutex); + wake_up_all(&module_wq); return 0; } diff --git a/kernel/module_signing.c b/kernel/module_signing.c new file mode 100644 index 000000000000..ea1b1df5dbb0 --- /dev/null +++ b/kernel/module_signing.c @@ -0,0 +1,249 @@ +/* Module signature checker + * + * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include <linux/kernel.h> +#include <linux/err.h> +#include <crypto/public_key.h> +#include <crypto/hash.h> +#include <keys/asymmetric-type.h> +#include "module-internal.h" + +/* + * Module signature information block. + * + * The constituents of the signature section are, in order: + * + * - Signer's name + * - Key identifier + * - Signature data + * - Information block + */ +struct module_signature { + enum pkey_algo algo : 8; /* Public-key crypto algorithm */ + enum pkey_hash_algo hash : 8; /* Digest algorithm */ + enum pkey_id_type id_type : 8; /* Key identifier type */ + u8 signer_len; /* Length of signer's name */ + u8 key_id_len; /* Length of key identifier */ + u8 __pad[3]; + __be32 sig_len; /* Length of signature data */ +}; + +/* + * Digest the module contents. + */ +static struct public_key_signature *mod_make_digest(enum pkey_hash_algo hash, + const void *mod, + unsigned long modlen) +{ + struct public_key_signature *pks; + struct crypto_shash *tfm; + struct shash_desc *desc; + size_t digest_size, desc_size; + int ret; + + pr_devel("==>%s()\n", __func__); + + /* Allocate the hashing algorithm we're going to need and find out how + * big the hash operational data will be. + */ + tfm = crypto_alloc_shash(pkey_hash_algo[hash], 0, 0); + if (IS_ERR(tfm)) + return (PTR_ERR(tfm) == -ENOENT) ? ERR_PTR(-ENOPKG) : ERR_CAST(tfm); + + desc_size = crypto_shash_descsize(tfm) + sizeof(*desc); + digest_size = crypto_shash_digestsize(tfm); + + /* We allocate the hash operational data storage on the end of our + * context data and the digest output buffer on the end of that. + */ + ret = -ENOMEM; + pks = kzalloc(digest_size + sizeof(*pks) + desc_size, GFP_KERNEL); + if (!pks) + goto error_no_pks; + + pks->pkey_hash_algo = hash; + pks->digest = (u8 *)pks + sizeof(*pks) + desc_size; + pks->digest_size = digest_size; + + desc = (void *)pks + sizeof(*pks); + desc->tfm = tfm; + desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; + + ret = crypto_shash_init(desc); + if (ret < 0) + goto error; + + ret = crypto_shash_finup(desc, mod, modlen, pks->digest); + if (ret < 0) + goto error; + + crypto_free_shash(tfm); + pr_devel("<==%s() = ok\n", __func__); + return pks; + +error: + kfree(pks); +error_no_pks: + crypto_free_shash(tfm); + pr_devel("<==%s() = %d\n", __func__, ret); + return ERR_PTR(ret); +} + +/* + * Extract an MPI array from the signature data. This represents the actual + * signature. Each raw MPI is prefaced by a BE 2-byte value indicating the + * size of the MPI in bytes. + * + * RSA signatures only have one MPI, so currently we only read one. + */ +static int mod_extract_mpi_array(struct public_key_signature *pks, + const void *data, size_t len) +{ + size_t nbytes; + MPI mpi; + + if (len < 3) + return -EBADMSG; + nbytes = ((const u8 *)data)[0] << 8 | ((const u8 *)data)[1]; + data += 2; + len -= 2; + if (len != nbytes) + return -EBADMSG; + + mpi = mpi_read_raw_data(data, nbytes); + if (!mpi) + return -ENOMEM; + pks->mpi[0] = mpi; + pks->nr_mpi = 1; + return 0; +} + +/* + * Request an asymmetric key. + */ +static struct key *request_asymmetric_key(const char *signer, size_t signer_len, + const u8 *key_id, size_t key_id_len) +{ + key_ref_t key; + size_t i; + char *id, *q; + + pr_devel("==>%s(,%zu,,%zu)\n", __func__, signer_len, key_id_len); + + /* Construct an identifier. */ + id = kmalloc(signer_len + 2 + key_id_len * 2 + 1, GFP_KERNEL); + if (!id) + return ERR_PTR(-ENOKEY); + + memcpy(id, signer, signer_len); + + q = id + signer_len; + *q++ = ':'; + *q++ = ' '; + for (i = 0; i < key_id_len; i++) { + *q++ = hex_asc[*key_id >> 4]; + *q++ = hex_asc[*key_id++ & 0x0f]; + } + + *q = 0; + + pr_debug("Look up: \"%s\"\n", id); + + key = keyring_search(make_key_ref(modsign_keyring, 1), + &key_type_asymmetric, id); + if (IS_ERR(key)) + pr_warn("Request for unknown module key '%s' err %ld\n", + id, PTR_ERR(key)); + kfree(id); + + if (IS_ERR(key)) { + switch (PTR_ERR(key)) { + /* Hide some search errors */ + case -EACCES: + case -ENOTDIR: + case -EAGAIN: + return ERR_PTR(-ENOKEY); + default: + return ERR_CAST(key); + } + } + + pr_devel("<==%s() = 0 [%x]\n", __func__, key_serial(key_ref_to_ptr(key))); + return key_ref_to_ptr(key); +} + +/* + * Verify the signature on a module. + */ +int mod_verify_sig(const void *mod, unsigned long *_modlen) +{ + struct public_key_signature *pks; + struct module_signature ms; + struct key *key; + const void *sig; + size_t modlen = *_modlen, sig_len; + int ret; + + pr_devel("==>%s(,%zu)\n", __func__, modlen); + + if (modlen <= sizeof(ms)) + return -EBADMSG; + + memcpy(&ms, mod + (modlen - sizeof(ms)), sizeof(ms)); + modlen -= sizeof(ms); + + sig_len = be32_to_cpu(ms.sig_len); + if (sig_len >= modlen) + return -EBADMSG; + modlen -= sig_len; + if ((size_t)ms.signer_len + ms.key_id_len >= modlen) + return -EBADMSG; + modlen -= (size_t)ms.signer_len + ms.key_id_len; + + *_modlen = modlen; + sig = mod + modlen; + + /* For the moment, only support RSA and X.509 identifiers */ + if (ms.algo != PKEY_ALGO_RSA || + ms.id_type != PKEY_ID_X509) + return -ENOPKG; + + if (ms.hash >= PKEY_HASH__LAST || + !pkey_hash_algo[ms.hash]) + return -ENOPKG; + + key = request_asymmetric_key(sig, ms.signer_len, + sig + ms.signer_len, ms.key_id_len); + if (IS_ERR(key)) + return PTR_ERR(key); + + pks = mod_make_digest(ms.hash, mod, modlen); + if (IS_ERR(pks)) { + ret = PTR_ERR(pks); + goto error_put_key; + } + + ret = mod_extract_mpi_array(pks, sig + ms.signer_len + ms.key_id_len, + sig_len); + if (ret < 0) + goto error_free_pks; + + ret = verify_signature(key, pks); + pr_devel("verify_signature() = %d\n", ret); + +error_free_pks: + mpi_free(pks->rsa.s); + kfree(pks); +error_put_key: + key_put(key); + pr_devel("<==%s() = %d\n", __func__, ret); + return ret; +} diff --git a/kernel/pid.c b/kernel/pid.c index e86b291ad834..aebd4f5aaf41 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -479,6 +479,7 @@ pid_t pid_nr_ns(struct pid *pid, struct pid_namespace *ns) } return nr; } +EXPORT_SYMBOL_GPL(pid_nr_ns); pid_t pid_vnr(struct pid *pid) { diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index 6144bab8fd8e..7b07cc0dfb75 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -16,6 +16,7 @@ #include <linux/slab.h> #include <linux/proc_fs.h> #include <linux/reboot.h> +#include <linux/export.h> #define BITS_PER_PAGE (PAGE_SIZE*8) @@ -70,12 +71,22 @@ err_alloc: return NULL; } +/* MAX_PID_NS_LEVEL is needed for limiting size of 'struct pid' */ +#define MAX_PID_NS_LEVEL 32 + static struct pid_namespace *create_pid_namespace(struct pid_namespace *parent_pid_ns) { struct pid_namespace *ns; unsigned int level = parent_pid_ns->level + 1; - int i, err = -ENOMEM; + int i; + int err; + + if (level > MAX_PID_NS_LEVEL) { + err = -EINVAL; + goto out; + } + err = -ENOMEM; ns = kmem_cache_zalloc(pid_ns_cachep, GFP_KERNEL); if (ns == NULL) goto out; @@ -132,18 +143,26 @@ struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *old return create_pid_namespace(old_ns); } -void free_pid_ns(struct kref *kref) +static void free_pid_ns(struct kref *kref) { - struct pid_namespace *ns, *parent; + struct pid_namespace *ns; ns = container_of(kref, struct pid_namespace, kref); - - parent = ns->parent; destroy_pid_namespace(ns); +} + +void put_pid_ns(struct pid_namespace *ns) +{ + struct pid_namespace *parent; - if (parent != NULL) - put_pid_ns(parent); + while (ns != &init_pid_ns) { + parent = ns->parent; + if (!kref_put(&ns->kref, free_pid_ns)) + break; + ns = parent; + } } +EXPORT_SYMBOL_GPL(put_pid_ns); void zap_pid_ns_processes(struct pid_namespace *pid_ns) { diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index a70518c9d82f..5dfdc9ea180b 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -263,6 +263,10 @@ config PM_GENERIC_DOMAINS bool depends on PM +config PM_GENERIC_DOMAINS_SLEEP + def_bool y + depends on PM_SLEEP && PM_GENERIC_DOMAINS + config PM_GENERIC_DOMAINS_RUNTIME def_bool y depends on PM_RUNTIME && PM_GENERIC_DOMAINS diff --git a/kernel/power/poweroff.c b/kernel/power/poweroff.c index d52359374e85..68197a4e8fc9 100644 --- a/kernel/power/poweroff.c +++ b/kernel/power/poweroff.c @@ -37,7 +37,7 @@ static struct sysrq_key_op sysrq_poweroff_op = { .enable_mask = SYSRQ_ENABLE_BOOT, }; -static int pm_sysrq_init(void) +static int __init pm_sysrq_init(void) { register_sysrq_key('o', &sysrq_poweroff_op); return 0; diff --git a/kernel/power/process.c b/kernel/power/process.c index 19db29f67558..87da817f9e13 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -79,7 +79,7 @@ static int try_to_freeze_tasks(bool user_only) /* * We need to retry, but first give the freezing tasks some - * time to enter the regrigerator. + * time to enter the refrigerator. */ msleep(10); } diff --git a/kernel/power/qos.c b/kernel/power/qos.c index 6a031e684026..846bd42c7ed1 100644 --- a/kernel/power/qos.c +++ b/kernel/power/qos.c @@ -139,6 +139,7 @@ static inline int pm_qos_get_value(struct pm_qos_constraints *c) default: /* runtime check for not using enum */ BUG(); + return PM_QOS_DEFAULT_VALUE; } } diff --git a/kernel/printk.c b/kernel/printk.c index 66a2ea37b576..2d607f4d1797 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -1890,7 +1890,6 @@ static int __cpuinit console_cpu_notify(struct notifier_block *self, switch (action) { case CPU_ONLINE: case CPU_DEAD: - case CPU_DYING: case CPU_DOWN_FAILED: case CPU_UP_CANCELED: console_lock(); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index a232bb59d93f..1f5e55dda955 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -180,7 +180,8 @@ static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode) return has_ns_capability(current, ns, CAP_SYS_PTRACE); } -int __ptrace_may_access(struct task_struct *task, unsigned int mode) +/* Returns 0 on success, -errno on denial. */ +static int __ptrace_may_access(struct task_struct *task, unsigned int mode) { const struct cred *cred = current_cred(), *tcred; diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index 4e6a61b15e86..29ca1c6da594 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -45,6 +45,7 @@ #include <linux/mutex.h> #include <linux/export.h> #include <linux/hardirq.h> +#include <linux/delay.h> #define CREATE_TRACE_POINTS #include <trace/events/rcu.h> @@ -81,6 +82,9 @@ void __rcu_read_unlock(void) } else { barrier(); /* critical section before exit code. */ t->rcu_read_lock_nesting = INT_MIN; +#ifdef CONFIG_PROVE_RCU_DELAY + udelay(10); /* Make preemption more probable. */ +#endif /* #ifdef CONFIG_PROVE_RCU_DELAY */ barrier(); /* assign before ->rcu_read_unlock_special load */ if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) rcu_read_unlock_special(t); diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c index 547b1fe5b052..e4c6a598d6f7 100644 --- a/kernel/rcutiny.c +++ b/kernel/rcutiny.c @@ -56,25 +56,28 @@ static void __call_rcu(struct rcu_head *head, static long long rcu_dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; /* Common code for rcu_idle_enter() and rcu_irq_exit(), see kernel/rcutree.c. */ -static void rcu_idle_enter_common(long long oldval) +static void rcu_idle_enter_common(long long newval) { - if (rcu_dynticks_nesting) { + if (newval) { RCU_TRACE(trace_rcu_dyntick("--=", - oldval, rcu_dynticks_nesting)); + rcu_dynticks_nesting, newval)); + rcu_dynticks_nesting = newval; return; } - RCU_TRACE(trace_rcu_dyntick("Start", oldval, rcu_dynticks_nesting)); + RCU_TRACE(trace_rcu_dyntick("Start", rcu_dynticks_nesting, newval)); if (!is_idle_task(current)) { struct task_struct *idle = idle_task(smp_processor_id()); RCU_TRACE(trace_rcu_dyntick("Error on entry: not idle task", - oldval, rcu_dynticks_nesting)); + rcu_dynticks_nesting, newval)); ftrace_dump(DUMP_ALL); WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s", current->pid, current->comm, idle->pid, idle->comm); /* must be idle task! */ } rcu_sched_qs(0); /* implies rcu_bh_qsctr_inc(0) */ + barrier(); + rcu_dynticks_nesting = newval; } /* @@ -84,17 +87,16 @@ static void rcu_idle_enter_common(long long oldval) void rcu_idle_enter(void) { unsigned long flags; - long long oldval; + long long newval; local_irq_save(flags); - oldval = rcu_dynticks_nesting; WARN_ON_ONCE((rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK) == 0); if ((rcu_dynticks_nesting & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) - rcu_dynticks_nesting = 0; + newval = 0; else - rcu_dynticks_nesting -= DYNTICK_TASK_NEST_VALUE; - rcu_idle_enter_common(oldval); + newval = rcu_dynticks_nesting - DYNTICK_TASK_NEST_VALUE; + rcu_idle_enter_common(newval); local_irq_restore(flags); } EXPORT_SYMBOL_GPL(rcu_idle_enter); @@ -105,15 +107,15 @@ EXPORT_SYMBOL_GPL(rcu_idle_enter); void rcu_irq_exit(void) { unsigned long flags; - long long oldval; + long long newval; local_irq_save(flags); - oldval = rcu_dynticks_nesting; - rcu_dynticks_nesting--; - WARN_ON_ONCE(rcu_dynticks_nesting < 0); - rcu_idle_enter_common(oldval); + newval = rcu_dynticks_nesting - 1; + WARN_ON_ONCE(newval < 0); + rcu_idle_enter_common(newval); local_irq_restore(flags); } +EXPORT_SYMBOL_GPL(rcu_irq_exit); /* Common code for rcu_idle_exit() and rcu_irq_enter(), see kernel/rcutree.c. */ static void rcu_idle_exit_common(long long oldval) @@ -171,6 +173,7 @@ void rcu_irq_enter(void) rcu_idle_exit_common(oldval); local_irq_restore(flags); } +EXPORT_SYMBOL_GPL(rcu_irq_enter); #ifdef CONFIG_DEBUG_LOCK_ALLOC diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h index 918fd1e8509c..3d0190282204 100644 --- a/kernel/rcutiny_plugin.h +++ b/kernel/rcutiny_plugin.h @@ -278,7 +278,7 @@ static int rcu_boost(void) rcu_preempt_ctrlblk.exp_tasks == NULL) return 0; /* Nothing to boost. */ - raw_local_irq_save(flags); + local_irq_save(flags); /* * Recheck with irqs disabled: all tasks in need of boosting @@ -287,7 +287,7 @@ static int rcu_boost(void) */ if (rcu_preempt_ctrlblk.boost_tasks == NULL && rcu_preempt_ctrlblk.exp_tasks == NULL) { - raw_local_irq_restore(flags); + local_irq_restore(flags); return 0; } @@ -317,7 +317,7 @@ static int rcu_boost(void) t = container_of(tb, struct task_struct, rcu_node_entry); rt_mutex_init_proxy_locked(&mtx, t); t->rcu_boost_mutex = &mtx; - raw_local_irq_restore(flags); + local_irq_restore(flags); rt_mutex_lock(&mtx); rt_mutex_unlock(&mtx); /* Keep lockdep happy. */ @@ -991,9 +991,9 @@ static void rcu_trace_sub_qlen(struct rcu_ctrlblk *rcp, int n) { unsigned long flags; - raw_local_irq_save(flags); + local_irq_save(flags); rcp->qlen -= n; - raw_local_irq_restore(flags); + local_irq_restore(flags); } /* diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 25b15033c61f..aaa7b9f3532a 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -53,10 +53,11 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@fre static int nreaders = -1; /* # reader threads, defaults to 2*ncpus */ static int nfakewriters = 4; /* # fake writer threads */ -static int stat_interval; /* Interval between stats, in seconds. */ - /* Defaults to "only at end of test". */ +static int stat_interval = 60; /* Interval between stats, in seconds. */ + /* Zero means "only at end of test". */ static bool verbose; /* Print more debug info. */ -static bool test_no_idle_hz; /* Test RCU's support for tickless idle CPUs. */ +static bool test_no_idle_hz = true; + /* Test RCU support for tickless idle CPUs. */ static int shuffle_interval = 3; /* Interval between shuffles (in sec)*/ static int stutter = 5; /* Start/stop testing interval (in sec) */ static int irqreader = 1; /* RCU readers from irq (timers). */ @@ -119,11 +120,11 @@ MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, srcu)"); #define TORTURE_FLAG "-torture:" #define PRINTK_STRING(s) \ - do { printk(KERN_ALERT "%s" TORTURE_FLAG s "\n", torture_type); } while (0) + do { pr_alert("%s" TORTURE_FLAG s "\n", torture_type); } while (0) #define VERBOSE_PRINTK_STRING(s) \ - do { if (verbose) printk(KERN_ALERT "%s" TORTURE_FLAG s "\n", torture_type); } while (0) + do { if (verbose) pr_alert("%s" TORTURE_FLAG s "\n", torture_type); } while (0) #define VERBOSE_PRINTK_ERRSTRING(s) \ - do { if (verbose) printk(KERN_ALERT "%s" TORTURE_FLAG "!!! " s "\n", torture_type); } while (0) + do { if (verbose) pr_alert("%s" TORTURE_FLAG "!!! " s "\n", torture_type); } while (0) static char printk_buf[4096]; @@ -176,8 +177,14 @@ static long n_rcu_torture_boosts; static long n_rcu_torture_timers; static long n_offline_attempts; static long n_offline_successes; +static unsigned long sum_offline; +static int min_offline = -1; +static int max_offline; static long n_online_attempts; static long n_online_successes; +static unsigned long sum_online; +static int min_online = -1; +static int max_online; static long n_barrier_attempts; static long n_barrier_successes; static struct list_head rcu_torture_removed; @@ -235,7 +242,7 @@ rcutorture_shutdown_notify(struct notifier_block *unused1, if (fullstop == FULLSTOP_DONTSTOP) fullstop = FULLSTOP_SHUTDOWN; else - printk(KERN_WARNING /* but going down anyway, so... */ + pr_warn(/* but going down anyway, so... */ "Concurrent 'rmmod rcutorture' and shutdown illegal!\n"); mutex_unlock(&fullstop_mutex); return NOTIFY_DONE; @@ -248,7 +255,7 @@ rcutorture_shutdown_notify(struct notifier_block *unused1, static void rcutorture_shutdown_absorb(char *title) { if (ACCESS_ONCE(fullstop) == FULLSTOP_SHUTDOWN) { - printk(KERN_NOTICE + pr_notice( "rcutorture thread %s parking due to system shutdown\n", title); schedule_timeout_uninterruptible(MAX_SCHEDULE_TIMEOUT); @@ -1214,11 +1221,13 @@ rcu_torture_printk(char *page) n_rcu_torture_boost_failure, n_rcu_torture_boosts, n_rcu_torture_timers); - cnt += sprintf(&page[cnt], "onoff: %ld/%ld:%ld/%ld ", - n_online_successes, - n_online_attempts, - n_offline_successes, - n_offline_attempts); + cnt += sprintf(&page[cnt], + "onoff: %ld/%ld:%ld/%ld %d,%d:%d,%d %lu:%lu (HZ=%d) ", + n_online_successes, n_online_attempts, + n_offline_successes, n_offline_attempts, + min_online, max_online, + min_offline, max_offline, + sum_online, sum_offline, HZ); cnt += sprintf(&page[cnt], "barrier: %ld/%ld:%ld", n_barrier_successes, n_barrier_attempts, @@ -1267,7 +1276,7 @@ rcu_torture_stats_print(void) int cnt; cnt = rcu_torture_printk(printk_buf); - printk(KERN_ALERT "%s", printk_buf); + pr_alert("%s", printk_buf); } /* @@ -1380,20 +1389,20 @@ rcu_torture_stutter(void *arg) static inline void rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, char *tag) { - printk(KERN_ALERT "%s" TORTURE_FLAG - "--- %s: nreaders=%d nfakewriters=%d " - "stat_interval=%d verbose=%d test_no_idle_hz=%d " - "shuffle_interval=%d stutter=%d irqreader=%d " - "fqs_duration=%d fqs_holdoff=%d fqs_stutter=%d " - "test_boost=%d/%d test_boost_interval=%d " - "test_boost_duration=%d shutdown_secs=%d " - "onoff_interval=%d onoff_holdoff=%d\n", - torture_type, tag, nrealreaders, nfakewriters, - stat_interval, verbose, test_no_idle_hz, shuffle_interval, - stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter, - test_boost, cur_ops->can_boost, - test_boost_interval, test_boost_duration, shutdown_secs, - onoff_interval, onoff_holdoff); + pr_alert("%s" TORTURE_FLAG + "--- %s: nreaders=%d nfakewriters=%d " + "stat_interval=%d verbose=%d test_no_idle_hz=%d " + "shuffle_interval=%d stutter=%d irqreader=%d " + "fqs_duration=%d fqs_holdoff=%d fqs_stutter=%d " + "test_boost=%d/%d test_boost_interval=%d " + "test_boost_duration=%d shutdown_secs=%d " + "onoff_interval=%d onoff_holdoff=%d\n", + torture_type, tag, nrealreaders, nfakewriters, + stat_interval, verbose, test_no_idle_hz, shuffle_interval, + stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter, + test_boost, cur_ops->can_boost, + test_boost_interval, test_boost_duration, shutdown_secs, + onoff_interval, onoff_holdoff); } static struct notifier_block rcutorture_shutdown_nb = { @@ -1460,9 +1469,9 @@ rcu_torture_shutdown(void *arg) !kthread_should_stop()) { delta = shutdown_time - jiffies_snap; if (verbose) - printk(KERN_ALERT "%s" TORTURE_FLAG - "rcu_torture_shutdown task: %lu jiffies remaining\n", - torture_type, delta); + pr_alert("%s" TORTURE_FLAG + "rcu_torture_shutdown task: %lu jiffies remaining\n", + torture_type, delta); schedule_timeout_interruptible(delta); jiffies_snap = ACCESS_ONCE(jiffies); } @@ -1490,8 +1499,10 @@ static int __cpuinit rcu_torture_onoff(void *arg) { int cpu; + unsigned long delta; int maxcpu = -1; DEFINE_RCU_RANDOM(rand); + unsigned long starttime; VERBOSE_PRINTK_STRING("rcu_torture_onoff task started"); for_each_online_cpu(cpu) @@ -1506,29 +1517,51 @@ rcu_torture_onoff(void *arg) cpu = (rcu_random(&rand) >> 4) % (maxcpu + 1); if (cpu_online(cpu) && cpu_is_hotpluggable(cpu)) { if (verbose) - printk(KERN_ALERT "%s" TORTURE_FLAG - "rcu_torture_onoff task: offlining %d\n", - torture_type, cpu); + pr_alert("%s" TORTURE_FLAG + "rcu_torture_onoff task: offlining %d\n", + torture_type, cpu); + starttime = jiffies; n_offline_attempts++; if (cpu_down(cpu) == 0) { if (verbose) - printk(KERN_ALERT "%s" TORTURE_FLAG - "rcu_torture_onoff task: offlined %d\n", - torture_type, cpu); + pr_alert("%s" TORTURE_FLAG + "rcu_torture_onoff task: offlined %d\n", + torture_type, cpu); n_offline_successes++; + delta = jiffies - starttime; + sum_offline += delta; + if (min_offline < 0) { + min_offline = delta; + max_offline = delta; + } + if (min_offline > delta) + min_offline = delta; + if (max_offline < delta) + max_offline = delta; } } else if (cpu_is_hotpluggable(cpu)) { if (verbose) - printk(KERN_ALERT "%s" TORTURE_FLAG - "rcu_torture_onoff task: onlining %d\n", - torture_type, cpu); + pr_alert("%s" TORTURE_FLAG + "rcu_torture_onoff task: onlining %d\n", + torture_type, cpu); + starttime = jiffies; n_online_attempts++; if (cpu_up(cpu) == 0) { if (verbose) - printk(KERN_ALERT "%s" TORTURE_FLAG - "rcu_torture_onoff task: onlined %d\n", - torture_type, cpu); + pr_alert("%s" TORTURE_FLAG + "rcu_torture_onoff task: onlined %d\n", + torture_type, cpu); n_online_successes++; + delta = jiffies - starttime; + sum_online += delta; + if (min_online < 0) { + min_online = delta; + max_online = delta; + } + if (min_online > delta) + min_online = delta; + if (max_online < delta) + max_online = delta; } } schedule_timeout_interruptible(onoff_interval * HZ); @@ -1593,14 +1626,14 @@ static int __cpuinit rcu_torture_stall(void *args) if (!kthread_should_stop()) { stop_at = get_seconds() + stall_cpu; /* RCU CPU stall is expected behavior in following code. */ - printk(KERN_ALERT "rcu_torture_stall start.\n"); + pr_alert("rcu_torture_stall start.\n"); rcu_read_lock(); preempt_disable(); while (ULONG_CMP_LT(get_seconds(), stop_at)) continue; /* Induce RCU CPU stall warning. */ preempt_enable(); rcu_read_unlock(); - printk(KERN_ALERT "rcu_torture_stall end.\n"); + pr_alert("rcu_torture_stall end.\n"); } rcutorture_shutdown_absorb("rcu_torture_stall"); while (!kthread_should_stop()) @@ -1716,12 +1749,12 @@ static int rcu_torture_barrier_init(void) if (n_barrier_cbs == 0) return 0; if (cur_ops->call == NULL || cur_ops->cb_barrier == NULL) { - printk(KERN_ALERT "%s" TORTURE_FLAG - " Call or barrier ops missing for %s,\n", - torture_type, cur_ops->name); - printk(KERN_ALERT "%s" TORTURE_FLAG - " RCU barrier testing omitted from run.\n", - torture_type); + pr_alert("%s" TORTURE_FLAG + " Call or barrier ops missing for %s,\n", + torture_type, cur_ops->name); + pr_alert("%s" TORTURE_FLAG + " RCU barrier testing omitted from run.\n", + torture_type); return 0; } atomic_set(&barrier_cbs_count, 0); @@ -1814,7 +1847,7 @@ rcu_torture_cleanup(void) mutex_lock(&fullstop_mutex); rcutorture_record_test_transition(); if (fullstop == FULLSTOP_SHUTDOWN) { - printk(KERN_WARNING /* but going down anyway, so... */ + pr_warn(/* but going down anyway, so... */ "Concurrent 'rmmod rcutorture' and shutdown illegal!\n"); mutex_unlock(&fullstop_mutex); schedule_timeout_uninterruptible(10); @@ -1938,17 +1971,17 @@ rcu_torture_init(void) break; } if (i == ARRAY_SIZE(torture_ops)) { - printk(KERN_ALERT "rcu-torture: invalid torture type: \"%s\"\n", - torture_type); - printk(KERN_ALERT "rcu-torture types:"); + pr_alert("rcu-torture: invalid torture type: \"%s\"\n", + torture_type); + pr_alert("rcu-torture types:"); for (i = 0; i < ARRAY_SIZE(torture_ops); i++) - printk(KERN_ALERT " %s", torture_ops[i]->name); - printk(KERN_ALERT "\n"); + pr_alert(" %s", torture_ops[i]->name); + pr_alert("\n"); mutex_unlock(&fullstop_mutex); return -EINVAL; } if (cur_ops->fqs == NULL && fqs_duration != 0) { - printk(KERN_ALERT "rcu-torture: ->fqs NULL and non-zero fqs_duration, fqs disabled.\n"); + pr_alert("rcu-torture: ->fqs NULL and non-zero fqs_duration, fqs disabled.\n"); fqs_duration = 0; } if (cur_ops->init) @@ -1996,14 +2029,15 @@ rcu_torture_init(void) /* Start up the kthreads. */ VERBOSE_PRINTK_STRING("Creating rcu_torture_writer task"); - writer_task = kthread_run(rcu_torture_writer, NULL, - "rcu_torture_writer"); + writer_task = kthread_create(rcu_torture_writer, NULL, + "rcu_torture_writer"); if (IS_ERR(writer_task)) { firsterr = PTR_ERR(writer_task); VERBOSE_PRINTK_ERRSTRING("Failed to create writer"); writer_task = NULL; goto unwind; } + wake_up_process(writer_task); fakewriter_tasks = kzalloc(nfakewriters * sizeof(fakewriter_tasks[0]), GFP_KERNEL); if (fakewriter_tasks == NULL) { @@ -2118,14 +2152,15 @@ rcu_torture_init(void) } if (shutdown_secs > 0) { shutdown_time = jiffies + shutdown_secs * HZ; - shutdown_task = kthread_run(rcu_torture_shutdown, NULL, - "rcu_torture_shutdown"); + shutdown_task = kthread_create(rcu_torture_shutdown, NULL, + "rcu_torture_shutdown"); if (IS_ERR(shutdown_task)) { firsterr = PTR_ERR(shutdown_task); VERBOSE_PRINTK_ERRSTRING("Failed to create shutdown"); shutdown_task = NULL; goto unwind; } + wake_up_process(shutdown_task); } i = rcu_torture_onoff_init(); if (i != 0) { diff --git a/kernel/rcutree.c b/kernel/rcutree.c index f280e542e3e9..74df86bd9204 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -52,6 +52,7 @@ #include <linux/prefetch.h> #include <linux/delay.h> #include <linux/stop_machine.h> +#include <linux/random.h> #include "rcutree.h" #include <trace/events/rcu.h> @@ -61,6 +62,7 @@ /* Data structures. */ static struct lock_class_key rcu_node_class[RCU_NUM_LVLS]; +static struct lock_class_key rcu_fqs_class[RCU_NUM_LVLS]; #define RCU_STATE_INITIALIZER(sname, cr) { \ .level = { &sname##_state.node[0] }, \ @@ -72,7 +74,7 @@ static struct lock_class_key rcu_node_class[RCU_NUM_LVLS]; .orphan_nxttail = &sname##_state.orphan_nxtlist, \ .orphan_donetail = &sname##_state.orphan_donelist, \ .barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \ - .fqslock = __RAW_SPIN_LOCK_UNLOCKED(&sname##_state.fqslock), \ + .onoff_mutex = __MUTEX_INITIALIZER(sname##_state.onoff_mutex), \ .name = #sname, \ } @@ -88,7 +90,7 @@ LIST_HEAD(rcu_struct_flavors); /* Increase (but not decrease) the CONFIG_RCU_FANOUT_LEAF at boot time. */ static int rcu_fanout_leaf = CONFIG_RCU_FANOUT_LEAF; -module_param(rcu_fanout_leaf, int, 0); +module_param(rcu_fanout_leaf, int, 0444); int rcu_num_lvls __read_mostly = RCU_NUM_LVLS; static int num_rcu_lvl[] = { /* Number of rcu_nodes at specified level. */ NUM_RCU_LVL_0, @@ -133,13 +135,12 @@ static int rcu_scheduler_fully_active __read_mostly; */ static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task); DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status); -DEFINE_PER_CPU(int, rcu_cpu_kthread_cpu); DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); DEFINE_PER_CPU(char, rcu_cpu_has_work); #endif /* #ifdef CONFIG_RCU_BOOST */ -static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu); +static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu); static void invoke_rcu_core(void); static void invoke_rcu_callbacks(struct rcu_state *rsp, struct rcu_data *rdp); @@ -175,8 +176,6 @@ void rcu_sched_qs(int cpu) { struct rcu_data *rdp = &per_cpu(rcu_sched_data, cpu); - rdp->passed_quiesce_gpnum = rdp->gpnum; - barrier(); if (rdp->passed_quiesce == 0) trace_rcu_grace_period("rcu_sched", rdp->gpnum, "cpuqs"); rdp->passed_quiesce = 1; @@ -186,8 +185,6 @@ void rcu_bh_qs(int cpu) { struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu); - rdp->passed_quiesce_gpnum = rdp->gpnum; - barrier(); if (rdp->passed_quiesce == 0) trace_rcu_grace_period("rcu_bh", rdp->gpnum, "cpuqs"); rdp->passed_quiesce = 1; @@ -210,15 +207,18 @@ EXPORT_SYMBOL_GPL(rcu_note_context_switch); DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = { .dynticks_nesting = DYNTICK_TASK_EXIT_IDLE, .dynticks = ATOMIC_INIT(1), +#if defined(CONFIG_RCU_USER_QS) && !defined(CONFIG_RCU_USER_QS_FORCE) + .ignore_user_qs = true, +#endif }; static int blimit = 10; /* Maximum callbacks per rcu_do_batch. */ static int qhimark = 10000; /* If this many pending, ignore blimit. */ static int qlowmark = 100; /* Once only this many pending, use blimit. */ -module_param(blimit, int, 0); -module_param(qhimark, int, 0); -module_param(qlowmark, int, 0); +module_param(blimit, int, 0444); +module_param(qhimark, int, 0444); +module_param(qlowmark, int, 0444); int rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */ int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT; @@ -226,7 +226,14 @@ int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT; module_param(rcu_cpu_stall_suppress, int, 0644); module_param(rcu_cpu_stall_timeout, int, 0644); -static void force_quiescent_state(struct rcu_state *rsp, int relaxed); +static ulong jiffies_till_first_fqs = RCU_JIFFIES_TILL_FORCE_QS; +static ulong jiffies_till_next_fqs = RCU_JIFFIES_TILL_FORCE_QS; + +module_param(jiffies_till_first_fqs, ulong, 0644); +module_param(jiffies_till_next_fqs, ulong, 0644); + +static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *)); +static void force_quiescent_state(struct rcu_state *rsp); static int rcu_pending(int cpu); /* @@ -252,7 +259,7 @@ EXPORT_SYMBOL_GPL(rcu_batches_completed_bh); */ void rcu_bh_force_quiescent_state(void) { - force_quiescent_state(&rcu_bh_state, 0); + force_quiescent_state(&rcu_bh_state); } EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state); @@ -286,7 +293,7 @@ EXPORT_SYMBOL_GPL(rcutorture_record_progress); */ void rcu_sched_force_quiescent_state(void) { - force_quiescent_state(&rcu_sched_state, 0); + force_quiescent_state(&rcu_sched_state); } EXPORT_SYMBOL_GPL(rcu_sched_force_quiescent_state); @@ -305,7 +312,9 @@ cpu_has_callbacks_ready_to_invoke(struct rcu_data *rdp) static int cpu_needs_another_gp(struct rcu_state *rsp, struct rcu_data *rdp) { - return *rdp->nxttail[RCU_DONE_TAIL] && !rcu_gp_in_progress(rsp); + return *rdp->nxttail[RCU_DONE_TAIL + + ACCESS_ONCE(rsp->completed) != rdp->completed] && + !rcu_gp_in_progress(rsp); } /* @@ -317,45 +326,17 @@ static struct rcu_node *rcu_get_root(struct rcu_state *rsp) } /* - * If the specified CPU is offline, tell the caller that it is in - * a quiescent state. Otherwise, whack it with a reschedule IPI. - * Grace periods can end up waiting on an offline CPU when that - * CPU is in the process of coming online -- it will be added to the - * rcu_node bitmasks before it actually makes it online. The same thing - * can happen while a CPU is in the process of coming online. Because this - * race is quite rare, we check for it after detecting that the grace - * period has been delayed rather than checking each and every CPU - * each and every time we start a new grace period. - */ -static int rcu_implicit_offline_qs(struct rcu_data *rdp) -{ - /* - * If the CPU is offline for more than a jiffy, it is in a quiescent - * state. We can trust its state not to change because interrupts - * are disabled. The reason for the jiffy's worth of slack is to - * handle CPUs initializing on the way up and finding their way - * to the idle loop on the way down. - */ - if (cpu_is_offline(rdp->cpu) && - ULONG_CMP_LT(rdp->rsp->gp_start + 2, jiffies)) { - trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, "ofl"); - rdp->offline_fqs++; - return 1; - } - return 0; -} - -/* - * rcu_idle_enter_common - inform RCU that current CPU is moving towards idle + * rcu_eqs_enter_common - current CPU is moving towards extended quiescent state * * If the new value of the ->dynticks_nesting counter now is zero, * we really have entered idle, and must do the appropriate accounting. * The caller must have disabled interrupts. */ -static void rcu_idle_enter_common(struct rcu_dynticks *rdtp, long long oldval) +static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval, + bool user) { trace_rcu_dyntick("Start", oldval, 0); - if (!is_idle_task(current)) { + if (!user && !is_idle_task(current)) { struct task_struct *idle = idle_task(smp_processor_id()); trace_rcu_dyntick("Error on entry: not idle task", oldval, 0); @@ -372,7 +353,7 @@ static void rcu_idle_enter_common(struct rcu_dynticks *rdtp, long long oldval) WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1); /* - * The idle task is not permitted to enter the idle loop while + * It is illegal to enter an extended quiescent state while * in an RCU read-side critical section. */ rcu_lockdep_assert(!lock_is_held(&rcu_lock_map), @@ -383,6 +364,25 @@ static void rcu_idle_enter_common(struct rcu_dynticks *rdtp, long long oldval) "Illegal idle entry in RCU-sched read-side critical section."); } +/* + * Enter an RCU extended quiescent state, which can be either the + * idle loop or adaptive-tickless usermode execution. + */ +static void rcu_eqs_enter(bool user) +{ + long long oldval; + struct rcu_dynticks *rdtp; + + rdtp = &__get_cpu_var(rcu_dynticks); + oldval = rdtp->dynticks_nesting; + WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0); + if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) + rdtp->dynticks_nesting = 0; + else + rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE; + rcu_eqs_enter_common(rdtp, oldval, user); +} + /** * rcu_idle_enter - inform RCU that current CPU is entering idle * @@ -398,21 +398,70 @@ static void rcu_idle_enter_common(struct rcu_dynticks *rdtp, long long oldval) void rcu_idle_enter(void) { unsigned long flags; - long long oldval; + + local_irq_save(flags); + rcu_eqs_enter(false); + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(rcu_idle_enter); + +#ifdef CONFIG_RCU_USER_QS +/** + * rcu_user_enter - inform RCU that we are resuming userspace. + * + * Enter RCU idle mode right before resuming userspace. No use of RCU + * is permitted between this call and rcu_user_exit(). This way the + * CPU doesn't need to maintain the tick for RCU maintenance purposes + * when the CPU runs in userspace. + */ +void rcu_user_enter(void) +{ + unsigned long flags; struct rcu_dynticks *rdtp; + /* + * Some contexts may involve an exception occuring in an irq, + * leading to that nesting: + * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit() + * This would mess up the dyntick_nesting count though. And rcu_irq_*() + * helpers are enough to protect RCU uses inside the exception. So + * just return immediately if we detect we are in an IRQ. + */ + if (in_interrupt()) + return; + + WARN_ON_ONCE(!current->mm); + local_irq_save(flags); rdtp = &__get_cpu_var(rcu_dynticks); - oldval = rdtp->dynticks_nesting; - WARN_ON_ONCE((oldval & DYNTICK_TASK_NEST_MASK) == 0); - if ((oldval & DYNTICK_TASK_NEST_MASK) == DYNTICK_TASK_NEST_VALUE) - rdtp->dynticks_nesting = 0; - else - rdtp->dynticks_nesting -= DYNTICK_TASK_NEST_VALUE; - rcu_idle_enter_common(rdtp, oldval); + if (!rdtp->ignore_user_qs && !rdtp->in_user) { + rdtp->in_user = true; + rcu_eqs_enter(true); + } local_irq_restore(flags); } -EXPORT_SYMBOL_GPL(rcu_idle_enter); + +/** + * rcu_user_enter_after_irq - inform RCU that we are going to resume userspace + * after the current irq returns. + * + * This is similar to rcu_user_enter() but in the context of a non-nesting + * irq. After this call, RCU enters into idle mode when the interrupt + * returns. + */ +void rcu_user_enter_after_irq(void) +{ + unsigned long flags; + struct rcu_dynticks *rdtp; + + local_irq_save(flags); + rdtp = &__get_cpu_var(rcu_dynticks); + /* Ensure this irq is interrupting a non-idle RCU state. */ + WARN_ON_ONCE(!(rdtp->dynticks_nesting & DYNTICK_TASK_MASK)); + rdtp->dynticks_nesting = 1; + local_irq_restore(flags); +} +#endif /* CONFIG_RCU_USER_QS */ /** * rcu_irq_exit - inform RCU that current CPU is exiting irq towards idle @@ -444,18 +493,19 @@ void rcu_irq_exit(void) if (rdtp->dynticks_nesting) trace_rcu_dyntick("--=", oldval, rdtp->dynticks_nesting); else - rcu_idle_enter_common(rdtp, oldval); + rcu_eqs_enter_common(rdtp, oldval, true); local_irq_restore(flags); } /* - * rcu_idle_exit_common - inform RCU that current CPU is moving away from idle + * rcu_eqs_exit_common - current CPU moving away from extended quiescent state * * If the new value of the ->dynticks_nesting counter was previously zero, * we really have exited idle, and must do the appropriate accounting. * The caller must have disabled interrupts. */ -static void rcu_idle_exit_common(struct rcu_dynticks *rdtp, long long oldval) +static void rcu_eqs_exit_common(struct rcu_dynticks *rdtp, long long oldval, + int user) { smp_mb__before_atomic_inc(); /* Force ordering w/previous sojourn. */ atomic_inc(&rdtp->dynticks); @@ -464,7 +514,7 @@ static void rcu_idle_exit_common(struct rcu_dynticks *rdtp, long long oldval) WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1)); rcu_cleanup_after_idle(smp_processor_id()); trace_rcu_dyntick("End", oldval, rdtp->dynticks_nesting); - if (!is_idle_task(current)) { + if (!user && !is_idle_task(current)) { struct task_struct *idle = idle_task(smp_processor_id()); trace_rcu_dyntick("Error on exit: not idle task", @@ -476,6 +526,25 @@ static void rcu_idle_exit_common(struct rcu_dynticks *rdtp, long long oldval) } } +/* + * Exit an RCU extended quiescent state, which can be either the + * idle loop or adaptive-tickless usermode execution. + */ +static void rcu_eqs_exit(bool user) +{ + struct rcu_dynticks *rdtp; + long long oldval; + + rdtp = &__get_cpu_var(rcu_dynticks); + oldval = rdtp->dynticks_nesting; + WARN_ON_ONCE(oldval < 0); + if (oldval & DYNTICK_TASK_NEST_MASK) + rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE; + else + rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; + rcu_eqs_exit_common(rdtp, oldval, user); +} + /** * rcu_idle_exit - inform RCU that current CPU is leaving idle * @@ -490,21 +559,67 @@ static void rcu_idle_exit_common(struct rcu_dynticks *rdtp, long long oldval) void rcu_idle_exit(void) { unsigned long flags; + + local_irq_save(flags); + rcu_eqs_exit(false); + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(rcu_idle_exit); + +#ifdef CONFIG_RCU_USER_QS +/** + * rcu_user_exit - inform RCU that we are exiting userspace. + * + * Exit RCU idle mode while entering the kernel because it can + * run a RCU read side critical section anytime. + */ +void rcu_user_exit(void) +{ + unsigned long flags; struct rcu_dynticks *rdtp; - long long oldval; + + /* + * Some contexts may involve an exception occuring in an irq, + * leading to that nesting: + * rcu_irq_enter() rcu_user_exit() rcu_user_exit() rcu_irq_exit() + * This would mess up the dyntick_nesting count though. And rcu_irq_*() + * helpers are enough to protect RCU uses inside the exception. So + * just return immediately if we detect we are in an IRQ. + */ + if (in_interrupt()) + return; local_irq_save(flags); rdtp = &__get_cpu_var(rcu_dynticks); - oldval = rdtp->dynticks_nesting; - WARN_ON_ONCE(oldval < 0); - if (oldval & DYNTICK_TASK_NEST_MASK) - rdtp->dynticks_nesting += DYNTICK_TASK_NEST_VALUE; - else - rdtp->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; - rcu_idle_exit_common(rdtp, oldval); + if (rdtp->in_user) { + rdtp->in_user = false; + rcu_eqs_exit(true); + } local_irq_restore(flags); } -EXPORT_SYMBOL_GPL(rcu_idle_exit); + +/** + * rcu_user_exit_after_irq - inform RCU that we won't resume to userspace + * idle mode after the current non-nesting irq returns. + * + * This is similar to rcu_user_exit() but in the context of an irq. + * This is called when the irq has interrupted a userspace RCU idle mode + * context. When the current non-nesting interrupt returns after this call, + * the CPU won't restore the RCU idle mode. + */ +void rcu_user_exit_after_irq(void) +{ + unsigned long flags; + struct rcu_dynticks *rdtp; + + local_irq_save(flags); + rdtp = &__get_cpu_var(rcu_dynticks); + /* Ensure we are interrupting an RCU idle mode. */ + WARN_ON_ONCE(rdtp->dynticks_nesting & DYNTICK_TASK_NEST_MASK); + rdtp->dynticks_nesting += DYNTICK_TASK_EXIT_IDLE; + local_irq_restore(flags); +} +#endif /* CONFIG_RCU_USER_QS */ /** * rcu_irq_enter - inform RCU that current CPU is entering irq away from idle @@ -539,7 +654,7 @@ void rcu_irq_enter(void) if (oldval) trace_rcu_dyntick("++=", oldval, rdtp->dynticks_nesting); else - rcu_idle_exit_common(rdtp, oldval); + rcu_eqs_exit_common(rdtp, oldval, true); local_irq_restore(flags); } @@ -603,6 +718,21 @@ int rcu_is_cpu_idle(void) } EXPORT_SYMBOL(rcu_is_cpu_idle); +#ifdef CONFIG_RCU_USER_QS +void rcu_user_hooks_switch(struct task_struct *prev, + struct task_struct *next) +{ + struct rcu_dynticks *rdtp; + + /* Interrupts are disabled in context switch */ + rdtp = &__get_cpu_var(rcu_dynticks); + if (!rdtp->ignore_user_qs) { + clear_tsk_thread_flag(prev, TIF_NOHZ); + set_tsk_thread_flag(next, TIF_NOHZ); + } +} +#endif /* #ifdef CONFIG_RCU_USER_QS */ + #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) /* @@ -673,7 +803,7 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp) * Return true if the specified CPU has passed through a quiescent * state by virtue of being in or having passed through an dynticks * idle state since the last call to dyntick_save_progress_counter() - * for this same CPU. + * for this same CPU, or by virtue of having been offline. */ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) { @@ -697,8 +827,26 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) return 1; } - /* Go check for the CPU being offline. */ - return rcu_implicit_offline_qs(rdp); + /* + * Check for the CPU being offline, but only if the grace period + * is old enough. We don't need to worry about the CPU changing + * state: If we see it offline even once, it has been through a + * quiescent state. + * + * The reason for insisting that the grace period be at least + * one jiffy old is that CPUs that are not quite online and that + * have just gone offline can still execute RCU read-side critical + * sections. + */ + if (ULONG_CMP_GE(rdp->rsp->gp_start + 2, jiffies)) + return 0; /* Grace period is not old enough. */ + barrier(); + if (cpu_is_offline(rdp->cpu)) { + trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, "ofl"); + rdp->offline_fqs++; + return 1; + } + return 0; } static int jiffies_till_stall_check(void) @@ -755,14 +903,15 @@ static void print_other_cpu_stall(struct rcu_state *rsp) rcu_for_each_leaf_node(rsp, rnp) { raw_spin_lock_irqsave(&rnp->lock, flags); ndetected += rcu_print_task_stall(rnp); + if (rnp->qsmask != 0) { + for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++) + if (rnp->qsmask & (1UL << cpu)) { + print_cpu_stall_info(rsp, + rnp->grplo + cpu); + ndetected++; + } + } raw_spin_unlock_irqrestore(&rnp->lock, flags); - if (rnp->qsmask == 0) - continue; - for (cpu = 0; cpu <= rnp->grphi - rnp->grplo; cpu++) - if (rnp->qsmask & (1UL << cpu)) { - print_cpu_stall_info(rsp, rnp->grplo + cpu); - ndetected++; - } } /* @@ -782,11 +931,11 @@ static void print_other_cpu_stall(struct rcu_state *rsp) else if (!trigger_all_cpu_backtrace()) dump_stack(); - /* If so configured, complain about tasks blocking the grace period. */ + /* Complain about tasks blocking the grace period. */ rcu_print_detail_task_stall(rsp); - force_quiescent_state(rsp, 0); /* Kick them all. */ + force_quiescent_state(rsp); /* Kick them all. */ } static void print_cpu_stall(struct rcu_state *rsp) @@ -827,7 +976,8 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp) j = ACCESS_ONCE(jiffies); js = ACCESS_ONCE(rsp->jiffies_stall); rnp = rdp->mynode; - if ((ACCESS_ONCE(rnp->qsmask) & rdp->grpmask) && ULONG_CMP_GE(j, js)) { + if (rcu_gp_in_progress(rsp) && + (ACCESS_ONCE(rnp->qsmask) & rdp->grpmask) && ULONG_CMP_GE(j, js)) { /* We haven't checked in, so go dump stack. */ print_cpu_stall(rsp); @@ -889,12 +1039,8 @@ static void __note_new_gpnum(struct rcu_state *rsp, struct rcu_node *rnp, struct */ rdp->gpnum = rnp->gpnum; trace_rcu_grace_period(rsp->name, rdp->gpnum, "cpustart"); - if (rnp->qsmask & rdp->grpmask) { - rdp->qs_pending = 1; - rdp->passed_quiesce = 0; - } else { - rdp->qs_pending = 0; - } + rdp->passed_quiesce = 0; + rdp->qs_pending = !!