static void
p2m_remove_page(struct p2m_domain *p2m, unsigned long gfn, unsigned long mfn,
unsigned int page_order)
{
unsigned long i;
mfn_t mfn_return;
p2m_type_t t;
p2m_access_t a;
if ( !paging_mode_translate(p2m->domain) )
{
if ( need_iommu(p2m->domain) )
for ( i = 0; i < (1 << page_order); i++ )
iommu_unmap_page(p2m->domain, mfn + i);
return;
}
ASSERT(gfn_locked_by_me(p2m, gfn));
P2M_DEBUG("removing gfn=%#lx mfn=%#lx\n", gfn, mfn);
if ( mfn_valid(_mfn(mfn)) )
{
for ( i = 0; i < (1UL << page_order); i++ )
{
mfn_return = p2m->get_entry(p2m, gfn + i, &t, &a, 0, NULL);
if ( !p2m_is_grant(t) && !p2m_is_shared(t) )
set_gpfn_from_mfn(mfn+i, INVALID_M2P_ENTRY);
ASSERT( !p2m_is_valid(t) || mfn + i == mfn_x(mfn_return) );
}
}
set_p2m_entry(p2m, gfn, _mfn(INVALID_MFN), page_order, p2m_invalid, p2m->default_access);
}
int
clear_mmio_p2m_entry(struct domain *d, unsigned long gfn)
{
int rc = 0;
mfn_t mfn;
p2m_access_t a;
p2m_type_t t;
struct p2m_domain *p2m = p2m_get_hostp2m(d);
if ( !paging_mode_translate(d) )
return 0;
gfn_lock(p2m, gfn, 0);
mfn = p2m->get_entry(p2m, gfn, &t, &a, 0, NULL);
/* Do not use mfn_valid() here as it will usually fail for MMIO pages. */
if ( (INVALID_MFN == mfn_x(mfn)) || (t != p2m_mmio_direct) )
{
gdprintk(XENLOG_ERR,
"clear_mmio_p2m_entry: gfn_to_mfn failed! gfn=%08lx\n", gfn);
goto out;
}
rc = set_p2m_entry(p2m, gfn, _mfn(INVALID_MFN), PAGE_ORDER_4K, p2m_invalid, p2m->default_access);
out:
gfn_unlock(p2m, gfn, 0);
return rc;
}
static void pvpmu_finish(struct domain *d, xen_pmu_params_t *params)
{
struct vcpu *v;
struct vpmu_struct *vpmu;
uint64_t mfn;
void *xenpmu_data;
if ( (params->vcpu >= d->max_vcpus) || (d->vcpu[params->vcpu] == NULL) )
return;
v = d->vcpu[params->vcpu];
if ( v != current )
vcpu_pause(v);
vpmu = vcpu_vpmu(v);
spin_lock(&vpmu->vpmu_lock);
vpmu_arch_destroy(v);
xenpmu_data = vpmu->xenpmu_data;
vpmu->xenpmu_data = NULL;
spin_unlock(&vpmu->vpmu_lock);
if ( xenpmu_data )
{
mfn = domain_page_map_to_mfn(xenpmu_data);
ASSERT(mfn_valid(_mfn(mfn)));
unmap_domain_page_global(xenpmu_data);
put_page_and_type(mfn_to_page(mfn));
}
if ( v != current )
vcpu_unpause(v);
}
int set_p2m_entry(struct p2m_domain *p2m, unsigned long gfn, mfn_t mfn,
unsigned int page_order, p2m_type_t p2mt, p2m_access_t p2ma)
{
struct domain *d = p2m->domain;
unsigned long todo = 1ul << page_order;
unsigned int order;
int rc = 1;
ASSERT(gfn_locked_by_me(p2m, gfn));
while ( todo )
{
if ( hap_enabled(d) )
order = ( (((gfn | mfn_x(mfn) | todo) & ((1ul << PAGE_ORDER_1G) - 1)) == 0) &&
hvm_hap_has_1gb(d) && opt_hap_1gb ) ? PAGE_ORDER_1G :
((((gfn | mfn_x(mfn) | todo) & ((1ul << PAGE_ORDER_2M) - 1)) == 0) &&
