freebsd-skq/sys/geom/geom.h

417 lines
13 KiB
C
Raw Normal View History

/*-
* Copyright (c) 2002 Poul-Henning Kamp
* Copyright (c) 2002 Networks Associates Technology, Inc.
* All rights reserved.
*
* This software was developed for the FreeBSD Project by Poul-Henning Kamp
* and NAI Labs, the Security Research Division of Network Associates, Inc.
* under DARPA/SPAWAR contract N66001-01-C-8035 ("CBOSS"), as part of the
* DARPA CHATS research program.
*
* 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. The names of the authors may not be used to endorse or promote
* products derived from this software without specific prior written
* permission.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR 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 AUTHOR 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.
*
* $FreeBSD$
*/
#ifndef _GEOM_GEOM_H_
#define _GEOM_GEOM_H_
#include <sys/lock.h>
#include <sys/mutex.h>
#include <sys/sx.h>
#include <sys/queue.h>
#include <sys/ioccom.h>
#include <sys/conf.h>
#include <sys/module.h>
struct g_class;
struct g_geom;
struct g_consumer;
struct g_provider;
struct g_stat;
struct thread;
struct bio;
struct sbuf;
struct gctl_req;
struct g_configargs;
typedef int g_config_t (struct g_configargs *ca);
typedef void g_ctl_req_t (struct gctl_req *, struct g_class *cp, char const *verb);
typedef int g_ctl_create_geom_t (struct gctl_req *, struct g_class *cp, struct g_provider *pp);
typedef int g_ctl_destroy_geom_t (struct gctl_req *, struct g_class *cp, struct g_geom *gp);
typedef int g_ctl_config_geom_t (struct gctl_req *, struct g_geom *gp, const char *verb);
typedef void g_init_t (struct g_class *mp);
typedef void g_fini_t (struct g_class *mp);
typedef struct g_geom * g_taste_t (struct g_class *, struct g_provider *, int flags);
typedef int g_ioctl_t(struct g_provider *pp, u_long cmd, void *data, int fflag, struct thread *td);
#define G_TF_NORMAL 0
#define G_TF_INSIST 1
#define G_TF_TRANSPARENT 2
typedef int g_access_t (struct g_provider *, int, int, int);
/* XXX: not sure about the thread arg */
typedef void g_orphan_t (struct g_consumer *);
typedef void g_start_t (struct bio *);
typedef void g_spoiled_t (struct g_consumer *);
Plumb device physical path reporting from CAM devices, through GEOM and DEVFS, and make it accessible via the diskinfo utility. Extend GEOM's generic attribute query mechanism into generic disk consumers. sys/geom/geom_disk.c: sys/geom/geom_disk.h: sys/cam/scsi/scsi_da.c: sys/cam/ata/ata_da.c: - Allow disk providers to implement a new method which can override the default BIO_GETATTR response, d_getattr(struct bio *). This function returns -1 if not handled, otherwise it returns 0 or an errno to be passed to g_io_deliver(). sys/cam/scsi/scsi_da.c: sys/cam/ata/ata_da.c: - Don't copy the serial number to dp->d_ident anymore, as the CAM XPT is now responsible for returning this information via d_getattr()->(a)dagetattr()->xpt_getatr(). sys/geom/geom_dev.c: - Implement a new ioctl, DIOCGPHYSPATH, which returns the GEOM attribute "GEOM::physpath", if possible. If the attribute request returns a zero-length string, ENOENT is returned. usr.sbin/diskinfo/diskinfo.c: - If the DIOCGPHYSPATH ioctl is successful, report physical path data when diskinfo is executed with the '-v' option. Submitted by: will Reviewed by: gibbs Sponsored by: Spectra Logic Corporation Add generic attribute change notification support to GEOM. sys/sys/geom/geom.h: Add a new attrchanged method field to both g_class and g_geom. sys/sys/geom/geom.h: sys/geom/geom_event.c: - Provide the g_attr_changed() function that providers can use to advertise attribute changes. - Perform delivery of attribute change notifications from a thread context via the standard GEOM event mechanism. sys/geom/geom_subr.c: Inherit the attrchanged method from class to geom (class instance). sys/geom/geom_disk.c: Provide disk_attr_changed() to provide g_attr_changed() access to consumers of the disk API. sys/cam/scsi/scsi_pass.c: sys/cam/scsi/scsi_da.c: sys/geom/geom_dev.c: sys/geom/geom_disk.c: Use attribute changed events to track updates to physical path information. sys/cam/scsi/scsi_da.c: Add AC_ADVINFO_CHANGED to the registered asynchronous CAM events for this driver. When this event occurs, and the updated buffer type references our physical path attribute, emit a GEOM attribute changed event via the disk_attr_changed() API. sys/cam/scsi/scsi_pass.c: Add AC_ADVINFO_CHANGED to the registered asynchronous CAM events for this driver. When this event occurs, update the physical patch devfs alias for this pass instance. Submitted by: gibbs Sponsored by: Spectra Logic Corporation
2011-06-14 17:10:32 +00:00
typedef void g_attrchanged_t (struct g_consumer *, const char *attr);
