freebsd-skq/sys/xen/gnttab.c
gibbs 831bbfaf75 Improve the Xen para-virtualized device infrastructure of FreeBSD:
o Add support for backend devices (e.g. blkback)
 o Implement extensions to the Xen para-virtualized block API to allow
   for larger and more outstanding I/Os.
 o Import a completely rewritten block back driver with support for fronting
   I/O to both raw devices and files.
 o General cleanup and documentation of the XenBus and XenStore support code.
 o Robustness and performance updates for the block front driver.
 o Fixes to the netfront driver.

Sponsored by: Spectra Logic Corporation

sys/xen/xenbus/init.txt:
	Deleted: This file explains the Linux method for XenBus device
	enumeration and thus does not apply to FreeBSD's NewBus approach.

sys/xen/xenbus/xenbus_probe_backend.c:
	Deleted: Linux version of backend XenBus service routines.  It
	was never ported to FreeBSD.  See xenbusb.c, xenbusb_if.m,
	xenbusb_front.c xenbusb_back.c for details of FreeBSD's XenBus
	support.

sys/xen/xenbus/xenbusvar.h:
sys/xen/xenbus/xenbus_xs.c:
sys/xen/xenbus/xenbus_comms.c:
sys/xen/xenbus/xenbus_comms.h:
sys/xen/xenstore/xenstorevar.h:
sys/xen/xenstore/xenstore.c:
	Split XenStore into its own tree.  XenBus is a software layer built
	on top of XenStore.  The old arrangement and the naming of some
	structures and functions blurred these lines making it difficult to
	discern what services are provided by which layer and at what times
	these services are available (e.g. during system startup and shutdown).

sys/xen/xenbus/xenbus_client.c:
sys/xen/xenbus/xenbus.c:
sys/xen/xenbus/xenbus_probe.c:
sys/xen/xenbus/xenbusb.c:
sys/xen/xenbus/xenbusb.h:
	Split up XenBus code into methods available for use by client
	drivers (xenbus.c) and code used by the XenBus "bus code" to
	enumerate, attach, detach, and service bus drivers.

sys/xen/reboot.c:
sys/dev/xen/control/control.c:
	Add a XenBus front driver for handling shutdown, reboot, suspend, and
	resume events published in the XenStore.  Move all PV suspend/reboot
	support from reboot.c into this driver.

sys/xen/blkif.h:
	New file from Xen vendor with macros and structures used by
	a block back driver to service requests from a VM running a
	different ABI (e.g. amd64 back with i386 front).

sys/conf/files:
	Adjust kernel build spec for new XenBus/XenStore layout and added
	Xen functionality.

sys/dev/xen/balloon/balloon.c:
sys/dev/xen/netfront/netfront.c:
sys/dev/xen/blkfront/blkfront.c:
sys/xen/xenbus/...
sys/xen/xenstore/...
	o Rename XenStore APIs and structures from xenbus_* to xs_*.
	o Adjust to use of M_XENBUS and M_XENSTORE malloc types for allocation
	  of objects returned by these APIs.
	o Adjust for changes in the bus interface for Xen drivers.

sys/xen/xenbus/...
sys/xen/xenstore/...
	Add Doxygen comments for these interfaces and the code that
	implements them.

sys/dev/xen/blkback/blkback.c:
	o Rewrite the Block Back driver to attach properly via newbus,
	  operate correctly in both PV and HVM mode regardless of domain
	  (e.g. can be in a DOM other than 0), and to deal with the latest
	  metadata available in XenStore for block devices.

	o Allow users to specify a file as a backend to blkback, in addition
	  to character devices.  Use the namei lookup of the backend path
	  to automatically configure, based on file type, the appropriate
	  backend method.

	The current implementation is limited to a single outstanding I/O
	at a time to file backed storage.

sys/dev/xen/blkback/blkback.c:
sys/xen/interface/io/blkif.h:
sys/xen/blkif.h:
sys/dev/xen/blkfront/blkfront.c:
sys/dev/xen/blkfront/block.h:
	Extend the Xen blkif API: Negotiable request size and number of
	requests.