hvm_hap_has_2mb(d) && opt_hap_2mb) ? PAGE_ORDER_2M : PAGE_ORDER_4K;
else
order = 0;
if ( !p2m->set_entry(p2m, gfn, mfn, order, p2mt, p2ma) )
rc = 0;
gfn += 1ul << order;
if ( mfn_x(mfn) != INVALID_MFN )
mfn = _mfn(mfn_x(mfn) + (1ul << order));
todo -= 1ul << order;
}
return rc;
}
static int __init modify_identity_mmio(struct domain *d, unsigned long pfn,
unsigned long nr_pages, const bool map)
{
int rc;
for ( ; ; )
{
rc = (map ? map_mmio_regions : unmap_mmio_regions)
(d, _gfn(pfn), nr_pages, _mfn(pfn));
if ( rc == 0 )
break;
if ( rc < 0 )
{
printk(XENLOG_WARNING
"Failed to identity %smap [%#lx,%#lx) for d%d: %d\n",
map ? "" : "un", pfn, pfn + nr_pages, d->domain_id, rc);
break;
}
nr_pages -= rc;
pfn += rc;
process_pending_softirqs();
}
return rc;
}
/* Assign the low 1MB to Dom0. */
static void __init pvh_steal_low_ram(struct domain *d, unsigned long start,
unsigned long nr_pages)
{
unsigned long mfn;
ASSERT(start + nr_pages <= PFN_DOWN(MB(1)));
for ( mfn = start; mfn < start + nr_pages; mfn++ )
{
struct page_info *pg = mfn_to_page(mfn);
int rc;
rc = unshare_xen_page_with_guest(pg, dom_io);
if ( rc )
{
printk("Unable to unshare Xen mfn %#lx: %d\n", mfn, rc);
continue;
}
share_xen_page_with_guest(pg, d, XENSHARE_writable);
rc = guest_physmap_add_entry(d, _gfn(mfn), _mfn(mfn), 0, p2m_ram_rw);
if ( rc )
printk("Unable to add mfn %#lx to p2m: %d\n", mfn, rc);
}
}
mfn_t __get_gfn_type_access(struct p2m_domain *p2m, unsigned long gfn,
p2m_type_t *t, p2m_access_t *a, p2m_query_t q,
unsigned int *page_order, bool_t locked)
{
mfn_t mfn;
/* Unshare makes no sense withuot populate. */
if ( q & P2M_UNSHARE )
q |= P2M_ALLOC;
if ( !p2m || !paging_mode_translate(p2m->domain) )
{
/* Not necessarily true, but for non-translated guests, we claim
* it's the most generic kind of memory */
*t = p2m_ram_rw;
return _mfn(gfn);
}
if ( locked )
/* Grab the lock here, don't release until put_gfn */
gfn_lock(p2m, gfn, 0);
mfn = p2m->get_entry(p2m, gfn, t, a, q, page_order);
if ( (q & P2M_UNSHARE) && p2m_is_shared(*t) )
{
ASSERT(!p2m_is_nestedp2m(p2m));
/* Try to unshare. If we fail, communicate ENOMEM without
* sleeping. */
if ( mem_sharing_unshare_page(p2m->domain, gfn, 0) < 0 )
(void)mem_sharing_notify_enomem(p2m->domain, gfn, 0);
mfn = p2m->get_entry(p2m, gfn, t, a, q, page_order);
}
if (unlikely((p2m_is_broken(*t))))
{
/* Return invalid_mfn to avoid caller's access */
mfn = _mfn(INVALID_MFN);
if ( q & P2M_ALLOC )
domain_crash(p2m->domain);
}
return mfn;
}
/**
* p2m_mem_paging_evict - Mark a guest page as paged-out
* @d: guest domain
* @gfn: guest page to evict
*
* Returns 0 for success or negative errno values if eviction is not possible.