Fix a bug which causes a panic in daopen(). The panic is caused by a da(4) instance going away while GEOM is still probing it. In this case, the GEOM disk class instance has been created by disk_create(), and the taste of the disk is queued in the GEOM event queue. While that event is queued, the da(4) instance goes away. When the open call comes into the da(4) driver, it dereferences the freed (but non-NULL) peripheral pointer provided by GEOM, which results in a panic. The solution is to add a callback to the GEOM disk code that is called when all of its resources are cleaned up. This is implemented inside GEOM by adding an optional callback that is called when all consumers have detached from a provider, and the provider is about to be deleted. scsi_cd.c, scsi_da.c: In the register routine for the cd(4) and da(4) routines, acquire a reference to the CAM peripheral instance just before we call disk_create(). Use the new GEOM disk d_gone() callback to register a callback (dadiskgonecb()/cddiskgonecb()) that decrements the peripheral reference count once GEOM has finished cleaning up its resources. In the cd(4) driver, clean up open and close behavior slightly. GEOM makes sure we only get one open() and one close call, so there is no need to set an open flag and decrement the reference count if we are not the first open. In the cd(4) driver, use cam_periph_release_locked() in a couple of error scenarios to avoid extra mutex calls. geom.h: Add a new, optional, providergone callback that is called when a provider is about to be deleted. geom_disk.h: Add a new d_gone() callback to the GEOM disk interface. Bump the DISK_VERSION to version 2. This probably should have been done after a couple of previous changes, especially the addition of the d_getattr() callback. geom_disk.c: Add a providergone callback for the disk class, g_disk_providergone(), that calls the user's d_gone() callback if it exists. Bump the DISK_VERSION to 2. geom_subr.c: In g_destroy_provider(), call the providergone callback if it has been provided. In g_new_geomf(), propagate the class's providergone callback to the new geom instance. blkfront.c: Callers of disk_create() are supposed to pass in DISK_VERSION, not an explicit disk API version number. Update the blkfront driver to do that. disk.9: Update the disk(9) man page to include information on the new d_gone() callback, as well as the previously added d_getattr() callback, d_descr field, and HBA PCI ID fields. MFC after: 5 days
2012-06-24 04:29:03 +00:00
typedef void g_provgone_t (struct g_provider *);
typedef void g_dumpconf_t (struct sbuf *, const char *indent, struct g_geom *,
struct g_consumer *, struct g_provider *);
typedef void g_resize_t(struct g_consumer *cp);
/*
* The g_class structure describes a transformation class. In other words
* all BSD disklabel handlers share one g_class, all MBR handlers share
* one common g_class and so on.
* Certain operations are instantiated on the class, most notably the
* taste and config_geom functions.
*/
struct g_class {
const char *name;
u_int version;
u_int spare0;
g_taste_t *taste;
g_config_t *config;
g_ctl_req_t *ctlreq;
g_init_t *init;
g_fini_t *fini;
g_ctl_destroy_geom_t *destroy_geom;
/*
2005-09-03 11:03:10 +00:00
* Default values for geom methods
*/
g_start_t *start;
g_spoiled_t *spoiled;
Plumb device physical path reporting from CAM devices, through GEOM and DEVFS, and make it accessible via the diskinfo utility. Extend GEOM's generic attribute query mechanism into generic disk consumers. sys/geom/geom_disk.c: sys/geom/geom_disk.h: sys/cam/scsi/scsi_da.c: sys/cam/ata/ata_da.c: - Allow disk providers to implement a new method which can override the default BIO_GETATTR response, d_getattr(struct bio *). This function returns -1 if not handled, otherwise it returns 0 or an errno to be passed to g_io_deliver(). sys/cam/scsi/scsi_da.c: sys/cam/ata/ata_da.c: - Don't copy the serial number to dp->d_ident anymore, as the CAM XPT is now responsible for returning this information via d_getattr()->(a)dagetattr()->xpt_getatr(). sys/geom/geom_dev.c: - Implement a new ioctl, DIOCGPHYSPATH, which returns the GEOM attribute "GEOM::physpath", if possible. If the attribute request returns a zero-length string, ENOENT is returned. usr.sbin/diskinfo/diskinfo.c: - If the DIOCGPHYSPATH ioctl is successful, report physical path data when diskinfo is executed with the '-v' option. Submitted by: will Reviewed by: gibbs Sponsored by: Spectra Logic Corporation Add generic attribute change notification support to GEOM. sys/sys/geom/geom.h: Add a new attrchanged method field to both g_class and g_geom. sys/sys/geom/geom.h: sys/geom/geom_event.c: - Provide the g_attr_changed() function that providers can use to advertise attribute changes. - Perform delivery of attribute change notifications from a thread context via the standard GEOM event mechanism. sys/geom/geom_subr.c: Inherit the attrchanged method from class to geom (class instance). sys/geom/geom_disk.c: Provide disk_attr_changed() to provide g_attr_changed() access to consumers of the disk API. sys/cam/scsi/scsi_pass.c: sys/cam/scsi/scsi_da.c: sys/geom/geom_dev.c: sys/geom/geom_disk.c: Use attribute changed events to track updates to physical path information. sys/cam/scsi/scsi_da.c: Add AC_ADVINFO_CHANGED to the registered asynchronous CAM events for this driver. When this event occurs, and the updated buffer type references our physical path attribute, emit a GEOM attribute changed event via the disk_attr_changed() API. sys/cam/scsi/scsi_pass.c: Add AC_ADVINFO_CHANGED to the registered asynchronous CAM events for this driver. When this event occurs, update the physical patch devfs alias for this pass instance. Submitted by: gibbs Sponsored by: Spectra Logic Corporation
2011-06-14 17:10:32 +00:00
g_attrchanged_t *attrchanged;
g_dumpconf_t *dumpconf;
g_access_t *access;
g_orphan_t *orphan;
g_ioctl_t *ioctl;
g_provgone_t *providergone;
g_resize_t *resize;
void *spare1;
void *spare2;
/*
* The remaining elements are private
*/
LIST_ENTRY(g_class) class;
LIST_HEAD(,g_geom) geom;
};
#define G_VERSION_00 0x19950323
#define G_VERSION_01 0x20041207 /* add fflag to g_ioctl_t */
#define G_VERSION G_VERSION_01
/*
* The g_geom is an instance of a g_class.
