freebsd-skq/sys/amd64/vmm/vmm_mem.c
Neel Natu 318224bbe6 Merge projects/bhyve_npt_pmap into head.
Make the amd64/pmap code aware of nested page table mappings used by bhyve
guests. This allows bhyve to associate each guest with its own vmspace and
deal with nested page faults in the context of that vmspace. This also
enables features like accessed/dirty bit tracking, swapping to disk and
transparent superpage promotions of guest memory.

Guest vmspace:
Each bhyve guest has a unique vmspace to represent the physical memory
allocated to the guest. Each memory segment allocated by the guest is
mapped into the guest's address space via the 'vmspace->vm_map' and is
backed by an object of type OBJT_DEFAULT.

pmap types:
The amd64/pmap now understands two types of pmaps: PT_X86 and PT_EPT.

The PT_X86 pmap type is used by the vmspace associated with the host kernel
as well as user processes executing on the host. The PT_EPT pmap is used by
the vmspace associated with a bhyve guest.

Page Table Entries:
The EPT page table entries as mostly similar in functionality to regular
page table entries although there are some differences in terms of what
bits are used to express that functionality. For e.g. the dirty bit is
represented by bit 9 in the nested PTE as opposed to bit 6 in the regular
x86 PTE. Therefore the bitmask representing the dirty bit is now computed
at runtime based on the type of the pmap. Thus PG_M that was previously a
macro now becomes a local variable that is initialized at runtime using
'pmap_modified_bit(pmap)'.

An additional wrinkle associated with EPT mappings is that older Intel
processors don't have hardware support for tracking accessed/dirty bits in
the PTE. This means that the amd64/pmap code needs to emulate these bits to
provide proper accounting to the VM subsystem. This is achieved by using
the following mapping for EPT entries that need emulation of A/D bits:
               Bit Position           Interpreted By
PG_V               52                 software (accessed bit emulation handler)
PG_RW              53                 software (dirty bit emulation handler)
PG_A               0                  hardware (aka EPT_PG_RD)
PG_M               1                  hardware (aka EPT_PG_WR)

The idea to use the mapping listed above for A/D bit emulation came from
Alan Cox (alc@).

The final difference with respect to x86 PTEs is that some EPT implementations
do not support superpage mappings. This is recorded in the 'pm_flags' field
of the pmap.

TLB invalidation:
The amd64/pmap code has a number of ways to do invalidation of mappings
that may be cached in the TLB: single page, multiple pages in a range or the
entire TLB. All of these funnel into a single EPT invalidation routine called
'pmap_invalidate_ept()'. This routine bumps up the EPT generation number and
sends an IPI to the host cpus that are executing the guest's vcpus. On a
subsequent entry into the guest it will detect that the EPT has changed and
invalidate the mappings from the TLB.

Guest memory access:
Since the guest memory is no longer wired we need to hold the host physical
page that backs the guest physical page before we can access it. The helper
functions 'vm_gpa_hold()/vm_gpa_release()' are available for this purpose.

PCI passthru:
Guest's with PCI passthru devices will wire the entire guest physical address
space. The MMIO BAR associated with the passthru device is backed by a
vm_object of type OBJT_SG. An IOMMU domain is created only for guest's that
have one or more PCI passthru devices attached to them.

Limitations:
There isn't a way to map a guest physical page without execute permissions.
This is because the amd64/pmap code interprets the guest physical mappings as
user mappings since they are numerically below VM_MAXUSER_ADDRESS. Since PG_U
shares the same bit position as EPT_PG_EXECUTE all guest mappings become
automatically executable.

Thanks to Alan Cox and Konstantin Belousov for their rigorous code reviews
as well as their support and encouragement.

Thanks for John Baldwin for reviewing the use of OBJT_SG as the backing
object for pci passthru mmio regions.

Special thanks to Peter Holm for testing the patch on short notice.