(rnp->qsmask & rdp->grpmask); zero_cpu_stall_ticks(rdp); } } @@ -974,10 +1120,13 @@ __rcu_process_gp_end(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_dat * our behalf. Catch up with this state to avoid noting * spurious new grace periods. If another grace period * has started, then rnp->gpnum will have advanced, so - * we will detect this later on. + * we will detect this later on. Of course, any quiescent + * states we found for the old GP are now invalid. */ - if (ULONG_CMP_LT(rdp->gpnum, rdp->completed)) + if (ULONG_CMP_LT(rdp->gpnum, rdp->completed)) { rdp->gpnum = rdp->completed; + rdp->passed_quiesce = 0; + } /* * If RCU does not need a quiescent state from this CPU, @@ -1021,97 +1170,56 @@ rcu_start_gp_per_cpu(struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_dat /* Prior grace period ended, so advance callbacks for current CPU. */ __rcu_process_gp_end(rsp, rnp, rdp); - /* - * Because this CPU just now started the new grace period, we know - * that all of its callbacks will be covered by this upcoming grace - * period, even the ones that were registered arbitrarily recently. - * Therefore, advance all outstanding callbacks to RCU_WAIT_TAIL. - * - * Other CPUs cannot be sure exactly when the grace period started. - * Therefore, their recently registered callbacks must pass through - * an additional RCU_NEXT_READY stage, so that they will be handled - * by the next RCU grace period. - */ - rdp->nxttail[RCU_NEXT_READY_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; - rdp->nxttail[RCU_WAIT_TAIL] = rdp->nxttail[RCU_NEXT_TAIL]; - /* Set state so that this CPU will detect the next quiescent state. */ __note_new_gpnum(rsp, rnp, rdp); } /* - * Start a new RCU grace period if warranted, re-initializing the hierarchy - * in preparation for detecting the next grace period. The caller must hold - * the root node's ->lock, which is released before return. Hard irqs must - * be disabled. - * - * Note that it is legal for a dying CPU (which is marked as offline) to - * invoke this function. This can happen when the dying CPU reports its - * quiescent state. + * Initialize a new grace period. */ -static void -rcu_start_gp(struct rcu_state *rsp, unsigned long flags) - __releases(rcu_get_root(rsp)->lock) +static int rcu_gp_init(struct rcu_state *rsp) { - struct rcu_data *rdp = this_cpu_ptr(rsp->rda); + struct rcu_data *rdp; struct rcu_node *rnp = rcu_get_root(rsp); - if (!rcu_scheduler_fully_active || - !cpu_needs_another_gp(rsp, rdp)) { - /* - * Either the scheduler hasn't yet spawned the first - * non-idle task or this CPU does not need another - * grace period. Either way, don't start a new grace - * period. - */ - raw_spin_unlock_irqrestore(&rnp->lock, flags); - return; - } + raw_spin_lock_irq(&rnp->lock); + rsp->gp_flags = 0; /* Clear all flags: New grace period. */ - if (rsp->fqs_active) { - /* - * This CPU needs a grace period, but force_quiescent_state() - * is running. Tell it to start one on this CPU's behalf. - */ - rsp->fqs_need_gp = 1; - raw_spin_unlock_irqrestore(&rnp->lock, flags); - return; + if (rcu_gp_in_progress(rsp)) { + /* Grace period already in progress, don't start another. */ + raw_spin_unlock_irq(&rnp->lock); + return 0; } /* Advance to a new grace period and initialize state. */ rsp->gpnum++; trace_rcu_grace_period(rsp->name, rsp->gpnum, "start"); - WARN_ON_ONCE(rsp->fqs_state == RCU_GP_INIT); - rsp->fqs_state = RCU_GP_INIT; /* Hold off force_quiescent_state. */ - rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS; record_gp_stall_check_time(rsp); - raw_spin_unlock(&rnp->lock); /* leave irqs disabled. */ + raw_spin_unlock_irq(&rnp->lock); /* Exclude any concurrent CPU-hotplug operations. */ - raw_spin_lock(&rsp->onofflock); /* irqs already disabled. */ + mutex_lock(&rsp->onoff_mutex); /* * Set the quiescent-state-needed bits in all the rcu_node - * structures for all currently online CPUs in breadth-first - * order, starting from the root rcu_node structure. This - * operation relies on the layout of the hierarchy within the - * rsp->node[] array. Note that other CPUs will access only - * the leaves of the hierarchy, which still indicate that no + * structures for all currently online CPUs in breadth-first order, + * starting from the root rcu_node structure, relying on the layout + * of the tree within the rsp->node[] array. Note that other CPUs + * will access only the leaves of the hierarchy, thus seeing that no * grace period is in progress, at least until the corresponding * leaf node has been initialized. In addition, we have excluded * CPU-hotplug operations. * - * Note that the grace period cannot complete until we finish - * the initialization process, as there will be at least one - * qsmask bit set in the root node until that time, namely the - * one corresponding to this CPU, due to the fact that we have - * irqs disabled. + * The grace period cannot complete until the initialization + * process finishes, because this kthread handles both. */ rcu_for_each_node_breadth_first(rsp, rnp) { - raw_spin_lock(&rnp->lock); /* irqs already disabled. */ + raw_spin_lock_irq(&rnp->lock); + rdp = this_cpu_ptr(rsp->rda); rcu_preempt_check_blocked_tasks(rnp); rnp->qsmask = rnp->qsmaskinit; rnp->gpnum = rsp->gpnum; + WARN_ON_ONCE(rnp->completed != rsp->completed); rnp->completed = rsp->completed; if (rnp == rdp->mynode) rcu_start_gp_per_cpu(rsp, rnp, rdp); @@ -1119,37 +1227,54 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags) trace_rcu_grace_period_init(rsp->name, rnp->gpnum, rnp->level, rnp->grplo, rnp->grphi, rnp->qsmask); - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + raw_spin_unlock_irq(&rnp->lock); +#ifdef CONFIG_PROVE_RCU_DELAY + if ((random32() % (rcu_num_nodes * 8)) == 0) + schedule_timeout_uninterruptible(2); +#endif /* #ifdef CONFIG_PROVE_RCU_DELAY */ + cond_resched(); } - rnp = rcu_get_root(rsp); - raw_spin_lock(&rnp->lock); /* irqs already disabled. */ - rsp->fqs_state = RCU_SIGNAL_INIT; /* force_quiescent_state now OK. */ - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ - raw_spin_unlock_irqrestore(&rsp->onofflock, flags); + mutex_unlock(&rsp->onoff_mutex); + return 1; } /* - * Report a full set of quiescent states to the specified rcu_state - * data structure. This involves cleaning up after the prior grace - * period and letting rcu_start_gp() start up the next grace period - * if one is needed. Note that the caller must hold rnp->lock, as - * required by rcu_start_gp(), which will release it. + * Do one round of quiescent-state forcing. */ -static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) - __releases(rcu_get_root(rsp)->lock) +int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in) { - unsigned long gp_duration; + int fqs_state = fqs_state_in; struct rcu_node *rnp = rcu_get_root(rsp); - struct rcu_data *rdp = this_cpu_ptr(rsp->rda); - WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); + rsp->n_force_qs++; + if (fqs_state == RCU_SAVE_DYNTICK) { + /* Collect dyntick-idle snapshots. */ + force_qs_rnp(rsp, dyntick_save_progress_counter); + fqs_state = RCU_FORCE_QS; + } else { + /* Handle dyntick-idle and offline CPUs. */ + force_qs_rnp(rsp, rcu_implicit_dynticks_qs); + } + /* Clear flag to prevent immediate re-entry. */ + if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { + raw_spin_lock_irq(&rnp->lock); + rsp->gp_flags &= ~RCU_GP_FLAG_FQS; + raw_spin_unlock_irq(&rnp->lock); + } + return fqs_state; +} - /* - * Ensure that all grace-period and pre-grace-period activity - * is seen before the assignment to rsp->completed. - */ - smp_mb(); /* See above block comment. */ +/* + * Clean up after the old grace period. + */ +static void rcu_gp_cleanup(struct rcu_state *rsp) +{ + unsigned long gp_duration; + struct rcu_data *rdp; + struct rcu_node *rnp = rcu_get_root(rsp); + + raw_spin_lock_irq(&rnp->lock); gp_duration = jiffies - rsp->gp_start; if (gp_duration > rsp->gp_max) rsp->gp_max = gp_duration; @@ -1161,35 +1286,149 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) * they can do to advance the grace period. It is therefore * safe for us to drop the lock in order to mark the grace * period as completed in all of the rcu_node structures. - * - * But if this CPU needs another grace period, it will take - * care of this while initializing the next grace period. - * We use RCU_WAIT_TAIL instead of the usual RCU_DONE_TAIL - * because the callbacks have not yet been advanced: Those - * callbacks are waiting on the grace period that just now - * completed. */ - if (*rdp->nxttail[RCU_WAIT_TAIL] == NULL) { - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + raw_spin_unlock_irq(&rnp->lock); - /* - * Propagate new ->completed value to rcu_node structures - * so that other CPUs don't have to wait until the start - * of the next grace period to process their callbacks. - */ - rcu_for_each_node_breadth_first(rsp, rnp) { - raw_spin_lock(&rnp->lock); /* irqs already disabled. */ - rnp->completed = rsp->gpnum; - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ - } - rnp = rcu_get_root(rsp); - raw_spin_lock(&rnp->lock); /* irqs already disabled. */ + /* + * Propagate new ->completed value to rcu_node structures so + * that other CPUs don't have to wait until the start of the next + * grace period to process their callbacks. This also avoids + * some nasty RCU grace-period initialization races by forcing + * the end of the current grace period to be completely recorded in + * all of the rcu_node structures before the beginning of the next + * grace period is recorded in any of the rcu_node structures. + */ + rcu_for_each_node_breadth_first(rsp, rnp) { + raw_spin_lock_irq(&rnp->lock); + rnp->completed = rsp->gpnum; + raw_spin_unlock_irq(&rnp->lock); + cond_resched(); } + rnp = rcu_get_root(rsp); + raw_spin_lock_irq(&rnp->lock); - rsp->completed = rsp->gpnum; /* Declare the grace period complete. */ + rsp->completed = rsp->gpnum; /* Declare grace period done. */ trace_rcu_grace_period(rsp->name, rsp->completed, "end"); rsp->fqs_state = RCU_GP_IDLE; - rcu_start_gp(rsp, flags); /* releases root node's rnp->lock. */ + rdp = this_cpu_ptr(rsp->rda); + if (cpu_needs_another_gp(rsp, rdp)) + rsp->gp_flags = 1; + raw_spin_unlock_irq(&rnp->lock); +} + +/* + * Body of kthread that handles grace periods. + */ +static int __noreturn rcu_gp_kthread(void *arg) +{ + int fqs_state; + unsigned long j; + int ret; + struct rcu_state *rsp = arg; + struct rcu_node *rnp = rcu_get_root(rsp); + + for (;;) { + + /* Handle grace-period start. */ + for (;;) { + wait_event_interruptible(rsp->gp_wq, + rsp->gp_flags & + RCU_GP_FLAG_INIT); + if ((rsp->gp_flags & RCU_GP_FLAG_INIT) && + rcu_gp_init(rsp)) + break; + cond_resched(); + flush_signals(current); + } + + /* Handle quiescent-state forcing. */ + fqs_state = RCU_SAVE_DYNTICK; + j = jiffies_till_first_fqs; + if (j > HZ) { + j = HZ; + jiffies_till_first_fqs = HZ; + } + for (;;) { + rsp->jiffies_force_qs = jiffies + j; + ret = wait_event_interruptible_timeout(rsp->gp_wq, + (rsp->gp_flags & RCU_GP_FLAG_FQS) || + (!ACCESS_ONCE(rnp->qsmask) && + !rcu_preempt_blocked_readers_cgp(rnp)), + j); + /* If grace period done, leave loop. */ + if (!ACCESS_ONCE(rnp->qsmask) && + !rcu_preempt_blocked_readers_cgp(rnp)) + break; + /* If time for quiescent-state forcing, do it. */ + if (ret == 0 || (rsp->gp_flags & RCU_GP_FLAG_FQS)) { + fqs_state = rcu_gp_fqs(rsp, fqs_state); + cond_resched(); + } else { + /* Deal with stray signal. */ + cond_resched(); + flush_signals(current); + } + j = jiffies_till_next_fqs; + if (j > HZ) { + j = HZ; + jiffies_till_next_fqs = HZ; + } else if (j < 1) { + j = 1; + jiffies_till_next_fqs = 1; + } + } + + /* Handle grace-period end. */ + rcu_gp_cleanup(rsp); + } +} + +/* + * Start a new RCU grace period if warranted, re-initializing the hierarchy + * in preparation for detecting the next grace period. The caller must hold + * the root node's ->lock, which is released before return. Hard irqs must + * be disabled. + * + * Note that it is legal for a dying CPU (which is marked as offline) to + * invoke this function. This can happen when the dying CPU reports its + * quiescent state. + */ +static void +rcu_start_gp(struct rcu_state *rsp, unsigned long flags) + __releases(rcu_get_root(rsp)->lock) +{ + struct rcu_data *rdp = this_cpu_ptr(rsp->rda); + struct rcu_node *rnp = rcu_get_root(rsp); + + if (!rsp->gp_kthread || + !cpu_needs_another_gp(rsp, rdp)) { + /* + * Either we have not yet spawned the grace-period + * task or this CPU does not need another grace period. + * Either way, don't start a new grace period. + */ + raw_spin_unlock_irqrestore(&rnp->lock, flags); + return; + } + + rsp->gp_flags = RCU_GP_FLAG_INIT; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + wake_up(&rsp->gp_wq); +} + +/* + * Report a full set of quiescent states to the specified rcu_state + * data structure. This involves cleaning up after the prior grace + * period and letting rcu_start_gp() start up the next grace period + * if one is needed. Note that the caller must hold rnp->lock, as + * required by rcu_start_gp(), which will release it. + */ +static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) + __releases(rcu_get_root(rsp)->lock) +{ + WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); + raw_spin_unlock_irqrestore(&rcu_get_root(rsp)->lock, flags); + wake_up(&rsp->gp_wq); /* Memory barrier implied by wake_up() path. */ } /* @@ -1258,7 +1497,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp, * based on quiescent states detected in an earlier grace period! */ static void -rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long lastgp) +rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp) { unsigned long flags; unsigned long mask; @@ -1266,7 +1505,8 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp, long las rnp = rdp->mynode; raw_spin_lock_irqsave(&rnp->lock, flags); - if (lastgp != rnp->gpnum || rnp->completed == rnp->gpnum) { + if (rdp->passed_quiesce == 0 || rdp->gpnum != rnp->gpnum || + rnp->completed == rnp->gpnum) { /* * The grace period in which this quiescent state was @@ -1325,7 +1565,7 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp) * Tell RCU we are done (but rcu_report_qs_rdp() will be the * judge of that). */ - rcu_report_qs_rdp(rdp->cpu, rsp, rdp, rdp->passed_quiesce_gpnum); + rcu_report_qs_rdp(rdp->cpu, rsp, rdp); } #ifdef CONFIG_HOTPLUG_CPU @@ -1390,17 +1630,6 @@ static void rcu_adopt_orphan_cbs(struct rcu_state *rsp) int i; struct rcu_data *rdp = __this_cpu_ptr(rsp->rda); - /* - * If there is an rcu_barrier() operation in progress, then - * only the task doing that operation is permitted to adopt - * callbacks. To do otherwise breaks rcu_barrier() and friends - * by causing them to fail to wait for the callbacks in the - * orphanage. - */ - if (rsp->rcu_barrier_in_progress && - rsp->rcu_barrier_in_progress != current) - return; - /* Do the accounting first. */ rdp->qlen_lazy += rsp->qlen_lazy; rdp->qlen += rsp->qlen; @@ -1455,9 +1684,8 @@ static void rcu_cleanup_dying_cpu(struct rcu_state *rsp) * The CPU has been completely removed, and some other CPU is reporting * this fact from process context. Do the remainder of the cleanup, * including orphaning the outgoing CPU's RCU callbacks, and also - * adopting them, if there is no _rcu_barrier() instance running. - * There can only be one CPU hotplug operation at a time, so no other - * CPU can be attempting to update rcu_cpu_kthread_task. + * adopting them. There can only be one CPU hotplug operation at a time, + * so no other CPU can be attempting to update rcu_cpu_kthread_task. */ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) { @@ -1468,12 +1696,12 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */ /* Adjust any no-longer-needed kthreads. */ - rcu_stop_cpu_kthread(cpu); - rcu_node_kthread_setaffinity(rnp, -1); + rcu_boost_kthread_setaffinity(rnp, -1); /* Remove the dead CPU from the bitmasks in the rcu_node hierarchy. */ /* Exclude any attempts to start a new grace period. */ + mutex_lock(&rsp->onoff_mutex); raw_spin_lock_irqsave(&rsp->onofflock, flags); /* Orphan the dead CPU's callbacks, and adopt them if appropriate. */ @@ -1515,14 +1743,14 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) WARN_ONCE(rdp->qlen != 0 || rdp->nxtlist != NULL, "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, nxtlist=%p\n", cpu, rdp->qlen, rdp->nxtlist); + init_callback_list(rdp); + /* Disallow further callbacks on this CPU. */ + rdp->nxttail[RCU_NEXT_TAIL] = NULL; + mutex_unlock(&rsp->onoff_mutex); } #else /* #ifdef CONFIG_HOTPLUG_CPU */ -static void rcu_adopt_orphan_cbs(struct rcu_state *rsp) -{ -} - static void rcu_cleanup_dying_cpu(struct rcu_state *rsp) { } @@ -1687,6 +1915,7 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *)) struct rcu_node *rnp; rcu_for_each_leaf_node(rsp, rnp) { + cond_resched(); mask = 0; raw_spin_lock_irqsave(&rnp->lock, flags); if (!rcu_gp_in_progress(rsp)) { @@ -1723,72 +1952,39 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *)) * Force quiescent states on reluctant CPUs, and also detect which * CPUs are in dyntick-idle mode. */ -static void force_quiescent_state(struct rcu_state *rsp, int relaxed) +static void force_quiescent_state(struct rcu_state *rsp) { unsigned long flags; - struct rcu_node *rnp = rcu_get_root(rsp); - - trace_rcu_utilization("Start fqs"); - if (!rcu_gp_in_progress(rsp)) { - trace_rcu_utilization("End fqs"); - return; /* No grace period in progress, nothing to force. */ - } - if (!raw_spin_trylock_irqsave(&rsp->fqslock, flags)) { - rsp->n_force_qs_lh++; /* Inexact, can lose counts. Tough! */ - trace_rcu_utilization("End fqs"); - return; /* Someone else is already on the job. */ - } - if (relaxed && ULONG_CMP_GE(rsp->jiffies_force_qs, jiffies)) - goto unlock_fqs_ret; /* no emergency and done recently. */ - rsp->n_force_qs++; - raw_spin_lock(&rnp->lock); /* irqs already disabled */ - rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS; - if(!rcu_gp_in_progress(rsp)) { - rsp->n_force_qs_ngp++; - raw_spin_unlock(&rnp->lock); /* irqs remain disabled */ - goto unlock_fqs_ret; /* no GP in progress, time updated. */ - } - rsp->fqs_active = 1; - switch (rsp->fqs_state) { - case RCU_GP_IDLE: - case RCU_GP_INIT: - - break; /* grace period idle or initializing, ignore. */ - - case RCU_SAVE_DYNTICK: - - raw_spin_unlock(&rnp->lock); /* irqs remain disabled */ - - /* Record dyntick-idle state. */ - force_qs_rnp(rsp, dyntick_save_progress_counter); - raw_spin_lock(&rnp->lock); /* irqs already disabled */ - if (rcu_gp_in_progress(rsp)) - rsp->fqs_state = RCU_FORCE_QS; - break; - - case RCU_FORCE_QS: - - /* Check dyntick-idle state, send IPI to laggarts. */ - raw_spin_unlock(&rnp->lock); /* irqs remain disabled */ - force_qs_rnp(rsp, rcu_implicit_dynticks_qs); - - /* Leave state in case more forcing is required. */ - - raw_spin_lock(&rnp->lock); /* irqs already disabled */ - break; + bool ret; + struct rcu_node *rnp; + struct rcu_node *rnp_old = NULL; + + /* Funnel through hierarchy to reduce memory contention. */ + rnp = per_cpu_ptr(rsp->rda, raw_smp_processor_id())->mynode; + for (; rnp != NULL; rnp = rnp->parent) { + ret = (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) || + !raw_spin_trylock(&rnp->fqslock); + if (rnp_old != NULL) + raw_spin_unlock(&rnp_old->fqslock); + if (ret) { + rsp->n_force_qs_lh++; + return; + } + rnp_old = rnp; } - rsp->fqs_active = 0; - if (rsp->fqs_need_gp) { - raw_spin_unlock(&rsp->fqslock); /* irqs remain disabled */ - rsp->fqs_need_gp = 0; - rcu_start_gp(rsp, flags); /* releases rnp->lock */ - trace_rcu_utilization("End fqs"); - return; + /* rnp_old == rcu_get_root(rsp), rnp == NULL. */ + + /* Reached the root of the rcu_node tree, acquire lock. */ + raw_spin_lock_irqsave(&rnp_old->lock, flags); + raw_spin_unlock(&rnp_old->fqslock); + if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) { + rsp->n_force_qs_lh++; + raw_spin_unlock_irqrestore(&rnp_old->lock, flags); + return; /* Someone beat us to it. */ } - raw_spin_unlock(&rnp->lock); /* irqs remain disabled */ -unlock_fqs_ret: - raw_spin_unlock_irqrestore(&rsp->fqslock, flags); - trace_rcu_utilization("End fqs"); + rsp->gp_flags |= RCU_GP_FLAG_FQS; + raw_spin_unlock_irqrestore(&rnp_old->lock, flags); + wake_up(&rsp->gp_wq); /* Memory barrier implied by wake_up() path. */ } /* @@ -1805,13 +2001,6 @@ __rcu_process_callbacks(struct rcu_state *rsp) WARN_ON_ONCE(rdp->beenonline == 0); /* - * If an RCU GP has gone long enough, go check for dyntick - * idle CPUs and, if needed, send resched IPIs. - */ - if (ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs), jiffies)) - force_quiescent_state(rsp, 1); - - /* * Advance callbacks in response to end of earlier grace * period that some other CPU ended. */ @@ -1838,6 +2027,8 @@ static void rcu_process_callbacks(struct softirq_action *unused) { struct rcu_state *rsp; + if (cpu_is_offline(smp_processor_id())) + return; trace_rcu_utilization("Start RCU core"); for_each_rcu_flavor(rsp) __rcu_process_callbacks(rsp); @@ -1909,12 +2100,11 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, rdp->blimit = LONG_MAX; if (rsp->n_force_qs == rdp->n_force_qs_snap && *rdp->nxttail[RCU_DONE_TAIL] != head) - force_quiescent_state(rsp, 0); + force_quiescent_state(rsp); rdp->n_force_qs_snap = rsp->n_force_qs; rdp->qlen_last_fqs_check = rdp->qlen; } - } else if (ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs), jiffies)) - force_quiescent_state(rsp, 1); + } } static void @@ -1929,8 +2119,6 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), head->func = func; head->next = NULL; - smp_mb(); /* Ensure RCU update seen before callback registry. */ - /* * Opportunistically note grace-period endings and beginnings. * Note that we might see a beginning right after we see an @@ -1941,6 +2129,12 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), rdp = this_cpu_ptr(rsp->rda); /* Add the callback to our list. */ + if (unlikely(rdp->nxttail[RCU_NEXT_TAIL] == NULL)) { + /* _call_rcu() is illegal on offline CPU; leak the callback. */ + WARN_ON_ONCE(1); + local_irq_restore(flags); + return; + } ACCESS_ONCE(rdp->qlen)++; if (lazy) rdp->qlen_lazy++; @@ -2195,17 +2389,7 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) /* Is the RCU core waiting for a quiescent state from this CPU? */ if (rcu_scheduler_fully_active && rdp->qs_pending && !rdp->passed_quiesce) { - - /* - * If force_quiescent_state() coming soon and this CPU - * needs a quiescent state, and this is either RCU-sched - * or RCU-bh, force a local reschedule. - */ rdp->n_rp_qs_pending++; - if (!rdp->preemptible && - ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs) - 1, - jiffies)) - set_need_resched(); } else if (rdp->qs_pending && rdp->passed_quiesce) { rdp->n_rp_report_qs++; return 1; @@ -2235,13 +2419,6 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp) return 1; } - /* Has an RCU GP gone long enough to send resched IPIs &c? */ - if (rcu_gp_in_progress(rsp) && - ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs), jiffies)) { - rdp->n_rp_need_fqs++; - return 1; - } - /* nothing to do */ rdp->n_rp_need_nothing++; return 0; @@ -2326,13 +2503,10 @@ static void rcu_barrier_func(void *type) static void _rcu_barrier(struct rcu_state *rsp) { int cpu; - unsigned long flags; struct rcu_data *rdp; - struct rcu_data rd; unsigned long snap = ACCESS_ONCE(rsp->n_barrier_done); unsigned long snap_done; - init_rcu_head_on_stack(&rd.barrier_head); _rcu_barrier_trace(rsp, "Begin", -1, snap); /* Take mutex to serialize concurrent rcu_barrier() requests. */ @@ -2372,70 +2546,30 @@ static void _rcu_barrier(struct rcu_state *rsp) /* * Initialize the count to one rather than to zero in order to * avoid a too-soon return to zero in case of a short grace period - * (or preemption of this task). Also flag this task as doing - * an rcu_barrier(). This will prevent anyone else from adopting - * orphaned callbacks, which could cause otherwise failure if a - * CPU went offline and quickly came back online. To see this, - * consider the following sequence of events: - * - * 1. We cause CPU 0 to post an rcu_barrier_callback() callback. - * 2. CPU 1 goes offline, orphaning its callbacks. - * 3. CPU 0 adopts CPU 1's orphaned callbacks. - * 4. CPU 1 comes back online. - * 5. We cause CPU 1 to post an rcu_barrier_callback() callback. - * 6. Both rcu_barrier_callback() callbacks are invoked, awakening - * us -- but before CPU 1's orphaned callbacks are invoked!!! + * (or preemption of this task). Exclude CPU-hotplug operations + * to ensure that no offline CPU has callbacks queued. */ init_completion(&rsp->barrier_completion); atomic_set(&rsp->barrier_cpu_count, 1); - raw_spin_lock_irqsave(&rsp->onofflock, flags); - rsp->rcu_barrier_in_progress = current; - raw_spin_unlock_irqrestore(&rsp->onofflock, flags); + get_online_cpus(); /* - * Force every CPU with callbacks to register a new callback - * that will tell us when all the preceding callbacks have - * been invoked. If an offline CPU has callbacks, wait for - * it to either come back online or to finish orphaning those - * callbacks. + * Force each CPU with callbacks to register a new callback. + * When that callback is invoked, we will know that all of the + * corresponding CPU's preceding callbacks have been invoked. */ - for_each_possible_cpu(cpu) { - preempt_disable(); + for_each_online_cpu(cpu) { rdp = per_cpu_ptr(rsp->rda, cpu); - if (cpu_is_offline(cpu)) { - _rcu_barrier_trace(rsp, "Offline", cpu, - rsp->n_barrier_done); - preempt_enable(); - while (cpu_is_offline(cpu) && ACCESS_ONCE(rdp->qlen)) - schedule_timeout_interruptible(1); - } else if (ACCESS_ONCE(rdp->qlen)) { + if (ACCESS_ONCE(rdp->qlen)) { _rcu_barrier_trace(rsp, "OnlineQ", cpu, rsp->n_barrier_done); smp_call_function_single(cpu, rcu_barrier_func, rsp, 1); - preempt_enable(); } else { _rcu_barrier_trace(rsp, "OnlineNQ", cpu, rsp->n_barrier_done); - preempt_enable(); } } - - /* - * Now that all online CPUs have rcu_barrier_callback() callbacks - * posted, we can adopt all of the orphaned callbacks and place - * an rcu_barrier_callback() callback after them. When that is done, - * we are guaranteed to have an rcu_barrier_callback() callback - * following every callback that could possibly have been - * registered before _rcu_barrier() was called. - */ - raw_spin_lock_irqsave(&rsp->onofflock, flags); - rcu_adopt_orphan_cbs(rsp); - rsp->rcu_barrier_in_progress = NULL; - raw_spin_unlock_irqrestore(&rsp->onofflock, flags); - atomic_inc(&rsp->barrier_cpu_count); - smp_mb__after_atomic_inc(); /* Ensure atomic_inc() before callback. */ - rd.rsp = rsp; - rsp->call(&rd.barrier_head, rcu_barrier_callback); + put_online_cpus(); /* * Now that we have an rcu_barrier_callback() callback on each @@ -2456,8 +2590,6 @@ static void _rcu_barrier(struct rcu_state *rsp) /* Other rcu_barrier() invocations can now safely proceed. */ mutex_unlock(&rsp->barrier_mutex); - - destroy_rcu_head_on_stack(&rd.barrier_head); } /** @@ -2497,6 +2629,9 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) rdp->dynticks = &per_cpu(rcu_dynticks, cpu); WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE); WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1); +#ifdef CONFIG_RCU_USER_QS + WARN_ON_ONCE(rdp->dynticks->in_user); +#endif rdp->cpu = cpu; rdp->rsp = rsp; raw_spin_unlock_irqrestore(&rnp->lock, flags); @@ -2516,6 +2651,9 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible) struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); struct rcu_node *rnp = rcu_get_root(rsp); + /* Exclude new grace periods. */ + mutex_lock(&rsp->onoff_mutex); + /* Set up local state, ensuring consistent view of global state. */ raw_spin_lock_irqsave(&rnp->lock, flags); rdp->beenonline = 1; /* We have now been online. */ @@ -2523,20 +2661,13 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible) rdp->qlen_last_fqs_check = 0; rdp->n_force_qs_snap = rsp->n_force_qs; rdp->blimit = blimit; + init_callback_list(rdp); /* Re-enable callbacks on this CPU. */ rdp->dynticks->dynticks_nesting = DYNTICK_TASK_EXIT_IDLE; atomic_set(&rdp->dynticks->dynticks, (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1); rcu_prepare_for_idle_init(cpu); raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ - /* - * A new grace period might start here. If so, we won't be part - * of it, but that is OK, as we are currently in a quiescent state. - */ - - /* Exclude any attempts to start a new GP on large systems. */ - raw_spin_lock(&rsp->onofflock); /* irqs already disabled. */ - /* Add CPU to rcu_node bitmasks. */ rnp = rdp->mynode; mask = rdp->grpmask; @@ -2555,14 +2686,14 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible) rdp->completed = rnp->completed; rdp->passed_quiesce = 0; rdp->qs_pending = 0; - rdp->passed_quiesce_gpnum = rnp->gpnum - 1; trace_rcu_grace_period(rsp->name, rdp->gpnum, "cpuonl"); } raw_spin_unlock(&rnp->lock); /* irqs already disabled. */ rnp = rnp->parent; } while (rnp != NULL && !(rnp->qsmaskinit & mask)); + local_irq_restore(flags); - raw_spin_unlock_irqrestore(&rsp->onofflock, flags); + mutex_unlock(&rsp->onoff_mutex); } static void __cpuinit rcu_prepare_cpu(int cpu) @@ -2594,12 +2725,10 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self, break; case CPU_ONLINE: case CPU_DOWN_FAILED: - rcu_node_kthread_setaffinity(rnp, -1); - rcu_cpu_kthread_setrt(cpu, 1); + rcu_boost_kthread_setaffinity(rnp, -1); break; case CPU_DOWN_PREPARE: - rcu_node_kthread_setaffinity(rnp, cpu); - rcu_cpu_kthread_setrt(cpu, 0); + rcu_boost_kthread_setaffinity(rnp, cpu); break; case CPU_DYING: case CPU_DYING_FROZEN: @@ -2627,6 +2756,28 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self, } /* + * Spawn the kthread that handles this RCU flavor's grace periods. + */ +static int __init rcu_spawn_gp_kthread(void) +{ + unsigned long flags; + struct rcu_node *rnp; + struct rcu_state *rsp; + struct task_struct *t; + + for_each_rcu_flavor(rsp) { + t = kthread_run(rcu_gp_kthread, rsp, rsp->name); + BUG_ON(IS_ERR(t)); + rnp = rcu_get_root(rsp); + raw_spin_lock_irqsave(&rnp->lock, flags); + rsp->gp_kthread = t; + raw_spin_unlock_irqrestore(&rnp->lock, flags); + } + return 0; +} +early_initcall(rcu_spawn_gp_kthread); + +/* * This function is invoked towards the end of the scheduler's initialization * process. Before this is called, the idle task might contain * RCU read-side critical sections (during which time, this idle @@ -2661,7 +2812,7 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp) int cprv; int i; - cprv = NR_CPUS; + cprv = nr_cpu_ids; for (i = rcu_num_lvls - 1; i >= 0; i--) { ccur = rsp->levelcnt[i]; rsp->levelspread[i] = (cprv + ccur - 1) / ccur; @@ -2676,10 +2827,14 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp) static void __init rcu_init_one(struct rcu_state *rsp, struct rcu_data __percpu *rda) { - static char *buf[] = { "rcu_node_level_0", - "rcu_node_level_1", - "rcu_node_level_2", - "rcu_node_level_3" }; /* Match MAX_RCU_LVLS */ + static char *buf[] = { "rcu_node_0", + "rcu_node_1", + "rcu_node_2", + "rcu_node_3" }; /* Match MAX_RCU_LVLS */ + static char *fqs[] = { "rcu_node_fqs_0", + "rcu_node_fqs_1", + "rcu_node_fqs_2", + "rcu_node_fqs_3" }; /* Match MAX_RCU_LVLS */ int cpustride = 1; int i; int j; @@ -2704,7 +2859,11 @@ static void __init rcu_init_one(struct rcu_state *rsp, raw_spin_lock_init(&rnp->lock); lockdep_set_class_and_name(&rnp->lock, &rcu_node_class[i], buf[i]); - rnp->gpnum = 0; + raw_spin_lock_init(&rnp->fqslock); + lockdep_set_class_and_name(&rnp->fqslock, + &rcu_fqs_class[i], fqs[i]); + rnp->gpnum = rsp->gpnum; + rnp->completed = rsp->completed; rnp->qsmask = 0; rnp->qsmaskinit = 0; rnp->grplo = j * cpustride; @@ -2727,6 +2886,7 @@ static void __init rcu_init_one(struct rcu_state *rsp, } rsp->rda = rda; + init_waitqueue_head(&rsp->gp_wq); rnp = rsp->level[rcu_num_lvls - 1]; for_each_possible_cpu(i) { while (i > rnp->grphi) @@ -2750,7 +2910,8 @@ static void __init rcu_init_geometry(void) int rcu_capacity[MAX_RCU_LVLS + 1]; /* If the compile-time values are accurate, just leave. */ - if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF) + if (rcu_fanout_leaf == CONFIG_RCU_FANOUT_LEAF && + nr_cpu_ids == NR_CPUS) return; /* diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 4d29169f2124..a240f032848e 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -102,6 +102,10 @@ struct rcu_dynticks { /* idle-period nonlazy_posted snapshot. */ int tick_nohz_enabled_snap; /* Previously seen value from sysfs. */ #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */ +#ifdef CONFIG_RCU_USER_QS + bool ignore_user_qs; /* Treat userspace as extended QS or not */ + bool in_user; /* Is the CPU in userland from RCU POV? */ +#endif }; /* RCU's kthread states for tracing. */ @@ -196,12 +200,7 @@ struct rcu_node { /* Refused to boost: not sure why, though. */ /* This can happen due to race conditions. */ #endif /* #ifdef CONFIG_RCU_BOOST */ - struct task_struct *node_kthread_task; - /* kthread that takes care of this rcu_node */ - /* structure, for example, awakening the */ - /* per-CPU kthreads as needed. */ - unsigned int node_kthread_status; - /* State of node_kthread_task for tracing. */ + raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp; } ____cacheline_internodealigned_in_smp; /* @@ -245,8 +244,6 @@ struct rcu_data { /* in order to detect GP end. */ unsigned long gpnum; /* Highest gp number that this CPU */ /* is aware of having started. */ - unsigned long passed_quiesce_gpnum; - /* gpnum at time of quiescent state. */ bool passed_quiesce; /* User-mode/idle loop etc. */ bool qs_pending; /* Core waits for quiesc state. */ bool beenonline; /* CPU online at least once. */ @@ -312,11 +309,13 @@ struct rcu_data { unsigned long n_rp_cpu_needs_gp; unsigned long n_rp_gp_completed; unsigned long n_rp_gp_started; - unsigned long n_rp_need_fqs; unsigned long n_rp_need_nothing; - /* 6) _rcu_barrier() callback. */ + /* 6) _rcu_barrier() and OOM callbacks. */ struct rcu_head barrier_head; +#ifdef CONFIG_RCU_FAST_NO_HZ + struct rcu_head oom_head; +#endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */ int cpu; struct rcu_state *rsp; @@ -375,20 +374,17 @@ struct rcu_state { u8 fqs_state ____cacheline_internodealigned_in_smp; /* Force QS state. */ - u8 fqs_active; /* force_quiescent_state() */ - /* is running. */ - u8 fqs_need_gp; /* A CPU was prevented from */ - /* starting a new grace */ - /* period because */ - /* force_quiescent_state() */ - /* was running. */ u8 boost; /* Subject to priority boost. */ unsigned long gpnum; /* Current gp number. */ unsigned long completed; /* # of last completed gp. */ + struct task_struct *gp_kthread; /* Task for grace periods. */ + wait_queue_head_t gp_wq; /* Where GP task waits. */ + int gp_flags; /* Commands for GP task. */ /* End of fields guarded by root rcu_node's lock. */ - raw_spinlock_t onofflock; /* exclude on/offline and */ + raw_spinlock_t onofflock ____cacheline_internodealigned_in_smp; + /* exclude on/offline and */ /* starting new GP. */ struct rcu_head *orphan_nxtlist; /* Orphaned callbacks that */ /* need a grace period. */ @@ -398,16 +394,17 @@ struct rcu_state { struct rcu_head **orphan_donetail; /* Tail of above. */ long qlen_lazy; /* Number of lazy callbacks. */ long qlen; /* Total number of callbacks. */ - struct task_struct *rcu_barrier_in_progress; - /* Task doing rcu_barrier(), */ - /* or NULL if no barrier. */ + /* End of fields guarded by onofflock. */ + + struct mutex onoff_mutex; /* Coordinate hotplug & GPs. */ + struct mutex barrier_mutex; /* Guards barrier fields. */ atomic_t barrier_cpu_count; /* # CPUs waiting on. */ struct completion barrier_completion; /* Wake at barrier end. */ unsigned long n_barrier_done; /* ++ at start and end of */ /* _rcu_barrier(). */ - raw_spinlock_t fqslock; /* Only one task forcing */ - /* quiescent states. */ + /* End of fields guarded by barrier_mutex. */ + unsigned long jiffies_force_qs; /* Time at which to invoke */ /* force_quiescent_state(). */ unsigned long n_force_qs; /* Number of calls to */ @@ -426,6 +423,10 @@ struct rcu_state { struct list_head flavors; /* List of RCU flavors. */ }; +/* Values for rcu_state structure's gp_flags field. */ +#define RCU_GP_FLAG_INIT 0x1 /* Need grace-period initialization. */ +#define RCU_GP_FLAG_FQS 0x2 /* Need grace-period quiescent-state forcing. */ + extern struct list_head rcu_struct_flavors; #define for_each_rcu_flavor(rsp) \ list_for_each_entry((rsp), &rcu_struct_flavors, flavors) @@ -468,7 +469,6 @@ static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp); #ifdef CONFIG_HOTPLUG_CPU static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags); -static void rcu_stop_cpu_kthread(int cpu); #endif /* #ifdef CONFIG_HOTPLUG_CPU */ static void rcu_print_detail_task_stall(struct rcu_state *rsp); static int rcu_print_task_stall(struct rcu_node *rnp); @@ -491,15 +491,9 @@ static void invoke_rcu_callbacks_kthread(void); static bool rcu_is_callbacks_kthread(void); #ifdef CONFIG_RCU_BOOST static void rcu_preempt_do_callbacks(void); -static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, - cpumask_var_t cm); static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp, - struct rcu_node *rnp, - int rnp_index); -static void invoke_rcu_node_kthread(struct rcu_node *rnp); -static void rcu_yield(void (*f)(unsigned long), unsigned long arg); + struct rcu_node *rnp); #endif /* #ifdef CONFIG_RCU_BOOST */ -static void rcu_cpu_kthread_setrt(int cpu, int to_rt); static void __cpuinit rcu_prepare_kthreads(int cpu); static void rcu_prepare_for_idle_init(int cpu); static void rcu_cleanup_after_idle(int cpu); diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 7f3244c0df01..f92115488187 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -25,6 +25,8 @@ */ #include <linux/delay.h> +#include <linux/oom.h> +#include <linux/smpboot.h> #define RCU_KTHREAD_PRIO 1 @@ -118,7 +120,7 @@ EXPORT_SYMBOL_GPL(rcu_batches_completed); */ void rcu_force_quiescent_state(void) { - force_quiescent_state(&rcu_preempt_state, 0); + force_quiescent_state(&rcu_preempt_state); } EXPORT_SYMBOL_GPL(rcu_force_quiescent_state); @@ -136,8 +138,6 @@ static void rcu_preempt_qs(int cpu) { struct rcu_data *rdp = &per_cpu(rcu_preempt_data, cpu); - rdp->passed_quiesce_gpnum = rdp->gpnum; - barrier(); if (rdp->passed_quiesce == 0) trace_rcu_grace_period("rcu_preempt", rdp->gpnum, "cpuqs"); rdp->passed_quiesce = 1; @@ -422,9 +422,11 @@ static void rcu_print_detail_task_stall_rnp(struct rcu_node *rnp) unsigned long flags; struct task_struct *t; - if (!rcu_preempt_blocked_readers_cgp(rnp)) - return; raw_spin_lock_irqsave(&rnp->lock, flags); + if (!rcu_preempt_blocked_readers_cgp(rnp)) { + raw_spin_unlock_irqrestore(&rnp->lock, flags); + return; + } t = list_entry(rnp->gp_tasks, struct task_struct, rcu_node_entry); list_for_each_entry_continue(t, &rnp->blkd_tasks, rcu_node_entry) @@ -584,17 +586,23 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp, raw_spin_unlock(&rnp_root->lock); /* irqs still disabled */ } + rnp->gp_tasks = NULL; + rnp->exp_tasks = NULL; #ifdef CONFIG_RCU_BOOST - /* In case root is being boosted and leaf is not. */ + rnp->boost_tasks = NULL; + /* + * In case root is being boosted and leaf was not. Make sure + * that we boost the tasks blocking the current grace period + * in this case. + */ raw_spin_lock(&rnp_root->lock); /* irqs already disabled */ if (rnp_root->boost_tasks != NULL && - rnp_root->boost_tasks != rnp_root->gp_tasks) + rnp_root->boost_tasks != rnp_root->gp_tasks && + rnp_root->boost_tasks != rnp_root->exp_tasks) rnp_root->boost_tasks = rnp_root->gp_tasks; raw_spin_unlock(&rnp_root->lock); /* irqs still disabled */ #endif /* #ifdef CONFIG_RCU_BOOST */ - rnp->gp_tasks = NULL; - rnp->exp_tasks = NULL; return retval; } @@ -676,7 +684,7 @@ void synchronize_rcu(void) EXPORT_SYMBOL_GPL(synchronize_rcu); static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq); -static long sync_rcu_preempt_exp_count; +static unsigned long sync_rcu_preempt_exp_count; static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex); /* @@ -791,7 +799,7 @@ void synchronize_rcu_expedited(void) unsigned long flags; struct rcu_node *rnp; struct rcu_state *rsp = &rcu_preempt_state; - long snap; + unsigned long snap; int trycount = 0; smp_mb(); /* Caller's modifications seen first by other CPUs. */ @@ -799,33 +807,47 @@ void synchronize_rcu_expedited(void) smp_mb(); /* Above access cannot bleed into critical section. */ /* + * Block CPU-hotplug operations. This means that any CPU-hotplug + * operation that finds an rcu_node structure with tasks in the + * process of being boosted will know that all tasks blocking + * this expedited grace period will already be in the process of + * being boosted. This simplifies the process of moving tasks + * from leaf to root rcu_node structures. + */ + get_online_cpus(); + + /* * Acquire lock, falling back to synchronize_rcu() if too many * lock-acquisition failures. Of course, if someone does the * expedited grace period for us, just leave. */ while (!mutex_trylock(&sync_rcu_preempt_exp_mutex)) { + if (ULONG_CMP_LT(snap, + ACCESS_ONCE(sync_rcu_preempt_exp_count))) { + put_online_cpus(); + goto mb_ret; /* Others did our work for us. */ + } if (trycount++ < 10) { udelay(trycount * num_online_cpus()); } else { + put_online_cpus(); synchronize_rcu(); return; } - if ((ACCESS_ONCE(sync_rcu_preempt_exp_count) - snap) > 0) - goto mb_ret; /* Others did our work for us. */ } - if ((ACCESS_ONCE(sync_rcu_preempt_exp_count) - snap) > 0) + if (ULONG_CMP_LT(snap, ACCESS_ONCE(sync_rcu_preempt_exp_count))) { + put_online_cpus(); goto unlock_mb_ret; /* Others did our work for us. */ + } /* force all RCU readers onto ->blkd_tasks lists. */ synchronize_sched_expedited(); - raw_spin_lock_irqsave(&rsp->onofflock, flags); - /* Initialize ->expmask for all non-leaf rcu_node structures. */ rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) { - raw_spin_lock(&rnp->lock); /* irqs already disabled. */ + raw_spin_lock_irqsave(&rnp->lock, flags); rnp->expmask = rnp->qsmaskinit; - raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ + raw_spin_unlock_irqrestore(&rnp->lock, flags); } /* Snapshot current state of ->blkd_tasks lists. */ @@ -834,7 +856,7 @@ void synchronize_rcu_expedited(void) if (NUM_RCU_NODES > 1) sync_rcu_preempt_exp_init(rsp, rcu_get_root(rsp)); - raw_spin_unlock_irqrestore(&rsp->onofflock, flags); + put_online_cpus(); /* Wait for snapshotted ->blkd_tasks lists to drain. */ rnp = rcu_get_root(rsp); @@ -1069,6 +1091,16 @@ static void rcu_initiate_boost_trace(struct rcu_node *rnp) #endif /* #else #ifdef CONFIG_RCU_TRACE */ +static void rcu_wake_cond(struct task_struct *t, int status) +{ + /* + * If the thread is yielding, only wake it when this + * is invoked from idle + */ + if (status != RCU_KTHREAD_YIELDING || is_idle_task(current)) + wake_up_process(t); +} + /* * Carry out RCU priority boosting on the task indicated by ->exp_tasks * or ->boost_tasks, advancing the pointer to the next task in the @@ -1141,17 +1173,6 @@ static int rcu_boost(struct rcu_node *rnp) } /* - * Timer handler to initiate waking up of boost kthreads that - * have yielded the CPU due to excessive numbers of tasks to - * boost. We wake up the per-rcu_node kthread, which in turn - * will wake up the booster kthread. - */ -static void rcu_boost_kthread_timer(unsigned long arg) -{ - invoke_rcu_node_kthread((struct rcu_node *)arg); -} - -/* * Priority-boosting kthread. One per leaf rcu_node and one for the * root rcu_node. */ @@ -1174,8 +1195,9 @@ static int rcu_boost_kthread(void *arg) else spincnt = 0; if (spincnt > 10) { + rnp->boost_kthread_status = RCU_KTHREAD_YIELDING; trace_rcu_utilization("End boost kthread@rcu_yield"); - rcu_yield(rcu_boost_kthread_timer, (unsigned long)rnp); + schedule_timeout_interruptible(2); trace_rcu_utilization("Start boost kthread@rcu_yield"); spincnt = 0; } @@ -1191,9 +1213,9 @@ static int rcu_boost_kthread(void *arg) * kthread to start boosting them. If there is an expedited grace * period in progress, it is always time to boost. * - * The caller must hold rnp->lock, which this function releases, - * but irqs remain disabled. The ->boost_kthread_task is immortal, - * so we don't need to worry about it going away. + * The caller must hold rnp->lock, which this function releases. + * The ->boost_kthread_task is immortal, so we don't need to worry + * about it going away. */ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) { @@ -1213,8 +1235,8 @@ static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags) rnp->boost_tasks = rnp->gp_tasks; raw_spin_unlock_irqrestore(&rnp->lock, flags); t = rnp->boost_kthread_task; - if (t != NULL) - wake_up_process(t); + if (t) + rcu_wake_cond(t, rnp->boost_kthread_status); } else { rcu_initiate_boost_trace(rnp); raw_spin_unlock_irqrestore(&rnp->lock, flags); @@ -1231,8 +1253,10 @@ static void invoke_rcu_callbacks_kthread(void) local_irq_save(flags); __this_cpu_write(rcu_cpu_has_work, 1); if (__this_cpu_read(rcu_cpu_kthread_task) != NULL && - current != __this_cpu_read(rcu_cpu_kthread_task)) - wake_up_process(__this_cpu_read(rcu_cpu_kthread_task)); + current != __this_cpu_read(rcu_cpu_kthread_task)) { + rcu_wake_cond(__this_cpu_read(rcu_cpu_kthread_task), + __this_cpu_read(rcu_cpu_kthread_status)); + } local_irq_restore(flags); } @@ -1245,21 +1269,6 @@ static bool rcu_is_callbacks_kthread(void) return __get_cpu_var(rcu_cpu_kthread_task) == current; } -/* - * Set the affinity of the boost kthread. The CPU-hotplug locks are - * held, so no one should be messing with the existence of the boost - * kthread. - */ -static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, - cpumask_var_t cm) -{ - struct task_struct *t; - - t = rnp->boost_kthread_task; - if (t != NULL) - set_cpus_allowed_ptr(rnp->boost_kthread_task, cm); -} - #define RCU_BOOST_DELAY_JIFFIES DIV_ROUND_UP(CONFIG_RCU_BOOST_DELAY * HZ, 1000) /* @@ -1276,15 +1285,19 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp) * Returns zero if all is well, a negated errno otherwise. */ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp, - struct rcu_node *rnp, - int rnp_index) + struct rcu_node *rnp) { + int rnp_index = rnp - &rsp->node[0]; unsigned long flags; struct sched_param sp; struct task_struct *t; if (&rcu_preempt_state != rsp) return 0; + + if (!rcu_scheduler_fully_active || rnp->qsmaskinit == 0) + return 0; + rsp->boost = 1; if (rnp->boost_kthread_task != NULL) return 0; @@ -1301,25 +1314,6 @@ static int __cpuinit rcu_spawn_one_boost_kthread(struct rcu_state *rsp, return 0; } -#ifdef CONFIG_HOTPLUG_CPU - -/* - * Stop the RCU's per-CPU kthread when its CPU goes offline,. - */ -static void rcu_stop_cpu_kthread(int cpu) -{ - struct task_struct *t; - - /* Stop the CPU's kthread. */ - t = per_cpu(rcu_cpu_kthread_task, cpu); - if (t != NULL) { - per_cpu(rcu_cpu_kthread_task, cpu) = NULL; - kthread_stop(t); - } -} - -#endif /* #ifdef CONFIG_HOTPLUG_CPU */ - static void rcu_kthread_do_work(void) { rcu_do_batch(&rcu_sched_state, &__get_cpu_var(rcu_sched_data)); @@ -1327,112 +1321,22 @@ static void rcu_kthread_do_work(void) rcu_preempt_do_callbacks(); } -/* - * Wake up the specified per-rcu_node-structure kthread. - * Because the per-rcu_node kthreads are immortal, we don't need - * to do anything to keep them alive. - */ -static void invoke_rcu_node_kthread(struct rcu_node *rnp) -{ - struct task_struct *t; - - t = rnp->node_kthread_task; - if (t != NULL) - wake_up_process(t); -} - -/* - * Set the specified CPU's kthread to run RT or not, as specified by - * the to_rt argument. The CPU-hotplug locks are held, so the task - * is not going away. - */ -static void rcu_cpu_kthread_setrt(int cpu, int to_rt) +static void rcu_cpu_kthread_setup(unsigned int cpu) { - int policy; struct sched_param sp; - struct task_struct *t; - t = per_cpu(rcu_cpu_kthread_task, cpu); - if (t == NULL) - return; - if (to_rt) { - policy = SCHED_FIFO; - sp.sched_priority = RCU_KTHREAD_PRIO; - } else { - policy = SCHED_NORMAL; - sp.sched_priority = 0; - } - sched_setscheduler_nocheck(t, policy, &sp); + sp.sched_priority = RCU_KTHREAD_PRIO; + sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); } -/* - * Timer handler to initiate the waking up of per-CPU kthreads that - * have yielded the CPU due to excess numbers of RCU callbacks. - * We wake up the per-rcu_node kthread, which in turn will wake up - * the booster kthread. - */ -static void rcu_cpu_kthread_timer(unsigned long arg) +static void rcu_cpu_kthread_park(unsigned int cpu) { - struct rcu_data *rdp = per_cpu_ptr(rcu_state->rda, arg); - struct rcu_node *rnp = rdp->mynode; - - atomic_or(rdp->grpmask, &rnp->wakemask); - invoke_rcu_node_kthread(rnp); + per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; } -/* - * Drop to non-real-time priority and yield, but only after posting a - * timer that will cause us to regain our real-time priority if we - * remain preempted. Either way, we restore our real-time priority - * before returning. - */ -static void rcu_yield(void (*f)(unsigned long), unsigned long arg) +static int rcu_cpu_kthread_should_run(unsigned int cpu) { - struct sched_param sp; - struct timer_list yield_timer; - int prio = current->rt_priority; - - setup_timer_on_stack(&yield_timer, f, arg); - mod_timer(&yield_timer, jiffies + 2); - sp.sched_priority = 0; - sched_setscheduler_nocheck(current, SCHED_NORMAL, &sp); - set_user_nice(current, 19); - schedule(); - set_user_nice(current, 0); - sp.sched_priority = prio; - sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); - del_timer(&yield_timer); -} - -/* - * Handle cases where the rcu_cpu_kthread() ends up on the wrong CPU. - * This can happen while the corresponding CPU is either coming online - * or going offline. We cannot wait until the CPU is fully online - * before starting the kthread, because the various notifier functions - * can wait for RCU grace periods. So we park rcu_cpu_kthread() until - * the corresponding CPU is online. - * - * Return 1 if the kthread needs to stop, 0 otherwise. - * - * Caller must disable bh. This function can momentarily enable it. - */ -static int rcu_cpu_kthread_should_stop(int cpu) -{ - while (cpu_is_offline(cpu) || - !cpumask_equal(¤t->cpus_allowed, cpumask_of(cpu)) || - smp_processor_id() != cpu) { - if (kthread_should_stop()) - return 1; - per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; - per_cpu(rcu_cpu_kthread_cpu, cpu) = raw_smp_processor_id(); - local_bh_enable(); - schedule_timeout_uninterruptible(1); - if (!cpumask_equal(¤t->cpus_allowed, cpumask_of(cpu))) - set_cpus_allowed_ptr(current, cpumask_of(cpu)); - local_bh_disable(); - } - per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu; - return 0; + return __get_cpu_var(rcu_cpu_has_work); } /* @@ -1440,138 +1344,35 @@ static int rcu_cpu_kthread_should_stop(int cpu) * RCU softirq used in flavors and configurations of RCU that do not * support RCU priority boosting. */ -static int rcu_cpu_kthread(void *arg) +static void rcu_cpu_kthread(unsigned int cpu) { - int cpu = (int)(long)arg; - unsigned long flags; - int spincnt = 0; - unsigned int *statusp = &per_cpu(rcu_cpu_kthread_status, cpu); - char work; - char *workp = &per_cpu(rcu_cpu_has_work, cpu); + unsigned int *statusp = &__get_cpu_var(rcu_cpu_kthread_status); + char work, *workp = &__get_cpu_var(rcu_cpu_has_work); + int spincnt; - trace_rcu_utilization("Start CPU kthread@init"); - for (;;) { - *statusp = RCU_KTHREAD_WAITING; - trace_rcu_utilization("End CPU kthread@rcu_wait"); - rcu_wait(*workp != 0 || kthread_should_stop()); + for (spincnt = 0; spincnt < 10; spincnt++) { trace_rcu_utilization("Start CPU kthread@rcu_wait"); local_bh_disable(); - if (rcu_cpu_kthread_should_stop(cpu)) { - local_bh_enable(); - break; - } *statusp = RCU_KTHREAD_RUNNING; - per_cpu(rcu_cpu_kthread_loops, cpu)++; - local_irq_save(flags); + this_cpu_inc(rcu_cpu_kthread_loops); + local_irq_disable(); work = *workp; *workp = 0; - local_irq_restore(flags); + local_irq_enable(); if (work) rcu_kthread_do_work(); local_bh_enable(); - if (*workp != 0) - spincnt++; - else - spincnt = 0; - if (spincnt > 10) { - *statusp = RCU_KTHREAD_YIELDING; - trace_rcu_utilization("End CPU kthread@rcu_yield"); - rcu_yield(rcu_cpu_kthread_timer, (unsigned long)cpu); - trace_rcu_utilization("Start CPU kthread@rcu_yield"); - spincnt = 0; - } - } - *statusp = RCU_KTHREAD_STOPPED; - trace_rcu_utilization("End CPU kthread@term"); - return 0; -} - -/* - * Spawn a per-CPU kthread, setting up affinity and priority. - * Because the CPU hotplug lock is held, no other CPU will be attempting - * to manipulate rcu_cpu_kthread_task. There might be another CPU - * attempting to access it during boot, but the locking in kthread_bind() - * will enforce sufficient ordering. - * - * Please note that we cannot simply refuse to wake up the per-CPU - * kthread because kthreads are created in TASK_UNINTERRUPTIBLE state, - * which can result in softlockup complaints if the task ends up being - * idle for more than a couple of minutes. - * - * However, please note also that we cannot bind the per-CPU kthread to its - * CPU until that CPU is fully online. We also cannot wait until the - * CPU is fully online before we create its per-CPU kthread, as this would - * deadlock the system when CPU notifiers tried waiting for grace - * periods. So we bind the per-CPU kthread to its CPU only if the CPU - * is online. If its CPU is not yet fully online, then the code in - * rcu_cpu_kthread() will wait until it is fully online, and then do - * the binding. - */ -static int __cpuinit rcu_spawn_one_cpu_kthread(int cpu) -{ - struct sched_param sp; - struct task_struct *t; - - if (!rcu_scheduler_fully_active || - per_cpu(rcu_cpu_kthread_task, cpu) != NULL) - return 0; - t = kthread_create_on_node(rcu_cpu_kthread, - (void *)(long)cpu, - cpu_to_node(cpu), - "rcuc/%d", cpu); - if (IS_ERR(t)) - return PTR_ERR(t); - if (cpu_online(cpu)) - kthread_bind(t, cpu); - per_cpu(rcu_cpu_kthread_cpu, cpu) = cpu; - WARN_ON_ONCE(per_cpu(rcu_cpu_kthread_task, cpu) != NULL); - sp.sched_priority = RCU_KTHREAD_PRIO; - sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); - per_cpu(rcu_cpu_kthread_task, cpu) = t; - wake_up_process(t); /* Get to TASK_INTERRUPTIBLE quickly. */ - return 0; -} - -/* - * Per-rcu_node kthread, which is in charge of waking up the per-CPU - * kthreads when needed. We ignore requests to wake up kthreads - * for offline CPUs, which is OK because force_quiescent_state() - * takes care of this case. - */ -static int rcu_node_kthread(void *arg) -{ - int cpu; - unsigned long flags; - unsigned long mask; - struct rcu_node *rnp = (struct rcu_node *)arg; - struct sched_param sp; - struct task_struct *t; - - for (;;) { - rnp->node_kthread_status = RCU_KTHREAD_WAITING; - rcu_wait(atomic_read(&rnp->wakemask) != 0); - rnp->node_kthread_status = RCU_KTHREAD_RUNNING; - raw_spin_lock_irqsave(&rnp->lock, flags); - mask = atomic_xchg(&rnp->wakemask, 0); - rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */ - for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) { - if ((mask & 0x1) == 0) - continue; - preempt_disable(); - t = per_cpu(rcu_cpu_kthread_task, cpu); - if (!cpu_online(cpu) || t == NULL) { - preempt_enable(); - continue; - } - per_cpu(rcu_cpu_has_work, cpu) = 1; - sp.sched_priority = RCU_KTHREAD_PRIO; - sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); - preempt_enable(); + if (*workp == 0) { + trace_rcu_utilization("End CPU kthread@rcu_wait"); + *statusp = RCU_KTHREAD_WAITING; + return; } } - /* NOTREACHED */ - rnp->node_kthread_status = RCU_KTHREAD_STOPPED; - return 0; + *statusp = RCU_KTHREAD_YIELDING; + trace_rcu_utilization("Start CPU kthread@rcu_yield"); + schedule_timeout_interruptible(2); + trace_rcu_utilization("End CPU kthread@rcu_yield"); + *statusp = RCU_KTHREAD_WAITING; } /* @@ -1583,17 +1384,17 @@ static int rcu_node_kthread(void *arg) * no outgoing CPU. If there are no CPUs left in the affinity set, * this function allows the kthread to execute on any CPU. */ -static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) +static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) { + struct task_struct *t = rnp->boost_kthread_task; + unsigned long mask = rnp->qsmaskinit; cpumask_var_t cm; int cpu; - unsigned long mask = rnp->qsmaskinit; - if (rnp->node_kthread_task == NULL) + if (!t) return; - if (!alloc_cpumask_var(&cm, GFP_KERNEL)) + if (!zalloc_cpumask_var(&cm, GFP_KERNEL)) return; - cpumask_clear(cm); for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++, mask >>= 1) if ((mask & 0x1) && cpu != outgoingcpu) cpumask_set_cpu(cpu, cm); @@ -1603,62 +1404,36 @@ static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) cpumask_clear_cpu(cpu, cm); WARN_ON_ONCE(cpumask_weight(cm) == 0); } - set_cpus_allowed_ptr(rnp->node_kthread_task, cm); - rcu_boost_kthread_setaffinity(rnp, cm); + set_cpus_allowed_ptr(t, cm); free_cpumask_var(cm); } -/* - * Spawn a per-rcu_node kthread, setting priority and affinity. - * Called during boot before online/offline can happen, or, if - * during runtime, with the main CPU-hotplug locks held. So only - * one of these can be executing at a time. - */ -static int __cpuinit rcu_spawn_one_node_kthread(struct rcu_state *rsp, - struct rcu_node *rnp) -{ - unsigned long flags; - int rnp_index = rnp - &rsp->node[0]; - struct sched_param sp; - struct task_struct *t; - - if (!rcu_scheduler_fully_active || - rnp->qsmaskinit == 0) - return 0; - if (rnp->node_kthread_task == NULL) { - t = kthread_create(rcu_node_kthread, (void *)rnp, - "rcun/%d", rnp_index); - if (IS_ERR(t)) - return PTR_ERR(t); - raw_spin_lock_irqsave(&rnp->lock, flags); - rnp->node_kthread_task = t; - raw_spin_unlock_irqrestore(&rnp->lock, flags); - sp.sched_priority = 99; - sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); - wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */ - } - return rcu_spawn_one_boost_kthread(rsp, rnp, rnp_index); -} +static struct smp_hotplug_thread rcu_cpu_thread_spec = { + .store = &rcu_cpu_kthread_task, + .thread_should_run = rcu_cpu_kthread_should_run, + .thread_fn = rcu_cpu_kthread, + .thread_comm = "rcuc/%u", + .setup = rcu_cpu_kthread_setup, + .park = rcu_cpu_kthread_park, +}; /* * Spawn all kthreads -- called as soon as the scheduler is running. */ static int __init rcu_spawn_kthreads(void) { - int cpu; struct rcu_node *rnp; + int cpu; rcu_scheduler_fully_active = 1; - for_each_possible_cpu(cpu) { + for_each_possible_cpu(cpu) per_cpu(rcu_cpu_has_work, cpu) = 0; - if (cpu_online(cpu)) - (void)rcu_spawn_one_cpu_kthread(cpu); - } + BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); rnp = rcu_get_root(rcu_state); - (void)rcu_spawn_one_node_kthread(rcu_state, rnp); + (void)rcu_spawn_one_boost_kthread(rcu_state, rnp); if (NUM_RCU_NODES > 1) { rcu_for_each_leaf_node(rcu_state, rnp) - (void)rcu_spawn_one_node_kthread(rcu_state, rnp); + (void)rcu_spawn_one_boost_kthread(rcu_state, rnp); } return 0; } @@ -1670,11 +1445,8 @@ static void __cpuinit rcu_prepare_kthreads(int cpu) struct rcu_node *rnp = rdp->mynode; /* Fire up the incoming CPU's kthread and leaf rcu_node kthread. */ - if (rcu_scheduler_fully_active) { - (void)rcu_spawn_one_cpu_kthread(cpu); - if (rnp->node_kthread_task == NULL) - (void)rcu_spawn_one_node_kthread(rcu_state, rnp); - } + if (rcu_scheduler_fully_active) + (void)rcu_spawn_one_boost_kthread(rcu_state, rnp); } #else /* #ifdef CONFIG_RCU_BOOST */ @@ -1698,19 +1470,7 @@ static void rcu_preempt_boost_start_gp(struct rcu_node *rnp) { } -#ifdef CONFIG_HOTPLUG_CPU - -static void rcu_stop_cpu_kthread(int cpu) -{ -} - -#endif /* #ifdef CONFIG_HOTPLUG_CPU */ - -static void rcu_node_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) -{ -} - -static void rcu_cpu_kthread_setrt(int cpu, int to_rt) +static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) { } @@ -1997,6 +1757,26 @@ static void rcu_prepare_for_idle(int cpu) if (!tne) return; + /* Adaptive-tick mode, where usermode execution is idle to RCU. */ + if (!is_idle_task(current)) { + rdtp->dyntick_holdoff = jiffies - 1; + if (rcu_cpu_has_nonlazy_callbacks(cpu)) { + trace_rcu_prep_idle("User dyntick with callbacks"); + rdtp->idle_gp_timer_expires = + round_up(jiffies + RCU_IDLE_GP_DELAY, + RCU_IDLE_GP_DELAY); + } else if (rcu_cpu_has_callbacks(cpu)) { + rdtp->idle_gp_timer_expires = + round_jiffies(jiffies + RCU_IDLE_LAZY_GP_DELAY); + trace_rcu_prep_idle("User dyntick with lazy callbacks"); + } else { + return; + } + tp = &rdtp->idle_gp_timer; + mod_timer_pinned(tp, rdtp->idle_gp_timer_expires); + return; + } + /* * If this is an idle re-entry, for example, due to use of * RCU_NONIDLE() or the new idle-loop tracing API within the idle @@ -2075,16 +1855,16 @@ static void rcu_prepare_for_idle(int cpu) #ifdef CONFIG_TREE_PREEMPT_RCU if (per_cpu(rcu_preempt_data, cpu).nxtlist) { rcu_preempt_qs(cpu); - force_quiescent_state(&rcu_preempt_state, 0); + force_quiescent_state(&rcu_preempt_state); } #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ if (per_cpu(rcu_sched_data, cpu).nxtlist) { rcu_sched_qs(cpu); - force_quiescent_state(&rcu_sched_state, 0); + force_quiescent_state(&rcu_sched_state); } if (per_cpu(rcu_bh_data, cpu).nxtlist) { rcu_bh_qs(cpu); - force_quiescent_state(&rcu_bh_state, 0); + force_quiescent_state(&rcu_bh_state); } /* @@ -2112,6 +1892,88 @@ static void rcu_idle_count_callbacks_posted(void) __this_cpu_add(rcu_dynticks.nonlazy_posted, 1); } +/* + * Data for flushing lazy RCU callbacks at OOM time. + */ +static atomic_t oom_callback_count; +static DECLARE_WAIT_QUEUE_HEAD(oom_callback_wq); + +/* + * RCU OOM callback -- decrement the outstanding count and deliver the + * wake-up if we are the last one. + */ +static void rcu_oom_callback(struct rcu_head *rhp) +{ + if (atomic_dec_and_test(&oom_callback_count)) + wake_up(&oom_callback_wq); +} + +/* + * Post an rcu_oom_notify callback on the current CPU if it has at + * least one lazy callback. This will unnecessarily post callbacks + * to CPUs that already have a non-lazy callback at the end of their + * callback list, but this is an infrequent operation, so accept some + * extra overhead to keep things simple. + */ +static void rcu_oom_notify_cpu(void *unused) +{ + struct rcu_state *rsp; + struct rcu_data *rdp; + + for_each_rcu_flavor(rsp) { + rdp = __this_cpu_ptr(rsp->rda); + if (rdp->qlen_lazy != 0) { + atomic_inc(&oom_callback_count); + rsp->call(&rdp->oom_head, rcu_oom_callback); + } + } +} + +/* + * If low on memory, ensure that each CPU has a non-lazy callback. + * This will wake up CPUs that have only lazy callbacks, in turn + * ensuring that they free up the corresponding memory in a timely manner. + * Because an uncertain amount of memory will be freed in some uncertain + * timeframe, we do not claim to have freed anything. + */ +static int rcu_oom_notify(struct notifier_block *self, + unsigned long notused, void *nfreed) +{ + int cpu; + + /* Wait for callbacks from earlier instance to complete. */ + wait_event(oom_callback_wq, atomic_read(&oom_callback_count) == 0); + + /* + * Prevent premature wakeup: ensure that all increments happen + * before there is a chance of the counter reaching zero. + */ + atomic_set(&oom_callback_count, 1); + + get_online_cpus(); + for_each_online_cpu(cpu) { + smp_call_function_single(cpu, rcu_oom_notify_cpu, NULL, 1); + cond_resched(); + } + put_online_cpus(); + + /* Unconditionally decrement: no need to wake ourselves up. */ + atomic_dec(&oom_callback_count); + + return NOTIFY_OK; +} + +static struct notifier_block rcu_oom_nb = { + .notifier_call = rcu_oom_notify +}; + +static int __init rcu_register_oom_notifier(void) +{ + register_oom_notifier(&rcu_oom_nb); + return 0; +} +early_initcall(rcu_register_oom_notifier); + #endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */ #ifdef CONFIG_RCU_CPU_STALL_INFO @@ -2122,11 +1984,15 @@ static void print_cpu_stall_fast_no_hz(char *cp, int cpu) { struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); struct timer_list *tltp = &rdtp->idle_gp_timer; + char c; - sprintf(cp, "drain=%d %c timer=%lu", - rdtp->dyntick_drain, - rdtp->dyntick_holdoff == jiffies ? 'H' : '.', - timer_pending(tltp) ? tltp->expires - jiffies : -1); + c = rdtp->dyntick_holdoff == jiffies ? 'H' : '.'; + if (timer_pending(tltp)) + sprintf(cp, "drain=%d %c timer=%lu", + rdtp->dyntick_drain, c, tltp->expires - jiffies); + else + sprintf(cp, "drain=%d %c timer not pending", + rdtp->dyntick_drain, c); } #else /* #ifdef CONFIG_RCU_FAST_NO_HZ */ @@ -2194,11 +2060,10 @@ static void zero_cpu_stall_ticks(struct rcu_data *rdp) /* Increment ->ticks_this_gp for all flavors of RCU. */ static void increment_cpu_stall_ticks(void) { - __get_cpu_var(rcu_sched_data).ticks_this_gp++; - __get_cpu_var(rcu_bh_data).ticks_this_gp++; -#ifdef CONFIG_TREE_PREEMPT_RCU - __get_cpu_var(rcu_preempt_data).ticks_this_gp++; -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ + struct rcu_state *rsp; + + for_each_rcu_flavor(rsp) + __this_cpu_ptr(rsp->rda)->ticks_this_gp++; } #else /* #ifdef CONFIG_RCU_CPU_STALL_INFO */ diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c index abffb486e94e..693513bc50e6 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -51,8 +51,8 @@ static int show_rcubarrier(struct seq_file *m, void *unused) struct rcu_state *rsp; for_each_rcu_flavor(rsp) - seq_printf(m, "%s: %c bcc: %d nbd: %lu\n", - rsp->name, rsp->rcu_barrier_in_progress ? 'B' : '.', + seq_printf(m, "%s: bcc: %d nbd: %lu\n", + rsp->name, atomic_read(&rsp->barrier_cpu_count), rsp->n_barrier_done); return 0; @@ -86,12 +86,11 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) { if (!rdp->beenonline) return; - seq_printf(m, "%3d%cc=%lu g=%lu pq=%d pgp=%lu qp=%d", + seq_printf(m, "%3d%cc=%lu g=%lu pq=%d qp=%d", rdp->cpu, cpu_is_offline(rdp->cpu) ? '!' : ' ', rdp->completed, rdp->gpnum, - rdp->passed_quiesce, rdp->passed_quiesce_gpnum, - rdp->qs_pending); + rdp->passed_quiesce, rdp->qs_pending); seq_printf(m, " dt=%d/%llx/%d df=%lu", atomic_read(&rdp->dynticks->dynticks), rdp->dynticks->dynticks_nesting, @@ -108,11 +107,10 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) rdp->nxttail[RCU_WAIT_TAIL]], ".D"[&rdp->nxtlist != rdp->nxttail[RCU_DONE_TAIL]]); #ifdef CONFIG_RCU_BOOST - seq_printf(m, " kt=%d/%c/%d ktl=%x", + seq_printf(m, " kt=%d/%c ktl=%x", per_cpu(rcu_cpu_has_work, rdp->cpu), convert_kthread_status(per_cpu(rcu_cpu_kthread_status, rdp->cpu)), - per_cpu(rcu_cpu_kthread_cpu, rdp->cpu), per_cpu(rcu_cpu_kthread_loops, rdp->cpu) & 0xffff); #endif /* #ifdef CONFIG_RCU_BOOST */ seq_printf(m, " b=%ld", rdp->blimit); @@ -150,12 +148,11 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp) { if (!rdp->beenonline) return; - seq_printf(m, "%d,%s,%lu,%lu,%d,%lu,%d", + seq_printf(m, "%d,%s,%lu,%lu,%d,%d", rdp->cpu, cpu_is_offline(rdp->cpu) ? "\"N\"" : "\"Y\"", rdp->completed, rdp->gpnum, - rdp->passed_quiesce, rdp->passed_quiesce_gpnum, - rdp->qs_pending); + rdp->passed_quiesce, rdp->qs_pending); seq_printf(m, ",%d,%llx,%d,%lu", atomic_read(&rdp->dynticks->dynticks), rdp->dynticks->dynticks_nesting, @@ -186,7 +183,7 @@ static int show_rcudata_csv(struct seq_file *m, void *unused) int cpu; struct rcu_state *rsp; - seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pgp\",\"pq\","); + seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pq\","); seq_puts(m, "\"dt\",\"dt nesting\",\"dt NMI nesting\",\"df\","); seq_puts(m, "\"of\",\"qll\",\"ql\",\"qs\""); #ifdef CONFIG_RCU_BOOST @@ -386,10 +383,9 @@ static void print_one_rcu_pending(struct seq_file *m, struct rcu_data *rdp) rdp->n_rp_report_qs, rdp->n_rp_cb_ready, rdp->n_rp_cpu_needs_gp); - seq_printf(m, "gpc=%ld gps=%ld nf=%ld nn=%ld\n", + seq_printf(m, "gpc=%ld gps=%ld nn=%ld\n", rdp->n_rp_gp_completed, rdp->n_rp_gp_started, - rdp->n_rp_need_fqs, rdp->n_rp_need_nothing); } diff --git a/kernel/resource.c b/kernel/resource.c index 34d45886ee84..73f35d4b30b9 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -763,6 +763,7 @@ static void __init __reserve_region_with_split(struct resource *root, struct resource *parent = root; struct resource *conflict; struct resource *res = kzalloc(sizeof(*res), GFP_ATOMIC); + struct resource *next_res = NULL; if (!res) return; @@ -772,21 +773,46 @@ static void __init __reserve_region_with_split(struct resource *root, res->end = end; res->flags = IORESOURCE_BUSY; - conflict = __request_resource(parent, res); - if (!conflict) - return; + while (1) { - /* failed, split and try again */ - kfree(res); + conflict = __request_resource(parent, res); + if (!conflict) { + if (!next_res) + break; + res = next_res; + next_res = NULL; + continue; + } - /* conflict covered whole area */ - if (conflict->start <= start && conflict->end >= end) - return; + /* conflict covered whole area */ + if (conflict->start <= res->start && + conflict->end >= res->end) { + kfree(res); + WARN_ON(next_res); + break; + } + + /* failed, split and try again */ + if (conflict->start > res->start) { + end = res->end; + res->end = conflict->start - 1; + if (conflict->end < end) { + next_res = kzalloc(sizeof(*next_res), + GFP_ATOMIC); + if (!next_res) { + kfree(res); + break; + } + next_res->name = name; + next_res->start = conflict->end + 1; + next_res->end = end; + next_res->flags = IORESOURCE_BUSY; + } + } else { + res->start = conflict->end + 1; + } + } - if (conflict->start > start) - __reserve_region_with_split(root, start, conflict->start-1, name); - if (conflict->end < end) - __reserve_region_with_split(root, conflict->end+1, end, name); } void __init reserve_region_with_split(struct resource *root, diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 173ea52f3af0..f06d249e103b 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -11,7 +11,7 @@ ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y) CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer endif -obj-y += core.o clock.o idle_task.o fair.o rt.o stop_task.o +obj-y += core.o clock.o cputime.o idle_task.o fair.o rt.o stop_task.o obj-$(CONFIG_SMP) += cpupri.o obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o obj-$(CONFIG_SCHEDSTATS) += stats.o diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 649c9f876cb1..2d8927fda712 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -505,7 +505,7 @@ static inline void init_hrtick(void) #ifdef CONFIG_SMP #ifndef tsk_is_polling -#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG) +#define tsk_is_polling(t) 0 #endif void resched_task(struct task_struct *p) @@ -740,126 +740,6 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags) dequeue_task(rq, p, flags); } -#ifdef CONFIG_IRQ_TIME_ACCOUNTING - -/* - * There are no locks covering percpu hardirq/softirq time. - * They are only modified in account_system_vtime, on corresponding CPU - * with interrupts disabled. So, writes are safe. - * They are read and saved off onto struct rq in update_rq_clock(). - * This may result in other CPU reading this CPU's irq time and can - * race with irq/account_system_vtime on this CPU. We would either get old - * or new value with a side effect of accounting a slice of irq time to wrong - * task when irq is in progress while we read rq->clock. That is a worthy - * compromise in place of having locks on each irq in account_system_time. - */ -static DEFINE_PER_CPU(u64, cpu_hardirq_time); -static DEFINE_PER_CPU(u64, cpu_softirq_time); - -static DEFINE_PER_CPU(u64, irq_start_time); -static int sched_clock_irqtime; - -void enable_sched_clock_irqtime(void) -{ - sched_clock_irqtime = 1; -} - -void disable_sched_clock_irqtime(void) -{ - sched_clock_irqtime = 0; -} - -#ifndef CONFIG_64BIT -static DEFINE_PER_CPU(seqcount_t, irq_time_seq); - -static inline void irq_time_write_begin(void) -{ - __this_cpu_inc(irq_time_seq.sequence); - smp_wmb(); -} - -static inline void irq_time_write_end(void) -{ - smp_wmb(); - __this_cpu_inc(irq_time_seq.sequence); -} - -static inline u64 irq_time_read(int cpu) -{ - u64 irq_time; - unsigned seq; - - do { - seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu)); - irq_time = per_cpu(cpu_softirq_time, cpu) + - per_cpu(cpu_hardirq_time, cpu); - } while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq)); - - return irq_time; -} -#else /* CONFIG_64BIT */ -static inline void irq_time_write_begin(void) -{ -} - -static inline void irq_time_write_end(void) -{ -} - -static inline u64 irq_time_read(int cpu) -{ - return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu); -} -#endif /* CONFIG_64BIT */ - -/* - * Called before incrementing preempt_count on {soft,}irq_enter - * and before decrementing preempt_count on {soft,}irq_exit. - */ -void account_system_vtime(struct task_struct *curr) -{ - unsigned long flags; - s64 delta; - int cpu; - - if (!sched_clock_irqtime) - return; - - local_irq_save(flags); - - cpu = smp_processor_id(); - delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time); - __this_cpu_add(irq_start_time, delta); - - irq_time_write_begin(); - /* - * We do not account for softirq time from ksoftirqd here. - * We want to continue accounting softirq time to ksoftirqd thread - * in that case, so as not to confuse scheduler with a special task - * that do not consume any time, but still wants to run. - */ - if (hardirq_count()) - __this_cpu_add(cpu_hardirq_time, delta); - else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) - __this_cpu_add(cpu_softirq_time, delta); - - irq_time_write_end(); - local_irq_restore(flags); -} -EXPORT_SYMBOL_GPL(account_system_vtime); - -#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ - -#ifdef CONFIG_PARAVIRT -static inline u64 steal_ticks(u64 steal) -{ - if (unlikely(steal > NSEC_PER_SEC)) - return div_u64(steal, TICK_NSEC); - - return __iter_div_u64_rem(steal, TICK_NSEC, &steal); -} -#endif - static void update_rq_clock_task(struct rq *rq, s64 delta) { /* @@ -920,43 +800,6 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) #endif } -#ifdef CONFIG_IRQ_TIME_ACCOUNTING -static int irqtime_account_hi_update(void) -{ - u64 *cpustat = kcpustat_this_cpu->cpustat; - unsigned long flags; - u64 latest_ns; - int ret = 0; - - local_irq_save(flags); - latest_ns = this_cpu_read(cpu_hardirq_time); - if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_IRQ]) - ret = 1; - local_irq_restore(flags); - return ret; -} - -static int irqtime_account_si_update(void) -{ - u64 *cpustat = kcpustat_this_cpu->cpustat; - unsigned long flags; - u64 latest_ns; - int ret = 0; - - local_irq_save(flags); - latest_ns = this_cpu_read(cpu_softirq_time); - if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_SOFTIRQ]) - ret = 1; - local_irq_restore(flags); - return ret; -} - -#else /* CONFIG_IRQ_TIME_ACCOUNTING */ - -#define sched_clock_irqtime (0) - -#endif - void sched_set_stop_task(int cpu, struct task_struct *stop) { struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 }; @@ -1518,25 +1361,6 @@ static void ttwu_queue_remote(struct task_struct *p, int cpu) smp_send_reschedule(cpu); } -#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW -static int ttwu_activate_remote(struct task_struct *p, int wake_flags) -{ - struct rq *rq; - int ret = 0; - - rq = __task_rq_lock(p); - if (p->on_cpu) { - ttwu_activate(rq, p, ENQUEUE_WAKEUP); - ttwu_do_wakeup(rq, p, wake_flags); - ret = 1; - } - __task_rq_unlock(rq); - - return ret; - -} -#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ - bool cpus_share_cache(int this_cpu, int that_cpu) { return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu); @@ -1597,21 +1421,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) * If the owning (remote) cpu is still in the middle of schedule() with * this task as prev, wait until its done referencing the task. */ - while (p->on_cpu) { -#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW - /* - * In case the architecture enables interrupts in - * context_switch(), we cannot busy wait, since that - * would lead to deadlocks when an interrupt hits and - * tries to wake up @prev. So bail and do a complete - * remote wakeup. - */ - if (ttwu_activate_remote(p, wake_flags)) - goto stat; -#else + while (p->on_cpu) cpu_relax(); -#endif - } /* * Pairs with the smp_wmb() in finish_lock_switch(). */ @@ -1953,14 +1764,9 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) * Manfred Spraul <manfred@colorfullife.com> */ prev_state = prev->state; + vtime_task_switch(prev); finish_arch_switch(prev); -#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW - local_irq_disable(); -#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ perf_event_task_sched_in(prev, current); -#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW - local_irq_enable(); -#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ finish_lock_switch(rq, prev); finish_arch_post_lock_switch(); @@ -2081,6 +1887,7 @@ context_switch(struct rq *rq, struct task_struct *prev, #endif /* Here we just switch the register state and the stack. */ + rcu_switch(prev, next); switch_to(prev, next, prev); barrier(); @@ -2809,404 +2616,6 @@ unsigned long long task_sched_runtime(struct task_struct *p) return ns; } -#ifdef CONFIG_CGROUP_CPUACCT -struct cgroup_subsys cpuacct_subsys; -struct cpuacct root_cpuacct; -#endif - -static inline void task_group_account_field(struct task_struct *p, int index, - u64 tmp) -{ -#ifdef CONFIG_CGROUP_CPUACCT - struct kernel_cpustat *kcpustat; - struct cpuacct *ca; -#endif - /* - * Since all updates are sure to touch the root cgroup, we - * get ourselves ahead and touch it first. If the root cgroup - * is the only cgroup, then nothing else should be necessary. - * - */ - __get_cpu_var(kernel_cpustat).cpustat[index] += tmp; - -#ifdef CONFIG_CGROUP_CPUACCT - if (unlikely(!cpuacct_subsys.active)) - return; - - rcu_read_lock(); - ca = task_ca(p); - while (ca && (ca != &root_cpuacct)) { - kcpustat = this_cpu_ptr(ca->cpustat); - kcpustat->cpustat[index] += tmp; - ca = parent_ca(ca); - } - rcu_read_unlock(); -#endif -} - - -/* - * Account user cpu time to a process. - * @p: the process that the cpu time gets accounted to - * @cputime: the cpu time spent in user space since the last update - * @cputime_scaled: cputime scaled by cpu frequency - */ -void account_user_time(struct task_struct *p, cputime_t cputime, - cputime_t cputime_scaled) -{ - int index; - - /* Add user time to process. */ - p->utime += cputime; - p->utimescaled += cputime_scaled; - account_group_user_time(p, cputime); - - index = (TASK_NICE(p) > 0) ? CPUTIME_NICE : CPUTIME_USER; - - /* Add user time to cpustat. */ - task_group_account_field(p, index, (__force u64) cputime); - - /* Account for user time used */ - acct_update_integrals(p); -} - -/* - * Account guest cpu time to a process. - * @p: the process that the cpu time gets accounted to - * @cputime: the cpu time spent in virtual machine since the last update - * @cputime_scaled: cputime scaled by cpu frequency - */ -static void account_guest_time(struct task_struct *p, cputime_t cputime, - cputime_t cputime_scaled) -{ - u64 *cpustat = kcpustat_this_cpu->cpustat; - - /* Add guest time to process. */ - p->utime += cputime; - p->utimescaled += cputime_scaled; - account_group_user_time(p, cputime); - p->gtime += cputime; - - /* Add guest time to cpustat. */ - if (TASK_NICE(p) > 0) { - cpustat[CPUTIME_NICE] += (__force u64) cputime; - cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime; - } else { - cpustat[CPUTIME_USER] += (__force u64) cputime; - cpustat[CPUTIME_GUEST] += (__force u64) cputime; - } -} - -/* - * Account system cpu time to a process and desired cpustat field - * @p: the process that the cpu time gets accounted to - * @cputime: the cpu time spent in kernel space since the last update - * @cputime_scaled: cputime scaled by cpu frequency - * @target_cputime64: pointer to cpustat field that has to be updated - */ -static inline -void __account_system_time(struct task_struct *p, cputime_t cputime, - cputime_t cputime_scaled, int index) -{ - /* Add system time to process. */ - p->stime += cputime; - p->stimescaled += cputime_scaled; - account_group_system_time(p, cputime); - - /* Add system time to cpustat. */ - task_group_account_field(p, index, (__force u64) cputime); - - /* Account for system time used */ - acct_update_integrals(p); -} - -/* - * Account system cpu time to a process. - * @p: the process that the cpu time gets accounted to - * @hardirq_offset: the offset to subtract from hardirq_count() - * @cputime: the cpu time spent in kernel space since the last