freebsd-dev/sys/kern/subr_uio.c

628 lines
13 KiB
C
Raw Normal View History

/*-
* SPDX-License-Identifier: BSD-3-Clause
*
1994-05-24 10:09:53 +00:00
* Copyright (c) 1982, 1986, 1991, 1993
* The Regents of the University of California. All rights reserved.
* (c) UNIX System Laboratories, Inc.
* All or some portions of this file are derived from material licensed
* to the University of California by American Telephone and Telegraph
* Co. or Unix System Laboratories, Inc. and are reproduced herein with
* the permission of UNIX System Laboratories, Inc.
*
* Copyright (c) 2014 The FreeBSD Foundation
*
* Portions of this software were developed by Konstantin Belousov
* under sponsorship from the FreeBSD Foundation.
*
1994-05-24 10:09:53 +00:00
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. Neither the name of the University nor the names of its contributors
1994-05-24 10:09:53 +00:00
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* @(#)kern_subr.c 8.3 (Berkeley) 1/21/94
*/
2003-06-11 00:56:59 +00:00
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
1994-05-24 10:09:53 +00:00
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/kernel.h>
#include <sys/limits.h>
#include <sys/lock.h>
#include <sys/mman.h>
1994-05-24 10:09:53 +00:00
#include <sys/proc.h>
#include <sys/resourcevar.h>
Switch the vm_object mutex to be a rwlock. This will enable in the future further optimizations where the vm_object lock will be held in read mode most of the time the page cache resident pool of pages are accessed for reading purposes. The change is mostly mechanical but few notes are reported: * The KPI changes as follow: - VM_OBJECT_LOCK() -> VM_OBJECT_WLOCK() - VM_OBJECT_TRYLOCK() -> VM_OBJECT_TRYWLOCK() - VM_OBJECT_UNLOCK() -> VM_OBJECT_WUNLOCK() - VM_OBJECT_LOCK_ASSERT(MA_OWNED) -> VM_OBJECT_ASSERT_WLOCKED() (in order to avoid visibility of implementation details) - The read-mode operations are added: VM_OBJECT_RLOCK(), VM_OBJECT_TRYRLOCK(), VM_OBJECT_RUNLOCK(), VM_OBJECT_ASSERT_RLOCKED(), VM_OBJECT_ASSERT_LOCKED() * The vm/vm_pager.h namespace pollution avoidance (forcing requiring sys/mutex.h in consumers directly to cater its inlining functions using VM_OBJECT_LOCK()) imposes that all the vm/vm_pager.h consumers now must include also sys/rwlock.h. * zfs requires a quite convoluted fix to include FreeBSD rwlocks into the compat layer because the name clash between FreeBSD and solaris versions must be avoided. At this purpose zfs redefines the vm_object locking functions directly, isolating the FreeBSD components in specific compat stubs. The KPI results heavilly broken by this commit. Thirdy part ports must be updated accordingly (I can think off-hand of VirtualBox, for example). Sponsored by: EMC / Isilon storage division Reviewed by: jeff Reviewed by: pjd (ZFS specific review) Discussed with: alc Tested by: pho
2013-03-09 02:32:23 +00:00
#include <sys/rwlock.h>
#include <sys/sched.h>
#include <sys/sysctl.h>
VM level code cleanups. 1) Start using TSM. Struct procs continue to point to upages structure, after being freed. Struct vmspace continues to point to pte object and kva space for kstack. u_map is now superfluous. 2) vm_map's don't need to be reference counted. They always exist either in the kernel or in a vmspace. The vmspaces are managed by reference counts. 3) Remove the "wired" vm_map nonsense. 4) No need to keep a cache of kernel stack kva's. 5) Get rid of strange looking ++var, and change to var++. 6) Change more data structures to use our "zone" allocator. Added struct proc, struct vmspace and struct vnode. This saves a significant amount of kva space and physical memory. Additionally, this enables TSM for the zone managed memory. 7) Keep ioopt disabled for now. 8) Remove the now bogus "single use" map concept. 9) Use generation counts or id's for data structures residing in TSM, where it allows us to avoid unneeded restart overhead during traversals, where blocking might occur. 10) Account better for memory deficits, so the pageout daemon will be able to make enough memory available (experimental.) 11) Fix some vnode locking problems. (From Tor, I think.) 12) Add a check in ufs_lookup, to avoid lots of unneeded calls to bcmp. (experimental.) 13) Significantly shrink, cleanup, and make slightly faster the vm_fault.c code. Use generation counts, get rid of unneded collpase operations, and clean up the cluster code. 14) Make vm_zone more suitable for TSM. This commit is partially as a result of discussions and contributions from other people, including DG, Tor Egge, PHK, and probably others that I have forgotten to attribute (so let me know, if I forgot.) This is not the infamous, final cleanup of the vnode stuff, but a necessary step. Vnode mgmt should be correct, but things might still change, and there is still some missing stuff (like ioopt, and physical backing of non-merged cache files, debugging of layering concepts.)
