litmus-rt.git - The LITMUS^RT kernel.

diff options

-rw-r--r--

2 files changed, 1 insertions, 12 deletions

 5.1 force_empty
   memory.force_empty interface is provided to make cgroup's memory usage empty.
-  You can use this interface only when the cgroup has no tasks.
   When writing anything to this
   # echo 0 > memory.force_empty
-  Almost all pages tracked by this memory cgroup will be unmapped and freed.
+  the cgroup will be reclaimed and as many pages reclaimed as possible.
-  Some pages cannot be freed because they are locked or in-use. Such pages are
-  moved to parent (if use_hierarchy==1) or root (if use_hierarchy==0) and this
-  cgroup will be empty.
   The typical use case for this interface is before calling rmdir().
   Because rmdir() moves all pages to parent, some out-of-use page caches can be
 static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
 {
         int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
-        struct cgroup *cgrp = memcg->css.cgroup;
-        /* returns EBUSY if there is a task or if we come here twice. */
-        if (cgroup_has_tasks(cgrp) || !list_empty(&cgrp->children))
-                return -EBUSY;
         /* we call try-to-free pages for make this cgroup empty */
         lru_add_drain_all();
                 }
         }
-        lru_add_drain();
-        mem_cgroup_reparent_charges(memcg);
         return 0;
 }

/* * History: * Started: Aug 9 by Lawrence Foard (entropy@world.std.com), * to allow user process control of SCSI devices. * Development Sponsored by Killy Corp. NY NY * * Original driver (sg.c): * Copyright (C) 1992 Lawrence Foard * Version 2 and 3 extensions to driver: * Copyright (C) 1998 - 2005 Douglas Gilbert * * Modified 19-JAN-1998 Richard Gooch <rgooch@atnf.csiro.au> Devfs support * * 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; either version 2, or (at your option) * any later version. * */ static int sg_version_num = 30533; /* 2 digits for each component */ #define SG_VERSION_STR "3.5.33" /* * D. P. Gilbert (dgilbert@interlog.com, dougg@triode.net.au), notes: * - scsi logging is available via SCSI_LOG_TIMEOUT macros. First * the kernel/module needs to be built with CONFIG_SCSI_LOGGING * (otherwise the macros compile to empty statements). * */ #include <linux/module.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/errno.h> #include <linux/mtio.h> #include <linux/ioctl.h> #include <linux/fcntl.h> #include <linux/init.h> #include <linux/poll.h> #include <linux/smp_lock.h> #include <linux/moduleparam.h> #include <linux/cdev.h> #include <linux/seq_file.h> #include <linux/blkdev.h> #include <linux/delay.h> #include <linux/scatterlist.h> #include "scsi.h" #include <scsi/scsi_dbg.h> #include <scsi/scsi_host.h> #include <scsi/scsi_driver.h> #include <scsi/scsi_ioctl.h> #include <scsi/sg.h> #include "scsi_logging.h" #ifdef CONFIG_SCSI_PROC_FS #include <linux/proc_fs.h> static char *sg_version_date = "20050908"; static int sg_proc_init(void); static void sg_proc_cleanup(void); #endif #define SG_ALLOW_DIO_DEF 0 #define SG_ALLOW_DIO_CODE /* compile out by commenting this define */ #define SG_MAX_DEVS 32768 /* * Suppose you want to calculate the formula muldiv(x,m,d)=int(x * m / d) * Then when using 32 bit integers x * m may overflow during the calculation. * Replacing muldiv(x) by muldiv(x)=((x % d) * m) / d + int(x / d) * m * calculates the same, but prevents the overflow when both m and d * are "small" numbers (like HZ and USER_HZ). * Of course an overflow is inavoidable if the result of muldiv doesn't fit * in 32 bits. */ #define MULDIV(X,MUL,DIV) ((((X % DIV) * MUL) / DIV) + ((X / DIV) * MUL)) #define SG_DEFAULT_TIMEOUT MULDIV(SG_DEFAULT_TIMEOUT_USER, HZ, USER_HZ) int sg_big_buff = SG_DEF_RESERVED_SIZE; /* N.B. This variable is readable and writeable via /proc/scsi/sg/def_reserved_size . Each time sg_open() is called a buffer of this size (or less if there is not enough memory) will be reserved for use by this file descriptor. [Deprecated usage: this variable is also readable via /proc/sys/kernel/sg-big-buff if the sg driver is built into the kernel (i.e. it is not a module).] */ static int def_reserved_size = -1; /* picks up init parameter */ static int sg_allow_dio = SG_ALLOW_DIO_DEF; #define SG_SECTOR_SZ 512 #define SG_SECTOR_MSK (SG_SECTOR_SZ - 1) #define SG_DEV_ARR_LUMP 32 /* amount to over allocate sg_dev_arr by */ static int sg_add(struct class_device *, struct class_interface *); static void sg_remove(struct class_device *, struct class_interface *); static DEFINE_RWLOCK(sg_dev_arr_lock); /* Also used to lock file descriptor list for device */ static struct class_interface