	This change extends the information recorded in the XenStore
	allowing block front/back devices to negotiate for optimal I/O
	parameters.  This has been achieved without sacrificing backward
	compatibility with drivers that are unaware of these protocol
	enhancements.  The extensions center around the connection protocol
	which now includes these additions:

	o The back-end device publishes its maximum supported values for,
	  request I/O size, the number of page segments that can be
	  associated with a request, the maximum number of requests that
	  can be concurrently active, and the maximum number of pages that
	  can be in the shared request ring.  These values are published
	  before the back-end enters the XenbusStateInitWait state.

	o The front-end waits for the back-end to enter either the InitWait
	  or Initialize state.  At this point, the front end limits it's
	  own capabilities to the lesser of the values it finds published
	  by the backend, it's own maximums, or, should any back-end data
	  be missing in the store, the values supported by the original
	  protocol.  It then initializes it's internal data structures
	  including allocation of the shared ring, publishes its maximum
	  capabilities to the XenStore and transitions to the Initialized
	  state.

	o The back-end waits for the front-end to enter the Initalized
	  state.  At this point, the back end limits it's own capabilities
	  to the lesser of the values it finds published by the frontend,
	  it's own maximums, or, should any front-end data be missing in
	  the store, the values supported by the original protocol.  It
	  then initializes it's internal data structures, attaches to the
	  shared ring and transitions to the Connected state.

	o The front-end waits for the back-end to enter the Connnected
	  state, transitions itself to the connected state, and can
	  commence I/O.

	Although an updated front-end driver must be aware of the back-end's
	InitWait state, the back-end has been coded such that it can
	tolerate a front-end that skips this step and transitions directly
	to the Initialized state without waiting for the back-end.

sys/xen/interface/io/blkif.h:
	o Increase BLKIF_MAX_SEGMENTS_PER_REQUEST to 255.  This is
	  the maximum number possible without changing the blkif
	  request header structure (nr_segs is a uint8_t).

	o Add two new constants:
	  BLKIF_MAX_SEGMENTS_PER_HEADER_BLOCK, and
	  BLKIF_MAX_SEGMENTS_PER_SEGMENT_BLOCK.  These respectively
	  indicate the number of segments that can fit in the first
	  ring-buffer entry of a request, and for each subsequent
	  (sg element only) ring-buffer entry associated with the
          "header" ring-buffer entry of the request.

	o Add the blkif_request_segment_t typedef for segment
	  elements.

	o Add the BLKRING_GET_SG_REQUEST() macro which wraps the
	  RING_GET_REQUEST() macro and returns a properly cast
	  pointer to an array of blkif_request_segment_ts.

	o Add the BLKIF_SEGS_TO_BLOCKS() macro which calculates the
	  number of ring entries that will be consumed by a blkif
	  request with the given number of segments.

sys/xen/blkif.h:
	o Update for changes in interface/io/blkif.h macros.

	o Update the BLKIF_MAX_RING_REQUESTS() macro to take the
	  ring size as an argument to allow this calculation on
	  multi-page rings.

	o Add a companion macro to BLKIF_MAX_RING_REQUESTS(),
	  BLKIF_RING_PAGES().  This macro determines the number of
	  ring pages required in order to support a ring with the
	  supplied number of request blocks.

sys/dev/xen/blkback/blkback.c:
sys/dev/xen/blkfront/blkfront.c:
sys/dev/xen/blkfront/block.h:
	o Negotiate with the other-end with the following limits:
	      Reqeust Size:   MAXPHYS
	      Max Segments:   (MAXPHYS/PAGE_SIZE) + 1
	      Max Requests:   256
	      Max Ring Pages: Sufficient to support Max Requests with
	                      Max Segments.

	o Dynamically allocate request pools and segemnts-per-request.

	o Update ring allocation/attachment code to support a
	  multi-page shared ring.

	o Update routines that access the shared ring to handle
	  multi-block requests.

