From 6b4e306aa3dc94a0545eb9279475b1ab6209a31f Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Sun, 7 Mar 2010 16:41:34 -0800 Subject: ns: proc files for namespace naming policy. Create files under /proc//ns/ to allow controlling the namespaces of a process. This addresses three specific problems that can make namespaces hard to work with. - Namespaces require a dedicated process to pin them in memory. - It is not possible to use a namespace unless you are the child of the original creator. - Namespaces don't have names that userspace can use to talk about them. The namespace files under /proc//ns/ can be opened and the file descriptor can be used to talk about a specific namespace, and to keep the specified namespace alive. A namespace can be kept alive by either holding the file descriptor open or bind mounting the file someplace else. aka: mount --bind /proc/self/ns/net /some/filesystem/path mount --bind /proc/self/fd/ /some/filesystem/path This allows namespaces to be named with userspace policy. It requires additional support to make use of these filedescriptors and that will be comming in the following patches. Acked-by: Daniel Lezcano Signed-off-by: Eric W. Biederman --- fs/proc/base.c | 20 +++++++++----------- 1 file changed, 9 insertions(+), 11 deletions(-) (limited to 'fs/proc/base.c') diff --git a/fs/proc/base.c b/fs/proc/base.c index dfa532730e55..dc8bca72b002 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -600,7 +600,7 @@ static int proc_fd_access_allowed(struct inode *inode) return allowed; } -static int proc_setattr(struct dentry *dentry, struct iattr *attr) +int proc_setattr(struct dentry *dentry, struct iattr *attr) { int error; struct inode *inode = dentry->d_inode; @@ -1736,8 +1736,7 @@ static int task_dumpable(struct task_struct *task) return 0; } - -static struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task) +struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task) { struct inode * inode; struct proc_inode *ei; @@ -1779,7 +1778,7 @@ out_unlock: return NULL; } -static int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) +int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) { struct inode *inode = dentry->d_inode; struct task_struct *task; @@ -1820,7 +1819,7 @@ static int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat * made this apply to all per process world readable and executable * directories. */ -static int pid_revalidate(struct dentry *dentry, struct nameidata *nd) +int pid_revalidate(struct dentry *dentry, struct nameidata *nd) { struct inode *inode; struct task_struct *task; @@ -1862,7 +1861,7 @@ static int pid_delete_dentry(const struct dentry * dentry) return !proc_pid(dentry->d_inode)->tasks[PIDTYPE_PID].first; } -static const struct dentry_operations pid_dentry_operations = +const struct dentry_operations pid_dentry_operations = { .d_revalidate = pid_revalidate, .d_delete = pid_delete_dentry, @@ -1870,9 +1869,6 @@ static const struct dentry_operations pid_dentry_operations = /* Lookups */ -typedef struct dentry *instantiate_t(struct inode *, struct dentry *, - struct task_struct *, const void *); - /* * Fill a directory entry. * @@ -1885,8 +1881,8 @@ typedef struct dentry *instantiate_t(struct inode *, struct dentry *, * reported by readdir in sync with the inode numbers reported * by stat. */ -static int proc_fill_cache(struct file *filp, void *dirent, filldir_t filldir, - char *name, int len, +int proc_fill_cache(struct file *filp, void *dirent, filldir_t filldir, + const char *name, int len, instantiate_t instantiate, struct task_struct *task, const void *ptr) { struct dentry *child, *dir = filp->f_path.dentry; @@ -2820,6 +2816,7 @@ static const struct pid_entry tgid_base_stuff[] = { DIR("task", S_IRUGO|S_IXUGO, proc_task_inode_operations, proc_task_operations), DIR("fd", S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations), DIR("fdinfo", S_IRUSR|S_IXUSR, proc_fdinfo_inode_operations, proc_fdinfo_operations), + DIR("ns", S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations), #ifdef CONFIG_NET