sg_interface = { .add = sg_add, .remove = sg_remove, }; typedef struct sg_scatter_hold { /* holding area for scsi scatter gather info */ unsigned short k_use_sg; /* Count of kernel scatter-gather pieces */ unsigned short sglist_len; /* size of malloc'd scatter-gather list ++ */ unsigned bufflen; /* Size of (aggregate) data buffer */ unsigned b_malloc_len; /* actual len malloc'ed in buffer */ struct scatterlist *buffer;/* scatter list */ char dio_in_use; /* 0->indirect IO (or mmap), 1->dio */ unsigned char cmd_opcode; /* first byte of command */ } Sg_scatter_hold; struct sg_device; /* forward declarations */ struct sg_fd; typedef struct sg_request { /* SG_MAX_QUEUE requests outstanding per file */ struct sg_request *nextrp; /* NULL -> tail request (slist) */ struct sg_fd *parentfp; /* NULL -> not in use */ Sg_scatter_hold data; /* hold buffer, perhaps scatter list */ sg_io_hdr_t header; /* scsi command+info, see <scsi/sg.h> */ unsigned char sense_b[SCSI_SENSE_BUFFERSIZE]; char res_used; /* 1 -> using reserve buffer, 0 -> not ... */ char orphan; /* 1 -> drop on sight, 0 -> normal */ char sg_io_owned; /* 1 -> packet belongs to SG_IO */ volatile char done; /* 0->before bh, 1->before read, 2->read */ } Sg_request; typedef struct sg_fd { /* holds the state of a file descriptor */ struct sg_fd *nextfp; /* NULL when last opened fd on this device */ struct sg_device *parentdp; /* owning device */ wait_queue_head_t read_wait; /* queue read until command done */ rwlock_t rq_list_lock; /* protect access to list in req_arr */ int timeout; /* defaults to SG_DEFAULT_TIMEOUT */ int timeout_user; /* defaults to SG_DEFAULT_TIMEOUT_USER */ Sg_scatter_hold reserve; /* buffer held for this file descriptor */ unsigned save_scat_len; /* original length of trunc. scat. element */ Sg_request *headrp; /* head of request slist, NULL->empty */ struct fasync_struct *async_qp; /* used by asynchronous notification */ Sg_request req_arr[SG_MAX_QUEUE]; /* used as singly-linked list */ char low_dma; /* as in parent but possibly overridden to 1 */ char force_packid; /* 1 -> pack_id input to read(), 0 -> ignored */ volatile char closed; /* 1 -> fd closed but request(s) outstanding */ char cmd_q; /* 1 -> allow command queuing, 0 -> don't */ char next_cmd_len; /* 0 -> automatic (def), >0 -> use on next write() */ char keep_orphan; /* 0 -> drop orphan (def), 1 -> keep for read() */ char mmap_called; /* 0 -> mmap() never called on this fd */ } Sg_fd; typedef struct sg_device { /* holds the state of each scsi generic device */ struct scsi_device *device; wait_queue_head_t o_excl_wait; /* queue open() when O_EXCL in use */ int sg_tablesize; /* adapter's max scatter-gather table size */ Sg_fd *headfp; /* first open fd belonging to this device */ volatile char detached; /* 0->attached, 1->detached pending removal */ volatile char exclude; /* opened for exclusive access */ char sgdebug; /* 0->off, 1->sense, 9->dump dev, 10-> all devs */ struct gendisk *disk; struct cdev * cdev; /* char_dev [sysfs: /sys/cdev/major/sg<n>] */ } Sg_device; static int sg_fasync(int fd, struct file *filp, int mode); /* tasklet or soft irq callback */ static void sg_cmd_done(void *data, char *sense, int result, int resid); static int sg_start_req(Sg_request * srp); static void sg_finish_rem_req(Sg_request * srp); static int sg_build_indirect(Sg_scatter_hold * schp, Sg_fd * sfp, int buff_size); static int sg_build_sgat(Sg_scatter_hold * schp, const Sg_fd * sfp, int tablesize); static ssize_t sg_new_read(Sg_fd * sfp, char __user *buf, size_t count, Sg_request * srp); static ssize_t sg_new_write(Sg_fd * sfp, const char __user *buf, size_t count, int blocking, int read_only, Sg_request ** o_srp); static int sg_common_write(Sg_fd * sfp, Sg_request * srp, unsigned char *cmnd, int timeout, int blocking); static int sg_u_iovec(sg_io_hdr_t * hp, int sg_num, int ind, int wr_xf, int *countp, unsigned char __user **up); static int sg_write_xfer(Sg_request * srp); static int sg_read_xfer(Sg_request * srp); static int sg_read_oxfer(Sg_request * srp, char __user *outp, int num_read_xfer); static void sg_remove_scat(Sg_scatter_hold * schp); static void sg_build_reserve(Sg_fd * sfp, int req_size); static void sg_link_reserve(Sg_fd * sfp, Sg_request * srp, int size); static void sg_unlink_reserve(Sg_fd * sfp, Sg_request * srp); static struct page *sg_page_malloc(int rqSz, int lowDma, int *retSzp); static void sg_page_free(struct page *page, int size); static Sg_fd *sg_add_sfp(Sg_device * sdp, int dev); static int sg_remove_sfp(Sg_device * sdp, Sg_fd * sfp); static void __sg_remove_sfp(Sg_device * sdp, Sg_fd * sfp); static Sg_request *sg_get_rq_mark(Sg_fd * sfp, int pack_id); static Sg_request *sg_add_request(Sg_fd * sfp); static int sg_remove_request(Sg_fd * sfp, Sg_request * srp); static int sg_res_in_use(Sg_fd * sfp); static int sg_allow_access(unsigned char opcode, char dev_type); static int sg_build_direct(Sg_request * srp, Sg_fd * sfp, int dxfer_len); static Sg_device *sg_get_dev(int dev); #ifdef CONFIG_SCSI_PROC_FS static int sg_last_dev(void); #endif static Sg_device **sg_dev_arr = NULL; static int sg_dev_max; static int sg_nr_dev; #define SZ_SG_HEADER sizeof(struct sg_header) #define SZ_SG_IO_HDR sizeof(sg_io_hdr_t) #define SZ_SG_IOVEC sizeof(sg_iovec_t) #define SZ_SG_REQ_INFO sizeof(sg_req_info_t) static int sg_open(struct inode *inode, struct file *filp) { int dev = iminor(inode); int flags = filp->f_flags; struct request_queue *q; Sg_device *sdp; Sg_fd *sfp; int res; int retval; nonseekable_open(inode, filp); SCSI_LOG_TIMEOUT(3, printk("sg_open: dev=%d, flags=0x%x\n", dev, flags)); sdp = sg_get_dev(dev); if ((!sdp) || (!sdp->device)) return -ENXIO; if (sdp->detached) return -ENODEV; /* This driver's module count bumped by fops_get in <linux/fs.h> */ /* Prevent the device driver from vanishing while we sleep */ retval = scsi_device_get(sdp->device); if (retval) return retval; if (!((flags & O_NONBLOCK) || scsi_block_when_processing_errors(sdp->device))) { retval = -ENXIO; /* we are in error recovery for this device */ goto error_out; } if (flags & O_EXCL) { if (O_RDONLY == (flags & O_ACCMODE)) { retval = -EPERM; /* Can't lock it with read only access */ goto error_out; } if (sdp->headfp && (flags & O_NONBLOCK)) { retval = -EBUSY; goto error_out; } res = 0; __wait_event_interruptible(sdp->o_excl_wait, ((sdp->headfp || sdp->exclude) ? 0 : (sdp->exclude = 1)), res); if (res) { retval = res; /* -ERESTARTSYS because signal hit process */ goto error_out; } } else if (sdp->exclude) { /* some other fd has an exclusive lock on dev */ if (flags & O_NONBLOCK) { retval = -EBUSY; goto error_out; } res = 0; __wait_event_interruptible(sdp->o_excl_wait, (!sdp->exclude), res); if (res) { retval = res; /* -ERESTARTSYS because signal hit process */ goto error_out; } } if (sdp->detached) { retval = -ENODEV; goto error_out; } if (!sdp->headfp) { /* no existing opens on this device */ sdp->sgdebug = 0; q = sdp->device->request_queue; sdp->sg_tablesize = min(q->max_hw_segments, q->max_phys_segments); } if ((sfp = sg_add_sfp(sdp, dev))) filp->private_data = sfp; else { if (flags & O_EXCL) sdp->exclude = 0; /* undo if error */ retval = -ENOMEM; goto error_out; } return 0; error_out: scsi_device_put(sdp->device); return retval; } /* Following function was formerly called 'sg_close' */ static int sg_release(struct inode *inode, struct file *filp) { Sg_device *sdp; Sg_fd *sfp; if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp))) return -ENXIO; SCSI_LOG_TIMEOUT(3, printk("sg_release: %s\n", sdp->disk->disk_name)); sg_fasync(-1, filp, 0); /* remove filp from async notification list */ if (0 == sg_remove_sfp(sdp, sfp)) { /* Returns 1 when sdp gone */ if (!sdp->detached) { scsi_device_put(sdp->device); } sdp->exclude = 0; wake_up_interruptible(&sdp->o_excl_wait); } return 0; } static ssize_t sg_read(struct file *filp, char __user *buf, size_t count, loff_t * ppos) { Sg_device *sdp; Sg_fd *sfp; Sg_request *srp; int req_pack_id = -1; sg_io_hdr_t *hp; struct sg_header *old_hdr = NULL; int retval = 0; if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp))) return -ENXIO; SCSI_LOG_TIMEOUT(3, printk("sg_read: %s, count=%d\n", sdp->disk->disk_name, (int) count)); if (!access_ok(VERIFY_WRITE, buf, count)) return -EFAULT; if (sfp->force_packid && (count >= SZ_SG_HEADER)) { old_hdr = kmalloc(SZ_SG_HEADER, GFP_KERNEL); if (!old_hdr) return -ENOMEM; if (__copy_from_user(old_hdr, buf, SZ_SG_HEADER)) { retval = -EFAULT; goto free_old_hdr; } if (old_hdr->reply_len < 0) { if (count >= SZ_SG_IO_HDR) { sg_io_hdr_t *new_hdr; new_hdr = kmalloc(SZ_SG_IO_HDR, GFP_KERNEL); if (!new_hdr) { retval = -ENOMEM; goto free_old_hdr; } retval =__copy_from_user (new_hdr, buf, SZ_SG_IO_HDR); req_pack_id = new_hdr->pack_id; kfree(new_hdr); if (retval) { retval = -EFAULT; goto free_old_hdr; } } } else req_pack_id = old_hdr->pack_id; } srp = sg_get_rq_mark(sfp, req_pack_id); if (!srp) { /* now wait on packet to arrive */ if (sdp->detached) { retval = -ENODEV; goto free_old_hdr; } if (filp->f_flags & O_NONBLOCK) { retval = -EAGAIN; goto free_old_hdr; } while (1) { retval = 0; /* following macro beats race condition */ __wait_event_interruptible(sfp->read_wait, (sdp->detached || (srp = sg_get_rq_mark(sfp, req_pack_id))), retval); if (sdp->detached) { retval = -ENODEV; goto free_old_hdr; } if (0 == retval) break; /* -ERESTARTSYS as signal hit process */ goto free_old_hdr; } } if (srp->header.interface_id != '\0') { retval = sg_new_read(sfp, buf, count, srp); goto free_old_hdr; } hp = &srp->header; if (old_hdr == NULL) { old_hdr = kmalloc(SZ_SG_HEADER, GFP_KERNEL); if (! old_hdr) { retval = -ENOMEM; goto free_old_hdr; } } memset(old_hdr, 0, SZ_SG_HEADER); old_hdr->reply_len = (int) hp->timeout; old_hdr->pack_len = old_hdr->reply_len; /* old, strange behaviour */ old_hdr->pack_id = hp->pack_id; old_hdr->twelve_byte = ((srp->data.cmd_opcode >= 0xc0) && (12 == hp->cmd_len)) ? 