sys/dev/xen/blkfront/blkfront.c:
	o Track blkfront allocations in a blkfront driver specific
	  malloc pool.

	o Strip out XenStore transaction retry logic in the
	  connection code.  Transactions only need to be used when
	  the update to multiple XenStore nodes must be atomic.
	  That is not the case here.

	o Fully disable blkif_resume() until it can be fixed
	  properly (it didn't work before this change).

	o Destroy bus-dma objects during device instance tear-down.

	o Properly handle backend devices with powef-of-2 sector
	  sizes larger than 512b.

sys/dev/xen/blkback/blkback.c:
	Advertise support for and implement the BLKIF_OP_WRITE_BARRIER
	and BLKIF_OP_FLUSH_DISKCACHE blkif opcodes using BIO_FLUSH and
	the BIO_ORDERED attribute of bios.

sys/dev/xen/blkfront/blkfront.c:
sys/dev/xen/blkfront/block.h:
	Fix various bugs in blkfront.

       o gnttab_alloc_grant_references() returns 0 for success and
	 non-zero for failure.  The check for < 0 is a leftover
	 Linuxism.

       o When we negotiate with blkback and have to reduce some of our
	 capabilities, print out the original and reduced capability before
	 changing the local capability.  So the user now gets the correct
	 information.

	o Fix blkif_restart_queue_callback() formatting.  Make sure we hold
	  the mutex in that function before calling xb_startio().

	o Fix a couple of KASSERT()s.

        o Fix a check in the xb_remove_* macro to be a little more specific.

sys/xen/gnttab.h:
sys/xen/gnttab.c:
	Define GNTTAB_LIST_END publicly as GRANT_REF_INVALID.

sys/dev/xen/netfront/netfront.c:
	Use GRANT_REF_INVALID instead of driver private definitions of the
	same constant.

sys/xen/gnttab.h:
sys/xen/gnttab.c:
	Add the gnttab_end_foreign_access_references() API.

	This API allows a client to batch the release of an array of grant
	references, instead of coding a private for loop.  The implementation
	takes advantage of this batching to reduce lock overhead to one
	acquisition and release per-batch instead of per-freed grant reference.

	While here, reduce the duration the gnttab_list_lock is held during
	gnttab_free_grant_references() operations.  The search to find the
	tail of the incoming free list does not rely on global state and so
	can be performed without holding the lock.

sys/dev/xen/xenpci/evtchn.c:
sys/dev/xen/evtchn/evtchn.c:
sys/xen/xen_intr.h:
	o Implement the bind_interdomain_evtchn_to_irqhandler API for HVM mode.
	  This allows an HVM domain to serve back end devices to other domains.
	  This API is already implemented for PV mode.

	o Synchronize the API between HVM and PV.

sys/dev/xen/xenpci/xenpci.c:
	o Scan the full region of CPUID space in which the Xen VMM interface
	  may be implemented.  On systems using SuSE as a Dom0 where the
	  Viridian API is also exported, the VMM interface is above the region
	  we used to search.

	o Pass through bus_alloc_resource() calls so that XenBus drivers
	  attaching on an HVM system can allocate unused physical address
	  space from the nexus.  The block back driver makes use of this
	  facility.

sys/i386/xen/xen_machdep.c:
	Use the correct type for accessing the statically mapped xenstore
	metadata.

sys/xen/interface/hvm/params.h:
sys/xen/xenstore/xenstore.c:
	Move hvm_get_parameter() to the correct global header file instead
	of as a private method to the XenStore.

sys/xen/interface/io/protocols.h:
	Sync with vendor.

sys/xeninterface/io/ring.h:
	Add macro for calculating the number of ring pages needed for an N
	deep ring.

	To avoid duplication within the macros, create and use the new
	__RING_HEADER_SIZE() macro.  This macro calculates the size of the
	ring book keeping struct (producer/consumer indexes, etc.) that
	resides at the head of the ring.

