diff options
44 files changed, 525 insertions, 313 deletions
diff --git a/Documentation/cgroups/memcg_test.txt b/Documentation/cgroups/memcg_test.txt index 19533f93b7a..523a9c16c40 100644 --- a/Documentation/cgroups/memcg_test.txt +++ b/Documentation/cgroups/memcg_test.txt @@ -1,6 +1,6 @@ Memory Resource Controller(Memcg) Implementation Memo. -Last Updated: 2008/12/15 -Base Kernel Version: based on 2.6.28-rc8-mm. +Last Updated: 2009/1/19 +Base Kernel Version: based on 2.6.29-rc2. Because VM is getting complex (one of reasons is memcg...), memcg's behavior is complex. This is a document for memcg's internal behavior. @@ -340,3 +340,23 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y. # mount -t cgroup none /cgroup -t cpuset,memory,cpu,devices and do task move, mkdir, rmdir etc...under this. + + 9.7 swapoff. + Besides management of swap is one of complicated parts of memcg, + call path of swap-in at swapoff is not same as usual swap-in path.. + It's worth to be tested explicitly. + + For example, test like following is good. + (Shell-A) + # mount -t cgroup none /cgroup -t memory + # mkdir /cgroup/test + # echo 40M > /cgroup/test/memory.limit_in_bytes + # echo 0 > /cgroup/test/tasks + Run malloc(100M) program under this. You'll see 60M of swaps. + (Shell-B) + # move all tasks in /cgroup/test to /cgroup + # /sbin/swapoff -a + # rmdir /test/cgroup + # kill malloc task. + + Of course, tmpfs v.s. swapoff test should be tested, too. diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index bbebc3a43ac..a87be42f821 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -2027,6 +2027,34 @@ increase the likelihood of this process being killed by the oom-killer. Valid values are in the range -16 to +15, plus the special value -17, which disables oom-killing altogether for this process. +The process to be killed in an out-of-memory situation is selected among all others +based on its badness score. This value equals the original memory size of the process +and is then updated according to its CPU time (utime + stime) and the +run time (uptime - start time). The longer it runs the smaller is the score. +Badness score is divided by the square root of the CPU time and then by +the double square root of the run time. + +Swapped out tasks are killed first. Half of each child's memory size is added to +the parent's score if they do not share the same memory. Thus forking servers +are the prime candidates to be killed. Having only one 'hungry' child will make +parent less preferable than the child. + +/proc/<pid>/oom_score shows process' current badness score. + +The following heuristics are then applied: + * if the task was reniced, its score doubles + * superuser or direct hardware access tasks (CAP_SYS_ADMIN, CAP_SYS_RESOURCE + or CAP_SYS_RAWIO) have their score divided by 4 + * if oom condition happened in one cpuset and checked task does not belong + to it, its score is divided by 8 + * the resulting score is multiplied by two to the power of oom_adj, i.e. + points <<= oom_adj when it is positive and + points >>= -(oom_adj) otherwise + +The task with the highest badness score is then selected and its children +are killed, process itself will be killed in an OOM situation when it does +not have children or some of them disabled oom like described above. + 2.13 /proc/<pid>/oom_score - Display current oom-killer score ------------------------------------------------------------- diff --git a/Documentation/lguest/Makefile b/Documentation/lguest/Makefile index 725eef81cd4..1f4f9e888bd 100644 --- a/Documentation/lguest/Makefile +++ b/Documentation/lguest/Makefile @@ -1,5 +1,5 @@ # This creates the demonstration utility "lguest" which runs a Linux guest. -CFLAGS:=-Wall -Wmissing-declarations -Wmissing-prototypes -O3 -I../../include -I../../arch/x86/include +CFLAGS:=-Wall -Wmissing-declarations -Wmissing-prototypes -O3 -I../../include -I../../arch/x86/include -U_FORTIFY_SOURCE LDLIBS:=-lz all: lguest diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 6110197757a..9fb8aae5c39 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -8,6 +8,7 @@ config ALPHA select HAVE_AOUT select HAVE_IDE select HAVE_OPROFILE + select HAVE_SYSCALL_WRAPPERS help The Alpha is a 64-bit general-purpose processor designed and marketed by the Digital Equipment Corporation of blessed memory, diff --git a/arch/alpha/include/asm/bug.h b/arch/alpha/include/asm/bug.h index 695a5ee4b5d..7b85b7c9370 100644 --- a/arch/alpha/include/asm/bug.h +++ b/arch/alpha/include/asm/bug.h @@ -8,17 +8,12 @@ /* ??? Would be nice to use .gprel32 here, but we can't be sure that the function loaded the GP, so this could fail in modules. */ -static inline void ATTRIB_NORET __BUG(const char *file, int line) -{ - __asm__ __volatile__( - "call_pal %0 # bugchk\n\t" - ".long %1\n\t.8byte %2" - : : "i" (PAL_bugchk), "i"(line), "i"(file)); - for ( ; ; ) - ; -} - -#define BUG() __BUG(__FILE__, __LINE__) +#define BUG() { \ + __asm__ __volatile__( \ + "call_pal %0 # bugchk\n\t" \ + ".long %1\n\t.8byte %2" \ + : : "i"(PAL_bugchk), "i"(__LINE__), "i"(__FILE__)); \ + for ( ; ; ); } #define HAVE_ARCH_BUG #endif diff --git a/arch/alpha/include/asm/dma-mapping.h b/arch/alpha/include/asm/dma-mapping.h index a5801ae02e4..04eb5681448 100644 --- a/arch/alpha/include/asm/dma-mapping.h +++ b/arch/alpha/include/asm/dma-mapping.h @@ -29,6 +29,8 @@ #else /* no PCI - no IOMMU. */ +#include <asm/io.h> /* for virt_to_phys() */ + struct scatterlist; void *dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp); diff --git a/arch/alpha/kernel/entry.S b/arch/alpha/kernel/entry.S index aa2e50cf985..e4a54b61589 100644 --- a/arch/alpha/kernel/entry.S +++ b/arch/alpha/kernel/entry.S @@ -933,7 +933,7 @@ sys_execve: osf_sigprocmask: .prologue 0 mov $sp, $18 - jmp $31, do_osf_sigprocmask + jmp $31, sys_osf_sigprocmask .end osf_sigprocmask .align 4 diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 18a3ea1aac5..ae41f097864 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -54,8 +54,7 @@ extern int do_pipe(int *); * identical to OSF as we don't return 0 on success, but doing otherwise * would require changes to libc. Hopefully this is good enough. */ -asmlinkage unsigned long -osf_brk(unsigned long brk) +SYSCALL_DEFINE1(osf_brk, unsigned long, brk) { unsigned long retval = sys_brk(brk); if (brk && brk != retval) @@ -66,9 +65,9 @@ osf_brk(unsigned long brk) /* * This is pure guess-work.. */ -asmlinkage int -osf_set_program_attributes(unsigned long text_start, unsigned long text_len, - unsigned long bss_start, unsigned long bss_len) +SYSCALL_DEFINE4(osf_set_program_attributes, unsigned long, text_start, + unsigned long, text_len, unsigned long, bss_start, + unsigned long, bss_len) { struct mm_struct *mm; @@ -146,9 +145,9 @@ Efault: return -EFAULT; } -asmlinkage int -osf_getdirentries(unsigned int fd, struct osf_dirent __user *dirent, - unsigned int count, long __user *basep) +SYSCALL_DEFINE4(osf_getdirentries, unsigned int, fd, + struct osf_dirent __user *, dirent, unsigned int, count, + long __user *, basep) { int error; struct file *file; @@ -177,9 +176,9 @@ osf_getdirentries(unsigned int fd, struct osf_dirent __user *dirent, #undef NAME_OFFSET -asmlinkage unsigned long -osf_mmap(unsigned long addr, unsigned long len, unsigned long prot, - unsigned long flags, unsigned long fd, unsigned long off) +SYSCALL_DEFINE6(osf_mmap, unsigned long, addr, unsigned long, len, + unsigned long, prot, unsigned long, flags, unsigned long, fd, + unsigned long, off) { struct file *file = NULL; unsigned long ret = -EBADF; @@ -254,8 +253,8 @@ do_osf_statfs(struct dentry * dentry, struct osf_statfs __user *buffer, return error; } -asmlinkage int -osf_statfs(char __user *pathname, struct osf_statfs __user *buffer, unsigned long bufsiz) +SYSCALL_DEFINE3(osf_statfs, char __user *, pathname, + struct osf_statfs __user *, buffer, unsigned long, bufsiz) { struct path path; int retval; @@ -268,8 +267,8 @@ osf_statfs(char __user *pathname, struct osf_statfs __user *buffer, unsigned lon return retval; } -asmlinkage int -osf_fstatfs(unsigned long fd, struct osf_statfs __user *buffer, unsigned long bufsiz) +SYSCALL_DEFINE3(osf_fstatfs, unsigned long, fd, + struct osf_statfs __user *, buffer, unsigned long, bufsiz) { struct file *file; int retval; @@ -368,8 +367,8 @@ osf_procfs_mount(char *dirname, struct procfs_args __user *args, int flags) return do_mount("", dirname, "proc", flags, NULL); } -asmlinkage int -osf_mount(unsigned long typenr, char __user *path, int flag, void __user *data) +SYSCALL_DEFINE4(osf_mount, unsigned long, typenr, char __user *, path, + int, flag, void __user *, data) { int retval = -EINVAL; char *name; @@ -399,8 +398,7 @@ osf_mount(unsigned long typenr, char __user *path, int flag, void __user *data) return retval; } -asmlinkage int -osf_utsname(char __user *name) +SYSCALL_DEFINE1(osf_utsname, char __user *, name) { int error; @@ -423,14 +421,12 @@ osf_utsname(char __user *name) return error; } -asmlinkage unsigned long -sys_getpagesize(void) +SYSCALL_DEFINE0(getpagesize) { return PAGE_SIZE; } -asmlinkage unsigned long -sys_getdtablesize(void) +SYSCALL_DEFINE0(getdtablesize) { return sysctl_nr_open; } @@ -438,8 +434,7 @@ sys_getdtablesize(void) /* * For compatibility with OSF/1 only. Use utsname(2) instead. */ -asmlinkage int -osf_getdomainname(char __user *name, int namelen) +SYSCALL_DEFINE2(osf_getdomainname, char __user *, name, int, namelen) { unsigned len; int i; @@ -527,8 +522,8 @@ enum pl_code { PL_DEL = 5, PL_FDEL = 6 }; -asmlinkage long -osf_proplist_syscall(enum pl_code code, union pl_args __user *args) +SYSCALL_DEFINE2(osf_proplist_syscall, enum pl_code, code, + union pl_args __user *, args) { long error; int __user *min_buf_size_ptr; @@ -567,8 +562,8 @@ osf_proplist_syscall(enum pl_code code, union pl_args __user *args) return error; } -asmlinkage int -osf_sigstack(struct sigstack __user *uss, struct sigstack __user *uoss) +SYSCALL_DEFINE2(osf_sigstack, struct sigstack __user *, uss, + struct sigstack __user *, uoss) { unsigned long usp = rdusp(); unsigned long oss_sp = current->sas_ss_sp + current->sas_ss_size; @@ -608,8 +603,7 @@ osf_sigstack(struct sigstack __user *uss, struct sigstack __user *uoss) return error; } -asmlinkage long -osf_sysinfo(int command, char __user *buf, long count) +SYSCALL_DEFINE3(osf_sysinfo, int, command, char __user *, buf, long, count) { char *sysinfo_table[] = { utsname()->sysname, @@ -647,9 +641,8 @@ osf_sysinfo(int command, char __user *buf, long count) return err; } -asmlinkage unsigned long -osf_getsysinfo(unsigned long op, void __user *buffer, unsigned long nbytes, - int __user *start, void __user *arg) +SYSCALL_DEFINE5(osf_getsysinfo, unsigned long, op, void __user *, buffer, + unsigned long, nbytes, int __user *, start, void __user *, arg) { unsigned long w; struct percpu_struct *cpu; @@ -705,9 +698,8 @@ osf_getsysinfo(unsigned long op, void __user *buffer, unsigned long nbytes, return -EOPNOTSUPP; } -asmlinkage unsigned long -osf_setsysinfo(unsigned long op, void __user *buffer, unsigned long nbytes, - int __user *start, void __user *arg) +SYSCALL_DEFINE5(osf_setsysinfo, unsigned long, op, void __user *, buffer, + unsigned long, nbytes, int __user *, start, void __user *, arg) { switch (op) { case SSI_IEEE_FP_CONTROL: { @@ -880,8 +872,8 @@ jiffies_to_timeval32(unsigned long jiffies, struct timeval32 *value) value->tv_sec = jiffies / HZ; } -asmlinkage int -osf_gettimeofday(struct timeval32 __user *tv, struct timezone __user *tz) +SYSCALL_DEFINE2(osf_gettimeofday, struct timeval32 __user *, tv, + struct timezone __user *, tz) { if (tv) { struct timeval ktv; @@ -896,8 +888,8 @@ osf_gettimeofday(struct timeval32 __user *tv, struct timezone __user *tz) return 0; } -asmlinkage int -osf_settimeofday(struct timeval32 __user *tv, struct timezone __user *tz) +SYSCALL_DEFINE2(osf_settimeofday, struct timeval32 __user *, tv, + struct timezone __user *, tz) { struct timespec kts; struct timezone ktz; @@ -916,8 +908,7 @@ osf_settimeofday(struct timeval32 __user *tv, struct timezone __user *tz) return do_sys_settimeofday(tv ? &kts : NULL, tz ? &ktz : NULL); } -asmlinkage int -osf_getitimer(int which, struct itimerval32 __user *it) +SYSCALL_DEFINE2(osf_getitimer, int, which, struct itimerval32 __user *, it) { struct itimerval kit; int error; @@ -929,8 +920,8 @@ osf_getitimer(int which, struct itimerval32 __user *it) return error; } -asmlinkage int -osf_setitimer(int which, struct itimerval32 __user *in, struct itimerval32 __user *out) +SYSCALL_DEFINE3(osf_setitimer, int, which, struct itimerval32 __user *, in, + struct itimerval32 __user *, out) { struct itimerval kin, kout; int error; @@ -952,8 +943,8 @@ osf_setitimer(int which, struct itimerval32 __user *in, struct itimerval32 __use } -asmlinkage int -osf_utimes(char __user *filename, struct timeval32 __user *tvs) +SYSCALL_DEFINE2(osf_utimes, char __user *, filename, + struct timeval32 __user *, tvs) { struct timespec tv[2]; @@ -979,9 +970,8 @@ osf_utimes(char __user *filename, struct timeval32 __user *tvs) #define MAX_SELECT_SECONDS \ ((unsigned long) (MAX_SCHEDULE_TIMEOUT / HZ)-1) -asmlinkage int -osf_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, - struct timeval32 __user *tvp) +SYSCALL_DEFINE5(osf_select, int, n, fd_set __user *, inp, fd_set __user *, outp, + fd_set __user *, exp, struct timeval32 __user *, tvp) { struct timespec end_time, *to = NULL; if (tvp) { @@ -1026,8 +1016,7 @@ struct rusage32 { long ru_nivcsw; /* involuntary " */ }; -asmlinkage int -osf_getrusage(int who, struct rusage32 __user *ru) +SYSCALL_DEFINE2(osf_getrusage, int, who, struct rusage32 __user *, ru) { struct rusage32 r; @@ -1053,9 +1042,8 @@ osf_getrusage(int who, struct rusage32 __user *ru) return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0; } -asmlinkage long -osf_wait4(pid_t pid, int __user *ustatus, int options, - struct rusage32 __user *ur) +SYSCALL_DEFINE4(osf_wait4, pid_t, pid, int __user *, ustatus, int, options, + struct rusage32 __user *, ur) { struct rusage r; long ret, err; @@ -1101,8 +1089,8 @@ osf_wait4(pid_t pid, int __user *ustatus, int options, * seems to be a timeval pointer, and I suspect the second * one is the time remaining.. Ho humm.. No documentation. */ -asmlinkage int -osf_usleep_thread(struct timeval32 __user *sleep, struct timeval32 __user *remain) +SYSCALL_DEFINE2(osf_usleep_thread, struct timeval32 __user *, sleep, + struct timeval32 __user *, remain) { struct timeval tmp; unsigned long ticks; @@ -1155,8 +1143,7 @@ struct timex32 { int :32; int :32; int :32; int :32; }; -asmlinkage int -sys_old_adjtimex(struct timex32 __user *txc_p) +SYSCALL_DEFINE1(old_adjtimex, struct timex32 __user *, txc_p) { struct timex txc; int ret; @@ -1267,8 +1254,8 @@ osf_fix_iov_len(const struct iovec __user *iov, unsigned long count) return 0; } -asmlinkage ssize_t -osf_readv(unsigned long fd, const struct iovec __user * vector, unsigned long count) +SYSCALL_DEFINE3(osf_readv, unsigned long, fd, + const struct iovec __user *, vector, unsigned long, count) { if (unlikely(personality(current->personality) == PER_OSF4)) if (osf_fix_iov_len(vector, count)) @@ -1276,8 +1263,8 @@ osf_readv(unsigned long fd, const struct iovec __user * vector, unsigned long co return sys_readv(fd, vector, count); } -asmlinkage ssize_t -osf_writev(unsigned long fd, const struct iovec __user * vector, unsigned long count) +SYSCALL_DEFINE3(osf_writev, unsigned long, fd, + const struct iovec __user *, vector, unsigned long, count) { if (unlikely(personality(current->personality) == PER_OSF4)) if (osf_fix_iov_len(vector, count)) diff --git a/arch/alpha/kernel/pci-noop.c b/arch/alpha/kernel/pci-noop.c index 8ac08311f5a..c19a376520f 100644 --- a/arch/alpha/kernel/pci-noop.c +++ b/arch/alpha/kernel/pci-noop.c @@ -109,7 +109,8 @@ sys_pciconfig_write(unsigned long bus, unsigned long dfn, /* Stubs for the routines in pci_iommu.c: */ void * -pci_alloc_consistent(struct pci_dev *pdev, size_t size, dma_addr_t *dma_addrp) +__pci_alloc_consistent(struct pci_dev *pdev, size_t size, + dma_addr_t *dma_addrp, gfp_t gfp) { return NULL; } diff --git a/arch/alpha/kernel/signal.c b/arch/alpha/kernel/signal.c index 410af4f3140..df65eaa84c4 100644 --- a/arch/alpha/kernel/signal.c +++ b/arch/alpha/kernel/signal.c @@ -19,6 +19,7 @@ #include <linux/tty.h> #include <linux/binfmts.h> #include <linux/bitops.h> +#include <linux/syscalls.h> #include <asm/uaccess.h> #include <asm/sigcontext.h> @@ -51,8 +52,8 @@ static void do_signal(struct pt_regs *, struct switch_stack *, * Note that we don't need to acquire the kernel lock for SMP * operation, as all of this is local to this thread. */ -asmlinkage unsigned long -do_osf_sigprocmask(int how, unsigned long newmask, struct pt_regs *regs) +SYSCALL_DEFINE3(osf_sigprocmask, int, how, unsigned long, newmask, + struct pt_regs *, regs) { unsigned long oldmask = -EINVAL; @@ -81,9 +82,9 @@ do_osf_sigprocmask(int how, unsigned long newmask, struct pt_regs *regs) return oldmask; } -asmlinkage int -osf_sigaction(int sig, const struct osf_sigaction __user *act, - struct osf_sigaction __user *oact) +SYSCALL_DEFINE3(osf_sigaction, int, sig, + const struct osf_sigaction __user *, act, + struct osf_sigaction __user *, oact) { struct k_sigaction new_ka, old_ka; int ret; @@ -112,10 +113,9 @@ osf_sigaction(int sig, const struct osf_sigaction __user *act, return ret; } -asmlinkage long -sys_rt_sigaction(int sig, const struct sigaction __user *act, - struct sigaction __user *oact, - size_t sigsetsize, void __user *restorer) +SYSCALL_DEFINE5(rt_sigaction, int, sig, const struct sigaction __user *, act, + struct sigaction __user *, oact, + size_t, sigsetsize, void __user *, restorer) { struct k_sigaction new_ka, old_ka; int ret; diff --git a/arch/alpha/kernel/smp.c b/arch/alpha/kernel/smp.c index d953e510f68..00f1dc3dfd5 100644 --- a/arch/alpha/kernel/smp.c +++ b/arch/alpha/kernel/smp.c @@ -120,8 +120,9 @@ void __cpuinit smp_callin(void) { int cpuid = hard_smp_processor_id(); + cpumask_t mask = cpu_online_map; - if (cpu_test_and_set(cpuid, cpu_online_map)) { + if (cpu_test_and_set(cpuid, mask)) { printk("??, cpu 0x%x already present??