DIR("net", S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations), #endif @@ -3168,6 +3165,7 @@ out_no_task: static const struct pid_entry tid_base_stuff[] = { DIR("fd", S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations), DIR("fdinfo", S_IRUSR|S_IXUSR, proc_fdinfo_inode_operations, proc_fdinfo_operations), + DIR("ns", S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations), REG("environ", S_IRUSR, proc_environ_operations), INF("auxv", S_IRUSR, proc_pid_auxv), ONE("status", S_IRUGO, proc_pid_status), -- cgit v1.2.3 From 3864601387cf4196371e3c1897fdffa5228296f9 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Thu, 26 May 2011 16:25:46 -0700 Subject: mm: extract exe_file handling from procfs Setup and cleanup of mm_struct->exe_file is currently done in fs/proc/. This was because exe_file was needed only for /proc//exe. Since we will need the exe_file functionality also for core dumps (so core name can contain full binary path), built this functionality always into the kernel. To achieve that move that out of proc FS to the kernel/ where in fact it should belong. By doing that we can make dup_mm_exe_file static. Also we can drop linux/proc_fs.h inclusion in fs/exec.c and kernel/fork.c. Signed-off-by: Jiri Slaby Cc: Alexander Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/exec.c | 1 - fs/proc/base.c | 51 ----------------------------------------------- include/linux/mm.h | 10 ++-------- include/linux/mm_types.h | 2 -- include/linux/proc_fs.h | 19 ------------------ kernel/fork.c | 52 +++++++++++++++++++++++++++++++++++++++++++++++- 6 files changed, 53 insertions(+), 82 deletions(-) (limited to 'fs/proc/base.c') diff --git a/fs/exec.c b/fs/exec.c index 936f5776655c..88a16c572282 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -42,7 +42,6 @@ #include #include #include -#include #include #include #include diff --git a/fs/proc/base.c b/fs/proc/base.c index dc8bca72b002..c2ac2fb123c8 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1576,57 +1576,6 @@ static const struct file_operations proc_pid_set_comm_operations = { .release = single_release, }; -/* - * 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) - get_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 */ - down_read(&mm->mmap_sem); - exe_file = mm->exe_file; - if (exe_file) - get_file(exe_file); - up_read(&mm->mmap_sem); - return exe_file; -} - -void dup_mm_exe_file(struct mm_struct *oldmm, struct mm_struct *newmm) -{ - /* It's safe to write the exe_file pointer without exe_file_lock because - * this is called during fork when the task is not yet in /proc */ - newmm->exe_file = get_mm_exe_file(oldmm); -} - static int proc_exe_link(struct inode *inode, struct path *exe_path) { struct task_struct *task; diff --git a/include/linux/mm.h b/include/linux/mm.h index fb8e814f78dc..9670f71d7be9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1408,17 +1408,11 @@ extern void exit_mmap(struct mm_struct *); extern int mm_take_all_locks(struct mm_struct *mm); extern void mm_drop_all_locks(struct mm_struct *mm); -#ifdef CONFIG_PROC_FS /* From fs/proc/base.c. callers must _not_ hold the mm's exe_file_lock */ extern void added_exe_file_vma(struct mm_struct *mm); extern void removed_exe_file_vma(struct mm_struct *mm); -#else -static inline void added_exe_file_vma(struct mm_struct *mm) -{} - -static inline void removed_exe_file_vma(struct mm_struct *mm) -{} -#endif /* CONFIG_PROC_FS */ +extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); +extern struct file *get_mm_exe_file(struct mm_struct *mm); extern int may_expand_vm(struct mm_struct *mm, unsigned long npages); extern int install_special_mapping(struct mm_struct *mm, diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 6fe96c19f85e..2a78aae78c69 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -302,11 +302,9 @@ struct mm_struct { struct task_struct __rcu *owner; #endif -#ifdef CONFIG_PROC_FS /* store ref to file /proc//exe symlink points to */ struct file *exe_file; unsigned long num_exe_file_vmas; -#endif #ifdef CONFIG_MMU_NOTIFIER struct mmu_notifier_mm *mmu_notifier_mm; #endif diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h index 648c9c58add7..e7576cf9e32d 100644 --- a/include/linux/proc_fs.h +++ b/include/linux/proc_fs.h @@ -173,12 +173,6 @@ extern void proc_net_remove(struct net *net, const char *name); extern struct proc_dir_entry *proc_net_mkdir(struct net *net, const char *name, struct proc_dir_entry *parent); -/* While the {get|set|dup}_mm_exe_file functions are for mm_structs, they are - * only needed to implement /proc/|self/exe so we define them here. */ -extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); -extern struct file *get_mm_exe_file(struct mm_struct *mm); -extern void dup_mm_exe_file(struct mm_struct *oldmm, struct mm_struct *newmm); - extern struct file *proc_ns_fget(int fd); #else @@ -230,19 +224,6 @@ static inline void pid_ns_release_proc(struct pid_namespace *ns) { } -static inline void set_mm_exe_file(struct mm_struct *mm, - struct file *new_exe_file) -{} - -static inline struct file *get_mm_exe_file(struct mm_struct *mm) -{ - return NULL; -} - -static inline void dup_mm_exe_file(struct mm_struct *oldmm, - struct mm_struct *newmm) -{} - static inline struct file *proc_ns_fget(int fd) { return ERR_PTR(-EINVAL); diff --git a/kernel/fork.c b/kernel/fork.c index 1f84099ecce6..ca406d916713 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -59,7 +59,6 @@ #include #include #include -#include #include #include #include @@ -597,6 +596,57 @@ 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) + get_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 */ + down_read(&mm->mmap_sem); + exe_file = mm->exe_file; + if (exe_file) + get_file(exe_file); + up_read(&mm->mmap_sem); + return exe_file; +} + +static void dup_mm_exe_file(struct mm_struct *oldmm, struct mm_struct *newmm) +{ + /* It's safe to write the exe_file pointer without exe_file_lock because + * this is called during fork when the task is not yet in /proc */ + newmm->exe_file = get_mm_exe_file(oldmm); +} + /** * get_task_mm - acquire a reference to the task's mm * -- cgit v1.2.3 From 0a8cb8e34149251ad1f280fe099a4f971554639a Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Thu, 26 May 2011 16:25:50 -0700 Subject: fs/proc: convert to kstrtoX() Convert fs/proc/ from strict_strto*() to kstrto*() functions. Signed-off-by: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/base.c | 16 ++++++++-------- fs/proc/task_mmu.c | 8 +++++--- 2 files changed, 13 insertions(+), 11 deletions(-) (limited to 'fs/proc/base.c') diff --git a/fs/proc/base.c b/fs/proc/base.c index c2ac2fb123c8..0c2c50cc2cca 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1059,7 +1059,7 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf, { struct task_struct *task; char buffer[PROC_NUMBUF]; - long oom_adjust; + int oom_adjust; unsigned long flags; int err; @@ -1071,7 +1071,7 @@ static ssize_t oom_adjust_write(struct file *file, const char __user *buf, goto out; } - err = strict_strtol(strstrip(buffer), 0, &oom_adjust); + err = kstrtoint(strstrip(buffer), 0, &oom_adjust); if (err) goto out; if ((oom_adjust < OOM_ADJUST_MIN || oom_adjust > OOM_ADJUST_MAX) && @@ -1168,7 +1168,7 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf, struct task_struct *task; char buffer[PROC_NUMBUF]; unsigned long flags; - long oom_score_adj; + int oom_score_adj; int err; memset(buffer, 0, sizeof(buffer)); @@ -1179,7 +1179,7 @@ static ssize_t oom_score_adj_write(struct file *file, const char __user *buf, goto out; } - err = strict_strtol(strstrip(buffer), 0, &oom_score_adj); + err = kstrtoint(strstrip(buffer), 0, &oom_score_adj); if (err) goto out; if (oom_score_adj < OOM_SCORE_ADJ_MIN || @@ -1468,7 +1468,7 @@ sched_autogroup_write(struct file *file, const char __user *buf, struct inode *inode = file->f_path.dentry->d_inode; struct task_struct *p; char buffer[PROC_NUMBUF]; - long nice; + int nice; int err; memset(buffer, 0, sizeof(buffer)); @@ -1477,9 +1477,9 @@ sched_autogroup_write(struct file *file, const char __user *buf, if (copy_from_user(buffer, buf, count)) return -EFAULT; - err = strict_strtol(strstrip(buffer), 