	Add the __RING_PAGES() macro which calculates the number of shared
	ring pages required to support a ring with the given number of
	requests.

	These APIs are used to support the multi-page ring version of the
	Xen block API.

sys/xeninterface/io/xenbus.h:
	Add Comments.

sys/xen/xenbus/...
	o Refactor the FreeBSD XenBus support code to allow for both front and
	  backend device attachments.

	o Make use of new config_intr_hook capabilities to allow front and back
	  devices to be probed/attached in parallel.

	o Fix bugs in probe/attach state machine that could cause the system to
	  hang when confronted with a failure either in the local domain or in
	  a remote domain to which one of our driver instances is attaching.

	o Publish all required state to the XenStore on device detach and
	  failure.  The majority of the missing functionality was for serving
	  as a back end since the typical "hot-plug" scripts in Dom0 don't
	  handle the case of cleaning up for a "service domain" that is not
	  itself.

	o Add dynamic sysctl nodes exposing the generic ivars of
	  XenBus devices.

	o Add doxygen style comments to the majority of the code.

	o Cleanup types, formatting, etc.

sys/xen/xenbus/xenbusb.c:
	Common code used by both front and back XenBus busses.

sys/xen/xenbus/xenbusb_if.m:
	Method definitions for a XenBus bus.

sys/xen/xenbus/xenbusb_front.c:
sys/xen/xenbus/xenbusb_back.c:
	XenBus bus specialization for front and back devices.