update - * @cputime_scaled: cputime scaled by cpu frequency - */ -void account_system_time(struct task_struct *p, int hardirq_offset, - cputime_t cputime, cputime_t cputime_scaled) -{ - int index; - - if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) { - account_guest_time(p, cputime, cputime_scaled); - return; - } - - if (hardirq_count() - hardirq_offset) - index = CPUTIME_IRQ; - else if (in_serving_softirq()) - index = CPUTIME_SOFTIRQ; - else - index = CPUTIME_SYSTEM; - - __account_system_time(p, cputime, cputime_scaled, index); -} - -/* - * Account for involuntary wait time. - * @cputime: the cpu time spent in involuntary wait - */ -void account_steal_time(cputime_t cputime) -{ - u64 *cpustat = kcpustat_this_cpu->cpustat; - - cpustat[CPUTIME_STEAL] += (__force u64) cputime; -} - -/* - * Account for idle time. - * @cputime: the cpu time spent in idle wait - */ -void account_idle_time(cputime_t cputime) -{ - u64 *cpustat = kcpustat_this_cpu->cpustat; - struct rq *rq = this_rq(); - - if (atomic_read(&rq->nr_iowait) > 0) - cpustat[CPUTIME_IOWAIT] += (__force u64) cputime; - else - cpustat[CPUTIME_IDLE] += (__force u64) cputime; -} - -static __always_inline bool steal_account_process_tick(void) -{ -#ifdef CONFIG_PARAVIRT - if (static_key_false(¶virt_steal_enabled)) { - u64 steal, st = 0; - - steal = paravirt_steal_clock(smp_processor_id()); - steal -= this_rq()->prev_steal_time; - - st = steal_ticks(steal); - this_rq()->prev_steal_time += st * TICK_NSEC; - - account_steal_time(st); - return st; - } -#endif - return false; -} - -#ifndef CONFIG_VIRT_CPU_ACCOUNTING - -#ifdef CONFIG_IRQ_TIME_ACCOUNTING -/* - * Account a tick to a process and cpustat - * @p: the process that the cpu time gets accounted to - * @user_tick: is the tick from userspace - * @rq: the pointer to rq - * - * Tick demultiplexing follows the order - * - pending hardirq update - * - pending softirq update - * - user_time - * - idle_time - * - system time - * - check for guest_time - * - else account as system_time - * - * Check for hardirq is done both for system and user time as there is - * no timer going off while we are on hardirq and hence we may never get an - * opportunity to update it solely in system time. - * p->stime and friends are only updated on system time and not on irq - * softirq as those do not count in task exec_runtime any more. - */ -static void irqtime_account_process_tick(struct task_struct *p, int user_tick, - struct rq *rq) -{ - cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); - u64 *cpustat = kcpustat_this_cpu->cpustat; - - if (steal_account_process_tick()) - return; - - if (irqtime_account_hi_update()) { - cpustat[CPUTIME_IRQ] += (__force u64) cputime_one_jiffy; - } else if (irqtime_account_si_update()) { - cpustat[CPUTIME_SOFTIRQ] += (__force u64) cputime_one_jiffy; - } else if (this_cpu_ksoftirqd() == p) { - /* - * ksoftirqd time do not get accounted in cpu_softirq_time. - * So, we have to handle it separately here. - * Also, p->stime needs to be updated for ksoftirqd. - */ - __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled, - CPUTIME_SOFTIRQ); - } else if (user_tick) { - account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); - } else if (p == rq->idle) { - account_idle_time(cputime_one_jiffy); - } else if (p->flags & PF_VCPU) { /* System time or guest time */ - account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled); - } else { - __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled, - CPUTIME_SYSTEM); - } -} - -static void irqtime_account_idle_ticks(int ticks) -{ - int i; - struct rq *rq = this_rq(); - - for (i = 0; i < ticks; i++) - irqtime_account_process_tick(current, 0, rq); -} -#else /* CONFIG_IRQ_TIME_ACCOUNTING */ -static void irqtime_account_idle_ticks(int ticks) {} -static void irqtime_account_process_tick(struct task_struct *p, int user_tick, - struct rq *rq) {} -#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ - -/* - * Account a single tick of cpu time. - * @p: the process that the cpu time gets accounted to - * @user_tick: indicates if the tick is a user or a system tick - */ -void account_process_tick(struct task_struct *p, int user_tick) -{ - cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); - struct rq *rq = this_rq(); - - if (sched_clock_irqtime) { - irqtime_account_process_tick(p, user_tick, rq); - return; - } - - if (steal_account_process_tick()) - return; - - if (user_tick) - account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); - else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET)) - account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy, - one_jiffy_scaled); - else - account_idle_time(cputime_one_jiffy); -} - -/* - * Account multiple ticks of steal time. - * @p: the process from which the cpu time has been stolen - * @ticks: number of stolen ticks - */ -void account_steal_ticks(unsigned long ticks) -{ - account_steal_time(jiffies_to_cputime(ticks)); -} - -/* - * Account multiple ticks of idle time. - * @ticks: number of stolen ticks - */ -void account_idle_ticks(unsigned long ticks) -{ - - if (sched_clock_irqtime) { - irqtime_account_idle_ticks(ticks); - return; - } - - account_idle_time(jiffies_to_cputime(ticks)); -} - -#endif - -/* - * Use precise platform statistics if available: - */ -#ifdef CONFIG_VIRT_CPU_ACCOUNTING -void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) -{ - *ut = p->utime; - *st = p->stime; -} - -void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) -{ - struct task_cputime cputime; - - thread_group_cputime(p, &cputime); - - *ut = cputime.utime; - *st = cputime.stime; -} -#else - -#ifndef nsecs_to_cputime -# define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs) -#endif - -static cputime_t scale_utime(cputime_t utime, cputime_t rtime, cputime_t total) -{ - u64 temp = (__force u64) rtime; - - temp *= (__force u64) utime; - - if (sizeof(cputime_t) == 4) - temp = div_u64(temp, (__force u32) total); - else - temp = div64_u64(temp, (__force u64) total); - - return (__force cputime_t) temp; -} - -void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) -{ - cputime_t rtime, utime = p->utime, total = utime + p->stime; - - /* - * Use CFS's precise accounting: - */ - rtime = nsecs_to_cputime(p->se.sum_exec_runtime); - - if (total) - utime = scale_utime(utime, rtime, total); - else - utime = rtime; - - /* - * Compare with previous values, to keep monotonicity: - */ - p->prev_utime = max(p->prev_utime, utime); - p->prev_stime = max(p->prev_stime, rtime - p->prev_utime); - - *ut = p->prev_utime; - *st = p->prev_stime; -} - -/* - * Must be called with siglock held. - */ -void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) -{ - struct signal_struct *sig = p->signal; - struct task_cputime cputime; - cputime_t rtime, utime, total; - - thread_group_cputime(p, &cputime); - - total = cputime.utime + cputime.stime; - rtime = nsecs_to_cputime(cputime.sum_exec_runtime); - - if (total) - utime = scale_utime(cputime.utime, rtime, total); - else - utime = rtime; - - sig->prev_utime = max(sig->prev_utime, utime); - sig->prev_stime = max(sig->prev_stime, rtime - sig->prev_utime); - - *ut = sig->prev_utime; - *st = sig->prev_stime; -} -#endif - /* * This function gets called by the timer code, with HZ frequency. * We call it with interrupts disabled. @@ -3367,6 +2776,40 @@ pick_next_task(struct rq *rq) /* * __schedule() is the main scheduler function. + * + * The main means of driving the scheduler and thus entering this function are: + * + * 1. Explicit blocking: mutex, semaphore, waitqueue, etc. + * + * 2. TIF_NEED_RESCHED flag is checked on interrupt and userspace return + * paths. For example, see arch/x86/entry_64.S. + * + * To drive preemption between tasks, the scheduler sets the flag in timer + * interrupt handler scheduler_tick(). + * + * 3. Wakeups don't really cause entry into schedule(). They add a + * task to the run-queue and that's it. + * + * Now, if the new task added to the run-queue preempts the current + * task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets + * called on the nearest possible occasion: + * + * - If the kernel is preemptible (CONFIG_PREEMPT=y): + * + * - in syscall or exception context, at the next outmost + * preempt_enable(). (this might be as soon as the wake_up()'s + * spin_unlock()!) + * + * - in IRQ context, return from interrupt-handler to + * preemptible context + * + * - If the kernel is not preemptible (CONFIG_PREEMPT is not set) + * then at the next: + * + * - cond_resched() call + * - explicit schedule() call + * - return from syscall or exception to user-space + * - return from interrupt-handler to user-space */ static void __sched __schedule(void) { @@ -3468,6 +2911,21 @@ asmlinkage void __sched schedule(void) } EXPORT_SYMBOL(schedule); +#ifdef CONFIG_RCU_USER_QS +asmlinkage void __sched schedule_user(void) +{ + /* + * If we come here after a random call to set_need_resched(), + * or we have been woken up remotely but the IPI has not yet arrived, + * we haven't yet exited the RCU idle mode. Do it here manually until + * we find a better solution. + */ + rcu_user_exit(); + schedule(); + rcu_user_enter(); +} +#endif + /** * schedule_preempt_disabled - called with preemption disabled * @@ -3569,6 +3027,7 @@ asmlinkage void __sched preempt_schedule_irq(void) /* Catch callers which need to be fixed */ BUG_ON(ti->preempt_count || !irqs_disabled()); + rcu_user_exit(); do { add_preempt_count(PREEMPT_ACTIVE); local_irq_enable(); @@ -4868,13 +4327,6 @@ again: */ if (preempt && rq != p_rq) resched_task(p_rq->curr); - } else { - /* - * We might have set it in task_yield_fair(), but are - * not going to schedule(), so don't want to skip - * the next update. - */ - rq->skip_clock_update = 0; } out: @@ -5416,16 +4868,25 @@ static void sd_free_ctl_entry(struct ctl_table **tablep) *tablep = NULL; } +static int min_load_idx = 0; +static int max_load_idx = CPU_LOAD_IDX_MAX; + static void set_table_entry(struct ctl_table *entry, const char *procname, void *data, int maxlen, - umode_t mode, proc_handler *proc_handler) + umode_t mode, proc_handler *proc_handler, + bool load_idx) { entry->procname = procname; entry->data = data; entry->maxlen = maxlen; entry->mode = mode; entry->proc_handler = proc_handler; + + if (load_idx) { + entry->extra1 = &min_load_idx; + entry->extra2 = &max_load_idx; + } } static struct ctl_table * @@ -5437,30 +4898,30 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd) return NULL; set_table_entry(&table[0], "min_interval", &sd->min_interval, - sizeof(long), 0644, proc_doulongvec_minmax); + sizeof(long), 0644, proc_doulongvec_minmax, false); set_table_entry(&table[1], "max_interval", &sd->max_interval, - sizeof(long), 0644, proc_doulongvec_minmax); + sizeof(long), 0644, proc_doulongvec_minmax, false); set_table_entry(&table[2], "busy_idx", &sd->busy_idx, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, true); set_table_entry(&table[3], "idle_idx", &sd->idle_idx, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, true); set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, true); set_table_entry(&table[5], "wake_idx", &sd->wake_idx, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, true); set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, true); set_table_entry(&table[7], "busy_factor", &sd->busy_factor, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, false); set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, false); set_table_entry(&table[9], "cache_nice_tries", &sd->cache_nice_tries, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, false); set_table_entry(&table[10], "flags", &sd->flags, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, false); set_table_entry(&table[11], "name", sd->name, - CORENAME_MAX_SIZE, 0444, proc_dostring); + CORENAME_MAX_SIZE, 0444, proc_dostring, false); /* &table[12] is terminator */ return table; @@ -5604,7 +5065,9 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) migrate_tasks(cpu); BUG_ON(rq->nr_running != 1); /* the migration thread */ raw_spin_unlock_irqrestore(&rq->lock, flags); + break; + case CPU_DEAD: calc_load_migrate(rq); break; #endif @@ -6537,7 +6000,6 @@ sd_numa_init(struct sched_domain_topology_level *tl, int cpu) | 0*SD_BALANCE_FORK | 0*SD_BALANCE_WAKE | 0*SD_WAKE_AFFINE - | 0*SD_PREFER_LOCAL | 0*SD_SHARE_CPUPOWER | 0*SD_SHARE_PKG_RESOURCES | 1*SD_SERIALIZE @@ -6660,6 +6122,17 @@ static void sched_init_numa(void) * numbers. */ + /* + * Here, we should temporarily reset sched_domains_numa_levels to 0. + * If it fails to allocate memory for array sched_domains_numa_masks[][], + * the array will contain less then 'level' members. This could be + * dangerous when we use it to iterate array sched_domains_numa_masks[][] + * in other functions. + * + * We reset it to 'level' at the end of this function. + */ + sched_domains_numa_levels = 0; + sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL); if (!sched_domains_numa_masks) return; @@ -6714,11 +6187,68 @@ static void sched_init_numa(void) } sched_domain_topology = tl; + + sched_domains_numa_levels = level; +} + +static void sched_domains_numa_masks_set(int cpu) +{ + int i, j; + int node = cpu_to_node(cpu); + + for (i = 0; i < sched_domains_numa_levels; i++) { + for (j = 0; j < nr_node_ids; j++) { + if (node_distance(j, node) <= sched_domains_numa_distance[i]) + cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]); + } + } +} + +static void sched_domains_numa_masks_clear(int cpu) +{ + int i, j; + for (i = 0; i < sched_domains_numa_levels; i++) { + for (j = 0; j < nr_node_ids; j++) + cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]); + } +} + +/* + * Update sched_domains_numa_masks[level][node] array when new cpus + * are onlined. + */ +static int sched_domains_numa_masks_update(struct notifier_block *nfb, + unsigned long action, + void *hcpu) +{ + int cpu = (long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_ONLINE: + sched_domains_numa_masks_set(cpu); + break; + + case CPU_DEAD: + sched_domains_numa_masks_clear(cpu); + break; + + default: + return NOTIFY_DONE; + } + + return NOTIFY_OK; } #else static inline void sched_init_numa(void) { } + +static int sched_domains_numa_masks_update(struct notifier_block *nfb, + unsigned long action, + void *hcpu) +{ + return 0; +} #endif /* CONFIG_NUMA */ static int __sdt_alloc(const struct cpumask *cpu_map) @@ -7167,6 +6697,7 @@ void __init sched_init_smp(void) mutex_unlock(&sched_domains_mutex); put_online_cpus(); + hotcpu_notifier(sched_domains_numa_masks_update, CPU_PRI_SCHED_ACTIVE); hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE); hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE); @@ -8335,6 +7866,8 @@ struct cgroup_subsys cpu_cgroup_subsys = { * (balbir@in.ibm.com). */ +struct cpuacct root_cpuacct; + /* create a new cpu accounting group */ static struct cgroup_subsys_state *cpuacct_create(struct cgroup *cgrp) { diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c new file mode 100644 index 000000000000..81b763ba58a6 --- /dev/null +++ b/kernel/sched/cputime.c @@ -0,0 +1,530 @@ +#include <linux/export.h> +#include <linux/sched.h> +#include <linux/tsacct_kern.h> +#include <linux/kernel_stat.h> +#include <linux/static_key.h> +#include "sched.h" + + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + +/* + * There are no locks covering percpu hardirq/softirq time. + * They are only modified in vtime_account, on corresponding CPU + * with interrupts disabled. So, writes are safe. + * They are read and saved off onto struct rq in update_rq_clock(). + * This may result in other CPU reading this CPU's irq time and can + * race with irq/vtime_account on this CPU. We would either get old + * or new value with a side effect of accounting a slice of irq time to wrong + * task when irq is in progress while we read rq->clock. That is a worthy + * compromise in place of having locks on each irq in account_system_time. + */ +DEFINE_PER_CPU(u64, cpu_hardirq_time); +DEFINE_PER_CPU(u64, cpu_softirq_time); + +static DEFINE_PER_CPU(u64, irq_start_time); +static int sched_clock_irqtime; + +void enable_sched_clock_irqtime(void) +{ + sched_clock_irqtime = 1; +} + +void disable_sched_clock_irqtime(void) +{ + sched_clock_irqtime = 0; +} + +#ifndef CONFIG_64BIT +DEFINE_PER_CPU(seqcount_t, irq_time_seq); +#endif /* CONFIG_64BIT */ + +/* + * Called before incrementing preempt_count on {soft,}irq_enter + * and before decrementing preempt_count on {soft,}irq_exit. + */ +void vtime_account(struct task_struct *curr) +{ + unsigned long flags; + s64 delta; + int cpu; + + if (!sched_clock_irqtime) + return; + + local_irq_save(flags); + + cpu = smp_processor_id(); + delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time); + __this_cpu_add(irq_start_time, delta); + + irq_time_write_begin(); + /* + * We do not account for softirq time from ksoftirqd here. + * We want to continue accounting softirq time to ksoftirqd thread + * in that case, so as not to confuse scheduler with a special task + * that do not consume any time, but still wants to run. + */ + if (hardirq_count()) + __this_cpu_add(cpu_hardirq_time, delta); + else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) + __this_cpu_add(cpu_softirq_time, delta); + + irq_time_write_end(); + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(vtime_account); + +static int irqtime_account_hi_update(void) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + unsigned long flags; + u64 latest_ns; + int ret = 0; + + local_irq_save(flags); + latest_ns = this_cpu_read(cpu_hardirq_time); + if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_IRQ]) + ret = 1; + local_irq_restore(flags); + return ret; +} + +static int irqtime_account_si_update(void) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + unsigned long flags; + u64 latest_ns; + int ret = 0; + + local_irq_save(flags); + latest_ns = this_cpu_read(cpu_softirq_time); + if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_SOFTIRQ]) + ret = 1; + local_irq_restore(flags); + return ret; +} + +#else /* CONFIG_IRQ_TIME_ACCOUNTING */ + +#define sched_clock_irqtime (0) + +#endif /* !CONFIG_IRQ_TIME_ACCOUNTING */ + +static inline void task_group_account_field(struct task_struct *p, int index, + u64 tmp) +{ +#ifdef CONFIG_CGROUP_CPUACCT + struct kernel_cpustat *kcpustat; + struct cpuacct *ca; +#endif + /* + * Since all updates are sure to touch the root cgroup, we + * get ourselves ahead and touch it first. If the root cgroup + * is the only cgroup, then nothing else should be necessary. + * + */ + __get_cpu_var(kernel_cpustat).cpustat[index] += tmp; + +#ifdef CONFIG_CGROUP_CPUACCT + if (unlikely(!cpuacct_subsys.active)) + return; + + rcu_read_lock(); + ca = task_ca(p); + while (ca && (ca != &root_cpuacct)) { + kcpustat = this_cpu_ptr(ca->cpustat); + kcpustat->cpustat[index] += tmp; + ca = parent_ca(ca); + } + rcu_read_unlock(); +#endif +} + +/* + * Account user cpu time to a process. + * @p: the process that the cpu time gets accounted to + * @cputime: the cpu time spent in user space since the last update + * @cputime_scaled: cputime scaled by cpu frequency + */ +void account_user_time(struct task_struct *p, cputime_t cputime, + cputime_t cputime_scaled) +{ + int index; + + /* Add user time to process. */ + p->utime += cputime; + p->utimescaled += cputime_scaled; + account_group_user_time(p, cputime); + + index = (TASK_NICE(p) > 0) ? CPUTIME_NICE : CPUTIME_USER; + + /* Add user time to cpustat. */ + task_group_account_field(p, index, (__force u64) cputime); + + /* Account for user time used */ + acct_update_integrals(p); +} + +/* + * Account guest cpu time to a process. + * @p: the process that the cpu time gets accounted to + * @cputime: the cpu time spent in virtual machine since the last update + * @cputime_scaled: cputime scaled by cpu frequency + */ +static void account_guest_time(struct task_struct *p, cputime_t cputime, + cputime_t cputime_scaled) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + + /* Add guest time to process. */ + p->utime += cputime; + p->utimescaled += cputime_scaled; + account_group_user_time(p, cputime); + p->gtime += cputime; + + /* Add guest time to cpustat. */ + if (TASK_NICE(p) > 0) { + cpustat[CPUTIME_NICE] += (__force u64) cputime; + cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime; + } else { + cpustat[CPUTIME_USER] += (__force u64) cputime; + cpustat[CPUTIME_GUEST] += (__force u64) cputime; + } +} + +/* + * Account system cpu time to a process and desired cpustat field + * @p: the process that the cpu time gets accounted to + * @cputime: the cpu time spent in kernel space since the last update + * @cputime_scaled: cputime scaled by cpu frequency + * @target_cputime64: pointer to cpustat field that has to be updated + */ +static inline +void __account_system_time(struct task_struct *p, cputime_t cputime, + cputime_t cputime_scaled, int index) +{ + /* Add system time to process. */ + p->stime += cputime; + p->stimescaled += cputime_scaled; + account_group_system_time(p, cputime); + + /* Add system time to cpustat. */ + task_group_account_field(p, index, (__force u64) cputime); + + /* Account for system time used */ + acct_update_integrals(p); +} + +/* + * Account system cpu time to a process. + * @p: the process that the cpu time gets accounted to + * @hardirq_offset: the offset to subtract from hardirq_count() + * @cputime: the cpu time spent in kernel space since the last update + * @cputime_scaled: cputime scaled by cpu frequency + */ +void account_system_time(struct task_struct *p, int hardirq_offset, + cputime_t cputime, cputime_t cputime_scaled) +{ + int index; + + if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) { + account_guest_time(p, cputime, cputime_scaled); + return; + } + + if (hardirq_count() - hardirq_offset) + index = CPUTIME_IRQ; + else if (in_serving_softirq()) + index = CPUTIME_SOFTIRQ; + else + index = CPUTIME_SYSTEM; + + __account_system_time(p, cputime, cputime_scaled, index); +} + +/* + * Account for involuntary wait time. + * @cputime: the cpu time spent in involuntary wait + */ +void account_steal_time(cputime_t cputime) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + + cpustat[CPUTIME_STEAL] += (__force u64) cputime; +} + +/* + * Account for idle time. + * @cputime: the cpu time spent in idle wait + */ +void account_idle_time(cputime_t cputime) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + struct rq *rq = this_rq(); + + if (atomic_read(&rq->nr_iowait) > 0) + cpustat[CPUTIME_IOWAIT] += (__force u64) cputime; + else + cpustat[CPUTIME_IDLE] += (__force u64) cputime; +} + +static __always_inline bool steal_account_process_tick(void) +{ +#ifdef CONFIG_PARAVIRT + if (static_key_false(¶virt_steal_enabled)) { + u64 steal, st = 0; + + steal = paravirt_steal_clock(smp_processor_id()); + steal -= this_rq()->prev_steal_time; + + st = steal_ticks(steal); + this_rq()->prev_steal_time += st * TICK_NSEC; + + account_steal_time(st); + return st; + } +#endif + return false; +} + +#ifndef CONFIG_VIRT_CPU_ACCOUNTING + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING +/* + * Account a tick to a process and cpustat + * @p: the process that the cpu time gets accounted to + * @user_tick: is the tick from userspace + * @rq: the pointer to rq + * + * Tick demultiplexing follows the order + * - pending hardirq update + * - pending softirq update + * - user_time + * - idle_time + * - system time + * - check for guest_time + * - else account as system_time + * + * Check for hardirq is done both for system and user time as there is + * no timer going off while we are on hardirq and hence we may never get an + * opportunity to update it solely in system time. + * p->stime and friends are only updated on system time and not on irq + * softirq as those do not count in task exec_runtime any more. + */ +static void irqtime_account_process_tick(struct task_struct *p, int user_tick, + struct rq *rq) +{ + cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); + u64 *cpustat = kcpustat_this_cpu->cpustat; + + if (steal_account_process_tick()) + return; + + if (irqtime_account_hi_update()) { + cpustat[CPUTIME_IRQ] += (__force u64) cputime_one_jiffy; + } else if (irqtime_account_si_update()) { + cpustat[CPUTIME_SOFTIRQ] += (__force u64) cputime_one_jiffy; + } else if (this_cpu_ksoftirqd() == p) { + /* + * ksoftirqd time do not get accounted in cpu_softirq_time. + * So, we have to handle it separately here. + * Also, p->stime needs to be updated for ksoftirqd. + */ + __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled, + CPUTIME_SOFTIRQ); + } else if (user_tick) { + account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); + } else if (p == rq->idle) { + account_idle_time(cputime_one_jiffy); + } else if (p->flags & PF_VCPU) { /* System time or guest time */ + account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled); + } else { + __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled, + CPUTIME_SYSTEM); + } +} + +static void irqtime_account_idle_ticks(int ticks) +{ + int i; + struct rq *rq = this_rq(); + + for (i = 0; i < ticks; i++) + irqtime_account_process_tick(current, 0, rq); +} +#else /* CONFIG_IRQ_TIME_ACCOUNTING */ +static void irqtime_account_idle_ticks(int ticks) {} +static void irqtime_account_process_tick(struct task_struct *p, int user_tick, + struct rq *rq) {} +#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ + +/* + * Account a single tick of cpu time. + * @p: the process that the cpu time gets accounted to + * @user_tick: indicates if the tick is a user or a system tick + */ +void account_process_tick(struct task_struct *p, int user_tick) +{ + cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); + struct rq *rq = this_rq(); + + if (sched_clock_irqtime) { + irqtime_account_process_tick(p, user_tick, rq); + return; + } + + if (steal_account_process_tick()) + return; + + if (user_tick) + account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); + else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET)) + account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy, + one_jiffy_scaled); + else + account_idle_time(cputime_one_jiffy); +} + +/* + * Account multiple ticks of steal time. + * @p: the process from which the cpu time has been stolen + * @ticks: number of stolen ticks + */ +void account_steal_ticks(unsigned long ticks) +{ + account_steal_time(jiffies_to_cputime(ticks)); +} + +/* + * Account multiple ticks of idle time. + * @ticks: number of stolen ticks + */ +void account_idle_ticks(unsigned long ticks) +{ + + if (sched_clock_irqtime) { + irqtime_account_idle_ticks(ticks); + return; + } + + account_idle_time(jiffies_to_cputime(ticks)); +} + +#endif + +/* + * Use precise platform statistics if available: + */ +#ifdef CONFIG_VIRT_CPU_ACCOUNTING +void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + *ut = p->utime; + *st = p->stime; +} + +void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + struct task_cputime cputime; + + thread_group_cputime(p, &cputime); + + *ut = cputime.utime; + *st = cputime.stime; +} + +/* + * Archs that account the whole time spent in the idle task + * (outside irq) as idle time can rely on this and just implement + * vtime_account_system() and vtime_account_idle(). Archs that + * have other meaning of the idle time (s390 only includes the + * time spent by the CPU when it's in low power mode) must override + * vtime_account(). + */ +#ifndef __ARCH_HAS_VTIME_ACCOUNT +void vtime_account(struct task_struct *tsk) +{ + unsigned long flags; + + local_irq_save(flags); + + if (in_interrupt() || !is_idle_task(tsk)) + vtime_account_system(tsk); + else + vtime_account_idle(tsk); + + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(vtime_account); +#endif /* __ARCH_HAS_VTIME_ACCOUNT */ + +#else + +#ifndef nsecs_to_cputime +# define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs) +#endif + +static cputime_t scale_utime(cputime_t utime, cputime_t rtime, cputime_t total) +{ + u64 temp = (__force u64) rtime; + + temp *= (__force u64) utime; + + if (sizeof(cputime_t) == 4) + temp = div_u64(temp, (__force u32) total); + else + temp = div64_u64(temp, (__force u64) total); + + return (__force cputime_t) temp; +} + +void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + cputime_t rtime, utime = p->utime, total = utime + p->stime; + + /* + * Use CFS's precise accounting: + */ + rtime = nsecs_to_cputime(p->se.sum_exec_runtime); + + if (total) + utime = scale_utime(utime, rtime, total); + else + utime = rtime; + + /* + * Compare with previous values, to keep monotonicity: + */ + p->prev_utime = max(p->prev_utime, utime); + p->prev_stime = max(p->prev_stime, rtime - p->prev_utime); + + *ut = p->prev_utime; + *st = p->prev_stime; +} + +/* + * Must be called with siglock held. + */ +void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + struct signal_struct *sig = p->signal; + struct task_cputime cputime; + cputime_t rtime, utime, total; + + thread_group_cputime(p, &cputime); + + total = cputime.utime + cputime.stime; + rtime = nsecs_to_cputime(cputime.sum_exec_runtime); + + if (total) + utime = scale_utime(cputime.utime, rtime, total); + else + utime = rtime; + + sig->prev_utime = max(sig->prev_utime, utime); + sig->prev_stime = max(sig->prev_stime, rtime - sig->prev_utime); + + *ut = sig->prev_utime; + *st = sig->prev_stime; +} +#endif diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 96e2b18b6283..6b800a14b990 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -597,7 +597,7 @@ calc_delta_fair(unsigned long delta, struct sched_entity *se) /* * The idea is to set a period in which each task runs once. * - * When there are too many tasks (sysctl_sched_nr_latency) we have to stretch + * When there are too many tasks (sched_nr_latency) we have to stretch * this period because otherwise the slices get too small. * * p = (nr <= nl) ? l : l*nr/nl @@ -2700,7 +2700,6 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags) int prev_cpu = task_cpu(p); int new_cpu = cpu; int want_affine = 0; - int want_sd = 1; int sync = wake_flags & WF_SYNC; if (p->nr_cpus_allowed == 1) @@ -2718,48 +2717,21 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags) continue; /* - * If power savings logic is enabled for a domain, see if we - * are not overloaded, if so, don't balance wider. - */ - if (tmp->flags & (SD_PREFER_LOCAL)) { - unsigned long power = 0; - unsigned long nr_running = 0; - unsigned long capacity; - int i; - - for_each_cpu(i, sched_domain_span(tmp)) { - power += power_of(i); - nr_running += cpu_rq(i)->cfs.nr_running; - } - - capacity = DIV_ROUND_CLOSEST(power, SCHED_POWER_SCALE); - - if (nr_running < capacity) - want_sd = 0; - } - - /* * If both cpu and prev_cpu are part of this domain, * cpu is a valid SD_WAKE_AFFINE target. */ if (want_affine && (tmp->flags & SD_WAKE_AFFINE) && cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) { affine_sd = tmp; - want_affine = 0; - } - - if (!want_sd && !want_affine) break; + } - if (!(tmp->flags & sd_flag)) - continue; - - if (want_sd) + if (tmp->flags & sd_flag) sd = tmp; } if (affine_sd) { - if (cpu == prev_cpu || wake_affine(affine_sd, p, sync)) + if (cpu != prev_cpu && wake_affine(affine_sd, p, sync)) prev_cpu = cpu; new_cpu = select_idle_sibling(p, prev_cpu); @@ -4295,7 +4267,7 @@ redo: goto out_balanced; } - BUG_ON(busiest == this_rq); + BUG_ON(busiest == env.dst_rq); schedstat_add(sd, lb_imbalance[idle], env.imbalance); @@ -4316,7 +4288,7 @@ redo: update_h_load(env.src_cpu); more_balance: local_irq_save(flags); - double_rq_lock(this_rq, busiest); + double_rq_lock(env.dst_rq, busiest); /* * cur_ld_moved - load moved in current iteration @@ -4324,7 +4296,7 @@ more_balance: */ cur_ld_moved = move_tasks(&env); ld_moved += cur_ld_moved; - double_rq_unlock(this_rq, busiest); + double_rq_unlock(env.dst_rq, busiest); local_irq_restore(flags); if (env.flags & LBF_NEED_BREAK) { @@ -4360,8 +4332,7 @@ more_balance: if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0 && lb_iterations++ < max_lb_iterations) { - this_rq = cpu_rq(env.new_dst_cpu); - env.dst_rq = this_rq; + env.dst_rq = cpu_rq(env.new_dst_cpu); env.dst_cpu = env.new_dst_cpu; env.flags &= ~LBF_SOME_PINNED; env.loop = 0; @@ -4646,7 +4617,7 @@ static void nohz_balancer_kick(int cpu) return; } -static inline void clear_nohz_tick_stopped(int cpu) +static inline void nohz_balance_exit_idle(int cpu) { if (unlikely(test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))) { cpumask_clear_cpu(cpu, nohz.idle_cpus_mask); @@ -4686,28 +4657,23 @@ void set_cpu_sd_state_idle(void) } /* - * This routine will record that this cpu is going idle with tick stopped. + * This routine will record that the cpu is going idle with tick stopped. * This info will be used in performing idle load balancing in the future. */ -void select_nohz_load_balancer(int stop_tick) +void nohz_balance_enter_idle(int cpu) { - int cpu = smp_processor_id(); - /* * If this cpu is going down, then nothing needs to be done. */ if (!cpu_active(cpu)) return; - if (stop_tick) { - if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu))) - return; + if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu))) + return; - cpumask_set_cpu(cpu, nohz.idle_cpus_mask); - atomic_inc(&nohz.nr_cpus); - set_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)); - } - return; + cpumask_set_cpu(cpu, nohz.idle_cpus_mask); + atomic_inc(&nohz.nr_cpus); + set_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)); } static int __cpuinit sched_ilb_notifier(struct notifier_block *nfb, @@ -4715,7 +4681,7 @@ static int __cpuinit sched_ilb_notifier(struct notifier_block *nfb, { switch (action & ~CPU_TASKS_FROZEN) { case CPU_DYING: - clear_nohz_tick_stopped(smp_processor_id()); + nohz_balance_exit_idle(smp_processor_id()); return NOTIFY_OK; default: return NOTIFY_DONE; @@ -4837,14 +4803,15 @@ static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle) if (need_resched()) break; - raw_spin_lock_irq(&this_rq->lock); - update_rq_clock(this_rq); - update_idle_cpu_load(this_rq); - raw_spin_unlock_irq(&this_rq->lock); + rq = cpu_rq(balance_cpu); + + raw_spin_lock_irq(&rq->lock); + update_rq_clock(rq); + update_idle_cpu_load(rq); + raw_spin_unlock_irq(&rq->lock); rebalance_domains(balance_cpu, CPU_IDLE); - rq = cpu_rq(balance_cpu); if (time_after(this_rq->next_balance, rq->next_balance)) this_rq->next_balance = rq->next_balance; } @@ -4875,7 +4842,7 @@ static inline int nohz_kick_needed(struct rq *rq, int cpu) * busy tick after returning from idle, we will update the busy stats. */ set_cpu_sd_state_busy(); - clear_nohz_tick_stopped(cpu); + nohz_balance_exit_idle(cpu); /* * None are in tickless mode and hence no need for NOHZ idle load diff --git a/kernel/sched/features.h b/kernel/sched/features.h index de00a486c5c6..eebefcad7027 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -12,14 +12,6 @@ SCHED_FEAT(GENTLE_FAIR_SLEEPERS, true) SCHED_FEAT(START_DEBIT, true) /* - * Based on load and program behaviour, see if it makes sense to place - * a newly woken task on the same cpu as the task that woke it -- - * improve cache locality. Typically used with SYNC wakeups as - * generated by pipes and the like, see also SYNC_WAKEUPS. - */ -SCHED_FEAT(AFFINE_WAKEUPS, true) - -/* * Prefer to schedule the task we woke last (assuming it failed * wakeup-preemption), since its likely going to consume data we * touched, increases cache locality. @@ -42,7 +34,7 @@ SCHED_FEAT(CACHE_HOT_BUDDY, true) /* * Use arch dependent cpu power functions */ -SCHED_FEAT(ARCH_POWER, false) +SCHED_FEAT(ARCH_POWER, true) SCHED_FEAT(HRTICK, false) SCHED_FEAT(DOUBLE_TICK, false) diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index e0b7ba9c040f..418feb01344e 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1632,11 +1632,6 @@ static int push_rt_task(struct rq *rq) if (!next_task) return 0; -#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW - if (unlikely(task_running(rq, next_task))) - return 0; -#endif - retry: if (unlikely(next_task == rq->curr)) { WARN_ON(1); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 0848fa36c383..7a7db09cfabc 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -737,11 +737,7 @@ static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) */ next->on_cpu = 1; #endif -#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW - raw_spin_unlock_irq(&rq->lock); -#else raw_spin_unlock(&rq->lock); -#endif } static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) @@ -755,9 +751,7 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) smp_wmb(); prev->on_cpu = 0; #endif -#ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW local_irq_enable(); -#endif } #endif /* __ARCH_WANT_UNLOCKED_CTXSW */ @@ -891,6 +885,9 @@ struct cpuacct { struct kernel_cpustat __percpu *cpustat; }; +extern struct cgroup_subsys cpuacct_subsys; +extern struct cpuacct root_cpuacct; + /* return cpu accounting group corresponding to this container */ static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp) { @@ -917,6 +914,16 @@ extern void cpuacct_charge(struct task_struct *tsk, u64 cputime); static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {} #endif +#ifdef CONFIG_PARAVIRT +static inline u64 steal_ticks(u64 steal) +{ + if (unlikely(steal > NSEC_PER_SEC)) + return div_u64(steal, TICK_NSEC); + + return __iter_div_u64_rem(steal, TICK_NSEC, &steal); +} +#endif + static inline void inc_nr_running(struct rq *rq) { rq->nr_running++; @@ -1156,3 +1163,53 @@ enum rq_nohz_flag_bits { #define nohz_flags(cpu) (&cpu_rq(cpu)->nohz_flags) #endif + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + +DECLARE_PER_CPU(u64, cpu_hardirq_time); +DECLARE_PER_CPU(u64, cpu_softirq_time); + +#ifndef CONFIG_64BIT +DECLARE_PER_CPU(seqcount_t, irq_time_seq); + +static inline void irq_time_write_begin(void) +{ + __this_cpu_inc(irq_time_seq.sequence); + smp_wmb(); +} + +static inline void irq_time_write_end(void) +{ + smp_wmb(); + __this_cpu_inc(irq_time_seq.sequence); +} + +static inline u64 irq_time_read(int cpu) +{ + u64 irq_time; + unsigned seq; + + do { + seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu)); + irq_time = per_cpu(cpu_softirq_time, cpu) + + per_cpu(cpu_hardirq_time, cpu); + } while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq)); + + return irq_time; +} +#else /* CONFIG_64BIT */ +static inline void irq_time_write_begin(void) +{ +} + +static inline void irq_time_write_end(void) +{ +} + +static inline u64 irq_time_read(int cpu) +{ + return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu); +} +#endif /* CONFIG_64BIT */ +#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ + diff --git a/kernel/signal.c b/kernel/signal.c index be4f856d52f8..0af8868525d6 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -17,6 +17,7 @@ #include <linux/fs.h> #include <linux/tty.h> #include <linux/binfmts.h> +#include <linux/coredump.