Approved by:	re
Discussed with:	grehan
Reviewed by:	alc, kib
Tested by:	pho
2013-10-05 21:22:35 +00:00

155 lines
4.1 KiB
C

/*-
* Copyright (c) 2011 NetApp, Inc.
* All rights reserved.
*
* 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.
*
* THIS SOFTWARE IS PROVIDED BY NETAPP, INC ``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 NETAPP, INC 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.
*
* $FreeBSD$
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/malloc.h>
#include <sys/sglist.h>
#include <sys/lock.h>
#include <sys/rwlock.h>
#include <vm/vm.h>
#include <vm/vm_param.h>
#include <vm/pmap.h>
#include <vm/vm_map.h>
#include <vm/vm_object.h>
#include <vm/vm_page.h>
#include <vm/vm_pager.h>
#include <machine/md_var.h>
#include "vmm_mem.h"
int
vmm_mem_init(void)
{
return (0);
}
vm_object_t
vmm_mmio_alloc(struct vmspace *vmspace, vm_paddr_t gpa, size_t len,
vm_paddr_t hpa)
{
int error;
vm_object_t obj;
struct sglist *sg;
sg = sglist_alloc(1, M_WAITOK);
error = sglist_append_phys(sg, hpa, len);
KASSERT(error == 0, ("error %d appending physaddr to sglist", error));
obj = vm_pager_allocate(OBJT_SG, sg, len, VM_PROT_RW, 0, NULL);
if (obj != NULL) {
/*
* VT-x ignores the MTRR settings when figuring out the
* memory type for translations obtained through EPT.
*
* Therefore we explicitly force the pages provided by
* this object to be mapped as uncacheable.
*/
VM_OBJECT_WLOCK(obj);
error = vm_object_set_memattr(obj, VM_MEMATTR_UNCACHEABLE);
VM_OBJECT_WUNLOCK(obj);
if (error != KERN_SUCCESS) {
panic("vmm_mmio_alloc: vm_object_set_memattr error %d",
error);
}
error = vm_map_find(&vmspace->vm_map, obj, 0, &gpa, len, 0,
VMFS_NO_SPACE, VM_PROT_RW, VM_PROT_RW, 0);
if (error != KERN_SUCCESS) {
vm_object_deallocate(obj);
obj = NULL;
}
}
/*
* Drop the reference on the sglist.
*
* If the scatter/gather object was successfully allocated then it
* has incremented the reference count on the sglist. Dropping the
* initial reference count ensures that the sglist will be freed
* when the object is deallocated.
*
* If the object could not be allocated then we end up freeing the
* sglist.
*/
sglist_free(sg);
return (obj);
}
void
vmm_mmio_free(struct vmspace *vmspace, vm_paddr_t gpa, size_t len)
{
vm_map_remove(&vmspace->vm_map, gpa, gpa + len);
}
vm_object_t
vmm_mem_alloc(struct vmspace *vmspace, vm_paddr_t gpa, size_t len)
{
int error;
vm_object_t obj;
if (gpa & PAGE_MASK)
panic("vmm_mem_alloc: invalid gpa %#lx", gpa);
if (len == 0 || (len & PAGE_MASK) != 0)
panic("vmm_mem_alloc: invalid allocation size %lu", len);
obj = vm_object_allocate(OBJT_DEFAULT, len >> PAGE_SHIFT);
if (obj != NULL) {
error = vm_map_find(&vmspace->vm_map, obj, 0, &gpa, len, 0,
VMFS_NO_SPACE, VM_PROT_ALL, VM_PROT_ALL, 0);
if (error != KERN_SUCCESS) {
vm_object_deallocate(obj);
obj = NULL;
}
}
return (obj);
}
void
vmm_mem_free(struct vmspace *vmspace, vm_paddr_t gpa, size_t len)
{
vm_map_remove(&vmspace->vm_map, gpa, gpa + len);
}
vm_paddr_t
vmm_mem_maxaddr(void)
{
return (ptoa(Maxmem));
}