MFC after:	1 month
2010-10-19 20:53:30 +00:00

710 lines
15 KiB
C

/******************************************************************************
* gnttab.c
*
* Two sets of functionality:
* 1. Granting foreign access to our memory reservation.
* 2. Accessing others' memory reservations via grant references.
* (i.e., mechanisms for both sender and recipient of grant references)
*
* Copyright (c) 2005, Christopher Clark
* Copyright (c) 2004, K A Fraser
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include "opt_global.h"
#include "opt_pmap.h"
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/bus.h>
#include <sys/conf.h>
#include <sys/module.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/malloc.h>
#include <sys/mman.h>
#include <machine/xen/xen-os.h>
#include <xen/hypervisor.h>
#include <machine/xen/synch_bitops.h>
#include <xen/hypervisor.h>
#include <xen/gnttab.h>
#include <vm/vm.h>
#include <vm/vm_kern.h>
#include <vm/vm_extern.h>
#include <vm/pmap.h>
#define cmpxchg(a, b, c) atomic_cmpset_int((volatile u_int *)(a),(b),(c))
/* External tools reserve first few grant table entries. */
#define NR_RESERVED_ENTRIES 8
#define GREFS_PER_GRANT_FRAME (PAGE_SIZE / sizeof(grant_entry_t))
static grant_ref_t **gnttab_list;
static unsigned int nr_grant_frames;
static unsigned int boot_max_nr_grant_frames;
static int gnttab_free_count;
static grant_ref_t gnttab_free_head;
static struct mtx gnttab_list_lock;
static grant_entry_t *shared;
static struct gnttab_free_callback *gnttab_free_callback_list = NULL;
static int gnttab_expand(unsigned int req_entries);
#define RPP (PAGE_SIZE / sizeof(grant_ref_t))
#define gnttab_entry(entry) (gnttab_list[(entry) / RPP][(entry) % RPP])
static int
get_free_entries(int count, int *entries)
{
int ref, error;
grant_ref_t head;
mtx_lock(&gnttab_list_lock);
if ((gnttab_free_count < count) &&
((error = gnttab_expand(count - gnttab_free_count)) != 0)) {
mtx_unlock(&gnttab_list_lock);
return (error);
}
ref = head = gnttab_free_head;
gnttab_free_count -= count;
while (count-- > 1)
head = gnttab_entry(head);
gnttab_free_head = gnttab_entry(head);
gnttab_entry(head) = GNTTAB_LIST_END;
mtx_unlock(&gnttab_list_lock);
*entries = ref;
return (0);
}
static void
do_free_callbacks(void)
{
struct gnttab_free_callback *callback, *next;
callback = gnttab_free_callback_list;
gnttab_free_callback_list = NULL;
while (callback != NULL) {
next = callback->next;
if (gnttab_free_count >= callback->count) {
callback->next = NULL;
callback->fn(callback->arg);
} else {
callback->next = gnttab_free_callback_list;
gnttab_free_callback_list = callback;
}
callback = next;
}
}
static inline void
check_free_callbacks(void)
{
if (unlikely(gnttab_free_callback_list != NULL))
do_free_callbacks();
}
static void
put_free_entry(grant_ref_t ref)
{
mtx_lock(&gnttab_list_lock);
gnttab_entry(ref) = gnttab_free_head;
gnttab_free_head = ref;
gnttab_free_count++;
check_free_callbacks();
mtx_unlock(&gnttab_list_lock);
}
/*
* Public grant-issuing interface functions
*/
int
gnttab_grant_foreign_access(domid_t domid, unsigned long frame, int readonly,
grant_ref_t *result)
{
int error, ref;
error = get_free_entries(1, &ref);
if (unlikely(error))
return (error);
shared[ref].frame = frame;
shared[ref].domid = domid;
wmb();
shared[ref].flags = GTF_permit_access | (readonly ? GTF_readonly : 0);
if (result)
*result = ref;
return (0);
}
void
gnttab_grant_foreign_access_ref(grant_ref_t ref, domid_t domid,
unsigned long frame, int readonly)
{
shared[ref].frame = frame;
shared[ref].domid = domid;
wmb();