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/ptrace.h> @@ -1971,13 +1972,8 @@ static void ptrace_do_notify(int signr, int exit_code, int why) void ptrace_notify(int exit_code) { BUG_ON((exit_code & (0x7f | ~0xffff)) != SIGTRAP); - if (unlikely(current->task_works)) { - if (test_and_clear_ti_thread_flag(current_thread_info(), - TIF_NOTIFY_RESUME)) { - smp_mb__after_clear_bit(); - task_work_run(); - } - } + if (unlikely(current->task_works)) + task_work_run(); spin_lock_irq(¤t->sighand->siglock); ptrace_do_notify(SIGTRAP, exit_code, CLD_TRAPPED); @@ -2198,13 +2194,8 @@ int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka, struct signal_struct *signal = current->signal; int signr; - if (unlikely(current->task_works)) { - if (test_and_clear_ti_thread_flag(current_thread_info(), - TIF_NOTIFY_RESUME)) { - smp_mb__after_clear_bit(); - task_work_run(); - } - } + if (unlikely(current->task_works)) + task_work_run(); if (unlikely(uprobe_deny_signal())) return 0; @@ -2369,7 +2360,7 @@ relock: * first and our do_group_exit call below will use * that value and ignore the one we pass it. */ - do_coredump(info->si_signo, info->si_signo, regs); + do_coredump(info, regs); } /* diff --git a/kernel/smpboot.c b/kernel/smpboot.c index 98f60c5caa1b..d6c5fc054242 100644 --- a/kernel/smpboot.c +++ b/kernel/smpboot.c @@ -1,14 +1,22 @@ /* * Common SMP CPU bringup/teardown functions */ +#include <linux/cpu.h> #include <linux/err.h> #include <linux/smp.h> #include <linux/init.h> +#include <linux/list.h> +#include <linux/slab.h> #include <linux/sched.h> +#include <linux/export.h> #include <linux/percpu.h> +#include <linux/kthread.h> +#include <linux/smpboot.h> #include "smpboot.h" +#ifdef CONFIG_SMP + #ifdef CONFIG_GENERIC_SMP_IDLE_THREAD /* * For the hotplug case we keep the task structs around and reuse @@ -65,3 +73,228 @@ void __init idle_threads_init(void) } } #endif + +#endif /* #ifdef CONFIG_SMP */ + +static LIST_HEAD(hotplug_threads); +static DEFINE_MUTEX(smpboot_threads_lock); + +struct smpboot_thread_data { + unsigned int cpu; + unsigned int status; + struct smp_hotplug_thread *ht; +}; + +enum { + HP_THREAD_NONE = 0, + HP_THREAD_ACTIVE, + HP_THREAD_PARKED, +}; + +/** + * smpboot_thread_fn - percpu hotplug thread loop function + * @data: thread data pointer + * + * Checks for thread stop and park conditions. Calls the necessary + * setup, cleanup, park and unpark functions for the registered + * thread. + * + * Returns 1 when the thread should exit, 0 otherwise. + */ +static int smpboot_thread_fn(void *data) +{ + struct smpboot_thread_data *td = data; + struct smp_hotplug_thread *ht = td->ht; + + while (1) { + set_current_state(TASK_INTERRUPTIBLE); + preempt_disable(); + if (kthread_should_stop()) { + set_current_state(TASK_RUNNING); + preempt_enable(); + if (ht->cleanup) + ht->cleanup(td->cpu, cpu_online(td->cpu)); + kfree(td); + return 0; + } + + if (kthread_should_park()) { + __set_current_state(TASK_RUNNING); + preempt_enable(); + if (ht->park && td->status == HP_THREAD_ACTIVE) { + BUG_ON(td->cpu != smp_processor_id()); + ht->park(td->cpu); + td->status = HP_THREAD_PARKED; + } + kthread_parkme(); + /* We might have been woken for stop */ + continue; + } + + BUG_ON(td->cpu != smp_processor_id()); + + /* Check for state change setup */ + switch (td->status) { + case HP_THREAD_NONE: + preempt_enable(); + if (ht->setup) + ht->setup(td->cpu); + td->status = HP_THREAD_ACTIVE; + preempt_disable(); + break; + case HP_THREAD_PARKED: + preempt_enable(); + if (ht->unpark) + ht->unpark(td->cpu); + td->status = HP_THREAD_ACTIVE; + preempt_disable(); + break; + } + + if (!ht->thread_should_run(td->cpu)) { + preempt_enable(); + schedule(); + } else { + set_current_state(TASK_RUNNING); + preempt_enable(); + ht->thread_fn(td->cpu); + } + } +} + +static int +__smpboot_create_thread(struct smp_hotplug_thread *ht, unsigned int cpu) +{ + struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu); + struct smpboot_thread_data *td; + + if (tsk) + return 0; + + td = kzalloc_node(sizeof(*td), GFP_KERNEL, cpu_to_node(cpu)); + if (!td) + return -ENOMEM; + td->cpu = cpu; + td->ht = ht; + + tsk = kthread_create_on_cpu(smpboot_thread_fn, td, cpu, + ht->thread_comm); + if (IS_ERR(tsk)) { + kfree(td); + return PTR_ERR(tsk); + } + + get_task_struct(tsk); + *per_cpu_ptr(ht->store, cpu) = tsk; + return 0; +} + +int smpboot_create_threads(unsigned int cpu) +{ + struct smp_hotplug_thread *cur; + int ret = 0; + + mutex_lock(&smpboot_threads_lock); + list_for_each_entry(cur, &hotplug_threads, list) { + ret = __smpboot_create_thread(cur, cpu); + if (ret) + break; + } + mutex_unlock(&smpboot_threads_lock); + return ret; +} + +static void smpboot_unpark_thread(struct smp_hotplug_thread *ht, unsigned int cpu) +{ + struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu); + + kthread_unpark(tsk); +} + +void smpboot_unpark_threads(unsigned int cpu) +{ + struct smp_hotplug_thread *cur; + + mutex_lock(&smpboot_threads_lock); + list_for_each_entry(cur, &hotplug_threads, list) + smpboot_unpark_thread(cur, cpu); + mutex_unlock(&smpboot_threads_lock); +} + +static void smpboot_park_thread(struct smp_hotplug_thread *ht, unsigned int cpu) +{ + struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu); + + if (tsk) + kthread_park(tsk); +} + +void smpboot_park_threads(unsigned int cpu) +{ + struct smp_hotplug_thread *cur; + + mutex_lock(&smpboot_threads_lock); + list_for_each_entry_reverse(cur, &hotplug_threads, list) + smpboot_park_thread(cur, cpu); + mutex_unlock(&smpboot_threads_lock); +} + +static void smpboot_destroy_threads(struct smp_hotplug_thread *ht) +{ + unsigned int cpu; + + /* We need to destroy also the parked threads of offline cpus */ + for_each_possible_cpu(cpu) { + struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu); + + if (tsk) { + kthread_stop(tsk); + put_task_struct(tsk); + *per_cpu_ptr(ht->store, cpu) = NULL; + } + } +} + +/** + * smpboot_register_percpu_thread - Register a per_cpu thread related to hotplug + * @plug_thread: Hotplug thread descriptor + * + * Creates and starts the threads on all online cpus. + */ +int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread) +{ + unsigned int cpu; + int ret = 0; + + mutex_lock(&smpboot_threads_lock); + for_each_online_cpu(cpu) { + ret = __smpboot_create_thread(plug_thread, cpu); + if (ret) { + smpboot_destroy_threads(plug_thread); + goto out; + } + smpboot_unpark_thread(plug_thread, cpu); + } + list_add(&plug_thread->list, &hotplug_threads); +out: + mutex_unlock(&smpboot_threads_lock); + return ret; +} +EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread); + +/** + * smpboot_unregister_percpu_thread - Unregister a per_cpu thread related to hotplug + * @plug_thread: Hotplug thread descriptor + * + * Stops all threads on all possible cpus. + */ +void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread) +{ + get_online_cpus(); + mutex_lock(&smpboot_threads_lock); + list_del(&plug_thread->list); + smpboot_destroy_threads(plug_thread); + mutex_unlock(&smpboot_threads_lock); + put_online_cpus(); +} +EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread); diff --git a/kernel/smpboot.h b/kernel/smpboot.h index 6ef9433e1c70..72415a0eb955 100644 --- a/kernel/smpboot.h +++ b/kernel/smpboot.h @@ -13,4 +13,8 @@ static inline void idle_thread_set_boot_cpu(void) { } static inline void idle_threads_init(void) { } #endif +int smpboot_create_threads(unsigned int cpu); +void smpboot_park_threads(unsigned int cpu); +void smpboot_unpark_threads(unsigned int cpu); + #endif diff --git a/kernel/softirq.c b/kernel/softirq.c index b73e681df09e..cc96bdc0c2c9 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -23,6 +23,7 @@ #include <linux/rcupdate.h> #include <linux/ftrace.h> #include <linux/smp.h> +#include <linux/smpboot.h> #include <linux/tick.h> #define CREATE_TRACE_POINTS @@ -220,7 +221,7 @@ asmlinkage void __do_softirq(void) current->flags &= ~PF_MEMALLOC; pending = local_softirq_pending(); - account_system_vtime(current); + vtime_account(current); __local_bh_disable((unsigned long)__builtin_return_address(0), SOFTIRQ_OFFSET); @@ -271,7 +272,7 @@ restart: lockdep_softirq_exit(); - account_system_vtime(current); + vtime_account(current); __local_bh_enable(SOFTIRQ_OFFSET); tsk_restore_flags(current, old_flags, PF_MEMALLOC); } @@ -340,7 +341,7 @@ static inline void invoke_softirq(void) */ void irq_exit(void) { - account_system_vtime(current); + vtime_account(current); trace_hardirq_exit(); sub_preempt_count(IRQ_EXIT_OFFSET); if (!in_interrupt() && local_softirq_pending()) @@ -742,49 +743,22 @@ void __init softirq_init(void) open_softirq(HI_SOFTIRQ, tasklet_hi_action); } -static int run_ksoftirqd(void * __bind_cpu) +static int ksoftirqd_should_run(unsigned int cpu) { - set_current_state(TASK_INTERRUPTIBLE); - - while (!kthread_should_stop()) { - preempt_disable(); - if (!local_softirq_pending()) { - schedule_preempt_disabled(); - } - - __set_current_state(TASK_RUNNING); - - while (local_softirq_pending()) { - /* Preempt disable stops cpu going offline. - If already offline, we'll be on wrong CPU: - don't process */ - if (cpu_is_offline((long)__bind_cpu)) - goto wait_to_die; - local_irq_disable(); - if (local_softirq_pending()) - __do_softirq(); - local_irq_enable(); - sched_preempt_enable_no_resched(); - cond_resched(); - preempt_disable(); - rcu_note_context_switch((long)__bind_cpu); - } - preempt_enable(); - set_current_state(TASK_INTERRUPTIBLE); - } - __set_current_state(TASK_RUNNING); - return 0; + return local_softirq_pending(); +} -wait_to_die: - preempt_enable(); - /* Wait for kthread_stop */ - set_current_state(TASK_INTERRUPTIBLE); - while (!kthread_should_stop()) { - schedule(); - set_current_state(TASK_INTERRUPTIBLE); +static void run_ksoftirqd(unsigned int cpu) +{ + local_irq_disable(); + if (local_softirq_pending()) { + __do_softirq(); + rcu_note_context_switch(cpu); + local_irq_enable(); + cond_resched(); + return; } - __set_current_state(TASK_RUNNING); - return 0; + local_irq_enable(); } #ifdef CONFIG_HOTPLUG_CPU @@ -850,50 +824,14 @@ static int __cpuinit cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { - int hotcpu = (unsigned long)hcpu; - struct task_struct *p; - switch (action) { - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: - p = kthread_create_on_node(run_ksoftirqd, - hcpu, - cpu_to_node(hotcpu), - "ksoftirqd/%d", hotcpu); - if (IS_ERR(p)) { - printk("ksoftirqd for %i failed\n", hotcpu); - return notifier_from_errno(PTR_ERR(p)); - } - kthread_bind(p, hotcpu); - per_cpu(ksoftirqd, hotcpu) = p; - break; - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - wake_up_process(per_cpu(ksoftirqd, hotcpu)); - break; #ifdef CONFIG_HOTPLUG_CPU - case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: - if (!per_cpu(ksoftirqd, hotcpu)) - break; - /* Unbind so it can run. Fall thru. */ - kthread_bind(per_cpu(ksoftirqd, hotcpu), - cpumask_any(cpu_online_mask)); case CPU_DEAD: - case CPU_DEAD_FROZEN: { - static const struct sched_param param = { - .sched_priority = MAX_RT_PRIO-1 - }; - - p = per_cpu(ksoftirqd, hotcpu); - per_cpu(ksoftirqd, hotcpu) = NULL; - sched_setscheduler_nocheck(p, SCHED_FIFO, ¶m); - kthread_stop(p); - takeover_tasklets(hotcpu); + case CPU_DEAD_FROZEN: + takeover_tasklets((unsigned long)hcpu); break; - } #endif /* CONFIG_HOTPLUG_CPU */ - } + } return NOTIFY_OK; } @@ -901,14 +839,19 @@ static struct notifier_block __cpuinitdata cpu_nfb = { .notifier_call = cpu_callback }; +static struct smp_hotplug_thread softirq_threads = { + .store = &ksoftirqd, + .thread_should_run = ksoftirqd_should_run, + .thread_fn = run_ksoftirqd, + .thread_comm = "ksoftirqd/%u", +}; + static __init int spawn_ksoftirqd(void) { - void *cpu = (void *)(long)smp_processor_id(); - int err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu); - - BUG_ON(err != NOTIFY_OK); - cpu_callback(&cpu_nfb, CPU_ONLINE, cpu); register_cpu_notifier(&cpu_nfb); + + BUG_ON(smpboot_register_percpu_thread(&softirq_threads)); + return 0; } early_initcall(spawn_ksoftirqd); diff --git a/kernel/srcu.c b/kernel/srcu.c index 2095be3318d5..97c465ebd844 100644 --- a/kernel/srcu.c +++ b/kernel/srcu.c @@ -379,7 +379,7 @@ void call_srcu(struct srcu_struct *sp, struct rcu_head *head, rcu_batch_queue(&sp->batch_queue, head); if (!sp->running) { sp->running = true; - queue_delayed_work(system_nrt_wq, &sp->work, 0); + schedule_delayed_work(&sp->work, 0); } spin_unlock_irqrestore(&sp->queue_lock, flags); } @@ -631,7 +631,7 @@ static void srcu_reschedule(struct srcu_struct *sp) } if (pending) - queue_delayed_work(system_nrt_wq, &sp->work, SRCU_INTERVAL); + schedule_delayed_work(&sp->work, SRCU_INTERVAL); } /* diff --git a/kernel/sys.c b/kernel/sys.c index 241507f23eca..e6e0ece5f6a0 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -368,6 +368,7 @@ EXPORT_SYMBOL(unregister_reboot_notifier); void kernel_restart(char *cmd) { kernel_restart_prepare(cmd); + disable_nonboot_cpus(); if (!cmd) printk(KERN_EMERG "Restarting system.\n"); else @@ -1264,15 +1265,16 @@ DECLARE_RWSEM(uts_sem); * Work around broken programs that cannot handle "Linux 3.0". * Instead we map 3.x to 2.6.40+x, so e.g. 3.0 would be 2.6.40 */ -static int override_release(char __user *release, int len) +static int override_release(char __user *release, size_t len) { int ret = 0; - char buf[65]; if (current->personality & UNAME26) { - char *rest = UTS_RELEASE; + const char *rest = UTS_RELEASE; + char buf[65] = { 0 }; int ndots = 0; unsigned v; + size_t copy; while (*rest) { if (*rest == '.' && ++ndots >= 3) @@ -1282,8 +1284,9 @@ static int override_release(char __user *release, int len) rest++; } v = ((LINUX_VERSION_CODE >> 8) & 0xff) + 40; - snprintf(buf, len, "2.6.%u%s", v, rest); - ret = copy_to_user(release, buf, len); + copy = clamp_t(size_t, len, 1, sizeof(buf)); + copy = scnprintf(buf, copy, "2.6.%u%s", v, rest); + ret = copy_to_user(release, buf, copy + 1); } return ret; } @@ -1788,15 +1791,15 @@ SYSCALL_DEFINE1(umask, int, mask) #ifdef CONFIG_CHECKPOINT_RESTORE static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd) { - struct file *exe_file; + struct fd exe; struct dentry *dentry; int err; - exe_file = fget(fd); - if (!exe_file) + exe = fdget(fd); + if (!exe.file) return -EBADF; - dentry = exe_file->f_path.dentry; + dentry = exe.file->f_path.dentry; /* * Because the original mm->exe_file points to executable file, make @@ -1805,7 +1808,7 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd) */ err = -EACCES; if (!S_ISREG(dentry->d_inode->i_mode) || - exe_file->f_path.mnt->mnt_flags & MNT_NOEXEC) + exe.file->f_path.mnt->mnt_flags & MNT_NOEXEC) goto exit; err = inode_permission(dentry->d_inode, MAY_EXEC); @@ -1839,12 +1842,12 @@ static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd) goto exit_unlock; err = 0; - set_mm_exe_file(mm, exe_file); + set_mm_exe_file(mm, exe.file); /* this grabs a reference to exe.file */ exit_unlock: up_write(&mm->mmap_sem); exit: - fput(exe_file); + fdput(exe); return err; } @@ -2204,7 +2207,7 @@ static int __orderly_poweroff(void) return -ENOMEM; } - ret = call_usermodehelper_fns(argv[0], argv, envp, UMH_NO_WAIT, + ret = call_usermodehelper_fns(argv[0], argv, envp, UMH_WAIT_EXEC, NULL, argv_cleanup, NULL); if (ret == -ENOMEM) argv_free(argv); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 87174ef59161..26f65eaa01f9 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -97,10 +97,12 @@ extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; extern int max_threads; -extern int core_uses_pid; extern int suid_dumpable; +#ifdef CONFIG_COREDUMP +extern int core_uses_pid; extern char core_pattern[]; extern unsigned int core_pipe_limit; +#endif extern int pid_max; extern int min_free_kbytes; extern int pid_max_min, pid_max_max; @@ -177,8 +179,10 @@ static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write, static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); +#ifdef CONFIG_COREDUMP static int proc_dostring_coredump(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); +#endif #ifdef CONFIG_MAGIC_SYSRQ /* Note: sysrq code uses it's own private copy */ @@ -307,7 +311,7 @@ static struct ctl_table kern_table[] = { .extra2 = &max_sched_tunable_scaling, }, { - .procname = "sched_migration_cost", + .procname = "sched_migration_cost_ns", .data = &sysctl_sched_migration_cost, .maxlen = sizeof(unsigned int), .mode = 0644, @@ -321,14 +325,14 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dointvec, }, { - .procname = "sched_time_avg", + .procname = "sched_time_avg_ms", .data = &sysctl_sched_time_avg, .maxlen = sizeof(unsigned int), .mode = 0644, .proc_handler = proc_dointvec, }, { - .procname = "sched_shares_window", + .procname = "sched_shares_window_ns", .data = &sysctl_sched_shares_window, .maxlen = sizeof(unsigned int), .mode = 0644, @@ -404,6 +408,7 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, +#ifdef CONFIG_COREDUMP { .procname = "core_uses_pid", .data = &core_uses_pid, @@ -425,6 +430,7 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, +#endif #ifdef CONFIG_PROC_SYSCTL { .procname = "tainted", @@ -1543,8 +1549,7 @@ static struct ctl_table fs_table[] = { }; static struct ctl_table debug_table[] = { -#if defined(CONFIG_X86) || defined(CONFIG_PPC) || defined(CONFIG_SPARC) || \ - defined(CONFIG_S390) || defined(CONFIG_TILE) +#ifdef CONFIG_SYSCTL_EXCEPTION_TRACE { .procname = "exception-trace", .data = &show_unhandled_signals, @@ -2036,12 +2041,14 @@ int proc_dointvec_minmax(struct ctl_table *table, int write, static void validate_coredump_safety(void) { +#ifdef CONFIG_COREDUMP if (suid_dumpable == SUID_DUMPABLE_SAFE && core_pattern[0] != '/' && core_pattern[0] != '|') { printk(KERN_WARNING "Unsafe core_pattern used with "\ "suid_dumpable=2. Pipe handler or fully qualified "\ "core dump path required.\n"); } +#endif } static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write, @@ -2053,6 +2060,7 @@ static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write, return error; } +#ifdef CONFIG_COREDUMP static int proc_dostring_coredump(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -2061,6 +2069,7 @@ static int proc_dostring_coredump(struct ctl_table *table, int write, validate_coredump_safety(); return error; } +#endif static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int write, void __user *buffer, diff --git a/kernel/task_work.c b/kernel/task_work.c index d320d44903bd..65bd3c92d6f3 100644 --- a/kernel/task_work.c +++ b/kernel/task_work.c @@ -2,26 +2,20 @@ #include <linux/task_work.h> #include <linux/tracehook.h> +static struct callback_head work_exited; /* all we need is ->next == NULL */ + int -task_work_add(struct task_struct *task, struct callback_head *twork, bool notify) +task_work_add(struct task_struct *task, struct callback_head *work, bool notify) { - struct callback_head *last, *first; - unsigned long flags; + struct callback_head *head; - /* - * Not inserting the new work if the task has already passed - * exit_task_work() is the responisbility of callers. - */ - raw_spin_lock_irqsave(&task->pi_lock, flags); - last = task->task_works; - first = last ? last->next : twork; - twork->next = first; - if (last) - last->next = twork; - task->task_works = twork; - raw_spin_unlock_irqrestore(&task->pi_lock, flags); + do { + head = ACCESS_ONCE(task->task_works); + if (unlikely(head == &work_exited)) + return -ESRCH; + work->next = head; + } while (cmpxchg(&task->task_works, head, work) != head); - /* test_and_set_bit() implies mb(), see tracehook_notify_resume(). */ if (notify) set_notify_resume(task); return 0; @@ -30,52 +24,69 @@ task_work_add(struct task_struct *task, struct callback_head *twork, bool notify struct callback_head * task_work_cancel(struct task_struct *task, task_work_func_t func) { + struct callback_head **pprev = &task->task_works; + struct callback_head *work = NULL; unsigned long flags; - struct callback_head *last, *res = NULL; - + /* + * If cmpxchg() fails we continue without updating pprev. + * Either we raced with task_work_add() which added the + * new entry before this work, we will find it again. Or + * we raced with task_work_run(), *pprev == NULL/exited. + */ raw_spin_lock_irqsave(&task->pi_lock, flags); - last = task->task_works; - if (last) { - struct callback_head *q = last, *p = q->next; - while (1) { - if (p->func == func) { - q->next = p->next; - if (p == last) - task->task_works = q == p ? NULL : q; - res = p; - break; - } - if (p == last) - break; - q = p; - p = q->next; - } + while ((work = ACCESS_ONCE(*pprev))) { + read_barrier_depends(); + if (work->func != func) + pprev = &work->next; + else if (cmpxchg(pprev, work, work->next) == work) + break; } raw_spin_unlock_irqrestore(&task->pi_lock, flags); - return res; + + return work; } void task_work_run(void) { struct task_struct *task = current; - struct callback_head *p, *q; + struct callback_head *work, *head, *next; + + for (;;) { + /* + * work->func() can do task_work_add(), do not set + * work_exited unless the list is empty. + */ + do { + work = ACCESS_ONCE(task->task_works); + head = !work && (task->flags & PF_EXITING) ? + &work_exited : NULL; + } while (cmpxchg(&task->task_works, work, head) != work); - while (1) { - raw_spin_lock_irq(&task->pi_lock); - p = task->task_works; - task->task_works = NULL; - raw_spin_unlock_irq(&task->pi_lock); + if (!work) + break; + /* + * Synchronize with task_work_cancel(). It can't remove + * the first entry == work, cmpxchg(task_works) should + * fail, but it can play with *work and other entries. + */ + raw_spin_unlock_wait(&task->pi_lock); + smp_mb(); - if (unlikely(!p)) - return; + /* Reverse the list to run the works in fifo order */ + head = NULL; + do { + next = work->next; + work->next = head; + head = work; + work = next; + } while (work); - q = p->next; /* head */ - p->next = NULL; /* cut it */ - while (q) { - p = q->next; - q->func(q); - q = p; + work = head; + do { + next = work->next; + work->func(work); + work = next; cond_resched(); - } + } while (work); } } diff --git a/kernel/taskstats.c b/kernel/taskstats.c index d0a32796550f..145bb4d3bd4d 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -27,6 +27,7 @@ #include <linux/cgroup.h> #include <linux/fs.h> #include <linux/file.h> +#include <linux/pid_namespace.h> #include <net/genetlink.h> #include <linux/atomic.h> @@ -174,7 +175,9 @@ static void send_cpu_listeners(struct sk_buff *skb, up_write(&listeners->sem); } -static void fill_stats(struct task_struct *tsk, struct taskstats *stats) +static void fill_stats(struct user_namespace *user_ns, + struct pid_namespace *pid_ns, + struct task_struct *tsk, struct taskstats *stats) { memset(stats, 0, sizeof(*stats)); /* @@ -190,7 +193,7 @@ static void fill_stats(struct task_struct *tsk, struct taskstats *stats) stats->version = TASKSTATS_VERSION; stats->nvcsw = tsk->nvcsw; stats->nivcsw = tsk->nivcsw; - bacct_add_tsk(stats, tsk); + bacct_add_tsk(user_ns, pid_ns, stats, tsk); /* fill in extended acct fields */ xacct_add_tsk(stats, tsk); @@ -207,7 +210,7 @@ static int fill_stats_for_pid(pid_t pid, struct taskstats *stats) rcu_read_unlock(); if (!tsk) return -ESRCH; - fill_stats(tsk, stats); + fill_stats(current_user_ns(), task_active_pid_ns(current), tsk, stats); put_task_struct(tsk); return 0; } @@ -291,6 +294,12 @@ static int add_del_listener(pid_t pid, const struct cpumask *mask, int isadd) if (!cpumask_subset(mask, cpu_possible_mask)) return -EINVAL; + if (current_user_ns() != &init_user_ns) + return -EINVAL; + + if (task_active_pid_ns(current) != &init_pid_ns) + return -EINVAL; + if (isadd == REGISTER) { for_each_cpu(cpu, mask) { s = kmalloc_node(sizeof(struct listener), @@ -415,16 +424,15 @@ static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info) struct nlattr *na; size_t size; u32 fd; - struct file *file; - int fput_needed; + struct fd f; na = info->attrs[CGROUPSTATS_CMD_ATTR_FD]; if (!na) return -EINVAL; fd = nla_get_u32(info->attrs[CGROUPSTATS_CMD_ATTR_FD]); - file = fget_light(fd, &fput_needed); - if (!file) + f = fdget(fd); + if (!f.file) return 0; size = nla_total_size(sizeof(struct cgroupstats)); @@ -437,6 +445,7 @@ static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info) na = nla_reserve(rep_skb, CGROUPSTATS_TYPE_CGROUP_STATS, sizeof(struct cgroupstats)); if (na == NULL) { + nlmsg_free(rep_skb); rc = -EMSGSIZE; goto err; } @@ -444,7 +453,7 @@ static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info) stats = nla_data(na); memset(stats, 0, sizeof(*stats)); - rc = cgroupstats_build(stats, file->f_dentry); + rc = cgroupstats_build(stats, f.file->f_dentry); if (rc < 0) { nlmsg_free(rep_skb); goto err; @@ -453,7 +462,7 @@ static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info) rc = send_reply(rep_skb, info); err: - fput_light(file, fput_needed); + fdput(f); return rc; } @@ -467,7 +476,7 @@ static int cmd_attr_register_cpumask(struct genl_info *info) rc = parse(info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK], mask); if (rc < 0) goto out; - rc = add_del_listener(info->snd_pid, mask, REGISTER); + rc = add_del_listener(info->snd_portid, mask, REGISTER); out: free_cpumask_var(mask); return rc; @@ -483,7 +492,7 @@ static int cmd_attr_deregister_cpumask(struct genl_info *info) rc = parse(info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK], mask); if (rc < 0) goto out; - rc = add_del_listener(info->snd_pid, mask, DEREGISTER); + rc = add_del_listener(info->snd_portid, mask, DEREGISTER); out: free_cpumask_var(mask); return rc; @@ -631,11 +640,12 @@ void taskstats_exit(struct task_struct *tsk, int group_dead) if (rc < 0) return; - stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, tsk->pid); + stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, + task_pid_nr_ns(tsk, &init_pid_ns)); if (!stats) goto err; - fill_stats(tsk, stats); + fill_stats(&init_user_ns, &init_pid_ns, tsk, stats); /* * Doesn't matter if tsk is the leader or the last group member leaving @@ -643,7 +653,8 @@ void taskstats_exit(struct task_struct *tsk, int group_dead) if (!is_thread_group || !group_dead) goto send; - stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, tsk->tgid); + stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, + task_tgid_nr_ns(tsk, &init_pid_ns)); if (!stats) goto err; diff --git a/kernel/time.c b/kernel/time.c index ba744cf80696..d226c6a3fd28 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -30,7 +30,7 @@ #include <linux/export.h> #include <linux/timex.h> #include <linux/capability.h> -#include <linux/clocksource.h> +#include <linux/timekeeper_internal.h> #include <linux/errno.h> #include <linux/syscalls.h> #include <linux/security.h> diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index fd42bd452b75..8601f0db1261 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -16,6 +16,10 @@ config ARCH_CLOCKSOURCE_DATA config GENERIC_TIME_VSYSCALL bool +# Timekeeping vsyscall support +config GENERIC_TIME_VSYSCALL_OLD + bool + # ktime_t scalar 64bit nsec representation config KTIME_SCALAR bool diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index aa27d391bfc8..f11d83b12949 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -37,7 +37,6 @@ static struct alarm_base { spinlock_t lock; struct timerqueue_head timerqueue; - struct hrtimer timer; ktime_t (*gettime)(void); clockid_t base_clockid; } alarm_bases[ALARM_NUMTYPE]; @@ -46,6 +45,8 @@ static struct alarm_base { static ktime_t freezer_delta; static DEFINE_SPINLOCK(freezer_delta_lock); +static struct wakeup_source *ws; + #ifdef CONFIG_RTC_CLASS /* rtc timer and device for setting alarm wakeups at suspend */ static struct rtc_timer rtctimer; @@ -130,50 +131,35 @@ static inline void alarmtimer_rtc_timer_init(void) { } * @base: pointer to the base where the timer is being run * @alarm: pointer to alarm being enqueued. * - * Adds alarm to a alarm_base timerqueue and if necessary sets - * an hrtimer to run. + * Adds alarm to a alarm_base timerqueue * * Must hold base->lock when calling. */ static void alarmtimer_enqueue(struct alarm_base *base, struct alarm *alarm) { + if (alarm->state & ALARMTIMER_STATE_ENQUEUED) + timerqueue_del(&base->timerqueue, &alarm->node); + timerqueue_add(&base->timerqueue, &alarm->node); alarm->state |= ALARMTIMER_STATE_ENQUEUED; - - if (&alarm->node == timerqueue_getnext(&base->timerqueue)) { - hrtimer_try_to_cancel(&base->timer); - hrtimer_start(&base->timer, alarm->node.expires, - HRTIMER_MODE_ABS); - } } /** - * alarmtimer_remove - Removes an alarm timer from an alarm_base timerqueue + * alarmtimer_dequeue - Removes an alarm timer from an alarm_base timerqueue * @base: pointer to the base where the timer is running * @alarm: pointer to alarm being removed * - * Removes alarm to a alarm_base timerqueue and if necessary sets - * a new timer to run. + * Removes alarm to a alarm_base timerqueue * * Must hold base->lock when calling. */ -static void alarmtimer_remove(struct alarm_base *base, struct alarm *alarm) +static void alarmtimer_dequeue(struct alarm_base *base, struct alarm *alarm) { - struct timerqueue_node *next = timerqueue_getnext(&base->timerqueue); - if (!(alarm->state & ALARMTIMER_STATE_ENQUEUED)) return; timerqueue_del(&base->timerqueue, &alarm->node); alarm->state &= ~ALARMTIMER_STATE_ENQUEUED; - - if (next == &alarm->node) { - hrtimer_try_to_cancel(&base->timer); - next = timerqueue_getnext(&base->timerqueue); - if (!next) - return; - hrtimer_start(&base->timer, next->expires, HRTIMER_MODE_ABS); - } } @@ -188,42 +174,23 @@ static void alarmtimer_remove(struct alarm_base *base, struct alarm *alarm) */ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer) { - struct alarm_base *base = container_of(timer, struct alarm_base, timer); - struct timerqueue_node *next; + struct alarm *alarm = container_of(timer, struct alarm, timer); + struct alarm_base *base = &alarm_bases[alarm->type]; unsigned long flags; - ktime_t now; int ret = HRTIMER_NORESTART; int restart = ALARMTIMER_NORESTART; spin_lock_irqsave(&base->lock, flags); - now = base->gettime(); - while ((next = timerqueue_getnext(&base->timerqueue))) { - struct alarm *alarm; - ktime_t expired = next->expires; - - if (expired.tv64 > now.tv64) - break; - - alarm = container_of(next, struct alarm, node); - - timerqueue_del(&base->timerqueue, &alarm->node); - alarm->state &= ~ALARMTIMER_STATE_ENQUEUED; - - alarm->state |= ALARMTIMER_STATE_CALLBACK; - spin_unlock_irqrestore(&base->lock, flags); - if (alarm->function) - restart = alarm->function(alarm, now); - spin_lock_irqsave(&base->lock, flags); - alarm->state &= ~ALARMTIMER_STATE_CALLBACK; + alarmtimer_dequeue(base, alarm); + spin_unlock_irqrestore(&base->lock, flags); - if (restart != ALARMTIMER_NORESTART) { - timerqueue_add(&base->timerqueue, &alarm->node); - alarm->state |= ALARMTIMER_STATE_ENQUEUED; - } - } + if (alarm->function) + restart = alarm->function(alarm, base->gettime()); - if (next) { - hrtimer_set_expires(&base->timer, next->expires); + spin_lock_irqsave(&base->lock, flags); + if (restart != ALARMTIMER_NORESTART) { + hrtimer_set_expires(&alarm->timer, alarm->node.expires); + alarmtimer_enqueue(base, alarm); ret = HRTIMER_RESTART; } spin_unlock_irqrestore(&base->lock, flags); @@ -250,6 +217,7 @@ static int alarmtimer_suspend(struct device *dev) unsigned long flags; struct rtc_device *rtc; int i; + int ret; spin_lock_irqsave(&freezer_delta_lock, flags); min = freezer_delta; @@ -279,8 +247,10 @@ static int alarmtimer_suspend(struct device *dev) if (min.tv64 == 0) return 0; - /* XXX - Should we enforce a minimum sleep time? */ - WARN_ON(min.tv64 < NSEC_PER_SEC); + if (ktime_to_ns(min) < 2 * NSEC_PER_SEC) { + __pm_wakeup_event(ws, 2 * MSEC_PER_SEC); + return -EBUSY; + } /* Setup an rtc timer to fire that far in the future */ rtc_timer_cancel(rtc, &rtctimer); @@ -288,9 +258,11 @@ static int alarmtimer_suspend(struct device *dev) now = rtc_tm_to_ktime(tm); now = ktime_add(now, min); - rtc_timer_start(rtc, &rtctimer, now, ktime_set(0, 0)); - - return 0; + /* Set alarm, if in the past reject suspend briefly to handle */ + ret = rtc_timer_start(rtc, &rtctimer, now, ktime_set(0, 0)); + if (ret < 0) + __pm_wakeup_event(ws, MSEC_PER_SEC); + return ret; } #else static int alarmtimer_suspend(struct device *dev) @@ -324,6 +296,9 @@ void alarm_init(struct alarm *alarm, enum alarmtimer_type type, enum alarmtimer_restart (*function)(struct alarm *, ktime_t)) { timerqueue_init(&alarm->node); + hrtimer_init(&alarm->timer, alarm_bases[type].base_clockid, + HRTIMER_MODE_ABS); + alarm->timer.function = alarmtimer_fired; alarm->function = function; alarm->type = type; alarm->state = ALARMTIMER_STATE_INACTIVE; @@ -334,17 +309,19 @@ void alarm_init(struct alarm *alarm, enum alarmtimer_type type, * @alarm: ptr to alarm to set * @start: time to run the alarm */ -void alarm_start(struct alarm *alarm, ktime_t start) +int alarm_start(struct alarm *alarm, ktime_t start) { struct alarm_base *base = &alarm_bases[alarm->type]; unsigned long flags; + int ret; spin_lock_irqsave(&base->lock, flags); - if (alarmtimer_active(alarm)) - alarmtimer_remove(base, alarm); alarm->node.expires = start; alarmtimer_enqueue(base, alarm); + ret = hrtimer_start(&alarm->timer, alarm->node.expires, + HRTIMER_MODE_ABS); spin_unlock_irqrestore(&base->lock, flags); + return ret; } /** @@ -358,18 +335,12 @@ int alarm_try_to_cancel(struct alarm *alarm) { struct alarm_base *base = &alarm_bases[alarm->type]; unsigned long flags; - int ret = -1; - spin_lock_irqsave(&base->lock, flags); - - if (alarmtimer_callback_running(alarm)) - goto out; + int ret; - if (alarmtimer_is_queued(alarm)) { - alarmtimer_remove(base, alarm); - ret = 1; - } else - ret = 0; -out: + spin_lock_irqsave(&base->lock, flags); + ret = hrtimer_try_to_cancel(&alarm->timer); + if (ret >= 0) + alarmtimer_dequeue(base, alarm); spin_unlock_irqrestore(&base->lock, flags); return ret; } @@ -802,10 +773,6 @@ static int __init alarmtimer_init(void) for (i = 0; i < ALARM_NUMTYPE; i++) { timerqueue_init_head(&alarm_bases[i].timerqueue); spin_lock_init(&alarm_bases[i].lock); - hrtimer_init(&alarm_bases[i].timer, - alarm_bases[i].base_clockid, - HRTIMER_MODE_ABS); - alarm_bases[i].timer.function = alarmtimer_fired; } error = alarmtimer_rtc_interface_setup(); @@ -821,6 +788,7 @@ static int __init alarmtimer_init(void) error = PTR_ERR(pdev); goto out_drv; } + ws = wakeup_source_register("alarmtimer"); return 0; out_drv: diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 7e1ce012a851..30b6de0d977c 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -397,6 +397,30 @@ void clockevents_exchange_device(struct clock_event_device *old, local_irq_restore(flags); } +/** + * clockevents_suspend - suspend clock devices + */ +void clockevents_suspend(void) +{ + struct clock_event_device *dev; + + list_for_each_entry_reverse(dev, &clockevent_devices, list) + if (dev->suspend) + dev->suspend(dev); +} + +/** + * clockevents_resume - resume clock devices + */ +void clockevents_resume(void) +{ + struct clock_event_device *dev; + + list_for_each_entry(dev, &clockevent_devices, list) + if (dev->resume) + dev->resume(dev); +} + #ifdef CONFIG_GENERIC_CLOCKEVENTS /** * clockevents_notify - notification about relevant events diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index 46da0537c10b..6629bf7b5285 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -37,7 +37,7 @@ * requested HZ value. It is also not recommended * for "tick-less" systems. */ -#define NSEC_PER_JIFFY ((u32)((((u64)NSEC_PER_SEC)<<8)/SHIFTED_HZ)) +#define NSEC_PER_JIFFY ((NSEC_PER_SEC+HZ/2)/HZ) /* Since jiffies uses a simple NSEC_PER_JIFFY multiplier * conversion, the .shift value could be zero. However @@ -95,3 +95,33 @@ struct clocksource * __init __weak clocksource_default_clock(void) { return &clocksource_jiffies; } + +struct clocksource refined_jiffies; + +int register_refined_jiffies(long cycles_per_second) +{ + u64 nsec_per_tick, shift_hz; + long cycles_per_tick; + + + + refined_jiffies = clocksource_jiffies; + refined_jiffies.name = "refined-jiffies"; + refined_jiffies.rating++; + + /* Calc cycles per tick */ + cycles_per_tick = (cycles_per_second + HZ/2)/HZ; + /* shift_hz stores hz<<8 for extra accuracy */ + shift_hz = (u64)cycles_per_second << 8; + shift_hz += cycles_per_tick/2; + do_div(shift_hz, cycles_per_tick); + /* Calculate nsec_per_tick using shift_hz */ + nsec_per_tick = (u64)NSEC_PER_SEC << 8; + nsec_per_tick += (u32)shift_hz/2; + do_div(nsec_per_tick, (u32)shift_hz); + + refined_jiffies.mult = ((u32)nsec_per_tick) << JIFFIES_SHIFT; + + clocksource_register(&refined_jiffies); + return 0; +} diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 3a9e5d5c1091..a40260885265 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -372,7 +372,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, * the scheduler tick in nohz_restart_sched_tick. */ if (!ts->tick_stopped) { - select_nohz_load_balancer(1); + nohz_balance_enter_idle(cpu); calc_load_enter_idle(); ts->last_tick = hrtimer_get_expires(&ts->sched_timer); @@ -436,7 +436,8 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) if (unlikely(local_softirq_pending() && cpu_online(cpu))) { static int ratelimit; - if (ratelimit < 10) { + if (ratelimit < 10 && + (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) { printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", (unsigned int) local_softirq_pending()); ratelimit++; @@ -569,7 +570,6 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now) { /* Update jiffies first */ - select_nohz_load_balancer(0); tick_do_update_jiffies64(now); update_cpu_load_nohz(); @@ -835,7 +835,7 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer) */ if (ts->tick_stopped) { touch_softlockup_watchdog(); - if (idle_cpu(cpu)) + if (is_idle_task(current)) ts->idle_jiffies++; } update_process_times(user_mode(regs)); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index d3b91e75cecd..e424970bb562 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -8,6 +8,7 @@ * */ +#include <linux/timekeeper_internal.h> #include <linux/module.h> #include <linux/interrupt.h> #include <linux/percpu.h> @@ -21,61 +22,6 @@ #include <linux/tick.h> #include <linux/stop_machine.h> -/* Structure holding internal timekeeping values. */ -struct timekeeper { - /* Current clocksource used for timekeeping. */ - struct clocksource *clock; - /* NTP adjusted clock multiplier */ - u32 mult; - /* The shift value of the current clocksource. */ - u32 shift; - /* Number of clock cycles in one NTP interval. */ - cycle_t cycle_interval; - /* Number of clock shifted nano seconds in one NTP interval. */ - u64 xtime_interval; - /* shifted nano seconds left over when rounding cycle_interval */ - s64 xtime_remainder; - /* Raw nano seconds accumulated per NTP interval. */ - u32 raw_interval; - - /* Current CLOCK_REALTIME time in seconds */ - u64 xtime_sec; - /* Clock shifted nano seconds */ - u64 xtime_nsec; - - /* Difference between accumulated time and NTP time in ntp - * shifted nano seconds. */ - s64 ntp_error; - /* Shift conversion between clock shifted nano seconds and - * ntp shifted nano seconds. */ - u32 ntp_error_shift; - - /* - * wall_to_monotonic is what we need to add to xtime (or xtime corrected - * for sub jiffie times) to get to monotonic time. Monotonic is pegged - * at zero at system boot time, so wall_to_monotonic will be negative, - * however, we will ALWAYS keep the tv_nsec part positive so we can use - * the usual normalization. - * - * wall_to_monotonic is moved after resume from suspend for the - * monotonic time not to jump. We need to add total_sleep_time to - * wall_to_monotonic to get the real boot based time offset. - * - * - wall_to_monotonic is no longer the boot time, getboottime must be - * used instead. - */ - struct timespec wall_to_monotonic; - /* Offset clock monotonic -> clock realtime */ - ktime_t offs_real; - /* time spent in suspend */ - struct timespec total_sleep_time; - /* Offset clock monotonic -> clock boottime */ - ktime_t offs_boot; - /* The raw monotonic time for the CLOCK_MONOTONIC_RAW posix clock. */ - struct timespec raw_time; - /* Seqlock for all timekeeper values */ - seqlock_t lock; -}; static struct timekeeper timekeeper; @@ -96,15 +42,6 @@ static inline void tk_normalize_xtime(struct timekeeper *tk) } } -static struct timespec tk_xtime(struct timekeeper *tk) -{ - struct timespec ts; - - ts.tv_sec = tk->xtime_sec; - ts.tv_nsec = (long)(tk->xtime_nsec >> tk->shift); - return ts; -} - static void tk_set_xtime(struct timekeeper *tk, const struct timespec *ts) { tk->xtime_sec = ts->tv_sec; @@ -246,14 +183,11 @@ static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk) /* must hold write on timekeeper.lock */ static void timekeeping_update(struct timekeeper *tk, bool clearntp) { - struct timespec xt; - if (clearntp) { tk->ntp_error = 0; ntp_clear(); } - xt = tk_xtime(tk); - update_vsyscall(&xt, &tk->wall_to_monotonic, tk->clock, tk->mult); + update_vsyscall(tk); } /** @@ -776,6 +710,7 @@ static void timekeeping_resume(void) read_persistent_clock(&ts); + clockevents_resume(); clocksource_resume(); write_seqlock_irqsave(&tk->lock, flags); @@ -835,6 +770,7 @@ static int timekeeping_suspend(void) clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL); clocksource_suspend(); + clockevents_suspend(); return 0; } @@ -1111,7 +1047,7 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset, accumulate_nsecs_to_secs(tk); /* Accumulate raw time */ - raw_nsecs = tk->raw_interval << shift; + raw_nsecs = (u64)tk->raw_interval << shift; raw_nsecs += tk->raw_time.tv_nsec; if (raw_nsecs >= NSEC_PER_SEC) { u64 raw_secs = raw_nsecs; @@ -1128,6 +1064,33 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset, return offset; } +#ifdef CONFIG_GENERIC_TIME_VSYSCALL_OLD +static inline void old_vsyscall_fixup(struct timekeeper *tk) +{ + s64 remainder; + + /* + * Store only full nanoseconds into xtime_nsec after rounding + * it up and add the remainder to the error difference. + * XXX - This is necessary to avoid small 1ns inconsistnecies caused + * by truncating the remainder in vsyscalls. However, it causes + * additional work to be done in timekeeping_adjust(). Once + * the vsyscall implementations are converted to use xtime_nsec + * (shifted nanoseconds), and CONFIG_GENERIC_TIME_VSYSCALL_OLD + * users are removed, this can be killed. + */ + remainder = tk->xtime_nsec & ((1ULL << tk->shift) - 1); + tk->xtime_nsec -= remainder; + tk->xtime_nsec += 1ULL << tk->shift; + tk->ntp_error += remainder << tk->ntp_error_shift; + +} +#else +#define old_vsyscall_fixup(tk) +#endif + + + /** * update_wall_time - Uses the current clocksource to increment the wall time * @@ -1139,7 +1102,6 @@ static void update_wall_time(void) cycle_t offset; int shift = 0, maxshift; unsigned long flags; - s64 remainder; write_seqlock_irqsave(&tk->lock, flags); @@ -1181,20 +1143,11 @@ static void update_wall_time(void) /* correct the clock when NTP error is too big */ timekeeping_adjust(tk, offset); - /* - * Store only full nanoseconds into xtime_nsec after rounding - * it up and add the remainder to the error difference. - * XXX - This is necessary to avoid small 1ns inconsistnecies caused - * by truncating the remainder in vsyscalls. However, it causes - * additional work to be done in timekeeping_adjust(). Once - * the vsyscall implementations are converted to use xtime_nsec - * (shifted nanoseconds), this can be killed. - */ - remainder = tk->xtime_nsec & ((1ULL << tk->shift) - 1); - tk->xtime_nsec -= remainder; - tk->xtime_nsec += 1ULL << tk->shift; - tk->ntp_error += remainder << tk->ntp_error_shift; + * XXX This can be killed once everyone converts + * to the new update_vsyscall. + */ + old_vsyscall_fixup(tk); /* * Finally, make sure that after the rounding diff --git a/kernel/timer.c b/kernel/timer.c index 8c5e7b908c68..367d00858482 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -63,6 +63,7 @@ EXPORT_SYMBOL(jiffies_64); #define TVR_SIZE (1 << TVR_BITS) #define TVN_MASK (TVN_SIZE - 1) #define TVR_MASK (TVR_SIZE - 1) +#define MAX_TVAL ((unsigned long)((1ULL << (TVR_BITS + 4*TVN_BITS)) - 1)) struct tvec { struct list_head vec[TVN_SIZE]; @@ -92,24 +93,25 @@ static DEFINE_PER_CPU(struct tvec_base *, tvec_bases) = &boot_tvec_bases; /* Functions below help us manage 'deferrable' flag */ static inline unsigned int tbase_get_deferrable(struct tvec_base *base) { - return ((unsigned int)(unsigned long)base & TBASE_DEFERRABLE_FLAG); + return ((unsigned int)(unsigned long)base & TIMER_DEFERRABLE); } -static inline struct tvec_base *tbase_get_base(struct tvec_base *base) +static inline unsigned int tbase_get_irqsafe(struct tvec_base *base) { - return ((struct tvec_base *)((unsigned