0, &nice); - if (err) - return -EINVAL; + err = kstrtoint(strstrip(buffer), 0, &nice); + if (err < 0) + return err; p = get_proc_task(inode); if (!p) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index db15935fa757..30a6a72d05b2 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -536,15 +536,17 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf, char buffer[PROC_NUMBUF]; struct mm_struct *mm; struct vm_area_struct *vma; - long type; + int type; + int rv; memset(buffer, 0, sizeof(buffer)); if (count > sizeof(buffer) - 1) count = sizeof(buffer) - 1; if (copy_from_user(buffer, buf, count)) return -EFAULT; - if (strict_strtol(strstrip(buffer), 10, &type)) - return -EINVAL; + rv = kstrtoint(strstrip(buffer), 10, &type); + if (rv < 0) + return rv; if (type < CLEAR_REFS_ALL || type > CLEAR_REFS_MAPPED) return -EINVAL; task = get_proc_task(file->f_path.dentry->d_inode); -- cgit v1.2.3 From 30cd8903913dac7b0918807cac46be3ecde5a5a7 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Thu, 26 May 2011 16:25:52 -0700 Subject: proc: put check_mem_permission after __get_free_page in mem_write It whould be better if put check_mem_permission after __get_free_page in mem_write, to be same as function mem_read. Hugh Dickins explained the reason. check_mem_permission gets a reference to the mm. If we __get_free_page after check_mem_permission, imagine what happens if the system is out of memory, and the mm we're looking at is selected for killing by the OOM killer: while we wait in __get_free_page for more memory, no memory is freed from the selected mm because it cannot reach exit_mmap while we hold that reference. Reported-by: Jovi Zhang Signed-off-by: KOSAKI Motohiro Acked-by: Hugh Dickins Reviewed-by: Stephen Wilson Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/base.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'fs/proc/base.c') diff --git a/fs/proc/base.c b/fs/proc/base.c index 0c2c50cc2cca..4ede550517a6 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -894,20 +894,20 @@ static ssize_t mem_write(struct file * file, const char __user *buf, if (!task) goto out_no_task; + copied = -ENOMEM; + page = (char *)__get_free_page(GFP_TEMPORARY); + if (!page) + goto out_task; + mm = check_mem_permission(task); copied = PTR_ERR(mm); if (IS_ERR(mm)) - goto out_task; + goto out_free; copied = -EIO; if (file->private_data != (void *)((long)current->self_exec_id)) goto out_mm; - copied = -ENOMEM; - page = (char *)__get_free_page(GFP_TEMPORARY); - if (!page) - goto out_mm; - copied = 0; while (count > 0) { int this_len, retval; @@ -929,9 +929,11 @@ static ssize_t mem_write(struct file * file, const char __user *buf, count -= retval; } *ppos = dst; - free_page((unsigned long) page); + out_mm: mmput(mm); +out_free: + free_page((unsigned long) page); out_task: put_task_struct(task); out_no_task: -- cgit v1.2.3 From f133ecca9cbb31b5e6e9bda27cbe3034fbf656df Mon Sep 17 00:00:00 2001 From: Chris Metcalf Date: Thu, 26 May 2011 12:40:09 -0400 Subject: arch/tile: more /proc and /sys file support This change introduces a few of the less controversial /proc and /proc/sys interfaces for tile, along with sysfs attributes for various things that were originally proposed as /proc/tile files. It also adjusts the "hardwall" proc API. Arnd Bergmann reviewed the initial arch/tile submission, which included a complete set of all the /proc/tile and /proc/sys/tile knobs that we had added in a somewhat ad hoc way during initial development, and provided feedback on where most of them should go. One knob turned out to be similar enough to the existing /proc/sys/debug/exception-trace that it was re-implemented to use that model instead. Another knob was /proc/tile/grid, which reported the "grid" dimensions of a tile chip (e.g. 8x8 processors = 64-core chip). Arnd suggested looking at sysfs for that, so this change moves that information to a pair of sysfs attributes (chip_width and chip_height) in the /sys/devices/system/cpu directory. We also put the "chip_serial" and "chip_revision" information from our old /proc/tile/board file as attributes in /sys/devices/system/cpu. Other information collected via hypervisor APIs is now placed in /sys/hypervisor. We create a /sys/hypervisor/type file (holding the constant string "tilera") to be parallel with the Xen use of /sys/hypervisor/type holding "xen". We create three top-level files, "version" (the hypervisor's own version), "config_version" (the version of the configuration file), and "hvconfig" (the contents of the configuration file). The remaining information from our old /proc/tile/board and /proc/tile/switch files becomes an attribute group appearing under /sys/hypervisor/board/. Finally, after some feedback from Arnd Bergmann for the previous version of this patch, the /proc/tile/hardwall file is split up into two conceptual parts. First, a directory /proc/tile/hardwall/ which contains one file per active hardwall, each file named after the hardwall's ID and holding a cpulist that says which cpus are enclosed by the hardwall. Second, a /proc/PID file "hardwall" that is either empty (for non-hardwall-using processes) or contains the hardwall ID. Finally, this change pushes the /proc/sys/tile/unaligned_fixup/ directory, with knobs controlling the kernel code for handling the fixup of unaligned exceptions. Reviewed-by: Arnd Bergmann Signed-off-by: Chris Metcalf --- arch/tile/Kconfig | 1 + arch/tile/include/asm/hardwall.h | 15 +++- arch/tile/kernel/Makefile | 2 +- arch/tile/kernel/hardwall.c | 90 ++++++++++++++----- arch/tile/kernel/proc.c | 73 +++++++++++++++ arch/tile/kernel/sysfs.c | 185 +++++++++++++++++++++++++++++++++++++++ fs/proc/base.c | 9 ++ 7 files changed, 347 insertions(+), 28 deletions(-) create mode 100644 arch/tile/kernel/sysfs.c (limited to 'fs/proc/base.c') diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index 635e1bfb1c5d..3f7d63c7ae85 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -12,6 +12,7 @@ config TILE select GENERIC_IRQ_PROBE select GENERIC_PENDING_IRQ if SMP select GENERIC_IRQ_SHOW + select SYS_HYPERVISOR # FIXME: investigate whether we need/want these options. # select HAVE_IOREMAP_PROT diff --git a/arch/tile/include/asm/hardwall.h b/arch/tile/include/asm/hardwall.h index 0bed3ec7b42c..2ac422848c7d 100644 --- a/arch/tile/include/asm/hardwall.h +++ b/arch/tile/include/asm/hardwall.h @@ -40,6 +40,10 @@ #define HARDWALL_DEACTIVATE \ _IO(HARDWALL_IOCTL_BASE, _HARDWALL_DEACTIVATE) +#define _HARDWALL_GET_ID 4 +#define HARDWALL_GET_ID \ + _IO(HARDWALL_IOCTL_BASE, _HARDWALL_GET_ID) + #ifndef __KERNEL__ /* This is the canonical name expected by userspace. */ @@ -47,9 +51,14 @@ #else -/* Hook for /proc/tile/hardwall. */ -struct seq_file; -int proc_tile_hardwall_show(struct seq_file *sf, void *v); +/* /proc hooks for hardwall. */ +struct proc_dir_entry; +#ifdef CONFIG_HARDWALL +void proc_tile_hardwall_init(struct proc_dir_entry *root); +int proc_pid_hardwall(struct task_struct *task, char *buffer); +#else +static inline void proc_tile_hardwall_init(struct proc_dir_entry *root) {} +#endif #endif diff --git a/arch/tile/kernel/Makefile b/arch/tile/kernel/Makefile index b4c8e8ec45dc..b4dbc057baad 100644 --- a/arch/tile/kernel/Makefile +++ b/arch/tile/kernel/Makefile @@ -5,7 +5,7 @@ extra-y := vmlinux.lds head_$(BITS).o obj-y := backtrace.o entry.o init_task.o irq.o messaging.o \ pci-dma.o proc.o process.o ptrace.o reboot.o \ - setup.o signal.o single_step.o stack.o sys.o time.o traps.o \ + setup.o signal.o single_step.o stack.o sys.o sysfs.o time.o traps.o \ intvec_$(BITS).o regs_$(BITS).o tile-desc_$(BITS).o obj-$(CONFIG_HARDWALL) += hardwall.o diff --git a/arch/tile/kernel/hardwall.c b/arch/tile/kernel/hardwall.c index 3bddef710de4..8c41891aab34 100644 --- a/arch/tile/kernel/hardwall.c +++ b/arch/tile/kernel/hardwall.c @@ -40,16 +40,25 @@ struct hardwall_info { struct list_head list; /* "rectangles" list */ struct list_head task_head; /* head of tasks in this hardwall */ + struct cpumask cpumask; /* cpus in the rectangle */ int ulhc_x; /* upper left hand corner x coord */ int ulhc_y; /* upper left hand corner y coord */ int width; /* rectangle width */ int height; /* rectangle height */ + int id; /* integer id for this hardwall */ int teardown_in_progress; /* are we tearing this one down? */ }; /* Currently allocated hardwall rectangles */ static LIST_HEAD(rectangles); +/* /proc/tile/hardwall */ +static struct proc_dir_entry *hardwall_proc_dir; + +/* Functions to manage files in /proc/tile/hardwall. */ +static void hardwall_add_proc(struct hardwall_info *rect); +static void hardwall_remove_proc(struct hardwall_info *rect); + /* * Guard changes to the hardwall data structures. * This could be finer grained (e.g. one lock for the list of hardwall @@ -105,6 +114,8 @@ static int setup_rectangle(struct hardwall_info *r, struct cpumask *mask) r->ulhc_y = cpu_y(ulhc); r->width = cpu_x(lrhc) - r->ulhc_x + 1; r->height = cpu_y(lrhc) - r->ulhc_y + 1; + cpumask_copy(&r->cpumask, mask); + r->id = ulhc; /* The ulhc cpu id can be the hardwall id. */ /* Width and height must be positive */ if (r->width <= 0 || r->height <= 0) @@ -388,6 +399,9 @@ static struct hardwall_info *hardwall_create( /* Set up appropriate hardwalling on all affected cpus. */ hardwall_setup(rect); + /* Create a /proc/tile/hardwall entry. */ + hardwall_add_proc(rect); + return rect; } @@ -645,6 +659,9 @@ static void hardwall_destroy(struct hardwall_info *rect) /* Restart switch and disable firewall. */ on_each_cpu_mask(&mask, restart_udn_switch, NULL, 1); + /* Remove the /proc/tile/hardwall entry. */ + hardwall_remove_proc(rect); + /* Now free the rectangle from the list. */ spin_lock_irqsave(&hardwall_lock, flags); BUG_ON(!list_empty(&rect->task_head)); @@ -654,35 +671,57 @@ static void hardwall_destroy(struct hardwall_info *rect) } -/* - * Dump hardwall state via /proc; initialized in arch/tile/sys/proc.c. - */ -int proc_tile_hardwall_show(struct seq_file *sf, void *v) +static int hardwall_proc_show(struct seq_file *sf, void *v) { - struct hardwall_info *r; + struct hardwall_info *rect = sf->private; + char buf[256]; - if (udn_disabled) { - seq_printf(sf, "%dx%d 0,0 pids:\n", smp_width, smp_height); - return 0; - } - - spin_lock_irq(&hardwall_lock); - list_for_each_entry(r, &rectangles, list) { - struct task_struct *p; - seq_printf(sf, "%dx%d %d,%d pids:", - r->width, r->height, r->ulhc_x, r->ulhc_y); - list_for_each_entry(p, &r->task_head, thread.hardwall_list) { - unsigned int cpu = cpumask_first(&p->cpus_allowed); - unsigned int x = cpu % smp_width; - unsigned int y = cpu / smp_width; - seq_printf(sf, " %d@%d,%d", p->pid, x, y); - } - seq_printf(sf, "\n"); - } - spin_unlock_irq(&hardwall_lock); + int rc = cpulist_scnprintf(buf, sizeof(buf), &rect->cpumask); + buf[rc++] = '\n'; + seq_write(sf, buf, rc); return 0; } +static int hardwall_proc_open(struct inode *inode, + struct file *file) +{ + return single_open(file, hardwall_proc_show, PDE(inode)->data); +} + +static const struct file_operations hardwall_proc_fops = { + .open = hardwall_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static void hardwall_add_proc(struct hardwall_info *rect) +{ + char buf[64]; + snprintf(buf, sizeof(buf), "%d", rect->id); + proc_create_data(buf, 0444, hardwall_proc_dir, + &hardwall_proc_fops, rect); +} + +static void hardwall_remove_proc(struct hardwall_info *rect) +{ + char buf[64]; + snprintf(buf, sizeof(buf), "%d", rect->id); + remove_proc_entry(buf, hardwall_proc_dir); +} + +int proc_pid_hardwall(struct task_struct *task, char *buffer) +{ + struct hardwall_info *rect = task->thread.hardwall; + return rect ? sprintf(buffer, "%d\n", rect->id) : 0; +} + +void proc_tile_hardwall_init(struct proc_dir_entry *root) +{ + if (!udn_disabled) + hardwall_proc_dir = proc_mkdir("hardwall", root); +} + /* * Character device support via ioctl/close. @@ -716,6 +755,9 @@ static long hardwall_ioctl(struct file *file, unsigned int a, unsigned long b) return -EINVAL; return hardwall_deactivate(current); + case _HARDWALL_GET_ID: + return rect ? rect->id : -EINVAL; + default: return -EINVAL; } diff --git a/arch/tile/kernel/proc.c b/arch/tile/kernel/proc.c index 2e02c41ddf3b..62d820833c68 100644 --- a/arch/tile/kernel/proc.c +++ b/arch/tile/kernel/proc.c @@ -27,6 +27,7 @@ #include #include #include +#include #include @@ -88,3 +89,75 @@ const struct seq_operations cpuinfo_op = { .stop = c_stop, .show = show_cpuinfo, }; + +/* + * Support /proc/tile directory + */ + +static int __init proc_tile_init(void) +{ + struct proc_dir_entry *root = proc_mkdir("tile", NULL); + if (root == NULL) + return 0; + + proc_tile_hardwall_init(root); + + return 0; +} + +arch_initcall(proc_tile_init); + +/* + * Support /proc/sys/tile directory + */ + +#ifndef __tilegx__ /* FIXME: GX: no support for unaligned access yet */ +static ctl_table unaligned_subtable[] = { + { + .procname = "enabled", + .data = &unaligned_fixup, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec + }, + { + .procname = "printk", + .data = &unaligned_printk, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec + }, + { + .procname = "count", + .data = &unaligned_fixup_count, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec + }, + {} +}; + +static ctl_table unaligned_table[] = { + { + .procname = "unaligned_fixup", + .mode = 0555, + .child = unaligned_subtable + }, + {} +}; +#endif + +static struct ctl_path tile_path[] = { + { .procname = "tile" }, + { } +}; + +static int __init proc_sys_tile_init(void) +{ +#ifndef __tilegx__ /* FIXME: GX: no support for unaligned access yet */ + register_sysctl_paths(tile_path, unaligned_table); +#endif + return 0; +} + +arch_initcall(proc_sys_tile_init); diff --git a/arch/tile/kernel/sysfs.c b/arch/tile/kernel/sysfs.c new file mode 100644 index 000000000000..b671a86f4515 --- /dev/null +++ b/arch/tile/kernel/sysfs.c @@ -0,0 +1,185 @@ +/* + * Copyright 2011 Tilera Corporation. All Rights Reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation, version 2. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + * + * /sys entry support. + */ + +#include +#include +#include +#include +#include + +/* Return a string queried from the hypervisor, truncated to page size. */ +static ssize_t get_hv_confstr(char *page, int query) +{ + ssize_t n = hv_confstr(query, (unsigned long)page, PAGE_SIZE - 1); + n = n < 0 ? 0 : min(n, (ssize_t)PAGE_SIZE - 1) - 1; + if (n) + page[n++] = '\n'; + page[n] = '\0'; + return n; +} + +static ssize_t chip_width_show(struct sysdev_class *dev, + struct sysdev_class_attribute *attr, + char *page) +{ + return sprintf(page, "%u\n", smp_width); +} +static SYSDEV_CLASS_ATTR(chip_width, 0444, chip_width_show, NULL); + +static ssize_t chip_height_show(struct sysdev_class *dev, + struct sysdev_class_attribute *attr, + char *page) +{ + return sprintf(page, "%u\n", smp_height); +} +static SYSDEV_CLASS_ATTR(chip_height, 0444, chip_height_show, NULL); + +static ssize_t chip_serial_show(struct sysdev_class *dev, + struct sysdev_class_attribute *attr, + char *page) +{ + return get_hv_confstr(page, HV_CONFSTR_CHIP_SERIAL_NUM); +} +static SYSDEV_CLASS_ATTR(chip_serial, 0444, chip_serial_show, NULL); + +static ssize_t chip_revision_show(struct sysdev_class *dev, + struct sysdev_class_attribute *attr, + char *page) +{ + return get_hv_confstr(page, HV_CONFSTR_CHIP_REV); +} +static SYSDEV_CLASS_ATTR(chip_revision, 0444, chip_revision_show, NULL); + + +static ssize_t type_show(struct sysdev_class *dev, + struct sysdev_class_attribute *attr, + char *page) +{ + return sprintf(page, "tilera\n"); +} +static SYSDEV_CLASS_ATTR(type, 0444, type_show, NULL); + +#define HV_CONF_ATTR(name, conf) \ + static ssize_t name ## _show(struct sysdev_class *dev, \ + struct sysdev_class_attribute *attr, \ + char *page) \ + { \ + return get_hv_confstr(page, conf); \ + } \ + static SYSDEV_CLASS_ATTR(name, 0444, name ## _show, NULL); + +HV_CONF_ATTR(version, HV_CONFSTR_HV_SW_VER) +HV_CONF_ATTR(config_version, HV_CONFSTR_HV_CONFIG_VER) + +HV_CONF_ATTR(board_part, HV_CONFSTR_BOARD_PART_NUM) +HV_CONF_ATTR(board_serial, HV_CONFSTR_BOARD_SERIAL_NUM) +HV_CONF_ATTR(board_revision, HV_CONFSTR_BOARD_REV) +HV_CONF_ATTR(board_description, HV_CONFSTR_BOARD_DESC) +HV_CONF_ATTR(mezz_part, HV_CONFSTR_MEZZ_PART_NUM) +HV_CONF_ATTR(mezz_serial, HV_CONFSTR_MEZZ_SERIAL_NUM) +HV_CONF_ATTR(mezz_revision, HV_CONFSTR_MEZZ_REV) +HV_CONF_ATTR(mezz_description, HV_CONFSTR_MEZZ_DESC) +HV_CONF_ATTR(switch_control, HV_CONFSTR_SWITCH_CONTROL) + +static