1 : 0; old_hdr->target_status = hp->masked_status; old_hdr->host_status = hp->host_status; old_hdr->driver_status = hp->driver_status; if ((CHECK_CONDITION & hp->masked_status) || (DRIVER_SENSE & hp->driver_status)) memcpy(old_hdr->sense_buffer, srp->sense_b, sizeof (old_hdr->sense_buffer)); switch (hp->host_status) { /* This setup of 'result' is for backward compatibility and is best ignored by the user who should use target, host + driver status */ case DID_OK: case DID_PASSTHROUGH: case DID_SOFT_ERROR: old_hdr->result = 0; break; case DID_NO_CONNECT: case DID_BUS_BUSY: case DID_TIME_OUT: old_hdr->result = EBUSY; break; case DID_BAD_TARGET: case DID_ABORT: case DID_PARITY: case DID_RESET: case DID_BAD_INTR: old_hdr->result = EIO; break; case DID_ERROR: old_hdr->result = (srp->sense_b[0] == 0 && hp->masked_status == GOOD) ? 0 : EIO; break; default: old_hdr->result = EIO; break; } /* Now copy the result back to the user buffer. */ if (count >= SZ_SG_HEADER) { if (__copy_to_user(buf, old_hdr, SZ_SG_HEADER)) { retval = -EFAULT; goto free_old_hdr; } buf += SZ_SG_HEADER; if (count > old_hdr->reply_len) count = old_hdr->reply_len; if (count > SZ_SG_HEADER) { if (sg_read_oxfer(srp, buf, count - SZ_SG_HEADER)) { retval = -EFAULT; goto free_old_hdr; } } } else count = (old_hdr->result == 0) ? 0 : -EIO; sg_finish_rem_req(srp); retval = count; free_old_hdr: kfree(old_hdr); return retval; } static ssize_t sg_new_read(Sg_fd * sfp, char __user *buf, size_t count, Sg_request * srp) { sg_io_hdr_t *hp = &srp->header; int err = 0; int len; if (count < SZ_SG_IO_HDR) { err = -EINVAL; goto err_out; } hp->sb_len_wr = 0; if ((hp->mx_sb_len > 0) && hp->sbp) { if ((CHECK_CONDITION & hp->masked_status) || (DRIVER_SENSE & hp->driver_status)) { int sb_len = SCSI_SENSE_BUFFERSIZE; sb_len = (hp->mx_sb_len > sb_len) ? sb_len : hp->mx_sb_len; len = 8 + (int) srp->sense_b[7]; /* Additional sense length field */ len = (len > sb_len) ? sb_len : len; if (copy_to_user(hp->sbp, srp->sense_b, len)) { err = -EFAULT; goto err_out; } hp->sb_len_wr = len; } } if (hp->masked_status || hp->host_status || hp->driver_status) hp->info |= SG_INFO_CHECK; if (copy_to_user(buf, hp, SZ_SG_IO_HDR)) { err = -EFAULT; goto err_out; } err = sg_read_xfer(srp); err_out: sg_finish_rem_req(srp); return (0 == err) ? count : err; } static ssize_t sg_write(struct file *filp, const char __user *buf, size_t count, loff_t * ppos) { int mxsize, cmd_size, k; int input_size, blocking; unsigned char opcode; Sg_device *sdp; Sg_fd *sfp; Sg_request *srp; struct sg_header old_hdr; sg_io_hdr_t *hp; unsigned char cmnd[MAX_COMMAND_SIZE]; if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp))) return -ENXIO; SCSI_LOG_TIMEOUT(3, printk("sg_write: %s, count=%d\n", sdp->disk->disk_name, (int) count)); if (sdp->detached) return -ENODEV; if (!((filp->f_flags & O_NONBLOCK) || scsi_block_when_processing_errors(sdp->device))) return -ENXIO; if (!access_ok(VERIFY_READ, buf, count)) return -EFAULT; /* protects following copy_from_user()s + get_user()s */ if (count < SZ_SG_HEADER) return -EIO; if (__copy_from_user(&old_hdr, buf, SZ_SG_HEADER)) return -EFAULT; blocking = !(filp->f_flags & O_NONBLOCK); if (old_hdr.reply_len < 0) return sg_new_write(sfp, buf, count, blocking, 0, NULL); if (count < (SZ_SG_HEADER + 6)) return -EIO; /* The minimum scsi command length is 6 bytes. */ if (!