*
* p2m_mem_paging_evict() is called by the pager and will free a guest page and
* release it back to Xen. If the following conditions are met the page can be
* freed:
* - the gfn is backed by a mfn
* - the gfn was nominated
* - the mfn has still exactly one user and has no special meaning
*
* After successful nomination some other process could have mapped the page. In
* this case eviction can not be done. If the gfn was populated before the pager
* could evict it, eviction can not be done either. In this case the gfn is
* still backed by a mfn.
*/
int p2m_mem_paging_evict(struct domain *d, unsigned long gfn)
{
struct page_info *page;
p2m_type_t p2mt;
p2m_access_t a;
mfn_t mfn;
struct p2m_domain *p2m = p2m_get_hostp2m(d);
int ret = -EBUSY;
gfn_lock(p2m, gfn, 0);
/* Get mfn */
mfn = p2m->get_entry(p2m, gfn, &p2mt, &a, 0, NULL);
if ( unlikely(!mfn_valid(mfn)) )
goto out;
/* Allow only nominated pages */
if ( p2mt != p2m_ram_paging_out )
goto out;
/* Get the page so it doesn't get modified under Xen's feet */
page = mfn_to_page(mfn);
if ( unlikely(!get_page(page, d)) )
goto out;
/* Check page count and type once more */
if ( (page->count_info & (PGC_count_mask | PGC_allocated)) !=
(2 | PGC_allocated) )
goto out_put;
if ( (page->u.inuse.type_info & PGT_count_mask) != 0 )
goto out_put;
/* Decrement guest domain's ref count of the page */
if ( test_and_clear_bit(_PGC_allocated, &page->count_info) )
put_page(page);
/* Remove mapping from p2m table */
set_p2m_entry(p2m, gfn, _mfn(INVALID_MFN), PAGE_ORDER_4K, p2m_ram_paged, a);
/* Clear content before returning the page to Xen */
scrub_one_page(page);
/* Track number of paged gfns */
atomic_inc(&d->paged_pages);
ret = 0;
out_put:
/* Put the page back so it gets freed */
put_page(page);
out:
gfn_unlock(p2m, gfn, 0);
return ret;
}
// Allocate a new p2m table for a domain.
//
// The structure of the p2m table is that of a pagetable for xen (i.e. it is
// controlled by CONFIG_PAGING_LEVELS).
//
// Returns 0 for success or -errno.
//
int p2m_alloc_table(struct p2m_domain *p2m)
{
struct page_info *p2m_top;
struct domain *d = p2m->domain;
p2m_lock(p2m);
if ( !p2m_is_nestedp2m(p2m)
&& !page_list_empty(&d->page_list) )
{
P2M_ERROR("dom %d already has memory allocated\n", d->domain_id);
p2m_unlock(p2m);
return -EINVAL;
}
if ( pagetable_get_pfn(p2m_get_pagetable(p2m)) != 0 )
{
P2M_ERROR("p2m already allocated for this domain\n");
p2m_unlock(p2m);
return -EINVAL;
}
P2M_PRINTK("allocating p2m table\n");
p2m_top = p2m_alloc_ptp(p2m, PGT_l4_page_table);
if ( p2m_top == NULL )
{
p2m_unlock(p2m);
return -ENOMEM;
}
p2m->phys_table = pagetable_from_mfn(page_to_mfn(p2m_top));
if ( hap_enabled(d) )
iommu_share_p2m_table(d);
P2M_PRINTK("populating p2m table\n");