1998-01-22 17:30:44 +00:00
#include <sys/vnode.h>
#include <vm/vm.h>
#include <vm/vm_param.h>
#include <vm/vm_extern.h>
#include <vm/vm_page.h>
#include <vm/vm_pageout.h>
#include <vm/vm_map.h>
1994-05-24 10:09:53 +00:00
Add asynchronous command support to the pass(4) driver, and the new camdd(8) utility. CCBs may be queued to the driver via the new CAMIOQUEUE ioctl, and completed CCBs may be retrieved via the CAMIOGET ioctl. User processes can use poll(2) or kevent(2) to get notification when I/O has completed. While the existing CAMIOCOMMAND blocking ioctl interface only supports user virtual data pointers in a CCB (generally only one per CCB), the new CAMIOQUEUE ioctl supports user virtual and physical address pointers, as well as user virtual and physical scatter/gather lists. This allows user applications to have more flexibility in their data handling operations. Kernel memory for data transferred via the queued interface is allocated from the zone allocator in MAXPHYS sized chunks, and user data is copied in and out. This is likely faster than the vmapbuf()/vunmapbuf() method used by the CAMIOCOMMAND ioctl in configurations with many processors (there are more TLB shootdowns caused by the mapping/unmapping operation) but may not be as fast as running with unmapped I/O. The new memory handling model for user requests also allows applications to send CCBs with request sizes that are larger than MAXPHYS. The pass(4) driver now limits queued requests to the I/O size listed by the SIM driver in the maxio field in the Path Inquiry (XPT_PATH_INQ) CCB. There are some things things would be good to add: 1. Come up with a way to do unmapped I/O on multiple buffers. Currently the unmapped I/O interface operates on a struct bio, which includes only one address and length. It would be nice to be able to send an unmapped scatter/gather list down to busdma. This would allow eliminating the copy we currently do for data. 2. Add an ioctl to list currently outstanding CCBs in the various queues. 3. Add an ioctl to cancel a request, or use the XPT_ABORT CCB to do that. 4. Test physical address support. Virtual pointers and scatter gather lists have been tested, but I have not yet tested physical addresses or scatter/gather lists. 5. Investigate multiple queue support. At the moment there is one queue of commands per pass(4) device. If multiple processes open the device, they will submit I/O into the same queue and get events for the same completions. This is probably the right model for most applications, but it is something that could be changed later on. Also, add a new utility, camdd(8) that uses the asynchronous pass(4) driver interface. This utility is intended to be a basic data transfer/copy utility, a simple benchmark utility, and an example of how to use the asynchronous pass(4) interface. It can copy data to and from pass(4) devices using any target queue depth, starting offset and blocksize for the input and ouptut devices. It currently only supports SCSI devices, but could be easily extended to support ATA devices. It can also copy data to and from regular files, block devices, tape devices, pipes, stdin, and stdout. It does not support queueing multiple commands to any of those targets, since it uses the standard read(2)/write(2)/writev(2)/readv(2) system calls. The I/O is done by two threads, one for the reader and one for the writer. The reader thread sends completed read requests to the writer thread in strictly sequential order, even if they complete out of order. That could be modified later on for random I/O patterns or slightly out of order I/O. camdd(8) uses kqueue(2)/kevent(2) to get I/O completion events from the pass(4) driver and also to send request notifications internally. For pass(4) devcies, camdd(8) uses a single buffer (CAM_DATA_VADDR) per CAM CCB on the reading side, and a scatter/gather list (CAM_DATA_SG) on the writing side. In addition to testing both interfaces, this makes any potential reblocking of I/O easier. No data is copied between the reader and the writer, but rather the reader's buffers are split into multiple I/O requests or combined into a single I/O request depending on the input and output blocksize. For the file I/O path, camdd(8) also uses a single buffer (read(2), write(2), pread(2) or pwrite(2)) on reads, and a scatter/gather list (readv(2), writev(2), preadv(2), pwritev(2)) on writes. Things that would be nice to do for camdd(8) eventually: 1. Add support for I/O pattern generation. Patterns like all zeros, all ones, LBA-based patterns, random patterns, etc. Right Now you can always use /dev/zero, /dev/random, etc. 2. Add support for a "sink" mode, so we do only reads with no writes. Right now, you can use /dev/null. 3. Add support for automatic queue depth probing, so that we can figure out the right queue depth on the input and output side for maximum throughput. At the moment it defaults to 6. 