(srp = sg_add_request(sfp))) { SCSI_LOG_TIMEOUT(1, printk("sg_write: queue full\n")); return -EDOM; } buf += SZ_SG_HEADER; __get_user(opcode, buf); if (sfp->next_cmd_len > 0) { if (sfp->next_cmd_len > MAX_COMMAND_SIZE) { SCSI_LOG_TIMEOUT(1, printk("sg_write: command length too long\n")); sfp->next_cmd_len = 0; sg_remove_request(sfp, srp); return -EIO; } cmd_size = sfp->next_cmd_len; sfp->next_cmd_len = 0; /* reset so only this write() effected */ } else { cmd_size = COMMAND_SIZE(opcode); /* based on SCSI command group */ if ((opcode >= 0xc0) && old_hdr.twelve_byte) cmd_size = 12; } SCSI_LOG_TIMEOUT(4, printk( "sg_write: scsi opcode=0x%02x, cmd_size=%d\n", (int) opcode, cmd_size)); /* Determine buffer size. */ input_size = count - cmd_size; mxsize = (input_size > old_hdr.reply_len) ? input_size : old_hdr.reply_len; mxsize -= SZ_SG_HEADER; input_size -= SZ_SG_HEADER; if (input_size < 0) { sg_remove_request(sfp, srp); return -EIO; /* User did not pass enough bytes for this command. */ } hp = &srp->header; hp->interface_id = '\0'; /* indicator of old interface tunnelled */ hp->cmd_len = (unsigned char) cmd_size; hp->iovec_count = 0; hp->mx_sb_len = 0; if (input_size > 0) hp->dxfer_direction = (old_hdr.reply_len > SZ_SG_HEADER) ? SG_DXFER_TO_FROM_DEV : SG_DXFER_TO_DEV; else hp->dxfer_direction = (mxsize > 0) ? SG_DXFER_FROM_DEV : SG_DXFER_NONE; hp->dxfer_len = mxsize; hp->dxferp = (char __user *)buf + cmd_size; hp->sbp = NULL; hp->timeout = old_hdr.reply_len; /* structure abuse ... */ hp->flags = input_size; /* structure abuse ... */ hp->pack_id = old_hdr.pack_id; hp->usr_ptr = NULL; if (__copy_from_user(cmnd, buf, cmd_size)) return -EFAULT; /* * SG_DXFER_TO_FROM_DEV is functionally equivalent to SG_DXFER_FROM_DEV, * but is is possible that the app intended SG_DXFER_TO_DEV, because there * is a non-zero input_size, so emit a warning. */ if (hp->dxfer_direction == SG_DXFER_TO_FROM_DEV) if (printk_ratelimit()) printk(KERN_WARNING "sg_write: data in/out %d/%d bytes for SCSI command 0x%x--" "guessing data in;\n" KERN_WARNING " " "program %s not setting count and/or reply_len properly\n", old_hdr.reply_len - (int)SZ_SG_HEADER, input_size, (unsigned int) cmnd[0], current->comm); k = sg_common_write(sfp, srp, cmnd, sfp->timeout, blocking); return (k < 0) ? k : count; } static ssize_t sg_new_write(Sg_fd * sfp, const char __user *buf, size_t count, int blocking, int read_only, Sg_request ** o_srp) { int k; Sg_request *srp; sg_io_hdr_t *hp; unsigned char cmnd[MAX_COMMAND_SIZE]; int timeout; unsigned long ul_timeout; if (count < SZ_SG_IO_HDR) return -EINVAL; if (!access_ok(VERIFY_READ, buf, count)) return -EFAULT; /* protects following copy_from_user()s + get_user()s */ sfp->cmd_q = 1; /* when sg_io_hdr seen, set command queuing on */ if (!(srp = sg_add_request(sfp))) { SCSI_LOG_TIMEOUT(1, printk("sg_new_write: queue full\n")); return -EDOM; } hp = &srp->header; if (__copy_from_user(hp, buf, SZ_SG_IO_HDR)) { sg_remove_request(sfp, srp); return -EFAULT; } if (hp->interface_id != 'S') { sg_remove_request(sfp, srp); return -ENOSYS; } if (hp->flags & SG_FLAG_MMAP_IO) { if (hp->dxfer_len > sfp->reserve.bufflen) { sg_remove_request(sfp, srp); return -ENOMEM; /* MMAP_IO size must fit in reserve buffer */ } if (hp->flags & SG_FLAG_DIRECT_IO) { sg_remove_request(sfp, srp); return -EINVAL; /* either MMAP_IO or DIRECT_IO (not both) */ } if (sg_res_in_use(sfp)) { sg_remove_request(sfp, srp); return -EBUSY; /* reserve buffer already being used */ } } ul_timeout = msecs_to_jiffies(srp->header.timeout); timeout = (ul_timeout < INT_MAX) ? ul_timeout : INT_MAX; if ((!hp->cmdp) || (hp->cmd_len < 6) || (hp->cmd_len > sizeof (cmnd))) { sg_remove_request(sfp, srp); return -EMSGSIZE; } if (!access_ok(VERIFY_READ, hp->cmdp, hp->cmd_len)) { sg_remove_request(sfp, srp); return -EFAULT; /* protects following copy_from_user()s + get_user()s */ } if (__copy_from_user(cmnd, hp->cmdp, hp->cmd_len)) { sg_remove_request(sfp, srp); return -EFAULT; } if (read_only && (!sg_allow_access(cmnd[0], sfp->parentdp->device->type))) { sg_remove_request(sfp, srp); return -EPERM; } k = sg_common_write(sfp, srp, cmnd, timeout, blocking); if (k < 0) return k; if (o_srp) *o_srp = srp; return count; } static int sg_common_write(Sg_fd * sfp, Sg_request * srp, unsigned char *cmnd, int timeout, int blocking) { int k, data_dir; Sg_device *sdp = sfp->parentdp; sg_io_hdr_t *hp = &srp->header; srp->data.cmd_opcode = cmnd[0]; /* hold opcode of command */ hp->status = 0; hp->masked_status = 0; hp->msg_status = 0; hp->info = 0; hp->host_status = 0; hp->driver_status = 0; hp->resid = 0; SCSI_LOG_TIMEOUT(4, printk("sg_common_write: scsi opcode=0x%02x, cmd_size=%d\n", (int) cmnd[0], (int) hp->cmd_len)); if ((k = sg_start_req(srp))) { SCSI_LOG_TIMEOUT(1, printk("sg_write: start_req err=%d\n", k)); sg_finish_rem_req(srp); return k; /* probably out of space --> ENOMEM */ } if ((k = sg_write_xfer(srp))) { SCSI_LOG_TIMEOUT(1, printk("sg_write: write_xfer, bad address\n")); sg_finish_rem_req(srp); return k; } if (sdp->detached) { sg_finish_rem_req(srp); return -ENODEV; } switch (hp->dxfer_direction) { case SG_DXFER_TO_FROM_DEV: case SG_DXFER_FROM_DEV: data_dir = DMA_FROM_DEVICE; break; case SG_DXFER_TO_DEV: data_dir = DMA_TO_DEVICE; break; case SG_DXFER_UNKNOWN: data_dir = DMA_BIDIRECTIONAL; break; default: data_dir = DMA_NONE; break; } hp->duration = jiffies_to_msecs(jiffies); /* Now send everything of to mid-level. The next time we hear about this packet is when sg_cmd_done() is called (i.e. a callback). */ if (scsi_execute_async(sdp->device, cmnd, hp->cmd_len, data_dir, srp->data.buffer, hp->dxfer_len, srp->data.k_use_sg, timeout, SG_DEFAULT_RETRIES, srp, sg_cmd_done, GFP_ATOMIC)) { SCSI_LOG_TIMEOUT(1, printk("sg_write: scsi_execute_async failed\n")); /* * most likely out of mem, but could also be a bad map */ sg_finish_rem_req(srp); return -ENOMEM; } else return 0; } static int sg_srp_done(Sg_request *srp, Sg_fd *sfp) { unsigned long iflags; int done; read_lock_irqsave(&sfp->rq_list_lock, iflags); done = srp->done; read_unlock_irqrestore(&sfp->rq_list_lock, iflags); return done; } static int sg_ioctl(struct inode *inode, struct file *filp, unsigned int cmd_in, unsigned long arg) { void __user *p = (void __user *)arg; int __user *ip = p; int result, val, read_only; Sg_device *sdp; Sg_fd *sfp; Sg_request *srp; unsigned long iflags; if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp))) return -ENXIO; SCSI_LOG_TIMEOUT(3, printk("sg_ioctl: %s, cmd=0x%x\n", sdp->disk->disk_name, (int) cmd_in)); read_only = (O_RDWR != (filp->f_flags & O_ACCMODE)); switch (cmd_in) { case SG_IO: { int blocking = 1; /* ignore O_NONBLOCK flag */ if (sdp->detached) return -ENODEV; if (!scsi_block_when_processing_errors(sdp->device)) return -ENXIO; if (!access_ok(VERIFY_WRITE, p, SZ_SG_IO_HDR)) return -EFAULT; result = sg_new_write(sfp, p, SZ_SG_IO_HDR, blocking, read_only, &srp); if (result < 0) return result; srp->sg_io_owned = 1; while (1) { result = 0; /* following macro to beat race condition */ __wait_event_interruptible(sfp->read_wait, (sdp->detached || sfp->closed || sg_srp_done(srp, sfp)), result); if (sdp->detached) return -ENODEV; if (sfp->closed) return 0; /* request packet dropped already */ if (0 == result) break; srp->orphan = 1; return result; /* -ERESTARTSYS because signal hit process */ } write_lock_irqsave(&sfp->rq_list_lock, iflags); srp->done = 2; write_unlock_irqrestore(&sfp->rq_list_lock, iflags); result = sg_new_read(sfp, p, SZ_SG_IO_HDR, srp); return (result < 0) ? result : 0; } case SG_SET_TIMEOUT: result = get_user(val, ip); if (result) return result; if (val < 0) return -EIO; if (val >= MULDIV (INT_MAX, USER_HZ, HZ)) val = MULDIV (INT_MAX, USER_HZ, HZ); sfp->timeout_user = val; sfp->timeout = MULDIV (val, HZ, USER_HZ); return 0; case SG_GET_TIMEOUT: /* N.B. User receives timeout as return value */ /* strange ..., for backward compatibility */ return sfp->timeout_user; case SG_SET_FORCE_LOW_DMA: result = get_user(val, ip); if (result) return result; if (val) { sfp->low_dma = 1; if ((0 == sfp->low_dma) && (0 == sg_res_in_use(sfp))) { val = (int) sfp->reserve.bufflen; sg_remove_scat(&sfp->reserve); sg_build_reserve(sfp, val); } } else { if (sdp->detached) return -ENODEV; sfp->low_dma = sdp->device->host->unchecked_isa_dma; } return 0; case SG_GET_LOW_DMA: return put_user((int) sfp->low_dma, ip); case SG_GET_SCSI_ID: if (!access_ok(VERIFY_WRITE, p, sizeof (sg_scsi_id_t))) return -EFAULT; else { sg_scsi_id_t __user *sg_idp = p; if (sdp->detached) return -ENODEV; __put_user((int) sdp->device->host->host_no, &sg_idp->host_no); __put_user((int) sdp->device->channel, &sg_idp->channel); __put_user((int) sdp->device->id, &sg_idp->scsi_id); __put_user((int) sdp->device->lun, &sg_idp->lun); __put_user((int) sdp->device->type, &sg_idp->scsi_type); __put_user((short) sdp->device->host->cmd_per_lun, &sg_idp->h_cmd_per_lun); __put_user((short) sdp->device->queue_depth, &sg_idp->d_queue_depth); __put_user(0, &sg_idp->unused[0]); __put_user(0, &sg_idp->unused[1]); return 0; } case SG_SET_FORCE_PACK_ID: result = get_user(val, ip); if (result) return result; sfp->force_packid = val ? 1 : 0; return 0; case SG_GET_PACK_ID: if (!access_ok(VERIFY_WRITE, ip, sizeof (int))) return -EFAULT; read_lock_irqsave(&sfp->rq_list_lock, iflags); for (srp = sfp->headrp; srp; srp = srp->nextrp) { if ((1 == srp->done) && (!srp->sg_io_owned)) { read_unlock_irqrestore(&sfp->rq_list_lock, iflags); __put_user(srp->header.pack_id, ip); return 0; } } read_unlock_irqrestore(&sfp->rq_list_lock, iflags); __put_user(-1, ip); return 0; case SG_GET_NUM_WAITING: read_lock_irqsave(&sfp->rq_list_lock, iflags); for (val = 0, srp = sfp->headrp; srp; srp = srp->nextrp) { if ((1 == srp->done) && (!srp->sg_io_owned)) ++val; } read_unlock_irqrestore(&sfp->rq_list_lock, iflags); return put_user(val, ip); case SG_GET_SG_TABLESIZE: return put_user(sdp->sg_tablesize, ip); case SG_SET_RESERVED_SIZE: result = get_user(val, ip); if (result) return result; if (val < 0) return -EINVAL; if (val != sfp->reserve.bufflen) { if (sg_res_in_use(sfp) || sfp->mmap_called) return -EBUSY; sg_remove_scat(&sfp->reserve); sg_build_reserve(sfp, val); } return 0; case SG_GET_RESERVED_SIZE: val = (int) sfp->reserve.bufflen; return put_user(val, ip); case SG_SET_COMMAND_Q: result = get_user(val, ip); if (result) return result; sfp->cmd_q = val ? 