/* Initialise physmap tables for slot zero. Other code assumes this. */
p2m->defer_nested_flush = 1;
if ( !set_p2m_entry(p2m, 0, _mfn(INVALID_MFN), PAGE_ORDER_4K,
p2m_invalid, p2m->default_access) )
goto error;
p2m->defer_nested_flush = 0;
P2M_PRINTK("p2m table initialised (%u pages)\n", page_count);
p2m_unlock(p2m);
return 0;
spin_unlock(&p2m->domain->page_alloc_lock);
error:
P2M_PRINTK("failed to initialize p2m table, gfn=%05lx, mfn=%"
PRI_mfn "\n", gfn, mfn_x(mfn));
p2m_unlock(p2m);
return -ENOMEM;
}
/* Free intermediate tables from a p2m sub-tree */
static void
p2m_free_entry(struct p2m_domain *p2m, l1_pgentry_t *p2m_entry, int page_order)
{
/* End if the entry is a leaf entry. */
if ( page_order == PAGE_ORDER_4K
|| !(l1e_get_flags(*p2m_entry) & _PAGE_PRESENT)
|| (l1e_get_flags(*p2m_entry) & _PAGE_PSE) )
return;
if ( page_order > PAGE_ORDER_2M )
{
l1_pgentry_t *l3_table = map_domain_page(_mfn(l1e_get_pfn(*p2m_entry)));
for ( int i = 0; i < L3_PAGETABLE_ENTRIES; i++ )
p2m_free_entry(p2m, l3_table + i, page_order - 9);
unmap_domain_page(l3_table);
}
p2m_free_ptp(p2m, mfn_to_page(_mfn(l1e_get_pfn(*p2m_entry))));
}
/* Populate a HVM memory range using the biggest possible order. */
static int __init pvh_populate_memory_range(struct domain *d,
unsigned long start,
unsigned long nr_pages)
{
unsigned int order, i = 0;
struct page_info *page;
int rc;
#define MAP_MAX_ITER 64
order = MAX_ORDER;
while ( nr_pages != 0 )
{
unsigned int range_order = get_order_from_pages(nr_pages + 1);
order = min(range_order ? range_order - 1 : 0, order);
page = alloc_domheap_pages(d, order, dom0_memflags);
if ( page == NULL )
{
if ( order == 0 && dom0_memflags )
{
/* Try again without any dom0_memflags. */
dom0_memflags = 0;
order = MAX_ORDER;
continue;
}
if ( order == 0 )
{
printk("Unable to allocate memory with order 0!\n");
return -ENOMEM;
}
order--;
continue;
}
rc = guest_physmap_add_page(d, _gfn(start), _mfn(page_to_mfn(page)),
order);
if ( rc != 0 )
{
printk("Failed to populate memory: [%#lx,%lx): %d\n",
start, start + (1UL << order), rc);
return -ENOMEM;
}
start += 1UL << order;
nr_pages -= 1UL << order;
if ( (++i % MAP_MAX_ITER) == 0 )
process_pending_softirqs();
}
return 0;
#undef MAP_MAX_ITER
}
void flush_page_to_ram(unsigned long mfn)
{
void *v = map_domain_page(_mfn(mfn));
clean_and_invalidate_dcache_va_range(v, PAGE_SIZE);
unmap_domain_page(v);
/*
* For some of the instruction cache (such as VIPT), the entire I-Cache
* needs to be flushed to guarantee that all the aliases of a given
* physical address will be removed from the cache.
* Invalidating the I-Cache by VA highly depends on the behavior of the
* I-Cache (See D4.9.2 in ARM DDI 0487A.k_iss10775). Instead of using flush
* by VA on select platforms, we just flush the entire cache here.