\n", cpuid); BUG(); } diff --git a/arch/alpha/kernel/systbls.S b/arch/alpha/kernel/systbls.S index 9d9e3a98bb9..95c9aef1c10 100644 --- a/arch/alpha/kernel/systbls.S +++ b/arch/alpha/kernel/systbls.S @@ -17,7 +17,7 @@ sys_call_table: .quad sys_write .quad alpha_ni_syscall /* 5 */ .quad sys_close - .quad osf_wait4 + .quad sys_osf_wait4 .quad alpha_ni_syscall .quad sys_link .quad sys_unlink /* 10 */ @@ -27,11 +27,11 @@ sys_call_table: .quad sys_mknod .quad sys_chmod /* 15 */ .quad sys_chown - .quad osf_brk + .quad sys_osf_brk .quad alpha_ni_syscall .quad sys_lseek .quad sys_getxpid /* 20 */ - .quad osf_mount + .quad sys_osf_mount .quad sys_umount .quad sys_setuid .quad sys_getxuid @@ -53,7 +53,7 @@ sys_call_table: .quad alpha_ni_syscall /* 40 */ .quad sys_dup .quad sys_alpha_pipe - .quad osf_set_program_attributes + .quad sys_osf_set_program_attributes .quad alpha_ni_syscall .quad sys_open /* 45 */ .quad alpha_ni_syscall @@ -81,7 +81,7 @@ sys_call_table: .quad sys_newlstat .quad alpha_ni_syscall .quad alpha_ni_syscall /* 70 */ - .quad osf_mmap + .quad sys_osf_mmap .quad alpha_ni_syscall .quad sys_munmap .quad sys_mprotect @@ -94,17 +94,17 @@ sys_call_table: .quad sys_setgroups /* 80 */ .quad alpha_ni_syscall .quad sys_setpgid - .quad osf_setitimer + .quad sys_osf_setitimer .quad alpha_ni_syscall .quad alpha_ni_syscall /* 85 */ - .quad osf_getitimer + .quad sys_osf_getitimer .quad sys_gethostname .quad sys_sethostname .quad sys_getdtablesize .quad sys_dup2 /* 90 */ .quad sys_newfstat .quad sys_fcntl - .quad osf_select + .quad sys_osf_select .quad sys_poll .quad sys_fsync /* 95 */ .quad sys_setpriority @@ -123,22 +123,22 @@ sys_call_table: .quad alpha_ni_syscall .quad alpha_ni_syscall /* 110 */ .quad sys_sigsuspend - .quad osf_sigstack + .quad sys_osf_sigstack .quad sys_recvmsg .quad sys_sendmsg .quad alpha_ni_syscall /* 115 */ - .quad osf_gettimeofday - .quad osf_getrusage + .quad sys_osf_gettimeofday + .quad sys_osf_getrusage .quad sys_getsockopt .quad alpha_ni_syscall #ifdef CONFIG_OSF4_COMPAT - .quad osf_readv /* 120 */ - .quad osf_writev + .quad sys_osf_readv /* 120 */ + .quad sys_osf_writev #else .quad sys_readv /* 120 */ .quad sys_writev #endif - .quad osf_settimeofday + .quad sys_osf_settimeofday .quad sys_fchown .quad sys_fchmod .quad sys_recvfrom /* 125 */ @@ -154,7 +154,7 @@ sys_call_table: .quad sys_socketpair /* 135 */ .quad sys_mkdir .quad sys_rmdir - .quad osf_utimes + .quad sys_osf_utimes .quad alpha_ni_syscall .quad alpha_ni_syscall /* 140 */ .quad sys_getpeername @@ -172,16 +172,16 @@ sys_call_table: .quad alpha_ni_syscall .quad alpha_ni_syscall .quad alpha_ni_syscall /* 155 */ - .quad osf_sigaction + .quad sys_osf_sigaction .quad alpha_ni_syscall .quad alpha_ni_syscall - .quad osf_getdirentries - .quad osf_statfs /* 160 */ - .quad osf_fstatfs + .quad sys_osf_getdirentries + .quad sys_osf_statfs /* 160 */ + .quad sys_osf_fstatfs .quad alpha_ni_syscall .quad alpha_ni_syscall .quad alpha_ni_syscall - .quad osf_getdomainname /* 165 */ + .quad sys_osf_getdomainname /* 165 */ .quad sys_setdomainname .quad alpha_ni_syscall .quad alpha_ni_syscall @@ -224,7 +224,7 @@ sys_call_table: .quad sys_semctl .quad sys_semget /* 205 */ .quad sys_semop - .quad osf_utsname + .quad sys_osf_utsname .quad sys_lchown .quad sys_shmat .quad sys_shmctl /* 210 */ @@ -258,23 +258,23 @@ sys_call_table: .quad alpha_ni_syscall .quad alpha_ni_syscall .quad alpha_ni_syscall /* 240 */ - .quad osf_sysinfo + .quad sys_osf_sysinfo .quad alpha_ni_syscall .quad alpha_ni_syscall - .quad osf_proplist_syscall + .quad sys_osf_proplist_syscall .quad alpha_ni_syscall /* 245 */ .quad alpha_ni_syscall .quad alpha_ni_syscall .quad alpha_ni_syscall .quad alpha_ni_syscall .quad alpha_ni_syscall /* 250 */ - .quad osf_usleep_thread + .quad sys_osf_usleep_thread .quad alpha_ni_syscall .quad alpha_ni_syscall .quad sys_sysfs .quad alpha_ni_syscall /* 255 */ - .quad osf_getsysinfo - .quad osf_setsysinfo + .quad sys_osf_getsysinfo + .quad sys_osf_setsysinfo .quad alpha_ni_syscall .quad alpha_ni_syscall .quad alpha_ni_syscall /* 260 */ diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index a7ed208f81e..92f1c6f3e19 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -931,7 +931,7 @@ static void lguest_restart(char *reason) * that we can fit comfortably. * * First we need assembly templates of each of the patchable Guest operations, - * and these are in lguest_asm.S. */ + * and these are in i386_head.S. */ /*G:060 We construct a table from the assembler templates: */ static const struct lguest_insns @@ -1093,7 +1093,7 @@ __init void lguest_init(void) acpi_ht = 0; #endif - /* We set the perferred console to "hvc". This is the "hypervisor + /* We set the preferred console to "hvc". This is the "hypervisor * virtual console" driver written by the PowerPC people, which we also * adapted for lguest's use. */ add_preferred_console("hvc", 0, NULL); diff --git a/drivers/firewire/fw-card.c b/drivers/firewire/fw-card.c index 6bd91a15d5e..7be2cf3514e 100644 --- a/drivers/firewire/fw-card.c +++ b/drivers/firewire/fw-card.c @@ -232,7 +232,7 @@ fw_card_bm_work(struct work_struct *work) root_id = root_node->node_id; grace = time_after(jiffies, card->reset_jiffies + DIV_ROUND_UP(HZ, 10)); - if (card->bm_generation + 1 == generation || + if (is_next_generation(generation, card->bm_generation) || (card->bm_generation != generation && grace)) { /* * This first step is to figure out who is IRM and @@ -512,7 +512,7 @@ fw_core_remove_card(struct fw_card *card) fw_core_initiate_bus_reset(card, 1); mutex_lock(&card_mutex); - list_del(&card->link); + list_del_init(&card->link); mutex_unlock(&card_mutex); /* Set up the dummy driver. */ diff --git a/drivers/firewire/fw-device.c b/drivers/firewire/fw-device.c index 2af5a8d1e01..bf53acb4565 100644 --- a/drivers/firewire/fw-device.c +++ b/drivers/firewire/fw-device.c @@ -25,6 +25,7 @@ #include <linux/device.h> #include <linux/delay.h> #include <linux/idr.h> +#include <linux/jiffies.h> #include <linux/string.h> #include <linux/rwsem.h> #include <linux/semaphore.h> @@ -634,12 +635,39 @@ struct fw_device *fw_device_get_by_devt(dev_t devt) return device; } +/* + * These defines control the retry behavior for reading the config + * rom. It shouldn't be necessary to tweak these; if the device + * doesn't respond to a config rom read within 10 seconds, it's not + * going to respond at all. As for the initial delay, a lot of + * devices will be able to respond within half a second after bus + * reset. On the other hand, it's not really worth being more + * aggressive than that, since it scales pretty well; if 10 devices + * are plugged in, they're all getting read within one second. + */ + +#define MAX_RETRIES 10 +#define RETRY_DELAY (3 * HZ) +#define INITIAL_DELAY (HZ / 2) +#define SHUTDOWN_DELAY (2 * HZ) + static void fw_device_shutdown(struct work_struct *work) { struct fw_device *device = container_of(work, struct fw_device, work.work); int minor = MINOR(device->device.devt); + if (time_is_after_jiffies(device->card->reset_jiffies + SHUTDOWN_DELAY) + && !list_empty(&device->card->link)) { + schedule_delayed_work(&device->work, SHUTDOWN_DELAY); + return; + } + + if (atomic_cmpxchg(&device->state, + FW_DEVICE_GONE, + FW_DEVICE_SHUTDOWN) != FW_DEVICE_GONE) + return; + fw_device_cdev_remove(device); device_for_each_child(&device->device, NULL, shutdown_unit); device_unregister(&device->device); @@ -647,6 +675,7 @@ static void fw_device_shutdown(struct work_struct *work) down_write(&fw_device_rwsem); idr_remove(&fw_device_idr, minor); up_write(&fw_device_rwsem); + fw_device_put(device); } @@ -654,25 +683,63 @@ static struct device_type fw_device_type = { .release = fw_device_release, }; +static void fw_device_update(struct work_struct *work); + /* - * These defines control the retry behavior for reading the config - * rom. It shouldn't be necessary to tweak these; if the device - * doesn't respond to a config rom read within 10 seconds, it's not - * going to respond at all. As for the initial delay, a lot of - * devices will be able to respond within half a second after bus - * reset. On the other hand, it's not really worth being more - * aggressive than that, since it scales pretty well; if 10 devices - * are plugged in, they're all getting read within one second. + * If a device was pending for deletion because its node went away but its + * bus info block and root directory header matches that of a newly discovered + * device, revive the existing