long)base & ~TBASE_DEFERRABLE_FLAG)); + return ((unsigned int)(unsigned long)base & TIMER_IRQSAFE); } -static inline void timer_set_deferrable(struct timer_list *timer) +static inline struct tvec_base *tbase_get_base(struct tvec_base *base) { - timer->base = TBASE_MAKE_DEFERRED(timer->base); + return ((struct tvec_base *)((unsigned long)base & ~TIMER_FLAG_MASK)); } static inline void timer_set_base(struct timer_list *timer, struct tvec_base *new_base) { - timer->base = (struct tvec_base *)((unsigned long)(new_base) | - tbase_get_deferrable(timer->base)); + unsigned long flags = (unsigned long)timer->base & TIMER_FLAG_MASK; + + timer->base = (struct tvec_base *)((unsigned long)(new_base) | flags); } static unsigned long round_jiffies_common(unsigned long j, int cpu, @@ -358,11 +360,12 @@ __internal_add_timer(struct tvec_base *base, struct timer_list *timer) vec = base->tv1.vec + (base->timer_jiffies & TVR_MASK); } else { int i; - /* If the timeout is larger than 0xffffffff on 64-bit - * architectures then we use the maximum timeout: + /* If the timeout is larger than MAX_TVAL (on 64-bit + * architectures or with CONFIG_BASE_SMALL=1) then we + * use the maximum timeout. */ - if (idx > 0xffffffffUL) { - idx = 0xffffffffUL; + if (idx > MAX_TVAL) { + idx = MAX_TVAL; expires = idx + base->timer_jiffies; } i = (expires >> (TVR_BITS + 3 * TVN_BITS)) & TVN_MASK; @@ -563,16 +566,14 @@ static inline void debug_timer_assert_init(struct timer_list *timer) debug_object_assert_init(timer, &timer_debug_descr); } -static void __init_timer(struct timer_list *timer, - const char *name, - struct lock_class_key *key); +static void do_init_timer(struct timer_list *timer, unsigned int flags, + const char *name, struct lock_class_key *key); -void init_timer_on_stack_key(struct timer_list *timer, - const char *name, - struct lock_class_key *key) +void init_timer_on_stack_key(struct timer_list *timer, unsigned int flags, + const char *name, struct lock_class_key *key) { debug_object_init_on_stack(timer, &timer_debug_descr); - __init_timer(timer, name, key); + do_init_timer(timer, flags, name, key); } EXPORT_SYMBOL_GPL(init_timer_on_stack_key); @@ -613,12 +614,13 @@ static inline void debug_assert_init(struct timer_list *timer) debug_timer_assert_init(timer); } -static void __init_timer(struct timer_list *timer, - const char *name, - struct lock_class_key *key) +static void do_init_timer(struct timer_list *timer, unsigned int flags, + const char *name, struct lock_class_key *key) { + struct tvec_base *base = __raw_get_cpu_var(tvec_bases); + timer->entry.next = NULL; - timer->base = __raw_get_cpu_var(tvec_bases); + timer->base = (void *)((unsigned long)base | flags); timer->slack = -1; #ifdef CONFIG_TIMER_STATS timer->start_site = NULL; @@ -628,22 +630,10 @@ 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 + * @flags: timer flags * @name: name of the timer * @key: lockdep class key of the fake lock used for tracking timer * sync lock dependencies @@ -651,24 +641,14 @@ EXPORT_SYMBOL_GPL(setup_deferrable_timer_on_stack_key); * init_timer_key() must be done to a timer prior calling *any* of the * other timer functions. */ -void init_timer_key(struct timer_list *timer, - const char *name, - struct lock_class_key *key) +void init_timer_key(struct timer_list *timer, unsigned int flags, + const char *name, struct lock_class_key *key) { debug_init(timer); - __init_timer(timer, name, key); + do_init_timer(timer, flags, name, key); } EXPORT_SYMBOL(init_timer_key); -void init_timer_deferrable_key(struct timer_list *timer, - const char *name, - struct lock_class_key *key) -{ - init_timer_key(timer, name, key); - timer_set_deferrable(timer); -} -EXPORT_SYMBOL(init_timer_deferrable_key); - static inline void detach_timer(struct timer_list *timer, bool clear_pending) { struct list_head *entry = &timer->entry; @@ -686,7 +666,7 @@ detach_expired_timer(struct timer_list *timer, struct tvec_base *base) { detach_timer(timer, true); if (!tbase_get_deferrable(timer->base)) - timer->base->active_timers--; + base->active_timers--; } static int detach_if_pending(struct timer_list *timer, struct tvec_base *base, @@ -697,7 +677,7 @@ static int detach_if_pending(struct timer_list *timer, struct tvec_base *base, detach_timer(timer, clear_pending); if (!tbase_get_deferrable(timer->base)) { - timer->base->active_timers--; + base->active_timers--; if (timer->expires == base->next_timer) base->next_timer = base->timer_jiffies; } @@ -1029,14 +1009,14 @@ EXPORT_SYMBOL(try_to_del_timer_sync); * * Synchronization rules: Callers must prevent restarting of the timer, * otherwise this function is meaningless. It must not be called from - * interrupt contexts. The caller must not hold locks which would prevent - * completion of the timer's handler. The timer's handler must not call - * add_timer_on(). Upon exit the timer is not queued and the handler is - * not running on any CPU. + * interrupt contexts unless the timer is an irqsafe one. The caller must + * not hold locks which would prevent completion of the timer's + * handler. The timer's handler must not call add_timer_on(). Upon exit the + * timer is not queued and the handler is not running on any CPU. * - * Note: You must not hold locks that are held in interrupt context - * while calling this function. Even if the lock has nothing to do - * with the timer in question. Here's why: + * Note: For !irqsafe timers, you must not hold locks that are held in + * interrupt context while calling this function. Even if the lock has + * nothing to do with the timer in question. Here's why: * * CPU0 CPU1 * ---- ---- @@ -1073,7 +1053,7 @@ int del_timer_sync(struct timer_list *timer) * don't use it in hardirq context, because it * could lead to deadlock. */ - WARN_ON(in_irq()); + WARN_ON(in_irq() && !tbase_get_irqsafe(timer->base)); for (;;) { int ret = try_to_del_timer_sync(timer); if (ret >= 0) @@ -1180,19 +1160,27 @@ static inline void __run_timers(struct tvec_base *base) while (!list_empty(head)) { void (*fn)(unsigned long); unsigned long data; + bool irqsafe; timer = list_first_entry(head, struct timer_list,entry); fn = timer->function; data = timer->data; + irqsafe = tbase_get_irqsafe(timer->base); timer_stats_account_timer(timer); base->running_timer = timer; detach_expired_timer(timer, base); - spin_unlock_irq(&base->lock); - call_timer_fn(timer, fn, data); - spin_lock_irq(&base->lock); + if (irqsafe) { + spin_unlock(&base->lock); + call_timer_fn(timer, fn, data); + spin_lock(&base->lock); + } else { + spin_unlock_irq(&base->lock); + call_timer_fn(timer, fn, data); + spin_lock_irq(&base->lock); + } } } base->running_timer = NULL; @@ -1791,9 +1779,13 @@ static struct notifier_block __cpuinitdata timers_nb = { void __init init_timers(void) { - int err = timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE, - (void *)(long)smp_processor_id()); + int err; + + /* ensure there are enough low bits for flags in timer->base pointer */ + BUILD_BUG_ON(__alignof__(struct tvec_base) & TIMER_FLAG_MASK); + err = timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE, + (void *)(long)smp_processor_id()); init_timer_stats(); BUG_ON(err != NOTIFY_OK); diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 8c4c07071cc5..4cea4f41c1d9 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -49,6 +49,11 @@ config HAVE_SYSCALL_TRACEPOINTS help See Documentation/trace/ftrace-design.txt +config HAVE_FENTRY + bool + help + Arch supports the gcc options -pg with -mfentry + config HAVE_C_RECORDMCOUNT bool help @@ -57,8 +62,12 @@ config HAVE_C_RECORDMCOUNT config TRACER_MAX_TRACE bool +config TRACE_CLOCK + bool + config RING_BUFFER bool + select TRACE_CLOCK config FTRACE_NMI_ENTER bool @@ -109,6 +118,7 @@ config TRACING select NOP_TRACER select BINARY_PRINTF select EVENT_TRACING + select TRACE_CLOCK config GENERIC_TRACER bool diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index b831087c8200..d7e2068e4b71 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -5,10 +5,12 @@ ifdef CONFIG_FUNCTION_TRACER ORIG_CFLAGS := $(KBUILD_CFLAGS) KBUILD_CFLAGS = $(subst -pg,,$(ORIG_CFLAGS)) +ifdef CONFIG_FTRACE_SELFTEST # selftest needs instrumentation CFLAGS_trace_selftest_dynamic.o = -pg obj-y += trace_selftest_dynamic.o endif +endif # If unlikely tracing is enabled, do not trace these files ifdef CONFIG_TRACING_BRANCHES @@ -17,11 +19,7 @@ endif CFLAGS_trace_events_filter.o := -I$(src) -# -# Make the trace clocks available generally: it's infrastructure -# relied on by ptrace for example: -# -obj-y += trace_clock.o +obj-$(CONFIG_TRACE_CLOCK) += trace_clock.o obj-$(CONFIG_FUNCTION_TRACER) += libftrace.o obj-$(CONFIG_RING_BUFFER) += ring_buffer.o diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index b4f20fba09fc..9dcf15d38380 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -64,12 +64,20 @@ #define FL_GLOBAL_CONTROL_MASK (FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_CONTROL) +static struct ftrace_ops ftrace_list_end __read_mostly = { + .func = ftrace_stub, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, +}; + /* ftrace_enabled is a method to turn ftrace on or off */ int ftrace_enabled __read_mostly; static int last_ftrace_enabled; /* Quick disabling of function tracer. */ -int function_trace_stop; +int function_trace_stop __read_mostly; + +/* Current function tracing op */ +struct ftrace_ops *function_trace_op __read_mostly = &ftrace_list_end; /* List for set_ftrace_pid's pids. */ LIST_HEAD(ftrace_pids); @@ -86,22 +94,43 @@ static int ftrace_disabled __read_mostly; static DEFINE_MUTEX(ftrace_lock); -static struct ftrace_ops ftrace_list_end __read_mostly = { - .func = ftrace_stub, -}; - static struct ftrace_ops *ftrace_global_list __read_mostly = &ftrace_list_end; static struct ftrace_ops *ftrace_control_list __read_mostly = &ftrace_list_end; static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end; ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; -static ftrace_func_t __ftrace_trace_function_delay __read_mostly = ftrace_stub; -ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub; ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub; static struct ftrace_ops global_ops; static struct ftrace_ops control_ops; -static void -ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip); +#if ARCH_SUPPORTS_FTRACE_OPS +static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs); +#else +/* See comment below, where ftrace_ops_list_func is defined */ +static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip); +#define ftrace_ops_list_func ((ftrace_func_t)ftrace_ops_no_ops) +#endif + +/** + * ftrace_nr_registered_ops - return number of ops registered + * + * Returns the number of ftrace_ops registered and tracing functions + */ +int ftrace_nr_registered_ops(void) +{ + struct ftrace_ops *ops; + int cnt = 0; + + mutex_lock(&ftrace_lock); + + for (ops = ftrace_ops_list; + ops != &ftrace_list_end; ops = ops->next) + cnt++; + + mutex_unlock(&ftrace_lock); + + return cnt; +} /* * Traverse the ftrace_global_list, invoking all entries. The reason that we @@ -112,29 +141,29 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip); * * Silly Alpha and silly pointer-speculation compiler optimizations! */ -static void ftrace_global_list_func(unsigned long ip, - unsigned long parent_ip) +static void +ftrace_global_list_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) { - struct ftrace_ops *op; - if (unlikely(trace_recursion_test(TRACE_GLOBAL_BIT))) return; trace_recursion_set(TRACE_GLOBAL_BIT); op = rcu_dereference_raw(ftrace_global_list); /*see above*/ while (op != &ftrace_list_end) { - op->func(ip, parent_ip); + op->func(ip, parent_ip, op, regs); op = rcu_dereference_raw(op->next); /*see above*/ }; trace_recursion_clear(TRACE_GLOBAL_BIT); } -static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip) +static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) { if (!test_tsk_trace_trace(current)) return; - ftrace_pid_function(ip, parent_ip); + ftrace_pid_function(ip, parent_ip, op, regs); } static void set_ftrace_pid_function(ftrace_func_t func) @@ -153,25 +182,9 @@ static void set_ftrace_pid_function(ftrace_func_t func) void clear_ftrace_function(void) { ftrace_trace_function = ftrace_stub; - __ftrace_trace_function = ftrace_stub; - __ftrace_trace_function_delay = ftrace_stub; ftrace_pid_function = ftrace_stub; } -#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST -/* - * For those archs that do not test ftrace_trace_stop in their - * mcount call site, we need to do it from C. - */ -static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip) -{ - if (function_trace_stop) - return; - - __ftrace_trace_function(ip, parent_ip); -} -#endif - static void control_ops_disable_all(struct ftrace_ops *ops) { int cpu; @@ -230,28 +243,27 @@ static void update_ftrace_function(void) /* * If we are at the end of the list and this ops is - * not dynamic, then have the mcount trampoline call - * the function directly + * recursion safe and not dynamic and the arch supports passing ops, + * then have the mcount trampoline call the function directly. */ if (ftrace_ops_list == &ftrace_list_end || (ftrace_ops_list->next == &ftrace_list_end && - !(ftrace_ops_list->flags & FTRACE_OPS_FL_DYNAMIC))) + !(ftrace_ops_list->flags & FTRACE_OPS_FL_DYNAMIC) && + (ftrace_ops_list->flags & FTRACE_OPS_FL_RECURSION_SAFE) && + !FTRACE_FORCE_LIST_FUNC)) { + /* Set the ftrace_ops that the arch callback uses */ + if (ftrace_ops_list == &global_ops) + function_trace_op = ftrace_global_list; + else + function_trace_op = ftrace_ops_list; func = ftrace_ops_list->func; - else + } else { + /* Just use the default ftrace_ops */ + function_trace_op = &ftrace_list_end; func = ftrace_ops_list_func; + } -#ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST ftrace_trace_function = func; -#else -#ifdef CONFIG_DYNAMIC_FTRACE - /* do not update till all functions have been modified */ - __ftrace_trace_function_delay = func; -#else - __ftrace_trace_function = func; -#endif - ftrace_trace_function = - (func == ftrace_stub) ? func : ftrace_test_stop_func; -#endif } static void add_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops) @@ -325,6 +337,20 @@ static int __register_ftrace_function(struct ftrace_ops *ops) if ((ops->flags & FL_GLOBAL_CONTROL_MASK) == FL_GLOBAL_CONTROL_MASK) return -EINVAL; +#ifndef ARCH_SUPPORTS_FTRACE_SAVE_REGS + /* + * If the ftrace_ops specifies SAVE_REGS, then it only can be used + * if the arch supports it, or SAVE_REGS_IF_SUPPORTED is also set. + * Setting SAVE_REGS_IF_SUPPORTED makes SAVE_REGS irrelevant. + */ + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS && + !(ops->flags & FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED)) + return -EINVAL; + + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED) + ops->flags |= FTRACE_OPS_FL_SAVE_REGS; +#endif + if (!core_kernel_data((unsigned long)ops)) ops->flags |= FTRACE_OPS_FL_DYNAMIC; @@ -773,7 +799,8 @@ ftrace_profile_alloc(struct ftrace_profile_stat *stat, unsigned long ip) } static void -function_profile_call(unsigned long ip, unsigned long parent_ip) +function_profile_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct pt_regs *regs) { struct ftrace_profile_stat *stat; struct ftrace_profile *rec; @@ -803,7 +830,7 @@ function_profile_call(unsigned long ip, unsigned long parent_ip) #ifdef CONFIG_FUNCTION_GRAPH_TRACER static int profile_graph_entry(struct ftrace_graph_ent *trace) { - function_profile_call(trace->func, 0); + function_profile_call(trace->func, 0, NULL, NULL); return 1; } @@ -863,6 +890,7 @@ static void unregister_ftrace_profiler(void) #else static struct ftrace_ops ftrace_profile_ops __read_mostly = { .func = function_profile_call, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static int register_ftrace_profiler(void) @@ -1045,6 +1073,7 @@ static struct ftrace_ops global_ops = { .func = ftrace_stub, .notrace_hash = EMPTY_HASH, .filter_hash = EMPTY_HASH, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static DEFINE_MUTEX(ftrace_regex_lock); @@ -1525,6 +1554,12 @@ static void __ftrace_hash_rec_update(struct ftrace_ops *ops, rec->flags++; if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == FTRACE_REF_MAX)) return; + /* + * If any ops wants regs saved for this function + * then all ops will get saved regs. + */ + if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) + rec->flags |= FTRACE_FL_REGS; } else { if (FTRACE_WARN_ON((rec->flags & ~FTRACE_FL_MASK) == 0)) return; @@ -1616,18 +1651,59 @@ static int ftrace_check_record(struct dyn_ftrace *rec, int enable, int update) if (enable && (rec->flags & ~FTRACE_FL_MASK)) flag = FTRACE_FL_ENABLED; + /* + * If enabling and the REGS flag does not match the REGS_EN, then + * do not ignore this record. Set flags to fail the compare against + * ENABLED. + */ + if (flag && + (!(rec->flags & FTRACE_FL_REGS) != !(rec->flags & FTRACE_FL_REGS_EN))) + flag |= FTRACE_FL_REGS; + /* If the state of this record hasn't changed, then do nothing */ if ((rec->flags & FTRACE_FL_ENABLED) == flag) return FTRACE_UPDATE_IGNORE; if (flag) { - if (update) + /* Save off if rec is being enabled (for return value) */ + flag ^= rec->flags & FTRACE_FL_ENABLED; + + if (update) { rec->flags |= FTRACE_FL_ENABLED; - return FTRACE_UPDATE_MAKE_CALL; + if (flag & FTRACE_FL_REGS) { + if (rec->flags & FTRACE_FL_REGS) + rec->flags |= FTRACE_FL_REGS_EN; + else + rec->flags &= ~FTRACE_FL_REGS_EN; + } + } + + /* + * If this record is being updated from a nop, then + * return UPDATE_MAKE_CALL. + * Otherwise, if the EN flag is set, then return + * UPDATE_MODIFY_CALL_REGS to tell the caller to convert + * from the non-save regs, to a save regs function. + * Otherwise, + * return UPDATE_MODIFY_CALL to tell the caller to convert + * from the save regs, to a non-save regs function. + */ + if (flag & FTRACE_FL_ENABLED) + return FTRACE_UPDATE_MAKE_CALL; + else if (rec->flags & FTRACE_FL_REGS_EN) + return FTRACE_UPDATE_MODIFY_CALL_REGS; + else + return FTRACE_UPDATE_MODIFY_CALL; } - if (update) - rec->flags &= ~FTRACE_FL_ENABLED; + if (update) { + /* If there's no more users, clear all flags */ + if (!(rec->flags & ~FTRACE_FL_MASK)) + rec->flags = 0; + else + /* Just disable the record (keep REGS state) */ + rec->flags &= ~FTRACE_FL_ENABLED; + } return FTRACE_UPDATE_MAKE_NOP; } @@ -1662,13 +1738,17 @@ int ftrace_test_record(struct dyn_ftrace *rec, int enable) static int __ftrace_replace_code(struct dyn_ftrace *rec, int enable) { + unsigned long ftrace_old_addr; unsigned long ftrace_addr; int ret; - ftrace_addr = (unsigned long)FTRACE_ADDR; - ret = ftrace_update_record(rec, enable); + if (rec->flags & FTRACE_FL_REGS) + ftrace_addr = (unsigned long)FTRACE_REGS_ADDR; + else + ftrace_addr = (unsigned long)FTRACE_ADDR; + switch (ret) { case FTRACE_UPDATE_IGNORE: return 0; @@ -1678,6 +1758,15 @@ __ftrace_replace_code(struct dyn_ftrace *rec, int enable) case FTRACE_UPDATE_MAKE_NOP: return ftrace_make_nop(NULL, rec, ftrace_addr); + + case FTRACE_UPDATE_MODIFY_CALL_REGS: + case FTRACE_UPDATE_MODIFY_CALL: + if (rec->flags & FTRACE_FL_REGS) + ftrace_old_addr = (unsigned long)FTRACE_ADDR; + else + ftrace_old_addr = (unsigned long)FTRACE_REGS_ADDR; + + return ftrace_modify_call(rec, ftrace_old_addr, ftrace_addr); } return -1; /* unknow ftrace bug */ @@ -1882,16 +1971,6 @@ static void ftrace_run_update_code(int command) */ arch_ftrace_update_code(command); -#ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST - /* - * For archs that call ftrace_test_stop_func(), we must - * wait till after we update all the function callers - * before we update the callback. This keeps different - * ops that record different functions from corrupting - * each other. - */ - __ftrace_trace_function = __ftrace_trace_function_delay; -#endif function_trace_stop--; ret = ftrace_arch_code_modify_post_process(); @@ -2441,8 +2520,9 @@ static int t_show(struct seq_file *m, void *v) seq_printf(m, "%ps", (void *)rec->ip); if (iter->flags & FTRACE_ITER_ENABLED) - seq_printf(m, " (%ld)", - rec->flags & ~FTRACE_FL_MASK); + seq_printf(m, " (%ld)%s", + rec->flags & ~FTRACE_FL_MASK, + rec->flags & FTRACE_FL_REGS ? " R" : ""); seq_printf(m, "\n"); return 0; @@ -2790,8 +2870,8 @@ static int __init ftrace_mod_cmd_init(void) } device_initcall(ftrace_mod_cmd_init); -static void -function_trace_probe_call(unsigned long ip, unsigned long parent_ip) +static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) { struct ftrace_func_probe *entry; struct hlist_head *hhd; @@ -3162,8 +3242,27 @@ ftrace_notrace_write(struct file *file, const char __user *ubuf, } static int -ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, - int reset, int enable) +ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove) +{ + struct ftrace_func_entry *entry; + + if (!ftrace_location(ip)) + return -EINVAL; + + if (remove) { + entry = ftrace_lookup_ip(hash, ip); + if (!entry) + return -ENOENT; + free_hash_entry(hash, entry); + return 0; + } + + return add_hash_entry(hash, ip); +} + +static int +ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len, + unsigned long ip, int remove, int reset, int enable) { struct ftrace_hash **orig_hash; struct ftrace_hash *hash; @@ -3192,6 +3291,11 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, ret = -EINVAL; goto out_regex_unlock; } + if (ip) { + ret = ftrace_match_addr(hash, ip, remove); + if (ret < 0) + goto out_regex_unlock; + } mutex_lock(&ftrace_lock); ret = ftrace_hash_move(ops, enable, orig_hash, hash); @@ -3208,6 +3312,37 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, return ret; } +static int +ftrace_set_addr(struct ftrace_ops *ops, unsigned long ip, int remove, + int reset, int enable) +{ + return ftrace_set_hash(ops, 0, 0, ip, remove, reset, enable); +} + +/** + * ftrace_set_filter_ip - set a function to filter on in ftrace by address + * @ops - the ops to set the filter with + * @ip - the address to add to or remove from the filter. + * @remove - non zero to remove the ip from the filter + * @reset - non zero to reset all filters before applying this filter. + * + * Filters denote which functions should be enabled when tracing is enabled + * If @ip is NULL, it failes to update filter. + */ +int ftrace_set_filter_ip(struct ftrace_ops *ops, unsigned long ip, + int remove, int reset) +{ + return ftrace_set_addr(ops, ip, remove, reset, 1); +} +EXPORT_SYMBOL_GPL(ftrace_set_filter_ip); + +static int +ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len, + int reset, int enable) +{ + return ftrace_set_hash(ops, buf, len, 0, 0, reset, enable); +} + /** * ftrace_set_filter - set a function to filter on in ftrace * @ops - the ops to set the filter with @@ -3912,6 +4047,7 @@ void __init ftrace_init(void) static struct ftrace_ops global_ops = { .func = ftrace_stub, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static int __init ftrace_nodyn_init(void) @@ -3942,10 +4078,9 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) #endif /* CONFIG_DYNAMIC_FTRACE */ static void -ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip) +ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) { - struct ftrace_ops *op; - if (unlikely(trace_recursion_test(TRACE_CONTROL_BIT))) return; @@ -3959,7 +4094,7 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip) while (op != &ftrace_list_end) { if (!ftrace_function_local_disabled(op) && ftrace_ops_test(op, ip)) - op->func(ip, parent_ip); + op->func(ip, parent_ip, op, regs); op = rcu_dereference_raw(op->next); }; @@ -3969,13 +4104,18 @@ ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops control_ops = { .func = ftrace_ops_control_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; -static void -ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip) +static inline void +__ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ignored, struct pt_regs *regs) { struct ftrace_ops *op; + if (function_trace_stop) + return; + if (unlikely(trace_recursion_test(TRACE_INTERNAL_BIT))) return; @@ -3988,13 +4128,39 @@ ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip) op = rcu_dereference_raw(ftrace_ops_list); while (op != &ftrace_list_end) { if (ftrace_ops_test(op, ip)) - op->func(ip, parent_ip); + op->func(ip, parent_ip, op, regs); op = rcu_dereference_raw(op->next); }; preempt_enable_notrace(); trace_recursion_clear(TRACE_INTERNAL_BIT); } +/* + * Some archs only support passing ip and parent_ip. Even though + * the list function ignores the op parameter, we do not want any + * C side effects, where a function is called without the caller + * sending a third parameter. + * Archs are to support both the regs and ftrace_ops at the same time. + * If they support ftrace_ops, it is assumed they support regs. + * If call backs want to use regs, they must either check for regs + * being NULL, or ARCH_SUPPORTS_FTRACE_SAVE_REGS. + * Note, ARCH_SUPPORT_SAVE_REGS expects a full regs to be saved. + * An architecture can pass partial regs with ftrace_ops and still + * set the ARCH_SUPPORT_FTARCE_OPS. + */ +#if ARCH_SUPPORTS_FTRACE_OPS +static void ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *regs) +{ + __ftrace_ops_list_func(ip, parent_ip, NULL, regs); +} +#else +static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip) +{ + __ftrace_ops_list_func(ip, parent_ip, NULL, NULL); +} +#endif + static void clear_ftrace_swapper(void) { struct task_struct *p; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 49491fa7daa2..b979426d16c6 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -1567,6 +1567,10 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size, put_online_cpus(); } else { + /* Make sure this CPU has been intitialized */ + if (!cpumask_test_cpu(cpu_id, buffer->cpumask)) + goto out; + cpu_buffer = buffer->buffers[cpu_id]; if (nr_pages == cpu_buffer->nr_pages) @@ -2816,7 +2820,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_enable); * to the buffer after this will fail and return NULL. * * This is different than ring_buffer_record_disable() as - * it works like an on/off switch, where as the disable() verison + * it works like an on/off switch, where as the disable() version * must be paired with a enable(). */ void ring_buffer_record_off(struct ring_buffer *buffer) @@ -2839,7 +2843,7 @@ EXPORT_SYMBOL_GPL(ring_buffer_record_off); * ring_buffer_record_off(). * * This is different than ring_buffer_record_enable() as - * it works like an on/off switch, where as the enable() verison + * it works like an on/off switch, where as the enable() version * must be paired with a disable(). */ void ring_buffer_record_on(struct ring_buffer *buffer) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 5c38c81496ce..31e4f55773f1 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -328,7 +328,7 @@ static DECLARE_WAIT_QUEUE_HEAD(trace_wait); unsigned long trace_flags = TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK | TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | TRACE_ITER_SLEEP_TIME | TRACE_ITER_GRAPH_TIME | TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE | - TRACE_ITER_IRQ_INFO; + TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS; static int trace_stop_count; static DEFINE_RAW_SPINLOCK(tracing_start_lock); @@ -426,15 +426,15 @@ __setup("trace_buf_size=", set_buf_size); static int __init set_tracing_thresh(char *str) { - unsigned long threshhold; + unsigned long threshold; int ret; if (!str) return 0; - ret = strict_strtoul(str, 0, &threshhold); + ret = strict_strtoul(str, 0, &threshold); if (ret < 0) return 0; - tracing_thresh = threshhold * 1000; + tracing_thresh = threshold * 1000; return 1; } __setup("tracing_thresh=", set_tracing_thresh); @@ -470,6 +470,7 @@ static const char *trace_options[] = { "overwrite", "disable_on_free", "irq-info", + "markers", NULL }; @@ -2060,7 +2061,8 @@ print_trace_header(struct seq_file *m, struct trace_iterator *iter) seq_puts(m, "# -----------------\n"); seq_printf(m, "# | task: %.16s-%d " "(uid:%d nice:%ld policy:%ld rt_prio:%ld)\n", - data->comm, data->pid, data->uid, data->nice, + data->comm, data->pid, + from_kuid_munged(seq_user_ns(m), data->uid), data->nice, data->policy, data->rt_priority); seq_puts(m, "# -----------------\n"); @@ -3886,6 +3888,9 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, if (tracing_disabled) return -EINVAL; + if (!(trace_flags & TRACE_ITER_MARKERS)) + return -EINVAL; + if (cnt > TRACE_BUF_SIZE) cnt = TRACE_BUF_SIZE; @@ -4195,12 +4200,6 @@ static void buffer_pipe_buf_release(struct pipe_inode_info *pipe, buf->private = 0; } -static int buffer_pipe_buf_steal(struct pipe_inode_info *pipe, - struct pipe_buffer *buf) -{ - return 1; -} - static void buffer_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { @@ -4216,7 +4215,7 @@ static const struct pipe_buf_operations buffer_pipe_buf_ops = { .unmap = generic_pipe_buf_unmap, .confirm = generic_pipe_buf_confirm, .release = buffer_pipe_buf_release, - .steal = buffer_pipe_buf_steal, + .steal = generic_pipe_buf_steal, .get = buffer_pipe_buf_get, }; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 55e1f7f0db12..c15f528c1af4 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -147,7 +147,7 @@ struct trace_array_cpu { unsigned long skipped_entries; cycle_t preempt_timestamp; pid_t pid; - uid_t uid; + kuid_t uid; char comm[TASK_COMM_LEN]; }; @@ -472,11 +472,11 @@ extern void trace_find_cmdline(int pid, char comm[]); #ifdef CONFIG_DYNAMIC_FTRACE extern unsigned long ftrace_update_tot_cnt; +#endif #define DYN_FTRACE_TEST_NAME trace_selftest_dynamic_test_func extern int DYN_FTRACE_TEST_NAME(void); #define DYN_FTRACE_TEST_NAME2 trace_selftest_dynamic_test_func2 extern int DYN_FTRACE_TEST_NAME2(void); -#endif extern int ring_buffer_expanded; extern bool tracing_selftest_disabled; @@ -680,6 +680,7 @@ enum trace_iterator_flags { TRACE_ITER_OVERWRITE = 0x200000, TRACE_ITER_STOP_ON_FREE = 0x400000, TRACE_ITER_IRQ_INFO = 0x800000, + TRACE_ITER_MARKERS = 0x1000000, }; /* diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 8a6d2ee2086c..84b1e045faba 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -258,7 +258,8 @@ EXPORT_SYMBOL_GPL(perf_trace_buf_prepare); #ifdef CONFIG_FUNCTION_TRACER static void -perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip) +perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *ops, struct pt_regs *pt_regs) { struct ftrace_entry *entry; struct hlist_head *head; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 29111da1d100..d608d09d08c0 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1199,6 +1199,31 @@ event_create_dir(struct ftrace_event_call *call, struct dentry *d_events, return 0; } +static void event_remove(struct ftrace_event_call *call) +{ + ftrace_event_enable_disable(call, 0); + if (call->event.funcs) + __unregister_ftrace_event(&call->event); + list_del(&call->list); +} + +static int event_init(struct ftrace_event_call *call) +{ + int ret = 0; + + if (WARN_ON(!call->name)) + return -EINVAL; + + if (call->class->raw_init) { + ret = call->class->raw_init(call); + if (ret < 0 && ret != -ENOSYS) + pr_warn("Could not initialize trace events/%s\n", + call->name); + } + + return ret; +} + static int __trace_add_event_call(struct ftrace_event_call *call, struct module *mod, const struct file_operations *id, @@ -1209,19 +1234,9 @@ __trace_add_event_call(struct ftrace_event_call *call, struct module *mod, struct dentry *d_events; int ret; - /* The linker may leave blanks */ - if (!call->name) - return -EINVAL; - - if (call->class->raw_init) { - ret = call->class->raw_init(call); - if (ret < 0) { - if (ret != -ENOSYS) - pr_warning("Could not initialize trace events/%s\n", - call->name); - return ret; - } - } + ret = event_init(call); + if (ret < 0) + return ret; d_events = event_trace_events_dir(); if (!d_events) @@ -1272,13 +1287,10 @@ static void remove_subsystem_dir(const char *name) */ static void __trace_remove_event_call(struct ftrace_event_call *call) { - ftrace_event_enable_disable(call, 0); - if (call->event.funcs) - __unregister_ftrace_event(&call->event); - debugfs_remove_recursive(call->dir); - list_del(&call->list); + event_remove(call); trace_destroy_fields(call); destroy_preds(call); + debugfs_remove_recursive(call->dir); remove_subsystem_dir(call->class->system); } @@ -1450,15 +1462,43 @@ static __init int setup_trace_event(char *str) } __setup("trace_event=", setup_trace_event); +static __init int event_trace_enable(void) +{ + struct ftrace_event_call **iter, *call; + char *buf = bootup_event_buf; + char *token; + int ret; + + for_each_event(iter, __start_ftrace_events, __stop_ftrace_events) { + + call = *iter; + ret = event_init(call); + if (!ret) + list_add(&call->list, &ftrace_events); + } + + while (true) { + token = strsep(&buf, ","); + + if (!token) + break; + if (!*token) + continue; + + ret = ftrace_set_clr_event(token, 1); + if (ret) + pr_warn("Failed to enable trace event: %s\n", token); + } + return 0; +} + static __init int event_trace_init(void) { - struct ftrace_event_call **call; + struct ftrace_event_call *call; struct dentry *d_tracer; struct dentry *entry; struct dentry *d_events; int ret; - char *buf = bootup_event_buf; - char *token; d_tracer = tracing_init_dentry(); if (!d_tracer) @@ -1497,24 +1537,19 @@ static __init int event_trace_init(void) if (trace_define_common_fields()) pr_warning("tracing: Failed to allocate common fields"); - for_each_event(call, __start_ftrace_events, __stop_ftrace_events) { - __trace_add_event_call(*call, NULL, &ftrace_event_id_fops, + /* + * Early initialization already enabled ftrace event. + * Now it's only necessary to create the event directory. + */ + list_for_each_entry(call, &ftrace_events, list) { + + ret = event_create_dir(call, d_events, + &ftrace_event_id_fops, &ftrace_enable_fops, &ftrace_event_filter_fops, &ftrace_event_format_fops); - } - - while (true) { - token = strsep(&buf, ","); - - if (!token) - break; - if (!*token) - continue; - - ret = ftrace_set_clr_event(token, 1); - if (ret) - pr_warning("Failed to enable trace event: %s\n", token); + if (ret < 0) + event_remove(call); } ret = register_module_notifier(&trace_module_nb); @@ -1523,6 +1558,7 @@ static __init int event_trace_init(void) return 0; } +core_initcall(event_trace_enable); fs_initcall(event_trace_init); #ifdef CONFIG_FTRACE_STARTUP_TEST @@ -1646,9 +1682,11 @@ static __init void event_trace_self_tests(void) event_test_stuff(); ret = __ftrace_set_clr_event(NULL, system->name, NULL, 0); - if (WARN_ON_ONCE(ret)) + if (WARN_ON_ONCE(ret)) { pr_warning("error disabling system %s\n", system->name); + continue; + } pr_cont("OK\n"); } @@ -1681,7 +1719,8 @@ static __init void event_trace_self_tests(void) static DEFINE_PER_CPU(atomic_t, ftrace_test_event_disable); static void -function_test_events_call(unsigned long ip, unsigned long parent_ip) +function_test_events_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) { struct ring_buffer_event *event; struct ring_buffer *buffer; @@ -1720,6 +1759,7 @@ function_test_events_call(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops trace_ops __initdata = { .func = function_test_events_call, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static __init void event_trace_self_test_with_function(void) diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index 431dba8b7542..c154797a7ff7 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -2002,7 +2002,7 @@ static int ftrace_function_set_regexp(struct ftrace_ops *ops, int filter, static int __ftrace_function_set_filter(int filter, char *buf, int len, struct function_filter_data *data) { - int i, re_cnt, ret; + int i, re_cnt, ret = -EINVAL; int *reset; char **re; diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index a426f410c060..507a7a9630bf 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -13,7 +13,6 @@ #include <linux/debugfs.h> #include <linux/uaccess.h> #include <linux/ftrace.h> -#include <linux/pstore.h> #include <linux/fs.h> #include "trace.h" @@ -49,7 +48,8 @@ static void function_trace_start(struct trace_array *tr) } static void -function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip) +function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) { struct trace_array *tr = func_trace; struct trace_array_cpu *data; @@ -75,16 +75,17 @@ function_trace_call_preempt_only(unsigned long ip, unsigned long parent_ip) preempt_enable_notrace(); } -/* Our two options */ +/* Our option */ enum { TRACE_FUNC_OPT_STACK = 0x1, - TRACE_FUNC_OPT_PSTORE = 0x2, }; static struct tracer_flags func_flags; static void -function_trace_call(unsigned long ip, unsigned long parent_ip) +function_trace_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) + { struct trace_array *tr = func_trace; struct trace_array_cpu *data; @@ -106,12 +107,6 @@ function_trace_call(unsigned long ip, unsigned long parent_ip) disabled = atomic_inc_return(&data->disabled); if (likely(disabled == 1)) { - /* - * So far tracing doesn't support multiple buffers, so - * we make an explicit call for now. - */ - if (unlikely(func_flags.val & TRACE_FUNC_OPT_PSTORE)) - pstore_ftrace_call(ip, parent_ip); pc = preempt_count(); trace_function(tr, ip, parent_ip, flags, pc); } @@ -121,7 +116,8 @@ function_trace_call(unsigned long ip, unsigned long parent_ip) } static void -function_stack_trace_call(unsigned long ip, unsigned long parent_ip) +function_stack_trace_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) { struct trace_array *tr = func_trace; struct trace_array_cpu *data; @@ -164,22 +160,19 @@ function_stack_trace_call(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops trace_ops __read_mostly = { .func = function_trace_call, - .flags = FTRACE_OPS_FL_GLOBAL, + .flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE, }; static struct ftrace_ops trace_stack_ops __read_mostly = { .func = function_stack_trace_call, - .flags = FTRACE_OPS_FL_GLOBAL, + .flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE, }; static struct tracer_opt func_opts[] = { #ifdef CONFIG_STACKTRACE { TRACER_OPT(func_stack_trace, TRACE_FUNC_OPT_STACK) }, #endif -#ifdef CONFIG_PSTORE_FTRACE - { TRACER_OPT(func_pstore, TRACE_FUNC_OPT_PSTORE) }, -#endif { } /* Always set a last empty entry */ }; @@ -232,8 +225,6 @@ static int func_set_flag(u32 old_flags, u32 bit, int set) } break; - case TRACE_FUNC_OPT_PSTORE: - break; default: return -EINVAL; } diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index ce27c8ba8d31..99b4378393d5 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -143,7 +143,7 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret, return; } -#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST +#if defined(CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST) && !defined(CC_USING_FENTRY) /* * The arch may choose to record the frame pointer used * and check it here to make sure that it is what we expect it @@ -154,6 +154,9 @@ ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret, * * Currently, x86_32 with optimize for size (-Os) makes the latest * gcc do the above. + * + * Note, -mfentry does not use frame pointers, and this test + * is not needed if CC_USING_FENTRY is set. */ if (unlikely(current->ret_stack[index].fp != frame_pointer)) { ftrace_graph_stop(); diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index 99d20e920368..d98ee8283b29 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -136,7 +136,8 @@ static int func_prolog_dec(struct trace_array *tr, * irqsoff uses its own tracer function to keep the overhead down: */ static void -irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip) +irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) { struct trace_array *tr = irqsoff_trace; struct trace_array_cpu *data; @@ -153,7 +154,7 @@ irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops trace_ops __read_mostly = { .func = irqsoff_tracer_call, - .flags = FTRACE_OPS_FL_GLOBAL, + .flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE, }; #endif /* CONFIG_FUNCTION_TRACER */ diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index ff791ea48b57..02170c00c413 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -108,7 +108,8 @@ out_enable: * wakeup uses its own tracer function to keep the overhead down: */ static void -wakeup_tracer_call(unsigned long ip, unsigned long parent_ip) +wakeup_tracer_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) { struct trace_array *tr = wakeup_trace; struct trace_array_cpu *data; @@ -129,7 +130,7 @@ wakeup_tracer_call(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops trace_ops __read_mostly = { .func = wakeup_tracer_call, - .flags = FTRACE_OPS_FL_GLOBAL, + .flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE, }; #endif /* CONFIG_FUNCTION_TRACER */ diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 288541f977fb..2c00a691a540 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -103,54 +103,67 @@ static inline void warn_failed_init_tracer(struct tracer *trace, int init_ret) static int trace_selftest_test_probe1_cnt; static void trace_selftest_test_probe1_func(unsigned long ip, - unsigned long pip) + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) { trace_selftest_test_probe1_cnt++; } static int trace_selftest_test_probe2_cnt; static void trace_selftest_test_probe2_func(unsigned long ip, - unsigned long pip) + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) { trace_selftest_test_probe2_cnt++; } static int trace_selftest_test_probe3_cnt; static void trace_selftest_test_probe3_func(unsigned long ip, - unsigned long pip) + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) { trace_selftest_test_probe3_cnt++; } static int trace_selftest_test_global_cnt; static void trace_selftest_test_global_func(unsigned long ip, - unsigned long pip) + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) { trace_selftest_test_global_cnt++; } static