*/
struct g_geom {
char *name;
struct g_class *class;
LIST_ENTRY(g_geom) geom;
LIST_HEAD(,g_consumer) consumer;
LIST_HEAD(,g_provider) provider;
TAILQ_ENTRY(g_geom) geoms; /* XXX: better name */
int rank;
g_start_t *start;
g_spoiled_t *spoiled;
Plumb device physical path reporting from CAM devices, through GEOM and DEVFS, and make it accessible via the diskinfo utility. Extend GEOM's generic attribute query mechanism into generic disk consumers. sys/geom/geom_disk.c: sys/geom/geom_disk.h: sys/cam/scsi/scsi_da.c: sys/cam/ata/ata_da.c: - Allow disk providers to implement a new method which can override the default BIO_GETATTR response, d_getattr(struct bio *). This function returns -1 if not handled, otherwise it returns 0 or an errno to be passed to g_io_deliver(). sys/cam/scsi/scsi_da.c: sys/cam/ata/ata_da.c: - Don't copy the serial number to dp->d_ident anymore, as the CAM XPT is now responsible for returning this information via d_getattr()->(a)dagetattr()->xpt_getatr(). sys/geom/geom_dev.c: - Implement a new ioctl, DIOCGPHYSPATH, which returns the GEOM attribute "GEOM::physpath", if possible. If the attribute request returns a zero-length string, ENOENT is returned. usr.sbin/diskinfo/diskinfo.c: - If the DIOCGPHYSPATH ioctl is successful, report physical path data when diskinfo is executed with the '-v' option. Submitted by: will Reviewed by: gibbs Sponsored by: Spectra Logic Corporation Add generic attribute change notification support to GEOM. sys/sys/geom/geom.h: Add a new attrchanged method field to both g_class and g_geom. sys/sys/geom/geom.h: sys/geom/geom_event.c: - Provide the g_attr_changed() function that providers can use to advertise attribute changes. - Perform delivery of attribute change notifications from a thread context via the standard GEOM event mechanism. sys/geom/geom_subr.c: Inherit the attrchanged method from class to geom (class instance). sys/geom/geom_disk.c: Provide disk_attr_changed() to provide g_attr_changed() access to consumers of the disk API. sys/cam/scsi/scsi_pass.c: sys/cam/scsi/scsi_da.c: sys/geom/geom_dev.c: sys/geom/geom_disk.c: Use attribute changed events to track updates to physical path information. sys/cam/scsi/scsi_da.c: Add AC_ADVINFO_CHANGED to the registered asynchronous CAM events for this driver. When this event occurs, and the updated buffer type references our physical path attribute, emit a GEOM attribute changed event via the disk_attr_changed() API. sys/cam/scsi/scsi_pass.c: Add AC_ADVINFO_CHANGED to the registered asynchronous CAM events for this driver. When this event occurs, update the physical patch devfs alias for this pass instance. Submitted by: gibbs Sponsored by: Spectra Logic Corporation
2011-06-14 17:10:32 +00:00
g_attrchanged_t *attrchanged;
g_dumpconf_t *dumpconf;
g_access_t *access;
g_orphan_t *orphan;
g_ioctl_t *ioctl;
g_provgone_t *providergone;
g_resize_t *resize;
void *spare0;
void *spare1;
void *softc;
unsigned flags;
#define G_GEOM_WITHER 1
#define G_GEOM_VOLATILE_BIO 2
};
/*
* The g_bioq is a queue of struct bio's.
* XXX: possibly collection point for statistics.
* XXX: should (possibly) be collapsed with sys/bio.h::bio_queue_head.
*/
struct g_bioq {
TAILQ_HEAD(, bio) bio_queue;
struct mtx bio_queue_lock;
int bio_queue_length;
};
/*
* A g_consumer is an attachment point for a g_provider. One g_consumer
* can only be attached to one g_provider, but multiple g_consumers
* can be attached to one g_provider.
*/
struct g_consumer {
struct g_geom *geom;
LIST_ENTRY(g_consumer) consumer;
struct g_provider *provider;
LIST_ENTRY(g_consumer) consumers; /* XXX: better name */
int acr, acw, ace;
Implement media change notification for DA and CD removable media devices. It includes three parts: 1) Modifications to CAM to detect media media changes and report them to disk(9) layer. For modern SATA (and potentially UAS) devices it utilizes Asynchronous Notification mechanism to receive events from hardware. Active polling with TEST UNIT READY commands with 3 seconds period is used for incapable hardware. After that both CD and DA drivers work the same way, detecting two conditions: "NOT READY: Medium not present" after medium was detected previously, and "UNIT ATTENTION: Not ready to ready change, medium may have changed". First one reported to disk(9) as media removal, second as media insert/change. To reliably receive second event new AC_UNIT_ATTENTION async added to make UAs broadcasted to all periphs by generic error handling code in cam_periph_error(). 2) Modifications to GEOM core to handle media remove and change events. Media removal handled by spoiling all consumers attached to the provider. Media change event also schedules provider retaste after spoiling to probe new media. New flag G_CF_ORPHAN was added to consumers to reflect that consumer is in process of destruction. It allows retaste to create new geom instance of the same class, while previous one is still dying. 3) Modifications to some GEOM classes: DEV -- to report media change events to devd; VFS -- to handle spoiling same as orphan to prevent accessing replaced media. PART class already handles spoiling alike to orphan. Reviewed by: silence on geom@ and scsi@ Tested by: avg Sponsored by: iXsystems, Inc. / PC-BSD MFC after: 2 months
2012-07-29 11:51:48 +00:00
int flags;
#define G_CF_SPOILED 0x1
#define G_CF_ORPHAN 0x4
Merge GEOM direct dispatch changes from the projects/camlock branch. When safety requirements are met, it allows to avoid passing I/O requests to GEOM g_up/g_down thread, executing them directly in the caller context. That allows to avoid CPU bottlenecks in g_up/g_down threads, plus avoid several context switches per I/O. The defined now safety requirements are: - caller should not hold any locks and should be reenterable; - callee should not depend on GEOM dual-threaded concurency semantics; - on the way down, if request is unmapped while callee doesn't support it, the context should be sleepable; - kernel thread stack usage should be below 50%. To keep compatibility with GEOM classes not meeting above requirements new provider and consumer flags added: - G_CF_DIRECT_SEND -- consumer code meets caller requirements (request); - G_CF_DIRECT_RECEIVE -- consumer code meets callee requirements (done); - G_PF_DIRECT_SEND -- provider code meets caller requirements (done); - G_PF_DIRECT_RECEIVE -- provider code meets callee requirements (request). Capable GEOM class can set them, allowing direct dispatch in cases where it is safe. If any of requirements are not met, request is queued to g_up or g_down thread same as before. Such GEOM classes were reviewed and updated to support direct dispatch: CONCAT, DEV, DISK, GATE, MD, MIRROR, MULTIPATH, NOP, PART, RAID, STRIPE, VFS, ZERO, ZFS::VDEV, ZFS::ZVOL, all classes based on g_slice KPI (LABEL, MAP, FLASHMAP, etc). To declare direct completion capability disk(9) KPI got new flag equivalent to G_PF_DIRECT_SEND -- DISKFLAG_DIRECT_COMPLETION. da(4) and ada(4) disk drivers got it set now thanks to earlier CAM locking work. This change more then twice increases peak block storage performance on systems with manu CPUs, together with earlier CAM locking changes reaching more then 1 million IOPS (512 byte raw reads from 16 SATA SSDs on 4 HBAs to 256 user-level threads). Sponsored by: iXsystems, Inc. MFC after: 2 months
2013-10-22 08:22:19 +00:00
#define G_CF_DIRECT_SEND 0x10
#define G_CF_DIRECT_RECEIVE 0x20
struct devstat *stat;
u_int nstart, nend;
/* Two fields for the implementing class to use */
void *private;
u_int index;
};
/*
* A g_provider is a "logical disk".
*/
struct g_provider {
char *name;
LIST_ENTRY(g_provider) provider;
struct g_geom *geom;
LIST_HEAD(,g_consumer) consumers;
int acr, acw, ace;
int error;
TAILQ_ENTRY(g_provider) orphan;
off_t mediasize;
u_int sectorsize;
u_int stripesize;
u_int stripeoffset;
struct devstat *stat;
u_int nstart, nend;
u_int flags;
2003-10-06 09:05:44 +00:00
#define G_PF_WITHER 0x2
#define G_PF_ORPHAN 0x4
Implement the concept of the unmapped VMIO buffers, i.e. buffers which do not map the b_pages pages into buffer_map KVA. The use of the unmapped buffers eliminate the need to perform TLB shootdown for mapping on the buffer creation and reuse, greatly reducing the amount of IPIs for shootdown on big-SMP machines and eliminating up to 25-30% of the system time on i/o intensive workloads. The unmapped buffer should be explicitely requested by the GB_UNMAPPED flag by the consumer. For unmapped buffer, no KVA reservation is performed at all. The consumer might request unmapped buffer which does have a KVA reserve, to manually map it without recursing into buffer cache and blocking, with the GB_KVAALLOC flag. When the mapped buffer is requested and unmapped buffer already exists, the cache performs an upgrade, possibly reusing the KVA reservation. Unmapped buffer is translated into unmapped bio in g_vfs_strategy(). Unmapped bio carry a pointer to the vm_page_t array, offset and length instead of the data pointer. The provider which processes the bio should explicitely specify a readiness to accept unmapped bio, otherwise g_down geom thread performs the transient upgrade of the bio request by mapping the pages into the new bio_transient_map KVA submap. The bio_transient_map submap claims up to 10% of the buffer map, and the total buffer_map + bio_transient_map KVA usage stays the same. Still, it could be manually tuned by kern.bio_transient_maxcnt tunable, in the units of the transient mappings. Eventually, the bio_transient_map could be removed after all geom classes and drivers can accept unmapped i/o requests. Unmapped support can be turned off by the vfs.unmapped_buf_allowed tunable, disabling which makes the buffer (or cluster) creation requests to ignore GB_UNMAPPED and GB_KVAALLOC flags. Unmapped buffers are only enabled by default on the architectures where pmap_copy_page() was implemented and tested. In the rework, filesystem metadata is not the subject to maxbufspace limit anymore. Since the metadata buffers are always mapped, the buffers still have to fit into the buffer map, which provides a reasonable (but practically unreachable) upper bound on it. The non-metadata buffer allocations, both mapped and unmapped, is accounted against maxbufspace, as before. Effectively, this means that the maxbufspace is forced on mapped and unmapped buffers separately. The pre-patch bufspace limiting code did not worked, because buffer_map fragmentation does not allow the limit to be reached. By Jeff Roberson request, the getnewbuf() function was split into smaller single-purpose functions. Sponsored by: The FreeBSD Foundation Discussed with: jeff (previous version) Tested by: pho, scottl (previous version), jhb, bf MFC after: 2 weeks
2013-03-19 14:13:12 +00:00
#define G_PF_ACCEPT_UNMAPPED 0x8
Merge GEOM direct dispatch changes from the projects/camlock branch. When safety requirements are met, it allows to avoid passing I/O requests to GEOM g_up/g_down thread, executing them directly in the caller context. That allows to avoid CPU bottlenecks in g_up/g_down threads, plus avoid several context switches per I/O. The defined now safety requirements are: - caller should not hold any locks and should be reenterable; - callee should not depend on GEOM dual-threaded concurency semantics; - on the way down, if request is unmapped while callee doesn't support it, the context should be sleepable; - kernel thread stack usage should be below 50%. To keep compatibility with GEOM classes not meeting above requirements new provider and consumer flags added: - G_CF_DIRECT_SEND -- consumer code meets caller requirements (request); - G_CF_DIRECT_RECEIVE -- consumer code meets callee requirements (done); - G_PF_DIRECT_SEND -- provider code meets caller requirements (done); - G_PF_DIRECT_RECEIVE -- provider code meets callee requirements (request). Capable GEOM class can set them, allowing direct dispatch in cases where it is safe. If any of requirements are not met, request is queued to g_up or g_down thread same as before. Such GEOM classes were reviewed and updated to support direct dispatch: CONCAT, DEV, DISK, GATE, MD, MIRROR, MULTIPATH, NOP, PART, RAID, STRIPE, VFS, ZERO, ZFS::VDEV, ZFS::ZVOL, all classes based on g_slice KPI (LABEL, MAP, FLASHMAP, etc). To declare direct completion capability disk(9) KPI got new flag equivalent to G_PF_DIRECT_SEND -- DISKFLAG_DIRECT_COMPLETION. da(4) and ada(4) disk drivers got it set now thanks to earlier CAM locking work. This change more then twice increases peak block storage performance on systems with manu CPUs, together with earlier CAM locking changes reaching more then 1 million IOPS (512 byte raw reads from 16 SATA SSDs on 4 HBAs to 256 user-level threads). Sponsored by: iXsystems, Inc. MFC after: 2 months
2013-10-22 08:22:19 +00:00
#define G_PF_DIRECT_SEND 0x10
#define G_PF_DIRECT_RECEIVE 0x20
/* Two fields for the implementing class to use */
void *private;
u_int index;
};
/*
* Descriptor of a classifier. We can register a function and
* an argument, which is called by g_io_request() on bio's
* that are not previously classified.
*/
struct g_classifier_hook {
TAILQ_ENTRY(g_classifier_hook) link;
int (*func)(void *arg, struct bio *bp);
void *arg;
};
/* BIO_GETATTR("GEOM::setstate") argument values. */
#define G_STATE_FAILED 0
#define G_STATE_REBUILD 1
#define G_STATE_RESYNC 2
#define G_STATE_ACTIVE 3
/* geom_dev.c */
struct cdev;
void g_dev_print(void);
Plumb device physical path reporting from CAM devices, through GEOM and DEVFS, and make it accessible via the diskinfo utility. Extend GEOM's generic attribute query mechanism into generic disk consumers. sys/geom/geom_disk.c: sys/geom/geom_disk.h: sys/cam/scsi/scsi_da.c: sys/cam/ata/ata_da.c: - Allow disk providers to implement a new method which can override the default BIO_GETATTR response, d_getattr(struct bio *). This function returns -1 if not handled, otherwise it returns 0 or an errno to be passed to g_io_deliver(). sys/cam/scsi/scsi_da.c: sys/cam/ata/ata_da.c: - Don't copy the serial number to dp->d_ident anymore, as the CAM XPT is now responsible for returning this information via d_getattr()->(a)dagetattr()->xpt_getatr(). sys/geom/geom_dev.c: - Implement a new ioctl, DIOCGPHYSPATH, which returns the GEOM attribute "GEOM::physpath", if possible. If the attribute request returns a zero-length string, ENOENT is returned. usr.sbin/diskinfo/diskinfo.c: - If the DIOCGPHYSPATH ioctl is successful, report physical path data when diskinfo is executed with the '-v' option. Submitted by: will Reviewed by: gibbs Sponsored by: Spectra Logic Corporation Add generic attribute change notification support to GEOM. sys/sys/geom/geom.h: Add a new attrchanged method field to both g_class and g_geom. sys/sys/geom/geom.h: sys/geom/geom_event.c: - Provide the g_attr_changed() function that providers can use to advertise attribute changes. - Perform delivery of attribute change notifications from a thread context via the standard GEOM event mechanism. sys/geom/geom_subr.c: Inherit the attrchanged method from class to geom (class instance). sys/geom/geom_disk.c: Provide disk_attr_changed() to provide g_attr_changed() access to consumers of the disk API. sys/cam/scsi/scsi_pass.c: sys/cam/scsi/scsi_da.c: sys/geom/geom_dev.c: sys/geom/geom_disk.c: Use attribute changed events to track updates to physical path information. sys/cam/scsi/scsi_da.c: Add AC_ADVINFO_CHANGED to the registered asynchronous CAM events for this driver. When this event occurs, and the updated buffer type references our physical path attribute, emit a GEOM attribute changed event via the disk_attr_changed() API. sys/cam/scsi/scsi_pass.c: Add AC_ADVINFO_CHANGED to the registered asynchronous CAM events for this driver. When this event occurs, update the physical patch devfs alias for this pass instance. Submitted by: gibbs Sponsored by: Spectra Logic Corporation
2011-06-14 17:10:32 +00:00
void g_dev_physpath_changed(void);
struct g_provider *g_dev_getprovider(struct cdev *dev);
/* geom_dump.c */
void g_trace(int level, const char *, ...);
# define G_T_TOPOLOGY 1
# define G_T_BIO 2
# define G_T_ACCESS 4
/* geom_event.c */
typedef void g_event_t(void *, int flag);
#define EV_CANCEL 1
int g_post_event(g_event_t *func, void *arg, int flag, ...);
int g_waitfor_event(g_event_t *func, void *arg, int flag, ...);
void g_cancel_event(void *ref);
Plumb device physical path reporting from CAM devices, through GEOM and DEVFS, and make it accessible via the diskinfo utility. Extend GEOM's generic attribute query mechanism into generic disk consumers. sys/geom/geom_disk.c: sys/geom/geom_disk.h: sys/cam/scsi/scsi_da.c: sys/cam/ata/ata_da.c: - Allow disk providers to implement a new method which can override the default BIO_GETATTR response, d_getattr(struct bio *). This function returns -1 if not handled, otherwise it returns 0 or an errno to be passed to g_io_deliver(). sys/cam/scsi/scsi_da.c: sys/cam/ata/ata_da.c: - Don't copy the serial number to dp->d_ident anymore, as the CAM XPT is now responsible for returning this information via d_getattr()->(a)dagetattr()->xpt_getatr(). sys/geom/geom_dev.c: - Implement a new ioctl, DIOCGPHYSPATH, which returns the GEOM attribute "GEOM::physpath", if possible. If the attribute request returns a zero-length string, ENOENT is returned. usr.sbin/diskinfo/diskinfo.c: - If the DIOCGPHYSPATH ioctl is successful, report physical path data when diskinfo is executed with the '-v' option. Submitted by: will Reviewed by: gibbs Sponsored by: Spectra Logic Corporation Add generic attribute change notification support to GEOM. sys/sys/geom/geom.h: Add a new attrchanged method field to both g_class and g_geom. sys/sys/geom/geom.h: sys/geom/geom_event.c: - Provide the g_attr_changed() function that providers can use to advertise attribute changes. - Perform delivery of attribute change notifications from a thread context via the standard GEOM event mechanism. sys/geom/geom_subr.c: Inherit the attrchanged method from class to geom (class instance). sys/geom/geom_disk.c: Provide disk_attr_changed() to provide g_attr_changed() access to consumers of the disk API. sys/cam/scsi/scsi_pass.c: sys/cam/scsi/scsi_da.c: sys/geom/geom_dev.c: sys/geom/geom_disk.c: Use attribute changed events to track updates to physical path information. sys/cam/scsi/scsi_da.c: Add AC_ADVINFO_CHANGED to the registered asynchronous CAM events for this driver. When this event occurs, and the updated buffer type references our physical path attribute, emit a GEOM attribute changed event via the disk_attr_changed() API. sys/cam/scsi/scsi_pass.c: Add AC_ADVINFO_CHANGED to the registered asynchronous CAM events for this driver. When this event occurs, update the physical patch devfs alias for this pass instance. Submitted by: gibbs Sponsored by: Spectra Logic Corporation
2011-06-14 17:10:32 +00:00
int g_attr_changed(struct g_provider *pp, const char *attr, int flag);
Implement media change notification for DA and CD removable media devices. It includes three parts: 1) Modifications to CAM to detect media media changes and report them to disk(9) layer. For modern SATA (and potentially UAS) devices it utilizes Asynchronous Notification mechanism to receive events from hardware. Active polling with TEST UNIT READY commands with 3 seconds period is used for incapable hardware. After that both CD and DA drivers work the same way, detecting two conditions: "NOT READY: Medium not present" after medium was detected previously, and "UNIT ATTENTION: Not ready to ready change, medium may have changed". First one reported to disk(9) as media removal, second as media insert/change. To reliably receive second event new AC_UNIT_ATTENTION async added to make UAs broadcasted to all periphs by generic error handling code in cam_periph_error(). 2) Modifications to GEOM core to handle media remove and change events. Media removal handled by spoiling all consumers attached to the provider. Media change event also schedules provider retaste after spoiling to probe new media. New flag G_CF_ORPHAN was added to consumers to reflect that consumer is in process of destruction. It allows retaste to create new geom instance of the same class, while previous one is still dying. 3) Modifications to some GEOM classes: DEV -- to report media change events to devd; VFS -- to handle spoiling same as orphan to prevent accessing replaced media. PART class already handles spoiling alike to orphan. Reviewed by: silence on geom@ and scsi@ Tested by: avg Sponsored by: iXsystems, Inc. / PC-BSD MFC after: 2 months
2012-07-29 11:51:48 +00:00
int g_media_changed(struct g_provider *pp, int flag);
int g_media_gone(struct g_provider *pp, int flag);
void g_orphan_provider(struct g_provider *pp, int error);
void g_waitidlelock(void);
/* geom_subr.c */
int g_access(struct g_consumer *cp, int nread, int nwrite, int nexcl);
int g_attach(struct g_consumer *cp, struct g_provider *pp);
int g_compare_names(const char *namea, const char *nameb);
void g_destroy_consumer(struct g_consumer *cp);
void g_destroy_geom(struct g_geom *pp);
void g_destroy_provider(struct g_provider *pp);
void g_detach(struct g_consumer *cp);
void g_error_provider(struct g_provider *pp, int error);
struct g_provider *g_provider_by_name(char const *arg);
int g_getattr__(const char *attr, struct g_consumer *cp, void *var, int len);
#define g_getattr(a, c, v) g_getattr__((a), (c), (v), sizeof *(v))
int g_handleattr(struct bio *bp, const char *attribute, const void *val,
int len);
int g_handleattr_int(struct bio *bp, const char *attribute, int val);
int g_handleattr_off_t(struct bio *bp, const char *attribute, off_t val);
Improve ZFS N-way mirror read performance by using load and locality information. The existing algorithm selects a preferred leaf vdev based on offset of the zio request modulo the number of members in the mirror. It assumes the devices are of equal performance and that spreading the requests randomly over both drives will be sufficient to saturate them. In practice this results in the leaf vdevs being under utilized. The new algorithm takes into the following additional factors: * Load of the vdevs (number outstanding I/O requests) * The locality of last queued I/O vs the new I/O request. Within the locality calculation additional knowledge about the underlying vdev is considered such as; is the device backing the vdev a rotating media device. This results in performance increases across the board as well as significant increases for predominantly streaming loads and for configurations which don't have evenly performing devices. The following are results from a setup with 3 Way Mirror with 2 x HD's and 1 x SSD from a basic test running multiple parrallel dd's. With pre-fetch disabled (vfs.zfs.prefetch_disable=1): == Stripe Balanced (default) == Read 15360MB using bs: 1048576, readers: 3, took 161 seconds @ 95 MB/s == Load Balanced (zfslinux) == Read 15360MB using bs: 1048576, readers: 3, took 297 seconds @ 51 MB/s == Load Balanced (locality freebsd) == Read 15360MB using bs: 1048576, readers: 3, took 54 seconds @ 284 MB/s With pre-fetch enabled (vfs.zfs.prefetch_disable=0): == Stripe Balanced (default) == Read 15360MB using bs: 1048576, readers: 3, took 91 seconds @ 168 MB/s == Load Balanced (zfslinux) == Read 15360MB using bs: 1048576, readers: 3, took 108 seconds @ 142 MB/s == Load Balanced (locality freebsd) == Read 15360MB using bs: 1048576, readers: 3, took 48 seconds @ 320 MB/s In addition to the performance changes the code was also restructured, with the help of Justin Gibbs, to provide a more logical flow which also ensures vdevs loads are only calculated from the set of valid candidates. The following additional sysctls where added to allow the administrator to tune the behaviour of the load algorithm: * vfs.zfs.vdev.mirror.rotating_inc * vfs.zfs.vdev.mirror.rotating_seek_inc * vfs.zfs.vdev.mirror.rotating_seek_offset * vfs.zfs.vdev.mirror.non_rotating_inc * vfs.zfs.vdev.mirror.non_rotating_seek_inc These changes where based on work started by the zfsonlinux developers: https://github.com/zfsonlinux/zfs/pull/1487 Reviewed by: gibbs, mav, will MFC after: 2 weeks Sponsored by: Multiplay
2013-10-23 09:54:58 +00:00
int g_handleattr_uint16_t(struct bio *bp, const char *attribute, uint16_t val);
int g_handleattr_str(struct bio *bp, const char *attribute, const char *str);
struct g_consumer * g_new_consumer(struct g_geom *gp);
struct g_geom * g_new_geomf(struct g_class *mp, const char *fmt, ...)
__printflike(2, 3);
struct g_provider * g_new_providerf(struct g_geom *gp, const char *fmt, ...)
__printflike(2, 3);
void g_resize_provider(struct g_provider *pp, off_t size);
int g_retaste(struct g_class *mp);
void g_spoil(struct g_provider *pp, struct g_consumer *cp);
int g_std_access(struct g_provider *pp, int dr, int dw, int de);
void g_std_done(struct bio *bp);
void g_std_spoiled(struct g_consumer *cp);
void g_wither_geom(struct g_geom *gp, int error);
2004-10-29 09:19:03 +00:00
void g_wither_geom_close(struct g_geom *gp, int error);
void g_wither_provider(struct g_provider *pp, int error);
#if defined(DIAGNOSTIC) || defined(DDB)
int g_valid_obj(void const *ptr);
#endif
#ifdef DIAGNOSTIC
#define G_VALID_CLASS(foo) \
KASSERT(g_valid_obj(foo) == 1, ("%p is not a g_class", foo))
#define G_VALID_GEOM(foo) \
KASSERT(g_valid_obj(foo) == 2, ("%p is not a g_geom", foo))
#define G_VALID_CONSUMER(foo) \
KASSERT(g_valid_obj(foo) == 3, ("%p is not a g_consumer", foo))
#define G_VALID_PROVIDER(foo) \
KASSERT(g_valid_obj(foo) == 4, ("%p is not a g_provider", foo))
#else
#define G_VALID_CLASS(foo) do { } while (0)
#define G_VALID_GEOM(foo) do { } while (0)
#define G_VALID_CONSUMER(foo) do { } while (0)
#define G_VALID_PROVIDER(foo) do { } while (0)
#endif
int g_modevent(module_t, int, void *);
/* geom_io.c */
struct bio * g_clone_bio(struct bio *);
struct bio * g_duplicate_bio(struct bio *);
void g_destroy_bio(struct bio *);
void g_io_deliver(struct bio *bp, int error);
int g_io_getattr(const char *attr, struct g_consumer *cp, int *len, void *ptr);
int g_io_flush(struct g_consumer *cp);
int g_register_classifier(struct g_classifier_hook *hook);
void g_unregister_classifier(struct g_classifier_hook *hook);
void g_io_request(struct bio *bp, struct g_consumer *cp);
struct bio *g_new_bio(void);
struct bio *g_alloc_bio(void);
void * g_read_data(struct g_consumer *cp, off_t offset, off_t length, int *error);
int g_write_data(struct g_consumer *cp, off_t offset, void *ptr, off_t length);
int g_delete_data(struct g_consumer *cp, off_t offset, off_t length);
void g_print_bio(struct bio *bp);
/* geom_kern.c / geom_kernsim.c */
#ifdef _KERNEL
extern struct sx topology_lock;
struct g_kerneldump {
off_t offset;
off_t length;
struct dumperinfo di;
};
MALLOC_DECLARE(M_GEOM);
static __inline void *
g_malloc(int size, int flags)
{
void *p;
p = malloc(size, M_GEOM, flags);
return (p);
}
static __inline void
g_free(void *ptr)
{
#ifdef DIAGNOSTIC
if (sx_xlocked(&topology_lock)) {
KASSERT(g_valid_obj(ptr) == 0,
("g_free(%p) of live object, type %d", ptr,
g_valid_obj(ptr)));
}
#endif
free(ptr, M_GEOM);
}
#define g_topology_lock() \
do { \
mtx_assert(&Giant, MA_NOTOWNED); \
sx_xlock(&topology_lock); \
} while (0)
#define g_topology_try_lock() sx_try_xlock(&topology_lock)
#define g_topology_unlock() \
do { \
sx_xunlock(&topology_lock); \
} while (0)
#define g_topology_assert() \
do { \
sx_assert(&topology_lock, SX_XLOCKED); \
} while (0)
#define g_topology_assert_not() \
do { \
sx_assert(&topology_lock, SX_UNLOCKED); \
} while (0)
#define g_topology_sleep(chan, timo) \
sx_sleep(chan, &topology_lock, 0, "gtopol", timo)
#define DECLARE_GEOM_CLASS(class, name) \
static moduledata_t name##_mod = { \
#name, g_modevent, &class \
}; \
DECLARE_MODULE(name, name##_mod, SI_SUB_DRIVERS, SI_ORDER_FIRST);
Merge GEOM direct dispatch changes from the projects/camlock branch. When safety requirements are met, it allows to avoid passing I/O requests to GEOM g_up/g_down thread, executing them directly in the caller context. That allows to avoid CPU bottlenecks in g_up/g_down threads, plus avoid several context switches per I/O. The defined now safety requirements are: - caller should not hold any locks and should be reenterable; - callee should not depend on GEOM dual-threaded concurency semantics; - on the way down, if request is unmapped while callee doesn't support it, the context should be sleepable; - kernel thread stack usage should be below 50%. To keep compatibility with GEOM classes not meeting above requirements new provider and consumer flags added: - G_CF_DIRECT_SEND -- consumer code meets caller requirements (request); - G_CF_DIRECT_RECEIVE -- consumer code meets callee requirements (done); - G_PF_DIRECT_SEND -- provider code meets caller requirements (done); - G_PF_DIRECT_RECEIVE -- provider code meets callee requirements (request). Capable GEOM class can set them, allowing direct dispatch in cases where it is safe. If any of requirements are not met, request is queued to g_up or g_down thread same as before. Such GEOM classes were reviewed and updated to support direct dispatch: CONCAT, DEV, DISK, GATE, MD, MIRROR, MULTIPATH, NOP, PART, RAID, STRIPE, VFS, ZERO, ZFS::VDEV, ZFS::ZVOL, all classes based on g_slice KPI (LABEL, MAP, FLASHMAP, etc). To declare direct completion capability disk(9) KPI got new flag equivalent to G_PF_DIRECT_SEND -- DISKFLAG_DIRECT_COMPLETION. da(4) and ada(4) disk drivers got it set now thanks to earlier CAM locking work. This change more then twice increases peak block storage performance on systems with manu CPUs, together with earlier CAM locking changes reaching more then 1 million IOPS (512 byte raw reads from 16 SATA SSDs on 4 HBAs to 256 user-level threads). Sponsored by: iXsystems, Inc. MFC after: 2 months
2013-10-22 08:22:19 +00:00
int g_is_geom_thread(struct thread *td);
#endif /* _KERNEL */
/* geom_ctl.c */
int gctl_set_param(struct gctl_req *req, const char *param, void const *ptr, int len);
void gctl_set_param_err(struct gctl_req *req, const char *param, void const *ptr, int len);
void *gctl_get_param(struct gctl_req *req, const char *param, int *len);
char const *gctl_get_asciiparam(struct gctl_req *req, const char *param);
void *gctl_get_paraml(struct gctl_req *req, const char *param, int len);
int gctl_error(struct gctl_req *req, const char *fmt, ...) __printflike(2, 3);
struct g_class *gctl_get_class(struct gctl_req *req, char const *arg);
struct g_geom *gctl_get_geom(struct gctl_req *req, struct g_class *mpr, char const *arg);
struct g_provider *gctl_get_provider(struct gctl_req *req, char const *arg);
#endif /* _GEOM_GEOM_H_ */