fw_device. + * The newly allocated fw_device becomes obsolete instead. */ +static int lookup_existing_device(struct device *dev, void *data) +{ + struct fw_device *old = fw_device(dev); + struct fw_device *new = data; + struct fw_card *card = new->card; + int match = 0; + + down_read(&fw_device_rwsem); /* serialize config_rom access */ + spin_lock_irq(&card->lock); /* serialize node access */ + + if (memcmp(old->config_rom, new->config_rom, 6 * 4) == 0 && + atomic_cmpxchg(&old->state, + FW_DEVICE_GONE, + FW_DEVICE_RUNNING) == FW_DEVICE_GONE) { + struct fw_node *current_node = new->node; + struct fw_node *obsolete_node = old->node; + + new->node = obsolete_node; + new->node->data = new; + old->node = current_node; + old->node->data = old; + + old->max_speed = new->max_speed; + old->node_id = current_node->node_id; + smp_wmb(); /* update node_id before generation */ + old->generation = card->generation; + old->config_rom_retries = 0; + fw_notify("rediscovered device %s\n", dev_name(dev)); -#define MAX_RETRIES 10 -#define RETRY_DELAY (3 * HZ) -#define INITIAL_DELAY (HZ / 2) + PREPARE_DELAYED_WORK(&old->work, fw_device_update); + schedule_delayed_work(&old->work, 0); + + if (current_node == card->root_node) + fw_schedule_bm_work(card, 0); + + match = 1; + } + + spin_unlock_irq(&card->lock); + up_read(&fw_device_rwsem); + + return match; +} static void fw_device_init(struct work_struct *work) { struct fw_device *device = container_of(work, struct fw_device, work.work); + struct device *revived_dev; int minor, err; /* @@ -696,6 +763,15 @@ static void fw_device_init(struct work_struct *work) return; } + revived_dev = device_find_child(device->card->device, + device, lookup_existing_device); + if (revived_dev) { + put_device(revived_dev); + fw_device_release(&device->device); + + return; + } + device_initialize(&device->device); fw_device_get(device); @@ -734,9 +810,10 @@ static void fw_device_init(struct work_struct *work) * fw_node_event(). */ if (atomic_cmpxchg(&device->state, - FW_DEVICE_INITIALIZING, - FW_DEVICE_RUNNING) == FW_DEVICE_SHUTDOWN) { - fw_device_shutdown(work); + FW_DEVICE_INITIALIZING, + FW_DEVICE_RUNNING) == FW_DEVICE_GONE) { + PREPARE_DELAYED_WORK(&device->work, fw_device_shutdown); + schedule_delayed_work(&device->work, SHUTDOWN_DELAY); } else { if (device->config_rom_retries) fw_notify("created device %s: GUID %08x%08x, S%d00, " @@ -847,8 +924,8 @@ static void fw_device_refresh(struct work_struct *work) case REREAD_BIB_UNCHANGED: if (atomic_cmpxchg(&device->state, - FW_DEVICE_INITIALIZING, - FW_DEVICE_RUNNING) == FW_DEVICE_SHUTDOWN) + FW_DEVICE_INITIALIZING, + FW_DEVICE_RUNNING) == FW_DEVICE_GONE) goto gone; fw_device_update(work); @@ -879,8 +956,8 @@ static void fw_device_refresh(struct work_struct *work) create_units(device); if (atomic_cmpxchg(&device->state, - FW_DEVICE_INITIALIZING, - FW_DEVICE_RUNNING) == FW_DEVICE_SHUTDOWN) + FW_DEVICE_INITIALIZING, + FW_DEVICE_RUNNING) == FW_DEVICE_GONE) goto gone; fw_notify("refreshed device %s\n", dev_name(&device->device)); @@ -890,8 +967,9 @@ static void fw_device_refresh(struct work_struct *work) give_up: fw_notify("giving up on refresh of device %s\n", dev_name(&device->device)); gone: - atomic_set(&device->state, FW_DEVICE_SHUTDOWN); - fw_device_shutdown(work); + atomic_set(&device->state, FW_DEVICE_GONE); + PREPARE_DELAYED_WORK(&device->work, fw_device_shutdown); + schedule_delayed_work(&device->work, SHUTDOWN_DELAY); out: if (node_id == card->root_node->node_id) fw_schedule_bm_work(card, 0); @@ -995,9 +1073,10 @@ void fw_node_event(struct fw_card *card, struct fw_node *node, int event) */ device = node->data; if (atomic_xchg(&device->state, - FW_DEVICE_SHUTDOWN) == FW_DEVICE_RUNNING) { + FW_DEVICE_GONE) == FW_DEVICE_RUNNING) { PREPARE_DELAYED_WORK(&device->work, fw_device_shutdown); - schedule_delayed_work(&device->work, 0); + schedule_delayed_work(&device->work, + list_empty(&card->link) ? 0 : SHUTDOWN_DELAY); } break; } diff --git a/drivers/firewire/fw-device.h b/drivers/firewire/fw-device.h index df51732608d..8ef6ec2ca21 100644 --- a/drivers/firewire/fw-device.h +++ b/drivers/firewire/fw-device.h @@ -28,6 +28,7 @@ enum fw_device_state { FW_DEVICE_INITIALIZING, FW_DEVICE_RUNNING, + FW_DEVICE_GONE, FW_DEVICE_SHUTDOWN, }; diff --git a/drivers/firewire/fw-ohci.c b/drivers/firewire/fw-ohci.c index ab9c01e462e..6d19828a93a 100644 --- a/drivers/firewire/fw-ohci.c +++ b/drivers/firewire/fw-ohci.c @@ -226,7 +226,7 @@ static inline struct fw_ohci *fw_ohci(struct fw_card *card) #define CONTEXT_DEAD 0x0800 #define CONTEXT_ACTIVE 0x0400 -#define OHCI1394_MAX_AT_REQ_RETRIES 0x2 +#define OHCI1394_MAX_AT_REQ_RETRIES 0xf #define OHCI1394_MAX_AT_RESP_RETRIES 0x2 #define OHCI1394_MAX_PHYS_RESP_RETRIES 0x8 @@ -896,11 +896,11 @@ static void context_stop(struct context *ctx) for (i = 0; i < 10; i++) { reg = reg_read(ctx->ohci, CONTROL_SET(ctx->regs)); if ((reg & CONTEXT_ACTIVE) == 0) - break; + return; - fw_notify("context_stop: still active (0x%08x)\n", reg); mdelay(1); } + fw_error("Error: DMA context still active (0x%08x)\n", reg); } struct driver_data { diff --git a/drivers/firewire/fw-sbp2.c b/drivers/firewire/fw-sbp2.c index e88d5067448..c71c4419d9e 100644 --- a/drivers/firewire/fw-sbp2.c +++ b/drivers/firewire/fw-sbp2.c @@ -168,6 +168,7 @@ struct sbp2_target { int address_high; unsigned int workarounds; unsigned int mgt_orb_timeout; + unsigned int max_payload; int dont_block; /* counter for each logical unit */ int blocked; /* ditto */ @@ -310,14 +311,16 @@ struct sbp2_command_orb { dma_addr_t page_table_bus; }; +#define SBP2_ROM_VALUE_WILDCARD ~0 /* match all */ +#define SBP2_ROM_VALUE_MISSING 0xff000000 /* not present in the unit dir. */ + /* * List of devices with known bugs. * * The firmware_revision field, masked with 0xffff00, is the best * indicator for the type of bridge chip of a device. It yields a few * false positives but this did not break correctly behaving devices - * so far. We use ~0 as a wildcard, since the 24 bit values we get - * from the config rom can never match that. + * so far. */ static const struct { u32 firmware_revision; @@ -339,33 +342,35 @@ static const struct { }, /* Initio bridges, actually only needed for some older ones */ { .firmware_revision = 0x000200, - .model = ~0, + .model = SBP2_ROM_VALUE_WILDCARD, .workarounds = SBP2_WORKAROUND_INQUIRY_36, }, /* PL-3507 bridge with Prolific firmware */ { .firmware_revision = 0x012800, - .model = ~0, + .model = SBP2_ROM_VALUE_WILDCARD, .workarounds = SBP2_WORKAROUND_POWER_CONDITION, }, /* Symbios bridge */ { .firmware_revision = 0xa0b800, - .model = ~0, + .model = SBP2_ROM_VALUE_WILDCARD, .workarounds = SBP2_WORKAROUND_128K_MAX_TRANS, }, /* Datafab MD2-FW2 with Symbios/LSILogic SYM13FW500 bridge */ { .firmware_revision = 0x002600, - .model = ~0, + .model = SBP2_ROM_VALUE_WILDCARD, .workarounds = SBP2_WORKAROUND_128K_MAX_TRANS, }, - /* - * There are iPods (2nd gen, 3rd gen) with model_id == 0, but - * these iPods do not feature the read_capacity bug according - * to one report. Read_capacity behaviour as well as model_id - * could change due to Apple-supplied firmware updates though. + * iPod 2nd generation: needs 128k max transfer size workaround + * iPod 3rd generation: needs fix capacity workaround */ - - /* iPod 4th generation. */ { + { + .firmware_revision = 0x0a2700, + .model = 0x000000, + .workarounds = SBP2_WORKAROUND_128K_MAX_TRANS | + SBP2_WORKAROUND_FIX_CAPACITY, + }, + /* iPod 4th generation */ { .firmware_revision = 0x0a2700, .model = 0x000021, .workarounds = SBP2_WORKAROUND_FIX_CAPACITY, @@ -1092,7 +1097,7 @@ static void sbp2_init_workarounds(struct sbp2_target *tgt, u32 model, continue; if (sbp2_workarounds_table[i].model != model && - sbp2_workarounds_table[i].model != ~0) + sbp2_workarounds_table[i].model != SBP2_ROM_VALUE_WILDCARD) continue; w |= sbp2_workarounds_table[i].workarounds; @@ -1142,20 +1147,28 @@ static int sbp2_probe(struct device *dev) fw_device_get(device); fw_unit_get(unit); - /* Initialize to values that won't match anything in our table. */ - firmware_revision = 0xff000000; - model = 0xff000000; - /* implicit directory ID */ tgt->directory_id = ((unit->directory - device->config_rom) * 4 + CSR_CONFIG_ROM) & 0xffffff; + firmware_revision = SBP2_ROM_VALUE_MISSING; + model = SBP2_ROM_VALUE_MISSING; + if (sbp2_scan_unit_dir(tgt, unit->directory, &model, &firmware_revision) < 0) goto fail_tgt_put; sbp2_init_workarounds(tgt, model, firmware_revision); + /* + * At S100 we can do 512 bytes per packet, at S200 1024 bytes, + * and so on up to 4096 bytes. The SBP-2 max_payload field + * specifies the max payload size as 2 ^ (max_payload + 2), so + * if we set this to max_speed + 7, we get the right value. + */ + tgt->max_payload = min(device->max_speed + 7, 10U); + tgt->max_payload = min(tgt->max_payload, device->card->max_receive - 1); + /* Do the login in