shared[ref].flags = GTF_permit_access | (readonly ? GTF_readonly : 0);
}
int
gnttab_query_foreign_access(grant_ref_t ref)
{
uint16_t nflags;
nflags = shared[ref].flags;
return (nflags & (GTF_reading|GTF_writing));
}
int
gnttab_end_foreign_access_ref(grant_ref_t ref)
{
uint16_t flags, nflags;
nflags = shared[ref].flags;
do {
if ( (flags = nflags) & (GTF_reading|GTF_writing) ) {
printf("%s: WARNING: g.e. still in use!\n", __func__);
return (0);
}
} while ((nflags = synch_cmpxchg(&shared[ref].flags, flags, 0)) !=
flags);
return (1);
}
void
gnttab_end_foreign_access(grant_ref_t ref, void *page)
{
if (gnttab_end_foreign_access_ref(ref)) {
put_free_entry(ref);
if (page != NULL) {
free(page, M_DEVBUF);
}
}
else {
/* XXX This needs to be fixed so that the ref and page are
placed on a list to be freed up later. */
printf("%s: WARNING: leaking g.e. and page still in use!\n",
__func__);
}
}
void
gnttab_end_foreign_access_references(u_int count, grant_ref_t *refs)
{
grant_ref_t *last_ref;
grant_ref_t head;
grant_ref_t tail;
head = GNTTAB_LIST_END;
tail = *refs;
last_ref = refs + count;
while (refs != last_ref) {
if (gnttab_end_foreign_access_ref(*refs)) {
gnttab_entry(*refs) = head;
head = *refs;
} else {
/*
* XXX This needs to be fixed so that the ref
* is placed on a list to be freed up later.
*/
printf("%s: WARNING: leaking g.e. still in use!\n",
__func__);
count--;
}
refs++;
}
if (count != 0) {
mtx_lock(&gnttab_list_lock);
gnttab_free_count += count;
gnttab_entry(tail) = gnttab_free_head;
gnttab_free_head = head;
mtx_unlock(&gnttab_list_lock);
}
}
int
gnttab_grant_foreign_transfer(domid_t domid, unsigned long pfn,
grant_ref_t *result)
{
int error, ref;
error = get_free_entries(1, &ref);
if (unlikely(error))
return (error);
gnttab_grant_foreign_transfer_ref(ref, domid, pfn);
*result = ref;
return (0);
}
void
gnttab_grant_foreign_transfer_ref(grant_ref_t ref, domid_t domid,
unsigned long pfn)
{
shared[ref].frame = pfn;
shared[ref].domid = domid;
wmb();
shared[ref].flags = GTF_accept_transfer;
}
unsigned long
gnttab_end_foreign_transfer_ref(grant_ref_t ref)
{
unsigned long frame;
uint16_t flags;
/*
* If a transfer is not even yet started, try to reclaim the grant
* reference and return failure (== 0).
*/
while (!((flags = shared[ref].flags) & GTF_transfer_committed)) {
if ( synch_cmpxchg(&shared[ref].flags, flags, 0) == flags )
return (0);
cpu_relax();
}
/* If a transfer is in progress then wait until it is completed. */
while (!(flags & GTF_transfer_completed)) {
flags = shared[ref].flags;
cpu_relax();
}
/* Read the frame number /after/ reading completion status. */
rmb();
frame = shared[ref].frame;
KASSERT(frame != 0, ("grant table inconsistent"));
return (frame);
}
unsigned long
gnttab_end_foreign_transfer(grant_ref_t ref)
{
unsigned long frame = gnttab_end_foreign_transfer_ref(ref);
put_free_entry(ref);
return (frame);
}
void
gnttab_free_grant_reference(grant_ref_t ref)
{
put_free_entry(ref);
}
void
gnttab_free_grant_references(grant_ref_t head)
{
grant_ref_t ref;
int count = 1;
if (head == GNTTAB_LIST_END)
return;
ref = head;
while (gnttab_entry(ref) != GNTTAB_LIST_END) {
ref = gnttab_entry(ref);
count++;
}
mtx_lock(&gnttab_list_lock);
gnttab_entry(ref) = gnttab_free_head;
gnttab_free_head = head;
gnttab_free_count += count;
check_free_callbacks();
mtx_unlock(&gnttab_list_lock);
}
int
gnttab_alloc_grant_references(uint16_t count, grant_ref_t *head)
{
int ref, error;
error = get_free_entries(count, &ref);
if (unlikely(error))
return (error);
*head = ref;
return (0);
}
int
gnttab_empty_grant_references(const grant_ref_t *private_head)