int trace_selftest_test_dyn_cnt; static void trace_selftest_test_dyn_func(unsigned long ip, - unsigned long pip) + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) { trace_selftest_test_dyn_cnt++; } static struct ftrace_ops test_probe1 = { .func = trace_selftest_test_probe1_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static struct ftrace_ops test_probe2 = { .func = trace_selftest_test_probe2_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static struct ftrace_ops test_probe3 = { .func = trace_selftest_test_probe3_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static struct ftrace_ops test_global = { - .func = trace_selftest_test_global_func, - .flags = FTRACE_OPS_FL_GLOBAL, + .func = trace_selftest_test_global_func, + .flags = FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_RECURSION_SAFE, }; static void print_counts(void) @@ -393,10 +406,253 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace, return ret; } + +static int trace_selftest_recursion_cnt; +static void trace_selftest_test_recursion_func(unsigned long ip, + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) +{ + /* + * This function is registered without the recursion safe flag. + * The ftrace infrastructure should provide the recursion + * protection. If not, this will crash the kernel! + */ + trace_selftest_recursion_cnt++; + DYN_FTRACE_TEST_NAME(); +} + +static void trace_selftest_test_recursion_safe_func(unsigned long ip, + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) +{ + /* + * We said we would provide our own recursion. By calling + * this function again, we should recurse back into this function + * and count again. But this only happens if the arch supports + * all of ftrace features and nothing else is using the function + * tracing utility. + */ + if (trace_selftest_recursion_cnt++) + return; + DYN_FTRACE_TEST_NAME(); +} + +static struct ftrace_ops test_rec_probe = { + .func = trace_selftest_test_recursion_func, +}; + +static struct ftrace_ops test_recsafe_probe = { + .func = trace_selftest_test_recursion_safe_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, +}; + +static int +trace_selftest_function_recursion(void) +{ + int save_ftrace_enabled = ftrace_enabled; + int save_tracer_enabled = tracer_enabled; + char *func_name; + int len; + int ret; + int cnt; + + /* The previous test PASSED */ + pr_cont("PASSED\n"); + pr_info("Testing ftrace recursion: "); + + + /* enable tracing, and record the filter function */ + ftrace_enabled = 1; + tracer_enabled = 1; + + /* Handle PPC64 '.' name */ + func_name = "*" __stringify(DYN_FTRACE_TEST_NAME); + len = strlen(func_name); + + ret = ftrace_set_filter(&test_rec_probe, func_name, len, 1); + if (ret) { + pr_cont("*Could not set filter* "); + goto out; + } + + ret = register_ftrace_function(&test_rec_probe); + if (ret) { + pr_cont("*could not register callback* "); + goto out; + } + + DYN_FTRACE_TEST_NAME(); + + unregister_ftrace_function(&test_rec_probe); + + ret = -1; + if (trace_selftest_recursion_cnt != 1) { + pr_cont("*callback not called once (%d)* ", + trace_selftest_recursion_cnt); + goto out; + } + + trace_selftest_recursion_cnt = 1; + + pr_cont("PASSED\n"); + pr_info("Testing ftrace recursion safe: "); + + ret = ftrace_set_filter(&test_recsafe_probe, func_name, len, 1); + if (ret) { + pr_cont("*Could not set filter* "); + goto out; + } + + ret = register_ftrace_function(&test_recsafe_probe); + if (ret) { + pr_cont("*could not register callback* "); + goto out; + } + + DYN_FTRACE_TEST_NAME(); + + unregister_ftrace_function(&test_recsafe_probe); + + /* + * If arch supports all ftrace features, and no other task + * was on the list, we should be fine. + */ + if (!ftrace_nr_registered_ops() && !FTRACE_FORCE_LIST_FUNC) + cnt = 2; /* Should have recursed */ + else + cnt = 1; + + ret = -1; + if (trace_selftest_recursion_cnt != cnt) { + pr_cont("*callback not called expected %d times (%d)* ", + cnt, trace_selftest_recursion_cnt); + goto out; + } + + ret = 0; +out: + ftrace_enabled = save_ftrace_enabled; + tracer_enabled = save_tracer_enabled; + + return ret; +} #else # define trace_selftest_startup_dynamic_tracing(trace, tr, func) ({ 0; }) +# define trace_selftest_function_recursion() ({ 0; }) #endif /* CONFIG_DYNAMIC_FTRACE */ +static enum { + TRACE_SELFTEST_REGS_START, + TRACE_SELFTEST_REGS_FOUND, + TRACE_SELFTEST_REGS_NOT_FOUND, +} trace_selftest_regs_stat; + +static void trace_selftest_test_regs_func(unsigned long ip, + unsigned long pip, + struct ftrace_ops *op, + struct pt_regs *pt_regs) +{ + if (pt_regs) + trace_selftest_regs_stat = TRACE_SELFTEST_REGS_FOUND; + else + trace_selftest_regs_stat = TRACE_SELFTEST_REGS_NOT_FOUND; +} + +static struct ftrace_ops test_regs_probe = { + .func = trace_selftest_test_regs_func, + .flags = FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_SAVE_REGS, +}; + +static int +trace_selftest_function_regs(void) +{ + int save_ftrace_enabled = ftrace_enabled; + int save_tracer_enabled = tracer_enabled; + char *func_name; + int len; + int ret; + int supported = 0; + +#ifdef ARCH_SUPPORTS_FTRACE_SAVE_REGS + supported = 1; +#endif + + /* The previous test PASSED */ + pr_cont("PASSED\n"); + pr_info("Testing ftrace regs%s: ", + !supported ? "(no arch support)" : ""); + + /* enable tracing, and record the filter function */ + ftrace_enabled = 1; + tracer_enabled = 1; + + /* Handle PPC64 '.' name */ + func_name = "*" __stringify(DYN_FTRACE_TEST_NAME); + len = strlen(func_name); + + ret = ftrace_set_filter(&test_regs_probe, func_name, len, 1); + /* + * If DYNAMIC_FTRACE is not set, then we just trace all functions. + * This test really doesn't care. + */ + if (ret && ret != -ENODEV) { + pr_cont("*Could not set filter* "); + goto out; + } + + ret = register_ftrace_function(&test_regs_probe); + /* + * Now if the arch does not support passing regs, then this should + * have failed. + */ + if (!supported) { + if (!ret) { + pr_cont("*registered save-regs without arch support* "); + goto out; + } + test_regs_probe.flags |= FTRACE_OPS_FL_SAVE_REGS_IF_SUPPORTED; + ret = register_ftrace_function(&test_regs_probe); + } + if (ret) { + pr_cont("*could not register callback* "); + goto out; + } + + + DYN_FTRACE_TEST_NAME(); + + unregister_ftrace_function(&test_regs_probe); + + ret = -1; + + switch (trace_selftest_regs_stat) { + case TRACE_SELFTEST_REGS_START: + pr_cont("*callback never called* "); + goto out; + + case TRACE_SELFTEST_REGS_FOUND: + if (supported) + break; + pr_cont("*callback received regs without arch support* "); + goto out; + + case TRACE_SELFTEST_REGS_NOT_FOUND: + if (!supported) + break; + pr_cont("*callback received NULL regs* "); + goto out; + } + + ret = 0; +out: + ftrace_enabled = save_ftrace_enabled; + tracer_enabled = save_tracer_enabled; + + return ret; +} + /* * Simple verification test of ftrace function tracer. * Enable ftrace, sleep 1/10 second, and then read the trace @@ -442,7 +698,14 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) ret = trace_selftest_startup_dynamic_tracing(trace, tr, DYN_FTRACE_TEST_NAME); + if (ret) + goto out; + ret = trace_selftest_function_recursion(); + if (ret) + goto out; + + ret = trace_selftest_function_regs(); out: ftrace_enabled = save_ftrace_enabled; tracer_enabled = save_tracer_enabled; @@ -778,6 +1041,8 @@ static int trace_wakeup_test_thread(void *data) set_current_state(TASK_INTERRUPTIBLE); schedule(); + complete(x); + /* we are awake, now wait to disappear */ while (!kthread_should_stop()) { /* @@ -821,24 +1086,21 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr) /* reset the max latency */ tracing_max_latency = 0; - /* sleep to let the RT thread sleep too */ - msleep(100); + while (p->on_rq) { + /* + * Sleep to make sure the RT thread is asleep too. + * On virtual machines we can't rely on timings, + * but we want to make sure this test still works. + */ + msleep(100); + } - /* - * Yes this is slightly racy. It is possible that for some - * strange reason that the RT thread we created, did not - * call schedule for 100ms after doing the completion, - * and we do a wakeup on a task that already is awake. - * But that is extremely unlikely, and the worst thing that - * happens in such a case, is that we disable tracing. - * Honestly, if this race does happen something is horrible - * wrong with the system. - */ + init_completion(&isrt); wake_up_process(p); - /* give a little time to let the thread wake up */ - msleep(100); + /* Wait for the task to wake up */ + wait_for_completion(&isrt); /* stop the tracing. */ tracing_stop(); diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index d4545f49242e..0c1b165778e5 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -111,7 +111,8 @@ static inline void check_stack(void) } static void -stack_trace_call(unsigned long ip, unsigned long parent_ip) +stack_trace_call(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct pt_regs *pt_regs) { int cpu; @@ -136,6 +137,7 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip) static struct ftrace_ops trace_ops __read_mostly = { .func = stack_trace_call, + .flags = FTRACE_OPS_FL_RECURSION_SAFE, }; static ssize_t diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 6b245f64c8dd..2485a7d09b11 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -487,7 +487,7 @@ int __init init_ftrace_syscalls(void) return 0; } -core_initcall(init_ftrace_syscalls); +early_initcall(init_ftrace_syscalls); #ifdef CONFIG_PERF_EVENTS diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 23b4d784ebdd..625df0b44690 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -26,7 +26,9 @@ /* * fill in basic accounting fields */ -void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk) +void bacct_add_tsk(struct user_namespace *user_ns, + struct pid_namespace *pid_ns, + struct taskstats *stats, struct task_struct *tsk) { const struct cred *tcred; struct timespec uptime, ts; @@ -55,13 +57,13 @@ void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk) stats->ac_flag |= AXSIG; stats->ac_nice = task_nice(tsk); stats->ac_sched = tsk->policy; - stats->ac_pid = tsk->pid; + stats->ac_pid = task_pid_nr_ns(tsk, pid_ns); rcu_read_lock(); tcred = __task_cred(tsk); - stats->ac_uid = tcred->uid; - stats->ac_gid = tcred->gid; + stats->ac_uid = from_kuid_munged(user_ns, tcred->uid); + stats->ac_gid = from_kgid_munged(user_ns, tcred->gid); stats->ac_ppid = pid_alive(tsk) ? - rcu_dereference(tsk->real_parent)->tgid : 0; + task_tgid_nr_ns(rcu_dereference(tsk->real_parent), pid_ns) : 0; rcu_read_unlock(); stats->ac_utime = cputime_to_usecs(tsk->utime); stats->ac_stime = cputime_to_usecs(tsk->stime); diff --git a/kernel/user.c b/kernel/user.c index b815fefbe76f..750acffbe9ec 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -38,6 +38,14 @@ struct user_namespace init_user_ns = { .count = 4294967295U, }, }, + .projid_map = { + .nr_extents = 1, + .extent[0] = { + .first = 0, + .lower_first = 0, + .count = 4294967295U, + }, + }, .kref = { .refcount = ATOMIC_INIT(3), }, diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 86602316422d..456a6b9fba34 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -19,6 +19,7 @@ #include <linux/fs.h> #include <linux/uaccess.h> #include <linux/ctype.h> +#include <linux/projid.h> static struct kmem_cache *user_ns_cachep __read_mostly; @@ -295,6 +296,75 @@ gid_t from_kgid_munged(struct user_namespace *targ, kgid_t kgid) } EXPORT_SYMBOL(from_kgid_munged); +/** + * make_kprojid - Map a user-namespace projid pair into a kprojid. + * @ns: User namespace that the projid is in + * @projid: Project identifier + * + * Maps a user-namespace uid pair into a kernel internal kuid, + * and returns that kuid. + * + * When there is no mapping defined for the user-namespace projid + * pair INVALID_PROJID is returned. Callers are expected to test + * for and handle handle INVALID_PROJID being returned. INVALID_PROJID + * may be tested for using projid_valid(). + */ +kprojid_t make_kprojid(struct user_namespace *ns, projid_t projid) +{ + /* Map the uid to a global kernel uid */ + return KPROJIDT_INIT(map_id_down(&ns->projid_map, projid)); +} +EXPORT_SYMBOL(make_kprojid); + +/** + * from_kprojid - Create a projid from a kprojid user-namespace pair. + * @targ: The user namespace we want a projid in. + * @kprojid: The kernel internal project identifier to start with. + * + * Map @kprojid into the user-namespace specified by @targ and + * return the resulting projid. + * + * There is always a mapping into the initial user_namespace. + * + * If @kprojid has no mapping in @targ (projid_t)-1 is returned. + */ +projid_t from_kprojid(struct user_namespace *targ, kprojid_t kprojid) +{ + /* Map the uid from a global kernel uid */ + return map_id_up(&targ->projid_map, __kprojid_val(kprojid)); +} +EXPORT_SYMBOL(from_kprojid); + +/** + * from_kprojid_munged - Create a projiid from a kprojid user-namespace pair. + * @targ: The user namespace we want a projid in. + * @kprojid: The kernel internal projid to start with. + * + * Map @kprojid into the user-namespace specified by @targ and + * return the resulting projid. + * + * There is always a mapping into the initial user_namespace. + * + * Unlike from_kprojid from_kprojid_munged never fails and always + * returns a valid projid. This makes from_kprojid_munged + * appropriate for use in syscalls like stat and where + * failing the system call and failing to provide a valid projid are + * not an options. + * + * If @kprojid has no mapping in @targ OVERFLOW_PROJID is returned. + */ +projid_t from_kprojid_munged(struct user_namespace *targ, kprojid_t kprojid) +{ + projid_t projid; + projid = from_kprojid(targ, kprojid); + + if (projid == (projid_t) -1) + projid = OVERFLOW_PROJID; + return projid; +} +EXPORT_SYMBOL(from_kprojid_munged); + + static int uid_m_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; @@ -337,6 +407,27 @@ static int gid_m_show(struct seq_file *seq, void *v) return 0; } +static int projid_m_show(struct seq_file *seq, void *v) +{ + struct user_namespace *ns = seq->private; + struct uid_gid_extent *extent = v; + struct user_namespace *lower_ns; + projid_t lower; + + lower_ns = seq_user_ns(seq); + if ((lower_ns == ns) && lower_ns->parent) + lower_ns = lower_ns->parent; + + lower = from_kprojid(lower_ns, KPROJIDT_INIT(extent->lower_first)); + + seq_printf(seq, "%10u %10u %10u\n", + extent->first, + lower, + extent->count); + + return 0; +} + static void *m_start(struct seq_file *seq, loff_t *ppos, struct uid_gid_map *map) { struct uid_gid_extent *extent = NULL; @@ -362,6 +453,13 @@ static void *gid_m_start(struct seq_file *seq, loff_t *ppos) return m_start(seq, ppos, &ns->gid_map); } +static void *projid_m_start(struct seq_file *seq, loff_t *ppos) +{ + struct user_namespace *ns = seq->private; + + return m_start(seq, ppos, &ns->projid_map); +} + static void *m_next(struct seq_file *seq, void *v, loff_t *pos) { (*pos)++; @@ -387,6 +485,13 @@ struct seq_operations proc_gid_seq_operations = { .show = gid_m_show, }; +struct seq_operations proc_projid_seq_operations = { + .start = projid_m_start, + .stop = m_stop, + .next = m_next, + .show = projid_m_show, +}; + static DEFINE_MUTEX(id_map_mutex); static ssize_t map_write(struct file *file, const char __user *buf, @@ -434,7 +539,7 @@ static ssize_t map_write(struct file *file, const char __user *buf, /* Require the appropriate privilege CAP_SETUID or CAP_SETGID * over the user namespace in order to set the id mapping. */ - if (!ns_capable(ns, cap_setid)) + if (cap_valid(cap_setid) && !ns_capable(ns, cap_setid)) goto out; /* Get a buffer */ @@ -584,9 +689,30 @@ ssize_t proc_gid_map_write(struct file *file, const char __user *buf, size_t siz &ns->gid_map, &ns->parent->gid_map); } +ssize_t proc_projid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) +{ + struct seq_file *seq = file->private_data; + struct user_namespace *ns = seq->private; + struct user_namespace *seq_ns = seq_user_ns(seq); + + if (!ns->parent) + return -EPERM; + + if ((seq_ns != ns) && (seq_ns != ns->parent)) + return -EPERM; + + /* Anyone can set any valid project id no capability needed */ + return map_write(file, buf, size, ppos, -1, + &ns->projid_map, &ns->parent->projid_map); +} + static bool new_idmap_permitted(struct user_namespace *ns, int cap_setid, struct uid_gid_map *new_map) { + /* Allow anyone to set a mapping that doesn't require privilege */ + if (!cap_valid(cap_setid)) + return true; + /* Allow the specified ids if we have the appropriate capability * (CAP_SETUID or CAP_SETGID) over the parent user namespace. */ diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 4b1dfba70f7c..9d4c8d5a1f53 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -22,6 +22,7 @@ #include <linux/notifier.h> #include <linux/module.h> #include <linux/sysctl.h> +#include <linux/smpboot.h> #include <asm/irq_regs.h> #include <linux/kvm_para.h> @@ -29,16 +30,18 @@ int watchdog_enabled = 1; int __read_mostly watchdog_thresh = 10; +static int __read_mostly watchdog_disabled; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog); static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer); static DEFINE_PER_CPU(bool, softlockup_touch_sync); static DEFINE_PER_CPU(bool, soft_watchdog_warn); +static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts); +static DEFINE_PER_CPU(unsigned long, soft_lockup_hrtimer_cnt); #ifdef CONFIG_HARDLOCKUP_DETECTOR static DEFINE_PER_CPU(bool, hard_watchdog_warn); static DEFINE_PER_CPU(bool, watchdog_nmi_touch); -static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts); static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved); static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); #endif @@ -248,13 +251,15 @@ static void watchdog_overflow_callback(struct perf_event *event, __this_cpu_write(hard_watchdog_warn, false); return; } +#endif /* CONFIG_HARDLOCKUP_DETECTOR */ + static void watchdog_interrupt_count(void) { __this_cpu_inc(hrtimer_interrupts); } -#else -static inline void watchdog_interrupt_count(void) { return; } -#endif /* CONFIG_HARDLOCKUP_DETECTOR */ + +static int watchdog_nmi_enable(unsigned int cpu); +static void watchdog_nmi_disable(unsigned int cpu); /* watchdog kicker functions */ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) @@ -327,49 +332,68 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) return HRTIMER_RESTART; } +static void watchdog_set_prio(unsigned int policy, unsigned int prio) +{ + struct sched_param param = { .sched_priority = prio }; -/* - * The watchdog thread - touches the timestamp. - */ -static int watchdog(void *unused) + sched_setscheduler(current, policy, ¶m); +} + +static void watchdog_enable(unsigned int cpu) { - struct sched_param param = { .sched_priority = 0 }; struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer); - /* initialize timestamp */ - __touch_watchdog(); + if (!watchdog_enabled) { + kthread_park(current); + return; + } + + /* Enable the perf event */ + watchdog_nmi_enable(cpu); /* kick off the timer for the hardlockup detector */ + hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer->function = watchdog_timer_fn; + /* done here because hrtimer_start can only pin to smp_processor_id() */ hrtimer_start(hrtimer, ns_to_ktime(get_sample_period()), HRTIMER_MODE_REL_PINNED); - set_current_state(TASK_INTERRUPTIBLE); - /* - * Run briefly (kicked by the hrtimer callback function) once every - * get_sample_period() seconds (4 seconds by default) to reset the - * softlockup timestamp. If this gets delayed for more than - * 2*watchdog_thresh seconds then the debug-printout triggers in - * watchdog_timer_fn(). - */ - while (!kthread_should_stop()) { - __touch_watchdog(); - schedule(); + /* initialize timestamp */ + watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1); + __touch_watchdog(); +} - if (kthread_should_stop()) - break; +static void watchdog_disable(unsigned int cpu) +{ + struct hrtimer *hrtimer = &__raw_get_cpu_var(watchdog_hrtimer); - set_current_state(TASK_INTERRUPTIBLE); - } - /* - * Drop the policy/priority elevation during thread exit to avoid a - * scheduling latency spike. - */ - __set_current_state(TASK_RUNNING); - sched_setscheduler(current, SCHED_NORMAL, ¶m); - return 0; + watchdog_set_prio(SCHED_NORMAL, 0); + hrtimer_cancel(hrtimer); + /* disable the perf event */ + watchdog_nmi_disable(cpu); } +static int watchdog_should_run(unsigned int cpu) +{ + return __this_cpu_read(hrtimer_interrupts) != + __this_cpu_read(soft_lockup_hrtimer_cnt); +} + +/* + * The watchdog thread function - touches the timestamp. + * + * It only runs once every get_sample_period() seconds (4 seconds by + * default) to reset the softlockup timestamp. If this gets delayed + * for more than 2*watchdog_thresh seconds then the debug-printout + * triggers in watchdog_timer_fn(). + */ +static void watchdog(unsigned int cpu) +{ + __this_cpu_write(soft_lockup_hrtimer_cnt, + __this_cpu_read(hrtimer_interrupts)); + __touch_watchdog(); +} #ifdef CONFIG_HARDLOCKUP_DETECTOR /* @@ -379,7 +403,7 @@ static int watchdog(void *unused) */ static unsigned long cpu0_err; -static int watchdog_nmi_enable(int cpu) +static int watchdog_nmi_enable(unsigned int cpu) { struct perf_event_attr *wd_attr; struct perf_event *event = per_cpu(watchdog_ev, cpu); @@ -433,7 +457,7 @@ out: return 0; } -static void watchdog_nmi_disable(int cpu) +static void watchdog_nmi_disable(unsigned int cpu) { struct perf_event *event = per_cpu(watchdog_ev, cpu); @@ -447,107 +471,35 @@ static void watchdog_nmi_disable(int cpu) return; } #else -static int watchdog_nmi_enable(int cpu) { return 0; } -static void watchdog_nmi_disable(int cpu) { return; } +static int watchdog_nmi_enable(unsigned int cpu) { return 0; } +static void watchdog_nmi_disable(unsigned int cpu) { return; } #endif /* CONFIG_HARDLOCKUP_DETECTOR */ /* prepare/enable/disable routines */ -static void watchdog_prepare_cpu(int cpu) -{ - struct hrtimer *hrtimer = &per_cpu(watchdog_hrtimer, cpu); - - WARN_ON(per_cpu(softlockup_watchdog, cpu)); - hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - hrtimer->function = watchdog_timer_fn; -} - -static int watchdog_enable(int cpu) -{ - struct task_struct *p = per_cpu(softlockup_watchdog, cpu); - int err = 0; - - /* enable the perf event */ - err = watchdog_nmi_enable(cpu); - - /* Regardless of err above, fall through and start softlockup */ - - /* create the watchdog thread */ - if (!p) { - struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; - p = kthread_create_on_node(watchdog, NULL, cpu_to_node(cpu), "watchdog/%d", cpu); - if (IS_ERR(p)) { - pr_err("softlockup watchdog for %i failed\n", cpu); - if (!err) { - /* if hardlockup hasn't already set this */ - err = PTR_ERR(p); - /* and disable the perf event */ - watchdog_nmi_disable(cpu); - } - goto out; - } - sched_setscheduler(p, SCHED_FIFO, ¶m); - kthread_bind(p, cpu); - per_cpu(watchdog_touch_ts, cpu) = 0; - per_cpu(softlockup_watchdog, cpu) = p; - wake_up_process(p); - } - -out: - return err; -} - -static void watchdog_disable(int cpu) -{ - struct task_struct *p = per_cpu(softlockup_watchdog, cpu); - struct hrtimer *hrtimer = &per_cpu(watchdog_hrtimer, cpu); - - /* - * cancel the timer first to stop incrementing the stats - * and waking up the kthread - */ - hrtimer_cancel(hrtimer); - - /* disable the perf event */ - watchdog_nmi_disable(cpu); - - /* stop the watchdog thread */ - if (p) { - per_cpu(softlockup_watchdog, cpu) = NULL; - kthread_stop(p); - } -} - /* sysctl functions */ #ifdef CONFIG_SYSCTL static void watchdog_enable_all_cpus(void) { - int cpu; - - watchdog_enabled = 0; - - for_each_online_cpu(cpu) - if (!watchdog_enable(cpu)) - /* if any cpu succeeds, watchdog is considered - enabled for the system */ - watchdog_enabled = 1; - - if (!watchdog_enabled) - pr_err("failed to be enabled on some cpus\n"); + unsigned int cpu; + if (watchdog_disabled) { + watchdog_disabled = 0; + for_each_online_cpu(cpu) + kthread_unpark(per_cpu(softlockup_watchdog, cpu)); + } } static void watchdog_disable_all_cpus(void) { - int cpu; - - for_each_online_cpu(cpu) - watchdog_disable(cpu); + unsigned int cpu; - /* if all watchdogs are disabled, then they are disabled for the system */ - watchdog_enabled = 0; + if (!watchdog_disabled) { + watchdog_disabled = 1; + for_each_online_cpu(cpu) + kthread_park(per_cpu(softlockup_watchdog, cpu)); + } } - /* * proc handler for /proc/sys/kernel/nmi_watchdog,watchdog_thresh */ @@ -557,73 +509,36 @@ int proc_dowatchdog(struct ctl_table *table, int write, { int ret; + if (watchdog_disabled < 0) + return -ENODEV; + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret || !write) - goto out; + return ret; if (watchdog_enabled && watchdog_thresh) watchdog_enable_all_cpus(); else watchdog_disable_all_cpus(); -out: return ret; } #endif /* CONFIG_SYSCTL */ - -/* - * Create/destroy watchdog threads as CPUs come and go: - */ -static int __cpuinit -cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) -{ - int hotcpu = (unsigned long)hcpu; - - switch (action) { - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: - watchdog_prepare_cpu(hotcpu); - break; - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - if (watchdog_enabled) - watchdog_enable(hotcpu); - break; -#ifdef CONFIG_HOTPLUG_CPU - case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: - watchdog_disable(hotcpu); - break; - case CPU_DEAD: - case CPU_DEAD_FROZEN: - watchdog_disable(hotcpu); - break; -#endif /* CONFIG_HOTPLUG_CPU */ - } - - /* - * hardlockup and softlockup are not important enough - * to block cpu bring up. Just always succeed and - * rely on printk output to flag problems. - */ - return NOTIFY_OK; -} - -static struct notifier_block __cpuinitdata cpu_nfb = { - .notifier_call = cpu_callback +static struct smp_hotplug_thread watchdog_threads = { + .store = &softlockup_watchdog, + .thread_should_run = watchdog_should_run, + .thread_fn = watchdog, + .thread_comm = "watchdog/%u", + .setup = watchdog_enable, + .park = watchdog_disable, + .unpark = watchdog_enable, }; void __init lockup_detector_init(void) { - void *cpu = (void *)(long)smp_processor_id(); - int err; - - err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu); - WARN_ON(notifier_to_errno(err)); - - cpu_callback(&cpu_nfb, CPU_ONLINE, cpu); - register_cpu_notifier(&cpu_nfb); - - return; + if (smpboot_register_percpu_thread(&watchdog_threads)) { + pr_err("Failed to create watchdog threads, disabled\n"); + watchdog_disabled = -ENODEV; + } } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 3c5a79e2134c..042d221d33cc 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -58,7 +58,7 @@ enum { * be executing on any CPU. The gcwq behaves as an unbound one. * * Note that DISASSOCIATED can be flipped only while holding - * managership of all pools on the gcwq to avoid changing binding + * assoc_mutex of all pools on the gcwq to avoid changing binding * state while create_worker() is in progress. */ GCWQ_DISASSOCIATED = 1 << 0, /* cpu can't serve workers */ @@ -73,11 +73,10 @@ enum { WORKER_DIE = 1 << 1, /* die die die */ WORKER_IDLE = 1 << 2, /* is idle */ WORKER_PREP = 1 << 3, /* preparing to run works */ - WORKER_REBIND = 1 << 5, /* mom is home, come back */ WORKER_CPU_INTENSIVE = 1 << 6, /* cpu intensive */ WORKER_UNBOUND = 1 << 7, /* worker is unbound */ - WORKER_NOT_RUNNING = WORKER_PREP | WORKER_REBIND | WORKER_UNBOUND | + WORKER_NOT_RUNNING = WORKER_PREP | WORKER_UNBOUND | WORKER_CPU_INTENSIVE, NR_WORKER_POOLS = 2, /* # worker pools per gcwq */ @@ -126,7 +125,6 @@ enum { struct global_cwq; struct worker_pool; -struct idle_rebind; /* * The poor guys doing the actual heavy lifting. All on-duty workers @@ -150,7 +148,6 @@ struct worker { int id; /* I: worker id */ /* for rebinding worker to CPU */ - struct idle_rebind *idle_rebind; /* L: for idle worker */ struct work_struct rebind_work; /* L: for busy worker */ }; @@ -160,13 +157,15 @@ struct worker_pool { struct list_head worklist; /* L: list of pending works */ int nr_workers; /* L: total number of workers */ + + /* nr_idle includes the ones off idle_list for rebinding */ int nr_idle; /* L: currently idle ones */ struct list_head idle_list; /* X: list of idle workers */ struct timer_list idle_timer; /* L: worker idle timeout */ struct timer_list mayday_timer; /* L: SOS timer for workers */ - struct mutex manager_mutex; /* mutex manager should hold */ + struct mutex assoc_mutex; /* protect GCWQ_DISASSOCIATED */ struct ida worker_ida; /* L: for worker IDs */ }; @@ -184,9 +183,8 @@ struct global_cwq { struct hlist_head busy_hash[BUSY_WORKER_HASH_SIZE]; /* L: hash of busy workers */ - struct worker_pool pools[2]; /* normal and highpri pools */ - - wait_queue_head_t rebind_hold; /* rebind hold wait */ + struct worker_pool pools[NR_WORKER_POOLS]; + /* normal and highpri pools */ } ____cacheline_aligned_in_smp; /* @@ -269,17 +267,15 @@ struct workqueue_struct { }; struct workqueue_struct *system_wq __read_mostly; -struct workqueue_struct *system_long_wq __read_mostly; -struct workqueue_struct *system_nrt_wq __read_mostly; -struct workqueue_struct *system_unbound_wq __read_mostly; -struct workqueue_struct *system_freezable_wq __read_mostly; -struct workqueue_struct *system_nrt_freezable_wq __read_mostly; EXPORT_SYMBOL_GPL(system_wq); +struct workqueue_struct *system_highpri_wq __read_mostly; +EXPORT_SYMBOL_GPL(system_highpri_wq); +struct workqueue_struct *system_long_wq __read_mostly; EXPORT_SYMBOL_GPL(system_long_wq); -EXPORT_SYMBOL_GPL(system_nrt_wq); +struct workqueue_struct *system_unbound_wq __read_mostly; EXPORT_SYMBOL_GPL(system_unbound_wq); +struct workqueue_struct *system_freezable_wq __read_mostly; EXPORT_SYMBOL_GPL(system_freezable_wq); -EXPORT_SYMBOL_GPL(system_nrt_freezable_wq); #define CREATE_TRACE_POINTS #include <trace/events/workqueue.h> @@ -534,18 +530,24 @@ static int work_next_color(int color) } /* - * A work's data points to the cwq with WORK_STRUCT_CWQ set while the - * work is on queue. Once execution starts, WORK_STRUCT_CWQ is - * cleared and the work data contains the cpu number it was last on. + * While queued, %WORK_STRUCT_CWQ is set and non flag bits of a work's data + * contain the pointer to the queued cwq. Once execution starts, the flag + * is cleared and the high bits contain OFFQ flags and CPU number. * - * set_work_{cwq|cpu}() and clear_work_data() can be used to set the - * cwq, cpu or clear work->data. These functions should only be - * called while the work is owned - ie. while the PENDING bit is set. + * set_work_cwq(), set_work_cpu_and_clear_pending(), mark_work_canceling() + * and clear_work_data() can be used to set the cwq, cpu or clear + * work->data. These functions should only be called while the work is + * owned - ie. while the PENDING bit is set. * - * get_work_[g]cwq() can be used to obtain the gcwq or cwq - * corresponding to a work. gcwq is available once the work has been - * queued anywhere after initialization. cwq is available only from - * queueing until execution starts. + * get_work_[g]cwq() can be used to obtain the gcwq or cwq corresponding to + * a work. gcwq is available once the work has been queued anywhere after + * initialization until it is sync canceled. cwq is available only while + * the work item is queued. + * + * %WORK_OFFQ_CANCELING is used to mark a work item which is being + * canceled. While being canceled, a work item may have its PENDING set + * but stay off timer and worklist for arbitrarily long and nobody should + * try to steal the PENDING bit. */ static inline void set_work_data(struct work_struct *work, unsigned long data, unsigned long flags) @@ -562,13 +564,22 @@ static void set_work_cwq(struct work_struct *work, WORK_STRUCT_PENDING | WORK_STRUCT_CWQ | extra_flags); } -static void set_work_cpu(struct work_struct *work, unsigned int cpu) +static void set_work_cpu_and_clear_pending(struct work_struct *work, + unsigned int cpu) { - set_work_data(work, cpu << WORK_STRUCT_FLAG_BITS, WORK_STRUCT_PENDING); + /* + * The following wmb is paired with the implied mb in + * test_and_set_bit(PENDING) and ensures all updates to @work made + * here are visible to and precede any updates by the next PENDING + * owner. + */ + smp_wmb(); + set_work_data(work, (unsigned long)cpu << WORK_OFFQ_CPU_SHIFT, 0); } static void clear_work_data(struct work_struct *work) { + smp_wmb(); /* see set_work_cpu_and_clear_pending() */ set_work_data(work, WORK_STRUCT_NO_CPU, 0); } @@ -591,7 +602,7 @@ static struct global_cwq *get_work_gcwq(struct work_struct *work) return ((struct cpu_workqueue_struct *) (data & WORK_STRUCT_WQ_DATA_MASK))->pool->gcwq; - cpu = data >> WORK_STRUCT_FLAG_BITS; + cpu = data >> WORK_OFFQ_CPU_SHIFT; if (cpu == WORK_CPU_NONE) return NULL; @@ -599,6 +610,22 @@ static struct global_cwq *get_work_gcwq(struct work_struct *work) return get_gcwq(cpu); } +static void mark_work_canceling(struct work_struct *work) +{ + struct global_cwq *gcwq = get_work_gcwq(work); + unsigned long cpu = gcwq ? gcwq->cpu : WORK_CPU_NONE; + + set_work_data(work, (cpu << WORK_OFFQ_CPU_SHIFT) | WORK_OFFQ_CANCELING, + WORK_STRUCT_PENDING); +} + +static bool work_is_canceling(struct work_struct *work) +{ + unsigned long data = atomic_long_read(&work->data); + + return !(data & WORK_STRUCT_CWQ) && (data & WORK_OFFQ_CANCELING); +} + /* * Policy functions. These define the policies on how the global worker * pools are managed. Unless noted otherwise, these functions assume that @@ -657,6 +684,13 @@ static bool too_many_workers(struct worker_pool *pool) int nr_idle = pool->nr_idle + managing; /* manager is considered idle */ int nr_busy = pool->nr_workers - nr_idle; + /* + * nr_idle and idle_list may disagree if idle rebinding is in + * progress. Never return %true if idle_list is empty. + */ + if (list_empty(&pool->idle_list)) + return false; + return nr_idle > 2 && (nr_idle - 2) * MAX_IDLE_WORKERS_RATIO >= nr_busy; } @@ -903,6 +937,206 @@ static struct worker *find_worker_executing_work(struct global_cwq *gcwq, } /** + * move_linked_works - move linked works to a list + * @work: start of series of works to be scheduled + * @head: target list to append @work to + * @nextp: out paramter for nested worklist walking + * + * Schedule linked works starting from @work to @head. Work series to + * be scheduled starts at @work and includes any consecutive work with + * WORK_STRUCT_LINKED set in its predecessor. + * + * If @nextp is not NULL, it's updated to point to the next work of + * the last scheduled work. This allows move_linked_works() to be + * nested inside outer list_for_each_entry_safe(). + * + * CONTEXT: + * spin_lock_irq(gcwq->lock). + */ +static void move_linked_works(struct work_struct *work, struct list_head *head, + struct work_struct **nextp) +{ + struct work_struct *n; + + /* + * Linked worklist will always end before the end of the list, + * use NULL for list head. + */ + list_for_each_entry_safe_from(work, n, NULL, entry) { + list_move_tail(&work->entry, head); + if (!(*work_data_bits(work) & WORK_STRUCT_LINKED)) + break; + } + + /* + * If we're already inside safe list traversal and have moved + * multiple works to the scheduled queue, the next position + * needs to be updated. + */ + if (nextp) + *nextp = n; +} + +static void cwq_activate_delayed_work(struct work_struct *work) +{ + struct cpu_workqueue_struct *cwq = get_work_cwq(work); + + trace_workqueue_activate_work(work); + move_linked_works(work, &cwq->pool->worklist, NULL); + __clear_bit(WORK_STRUCT_DELAYED_BIT, work_data_bits(work)); + cwq->nr_active++; +} + +static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq) +{ + struct work_struct *work = list_first_entry(&cwq->delayed_works, + struct work_struct, entry); + + cwq_activate_delayed_work(work); +} + +/** + * cwq_dec_nr_in_flight - decrement cwq's nr_in_flight + * @cwq: cwq of interest + * @color: color of work which left the queue + * + * A work either has completed or is removed from pending queue, + * decrement nr_in_flight of its cwq and handle workqueue flushing. + * + * CONTEXT: + * spin_lock_irq(gcwq->lock). + */ +static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color) +{ + /* ignore uncolored works */ + if (color == WORK_NO_COLOR) + return; + + cwq->nr_in_flight[color]--; + + cwq->nr_active--; + if (!list_empty(&cwq->delayed_works)) { + /* one down, submit a delayed one */ + if (cwq->nr_active < cwq->max_active) + cwq_activate_first_delayed(cwq); + } + + /* is flush in progress and are we at the flushing tip? */ + if (likely(cwq->flush_color != color)) + return; + + /* are there still in-flight works? */ + if (cwq->nr_in_flight[color]) + return; + + /* this cwq is done, clear flush_color */ + cwq->flush_color = -1; + + /* + * If this was the last cwq, wake up the first flusher. It + * will handle the rest. + */ + if (atomic_dec_and_test(&cwq->wq->nr_cwqs_to_flush)) + complete(&cwq->wq->first_flusher->done); +} + +/** + * try_to_grab_pending - steal work item from worklist and disable irq + * @work: work item to steal + * @is_dwork: @work is a delayed_work + * @flags: place to store irq state + * + * Try to grab PENDING bit of @work. This function can handle @work in any + * stable state - idle, on timer or on worklist. Return values are + * + * 1 if @work was pending and we successfully stole PENDING + * 0 if @work was idle and we claimed PENDING + * -EAGAIN if PENDING couldn't be grabbed at the moment, safe to busy-retry + * -ENOENT if someone else is canceling @work, this state may persist + * for arbitrarily long + * + * On >= 0 return, the caller owns @work's PENDING bit. To avoid getting + * interrupted while holding PENDING and @work off queue, irq must be + * disabled on entry. This, combined with delayed_work->timer being + * irqsafe, ensures that we return -EAGAIN for finite short period of time. + * + * On successful return, >= 0, irq is disabled and the caller is + * responsible for releasing it using local_irq_restore(*@flags). + * + * This function is safe to call from any context including IRQ handler. + */ +static int try_to_grab_pending(struct work_struct *work, bool is_dwork, + unsigned long *flags) +{ + struct global_cwq *gcwq; + + local_irq_save(*flags); + + /* try to steal the timer if it exists */ + if (is_dwork) { + struct delayed_work *dwork = to_delayed_work(work); + + /* + * dwork->timer is irqsafe. If del_timer() fails, it's + * guaranteed that the timer is not queued anywhere and not + * running on the local CPU. + */ + if (likely(del_timer(&dwork->timer))) + return 1; + } + + /* try to claim PENDING the normal way */ + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) + return 0; + + /* + * The queueing is in progress, or it is already queued. Try to + * steal it from ->worklist without clearing WORK_STRUCT_PENDING. + */ + gcwq = get_work_gcwq(work); + if (!gcwq) + goto fail; + + spin_lock(&gcwq->lock); + if (!list_empty(&work->entry)) { + /* + * This work is queued, but perhaps we locked the wrong gcwq. + * In that case we must see the new value after rmb(), see + * insert_work()->wmb(). + */ + smp_rmb(); + if (gcwq == get_work_gcwq(work)) { + debug_work_deactivate(work); + + /* + * A delayed work item cannot be grabbed directly + * because it might have linked NO_COLOR work items + * which, if left on the delayed_list, will confuse + * cwq->nr_active management later on and cause + * stall. Make sure the work item is activated + * before grabbing. + */ + if (*work_data_bits(work) & WORK_STRUCT_DELAYED) + cwq_activate_delayed_work(work); + + list_del_init(&work->entry); + cwq_dec_nr_in_flight(get_work_cwq(work), + get_work_color(work)); + + spin_unlock(&gcwq->lock); + return 1; + } + } + spin_unlock(&gcwq->lock); +fail: + local_irq_restore(*flags); + if (work_is_canceling(work)) + return -ENOENT; + cpu_relax(); + return -EAGAIN; +} + +/** * insert_work - insert a work into gcwq * @cwq: cwq @work belongs to * @work: work to insert @@ -982,7 +1216,15 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, struct cpu_workqueue_struct *cwq; struct list_head *worklist; unsigned int work_flags; - unsigned long flags; + unsigned int req_cpu = cpu; + + /* + * While a work item is PENDING && off queue, a task trying to + * steal the PENDING will busy-loop waiting for it to either get + * queued or lose PENDING. Grabbing PENDING and queueing should + * happen with IRQ disabled. + */ + WARN_ON_ONCE(!irqs_disabled()); debug_work_activate(work); @@ -995,21 +1237,22 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, if (!