a workqueue so we can easily reschedule retries. */ list_for_each_entry(lu, &tgt->lu_list, link) sbp2_queue_work(lu, DIV_ROUND_UP(HZ, 5)); @@ -1273,6 +1286,19 @@ static struct fw_driver sbp2_driver = { .id_table = sbp2_id_table, }; +static void sbp2_unmap_scatterlist(struct device *card_device, + struct sbp2_command_orb *orb) +{ + if (scsi_sg_count(orb->cmd)) + dma_unmap_sg(card_device, scsi_sglist(orb->cmd), + scsi_sg_count(orb->cmd), + orb->cmd->sc_data_direction); + + if (orb->request.misc & cpu_to_be32(COMMAND_ORB_PAGE_TABLE_PRESENT)) + dma_unmap_single(card_device, orb->page_table_bus, + sizeof(orb->page_table), DMA_TO_DEVICE); +} + static unsigned int sbp2_status_to_sense_data(u8 *sbp2_status, u8 *sense_data) { @@ -1352,15 +1378,7 @@ complete_command_orb(struct sbp2_orb *base_orb, struct sbp2_status *status) dma_unmap_single(device->card->device, orb->base.request_bus, sizeof(orb->request), DMA_TO_DEVICE); - - if (scsi_sg_count(orb->cmd) > 0) - dma_unmap_sg(device->card->device, scsi_sglist(orb->cmd), - scsi_sg_count(orb->cmd), - orb->cmd->sc_data_direction); - - if (orb->page_table_bus != 0) - dma_unmap_single(device->card->device, orb->page_table_bus, - sizeof(orb->page_table), DMA_TO_DEVICE); + sbp2_unmap_scatterlist(device->card->device, orb); orb->cmd->result = result; orb->done(orb->cmd); @@ -1434,7 +1452,6 @@ static int sbp2_scsi_queuecommand(struct scsi_cmnd *cmd, scsi_done_fn_t done) struct sbp2_logical_unit *lu = cmd->device->hostdata; struct fw_device *device = fw_device(lu->tgt->unit->device.parent); struct sbp2_command_orb *orb; - unsigned int max_payload; int generation, retval = SCSI_MLQUEUE_HOST_BUSY; /* @@ -1462,17 +1479,9 @@ static int sbp2_scsi_queuecommand(struct scsi_cmnd *cmd, scsi_done_fn_t done) orb->done = done; orb->cmd = cmd; - orb->request.next.high = cpu_to_be32(SBP2_ORB_NULL); - /* - * At speed 100 we can do 512 bytes per packet, at speed 200, - * 1024 bytes per packet etc. The SBP-2 max_payload field - * specifies the max payload size as 2 ^ (max_payload + 2), so - * if we set this to max_speed + 7, we get the right value. - */ - max_payload = min(device->max_speed + 7, - device->card->max_receive - 1); + orb->request.next.high = cpu_to_be32(SBP2_ORB_NULL); orb->request.misc = cpu_to_be32( - COMMAND_ORB_MAX_PAYLOAD(max_payload) | + COMMAND_ORB_MAX_PAYLOAD(lu->tgt->max_payload) | COMMAND_ORB_SPEED(device->max_speed) | COMMAND_ORB_NOTIFY); @@ -1491,8 +1500,10 @@ static int sbp2_scsi_queuecommand(struct scsi_cmnd *cmd, scsi_done_fn_t done) orb->base.request_bus = dma_map_single(device->card->device, &orb->request, sizeof(orb->request), DMA_TO_DEVICE); - if (dma_mapping_error(device->card->device, orb->base.request_bus)) + if (dma_mapping_error(device->card->device, orb->base.request_bus)) { + sbp2_unmap_scatterlist(device->card->device, orb); goto out; + } sbp2_send_orb(&orb->base, lu, lu->tgt->node_id, generation, lu->command_block_agent_address + SBP2_ORB_POINTER); diff --git a/drivers/firewire/fw-topology.c b/drivers/firewire/fw-topology.c index c9be6e6948c..8dd6703b55c 100644 --- a/drivers/firewire/fw-topology.c +++ b/drivers/firewire/fw-topology.c @@ -518,6 +518,18 @@ fw_core_handle_bus_reset(struct fw_card *card, struct fw_node *local_node; unsigned long flags; + /* + * If the selfID buffer is not the immediate successor of the + * previously processed one, we cannot reliably compare the + * old and new topologies. + */ + if (!is_next_generation(generation, card->generation) && + card->local_node != NULL) { + fw_notify("skipped bus generations, destroying all nodes\n"); + fw_destroy_nodes(card); + card->bm_retries = 0; + } + spin_lock_irqsave(&card->lock, flags); card->node_id = node_id; diff --git a/drivers/firewire/fw-transaction.h b/drivers/firewire/fw-transaction.h index c9ab12a15f6..1d78e9cc594 100644 --- a/drivers/firewire/fw-transaction.h +++ b/drivers/firewire/fw-transaction.h @@ -276,6 +276,15 @@ static inline void fw_card_put(struct fw_card *card) extern void fw_schedule_bm_work(struct fw_card *card, unsigned long delay); /* + * Check whether new_generation is the immediate successor of old_generation. + * Take counter roll-over at 255 (as per to OHCI) into account. + */ +static inline bool is_next_generation(int new_generation, int old_generation) +{ + return (new_generation & 0xff) == ((old_generation + 1) & 0xff); +} + +/* * The iso packet format allows for an immediate header/payload part * stored in 'header' immediately after the packet info plus an * indirect payload part that is pointer to by the 'payload' field. diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 35e7aea4222..42fb2fd24c0 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -789,6 +789,7 @@ int gpio_request(unsigned gpio, const char *label) } else { status = -EBUSY; module_put(chip->owner); + goto done; } if (chip->request) { diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c index 6b1148fc2cb..b36a5214d8d 100644 --- a/drivers/gpu/drm/i915/intel_lvds.c +++ b/drivers/gpu/drm/i915/intel_lvds.c @@ -311,7 +311,7 @@ static int intel_lvds_get_modes(struct drm_connector *connector) if (dev_priv->panel_fixed_mode != NULL) { struct drm_display_mode *mode; - mutex_unlock(&dev->mode_config.mutex); + mutex_lock(&dev->mode_config.mutex); mode = drm_mode_duplicate(dev, dev_priv->panel_fixed_mode); drm_mode_probed_add(connector, mode); mutex_unlock(&dev->mode_config.mutex); diff --git a/drivers/hwmon/applesmc.c b/drivers/hwmon/applesmc.c index e3018623658..678e34b01e5 100644 --- a/drivers/hwmon/applesmc.c +++ b/drivers/hwmon/applesmc.c @@ -83,7 +83,7 @@ /* * Temperature sensors keys (sp78 - 2 bytes). */ -static const char* temperature_sensors_sets[][36] = { +static const char *temperature_sensors_sets[][41] = { /* Set 0: Macbook Pro */ { "TA0P", "TB0T", "TC0D", "TC0P", "TG0H", "TG0P", "TG0T", "Th0H", "Th1H", "Tm0P", "Ts0P", "Ts1P", NULL }, @@ -135,6 +135,13 @@ static const char* temperature_sensors_sets[][36] = { { "TB0T", "TB1S", "TB1T", "TB2S", "TB2T", "TC0D", "TN0D", "TTF0", "TV0P", "TVFP", "TW0P", "Th0P", "Tp0P", "Tp1P", "TpFP", "Ts0P", "Ts0S", NULL }, +/* Set 16: Mac Pro 3,1 (2 x Quad-Core) */ + { "TA0P", "TCAG", "TCAH", "TCBG", "TCBH", "TC0C", "TC0D", "TC0P", + "TC1C", "TC1D", "TC2C", "TC2D", "TC3C", "TC3D", "TH0P", "TH1P", + "TH2P", "TH3P", "TMAP", "TMAS", "TMBS", "TM0P", "TM0S", "TM1P", + "TM1S", "TM2P", "TM2S", "TM3S", "TM8P", "TM8S", "TM9P", "TM9S", + "TN0C", "TN0D", "TN0H", "TS0C", "Tp0C", "Tp1C", "Tv0S", "Tv1S", + NULL }, }; /* List of keys used to read/write fan speeds */ @@ -1153,6 +1160,16 @@ static SENSOR_DEVICE_ATTR(temp34_input, S_IRUGO, applesmc_show_temperature, NULL, 33); static SENSOR_DEVICE_ATTR(temp35_input, S_IRUGO, applesmc_show_temperature, NULL, 34); +static SENSOR_DEVICE_ATTR(temp36_input, S_IRUGO, + applesmc_show_temperature, NULL, 35); +static SENSOR_DEVICE_ATTR(temp37_input, S_IRUGO, + applesmc_show_temperature, NULL, 36); +static SENSOR_DEVICE_ATTR(temp38_input, S_IRUGO, + applesmc_show_temperature, NULL, 37); +static SENSOR_DEVICE_ATTR(temp39_input, S_IRUGO, + applesmc_show_temperature, NULL, 38); +static SENSOR_DEVICE_ATTR(temp40_input, S_IRUGO, + applesmc_show_temperature, NULL, 39); static struct attribute *temperature_attributes[] = { &sensor_dev_attr_temp1_input.dev_attr.attr, @@ -1190,6 +1207,11 @@ static struct attribute *temperature_attributes[] = { &sensor_dev_attr_temp33_input.dev_attr.attr, &sensor_dev_attr_temp34_input.dev_attr.attr, &sensor_dev_attr_temp35_input.dev_attr.attr, + &sensor_dev_attr_temp36_input.dev_attr.attr, + &sensor_dev_attr_temp37_input.dev_attr.attr, + &sensor_dev_attr_temp38_input.dev_attr.attr, + &sensor_dev_attr_temp39_input.dev_attr.attr, + &sensor_dev_attr_temp40_input.dev_attr.attr, NULL }; @@ -1312,6 +1334,8 @@ static __initdata struct dmi_match_data applesmc_dmi_data[] = { { .accelerometer = 0, .light = 0, .temperature_set = 14 }, /* MacBook Air 2,1: accelerometer, backlight and temperature set 15 */ { .accelerometer = 1, .light = 1, .temperature_set = 15 }, +/* MacPro3,1: temperature set 16 */ + { .accelerometer = 0, .light = 0, .temperature_set = 16 }, }; /* Note that DMI_MATCH(...,"MacBook") will match "MacBookPro1,1". @@ -1369,6 +1393,10 @@ static __initdata struct dmi_system_id applesmc_whitelist[] = { DMI_MATCH(DMI_BOARD_VENDOR,"Apple"), DMI_MATCH(DMI_PRODUCT_NAME,"MacPro2") }, &applesmc_dmi_data[4]}, + { applesmc_dmi_match, "Apple MacPro3", { + DMI_MATCH(DMI_BOARD_VENDOR, "Apple"), + DMI_MATCH(DMI_PRODUCT_NAME, "MacPro3") }, + &applesmc_dmi_data[16]}, { applesmc_dmi_match, "Apple MacPro", { DMI_MATCH(DMI_BOARD_VENDOR, "Apple"), DMI_MATCH(DMI_PRODUCT_NAME, "MacPro") }, diff --git a/drivers/ieee1394/ieee1394.h b/drivers/ieee1394/ieee1394.h index e0ae0d3d747..af320e2c507 100644 --- a/drivers/ieee1394/ieee1394.h +++ b/drivers/ieee1394/ieee1394.h @@ -54,9 +54,7 @@ #define IEEE1394_SPEED_800 0x03 #define IEEE1394_SPEED_1600 