4. Add support for SATA device passthrough I/O. 5. Add support for random LBAs and/or lengths on the input and output sides. 6. Track average per-I/O latency and busy time. The busy time and latency could also feed in to the automatic queue depth determination. sys/cam/scsi/scsi_pass.h: Define two new ioctls, CAMIOQUEUE and CAMIOGET, that queue and fetch asynchronous CAM CCBs respectively. Although these ioctls do not have a declared argument, they both take a union ccb pointer. If we declare a size here, the ioctl code in sys/kern/sys_generic.c will malloc and free a buffer for either the CCB or the CCB pointer (depending on how it is declared). Since we have to keep a copy of the CCB (which is fairly large) anyway, having the ioctl malloc and free a CCB for each call is wasteful. sys/cam/scsi/scsi_pass.c: Add asynchronous CCB support. Add two new ioctls, CAMIOQUEUE and CAMIOGET. CAMIOQUEUE adds a CCB to the incoming queue. The CCB is executed immediately (and moved to the active queue) if it is an immediate CCB, but otherwise it will be executed in passstart() when a CCB is available from the transport layer. When CCBs are completed (because they are immediate or passdone() if they are queued), they are put on the done queue. If we get the final close on the device before all pending I/O is complete, all active I/O is moved to the abandoned queue and we increment the peripheral reference count so that the peripheral driver instance doesn't go away before all pending I/O is done. The new passcreatezone() function is called on the first call to the CAMIOQUEUE ioctl on a given device to allocate the UMA zones for I/O requests and S/G list buffers. This may be good to move off to a taskqueue at some point. The new passmemsetup() function allocates memory and scatter/gather lists to hold the user's data, and copies in any data that needs to be written. For virtual pointers (CAM_DATA_VADDR), the kernel buffer is malloced from the new pass(4) driver malloc bucket. For virtual scatter/gather lists (CAM_DATA_SG), buffers are allocated from a new per-pass(9) UMA zone in MAXPHYS-sized chunks. Physical pointers are passed in unchanged. We have support for up to 16 scatter/gather segments (for the user and kernel S/G lists) in the default struct pass_io_req, so requests with longer S/G lists require an extra kernel malloc. The new passcopysglist() function copies a user scatter/gather list to a kernel scatter/gather list. The number of elements in each list may be different, but (obviously) the amount of data stored has to be identical. The new passmemdone() function copies data out for the CAM_DATA_VADDR and CAM_DATA_SG cases. The new passiocleanup() function restores data pointers in user CCBs and frees memory. Add new functions to support kqueue(2)/kevent(2): passreadfilt() tells kevent whether or not the done queue is empty. passkqfilter() adds a knote to our list. passreadfiltdetach() removes a knote from our list. Add a new function, passpoll(), for poll(2)/select(2) to use. Add devstat(9) support for the queued CCB path. sys/cam/ata/ata_da.c: Add support for the BIO_VLIST bio type. sys/cam/cam_ccb.h: Add a new enumeration for the xflags field in the CCB header. (This doesn't change the CCB header, just adds an enumeration to use.) sys/cam/cam_xpt.c: Add a new function, xpt_setup_ccb_flags(), that allows specifying CCB flags. sys/cam/cam_xpt.h: Add a prototype for xpt_setup_ccb_flags(). sys/cam/scsi/scsi_da.c: Add support for BIO_VLIST. sys/dev/md/md.c: Add BIO_VLIST support to md(4). sys/geom/geom_disk.c: Add BIO_VLIST support to the GEOM disk class. Re-factor the I/O size limiting code in g_disk_start() a bit. sys/kern/subr_bus_dma.c: Change _bus_dmamap_load_vlist() to take a starting offset and length. Add a new function, _bus_dmamap_load_pages(), that will load a list of physical pages starting at an offset. Update _bus_dmamap_load_bio() to allow loading BIO_VLIST bios. Allow unmapped I/O to start at an offset. sys/kern/subr_uio.c: Add two new