(wq->flags & WQ_UNBOUND)) { struct global_cwq *last_gcwq; - if (unlikely(cpu == WORK_CPU_UNBOUND)) + if (cpu == WORK_CPU_UNBOUND) cpu = raw_smp_processor_id(); /* - * It's multi cpu. If @wq is non-reentrant and @work - * was previously on a different cpu, it might still - * be running there, in which case the work needs to - * be queued on that cpu to guarantee non-reentrance. + * It's multi cpu. If @work was previously on a different + * cpu, it might still be running there, in which case the + * work needs to be queued on that cpu to guarantee + * non-reentrancy. */ gcwq = get_gcwq(cpu); - if (wq->flags & WQ_NON_REENTRANT && - (last_gcwq = get_work_gcwq(work)) && last_gcwq != gcwq) { + last_gcwq = get_work_gcwq(work); + + if (last_gcwq && last_gcwq != gcwq) { struct worker *worker; - spin_lock_irqsave(&last_gcwq->lock, flags); + spin_lock(&last_gcwq->lock); worker = find_worker_executing_work(last_gcwq, work); @@ -1017,22 +1260,23 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, gcwq = last_gcwq; else { /* meh... not running there, queue here */ - spin_unlock_irqrestore(&last_gcwq->lock, flags); - spin_lock_irqsave(&gcwq->lock, flags); + spin_unlock(&last_gcwq->lock); + spin_lock(&gcwq->lock); } - } else - spin_lock_irqsave(&gcwq->lock, flags); + } else { + spin_lock(&gcwq->lock); + } } else { gcwq = get_gcwq(WORK_CPU_UNBOUND); - spin_lock_irqsave(&gcwq->lock, flags); + spin_lock(&gcwq->lock); } /* gcwq determined, get cwq and queue */ cwq = get_cwq(gcwq->cpu, wq); - trace_workqueue_queue_work(cpu, cwq, work); + trace_workqueue_queue_work(req_cpu, cwq, work); if (WARN_ON(!list_empty(&work->entry))) { - spin_unlock_irqrestore(&gcwq->lock, flags); + spin_unlock(&gcwq->lock); return; } @@ -1050,79 +1294,110 @@ static void __queue_work(unsigned int cpu, struct workqueue_struct *wq, insert_work(cwq, work, worklist, work_flags); - spin_unlock_irqrestore(&gcwq->lock, flags); + spin_unlock(&gcwq->lock); } /** - * queue_work - queue work on a workqueue + * queue_work_on - queue work on specific cpu + * @cpu: CPU number to execute work on * @wq: workqueue to use * @work: work to queue * - * Returns 0 if @work was already on a queue, non-zero otherwise. + * Returns %false if @work was already on a queue, %true otherwise. * - * We queue the work to the CPU on which it was submitted, but if the CPU dies - * it can be processed by another CPU. + * We queue the work to a specific CPU, the caller must ensure it + * can't go away. */ -int queue_work(struct workqueue_struct *wq, struct work_struct *work) +bool queue_work_on(int cpu, struct workqueue_struct *wq, + struct work_struct *work) { - int ret; + bool ret = false; + unsigned long flags; - ret = queue_work_on(get_cpu(), wq, work); - put_cpu(); + local_irq_save(flags); + + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { + __queue_work(cpu, wq, work); + ret = true; + } + local_irq_restore(flags); return ret; } -EXPORT_SYMBOL_GPL(queue_work); +EXPORT_SYMBOL_GPL(queue_work_on); /** - * queue_work_on - queue work on specific cpu - * @cpu: CPU number to execute work on + * queue_work - queue work on a workqueue * @wq: workqueue to use * @work: work to queue * - * Returns 0 if @work was already on a queue, non-zero otherwise. + * Returns %false if @work was already on a queue, %true otherwise. * - * We queue the work to a specific CPU, the caller must ensure it - * can't go away. + * We queue the work to the CPU on which it was submitted, but if the CPU dies + * it can be processed by another CPU. */ -int -queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work) +bool queue_work(struct workqueue_struct *wq, struct work_struct *work) { - int ret = 0; - - if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { - __queue_work(cpu, wq, work); - ret = 1; - } - return ret; + return queue_work_on(WORK_CPU_UNBOUND, wq, work); } -EXPORT_SYMBOL_GPL(queue_work_on); +EXPORT_SYMBOL_GPL(queue_work); -static void delayed_work_timer_fn(unsigned long __data) +void delayed_work_timer_fn(unsigned long __data) { struct delayed_work *dwork = (struct delayed_work *)__data; struct cpu_workqueue_struct *cwq = get_work_cwq(&dwork->work); - __queue_work(smp_processor_id(), cwq->wq, &dwork->work); + /* should have been called from irqsafe timer with irq already off */ + __queue_work(dwork->cpu, cwq->wq, &dwork->work); } +EXPORT_SYMBOL_GPL(delayed_work_timer_fn); -/** - * queue_delayed_work - queue work on a workqueue after delay - * @wq: workqueue to use - * @dwork: delayable work to queue - * @delay: number of jiffies to wait before queueing - * - * Returns 0 if @work was already on a queue, non-zero otherwise. - */ -int queue_delayed_work(struct workqueue_struct *wq, - struct delayed_work *dwork, unsigned long delay) +static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, + struct delayed_work *dwork, unsigned long delay) { - if (delay == 0) - return queue_work(wq, &dwork->work); + struct timer_list *timer = &dwork->timer; + struct work_struct *work = &dwork->work; + unsigned int lcpu; + + WARN_ON_ONCE(timer->function != delayed_work_timer_fn || + timer->data != (unsigned long)dwork); + BUG_ON(timer_pending(timer)); + BUG_ON(!list_empty(&work->entry)); + + timer_stats_timer_set_start_info(&dwork->timer); + + /* + * This stores cwq for the moment, for the timer_fn. Note that the + * work's gcwq is preserved to allow reentrance detection for + * delayed works. + */ + if (!(wq->flags & WQ_UNBOUND)) { + struct global_cwq *gcwq = get_work_gcwq(work); - return queue_delayed_work_on(-1, wq, dwork, delay); + /* + * If we cannot get the last gcwq from @work directly, + * select the last CPU such that it avoids unnecessarily + * triggering non-reentrancy check in __queue_work(). + */ + lcpu = cpu; + if (gcwq) + lcpu = gcwq->cpu; + if (lcpu == WORK_CPU_UNBOUND) + lcpu = raw_smp_processor_id(); + } else { + lcpu = WORK_CPU_UNBOUND; + } + + set_work_cwq(work, get_cwq(lcpu, wq), 0); + + dwork->cpu = cpu; + timer->expires = jiffies + delay; + + if (unlikely(cpu != WORK_CPU_UNBOUND)) + add_timer_on(timer, cpu); + else + add_timer(timer); } -EXPORT_SYMBOL_GPL(queue_delayed_work); /** * queue_delayed_work_on - queue work on specific CPU after delay @@ -1131,53 +1406,100 @@ EXPORT_SYMBOL_GPL(queue_delayed_work); * @dwork: work to queue * @delay: number of jiffies to wait before queueing * - * Returns 0 if @work was already on a queue, non-zero otherwise. + * Returns %false if @work was already on a queue, %true otherwise. If + * @delay is zero and @dwork is idle, it will be scheduled for immediate + * execution. */ -int queue_delayed_work_on(int cpu, struct workqueue_struct *wq, - struct delayed_work *dwork, unsigned long delay) +bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, + struct delayed_work *dwork, unsigned long delay) { - int ret = 0; - struct timer_list *timer = &dwork->timer; struct work_struct *work = &dwork->work; + bool ret = false; + unsigned long flags; - if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { - unsigned int lcpu; + if (!delay) + return queue_work_on(cpu, wq, &dwork->work); - BUG_ON(timer_pending(timer)); - BUG_ON(!list_empty(&work->entry)); + /* read the comment in __queue_work() */ + local_irq_save(flags); - timer_stats_timer_set_start_info(&dwork->timer); + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { + __queue_delayed_work(cpu, wq, dwork, delay); + ret = true; + } - /* - * This stores cwq for the moment, for the timer_fn. - * Note that the work's gcwq is preserved to allow - * reentrance detection for delayed works. - */ - if (!(wq->flags & WQ_UNBOUND)) { - struct global_cwq *gcwq = get_work_gcwq(work); + local_irq_restore(flags); + return ret; +} +EXPORT_SYMBOL_GPL(queue_delayed_work_on); - if (gcwq && gcwq->cpu != WORK_CPU_UNBOUND) - lcpu = gcwq->cpu; - else - lcpu = raw_smp_processor_id(); - } else - lcpu = WORK_CPU_UNBOUND; +/** + * queue_delayed_work - queue work on a workqueue after delay + * @wq: workqueue to use + * @dwork: delayable work to queue + * @delay: number of jiffies to wait before queueing + * + * Equivalent to queue_delayed_work_on() but tries to use the local CPU. + */ +bool queue_delayed_work(struct workqueue_struct *wq, + struct delayed_work *dwork, unsigned long delay) +{ + return queue_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); +} +EXPORT_SYMBOL_GPL(queue_delayed_work); - set_work_cwq(work, get_cwq(lcpu, wq), 0); +/** + * mod_delayed_work_on - modify delay of or queue a delayed work on specific CPU + * @cpu: CPU number to execute work on + * @wq: workqueue to use + * @dwork: work to queue + * @delay: number of jiffies to wait before queueing + * + * If @dwork is idle, equivalent to queue_delayed_work_on(); otherwise, + * modify @dwork's timer so that it expires after @delay. If @delay is + * zero, @work is guaranteed to be scheduled immediately regardless of its + * current state. + * + * Returns %false if @dwork was idle and queued, %true if @dwork was + * pending and its timer was modified. + * + * This function is safe to call from any context including IRQ handler. + * See try_to_grab_pending() for details. + */ +bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, + struct delayed_work *dwork, unsigned long delay) +{ + unsigned long flags; + int ret; - timer->expires = jiffies + delay; - timer->data = (unsigned long)dwork; - timer->function = delayed_work_timer_fn; + do { + ret = try_to_grab_pending(&dwork->work, true, &flags); + } while (unlikely(ret == -EAGAIN)); - if (unlikely(cpu >= 0)) - add_timer_on(timer, cpu); - else - add_timer(timer); - ret = 1; + if (likely(ret >= 0)) { + __queue_delayed_work(cpu, wq, dwork, delay); + local_irq_restore(flags); } + + /* -ENOENT from try_to_grab_pending() becomes %true */ return ret; } -EXPORT_SYMBOL_GPL(queue_delayed_work_on); +EXPORT_SYMBOL_GPL(mod_delayed_work_on); + +/** + * mod_delayed_work - modify delay of or queue a delayed work + * @wq: workqueue to use + * @dwork: work to queue + * @delay: number of jiffies to wait before queueing + * + * mod_delayed_work_on() on local CPU. + */ +bool mod_delayed_work(struct workqueue_struct *wq, struct delayed_work *dwork, + unsigned long delay) +{ + return mod_delayed_work_on(WORK_CPU_UNBOUND, wq, dwork, delay); +} +EXPORT_SYMBOL_GPL(mod_delayed_work); /** * worker_enter_idle - enter idle state @@ -1305,37 +1627,21 @@ __acquires(&gcwq->lock) } } -struct idle_rebind { - int cnt; /* # workers to be rebound */ - struct completion done; /* all workers rebound */ -}; - /* - * Rebind an idle @worker to its CPU. During CPU onlining, this has to - * happen synchronously for idle workers. worker_thread() will test - * %WORKER_REBIND before leaving idle and call this function. + * Rebind an idle @worker to its CPU. worker_thread() will test + * list_empty(@worker->entry) before leaving idle and call this function. */ static void idle_worker_rebind(struct worker *worker) { struct global_cwq *gcwq = worker->pool->gcwq; - /* CPU must be online at this point */ - WARN_ON(!worker_maybe_bind_and_lock(worker)); - if (!--worker->idle_rebind->cnt) - complete(&worker->idle_rebind->done); - spin_unlock_irq(&worker->pool->gcwq->lock); + /* CPU may go down again inbetween, clear UNBOUND only on success */ + if (worker_maybe_bind_and_lock(worker)) + worker_clr_flags(worker, WORKER_UNBOUND); - /* we did our part, wait for rebind_workers() to finish up */ - wait_event(gcwq->rebind_hold, !(worker->flags & WORKER_REBIND)); - - /* - * rebind_workers() shouldn't finish until all workers passed the - * above WORKER_REBIND wait. Tell it when done. - */ - spin_lock_irq(&worker->pool->gcwq->lock); - if (!--worker->idle_rebind->cnt) - complete(&worker->idle_rebind->done); - spin_unlock_irq(&worker->pool->gcwq->lock); + /* rebind complete, become available again */ + list_add(&worker->entry, &worker->pool->idle_list); + spin_unlock_irq(&gcwq->lock); } /* @@ -1349,16 +1655,8 @@ static void busy_worker_rebind_fn(struct work_struct *work) struct worker *worker = container_of(work, struct worker, rebind_work); struct global_cwq *gcwq = worker->pool->gcwq; - worker_maybe_bind_and_lock(worker); - - /* - * %WORKER_REBIND must be cleared even if the above binding failed; - * otherwise, we may confuse the next CPU_UP cycle or oops / get - * stuck by calling idle_worker_rebind() prematurely. If CPU went - * down again inbetween, %WORKER_UNBOUND would be set, so clearing - * %WORKER_REBIND is always safe. - */ - worker_clr_flags(worker, WORKER_REBIND); + if (worker_maybe_bind_and_lock(worker)) + worker_clr_flags(worker, WORKER_UNBOUND); spin_unlock_irq(&gcwq->lock); } @@ -1370,123 +1668,74 @@ static void busy_worker_rebind_fn(struct work_struct *work) * @gcwq->cpu is coming online. Rebind all workers to the CPU. Rebinding * is different for idle and busy ones. * - * The idle ones should be rebound synchronously and idle rebinding should - * be complete before any worker starts executing work items with - * concurrency management enabled; otherwise, scheduler may oops trying to - * wake up non-local idle worker from wq_worker_sleeping(). + * Idle ones will be removed from the idle_list and woken up. They will + * add themselves back after completing rebind. This ensures that the + * idle_list doesn't contain any unbound workers when re-bound busy workers + * try to perform local wake-ups for concurrency management. * - * This is achieved by repeatedly requesting rebinding until all idle - * workers are known to have been rebound under @gcwq->lock and holding all - * idle workers from becoming busy until idle rebinding is complete. + * Busy workers can rebind after they finish their current work items. + * Queueing the rebind work item at the head of the scheduled list is + * enough. Note that nr_running will be properly bumped as busy workers + * rebind. * - * Once idle workers are rebound, busy workers can be rebound as they - * finish executing their current work items. Queueing the rebind work at - * the head of their scheduled lists is enough. Note that nr_running will - * be properbly bumped as busy workers rebind. - * - * On return, all workers are guaranteed to either be bound or have rebind - * work item scheduled. + * On return, all non-manager workers are scheduled for rebind - see + * manage_workers() for the manager special case. Any idle worker + * including the manager will not appear on @idle_list until rebind is + * complete, making local wake-ups safe. */ static void rebind_workers(struct global_cwq *gcwq) - __releases(&gcwq->lock) __acquires(&gcwq->lock) { - struct idle_rebind idle_rebind; struct worker_pool *pool; - struct worker *worker; + struct worker *worker, *n; struct hlist_node *pos; int i; lockdep_assert_held(&gcwq->lock); for_each_worker_pool(pool, gcwq) - lockdep_assert_held(&pool->manager_mutex); + lockdep_assert_held(&pool->assoc_mutex); - /* - * Rebind idle workers. Interlocked both ways. We wait for - * workers to rebind via @idle_rebind.done. Workers will wait for - * us to finish up by watching %WORKER_REBIND. - */ - init_completion(&idle_rebind.done); -retry: - idle_rebind.cnt = 1; - INIT_COMPLETION(idle_rebind.done); - - /* set REBIND and kick idle ones, we'll wait for these later */ + /* dequeue and kick idle ones */ for_each_worker_pool(pool, gcwq) { - list_for_each_entry(worker, &pool->idle_list, entry) { - unsigned long worker_flags = worker->flags; - - if (worker->flags & WORKER_REBIND) - continue; - - /* morph UNBOUND to REBIND atomically */ - worker_flags &= ~WORKER_UNBOUND; - worker_flags |= WORKER_REBIND; - ACCESS_ONCE(worker->flags) = worker_flags; - - idle_rebind.cnt++; - worker->idle_rebind = &idle_rebind; + list_for_each_entry_safe(worker, n, &pool->idle_list, entry) { + /* + * idle workers should be off @pool->idle_list + * until rebind is complete to avoid receiving + * premature local wake-ups. + */ + list_del_init(&worker->entry); - /* worker_thread() will call idle_worker_rebind() */ + /* + * worker_thread() will see the above dequeuing + * and call idle_worker_rebind(). + */ wake_up_process(worker->task); } } - if (--idle_rebind.cnt) { - spin_unlock_irq(&gcwq->lock); - wait_for_completion(&idle_rebind.done); - spin_lock_irq(&gcwq->lock); - /* busy ones might have become idle while waiting, retry */ - goto retry; - } - - /* all idle workers are rebound, rebind busy workers */ + /* rebind busy workers */ for_each_busy_worker(worker, i, pos, gcwq) { struct work_struct *rebind_work = &worker->rebind_work; - unsigned long worker_flags = worker->flags; - - /* morph UNBOUND to REBIND atomically */ - worker_flags &= ~WORKER_UNBOUND; - worker_flags |= WORKER_REBIND; - ACCESS_ONCE(worker->flags) = worker_flags; + struct workqueue_struct *wq; if (test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(rebind_work))) continue; - /* wq doesn't matter, use the default one */ debug_work_activate(rebind_work); - insert_work(get_cwq(gcwq->cpu, system_wq), rebind_work, - worker->scheduled.next, - work_color_to_flags(WORK_NO_COLOR)); - } - - /* - * All idle workers are rebound and waiting for %WORKER_REBIND to - * be cleared inside idle_worker_rebind(). Clear and release. - * Clearing %WORKER_REBIND from this foreign context is safe - * because these workers are still guaranteed to be idle. - * - * We need to make sure all idle workers passed WORKER_REBIND wait - * in idle_worker_rebind() before returning; otherwise, workers can - * get stuck at the wait if hotplug cycle repeats. - */ - idle_rebind.cnt = 1; - INIT_COMPLETION(idle_rebind.done); - - for_each_worker_pool(pool, gcwq) { - list_for_each_entry(worker, &pool->idle_list, entry) { - worker->flags &= ~WORKER_REBIND; - idle_rebind.cnt++; - } - } - wake_up_all(&gcwq->rebind_hold); + /* + * wq doesn't really matter but let's keep @worker->pool + * and @cwq->pool consistent for sanity. + */ + if (worker_pool_pri(worker->pool)) + wq = system_highpri_wq; + else + wq = system_wq; - if (--idle_rebind.cnt) { - spin_unlock_irq(&gcwq->lock); - wait_for_completion(&idle_rebind.done); - spin_lock_irq(&gcwq->lock); + insert_work(get_cwq(gcwq->cpu, wq), rebind_work, + worker->scheduled.next, + work_color_to_flags(WORK_NO_COLOR)); } } @@ -1844,22 +2093,22 @@ static bool manage_workers(struct worker *worker) * grab %POOL_MANAGING_WORKERS to achieve this because that can * lead to idle worker depletion (all become busy thinking someone * else is managing) which in turn can result in deadlock under - * extreme circumstances. Use @pool->manager_mutex to synchronize + * extreme circumstances. Use @pool->assoc_mutex to synchronize * manager against CPU hotplug. * - * manager_mutex would always be free unless CPU hotplug is in + * assoc_mutex would always be free unless CPU hotplug is in * progress. trylock first without dropping @gcwq->lock. */ - if (unlikely(!mutex_trylock(&pool->manager_mutex))) { + if (unlikely(!mutex_trylock(&pool->assoc_mutex))) { spin_unlock_irq(&pool->gcwq->lock); - mutex_lock(&pool->manager_mutex); + mutex_lock(&pool->assoc_mutex); /* * CPU hotplug could have happened while we were waiting - * for manager_mutex. Hotplug itself can't handle us + * for assoc_mutex. Hotplug itself can't handle us * because manager isn't either on idle or busy list, and * @gcwq's state and ours could have deviated. * - * As hotplug is now excluded via manager_mutex, we can + * As hotplug is now excluded via assoc_mutex, we can * simply try to bind. It will succeed or fail depending * on @gcwq's current state. Try it and adjust * %WORKER_UNBOUND accordingly. @@ -1882,112 +2131,11 @@ static bool manage_workers(struct worker *worker) ret |= maybe_create_worker(pool); pool->flags &= ~POOL_MANAGING_WORKERS; - mutex_unlock(&pool->manager_mutex); + mutex_unlock(&pool->assoc_mutex); return ret; } /** - * move_linked_works - move linked works to a list - * @work: start of series of works to be scheduled - * @head: target list to append @work to - * @nextp: out paramter for nested worklist walking - * - * Schedule linked works starting from @work to @head. Work series to - * be scheduled starts at @work and includes any consecutive work with - * WORK_STRUCT_LINKED set in its predecessor. - * - * If @nextp is not NULL, it's updated to point to the next work of - * the last scheduled work. This allows move_linked_works() to be - * nested inside outer list_for_each_entry_safe(). - * - * CONTEXT: - * spin_lock_irq(gcwq->lock). - */ -static void move_linked_works(struct work_struct *work, struct list_head *head, - struct work_struct **nextp) -{ - struct work_struct *n; - - /* - * Linked worklist will always end before the end of the list, - * use NULL for list head. - */ - list_for_each_entry_safe_from(work, n, NULL, entry) { - list_move_tail(&work->entry, head); - if (!(*work_data_bits(work) & WORK_STRUCT_LINKED)) - break; - } - - /* - * If we're already inside safe list traversal and have moved - * multiple works to the scheduled queue, the next position - * needs to be updated. - */ - if (nextp) - *nextp = n; -} - -static void cwq_activate_first_delayed(struct cpu_workqueue_struct *cwq) -{ - struct work_struct *work = list_first_entry(&cwq->delayed_works, - struct work_struct, entry); - - trace_workqueue_activate_work(work); - move_linked_works(work, &cwq->pool->worklist, NULL); - __clear_bit(WORK_STRUCT_DELAYED_BIT, work_data_bits(work)); - cwq->nr_active++; -} - -/** - * cwq_dec_nr_in_flight - decrement cwq's nr_in_flight - * @cwq: cwq of interest - * @color: color of work which left the queue - * @delayed: for a delayed work - * - * A work either has completed or is removed from pending queue, - * decrement nr_in_flight of its cwq and handle workqueue flushing. - * - * CONTEXT: - * spin_lock_irq(gcwq->lock). - */ -static void cwq_dec_nr_in_flight(struct cpu_workqueue_struct *cwq, int color, - bool delayed) -{ - /* ignore uncolored works */ - if (color == WORK_NO_COLOR) - return; - - cwq->nr_in_flight[color]--; - - if (!delayed) { - cwq->nr_active--; - if (!list_empty(&cwq->delayed_works)) { - /* one down, submit a delayed one */ - if (cwq->nr_active < cwq->max_active) - cwq_activate_first_delayed(cwq); - } - } - - /* is flush in progress and are we at the flushing tip? */ - if (likely(cwq->flush_color != color)) - return; - - /* are there still in-flight works? */ - if (cwq->nr_in_flight[color]) - return; - - /* this cwq is done, clear flush_color */ - cwq->flush_color = -1; - - /* - * If this was the last cwq, wake up the first flusher. It - * will handle the rest. - */ - if (atomic_dec_and_test(&cwq->wq->nr_cwqs_to_flush)) - complete(&cwq->wq->first_flusher->done); -} - -/** * process_one_work - process single work * @worker: self * @work: work to process @@ -2030,7 +2178,7 @@ __acquires(&gcwq->lock) * necessary to avoid spurious warnings from rescuers servicing the * unbound or a disassociated gcwq. */ - WARN_ON_ONCE(!(worker->flags & (WORKER_UNBOUND | WORKER_REBIND)) && + WARN_ON_ONCE(!(worker->flags & WORKER_UNBOUND) && !(gcwq->flags & GCWQ_DISASSOCIATED) && raw_smp_processor_id() != gcwq->cpu); @@ -2046,15 +2194,13 @@ __acquires(&gcwq->lock) return; } - /* claim and process */ + /* claim and dequeue */ debug_work_deactivate(work); hlist_add_head(&worker->hentry, bwh); worker->current_work = work; worker->current_cwq = cwq; work_color = get_work_color(work); - /* record the current cpu number in the work data and dequeue */ - set_work_cpu(work, gcwq->cpu); list_del_init(&work->entry); /* @@ -2071,9 +2217,16 @@ __acquires(&gcwq->lock) if ((worker->flags & WORKER_UNBOUND) && need_more_worker(pool)) wake_up_worker(pool); + /* + * Record the last CPU and clear PENDING which should be the last + * update to @work. Also, do this inside @gcwq->lock so that + * PENDING and queued state changes happen together while IRQ is + * disabled. + */ + set_work_cpu_and_clear_pending(work, gcwq->cpu); + spin_unlock_irq(&gcwq->lock); - work_clear_pending(work); lock_map_acquire_read(&cwq->wq->lockdep_map); lock_map_acquire(&lockdep_map); trace_workqueue_execute_start(work); @@ -2087,11 +2240,9 @@ __acquires(&gcwq->lock) lock_map_release(&cwq->wq->lockdep_map); if (unlikely(in_atomic() || lockdep_depth(current) > 0)) { - printk(KERN_ERR "BUG: workqueue leaked lock or atomic: " - "%s/0x%08x/%d\n", - current->comm, preempt_count(), task_pid_nr(current)); - printk(KERN_ERR " last function: "); - print_symbol("%s\n", (unsigned long)f); + pr_err("BUG: workqueue leaked lock or atomic: %s/0x%08x/%d\n" + " last function: %pf\n", + current->comm, preempt_count(), task_pid_nr(current), f); debug_show_held_locks(current); dump_stack(); } @@ -2106,7 +2257,7 @@ __acquires(&gcwq->lock) hlist_del_init(&worker->hentry); worker->current_work = NULL; worker->current_cwq = NULL; - cwq_dec_nr_in_flight(cwq, work_color, false); + cwq_dec_nr_in_flight(cwq, work_color); } /** @@ -2151,18 +2302,17 @@ static int worker_thread(void *__worker) woke_up: spin_lock_irq(&gcwq->lock); - /* - * DIE can be set only while idle and REBIND set while busy has - * @worker->rebind_work scheduled. Checking here is enough. - */ - if (unlikely(worker->flags & (WORKER_REBIND | WORKER_DIE))) { + /* we are off idle list if destruction or rebind is requested */ + if (unlikely(list_empty(&worker->entry))) { spin_unlock_irq(&gcwq->lock); + /* if DIE is set, destruction is requested */ if (worker->flags & WORKER_DIE) { worker->task->flags &= ~PF_WQ_WORKER; return 0; } + /* otherwise, rebind */ idle_worker_rebind(worker); goto woke_up; } @@ -2645,8 +2795,8 @@ reflush: if (++flush_cnt == 10 || (flush_cnt % 100 == 0 && flush_cnt <= 1000)) - pr_warning("workqueue %s: flush on destruction isn't complete after %u tries\n", - wq->name, flush_cnt); + pr_warn("workqueue %s: flush on destruction isn't complete after %u tries\n", + wq->name, flush_cnt); goto reflush; } @@ -2657,8 +2807,7 @@ reflush: } EXPORT_SYMBOL_GPL(drain_workqueue); -static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, - bool wait_executing) +static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr) { struct worker *worker = NULL; struct global_cwq *gcwq; @@ -2680,13 +2829,12 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, cwq = get_work_cwq(work); if (unlikely(!cwq || gcwq != cwq->pool->gcwq)) goto already_gone; - } else if (wait_executing) { + } else { worker = find_worker_executing_work(gcwq, work); if (!worker) goto already_gone; cwq = worker->current_cwq; - } else - goto already_gone; + } insert_wq_barrier(cwq, barr, work, worker); spin_unlock_irq(&gcwq->lock); @@ -2713,15 +2861,8 @@ already_gone: * flush_work - wait for a work to finish executing the last queueing instance * @work: the work to flush * - * Wait until @work has finished execution. This function considers - * only the last queueing instance of @work. If @work has been - * enqueued across different CPUs on a non-reentrant workqueue or on - * multiple workqueues, @work might still be executing on return on - * some of the CPUs from earlier queueing. - * - * If @work was queued only on a non-reentrant, ordered or unbound - * workqueue, @work is guaranteed to be idle on return if it hasn't - * been requeued since flush started. + * Wait until @work has finished execution. @work is guaranteed to be idle + * on return if it hasn't been requeued since flush started. * * RETURNS: * %true if flush_work() waited for the work to finish execution, @@ -2734,140 +2875,36 @@ bool flush_work(struct work_struct *work) lock_map_acquire(&work->lockdep_map); lock_map_release(&work->lockdep_map); - if (start_flush_work(work, &barr, true)) { + if (start_flush_work(work, &barr)) { wait_for_completion(&barr.done); destroy_work_on_stack(&barr.work); return true; - } else - return false; -} -EXPORT_SYMBOL_GPL(flush_work); - -static bool wait_on_cpu_work(struct global_cwq *gcwq, struct work_struct *work) -{ - struct wq_barrier barr; - struct worker *worker; - - spin_lock_irq(&gcwq->lock); - - worker = find_worker_executing_work(gcwq, work); - if (unlikely(worker)) - insert_wq_barrier(worker->current_cwq, &barr, work, worker); - - spin_unlock_irq(&gcwq->lock); - - if (unlikely(worker)) { - wait_for_completion(&barr.done); - destroy_work_on_stack(&barr.work); - return true; - } else + } else { return false; -} - -static bool wait_on_work(struct work_struct *work) -{ - bool ret = false; - int cpu; - - might_sleep(); - - lock_map_acquire(&work->lockdep_map); - lock_map_release(&work->lockdep_map); - - for_each_gcwq_cpu(cpu) - ret |= wait_on_cpu_work(get_gcwq(cpu), work); - return ret; -} - -/** - * flush_work_sync - wait until a work has finished execution - * @work: the work to flush - * - * Wait until @work has finished execution. On return, it's - * guaranteed that all queueing instances of @work which happened - * before this function is called are finished. In other words, if - * @work hasn't been requeued since this function was called, @work is - * guaranteed to be idle on return. - * - * RETURNS: - * %true if flush_work_sync() waited for the work to finish execution, - * %false if it was already idle. - */ -bool flush_work_sync(struct work_struct *work) -{ - struct wq_barrier barr; - bool pending, waited; - - /* we'll wait for executions separately, queue barr only if pending */ - pending = start_flush_work(work, &barr, false); - - /* wait for executions to finish */ - waited = wait_on_work(work); - - /* wait for the pending one */ - if (pending) { - wait_for_completion(&barr.done); - destroy_work_on_stack(&barr.work); } - - return pending || waited; -} -EXPORT_SYMBOL_GPL(flush_work_sync); - -/* - * Upon a successful return (>= 0), the caller "owns" WORK_STRUCT_PENDING bit, - * so this work can't be re-armed in any way. - */ -static int try_to_grab_pending(struct work_struct *work) -{ - struct global_cwq *gcwq; - int ret = -1; - - if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) - return 0; - - /* - * The queueing is in progress, or it is already queued. Try to - * steal it from ->worklist without clearing WORK_STRUCT_PENDING. - */ - gcwq = get_work_gcwq(work); - if (!gcwq) - return ret; - - spin_lock_irq(&gcwq->lock); - if (!list_empty(&work->entry)) { - /* - * This work is queued, but perhaps we locked the wrong gcwq. - * In that case we must see the new value after rmb(), see - * insert_work()->wmb(). - */ - smp_rmb(); - if (gcwq == get_work_gcwq(work)) { - debug_work_deactivate(work); - list_del_init(&work->entry); - cwq_dec_nr_in_flight(get_work_cwq(work), - get_work_color(work), - *work_data_bits(work) & WORK_STRUCT_DELAYED); - ret = 1; - } - } - spin_unlock_irq(&gcwq->lock); - - return ret; } +EXPORT_SYMBOL_GPL(flush_work); -static bool __cancel_work_timer(struct work_struct *work, - struct timer_list* timer) +static bool __cancel_work_timer(struct work_struct *work, bool is_dwork) { + unsigned long flags; int ret; do { - ret = (timer && likely(del_timer(timer))); - if (!ret) - ret = try_to_grab_pending(work); - wait_on_work(work); + ret = try_to_grab_pending(work, is_dwork, &flags); + /* + * If someone else is canceling, wait for the same event it + * would be waiting for before retrying. + */ + if (unlikely(ret == -ENOENT)) + flush_work(work); } while (unlikely(ret < 0)); + /* tell other tasks trying to grab @work to back off */ + mark_work_canceling(work); + local_irq_restore(flags); + + flush_work(work); clear_work_data(work); return ret; } @@ -2892,7 +2929,7 @@ static bool __cancel_work_timer(struct work_struct *work, */ bool cancel_work_sync(struct work_struct *work) { - return __cancel_work_timer(work, NULL); + return __cancel_work_timer(work, false); } EXPORT_SYMBOL_GPL(cancel_work_sync); @@ -2910,33 +2947,44 @@ EXPORT_SYMBOL_GPL(cancel_work_sync); */ bool flush_delayed_work(struct delayed_work *dwork) { + local_irq_disable(); if (del_timer_sync(&dwork->timer)) - __queue_work(raw_smp_processor_id(), + __queue_work(dwork->cpu, get_work_cwq(&dwork->work)->wq, &dwork->work); + local_irq_enable(); return flush_work(&dwork->work); } EXPORT_SYMBOL(flush_delayed_work); /** - * flush_delayed_work_sync - wait for a dwork to finish - * @dwork: the delayed work to flush + * cancel_delayed_work - cancel a delayed work + * @dwork: delayed_work to cancel * - * Delayed timer is cancelled and the pending work is queued for - * execution immediately. Other than timer handling, its behavior - * is identical to flush_work_sync(). + * Kill off a pending delayed_work. Returns %true if @dwork was pending + * and canceled; %false if wasn't pending. Note that the work callback + * function may still be running on return, unless it returns %true and the + * work doesn't re-arm itself. Explicitly flush or use + * cancel_delayed_work_sync() to wait on it. * - * RETURNS: - * %true if flush_work_sync() waited for the work to finish execution, - * %false if it was already idle. + * This function is safe to call from any context including IRQ handler. */ -bool flush_delayed_work_sync(struct delayed_work *dwork) +bool cancel_delayed_work(struct delayed_work *dwork) { - if (del_timer_sync(&dwork->timer)) - __queue_work(raw_smp_processor_id(), - get_work_cwq(&dwork->work)->wq, &dwork->work); - return flush_work_sync(&dwork->work); + unsigned long flags; + int ret; + + do { + ret = try_to_grab_pending(&dwork->work, true, &flags); + } while (unlikely(ret == -EAGAIN)); + + if (unlikely(ret < 0)) + return false; + + set_work_cpu_and_clear_pending(&dwork->work, work_cpu(&dwork->work)); + local_irq_restore(flags); + return ret; } -EXPORT_SYMBOL(flush_delayed_work_sync); +EXPORT_SYMBOL(cancel_delayed_work); /** * cancel_delayed_work_sync - cancel a delayed work and wait for it to finish @@ -2949,54 +2997,39 @@ EXPORT_SYMBOL(flush_delayed_work_sync); */ bool cancel_delayed_work_sync(struct delayed_work *dwork) { - return __cancel_work_timer(&dwork->work, &dwork->timer); + return __cancel_work_timer(&dwork->work, true); } EXPORT_SYMBOL(cancel_delayed_work_sync); /** - * schedule_work - put work task in global workqueue - * @work: job to be done - * - * Returns zero if @work was already on the kernel-global workqueue and - * non-zero otherwise. - * - * This puts a job in the kernel-global workqueue if it was not already - * queued and leaves it in the same position on the kernel-global - * workqueue otherwise. - */ -int schedule_work(struct work_struct *work) -{ - return queue_work(system_wq, work); -} -EXPORT_SYMBOL(schedule_work); - -/* * schedule_work_on - put work task on a specific cpu * @cpu: cpu to put the work task on * @work: job to be done * * This puts a job on a specific cpu */ -int schedule_work_on(int cpu, struct work_struct *work) +bool schedule_work_on(int cpu, struct work_struct *work) { return queue_work_on(cpu, system_wq, work); } EXPORT_SYMBOL(schedule_work_on); /** - * schedule_delayed_work - put work task in global workqueue after delay - * @dwork: job to be done - * @delay: number of jiffies to wait or 0 for immediate execution + * schedule_work - put work task in global workqueue + * @work: job to be done * - * After waiting for a given time this puts a job in the kernel-global - * workqueue. + * Returns %false if @work was already on the kernel-global workqueue and + * %true otherwise. + * + * This puts a job in the kernel-global workqueue if it was not already + * queued and leaves it in the same position on the kernel-global + * workqueue otherwise. */ -int schedule_delayed_work(struct delayed_work *dwork, - unsigned long delay) +bool schedule_work(struct work_struct *work) { - return queue_delayed_work(system_wq, dwork, delay); + return queue_work(system_wq, work); } -EXPORT_SYMBOL(schedule_delayed_work); +EXPORT_SYMBOL(schedule_work); /** * schedule_delayed_work_on - queue work in global workqueue on CPU after delay @@ -3007,14 +3040,28 @@ EXPORT_SYMBOL(schedule_delayed_work); * After waiting for a given time this puts a job in the kernel-global * workqueue on the specified CPU. */ -int schedule_delayed_work_on(int cpu, - struct delayed_work *dwork, unsigned long delay) +bool schedule_delayed_work_on(int cpu, struct delayed_work *dwork, + unsigned long delay) { return queue_delayed_work_on(cpu, system_wq, dwork, delay); } EXPORT_SYMBOL(schedule_delayed_work_on); /** + * schedule_delayed_work - put work task in global workqueue after delay + * @dwork: job to be done + * @delay: number of jiffies to wait or 0 for immediate execution + * + * After waiting for a given time this puts a job in the kernel-global + * workqueue. + */ +bool schedule_delayed_work(struct delayed_work *dwork, unsigned long delay) +{ + return queue_delayed_work(system_wq, dwork, delay); +} +EXPORT_SYMBOL(schedule_delayed_work); + +/** * schedule_on_each_cpu - execute a function synchronously on each online CPU * @func: the function to call * @@ -3161,9 +3208,8 @@ static int wq_clamp_max_active(int max_active, unsigned int flags, int lim = flags & WQ_UNBOUND ? WQ_UNBOUND_MAX_ACTIVE : WQ_MAX_ACTIVE; if (max_active < 1 || max_active > lim) - printk(KERN_WARNING "workqueue: max_active %d requested for %s " - "is out of range, clamping between %d and %d\n", - max_active, name, 1, lim); + pr_warn("workqueue: max_active %d requested for %s is out of range, clamping between %d and %d\n", + max_active, name, 1, lim); return clamp_val(max_active, 1, lim); } @@ -3319,6 +3365,26 @@ void destroy_workqueue(struct workqueue_struct *wq) EXPORT_SYMBOL_GPL(destroy_workqueue); /** + * cwq_set_max_active - adjust max_active of a cwq + * @cwq: target cpu_workqueue_struct + * @max_active: new max_active value. + * + * Set @cwq->max_active to @max_active and activate delayed works if + * increased. + * + * CONTEXT: + * spin_lock_irq(gcwq->lock). + */ +static void cwq_set_max_active(struct cpu_workqueue_struct *cwq, int max_active) +{ + cwq->max_active = max_active; + + while (!list_empty(&cwq->delayed_works) && + cwq->nr_active < cwq->max_active) + cwq_activate_first_delayed(cwq); +} + +/** * workqueue_set_max_active - adjust max_active of a workqueue * @wq: target workqueue * @max_active: new max_active value. @@ -3345,7 +3411,7 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) if (!(wq->flags & WQ_FREEZABLE) || !(gcwq->flags & GCWQ_FREEZING)) - get_cwq(gcwq->cpu, wq)->max_active = max_active; + cwq_set_max_active(get_cwq(gcwq->cpu, wq), max_active); spin_unlock_irq(&gcwq->lock); } @@ -3440,23 +3506,23 @@ EXPORT_SYMBOL_GPL(work_busy); */ /* claim manager positions of all pools */ -static void gcwq_claim_management_and_lock(struct global_cwq *gcwq) +static void gcwq_claim_assoc_and_lock(struct global_cwq *gcwq) { struct worker_pool *pool; for_each_worker_pool(pool, gcwq) - mutex_lock_nested(&pool->manager_mutex, pool - gcwq->pools); + mutex_lock_nested(&pool->assoc_mutex, pool - gcwq->pools); spin_lock_irq(&gcwq->lock); } /* release manager positions */ -static void gcwq_release_management_and_unlock(struct global_cwq *gcwq) +static void gcwq_release_assoc_and_unlock(struct global_cwq *gcwq) { struct worker_pool *pool; spin_unlock_irq(&gcwq->lock); for_each_worker_pool(pool, gcwq) - mutex_unlock(&pool->manager_mutex); + mutex_unlock(&pool->assoc_mutex); } static void gcwq_unbind_fn(struct work_struct *work) @@ -3469,7 +3535,7 @@ static void gcwq_unbind_fn(struct work_struct *work) BUG_ON(gcwq->cpu != smp_processor_id()); - gcwq_claim_management_and_lock(gcwq); + gcwq_claim_assoc_and_lock(gcwq); /* * We've claimed all manager positions. Make all workers unbound @@ -3486,7 +3552,7 @@ static void gcwq_unbind_fn(struct work_struct *work) gcwq->flags |= GCWQ_DISASSOCIATED; - gcwq_release_management_and_unlock(gcwq); + gcwq_release_assoc_and_unlock(gcwq); /* * Call schedule() so that we cross rq->lock and thus can guarantee @@ -3514,7 +3580,7 @@ static void gcwq_unbind_fn(struct work_struct *work) * Workqueues should be brought up before normal priority CPU notifiers. * This will be registered high priority CPU notifier. */ -static int __devinit workqueue_cpu_up_callback(struct notifier_block *nfb, +static int __cpuinit workqueue_cpu_up_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { @@ -3542,10 +3608,10 @@ static int __devinit workqueue_cpu_up_callback(struct notifier_block *nfb, case CPU_DOWN_FAILED: case CPU_ONLINE: - gcwq_claim_management_and_lock(gcwq); + gcwq_claim_assoc_and_lock(gcwq); gcwq->flags &= ~GCWQ_DISASSOCIATED; rebind_workers(gcwq); - gcwq_release_management_and_unlock(gcwq); + gcwq_release_assoc_and_unlock(gcwq); break; } return NOTIFY_OK; @@ -3555,7 +3621,7 @@ static int __devinit workqueue_cpu_up_callback(struct notifier_block *nfb, * Workqueues should be brought down after normal priority CPU notifiers. * This will be registered as low priority CPU notifier. */ -static int __devinit workqueue_cpu_down_callback(struct notifier_block *nfb, +static int __cpuinit workqueue_cpu_down_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { @@ -3566,7 +3632,7 @@ static int __devinit workqueue_cpu_down_callback(struct notifier_block *nfb, case CPU_DOWN_PREPARE: /* unbinding should happen on the local CPU */ INIT_WORK_ONSTACK(&unbind_work, gcwq_unbind_fn); - schedule_work_on(cpu, &unbind_work); + queue_work_on(cpu, system_highpri_wq, &unbind_work); flush_work(&unbind_work); break; } @@ -3735,11 +3801,7 @@ void thaw_workqueues(void) continue; /* restore max_active and repopulate worklist */ - cwq->max_active = wq->saved_max_active; - - while (!list_empty(&cwq->delayed_works) && - cwq->nr_active < cwq->max_active) - cwq_activate_first_delayed(cwq); + cwq_set_max_active(cwq, wq->saved_max_active); } for_each_worker_pool(pool, gcwq) @@ -3759,8 +3821,12 @@ static int __init init_workqueues(void) unsigned int cpu; int i; + /* make sure we have enough bits for OFFQ CPU number */ + BUILD_BUG_ON((1LU << (BITS_PER_LONG - WORK_OFFQ_CPU_SHIFT)) < + WORK_CPU_LAST); + cpu_notifier(workqueue_cpu_up_callback, CPU_PRI_WORKQUEUE_UP); - cpu_notifier(workqueue_cpu_down_callback, CPU_PRI_WORKQUEUE_DOWN); + hotcpu_notifier(workqueue_cpu_down_callback, CPU_PRI_WORKQUEUE_DOWN); /* initialize gcwqs */ for_each_gcwq_cpu(cpu) { @@ -3786,11 +3852,9 @@ static int __init init_workqueues(void) setup_timer(&pool->mayday_timer, gcwq_mayday_timeout, (unsigned long)pool); - mutex_init(&pool->manager_mutex); + mutex_init(&pool->assoc_mutex); ida_init(&pool->worker_ida); } - - init_waitqueue_head(&gcwq->rebind_hold); } /* create the initial worker */ @@ -3813,17 +3877,14 @@ static int __init init_workqueues(void) } system_wq = alloc_workqueue("events", 0, 0); + system_highpri_wq = alloc_workqueue("events_highpri", WQ_HIGHPRI, 0); system_long_wq = alloc_workqueue("events_long", 0, 0); - system_nrt_wq = alloc_workqueue("events_nrt", WQ_NON_REENTRANT, 0); system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_UNBOUND_MAX_ACTIVE); system_freezable_wq = alloc_workqueue("events_freezable", WQ_FREEZABLE, 0); - system_nrt_freezable_wq = alloc_workqueue("events_nrt_freezable", - WQ_NON_REENTRANT | WQ_FREEZABLE, 0); - BUG_ON(!system_wq || !system_long_wq || !system_nrt_wq || - !system_unbound_wq || !system_freezable_wq || - !system_nrt_freezable_wq); + BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq || + !system_unbound_wq || !system_freezable_wq); return 0; } early_initcall(init_workqueues); |