0x04 #define IEEE1394_SPEED_3200 0x05 - -/* The current highest tested speed supported by the subsystem */ -#define IEEE1394_SPEED_MAX IEEE1394_SPEED_800 +#define IEEE1394_SPEED_MAX IEEE1394_SPEED_3200 /* Maps speed values above to a string representation */ extern const char *hpsb_speedto_str[]; diff --git a/drivers/ieee1394/ieee1394_core.c b/drivers/ieee1394/ieee1394_core.c index dcdb71a7718..2beb8d94f7b 100644 --- a/drivers/ieee1394/ieee1394_core.c +++ b/drivers/ieee1394/ieee1394_core.c @@ -338,6 +338,7 @@ static void build_speed_map(struct hpsb_host *host, int nodecount) u8 cldcnt[nodecount]; u8 *map = host->speed_map; u8 *speedcap = host->speed; + u8 local_link_speed = host->csr.lnk_spd; struct selfid *sid; struct ext_selfid *esid; int i, j, n; @@ -373,8 +374,8 @@ static void build_speed_map(struct hpsb_host *host, int nodecount) if (sid->port2 == SELFID_PORT_CHILD) cldcnt[n]++; speedcap[n] = sid->speed; - if (speedcap[n] > host->csr.lnk_spd) - speedcap[n] = host->csr.lnk_spd; + if (speedcap[n] > local_link_speed) + speedcap[n] = local_link_speed; n--; } } @@ -407,12 +408,11 @@ static void build_speed_map(struct hpsb_host *host, int nodecount) } } -#if SELFID_SPEED_UNKNOWN != IEEE1394_SPEED_MAX - /* assume maximum speed for 1394b PHYs, nodemgr will correct it */ - for (n = 0; n < nodecount; n++) - if (speedcap[n] == SELFID_SPEED_UNKNOWN) - speedcap[n] = IEEE1394_SPEED_MAX; -#endif + /* assume a maximum speed for 1394b PHYs, nodemgr will correct it */ + if (local_link_speed > SELFID_SPEED_UNKNOWN) + for (i = 0; i < nodecount; i++) + if (speedcap[i] == SELFID_SPEED_UNKNOWN) + speedcap[i] = local_link_speed; } diff --git a/drivers/ieee1394/ohci1394.h b/drivers/ieee1394/ohci1394.h index 4320bf01049..7fb8ab9780a 100644 --- a/drivers/ieee1394/ohci1394.h +++ b/drivers/ieee1394/ohci1394.h @@ -26,7 +26,7 @@ #define OHCI1394_DRIVER_NAME "ohci1394" -#define OHCI1394_MAX_AT_REQ_RETRIES 0x2 +#define OHCI1394_MAX_AT_REQ_RETRIES 0xf #define OHCI1394_MAX_AT_RESP_RETRIES 0x2 #define OHCI1394_MAX_PHYS_RESP_RETRIES 0x8 #define OHCI1394_MAX_SELF_ID_ERRORS 16 diff --git a/drivers/ieee1394/sbp2.c b/drivers/ieee1394/sbp2.c index ab1034ccb7f..f3fd8657ce4 100644 --- a/drivers/ieee1394/sbp2.c +++ b/drivers/ieee1394/sbp2.c @@ -115,8 +115,8 @@ */ static int sbp2_max_speed = IEEE1394_SPEED_MAX; module_param_named(max_speed, sbp2_max_speed, int, 0644); -MODULE_PARM_DESC(max_speed, "Force max speed " - "(3 = 800Mb/s, 2 = 400Mb/s, 1 = 200Mb/s, 0 = 100Mb/s)"); +MODULE_PARM_DESC(max_speed, "Limit data transfer speed (5 <= 3200, " + "4 <= 1600, 3 <= 800, 2 <= 400, 1 <= 200, 0 = 100 Mb/s)"); /* * Set serialize_io to 0 or N to use dynamically appended lists of command ORBs. @@ -256,7 +256,7 @@ static int sbp2_set_busy_timeout(struct sbp2_lu *); static int sbp2_max_speed_and_size(struct sbp2_lu *); -static const u8 sbp2_speedto_max_payload[] = { 0x7, 0x8, 0x9, 0xA, 0xB, 0xC }; +static const u8 sbp2_speedto_max_payload[] = { 0x7, 0x8, 0x9, 0xa, 0xa, 0xa }; static DEFINE_RWLOCK(sbp2_hi_logical_units_lock); @@ -347,8 +347,8 @@ static struct scsi_host_template sbp2_shost_template = { .sdev_attrs = sbp2_sysfs_sdev_attrs, }; -/* for match-all entries in sbp2_workarounds_table */ -#define SBP2_ROM_VALUE_WILDCARD 0x1000000 +#define SBP2_ROM_VALUE_WILDCARD ~0 /* match all */ +#define SBP2_ROM_VALUE_MISSING 0xff000000 /* not present in the unit dir. */ /* * List of devices with known bugs. @@ -359,60 +359,70 @@ static struct scsi_host_template sbp2_shost_template = { */ static const struct { u32 firmware_revision; - u32 model_id; + u32 model; unsigned workarounds; } sbp2_workarounds_table[] = { /* DViCO Momobay CX-1 with TSB42AA9 bridge */ { .firmware_revision = 0x002800, - .model_id = 0x001010, + .model = 0x001010, .workarounds = SBP2_WORKAROUND_INQUIRY_36 | SBP2_WORKAROUND_MODE_SENSE_8 | SBP2_WORKAROUND_POWER_CONDITION, }, /* DViCO Momobay FX-3A with TSB42AA9A bridge */ { .firmware_revision = 0x002800, - .model_id = 0x000000, + .model = 0x000000, .workarounds = SBP2_WORKAROUND_DELAY_INQUIRY | SBP2_WORKAROUND_POWER_CONDITION, }, /* Initio bridges, actually only needed for some older ones */ { .firmware_revision = 0x000200, - .model_id = SBP2_ROM_VALUE_WILDCARD, + .model = SBP2_ROM_VALUE_WILDCARD, .workarounds = SBP2_WORKAROUND_INQUIRY_36, }, /* PL-3507 bridge with Prolific firmware */ { .firmware_revision = 0x012800, - .model_id = SBP2_ROM_VALUE_WILDCARD, + .model = SBP2_ROM_VALUE_WILDCARD, .workarounds = SBP2_WORKAROUND_POWER_CONDITION, }, /* Symbios bridge */ { .firmware_revision = 0xa0b800, - .model_id = SBP2_ROM_VALUE_WILDCARD, + .model = SBP2_ROM_VALUE_WILDCARD, .workarounds = SBP2_WORKAROUND_128K_MAX_TRANS, }, /* Datafab MD2-FW2 with Symbios/LSILogic SYM13FW500 bridge */ { .firmware_revision = 0x002600, - .model_id = SBP2_ROM_VALUE_WILDCARD, + .model = SBP2_ROM_VALUE_WILDCARD, .workarounds = SBP2_WORKAROUND_128K_MAX_TRANS, }, + /* + * iPod 2nd generation: needs 128k max transfer size workaround + * iPod 3rd generation: needs fix capacity workaround + */ + { + .firmware_revision = 0x0a2700, + .model = 0x000000, + .workarounds = SBP2_WORKAROUND_128K_MAX_TRANS | + SBP2_WORKAROUND_FIX_CAPACITY, + }, /* iPod 4th generation */ { .firmware_revision = 0x0a2700, - .model_id = 0x000021, + .model = 0x000021, .workarounds = SBP2_WORKAROUND_FIX_CAPACITY, }, /* iPod mini */ { .firmware_revision = 0x0a2700, - .model_id = 0x000022, + .model = 0x000022, .workarounds = SBP2_WORKAROUND_FIX_CAPACITY, }, /* iPod mini */ { .firmware_revision = 0x0a2700, - .model_id = 0x000023, + .model = 0x000023, .workarounds = SBP2_WORKAROUND_FIX_CAPACITY, }, /* iPod Photo */ { .firmware_revision = 0x0a2700, - .model_id = 0x00007e, + .model = 0x00007e, .workarounds = SBP2_WORKAROUND_FIX_CAPACITY, } }; @@ -1341,13 +1351,15 @@ static void sbp2_parse_unit_directory(struct sbp2_lu *lu, struct csr1212_keyval *kv; struct csr1212_dentry *dentry; u64 management_agent_addr; - u32 unit_characteristics, firmware_revision; + u32 unit_characteristics, firmware_revision, model; unsigned workarounds; int i; management_agent_addr = 0; unit_characteristics = 0; - firmware_revision = 0; + firmware_revision = SBP2_ROM_VALUE_MISSING; + model = ud->flags & UNIT_DIRECTORY_MODEL_ID ? + ud->model_id : SBP2_ROM_VALUE_MISSING; csr1212_for_each_dir_entry(ud->ne->csr, kv, ud->ud_kv, dentry) { switch (kv->key.id) { @@ -1388,9 +1400,9 @@ static void sbp2_parse_unit_directory(struct sbp2_lu *lu, sbp2_workarounds_table[i].firmware_revision != (firmware_revision & 0xffff00)) continue; - if (sbp2_workarounds_table[i].model_id != + if (sbp2_workarounds_table[i].model != SBP2_ROM_VALUE_WILDCARD && - sbp2_workarounds_table[i].model_id != ud->model_id) + sbp2_workarounds_table[i].model != model) continue; workarounds |= sbp2_workarounds_table[i].workarounds; break; @@ -1403,7 +1415,7 @@ static void sbp2_parse_unit_directory(struct sbp2_lu *lu, NODE_BUS_ARGS(ud->ne->host, ud->ne->nodeid), workarounds, firmware_revision, ud->vendor_id ? ud->vendor_id : ud->ne->vendor_id, - ud->model_id); + model); /* We would need one SCSI host template for each target to adjust * max_sectors on the fly, therefore warn only. */ diff --git a/drivers/lguest/core.c b/drivers/lguest/core.c index 90663e01a56..60156dfdc60 100644 --- a/drivers/lguest/core.c +++ b/drivers/lguest/core.c @@ -224,7 +224,7 @@ int run_guest(struct lg_cpu *cpu, unsigned long __user *user) break; /* If the Guest asked to be stopped, we sleep. The Guest's - * clock timer or LHCALL_BREAK from the Waker will wake us. */ + * clock timer or LHREQ_BREAK from the Waker will wake us. */ if (cpu->halted) { set_current_state(TASK_INTERRUPTIBLE); schedule(); diff --git a/drivers/lguest/lguest_user.c b/drivers/lguest/lguest_user.c index 34bc017b8b3..b8ee103eed5 100644 --- a/drivers/lguest/lguest_user.c +++ b/drivers/lguest/lguest_user.c @@ -307,9 +307,8 @@ static int close(struct inode *inode, struct file *file) * kmalloc()ed string, either of which is ok to hand to kfree(). */ if (!IS_ERR(lg->dead)) kfree(lg->dead); - /* We clear the entire structure, which also marks it as free for the - * next user. */ - memset(lg, 0, sizeof(*lg)); + /* Free the memory allocated to the lguest_struct */ + kfree(lg); /* Release lock and exit. */ mutex_unlock(&lguest_lock); diff --git a/drivers/misc/hpilo.c b/drivers/misc/hpilo.c index 05e29828923..10c421b73ea 100644 --- a/drivers/misc/hpilo.c +++ b/drivers/misc/hpilo.c @@ -758,7 +758,7 @@ static void __exit ilo_exit(void) class_destroy(ilo_class); } -MODULE_VERSION("0.05"); +MODULE_VERSION("0.06"); MODULE_ALIAS(ILO_NAME); MODULE_DESCRIPTION(ILO_NAME); MODULE_AUTHOR("David Altobelli <david.altobelli@hp.com>"); diff --git a/drivers/misc/sgi-xp/xpc_channel.c b/drivers/misc/sgi-xp/xpc_channel.c index 9cd2ebe2a3b..45fd653dbe3 100644 --- a/drivers/misc/sgi-xp/xpc_channel.c +++ b/drivers/misc/sgi-xp/xpc_channel.c @@ -49,9 +49,6 @@ xpc_process_connect(struct xpc_channel *ch, unsigned long *irq_flags) if (ch->flags & (XPC_C_CONNECTED | XPC_C_DISCONNECTING)) return; - - DBUG_ON(ch->local_msgqueue == NULL); - DBUG_ON(ch->remote_msgqueue == NULL); } if (!