functions, physcopyin_vlist() and physcopyout_vlist(). sys/pc98/include/bus.h: Guard kernel-only parts of the pc98 machine/bus.h header with #ifdef _KERNEL. This allows userland programs to include <machine/bus.h> to get the definition of bus_addr_t and bus_size_t. sys/sys/bio.h: Add a new bio flag, BIO_VLIST. sys/sys/uio.h: Add prototypes for physcopyin_vlist() and physcopyout_vlist(). share/man/man4/pass.4: Document the CAMIOQUEUE and CAMIOGET ioctls. usr.sbin/Makefile: Add camdd. usr.sbin/camdd/Makefile: Add a makefile for camdd(8). usr.sbin/camdd/camdd.8: Man page for camdd(8). usr.sbin/camdd/camdd.c: The new camdd(8) utility. Sponsored by: Spectra Logic MFC after: 1 week
2015-12-03 20:54:55 +00:00
#include <machine/bus.h>
SYSCTL_INT(_kern, KERN_IOV_MAX, iov_max, CTLFLAG_RD, SYSCTL_NULL_INT_PTR, UIO_MAXIOV,
"Maximum number of elements in an I/O vector; sysconf(_SC_IOV_MAX)");
static int uiomove_faultflag(void *cp, int n, struct uio *uio, int nofault);
int
copyin_nofault(const void *udaddr, void *kaddr, size_t len)
{
int error, save;
save = vm_fault_disable_pagefaults();
error = copyin(udaddr, kaddr, len);
vm_fault_enable_pagefaults(save);
return (error);
}
int
copyout_nofault(const void *kaddr, void *udaddr, size_t len)
{
int error, save;
save = vm_fault_disable_pagefaults();
error = copyout(kaddr, udaddr, len);
vm_fault_enable_pagefaults(save);
return (error);
}
#define PHYS_PAGE_COUNT(len) (howmany(len, PAGE_SIZE) + 1)
int
physcopyin(void *src, vm_paddr_t dst, size_t len)
{
vm_page_t m[PHYS_PAGE_COUNT(len)];
struct iovec iov[1];
struct uio uio;
int i;
iov[0].iov_base = src;
iov[0].iov_len = len;
uio.uio_iov = iov;
uio.uio_iovcnt = 1;
uio.uio_offset = 0;
uio.uio_resid = len;
uio.uio_segflg = UIO_SYSSPACE;
uio.uio_rw = UIO_WRITE;
for (i = 0; i < PHYS_PAGE_COUNT(len); i++, dst += PAGE_SIZE)
m[i] = PHYS_TO_VM_PAGE(dst);
return (uiomove_fromphys(m, dst & PAGE_MASK, len, &uio));
}
int
physcopyout(vm_paddr_t src, void *dst, size_t len)
{
vm_page_t m[PHYS_PAGE_COUNT(len)];
struct iovec iov[1];
struct uio uio;
int i;
iov[0].iov_base = dst;
iov[0].iov_len = len;
uio.uio_iov = iov;
uio.uio_iovcnt = 1;
uio.uio_offset = 0;
uio.uio_resid = len;
uio.uio_segflg = UIO_SYSSPACE;
uio.uio_rw = UIO_READ;
for (i = 0; i < PHYS_PAGE_COUNT(len); i++, src += PAGE_SIZE)
m[i] = PHYS_TO_VM_PAGE(src);
return (uiomove_fromphys(m, src & PAGE_MASK, len, &uio));
}
#undef PHYS_PAGE_COUNT
Add asynchronous command support to the pass(4) driver, and the new camdd(8) utility. CCBs may be queued to the driver via the new CAMIOQUEUE ioctl, and completed CCBs may be retrieved via the CAMIOGET ioctl. User processes can use poll(2) or kevent(2) to get notification when I/O has completed. While the existing CAMIOCOMMAND blocking ioctl interface only supports user virtual data pointers in a CCB (generally only one per CCB), the new CAMIOQUEUE ioctl supports user virtual and physical address pointers, as well as user virtual and physical scatter/gather lists. This allows user applications to have more flexibility in their data handling operations. Kernel memory for data transferred via the queued interface is allocated from the zone allocator in MAXPHYS sized chunks, and user data is copied in and out. This is likely faster than the vmapbuf()/vunmapbuf() method used by the CAMIOCOMMAND ioctl in configurations with many processors (there are more TLB shootdowns caused by the mapping/unmapping operation) but may not be as fast as running with unmapped I/O. The new memory handling model for user requests also allows applications to send CCBs with request sizes that are larger than MAXPHYS. The pass(4) driver now limits queued requests to the I/O size listed by the SIM driver in the maxio field in the Path Inquiry (XPT_PATH_INQ) CCB. There are some things things would be good to add: 1. Come up with a way to do unmapped I/O on multiple buffers. Currently the unmapped I/O interface operates on a struct bio, which includes only one address and length. It would be nice to be able to send an unmapped scatter/gather list down to busdma. This would allow eliminating the copy we currently do for data. 2. Add an ioctl to list currently outstanding CCBs in the various queues. 3. Add an ioctl to cancel a request, or use the XPT_ABORT CCB to do that. 4. Test physical address support. Virtual pointers and scatter gather lists have been tested, but I have not yet tested physical addresses or scatter/gather lists. 