{
return (*private_head == GNTTAB_LIST_END);
}
int
gnttab_claim_grant_reference(grant_ref_t *private_head)
{
grant_ref_t g = *private_head;
if (unlikely(g == GNTTAB_LIST_END))
return (g);
*private_head = gnttab_entry(g);
return (g);
}
void
gnttab_release_grant_reference(grant_ref_t *private_head, grant_ref_t release)
{
gnttab_entry(release) = *private_head;
*private_head = release;
}
void
gnttab_request_free_callback(struct gnttab_free_callback *callback,
void (*fn)(void *), void *arg, uint16_t count)
{
mtx_lock(&gnttab_list_lock);
if (callback->next)
goto out;
callback->fn = fn;
callback->arg = arg;
callback->count = count;
callback->next = gnttab_free_callback_list;
gnttab_free_callback_list = callback;
check_free_callbacks();
out:
mtx_unlock(&gnttab_list_lock);
}
void
gnttab_cancel_free_callback(struct gnttab_free_callback *callback)
{
struct gnttab_free_callback **pcb;
mtx_lock(&gnttab_list_lock);
for (pcb = &gnttab_free_callback_list; *pcb; pcb = &(*pcb)->next) {
if (*pcb == callback) {
*pcb = callback->next;
break;
}
}
mtx_unlock(&gnttab_list_lock);
}
static int
grow_gnttab_list(unsigned int more_frames)
{
unsigned int new_nr_grant_frames, extra_entries, i;
new_nr_grant_frames = nr_grant_frames + more_frames;
extra_entries = more_frames * GREFS_PER_GRANT_FRAME;
for (i = nr_grant_frames; i < new_nr_grant_frames; i++)
{
gnttab_list[i] = (grant_ref_t *)
malloc(PAGE_SIZE, M_DEVBUF, M_NOWAIT);
if (!gnttab_list[i])
goto grow_nomem;
}
for (i = GREFS_PER_GRANT_FRAME * nr_grant_frames;
i < GREFS_PER_GRANT_FRAME * new_nr_grant_frames - 1; i++)
gnttab_entry(i) = i + 1;
gnttab_entry(i) = gnttab_free_head;
gnttab_free_head = GREFS_PER_GRANT_FRAME * nr_grant_frames;
gnttab_free_count += extra_entries;
nr_grant_frames = new_nr_grant_frames;
check_free_callbacks();
return (0);
grow_nomem:
for ( ; i >= nr_grant_frames; i--)
free(gnttab_list[i], M_DEVBUF);
return (ENOMEM);
}
static unsigned int
__max_nr_grant_frames(void)
{
struct gnttab_query_size query;
int rc;
query.dom = DOMID_SELF;
rc = HYPERVISOR_grant_table_op(GNTTABOP_query_size, &query, 1);
if ((rc < 0) || (query.status != GNTST_okay))
return (4); /* Legacy max supported number of frames */
return (query.max_nr_frames);
}
static inline
unsigned int max_nr_grant_frames(void)
{
unsigned int xen_max = __max_nr_grant_frames();
if (xen_max > boot_max_nr_grant_frames)
return (boot_max_nr_grant_frames);
return (xen_max);
}
#ifdef notyet
/*
* XXX needed for backend support
*
*/
static int
map_pte_fn(pte_t *pte, struct page *pmd_page,
unsigned long addr, void *data)
{
unsigned long **frames = (unsigned long **)data;
set_pte_at(&init_mm, addr, pte, pfn_pte_ma((*frames)[0], PAGE_KERNEL));
(*frames)++;
return 0;
}
static int
unmap_pte_fn(pte_t *pte, struct page *pmd_page,
unsigned long addr, void *data)
{
set_pte_at(&init_mm, addr, pte, __pte(0));
return 0;
}
#endif
#ifndef XENHVM
static int
gnttab_map(unsigned int start_idx, unsigned int end_idx)
{
struct gnttab_setup_table setup;
u_long *frames;
unsigned int nr_gframes = end_idx + 1;
int i, rc;
frames = malloc(nr_gframes * sizeof(unsigned long), M_DEVBUF, M_NOWAIT);
if (!frames)
return (ENOMEM);
setup.dom = DOMID_SELF;
setup.nr_frames = nr_gframes;
set_xen_guest_handle(setup.frame_list, frames);
rc = HYPERVISOR_grant_table_op(GNTTABOP_setup_table, &setup, 1);
if (rc == -ENOSYS) {
free(frames, M_DEVBUF);
return (ENOSYS);
}
KASSERT(!(rc || setup.status),
("unexpected result from grant_table_op"));
if (shared == NULL) {
vm_offset_t area;
area = kmem_alloc_nofault(kernel_map,
PAGE_SIZE * max_nr_grant_frames());