1 : 0; return 0; case SG_GET_COMMAND_Q: return put_user((int) sfp->cmd_q, ip); case SG_SET_KEEP_ORPHAN: result = get_user(val, ip); if (result) return result; sfp->keep_orphan = val; return 0; case SG_GET_KEEP_ORPHAN: return put_user((int) sfp->keep_orphan, ip); case SG_NEXT_CMD_LEN: result = get_user(val, ip); if (result) return result; sfp->next_cmd_len = (val > 0) ? val : 0; return 0; case SG_GET_VERSION_NUM: return put_user(sg_version_num, ip); case SG_GET_ACCESS_COUNT: /* faked - we don't have a real access count anymore */ val = (sdp->device ? 1 : 0); return put_user(val, ip); case SG_GET_REQUEST_TABLE: if (!access_ok(VERIFY_WRITE, p, SZ_SG_REQ_INFO * SG_MAX_QUEUE)) return -EFAULT; else { sg_req_info_t *rinfo; unsigned int ms; rinfo = kmalloc(SZ_SG_REQ_INFO * SG_MAX_QUEUE, GFP_KERNEL); if (!rinfo) return -ENOMEM; read_lock_irqsave(&sfp->rq_list_lock, iflags); for (srp = sfp->headrp, val = 0; val < SG_MAX_QUEUE; ++val, srp = srp ? srp->nextrp : srp) { memset(&rinfo[val], 0, SZ_SG_REQ_INFO); if (srp) { rinfo[val].req_state = srp->done + 1; rinfo[val].problem = srp->header.masked_status & srp->header.host_status & srp->header.driver_status; if (srp->done) rinfo[val].duration = srp->header.duration; else { ms = jiffies_to_msecs(jiffies); rinfo[val].duration = (ms > srp->header.duration) ? (ms - srp->header.duration) : 0; } rinfo[val].orphan = srp->orphan; rinfo[val].sg_io_owned = srp->sg_io_owned; rinfo[val].pack_id = srp->header.pack_id; rinfo[val].usr_ptr = srp->header.usr_ptr; } } read_unlock_irqrestore(&sfp->rq_list_lock, iflags); result = __copy_to_user(p, rinfo, SZ_SG_REQ_INFO * SG_MAX_QUEUE); result = result ? -EFAULT : 0; kfree(rinfo); return result; } case SG_EMULATED_HOST: if (sdp->detached) return -ENODEV; return put_user(sdp->device->host->hostt->emulated, ip); case SG_SCSI_RESET: if (sdp->detached) return -ENODEV; if (filp->f_flags & O_NONBLOCK) { if (scsi_host_in_recovery(sdp->device->host)) return -EBUSY; } else if (!scsi_block_when_processing_errors(sdp->device)) return -EBUSY; result = get_user(val, ip); if (result) return result; if (SG_SCSI_RESET_NOTHING == val) return 0; switch (val) { case SG_SCSI_RESET_DEVICE: val = SCSI_TRY_RESET_DEVICE; break; case SG_SCSI_RESET_BUS: val = SCSI_TRY_RESET_BUS; break; case SG_SCSI_RESET_HOST: val = SCSI_TRY_RESET_HOST; break; default: return -EINVAL; } if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO)) return -EACCES; return (scsi_reset_provider(sdp->device, val) == SUCCESS) ? 0 : -EIO; case SCSI_IOCTL_SEND_COMMAND: if (sdp->detached) return -ENODEV; if (read_only) { unsigned char opcode = WRITE_6; Scsi_Ioctl_Command __user *siocp = p; if (copy_from_user(&opcode, siocp->data, 1)) return -EFAULT; if (!sg_allow_access(opcode, sdp->device->type)) return -EPERM; } return sg_scsi_ioctl(filp, sdp->device->request_queue, NULL, p); case SG_SET_DEBUG: result = get_user(val, ip); if (result) return result; sdp->sgdebug = (char) val; return 0; case SCSI_IOCTL_GET_IDLUN: case SCSI_IOCTL_GET_BUS_NUMBER: case SCSI_IOCTL_PROBE_HOST: case SG_GET_TRANSFORM: if (sdp->detached) return -ENODEV; return scsi_ioctl(sdp->device, cmd_in, p); default: if (read_only) return -EPERM; /* don't know so take safe approach */ return scsi_ioctl(sdp->device, cmd_in, p); } } #ifdef CONFIG_COMPAT static long sg_compat_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg) { Sg_device *sdp; Sg_fd *sfp; struct scsi_device *sdev; if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp))) return -ENXIO; sdev = sdp->device; if (sdev->host->hostt->compat_ioctl) { int ret; ret = sdev->host->hostt->compat_ioctl(sdev, cmd_in, (void __user *)arg); return ret; } return -ENOIOCTLCMD; } #endif static unsigned int sg_poll(struct file *filp, poll_table * wait) { unsigned int res = 0; Sg_device *sdp; Sg_fd *sfp; Sg_request *srp; int count = 0; unsigned long iflags; if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp)) || sfp->closed) return POLLERR; poll_wait(filp, &sfp->read_wait, wait); read_lock_irqsave(&sfp->rq_list_lock, iflags); for (srp = sfp->headrp; srp; srp = srp->nextrp) { /* if any read waiting, flag it */ if ((0 == res) && (1 == srp->done) && (!srp->sg_io_owned)) res = POLLIN | POLLRDNORM; ++count; } read_unlock_irqrestore(&sfp->rq_list_lock, iflags); if (sdp->detached) res |= POLLHUP; else if (!sfp->cmd_q) { if (0 == count) res |= POLLOUT | POLLWRNORM; } else if (count < SG_MAX_QUEUE) res |= POLLOUT | POLLWRNORM; SCSI_LOG_TIMEOUT(3, printk("sg_poll: %s, res=0x%x\n", sdp->disk->disk_name, (int) res)); return res; } static int sg_fasync(int fd, struct file *filp, int mode) { int retval; Sg_device *sdp; Sg_fd *sfp; if ((!