5. Investigate multiple queue support. At the moment there is one queue of commands per pass(4) device. If multiple processes open the device, they will submit I/O into the same queue and get events for the same completions. This is probably the right model for most applications, but it is something that could be changed later on. Also, add a new utility, camdd(8) that uses the asynchronous pass(4) driver interface. This utility is intended to be a basic data transfer/copy utility, a simple benchmark utility, and an example of how to use the asynchronous pass(4) interface. It can copy data to and from pass(4) devices using any target queue depth, starting offset and blocksize for the input and ouptut devices. It currently only supports SCSI devices, but could be easily extended to support ATA devices. It can also copy data to and from regular files, block devices, tape devices, pipes, stdin, and stdout. It does not support queueing multiple commands to any of those targets, since it uses the standard read(2)/write(2)/writev(2)/readv(2) system calls. The I/O is done by two threads, one for the reader and one for the writer. The reader thread sends completed read requests to the writer thread in strictly sequential order, even if they complete out of order. That could be modified later on for random I/O patterns or slightly out of order I/O. camdd(8) uses kqueue(2)/kevent(2) to get I/O completion events from the pass(4) driver and also to send request notifications internally. For pass(4) devcies, camdd(8) uses a single buffer (CAM_DATA_VADDR) per CAM CCB on the reading side, and a scatter/gather list (CAM_DATA_SG) on the writing side. In addition to testing both interfaces, this makes any potential reblocking of I/O easier. No data is copied between the reader and the writer, but rather the reader's buffers are split into multiple I/O requests or combined into a single I/O request depending on the input and output blocksize. For the file I/O path, camdd(8) also uses a single buffer (read(2), write(2), pread(2) or pwrite(2)) on reads, and a scatter/gather list (readv(2), writev(2), preadv(2), pwritev(2)) on writes. Things that would be nice to do for camdd(8) eventually: 1. Add support for I/O pattern generation. Patterns like all zeros, all ones, LBA-based patterns, random patterns, etc. Right Now you can always use /dev/zero, /dev/random, etc. 2. Add support for a "sink" mode, so we do only reads with no writes. Right now, you can use /dev/null. 3. Add support for automatic queue depth probing, so that we can figure out the right queue depth on the input and output side for maximum throughput. At the moment it defaults to 6. 4. Add support for SATA device passthrough I/O. 5. Add support for random LBAs and/or lengths on the input and output sides. 6. Track average per-I/O latency and busy time. The busy time and latency could also feed in to the automatic queue depth determination. sys/cam/scsi/scsi_pass.h: Define two new ioctls, CAMIOQUEUE and CAMIOGET, that queue and fetch asynchronous CAM CCBs respectively. Although these ioctls do not have a declared argument, they both take a union ccb pointer. If we declare a size here, the ioctl code in sys/kern/sys_generic.c will malloc and free a buffer for either the CCB or the CCB pointer (depending on how it is declared). Since we have to keep a copy of the CCB (which is fairly large) anyway, having the ioctl malloc and free a CCB for each call is wasteful. sys/cam/scsi/scsi_pass.c: Add asynchronous CCB support. Add two new ioctls, CAMIOQUEUE and CAMIOGET. CAMIOQUEUE adds a CCB to the incoming queue. The CCB is executed immediately (and moved to the active queue) if it is an immediate CCB, but otherwise it will be executed in passstart() when a CCB is available from the transport layer. When CCBs are completed (because they are immediate or passdone() if they are queued), they are put on the done queue. If we get the final close on the device before all pending I/O is complete, all active I/O is moved to the abandoned queue and we increment the peripheral reference count so that the peripheral driver instance doesn't go away before all pending I/O is done. The new passcreatezone() function is called on the first call to the CAMIOQUEUE ioctl on a given device to allocate the UMA zones for I/O requests and S/G list buffers. This may be good to move off to a taskqueue at some point. The new passmemsetup() function allocates memory and scatter/gather lists to hold the user's data, and copies in any data that needs to be written. For virtual pointers (CAM_DATA_VADDR), the kernel buffer is malloced from the new pass(4) driver malloc bucket. For virtual scatter/gather lists (CAM_DATA_SG), buffers are allocated from a new per-pass(9) UMA zone in MAXPHYS-sized chunks. Physical pointers are passed in unchanged. We have support for up to 16 scatter/gather segments (for the user and kernel S/G lists) in the default struct pass_io_req, so requests with longer S/G lists require an extra kernel malloc. The new passcopysglist() function copies a user scatter/gather list to a kernel scatter/gather list. The number of elements in each list may be different, but (obviously) the amount of data stored has to be identical. The new passmemdone() function copies data out for the CAM_DATA_VADDR and CAM_DATA_SG cases. The new passiocleanup() function restores data pointers in user CCBs and frees memory. Add new functions to support kqueue(2)/kevent(2): passreadfilt() tells kevent whether or not the done queue is empty. passkqfilter() adds a knote to our list. passreadfiltdetach() removes a knote from our list. Add a new function, passpoll(), for poll(2)/select(2) to use. Add devstat(9) support for the queued CCB path. sys/cam/ata/ata_da.c: Add support for the BIO_VLIST bio type. sys/cam/cam_ccb.h: Add a new enumeration for the xflags field in the CCB header. (This doesn't change the CCB header, just adds an enumeration to use.) sys/cam/cam_xpt.c: Add a new function, xpt_setup_ccb_flags(), that allows specifying CCB flags. sys/cam/cam_xpt.h: Add a prototype for xpt_setup_ccb_flags(). sys/cam/scsi/scsi_da.c: Add support for BIO_VLIST. sys/dev/md/md.c: Add BIO_VLIST support to md(4). sys/geom/geom_disk.c: Add BIO_VLIST support to the GEOM disk class. Re-factor the I/O size limiting code in g_disk_start() a bit. sys/kern/subr_bus_dma.c: Change _bus_dmamap_load_vlist() to take a starting offset and length. Add a new function, _bus_dmamap_load_pages(), that will load a list of physical pages starting at an offset. Update _bus_dmamap_load_bio() to allow loading BIO_VLIST bios. Allow unmapped I/O to start at an offset. sys/kern/subr_uio.c: Add two new functions, physcopyin_vlist() and physcopyout_vlist(). sys/pc98/include/bus.h: Guard kernel-only parts of the pc98 machine/bus.h header with #ifdef _KERNEL. This allows userland programs to include <machine/bus.h> to get the definition of bus_addr_t and bus_size_t. sys/sys/bio.h: Add a new bio flag, BIO_VLIST. sys/sys/uio.h: Add prototypes for physcopyin_vlist() and physcopyout_vlist(). share/man/man4/pass.4: Document the CAMIOQUEUE and CAMIOGET ioctls. usr.sbin/Makefile: Add camdd. usr.sbin/camdd/Makefile: Add a makefile for camdd(8). usr.sbin/camdd/camdd.8: Man page for camdd(8). usr.sbin/camdd/camdd.c: The new camdd(8) utility. Sponsored by: Spectra Logic MFC after: 1 week
2015-12-03 20:54:55 +00:00
int
physcopyin_vlist(bus_dma_segment_t *src, off_t offset, vm_paddr_t dst,
size_t len)
{
size_t seg_len;
int error;
error = 0;
while (offset >= src->ds_len) {
offset -= src->ds_len;
src++;
}
while (len > 0 && error == 0) {
seg_len = MIN(src->ds_len - offset, len);
error = physcopyin((void *)(uintptr_t)(src->ds_addr + offset),
dst, seg_len);
offset = 0;
src++;
len -= seg_len;
dst += seg_len;
}
return (error);
}
int
physcopyout_vlist(vm_paddr_t src, bus_dma_segment_t *dst, off_t offset,
size_t len)
{
size_t seg_len;
int error;
error = 0;
while (offset >= dst->ds_len) {
offset -= dst->ds_len;
dst++;
}
while (len > 0 && error == 0) {
seg_len = MIN(dst->ds_len - offset, len);
error = physcopyout(src, (void *)(uintptr_t)(dst->ds_addr +
offset), seg_len);
offset = 0;
dst++;
len -= seg_len;
src += seg_len;
}
return (error);
}
int
uiomove(void *cp, int n, struct uio *uio)
1994-05-24 10:09:53 +00:00
{
return (uiomove_faultflag(cp, n, uio, 0));
}
int
uiomove_nofault(void *cp, int n, struct uio *uio)
{
return (uiomove_faultflag(cp, n, uio, 1));
}
static int
uiomove_faultflag(void *cp, int n, struct uio *uio, int nofault)
{
struct iovec *iov;
size_t cnt;
int error, newflags, save;
save = error = 0;
1994-05-24 10:09:53 +00:00
KASSERT(uio->uio_rw == UIO_READ || uio->uio_rw == UIO_WRITE,
1999-01-10 01:58:29 +00:00
("uiomove: mode"));
KASSERT(uio->uio_segflg != UIO_USERSPACE || uio->uio_td == curthread,
1999-01-10 01:58:29 +00:00
("uiomove proc"));
if (uio->uio_segflg == UIO_USERSPACE) {
newflags = TDP_DEADLKTREAT;
if (nofault) {
/*
* Fail if a non-spurious page fault occurs.
*/
newflags |= TDP_NOFAULTING | TDP_RESETSPUR;
} else {
WITNESS_WARN(WARN_GIANTOK | WARN_SLEEPOK, NULL,
"Calling uiomove()");
}
save = curthread_pflags_set(newflags);
} else {
KASSERT(nofault == 0, ("uiomove: nofault"));
}
1994-05-24 10:09:53 +00:00
while (n > 0 && uio->uio_resid) {
iov = uio->uio_iov;
cnt = iov->iov_len;
if (cnt == 0) {
uio->uio_iov++;
uio->uio_iovcnt--;
continue;
}
if (cnt > n)
cnt = n;
1995-02-12 09:11:47 +00:00
1994-05-24 10:09:53 +00:00
switch (uio->uio_segflg) {
case UIO_USERSPACE:
maybe_yield();
1994-05-24 10:09:53 +00:00
if (uio->uio_rw == UIO_READ)
error = copyout(cp, iov->iov_base, cnt);
else
error = copyin(iov->iov_base, cp, cnt);
if (error)
goto out;
1994-05-24 10:09:53 +00:00
break;
case UIO_SYSSPACE:
if (uio->uio_rw == UIO_READ)
bcopy(cp, iov->iov_base, cnt);
1994-05-24 10:09:53 +00:00
else
bcopy(iov->iov_base, cp, cnt);
break;
case UIO_NOCOPY:
break;
}
iov->iov_base = (char *)iov->iov_base + cnt;
iov->iov_len -= cnt;
uio->uio_resid -= cnt;
uio->uio_offset += cnt;
cp = (char *)cp + cnt;
n -= cnt;
}
out:
if (save)
curthread_pflags_restore(save);
return (error);
}
/*
* Wrapper for uiomove() that validates the arguments against a known-good
* kernel buffer. Currently, uiomove accepts a signed (n) argument, which
* is almost definitely a bad thing, so we catch that here as well. We
* return a runtime failure, but it might be desirable to generate a runtime
* assertion failure instead.
*/
int
uiomove_frombuf(void *buf, int buflen, struct uio *uio)
{
size_t offset, n;
if (uio->uio_offset < 0 || uio->uio_resid < 0 ||
(offset = uio->uio_offset) != uio->uio_offset)
return (EINVAL);
if (buflen <= 0 || offset >= buflen)
return (0);
if ((n = buflen - offset) > IOSIZE_MAX)
return (EINVAL);
return (uiomove((char *)buf + offset, n, uio));
}
1994-05-24 10:09:53 +00:00
/*
* Give next character to user as result of read.
*/
int
ureadc(int c, struct uio *uio)
1994-05-24 10:09:53 +00:00
{
struct iovec *iov;
char *iov_base;
1994-05-24 10:09:53 +00:00
WITNESS_WARN(WARN_GIANTOK | WARN_SLEEPOK, NULL,
"Calling ureadc()");
1994-05-24 10:09:53 +00:00
again:
if (uio->uio_iovcnt == 0 || uio->uio_resid == 0)
panic("ureadc");
iov = uio->uio_iov;
if (iov->iov_len == 0) {
uio->uio_iovcnt--;
uio->uio_iov++;
goto again;
}
switch (uio->uio_segflg) {
case UIO_USERSPACE:
if (subyte(iov->iov_base, c) < 0)
return (EFAULT);
break;
case UIO_SYSSPACE:
iov_base = iov->iov_base;
*iov_base = c;
1994-05-24 10:09:53 +00:00
break;
case UIO_NOCOPY:
break;
1994-05-24 10:09:53 +00:00
}
iov->iov_base = (char *)iov->iov_base + 1;
1994-05-24 10:09:53 +00:00
iov->iov_len--;
uio->uio_resid--;
uio->uio_offset++;
return (0);
}
int
copyinfrom(const void * __restrict src, void * __restrict dst, size_t len,
int seg)
{
int error = 0;
switch (seg) {
case UIO_USERSPACE:
error = copyin(src, dst, len);
break;
case UIO_SYSSPACE:
bcopy(src, dst, len);
break;
default:
panic("copyinfrom: bad seg %d\n", seg);
}
return (error);
}
int
copyinstrfrom(const void * __restrict src, void * __restrict dst, size_t len,
size_t * __restrict copied, int seg)
{
int error = 0;
switch (seg) {
case UIO_USERSPACE:
error = copyinstr(src, dst, len, copied);
break;
case UIO_SYSSPACE:
error = copystr(src, dst, len, copied);
break;
default:
panic("copyinstrfrom: bad seg %d\n", seg);
}
return (error);
}
int
copyiniov(const struct iovec *iovp, u_int iovcnt, struct iovec **iov, int error)
{
u_int iovlen;
*iov = NULL;
if (iovcnt > UIO_MAXIOV)
return (error);
iovlen = iovcnt * sizeof (struct iovec);
*iov = malloc(iovlen, M_IOV, M_WAITOK);
error = copyin(iovp, *iov, iovlen);
if (error) {
free(*iov, M_IOV);
*iov = NULL;
}
return (error);
}
int
copyinuio(const struct iovec *iovp, u_int iovcnt, struct uio **uiop)
{
2004-02-04 08:14:47 +00:00
struct iovec *iov;
struct uio *uio;
u_int iovlen;
2004-02-04 08:14:47 +00:00
int error, i;
*uiop = NULL;
if (iovcnt > UIO_MAXIOV)
return (EINVAL);
2004-02-04 08:14:47 +00:00
iovlen = iovcnt * sizeof (struct iovec);
uio = malloc(iovlen + sizeof *uio, M_IOV, M_WAITOK);
iov = (struct iovec *)(uio + 1);
error = copyin(iovp, iov, iovlen);
if (error) {
free(uio, M_IOV);
return (error);
2004-02-04 08:14:47 +00:00
}
uio->uio_iov = iov;
uio->uio_iovcnt = iovcnt;
uio->uio_segflg = UIO_USERSPACE;
uio->uio_offset = -1;
uio->uio_resid = 0;
for (i = 0; i < iovcnt; i++) {
if (iov->iov_len > IOSIZE_MAX - uio->uio_resid) {
free(uio, M_IOV);
return (EINVAL);
2004-02-04 08:14:47 +00:00
}
uio->uio_resid += iov->iov_len;
iov++;
}
*uiop = uio;
return (0);
}
struct uio *
cloneuio(struct uio *uiop)
{
struct uio *uio;
int iovlen;
iovlen = uiop->uio_iovcnt * sizeof (struct iovec);
uio = malloc(iovlen + sizeof *uio, M_IOV, M_WAITOK);
*uio = *uiop;
uio->uio_iov = (struct iovec *)(uio + 1);
bcopy(uiop->uio_iov, uio->uio_iov, iovlen);
return (uio);
}
/*
* Map some anonymous memory in user space of size sz, rounded up to the page
* boundary.