(ch->flags & XPC_C_OPENREPLY)) { diff --git a/drivers/misc/sgi-xp/xpc_sn2.c b/drivers/misc/sgi-xp/xpc_sn2.c index 82fb9958f22..2e975762c32 100644 --- a/drivers/misc/sgi-xp/xpc_sn2.c +++ b/drivers/misc/sgi-xp/xpc_sn2.c @@ -1106,8 +1106,6 @@ xpc_process_activate_IRQ_rcvd_sn2(void) int n_IRQs_expected; int n_IRQs_detected; - DBUG_ON(xpc_activate_IRQ_rcvd == 0); - spin_lock_irqsave(&xpc_activate_IRQ_rcvd_lock, irq_flags); n_IRQs_expected = xpc_activate_IRQ_rcvd; xpc_activate_IRQ_rcvd = 0; @@ -1726,6 +1724,7 @@ xpc_clear_local_msgqueue_flags_sn2(struct xpc_channel *ch) msg = (struct xpc_msg_sn2 *)((u64)ch_sn2->local_msgqueue + (get % ch->local_nentries) * ch->entry_size); + DBUG_ON(!(msg->flags & XPC_M_SN2_READY)); msg->flags = 0; } while (++get < ch_sn2->remote_GP.get); } @@ -1740,11 +1739,18 @@ xpc_clear_remote_msgqueue_flags_sn2(struct xpc_channel *ch) struct xpc_msg_sn2 *msg; s64 put; - put = ch_sn2->w_remote_GP.put; + /* flags are zeroed when the buffer is allocated */ + if (ch_sn2->remote_GP.put < ch->remote_nentries) + return; + + put = max(ch_sn2->w_remote_GP.put, ch->remote_nentries); do { msg = (struct xpc_msg_sn2 *)((u64)ch_sn2->remote_msgqueue + (put % ch->remote_nentries) * ch->entry_size); + DBUG_ON(!(msg->flags & XPC_M_SN2_READY)); + DBUG_ON(!(msg->flags & XPC_M_SN2_DONE)); + DBUG_ON(msg->number != put - ch->remote_nentries); msg->flags = 0; } while (++put < ch_sn2->remote_GP.put); } @@ -1836,6 +1842,7 @@ xpc_process_msg_chctl_flags_sn2(struct xpc_partition *part, int ch_number) */ xpc_clear_remote_msgqueue_flags_sn2(ch); + smp_wmb(); /* ensure flags have been cleared before bte_copy */ ch_sn2->w_remote_GP.put = ch_sn2->remote_GP.put; dev_dbg(xpc_chan, "w_remote_GP.put changed to %ld, partid=%d, " @@ -1934,7 +1941,7 @@ xpc_get_deliverable_payload_sn2(struct xpc_channel *ch) break; get = ch_sn2->w_local_GP.get; - rmb(); /* guarantee that .get loads before .put */ + smp_rmb(); /* guarantee that .get loads before .put */ if (get == ch_sn2->w_remote_GP.put) break; @@ -1956,11 +1963,13 @@ xpc_get_deliverable_payload_sn2(struct xpc_channel *ch) msg = xpc_pull_remote_msg_sn2(ch, get); - DBUG_ON(msg != NULL && msg->number != get); - DBUG_ON(msg != NULL && (msg->flags & XPC_M_SN2_DONE)); - DBUG_ON(msg != NULL && !(msg->flags & XPC_M_SN2_READY)); + if (msg != NULL) { + DBUG_ON(msg->number != get); + DBUG_ON(msg->flags & XPC_M_SN2_DONE); + DBUG_ON(!(msg->flags & XPC_M_SN2_READY)); - payload = &msg->payload; + payload = &msg->payload; + } break; } @@ -2053,7 +2062,7 @@ xpc_allocate_msg_sn2(struct xpc_channel *ch, u32 flags, while (1) { put = ch_sn2->w_local_GP.put; - rmb(); /* guarantee that .put loads before .get */ + smp_rmb(); /* guarantee that .put loads before .get */ if (put - ch_sn2->w_remote_GP.get < ch->local_nentries) { /* There are available message entries. We need to try @@ -2186,7 +2195,7 @@ xpc_send_payload_sn2(struct xpc_channel *ch, u32 flags, void *payload, * The preceding store of msg->flags must occur before the following * load of local_GP->put. */ - mb(); + smp_mb(); /* see if the message is next in line to be sent, if so send it */ @@ -2277,8 +2286,9 @@ xpc_received_payload_sn2(struct xpc_channel *ch, void *payload) dev_dbg(xpc_chan, "msg=0x%p, msg_number=%ld, partid=%d, channel=%d\n", (void *)msg, msg_number, ch->partid, ch->number); - DBUG_ON((((u64)msg - (u64)ch->remote_msgqueue) / ch->entry_size) != + DBUG_ON((((u64)msg - (u64)ch->sn.sn2.remote_msgqueue) / ch->entry_size) != msg_number % ch->remote_nentries); + DBUG_ON(!(msg->flags & XPC_M_SN2_READY)); DBUG_ON(msg->flags & XPC_M_SN2_DONE); msg->flags |= XPC_M_SN2_DONE; @@ -2287,7 +2297,7 @@ xpc_received_payload_sn2(struct xpc_channel *ch, void *payload) * The preceding store of msg->flags must occur before the following * load of local_GP->get. */ - mb(); + smp_mb(); /* * See if this message is next in line to be acknowledged as having diff --git a/drivers/misc/sgi-xp/xpc_uv.c b/drivers/misc/sgi-xp/xpc_uv.c index 91a55b1b103..f17f7d40ea2 100644 --- a/drivers/misc/sgi-xp/xpc_uv.c +++ b/drivers/misc/sgi-xp/xpc_uv.c @@ -1423,7 +1423,7 @@ xpc_send_payload_uv(struct xpc_channel *ch, u32 flags, void *payload, atomic_inc(&ch->n_to_notify); msg_slot->key = key; - wmb(); /* a non-NULL func must hit memory after the key */ + smp_wmb(); /* a non-NULL func must hit memory after the key */ msg_slot->func = func; if (ch->flags & XPC_C_DISCONNECTING) { diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c index 7c789f0a94d..de91ddab0a8 100644 --- a/drivers/platform/x86/hp-wmi.c +++ b/drivers/platform/x86/hp-wmi.c @@ -382,6 +382,11 @@ static int __init hp_wmi_input_setup(void) case KE_SW: set_bit(EV_SW, hp_wmi_input_dev->evbit); set_bit(key->keycode, hp_wmi_input_dev->swbit); + + /* Set initial dock state */ + input_report_switch(hp_wmi_input_dev, key->keycode, + hp_wmi_dock_state()); + input_sync(hp_wmi_input_dev); break; } } @@ -441,6 +446,7 @@ static int __init hp_wmi_bios_setup(struct platform_device *device) bluetooth_rfkill->toggle_radio = hp_wmi_bluetooth_set; bluetooth_rfkill->user_claim_unsupported = 1; err = rfkill_register(bluetooth_rfkill); + if (err) goto register_bluetooth_error; } diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig index c94f71980c1..f0267706cb4 100644 --- a/drivers/video/Kconfig +++ b/drivers/video/Kconfig @@ -41,7 +41,7 @@ menuconfig FB You need an utility program called fbset to make full use of frame buffer devices. Please read <file:Documentation/fb/framebuffer.txt> and the Framebuffer-HOWTO at - <http://www.tahallah.demon.co.uk/programming/prog.html> for more + <http://www.munted.org.uk/programming/Framebuffer-HOWTO-1.2.html> for more information. Say Y here and to the driver for your graphics board below if you diff --git a/fs/eventpoll.c b/fs/eventpoll.c index ba2f9ec7119..011b9b8c90c 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -234,8 +234,6 @@ struct ep_pqueue { /* * Configuration options available inside /proc/sys/fs/epoll/ */ -/* Maximum number of epoll devices, per user */ -static int max_user_instances __read_mostly; /* Maximum number of epoll watched descriptors, per user */ static int max_user_watches __read_mostly; @@ -261,14 +259,6 @@ static int zero; ctl_table epoll_table[] = { { - .procname = "max_user_instances", - .data = &max_user_instances, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .extra1 = &zero, - }, - { .procname = "max_user_watches", .data = &max_user_watches, .maxlen = sizeof(int), @@ -491,7 +481,6 @@ static void ep_free(struct eventpoll *ep) mutex_unlock(&epmutex); mutex_destroy(&ep->mtx); - atomic_dec(&ep->user->epoll_devs); free_uid(ep->user); kfree(ep); } @@ -581,10 +570,6 @@ static int ep_alloc(struct eventpoll **pep) struct eventpoll *ep; user = get_current_user(); - error = -EMFILE; - if (unlikely(atomic_read(&user->epoll_devs) >= - max_user_instances)) - goto free_uid; error = -ENOMEM; ep = kzalloc(sizeof(*ep), GFP_KERNEL); if (unlikely(!ep)) @@ -1141,7 +1126,6 @@ SYSCALL_DEFINE1(epoll_create1, int, flags) flags & O_CLOEXEC); if (fd < 0) ep_free(ep); - atomic_inc(&ep->user->epoll_devs); error_return: DNPRINTK(3, (KERN_INFO "[%p] eventpoll: sys_epoll_create(%d) = %d\n", @@ -1366,8 +1350,10 @@ static int __init eventpoll_init(void) struct sysinfo si; si_meminfo(&si); - max_user_instances = 128; - max_user_watches = (((si.totalram - si.totalhigh) / 32) << PAGE_SHIFT) / + /* + * Allows top 4% of lomem to be allocated for epoll watches (per user). + */ + max_user_watches = (((si.totalram - si.totalhigh) / 25) << PAGE_SHIFT) / EP_ITEM_COST; /* Initialize the structure used to perform safe poll wait head wake ups */ diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index e267e62827b..e4e8e117d27 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -99,6 +99,7 @@ static inline bool css_tryget(struct cgroup_subsys_state *css) while (!atomic_inc_not_zero(&css->refcnt)) { if (test_bit(CSS_REMOVED, &css->flags)) return false; + cpu_relax(); } return true; } diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index d6ea19e314b..32851eef48f 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -49,6 +49,13 @@ /* Attach to insert probes on any functions which should be ignored*/ #define __kprobes __attribute__((__section__(".kprobes.text"))) notrace +#else /* CONFIG_KPROBES */ +typedef int kprobe_opcode_t; +struct arch_specific_insn { + int dummy; +}; +#define __kprobes notrace +#endif /* CONFIG_KPROBES */ struct kprobe; struct pt_regs; @@ -131,23 +138,6 @@ struct jprobe { /* For backward compatibility with old code using JPROBE_ENTRY() */ #define JPROBE_ENTRY(handler) (handler) -DECLARE_PER_CPU(struct kprobe *, current_kprobe); -DECLARE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); - -#ifdef CONFIG_KRETPROBES -extern void arch_prepare_kretprobe(struct kretprobe_instance *ri, - struct pt_regs *regs); -extern int arch_trampoline_kprobe(struct kprobe *p); -#else /* CONFIG_KRETPROBES */ -static inline void arch_prepare_kretprobe(struct kretprobe *rp, - struct pt_regs *regs) -{ -} -static inline int arch_trampoline_kprobe(struct kprobe *p) -{ - return 0; -} -#endif /* CONFIG_KRETPROBES */ /* * Function-return probe - * Note: @@ -188,6 +178,25 @@ struct kprobe_blackpoint { unsigned long range; }; +#ifdef CONFIG_KPROBES +DECLARE_PER_CPU(struct kprobe *, current_kprobe); +DECLARE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); + +#ifdef CONFIG_KRETPROBES +extern void arch_prepare_kretprobe(struct kretprobe_instance *ri, + struct pt_regs *regs); +extern int arch_trampoline_kprobe(struct kprobe *p); +#else /* CONFIG_KRETPROBES */ +static inline void arch_prepare_kretprobe(struct kretprobe *rp, + struct pt_regs *regs) +{ +} +static inline int arch_trampoline_kprobe(struct kprobe *p) +{ + return 0; +} +#endif /* CONFIG_KRETPROBES */ + extern struct kretprobe_blackpoint kretprobe_blacklist[]; static inline void kretprobe_assert(struct kretprobe_instance *ri, @@ -264,10 +273,6 @@ void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head); #else /* CONFIG_KPROBES */ -#define __kprobes notrace -struct jprobe; -struct kretprobe; - static inline struct kprobe *get_kprobe(void *addr) { return NULL; diff --git a/include/linux/sched.h b/include/linux/sched.h index 02e16d20730..5a7c7638873 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -630,7 +630,6 @@ struct user_struct { atomic_t inotify_devs; /* How many inotify devs does this user have opened? */ #endif #ifdef CONFIG_EPOLL - atomic_t epoll_devs; /* The number of epoll descriptors currently open */ atomic_t epoll_watches; /* The number of file descriptors currently watched */ #endif #ifdef CONFIG_POSIX_MQUEUE diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 16875f89e6a..0eda02ff241 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -108,9 +108,14 @@ struct old_linux_dirent; asm ("\t.globl " #alias "\n\t.set " #alias ", " #name "\n" \ "\t.globl ." #alias "\n\t.set ." #alias ", ." #name) #else +#ifdef CONFIG_ALPHA +#define SYSCALL_ALIAS(alias, name) \ + asm ( #alias " = " #name "\n\t.globl " #alias) +#else #define SYSCALL_ALIAS(alias, name) \ asm ("\t.globl " #alias "\n\t.set " #alias ", " #name) #endif +#endif #ifdef CONFIG_HAVE_SYSCALL_WRAPPERS diff --git a/kernel/cgroup.c b/kernel/cgroup.c index c29831076e7..5a54ff42874 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1115,8 +1115,10 @@ static void cgroup_kill_sb(struct super_block *sb) { } write_unlock(&css_set_lock); - list_del(&root->root_list); - root_count--; + if (!list_empty(&root->root_list)) { + list_del(&root->root_list); + root_count--; + } mutex_unlock(&cgroup_mutex); @@ -2434,7 +2436,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, err_remove: + cgroup_lock_hierarchy(root); list_del(&cgrp->sibling); + cgroup_unlock_hierarchy(root); root->number_of_cgroups--; err_destroy: @@ -2507,7 +2511,7 @@ static int cgroup_clear_css_refs(struct cgroup *cgrp) for_each_subsys(cgrp->root, ss) { struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id]; int refcnt; - do { + while (1) { /* We can only remove a CSS with a refcnt==1 */ refcnt = atomic_read(&css->refcnt); if (refcnt > 1) { @@ -2521,7 +2525,10 @@ static int cgroup_clear_css_refs(struct cgroup *cgrp) * css_tryget() to spin until we set the * CSS_REMOVED bits or abort */ - } while (atomic_cmpxchg(&css->refcnt, refcnt, 0) != refcnt); + if (atomic_cmpxchg(&css->refcnt, refcnt, 0) == refcnt) + break; + cpu_relax(); + } } done: for_each_subsys(cgrp->root, ss) { @@ -2991,20 +2998,21 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys, mutex_unlock(&cgroup_mutex); return 0; } - task_lock(tsk); - cg = tsk->cgroups; - parent = task_cgroup(tsk, subsys->subsys_id); /* Pin the hierarchy */ - if (!atomic_inc_not_zero(&parent->root->sb->s_active)) { + if (!atomic_inc_not_zero(&root->sb->s_active)) { /* We race with the final deactivate_super() */ mutex_unlock(&cgroup_mutex); return 0; } /* Keep the cgroup alive */ + task_lock(tsk); + parent = task_cgroup(tsk, subsys->subsys_id); + cg = tsk->cgroups; get_css_set(cg); task_unlock(tsk); + mutex_unlock(&cgroup_mutex); /* Now do the VFS work to create a cgroup */ @@ -3043,7 +3051,7 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys, mutex_unlock(&inode->i_mutex); put_css_set(cg); - deactivate_super(parent->root->sb); + deactivate_super(root->sb); /* The cgroup is still accessible in the VFS, but * we're not going to try to rmdir() it at this * point. */ @@ -3069,7 +3077,7 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys, mutex_lock(&cgroup_mutex); put_css_set(cg); mutex_unlock(&cgroup_mutex); - deactivate_super(parent->root->sb); + deactivate_super(root->sb); return ret; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 4d0ea3ceba6..8e4be9cb2a6 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -202,6 +202,7 @@ pcg_default_flags[NR_CHARGE_TYPE] = { static void mem_cgroup_get(struct mem_cgroup *mem); static void mem_cgroup_put(struct mem_cgroup *mem); +static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem); static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, struct page_cgroup *pc, @@ -1684,7 +1685,7 @@ move_account: /* This is for making all *used* pages to be on LRU. */ lru_add_drain_all(); ret = 0; - for_each_node_state(node, N_POSSIBLE) { + for_each_node_state(node, N_HIGH_MEMORY) { for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) { enum lru_list l; for_each_lru(l) { @@ -2193,10 +2194,23 @@ static void mem_cgroup_get(struct mem_cgroup *mem) static void mem_cgroup_put(struct mem_cgroup *mem) { - if (atomic_dec_and_test(&mem->refcnt)) + if (atomic_dec_and_test(&mem->refcnt)) { + struct mem_cgroup *parent = parent_mem_cgroup(mem); __mem_cgroup_free(mem); + if (parent) + mem_cgroup_put(parent); + } } +/* + * Returns the parent mem_cgroup in memcgroup hierarchy with hierarchy enabled. + */ +static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem) +{ + if (!mem->res.parent) + return NULL; + return mem_cgroup_from_res_counter(mem->res.parent, res); +} #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP static void __init enable_swap_cgroup(void) @@ -2235,6 +2249,13 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) if (parent && parent->use_hierarchy) { res_counter_init(&mem->res, &parent->res); res_counter_init(&mem->memsw, &parent->memsw); + /* + * We increment refcnt of the parent to ensure that we can + * safely access it on res_counter_charge/uncharge. + * This refcnt will be decremented when freeing this + * mem_cgroup(see mem_cgroup_put). + */ + mem_cgroup_get(parent); } else { res_counter_init(&mem->res, NULL); res_counter_init(&mem->memsw, NULL); diff --git a/mm/mmap.c b/mm/mmap.c index 8d95902e9a3..d3fa10a726c 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1134,16 +1134,11 @@ munmap_back: } /* - * Can we just expand an old private anonymous mapping? - * The VM_SHARED test is necessary because shmem_zero_setup - * will create the file object for a shared anonymous map below. + * Can we just expand an old mapping? */ - if (!file && !(vm_flags & VM_SHARED)) { - vma = vma_merge(mm, prev, addr, addr + len, vm_flags, - NULL, NULL, pgoff, NULL); - if (vma) - goto out; - } + vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff, NULL); + if (vma) + goto out; /* * Determine the object being mapped and call the appropriate @@ -1206,17 +1201,8 @@ munmap_back: if (vma_wants_writenotify(vma)) vma->vm_page_prot = vm_get_page_prot(vm_flags & ~VM_SHARED); - if (file && vma_merge(mm, prev, addr, vma->vm_end, - vma->vm_flags, NULL, file, pgoff, vma_policy(vma))) { - mpol_put(vma_policy(vma)); - kmem_cache_free(vm_area_cachep, vma); - fput(file); - if (vm_flags & VM_EXECUTABLE) - removed_exe_file_vma(mm); - } else { - vma_link(mm, vma, prev, rb_link, rb_parent); - file = vma->vm_file; - } + vma_link(mm, vma, prev, rb_link, rb_parent); + file = vma->vm_file; /* Once vma denies write, undo our temporary denial count */ if (correct_wcount) diff --git a/mm/swapfile.c b/mm/swapfile.c index f48b831e5e5..7e6304dfafa 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -698,8 +698,10 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, pte_t *pte; int ret = 1; - if (mem_cgroup_try_charge_swapin(vma->vm_mm, page, GFP_KERNEL, &ptr)) + if (mem_cgroup_try_charge_swapin(vma->vm_mm, page, GFP_KERNEL, &ptr)) { ret = -ENOMEM; + goto out_nolock; + } pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte_same(*pte, swp_entry_to_pte(entry)))) { @@ -723,6 +725,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, activate_page(page); out: pte_unmap_unlock(pte, ptl); +out_nolock: return ret; } |