KASSERT(area, ("can't allocate VM space for grant table"));
shared = (grant_entry_t *)area;
}
for (i = 0; i < nr_gframes; i++)
PT_SET_MA(((caddr_t)shared) + i*PAGE_SIZE,
((vm_paddr_t)frames[i]) << PAGE_SHIFT | PG_RW | PG_V);
free(frames, M_DEVBUF);
return (0);
}
int
gnttab_resume(void)
{
if (max_nr_grant_frames() < nr_grant_frames)
return (ENOSYS);
return (gnttab_map(0, nr_grant_frames - 1));
}
int
gnttab_suspend(void)
{
int i;
for (i = 0; i < nr_grant_frames; i++)
pmap_kremove((vm_offset_t) shared + i * PAGE_SIZE);
return (0);
}
#else /* XENHVM */
#include <dev/xen/xenpci/xenpcivar.h>
static vm_paddr_t resume_frames;
static int
gnttab_map(unsigned int start_idx, unsigned int end_idx)
{
struct xen_add_to_physmap xatp;
unsigned int i = end_idx;
/*
* Loop backwards, so that the first hypercall has the largest index,
* ensuring that the table will grow only once.
*/
do {
xatp.domid = DOMID_SELF;
xatp.idx = i;
xatp.space = XENMAPSPACE_grant_table;
xatp.gpfn = (resume_frames >> PAGE_SHIFT) + i;
if (HYPERVISOR_memory_op(XENMEM_add_to_physmap, &xatp))
panic("HYPERVISOR_memory_op failed to map gnttab");
} while (i-- > start_idx);
if (shared == NULL) {
vm_offset_t area;
area = kmem_alloc_nofault(kernel_map,
PAGE_SIZE * max_nr_grant_frames());
KASSERT(area, ("can't allocate VM space for grant table"));
shared = (grant_entry_t *)area;
}
for (i = start_idx; i <= end_idx; i++) {
pmap_kenter((vm_offset_t) shared + i * PAGE_SIZE,
resume_frames + i * PAGE_SIZE);
}
return (0);
}
int
gnttab_resume(void)
{
int error;
unsigned int max_nr_gframes, nr_gframes;
nr_gframes = nr_grant_frames;
max_nr_gframes = max_nr_grant_frames();
if (max_nr_gframes < nr_gframes)
return (ENOSYS);
if (!resume_frames) {
error = xenpci_alloc_space(PAGE_SIZE * max_nr_gframes,
&resume_frames);
if (error) {
printf("error mapping gnttab share frames\n");
return (error);
}
}
return (gnttab_map(0, nr_gframes - 1));
}
#endif
static int
gnttab_expand(unsigned int req_entries)
{
int error;
unsigned int cur, extra;
cur = nr_grant_frames;
extra = ((req_entries + (GREFS_PER_GRANT_FRAME-1)) /
GREFS_PER_GRANT_FRAME);
if (cur + extra > max_nr_grant_frames())
return (ENOSPC);
error = gnttab_map(cur, cur + extra - 1);
if (!error)
error = grow_gnttab_list(extra);
return (error);
}
int
gnttab_init()
{
int i;
unsigned int max_nr_glist_frames;
unsigned int nr_init_grefs;
if (!is_running_on_xen())
return (ENODEV);
nr_grant_frames = 1;
boot_max_nr_grant_frames = __max_nr_grant_frames();
/* Determine the maximum number of frames required for the
* grant reference free list on the current hypervisor.
*/
max_nr_glist_frames = (boot_max_nr_grant_frames *
GREFS_PER_GRANT_FRAME /
(PAGE_SIZE / sizeof(grant_ref_t)));
gnttab_list = malloc(max_nr_glist_frames * sizeof(grant_ref_t *),
M_DEVBUF, M_NOWAIT);
if (gnttab_list == NULL)
return (ENOMEM);
for (i = 0; i < nr_grant_frames; i++) {
gnttab_list[i] = (grant_ref_t *)
malloc(PAGE_SIZE, M_DEVBUF, M_NOWAIT);
if (gnttab_list[i] == NULL)
goto ini_nomem;
}
if (gnttab_resume())
return (ENODEV);
nr_init_grefs = nr_grant_frames * GREFS_PER_GRANT_FRAME;
for (i = NR_RESERVED_ENTRIES; i < nr_init_grefs - 1; i++)
gnttab_entry(i) = i + 1;
gnttab_entry(nr_init_grefs - 1) = GNTTAB_LIST_END;
gnttab_free_count = nr_init_grefs - NR_RESERVED_ENTRIES;
gnttab_free_head = NR_RESERVED_ENTRIES;
if (bootverbose)
printf("Grant table initialized\n");
return (0);
ini_nomem:
for (i--; i >= 0; i--)
free(gnttab_list[i], M_DEVBUF);
free(gnttab_list, M_DEVBUF);
return (ENOMEM);
}
MTX_SYSINIT(gnttab, &gnttab_list_lock, "GNTTAB LOCK", MTX_DEF);