(sfp = (Sg_fd *) filp->private_data)) || (!(sdp = sfp->parentdp))) return -ENXIO; SCSI_LOG_TIMEOUT(3, printk("sg_fasync: %s, mode=%d\n", sdp->disk->disk_name, mode)); retval = fasync_helper(fd, filp, mode, &sfp->async_qp); return (retval < 0) ? retval : 0; } static struct page * sg_vma_nopage(struct vm_area_struct *vma, unsigned long addr, int *type) { Sg_fd *sfp; struct page *page = NOPAGE_SIGBUS; unsigned long offset, len, sa; Sg_scatter_hold *rsv_schp; struct scatterlist *sg; int k; if ((NULL == vma) || (!(sfp = (Sg_fd *) vma->vm_private_data))) return page; rsv_schp = &sfp->reserve; offset = addr - vma->vm_start; if (offset >= rsv_schp->bufflen) return page; SCSI_LOG_TIMEOUT(3, printk("sg_vma_nopage: offset=%lu, scatg=%d\n", offset, rsv_schp->k_use_sg)); sg = rsv_schp->buffer; sa = vma->vm_start; for (k = 0; (k < rsv_schp->k_use_sg) && (sa < vma->vm_end); ++k, ++sg) { len = vma->vm_end - sa; len = (len < sg->length) ? len : sg->length; if (offset < len) { page = sg->page; get_page(page); /* increment page count */ break; } sa += len; offset -= len; } if (type) *type = VM_FAULT_MINOR; return page; } static struct vm_operations_struct sg_mmap_vm_ops = { .nopage = sg_vma_nopage, }; static int sg_mmap(struct file *filp, struct vm_area_struct *vma) { Sg_fd *sfp; unsigned long req_sz, len, sa; Sg_scatter_hold *rsv_schp; int k; struct scatterlist *sg; if ((!filp) || (!vma) || (!(sfp = (Sg_fd *) filp->private_data))) return -ENXIO; req_sz = vma->vm_end - vma->vm_start; SCSI_LOG_TIMEOUT(3, printk("sg_mmap starting, vm_start=%p, len=%d\n", (void *) vma->vm_start, (int) req_sz)); if (vma->vm_pgoff) return -EINVAL; /* want no offset */ rsv_schp = &sfp->reserve; if (req_sz > rsv_schp->bufflen) return -ENOMEM; /* cannot map more than reserved buffer */ sa = vma->vm_start; sg = rsv_schp->buffer; for (k = 0; (k < rsv_schp->k_use_sg) && (sa < vma->vm_end); ++k, ++sg) { len = vma->vm_end - sa; len = (len < sg->length) ? len : sg->length; sa += len; } sfp->mmap_called = 1; vma->vm_flags |= VM_RESERVED; vma->vm_private_data = sfp; vma->vm_ops = &sg_mmap_vm_ops; return 0; } /* This function is a "bottom half" handler that is called by the * mid level when a command is completed (or has failed). */ static void sg_cmd_done(void *data, char *sense, int result, int resid) { Sg_request *srp = data; Sg_device *sdp = NULL; Sg_fd *sfp; unsigned long iflags; unsigned int ms; if (NULL == srp) { printk(KERN_ERR "sg_cmd_done: NULL request\n"); return; } sfp = srp->parentfp; if (sfp) sdp = sfp->parentdp; if ((NULL == sdp) || sdp->detached) { printk(KERN_INFO "sg_cmd_done: device detached\n"); return; } SCSI_LOG_TIMEOUT(4, printk("sg_cmd_done: %s, pack_id=%d, res=0x%x\n", sdp->disk->disk_name, srp->header.pack_id, result)); srp->header.resid = resid; ms = jiffies_to_msecs(jiffies); srp->header.duration = (ms > srp->header.duration) ? (ms - srp->header.duration) : 0; if (0 != result) { struct scsi_sense_hdr sshdr; memcpy(srp->sense_b, sense, sizeof (srp->sense_b)); srp->header.status = 0xff & result; srp->header.masked_status = status_byte(result); srp->header.msg_status = msg_byte(result); srp->header.host_status = host_byte(result); srp->header.driver_status = driver_byte(result); if ((sdp->sgdebug > 0) && ((CHECK_CONDITION == srp->header.masked_status) || (COMMAND_TERMINATED == srp->header.masked_status))) __scsi_print_sense("sg_cmd_done", sense, SCSI_SENSE_BUFFERSIZE); /* Following if statement is a patch supplied by Eric Youngdale */ if (driver_byte(result) != 0 && scsi_normalize_sense(sense, SCSI_SENSE_BUFFERSIZE, &sshdr) && !scsi_sense_is_deferred(&sshdr) && sshdr.sense_key == UNIT_ATTENTION && sdp->device->removable) { /* Detected possible disc change. Set the bit - this */ /* may be used if there are filesystems using this device */ sdp->device->changed = 1; } } /* Rely on write phase to clean out srp status values, so no "else" */ if (sfp->closed) { /* whoops this fd already released, cleanup */ SCSI_LOG_TIMEOUT(1, printk("sg_cmd_done: already closed, freeing ...\n")); sg_finish_rem_req(srp); srp = NULL; if (NULL == sfp->headrp) { SCSI_LOG_TIMEOUT(1, printk("sg...bh: already closed, final cleanup\n")); if (0 == sg_remove_sfp(sdp, sfp)) { /* device still present */ scsi_device_put(sdp->device); }


context:
space:
mode: