Commit Graph

229 Commits

Author SHA1 Message Date
Alan Cox
a28cc55e5b Reduce the number of times that we acquire and release the page queues
lock by making vm_page_rename()'s caller, rather than vm_page_rename(),
responsible for acquiring it.
2002-12-29 07:17:06 +00:00
Alan Cox
2ee5fea7d3 Assert that the page queues lock rather than Giant is held in
vm_page_flag_clear().
2002-12-28 22:49:37 +00:00
Alan Cox
24c9ad6bed - Remove vm_page_sleep_busy(). The transition to vm_page_sleep_if_busy(),
which incorporates page queue and field locking, is complete.
 - Assert that the page queue lock rather than Giant is held in
   vm_page_flag_set().
2002-12-19 07:23:46 +00:00
Alan Cox
495bedfbd0 Assert that the page queues lock is held in vm_page_unhold(),
vm_page_remove(), and vm_page_free_toq().
2002-12-15 00:06:02 +00:00
Alan Cox
178949e021 Hold the page queues/flags lock when calling vm_page_set_validclean().
Approved by:	re
2002-11-23 19:10:31 +00:00
Alan Cox
a12cc0e489 Remove vm_page_protect(). Instead, use pmap_page_protect() directly. 2002-11-18 04:05:22 +00:00
Alan Cox
4fec79bef8 Now that pmap_remove_all() is exported by our pmap implementations
use it directly.
2002-11-16 07:44:25 +00:00
Alan Cox
d154fb4fe6 When prot is VM_PROT_NONE, call pmap_page_protect() directly rather than
indirectly through vm_page_protect().  The one remaining page flag that
is updated by vm_page_protect() is already being updated by our various
pmap implementations.

Note: A later commit will similarly change the VM_PROT_READ case and
eliminate vm_page_protect().
2002-11-10 07:12:04 +00:00
Alan Cox
1f7c5f98d7 In vm_page_remove(), avoid calling vm_page_splay() if the object's memq
is empty.
2002-11-09 08:27:42 +00:00
Alan Cox
ada2a050be Export the function vm_page_splay(). 2002-11-04 19:21:39 +00:00
Alan Cox
c71f01affe - Remove the memory allocation for the object/offset hash table
because it's no longer used.  (See revision 1.215.)
 - Fix a harmless bug: the number of vm_page structures allocated wasn't
   properly adjusted when uma_bootstrap() was introduced.  Consequently,
   we were allocating 30 unused vm_page structures.
 - Wrap a long line.
2002-11-03 22:20:42 +00:00
Alan Cox
02af9de6fc Remove the vm page buckets mutex. As of revision 1.215 of vm/vm_page.c,
it is unused.
2002-11-02 22:39:30 +00:00
Jeff Roberson
026aa839a4 - Add a new flag to vm_page_alloc, VM_ALLOC_NOOBJ. This tells
vm_page_alloc not to insert this page into an object.  The pindex is
   still used for colorization.
 - Rework vm_page_select_* to accept a color instead of an object and
   pindex to work with VM_PAGE_NOOBJ.
 - Document other VM_ALLOC_ flags.

Reviewed by:	peter, jake
2002-11-01 00:59:03 +00:00
Alan Cox
f3b676f0ad o Reinline vm_page_undirty(), reducing the kernel size. (This reverts
a part of vm_page.h revision 1.87 and vm_page.c revision 1.167.)
2002-10-20 19:57:55 +00:00
Alan Cox
f4ecdf056e Complete the page queues locking needed for the page-based copy-
on-write (COW) mechanism.  (This mechanism is used by the zero-copy
TCP/IP implementation.)
 - Extend the scope of the page queues lock in vm_fault()
   to cover vm_page_cowfault().
 - Modify vm_page_cowfault() to release the page queues lock
   if it sleeps.
2002-10-19 18:34:39 +00:00
Matthew Dillon
b86ec922be Replace the vm_page hash table with a per-vmobject splay tree. There should
be no major change in performance from this change at this time but this
will allow other work to progress:  Giant lock removal around VM system
in favor of per-object mutexes, ranged fsyncs, more optimal COMMIT rpc's for
NFS, partial filesystem syncs by the syncer, more optimal object flushing,
etc.  Note that the buffer cache is already using a similar splay tree
mechanism.

Note that a good chunk of the old hash table code is still in the tree.
Alan or I will remove it prior to the release if the new code does not
introduce unsolvable bugs, else we can revert more easily.

Submitted by:	alc	(this is Alan's code)
Approved by:	re
2002-10-18 17:24:30 +00:00
Alan Cox
8a59b15cd4 o Synchronize updates to struct vm_page::cow with the page queues lock. 2002-09-02 04:04:12 +00:00
Alan Cox
fff6062ab6 o Retire vm_page_zero_fill() and vm_page_zero_fill_area(). Ever since
pmap_zero_page() and pmap_zero_page_area() were modified to accept
   a struct vm_page * instead of a physical address, vm_page_zero_fill()
   and vm_page_zero_fill_area() have served no purpose.
2002-08-25 00:22:31 +00:00
Alan Cox
60582cbe6d o Assert that the page queues lock is held in vm_page_activate(). 2002-08-11 00:21:40 +00:00
Alan Cox
db44450b11 o Remove the setting and clearing of the PG_MAPPED flag. (This flag is
obsolete.)
2002-08-10 07:11:16 +00:00
Alan Cox
06ec58b740 o Use pmap_page_is_mapped() in vm_page_protect() rather than the PG_MAPPED
flag.  (This is the only place in the entire kernel where the PG_MAPPED
   flag is tested.  It will be removed soon.)
2002-08-08 19:12:36 +00:00
Alan Cox
24c28f1ad6 o Acquire the page queues lock before checking the page's busy status
in vm_page_grab().  Also, replace the nearby tsleep() with an msleep()
   on the page queues lock.
2002-08-04 19:05:20 +00:00
Jeff Roberson
e6e370a7fe - Replace v_flag with v_iflag and v_vflag
- v_vflag is protected by the vnode lock and is used when synchronization
   with VOP calls is needed.
 - v_iflag is protected by interlock and is used for dealing with vnode
   management issues.  These flags include X/O LOCK, FREE, DOOMED, etc.
 - All accesses to v_iflag and v_vflag have either been locked or marked with
   mp_fixme's.
 - Many ASSERT_VOP_LOCKED calls have been added where the locking was not
   clear.
 - Many functions in vfs_subr.c were restructured to provide for stronger
   locking.

Idea stolen from:	BSD/OS
2002-08-04 10:29:36 +00:00
Alan Cox
aa9b1d9412 o Remove the setting of PG_MAPPED from vm_page_wire() and
vm_page_alloc(VM_ALLOC_WIRED).
2002-08-03 01:29:52 +00:00
Alan Cox
1e7ce68ff4 o Lock page queue accesses in nwfs and smbfs.
o Assert that the page queues lock is held in vm_page_deactivate().
2002-08-02 05:23:58 +00:00
Alan Cox
46086ddf91 o Acquire the page queues lock before calling vm_page_io_finish().
o Assert that the page queues lock is held in vm_page_io_finish().
2002-08-01 17:57:42 +00:00
Alan Cox
67c1fae92e o Lock page accesses by vm_page_io_start() with the page queues lock.
o Assert that the page queues lock is held in vm_page_io_start().
2002-07-31 07:27:08 +00:00
Alan Cox
e5f8bd9418 o Introduce vm_page_sleep_if_busy() as an eventual replacement for
vm_page_sleep_busy().  vm_page_sleep_if_busy() uses the page
   queues lock.
2002-07-29 19:41:22 +00:00
Alan Cox
2c071f61f0 o Modify vm_page_grab() to accept VM_ALLOC_WIRED. 2002-07-28 23:46:19 +00:00
Alan Cox
2999e9faca o Lock page queue accesses by vm_page_dontneed().
o Assert that the page queue lock is held in vm_page_dontneed().
2002-07-23 04:39:48 +00:00
Alan Cox
40eab1e944 o Lock page queue accesses by vm_page_try_to_cache(). (The accesses
in kern/vfs_bio.c are already locked.)
 o Assert that the page queues lock is held in vm_page_try_to_cache().
2002-07-20 20:58:46 +00:00
Alan Cox
d82efd2956 o Assert that the page queues lock is held in vm_page_try_to_free(). 2002-07-20 20:12:57 +00:00
Alan Cox
15a5d2108e o Lock page queue accesses by vm_page_cache() in vm_fault() and
vm_pageout_scan().  (The others are already locked.)
 o Assert that the page queues lock is held in vm_page_cache().
2002-07-20 19:34:21 +00:00
Alan Cox
eeeaf0fdd1 o Duplicate an odd side-effect of vm_page_wire() in vm_page_allocate()
when VM_ALLOC_WIRED is specified: set the PG_MAPPED bit in flags.
 o In both vm_page_wire() and vm_page_allocate() add a comment saying
   that setting PG_MAPPED does not belong there.
2002-07-19 03:33:04 +00:00
Alan Cox
827b2fa091 o Introduce an argument, VM_ALLOC_WIRED, that requests vm_page_alloc()
to return a wired page.
 o Use VM_ALLOC_WIRED within Alpha's pmap_growkernel().  Also, because
   Alpha's pmap_growkernel() calls vm_page_alloc() from within a critical
   section, specify VM_ALLOC_INTERRUPT instead of VM_ALLOC_SYSTEM.  (Only
   VM_ALLOC_INTERRUPT is implemented entirely with a spin mutex.)
 o Assert that the page queues mutex is held in vm_page_wire()
   on Alpha, just like the other platforms.
2002-07-18 04:08:10 +00:00
Alan Cox
8b8b8202f9 o Lock page queue accesses by vm_page_wire() that aren't
within a critical section.
 o Assert that the page queues lock is held in vm_page_wire()
   unless an Alpha.
2002-07-14 23:51:55 +00:00
Alan Cox
eed6f3fd45 o Lock page queue accesses by vm_page_unmanage().
o Assert that the page queues lock is held in vm_page_unmanage().
2002-07-13 23:55:30 +00:00
Alan Cox
1f54526952 o Complete the locking of page queue accesses by vm_page_unwire().
o Assert that the page queues lock is held in vm_page_unwire().
 o Make vm_page_lock_queues() and vm_page_unlock_queues() visible
   to kernel loadable modules.
2002-07-13 20:55:21 +00:00
Andrew Gallatin
f784043a9f Remove bogus vm_page_wakeup() in vm_page_cowfault() that will cause panics
in the zero-copy send path if a process attempts to write to a page
which is still in flight.

reviewed by: ken
2002-07-05 23:33:27 +00:00
Alan Cox
70c1763634 o Resurrect vm_page_lock_queues(), vm_page_unlock_queues(), and the free
queue lock (revision 1.33 of vm/vm_page.c removed them).
 o Make the free queue lock a spin lock because it's sometimes acquired
   inside of a critical section.
2002-07-04 22:07:37 +00:00
Kenneth D. Merry
98cb733c67 At long last, commit the zero copy sockets code.
MAKEDEV:	Add MAKEDEV glue for the ti(4) device nodes.

ti.4:		Update the ti(4) man page to include information on the
		TI_JUMBO_HDRSPLIT and TI_PRIVATE_JUMBOS kernel options,
		and also include information about the new character
		device interface and the associated ioctls.

man9/Makefile:	Add jumbo.9 and zero_copy.9 man pages and associated
		links.

jumbo.9:	New man page describing the jumbo buffer allocator
		interface and operation.

zero_copy.9:	New man page describing the general characteristics of
		the zero copy send and receive code, and what an
		application author should do to take advantage of the
		zero copy functionality.

NOTES:		Add entries for ZERO_COPY_SOCKETS, TI_PRIVATE_JUMBOS,
		TI_JUMBO_HDRSPLIT, MSIZE, and MCLSHIFT.

conf/files:	Add uipc_jumbo.c and uipc_cow.c.

conf/options:	Add the 5 options mentioned above.

kern_subr.c:	Receive side zero copy implementation.  This takes
		"disposable" pages attached to an mbuf, gives them to
		a user process, and then recycles the user's page.
		This is only active when ZERO_COPY_SOCKETS is turned on
		and the kern.ipc.zero_copy.receive sysctl variable is
		set to 1.

uipc_cow.c:	Send side zero copy functions.  Takes a page written
		by the user and maps it copy on write and assigns it
		kernel virtual address space.  Removes copy on write
		mapping once the buffer has been freed by the network
		stack.

uipc_jumbo.c:	Jumbo disposable page allocator code.  This allocates
		(optionally) disposable pages for network drivers that
		want to give the user the option of doing zero copy
		receive.

uipc_socket.c:	Add kern.ipc.zero_copy.{send,receive} sysctls that are
		enabled if ZERO_COPY_SOCKETS is turned on.

		Add zero copy send support to sosend() -- pages get
		mapped into the kernel instead of getting copied if
		they meet size and alignment restrictions.

uipc_syscalls.c:Un-staticize some of the sf* functions so that they
		can be used elsewhere.  (uipc_cow.c)

if_media.c:	In the SIOCGIFMEDIA ioctl in ifmedia_ioctl(), avoid
		calling malloc() with M_WAITOK.  Return an error if
		the M_NOWAIT malloc fails.

		The ti(4) driver and the wi(4) driver, at least, call
		this with a mutex held.  This causes witness warnings
		for 'ifconfig -a' with a wi(4) or ti(4) board in the
		system.  (I've only verified for ti(4)).

ip_output.c:	Fragment large datagrams so that each segment contains
		a multiple of PAGE_SIZE amount of data plus headers.
		This allows the receiver to potentially do page
		flipping on receives.

if_ti.c:	Add zero copy receive support to the ti(4) driver.  If
		TI_PRIVATE_JUMBOS is not defined, it now uses the
		jumbo(9) buffer allocator for jumbo receive buffers.

		Add a new character device interface for the ti(4)
		driver for the new debugging interface.  This allows
		(a patched version of) gdb to talk to the Tigon board
		and debug the firmware.  There are also a few additional
		debugging ioctls available through this interface.

		Add header splitting support to the ti(4) driver.

		Tweak some of the default interrupt coalescing
		parameters to more useful defaults.

		Add hooks for supporting transmit flow control, but
		leave it turned off with a comment describing why it
		is turned off.

if_tireg.h:	Change the firmware rev to 12.4.11, since we're really
		at 12.4.11 plus fixes from 12.4.13.

		Add defines needed for debugging.

		Remove the ti_stats structure, it is now defined in
		sys/tiio.h.

ti_fw.h:	12.4.11 firmware.

ti_fw2.h:	12.4.11 firmware, plus selected fixes from 12.4.13,
		and my header splitting patches.  Revision 12.4.13
		doesn't handle 10/100 negotiation properly.  (This
		firmware is the same as what was in the tree previously,
		with the addition of header splitting support.)

sys/jumbo.h:	Jumbo buffer allocator interface.

sys/mbuf.h:	Add a new external mbuf type, EXT_DISPOSABLE, to
		indicate that the payload buffer can be thrown away /
		flipped to a userland process.

socketvar.h:	Add prototype for socow_setup.

tiio.h:		ioctl interface to the character portion of the ti(4)
		driver, plus associated structure/type definitions.

uio.h:		Change prototype for uiomoveco() so that we'll know
		whether the source page is disposable.

ufs_readwrite.c:Update for new prototype of uiomoveco().

vm_fault.c:	In vm_fault(), check to see whether we need to do a page
		based copy on write fault.

vm_object.c:	Add a new function, vm_object_allocate_wait().  This
		does the same thing that vm_object allocate does, except
		that it gives the caller the opportunity to specify whether
		it should wait on the uma_zalloc() of the object structre.

		This allows vm objects to be allocated while holding a
		mutex.  (Without generating WITNESS warnings.)

		vm_object_allocate() is implemented as a call to
		vm_object_allocate_wait() with the malloc flag set to
		M_WAITOK.

vm_object.h:	Add prototype for vm_object_allocate_wait().

vm_page.c:	Add page-based copy on write setup, clear and fault
		routines.

vm_page.h:	Add page based COW function prototypes and variable in
		the vm_page structure.

Many thanks to Drew Gallatin, who wrote the zero copy send and receive
code, and to all the other folks who have tested and reviewed this code
over the years.
2002-06-26 03:37:47 +00:00
Jeff Roberson
e78f35b33f Turn VM_ALLOC_ZERO into a flag.
Submitted by:	tegge
Reviewed by:	dillon
2002-06-25 22:01:12 +00:00
Alan Cox
ea0f50bcf0 o Convert the vm_page buckets mutex to a spin lock. (This resolves
an issue on the Alpha platform found by jeff@.)
 o Simplify vm_page_lookup().

Reviewed by:	jhb
2002-04-30 21:24:47 +00:00
Peter Wemm
44e74ba6c3 We do not necessarily need to map/unmap pages to zero parts of them.
On systems where physical memory is also direct mapped (alpha, sparc,
ia64 etc) this is slightly harmful.
2002-04-28 00:15:48 +00:00
Alan Cox
cbd53e95fe o Control access to the vm_page_buckets with a mutex.
o Fix some style(9) bugs.
2002-04-26 22:44:15 +00:00
Peter Wemm
1a87a0da66 Pass vm_page_t instead of physical addresses to pmap_zero_page[_area]()
and pmap_copy_page().  This gets rid of a couple more physical addresses
in upper layers, with the eventual aim of supporting PAE and dealing with
the physical addressing mostly within pmap.  (We will need either 64 bit
physical addresses or page indexes, possibly both depending on the
circumstances.  Leaving this to pmap itself gives more flexibilitly.)

Reviewed by:	jake
Tested on:	i386, ia64 and (I believe) sparc64. (my alpha was hosed)
2002-04-15 16:00:03 +00:00
John Baldwin
6008862bc2 Change callers of mtx_init() to pass in an appropriate lock type name. In
most cases NULL is passed, but in some cases such as network driver locks
(which use the MTX_NETWORK_LOCK macro) and UMA zone locks, a name is used.

Tested on:	i386, alpha, sparc64
2002-04-04 21:03:38 +00:00
Jake Burkholder
48f9a59443 Fix a long standing 32bit-ism. Don't assume that the size of a chunk of
memory in phys_avail will fit in 'int', use vm_size_t.  This fixes booting
on sparc64 machines with more than 2 gigs of ram.

Thanks to Jan Chrillesen for providing me with access to a 4 gig machine.
2002-04-03 06:57:52 +00:00
Jeff Roberson
8355f576a9 This is the first part of the new kernel memory allocator. This replaces
malloc(9) and vm_zone with a slab like allocator.

Reviewed by:	arch@
2002-03-19 09:11:49 +00:00
Eivind Eklund
a128794977 - Remove a number of extra newlines that do not belong here according to
style(9)
- Minor space adjustment in cases where we have "( ", " )", if(), return(),
  while(), for(), etc.
- Add /* SYMBOL */ after a few #endifs.

Reviewed by:	alc
2002-03-10 21:52:48 +00:00