989 lines · 24.1 KB · C
RawDownload
// SPDX-License-Identifier: GPL-2.0-only/* * Copyright (C) 2006-2010 Red Hat, Inc.  All rights reserved. */ #include <linux/miscdevice.h>#include <linux/init.h>#include <linux/wait.h>#include <linux/file.h>#include <linux/fs.h>#include <linux/poll.h>#include <linux/signal.h>#include <linux/spinlock.h>#include <linux/dlm.h>#include <linux/dlm_device.h>#include <linux/slab.h>#include <linux/sched/signal.h> #include <trace/events/dlm.h> #include "dlm_internal.h"#include "lockspace.h"#include "lock.h"#include "lvb_table.h"#include "user.h"#include "ast.h"#include "config.h"#include "memory.h" static const char name_prefix[] = "dlm";static const struct file_operations device_fops;static atomic_t dlm_monitor_opened;static int dlm_monitor_unused = 1; #ifdef CONFIG_COMPAT struct dlm_lock_params32 {	__u8 mode;	__u8 namelen;	__u16 unused;	__u32 flags;	__u32 lkid;	__u32 parent;	__u64 xid;	__u64 timeout;	__u32 castparam;	__u32 castaddr;	__u32 bastparam;	__u32 bastaddr;	__u32 lksb;	char lvb[DLM_USER_LVB_LEN];	char name[];}; struct dlm_write_request32 {	__u32 version[3];	__u8 cmd;	__u8 is64bit;	__u8 unused[2]; 	union  {		struct dlm_lock_params32 lock;		struct dlm_lspace_params lspace;		struct dlm_purge_params purge;	} i;}; struct dlm_lksb32 {	__u32 sb_status;	__u32 sb_lkid;	__u8 sb_flags;	__u32 sb_lvbptr;}; struct dlm_lock_result32 {	__u32 version[3];	__u32 length;	__u32 user_astaddr;	__u32 user_astparam;	__u32 user_lksb;	struct dlm_lksb32 lksb;	__u8 bast_mode;	__u8 unused[3];	/* Offsets may be zero if no data is present */	__u32 lvb_offset;}; static void compat_input(struct dlm_write_request *kb,			 struct dlm_write_request32 *kb32,			 int namelen){	kb->version[0] = kb32->version[0];	kb->version[1] = kb32->version[1];	kb->version[2] = kb32->version[2]; 	kb->cmd = kb32->cmd;	kb->is64bit = kb32->is64bit;	if (kb->cmd == DLM_USER_CREATE_LOCKSPACE ||	    kb->cmd == DLM_USER_REMOVE_LOCKSPACE) {		kb->i.lspace.flags = kb32->i.lspace.flags;		kb->i.lspace.minor = kb32->i.lspace.minor;		memcpy(kb->i.lspace.name, kb32->i.lspace.name, namelen);	} else if (kb->cmd == DLM_USER_PURGE) {		kb->i.purge.nodeid = kb32->i.purge.nodeid;		kb->i.purge.pid = kb32->i.purge.pid;	} else {		kb->i.lock.mode = kb32->i.lock.mode;		kb->i.lock.namelen = kb32->i.lock.namelen;		kb->i.lock.flags = kb32->i.lock.flags;		kb->i.lock.lkid = kb32->i.lock.lkid;		kb->i.lock.parent = kb32->i.lock.parent;		kb->i.lock.xid = kb32->i.lock.xid;		kb->i.lock.timeout = kb32->i.lock.timeout;		kb->i.lock.castparam = (__user void *)(long)kb32->i.lock.castparam;		kb->i.lock.castaddr = (__user void *)(long)kb32->i.lock.castaddr;		kb->i.lock.bastparam = (__user void *)(long)kb32->i.lock.bastparam;		kb->i.lock.bastaddr = (__user void *)(long)kb32->i.lock.bastaddr;		kb->i.lock.lksb = (__user void *)(long)kb32->i.lock.lksb;		memcpy(kb->i.lock.lvb, kb32->i.lock.lvb, DLM_USER_LVB_LEN);		memcpy(kb->i.lock.name, kb32->i.lock.name, namelen);	}} static void compat_output(struct dlm_lock_result *res,			  struct dlm_lock_result32 *res32){	memset(res32, 0, sizeof(*res32)); 	res32->version[0] = res->version[0];	res32->version[1] = res->version[1];	res32->version[2] = res->version[2]; 	res32->user_astaddr = (__u32)(__force long)res->user_astaddr;	res32->user_astparam = (__u32)(__force long)res->user_astparam;	res32->user_lksb = (__u32)(__force long)res->user_lksb;	res32->bast_mode = res->bast_mode; 	res32->lvb_offset = res->lvb_offset;	res32->length = res->length; 	res32->lksb.sb_status = res->lksb.sb_status;	res32->lksb.sb_flags = res->lksb.sb_flags;	res32->lksb.sb_lkid = res->lksb.sb_lkid;	res32->lksb.sb_lvbptr = (__u32)(long)res->lksb.sb_lvbptr;}#endif /* Figure out if this lock is at the end of its life and no longer   available for the application to use.  The lkb still exists until   the final ast is read.  A lock becomes EOL in three situations:     1. a noqueue request fails with EAGAIN     2. an unlock completes with EUNLOCK     3. a cancel of a waiting request completes with ECANCEL/EDEADLK   An EOL lock needs to be removed from the process's list of locks.   And we can't allow any new operation on an EOL lock.  This is   not related to the lifetime of the lkb struct which is managed   entirely by refcount. */ static int lkb_is_endoflife(int mode, int status){	switch (status) {	case -DLM_EUNLOCK:		return 1;	case -DLM_ECANCEL:	case -ETIMEDOUT:	case -EDEADLK:	case -EAGAIN:		if (mode == DLM_LOCK_IV)			return 1;		break;	}	return 0;} /* we could possibly check if the cancel of an orphan has resulted in the lkb   being removed and then remove that lkb from the orphans list and free it */ void dlm_user_add_ast(struct dlm_lkb *lkb, uint32_t flags, int mode,		      int status, uint32_t sbflags){	struct dlm_ls *ls;	struct dlm_user_args *ua;	struct dlm_user_proc *proc;	struct dlm_callback *cb;	int rv, copy_lvb; 	if (test_bit(DLM_DFL_ORPHAN_BIT, &lkb->lkb_dflags) ||	    test_bit(DLM_IFL_DEAD_BIT, &lkb->lkb_iflags))		return; 	ls = lkb->lkb_resource->res_ls;	spin_lock_bh(&ls->ls_clear_proc_locks); 	/* If ORPHAN/DEAD flag is set, it means the process is dead so an ast	   can't be delivered.  For ORPHAN's, dlm_clear_proc_locks() freed	   lkb->ua so we can't try to use it.  This second check is necessary	   for cases where a completion ast is received for an operation that	   began before clear_proc_locks did its cancel/unlock. */ 	if (test_bit(DLM_DFL_ORPHAN_BIT, &lkb->lkb_dflags) ||	    test_bit(DLM_IFL_DEAD_BIT, &lkb->lkb_iflags))		goto out; 	DLM_ASSERT(lkb->lkb_ua, dlm_print_lkb(lkb););	ua = lkb->lkb_ua;	proc = ua->proc; 	if ((flags & DLM_CB_BAST) && ua->bastaddr == NULL)		goto out; 	if ((flags & DLM_CB_CAST) && lkb_is_endoflife(mode, status))		set_bit(DLM_IFL_ENDOFLIFE_BIT, &lkb->lkb_iflags); 	spin_lock_bh(&proc->asts_spin); 	if (!dlm_may_skip_callback(lkb, flags, mode, status, sbflags,				   &copy_lvb)) {		rv = dlm_get_cb(lkb, flags, mode, status, sbflags, &cb);		if (!rv) {			cb->copy_lvb = copy_lvb;			cb->ua = *ua;			cb->lkb_lksb = &cb->ua.lksb;			if (copy_lvb) {				memcpy(cb->lvbptr, ua->lksb.sb_lvbptr,				       DLM_USER_LVB_LEN);				cb->lkb_lksb->sb_lvbptr = cb->lvbptr;			} 			list_add_tail(&cb->list, &proc->asts);			wake_up_interruptible(&proc->wait);		}	}	spin_unlock_bh(&proc->asts_spin); 	if (test_bit(DLM_IFL_ENDOFLIFE_BIT, &lkb->lkb_iflags)) {		/* N.B. spin_lock locks_spin, not asts_spin */		spin_lock_bh(&proc->locks_spin);		if (!list_empty(&lkb->lkb_ownqueue)) {			list_del_init(&lkb->lkb_ownqueue);			dlm_put_lkb(lkb);		}		spin_unlock_bh(&proc->locks_spin);	} out:	spin_unlock_bh(&ls->ls_clear_proc_locks);} static int device_user_lock(struct dlm_user_proc *proc,			    struct dlm_lock_params *params){	struct dlm_ls *ls;	struct dlm_user_args *ua;	uint32_t lkid;	int error = -ENOMEM; 	ls = dlm_find_lockspace_local(proc->lockspace);	if (!ls)		return -ENOENT; 	if (!params->castaddr || !params->lksb) {		error = -EINVAL;		goto out;	} 	ua = kzalloc_obj(struct dlm_user_args, GFP_NOFS);	if (!ua)		goto out;	ua->proc = proc;	ua->user_lksb = params->lksb;	ua->castparam = params->castparam;	ua->castaddr = params->castaddr;	ua->bastparam = params->bastparam;	ua->bastaddr = params->bastaddr;	ua->xid = params->xid; 	if (params->flags & DLM_LKF_CONVERT) {		error = dlm_user_convert(ls, ua,					 params->mode, params->flags,					 params->lkid, params->lvb);	} else if (params->flags & DLM_LKF_ORPHAN) {		error = dlm_user_adopt_orphan(ls, ua,					 params->mode, params->flags,					 params->name, params->namelen,					 &lkid);		if (!error)			error = lkid;	} else {		error = dlm_user_request(ls, ua,					 params->mode, params->flags,					 params->name, params->namelen);		if (!error)			error = ua->lksb.sb_lkid;	} out:	dlm_put_lockspace(ls);	return error;} static int device_user_unlock(struct dlm_user_proc *proc,			      struct dlm_lock_params *params){	struct dlm_ls *ls;	struct dlm_user_args *ua;	int error = -ENOMEM; 	ls = dlm_find_lockspace_local(proc->lockspace);	if (!ls)		return -ENOENT; 	ua = kzalloc_obj(struct dlm_user_args, GFP_NOFS);	if (!ua)		goto out;	ua->proc = proc;	ua->user_lksb = params->lksb;	ua->castparam = params->castparam;	ua->castaddr = params->castaddr; 	if (params->flags & DLM_LKF_CANCEL)		error = dlm_user_cancel(ls, ua, params->flags, params->lkid);	else		error = dlm_user_unlock(ls, ua, params->flags, params->lkid,					params->lvb); out:	dlm_put_lockspace(ls);	return error;} static int device_user_deadlock(struct dlm_user_proc *proc,				struct dlm_lock_params *params){	struct dlm_ls *ls;	int error; 	ls = dlm_find_lockspace_local(proc->lockspace);	if (!ls)		return -ENOENT; 	error = dlm_user_deadlock(ls, params->flags, params->lkid); 	dlm_put_lockspace(ls);	return error;} static int dlm_device_register(struct dlm_ls *ls, char *name){	int error, len; 	/* The device is already registered.  This happens when the	   lockspace is created multiple times from userspace. */	if (ls->ls_device.name)		return 0; 	error = -ENOMEM;	len = strlen(name) + strlen(name_prefix) + 2;	ls->ls_device.name = kzalloc(len, GFP_NOFS);	if (!ls->ls_device.name)		goto fail; 	snprintf((char *)ls->ls_device.name, len, "%s_%s", name_prefix,		 name);	ls->ls_device.fops = &device_fops;	ls->ls_device.minor = MISC_DYNAMIC_MINOR; 	error = misc_register(&ls->ls_device);	if (error) {		kfree(ls->ls_device.name);		/* this has to be set to NULL		 * to avoid a double-free in dlm_device_deregister		 */		ls->ls_device.name = NULL;	}fail:	return error;} int dlm_device_deregister(struct dlm_ls *ls){	/* The device is not registered.  This happens when the lockspace	   was never used from userspace, or when device_create_lockspace()	   calls dlm_release_lockspace() after the register fails. */	if (!ls->ls_device.name)		return 0; 	misc_deregister(&ls->ls_device);	kfree(ls->ls_device.name);	return 0;} static int device_user_purge(struct dlm_user_proc *proc,			     struct dlm_purge_params *params){	struct dlm_ls *ls;	int error; 	ls = dlm_find_lockspace_local(proc->lockspace);	if (!ls)		return -ENOENT; 	error = dlm_user_purge(ls, proc, params->nodeid, params->pid); 	dlm_put_lockspace(ls);	return error;} static int device_create_lockspace(struct dlm_lspace_params *params){	dlm_lockspace_t *lockspace;	struct dlm_ls *ls;	int error; 	if (!capable(CAP_SYS_ADMIN))		return -EPERM; 	error = dlm_new_user_lockspace(params->name, dlm_config.ci_cluster_name,				       params->flags, DLM_USER_LVB_LEN, NULL,				       NULL, NULL, &lockspace);	if (error)		return error; 	ls = dlm_find_lockspace_local(lockspace);	if (!ls)		return -ENOENT; 	error = dlm_device_register(ls, params->name);	dlm_put_lockspace(ls); 	if (error)		dlm_release_lockspace(lockspace, DLM_RELEASE_NO_LOCKS);	else		error = ls->ls_device.minor; 	return error;} static int device_remove_lockspace(struct dlm_lspace_params *params){	dlm_lockspace_t *lockspace;	struct dlm_ls *ls;	int error, force = DLM_RELEASE_NO_LOCKS; 	if (!capable(CAP_SYS_ADMIN))		return -EPERM; 	ls = dlm_find_lockspace_device(params->minor);	if (!ls)		return -ENOENT; 	if (params->flags & DLM_USER_LSFLG_FORCEFREE)		force = DLM_RELEASE_NORMAL; 	lockspace = ls;	dlm_put_lockspace(ls); 	/* The final dlm_release_lockspace waits for references to go to	   zero, so all processes will need to close their device for the	   ls before the release will proceed.  release also calls the	   device_deregister above.  Converting a positive return value	   from release to zero means that userspace won't know when its	   release was the final one, but it shouldn't need to know. */ 	error = dlm_release_lockspace(lockspace, force);	if (error > 0)		error = 0;	return error;} /* Check the user's version matches ours */static int check_version(struct dlm_write_request *req){	if (req->version[0] != DLM_DEVICE_VERSION_MAJOR ||	    (req->version[0] == DLM_DEVICE_VERSION_MAJOR &&	     req->version[1] > DLM_DEVICE_VERSION_MINOR)) { 		printk(KERN_DEBUG "dlm: process %s (%d) version mismatch "		       "user (%d.%d.%d) kernel (%d.%d.%d)\n",		       current->comm,		       task_pid_nr(current),		       req->version[0],		       req->version[1],		       req->version[2],		       DLM_DEVICE_VERSION_MAJOR,		       DLM_DEVICE_VERSION_MINOR,		       DLM_DEVICE_VERSION_PATCH);		return -EINVAL;	}	return 0;} /* * device_write * *   device_user_lock *     dlm_user_request -> request_lock *     dlm_user_convert -> convert_lock * *   device_user_unlock *     dlm_user_unlock -> unlock_lock *     dlm_user_cancel -> cancel_lock * *   device_create_lockspace

Lines 1–500 of 989.