*/
int
copyout_map(struct thread *td, vm_offset_t *addr, size_t sz)
{
struct vmspace *vms;
int error;
vm_size_t size;
vms = td->td_proc->p_vmspace;
/*
* Map somewhere after heap in process memory.
*/
*addr = round_page((vm_offset_t)vms->vm_daddr +
lim_max(td, RLIMIT_DATA));
/* round size up to page boundary */
size = (vm_size_t)round_page(sz);
if (size == 0)
return (EINVAL);
error = vm_mmap_object(&vms->vm_map, addr, size, VM_PROT_READ |
VM_PROT_WRITE, VM_PROT_ALL, MAP_PRIVATE | MAP_ANON, NULL, 0,
FALSE, td);
return (error);
}
/*
* Unmap memory in user space.
*/
int
copyout_unmap(struct thread *td, vm_offset_t addr, size_t sz)
{
vm_map_t map;
vm_size_t size;
if (sz == 0)
return (0);
map = &td->td_proc->p_vmspace->vm_map;
size = (vm_size_t)round_page(sz);
if (vm_map_remove(map, addr, addr + size) != KERN_SUCCESS)
return (EINVAL);
return (0);
}
#ifdef NO_FUEWORD
/*
* XXXKIB The temporal implementation of fue*() functions which do not
* handle usermode -1 properly, mixing it with the fault code. Keep
* this until MD code is written. Currently sparc64 does not have a
* proper implementation.
*/
int
fueword(volatile const void *base, long *val)
{
long res;
res = fuword(base);
if (res == -1)
return (-1);
*val = res;
return (0);
}
int
fueword32(volatile const void *base, int32_t *val)
{
int32_t res;
res = fuword32(base);
if (res == -1)
return (-1);
*val = res;
return (0);
}
#ifdef _LP64
int
fueword64(volatile const void *base, int64_t *val)
{
int64_t res;
res = fuword64(base);
if (res == -1)
return (-1);
*val = res;
return (0);
}
#endif
int
casueword32(volatile uint32_t *base, uint32_t oldval, uint32_t *oldvalp,
uint32_t newval)
{
int32_t ov;
ov = casuword32(base, oldval, newval);
if (ov == -1)
return (-1);
*oldvalp = ov;
return (0);
}
int
casueword(volatile u_long *p, u_long oldval, u_long *oldvalp, u_long newval)
{
u_long ov;
ov = casuword(p, oldval, newval);
if (ov == -1)
return (-1);
*oldvalp = ov;
return (0);
}
#else /* NO_FUEWORD */
int32_t
fuword32(volatile const void *addr)
{
int rv;
int32_t val;
rv = fueword32(addr, &val);
return (rv == -1 ? -1 : val);
}
#ifdef _LP64
int64_t
fuword64(volatile const void *addr)
{
int rv;
int64_t val;
rv = fueword64(addr, &val);
return (rv == -1 ? -1 : val);
}
#endif /* _LP64 */
long
fuword(volatile const void *addr)
{
long val;
int rv;
rv = fueword(addr, &val);
return (rv == -1 ? -1 : val);
}
uint32_t
casuword32(volatile uint32_t *addr, uint32_t old, uint32_t new)
{
int rv;
uint32_t val;
rv = casueword32(addr, old, &val, new);
return (rv == -1 ? -1 : val);
}
u_long
casuword(volatile u_long *addr, u_long old, u_long new)
{
int rv;
u_long val;
rv = casueword(addr, old, &val, new);
return (rv == -1 ? -1 : val);
}
#endif /* NO_FUEWORD */