struct attribute *board_attrs[] = { + &attr_board_part.attr, + &attr_board_serial.attr, + &attr_board_revision.attr, + &attr_board_description.attr, + &attr_mezz_part.attr, + &attr_mezz_serial.attr, + &attr_mezz_revision.attr, + &attr_mezz_description.attr, + &attr_switch_control.attr, + NULL +}; + +static struct attribute_group board_attr_group = { + .name = "board", + .attrs = board_attrs, +}; + + +static struct bin_attribute hvconfig_bin; + +static ssize_t +hvconfig_bin_read(struct file *filp, struct kobject *kobj, + struct bin_attribute *bin_attr, + char *buf, loff_t off, size_t count) +{ + static size_t size; + + /* Lazily learn the true size (minus the trailing NUL). */ + if (size == 0) + size = hv_confstr(HV_CONFSTR_HV_CONFIG, 0, 0) - 1; + + /* Check and adjust input parameters. */ + if (off > size) + return -EINVAL; + if (count > size - off) + count = size - off; + + if (count) { + /* Get a copy of the hvc and copy out the relevant portion. */ + char *hvc; + + size = off + count; + hvc = kmalloc(size, GFP_KERNEL); + if (hvc == NULL) + return -ENOMEM; + hv_confstr(HV_CONFSTR_HV_CONFIG, (unsigned long)hvc, size); + memcpy(buf, hvc + off, count); + kfree(hvc); + } + + return count; +} + +static int __init create_sysfs_entries(void) +{ + struct sysdev_class *cls = &cpu_sysdev_class; + int err = 0; + +#define create_cpu_attr(name) \ + if (!err) \ + err = sysfs_create_file(&cls->kset.kobj, &attr_##name.attr); + create_cpu_attr(chip_width); + create_cpu_attr(chip_height); + create_cpu_attr(chip_serial); + create_cpu_attr(chip_revision); + +#define create_hv_attr(name) \ + if (!err) \ + err = sysfs_create_file(hypervisor_kobj, &attr_##name.attr); + create_hv_attr(type); + create_hv_attr(version); + create_hv_attr(config_version); + + if (!err) + err = sysfs_create_group(hypervisor_kobj, &board_attr_group); + + if (!err) { + sysfs_bin_attr_init(&hvconfig_bin); + hvconfig_bin.attr.name = "hvconfig"; + hvconfig_bin.attr.mode = S_IRUGO; + hvconfig_bin.read = hvconfig_bin_read; + hvconfig_bin.size = PAGE_SIZE; + err = sysfs_create_bin_file(hypervisor_kobj, &hvconfig_bin); + } + + return err; +} +subsys_initcall(create_sysfs_entries); diff --git a/fs/proc/base.c b/fs/proc/base.c index dfa532730e55..3ad615fb8656 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -83,6 +83,9 @@ #include #include #include +#ifdef CONFIG_HARDWALL +#include +#endif #include "internal.h" /* NOTE: @@ -2894,6 +2897,9 @@ static const struct pid_entry tgid_base_stuff[] = { #ifdef CONFIG_TASK_IO_ACCOUNTING INF("io", S_IRUGO, proc_tgid_io_accounting), #endif +#ifdef CONFIG_HARDWALL + INF("hardwall", S_IRUGO, proc_pid_hardwall), +#endif }; static int proc_tgid_base_readdir(struct file * filp, @@ -3232,6 +3238,9 @@ static const struct pid_entry tid_base_stuff[] = { #ifdef CONFIG_TASK_IO_ACCOUNTING INF("io", S_IRUGO, proc_tid_io_accounting), #endif +#ifdef CONFIG_HARDWALL + INF("hardwall", S_IRUGO, proc_pid_hardwall), +#endif }; static int proc_tid_base_readdir(struct file * filp, -- cgit v1.2.3 From cf1279111686d9742cbc4145bc9d526c83f59fea Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sat, 18 Jun 2011 20:35:23 -0400 Subject: proc_fd_permission() is doesn't need to bail out in RCU mode nothing blocking except generic_permission() Signed-off-by: Al Viro --- fs/proc/base.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'fs/proc/base.c') diff --git a/fs/proc/base.c b/fs/proc/base.c index 14def991d9dd..8a84210ca080 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2169,11 +2169,7 @@ static const struct file_operations proc_fd_operations = { */ static int proc_fd_permission(struct inode *inode, int mask, unsigned int flags) { - int rv; - - if (flags & IPERM_FLAG_RCU) - return -ECHILD; - rv = generic_permission(inode, mask, flags, NULL); + int rv = generic_permission(inode, mask, flags, NULL); if (rv == 0) return 0; if (task_pid(current) == proc_pid(inode)) -- cgit v1.2.3