*/
invalidate_icache();
}
static void mca_init_bank(enum mca_source who,
struct mc_info *mi, int bank)
{
struct mcinfo_bank *mib;
if (!mi)
return;
mib = x86_mcinfo_reserve(mi, sizeof(*mib), MC_TYPE_BANK);
if (!mib)
{
mi->flags |= MCINFO_FLAGS_UNCOMPLETE;
return;
}
mib->mc_status = mca_rdmsr(MSR_IA32_MCx_STATUS(bank));
mib->mc_bank = bank;
mib->mc_domid = DOMID_INVALID;
if (mib->mc_status & MCi_STATUS_MISCV)
mib->mc_misc = mca_rdmsr(MSR_IA32_MCx_MISC(bank));
if (mib->mc_status & MCi_STATUS_ADDRV)
mib->mc_addr = mca_rdmsr(MSR_IA32_MCx_ADDR(bank));
if ((mib->mc_status & MCi_STATUS_MISCV) &&
(mib->mc_status & MCi_STATUS_ADDRV) &&
(mc_check_addr(mib->mc_status, mib->mc_misc, MC_ADDR_PHYSICAL)) &&
(who == MCA_POLLER || who == MCA_CMCI_HANDLER) &&
(mfn_valid(_mfn(paddr_to_pfn(mib->mc_addr)))))
{
struct domain *d;
d = maddr_get_owner(mib->mc_addr);
if (d)
mib->mc_domid = d->domain_id;
}
if (who == MCA_CMCI_HANDLER) {
mib->mc_ctrl2 = mca_rdmsr(MSR_IA32_MC0_CTL2 + bank);
mib->mc_tsc = rdtsc();
}
}
int p2m_set_altp2m_mem_access(struct domain *d, struct p2m_domain *hp2m,
struct p2m_domain *ap2m, p2m_access_t a,
gfn_t gfn)
{
mfn_t mfn;
p2m_type_t t;
p2m_access_t old_a;
unsigned int page_order;
unsigned long gfn_l = gfn_x(gfn);
int rc;
mfn = ap2m->get_entry(ap2m, gfn_l, &t, &old_a, 0, NULL, NULL);
/* Check host p2m if no valid entry in alternate */
if ( !mfn_valid(mfn) )
{
mfn = __get_gfn_type_access(hp2m, gfn_l, &t, &old_a,
P2M_ALLOC | P2M_UNSHARE, &page_order, 0);
rc = -ESRCH;
if ( !mfn_valid(mfn) || t != p2m_ram_rw )
return rc;
/* If this is a superpage, copy that first */
if ( page_order != PAGE_ORDER_4K )
{
unsigned long mask = ~((1UL << page_order) - 1);
unsigned long gfn2_l = gfn_l & mask;
mfn_t mfn2 = _mfn(mfn_x(mfn) & mask);
rc = ap2m->set_entry(ap2m, gfn2_l, mfn2, page_order, t, old_a, 1);
if ( rc )
return rc;
}
}
return ap2m->set_entry(ap2m, gfn_l, mfn, PAGE_ORDER_4K, t, a,
(current->domain != d));
}
/* Read the current domain's p2m table (through the linear mapping). */
static mfn_t p2m_gfn_to_mfn_current(struct p2m_domain *p2m,
unsigned long gfn, p2m_type_t *t,
p2m_access_t *a, p2m_query_t q,
unsigned int *page_order)
{
mfn_t mfn = _mfn(INVALID_MFN);
p2m_type_t p2mt = p2m_mmio_dm;
paddr_t addr = ((paddr_t)gfn) << PAGE_SHIFT;
/* XXX This is for compatibility with the old model, where anything not
* XXX marked as RAM was considered to be emulated MMIO space.
* XXX Once we start explicitly registering MMIO regions in the p2m
* XXX we will return p2m_invalid for unmapped gfns */
l1_pgentry_t l1e = l1e_empty(), *p2m_entry;
l2_pgentry_t l2e = l2e_empty();
int ret;
#if CONFIG_PAGING_LEVELS >= 4
l3_pgentry_t l3e = l3e_empty();
#endif
ASSERT(gfn < (RO_MPT_VIRT_END - RO_MPT_VIRT_START)
/ sizeof(l1_pgentry_t));
#if CONFIG_PAGING_LEVELS >= 4
/*
* Read & process L3
*/
p2m_entry = (l1_pgentry_t *)
&__linear_l2_table[l2_linear_offset(RO_MPT_VIRT_START)
+ l3_linear_offset(addr)];
pod_retry_l3:
ret = __copy_from_user(&l3e, p2m_entry, sizeof(l3e));
if ( ret != 0 || !(l3e_get_flags(l3e) & _PAGE_PRESENT) )
{
if ( (l3e_get_flags(l3e) & _PAGE_PSE) &&
(p2m_flags_to_type(l3e_get_flags(l3e)) == p2m_populate_on_demand) )
{
/* The read has succeeded, so we know that mapping exists */
if ( q & P2M_ALLOC )
{
if ( !p2m_pod_demand_populate(p2m, gfn, PAGE_ORDER_1G, q) )
goto pod_retry_l3;
p2mt = p2m_invalid;
gdprintk(XENLOG_ERR, "%s: Allocate 1GB failed!\n", __func__);
goto out;
}
else
{
p2mt = p2m_populate_on_demand;
goto out;
}
}
goto pod_retry_l2;
}
if ( l3e_get_flags(l3e) & _PAGE_PSE )
{
p2mt = p2m_flags_to_type(l3e_get_flags(l3e));
ASSERT(l3e_get_pfn(l3e) != INVALID_MFN || !p2m_is_ram(p2mt));
if (p2m_is_valid(p2mt) )
mfn = _mfn(l3e_get_pfn(l3e) +
l2_table_offset(addr) * L1_PAGETABLE_ENTRIES +
l1_table_offset(addr));
else
p2mt = p2m_mmio_dm;
if ( page_order )
*page_order = PAGE_ORDER_1G;
goto out;
}
#endif
/*
* Read & process L2
*/
p2m_entry = &__linear_l1_table[l1_linear_offset(RO_MPT_VIRT_START)
+ l2_linear_offset(addr)];
pod_retry_l2:
ret = __copy_from_user(&l2e,
p2m_entry,
sizeof(l2e));
if ( ret != 0
|| !(l2e_get_flags(l2e) & _PAGE_PRESENT) )
{
if( (l2e_get_flags(l2e) & _PAGE_PSE)
&& ( p2m_flags_to_type(l2e_get_flags(l2e))
== p2m_populate_on_demand ) )
{
/* The read has succeeded, so we know that the mapping
* exits at this point. */
if ( q & P2M_ALLOC )
{
if ( !p2m_pod_demand_populate(p2m, gfn,
PAGE_ORDER_2M, q) )
goto pod_retry_l2;
/* Allocate failed. */
p2mt = p2m_invalid;
printk("%s: Allocate failed!\n", __func__);
goto out;
}
else
{
p2mt = p2m_populate_on_demand;
goto out;
}
}
goto pod_retry_l1;
}
if (l2e_get_flags(l2e) & _PAGE_PSE)
{
p2mt = p2m_flags_to_type(l2e_get_flags(l2e));
ASSERT(l2e_get_pfn(l2e) != INVALID_MFN || !p2m_is_ram(p2mt));
if ( p2m_is_valid(p2mt) )
mfn = _mfn(l2e_get_pfn(l2e) + l1_table_offset(addr));
else
p2mt = p2m_mmio_dm;
if ( page_order )
*page_order = PAGE_ORDER_2M;
goto out;
}
/*
* Read and process L1
*/
/* Need to __copy_from_user because the p2m is sparse and this
* part might not exist */
pod_retry_l1:
p2m_entry = &phys_to_machine_mapping[gfn];
ret = __copy_from_user(&l1e,
p2m_entry,
sizeof(l1e));
if ( ret == 0 ) {
unsigned long l1e_mfn = l1e_get_pfn(l1e);
p2mt = p2m_flags_to_type(l1e_get_flags(l1e));
ASSERT( mfn_valid(_mfn(l1e_mfn)) || !p2m_is_ram(p2mt) ||
p2m_is_paging(p2mt) );
if ( p2mt == p2m_populate_on_demand )
{
/* The read has succeeded, so we know that the mapping
* exits at this point. */
if ( q & P2M_ALLOC )
{
if ( !p2m_pod_demand_populate(p2m, gfn,
PAGE_ORDER_4K, q) )
goto pod_retry_l1;
/* Allocate failed. */
p2mt = p2m_invalid;
goto out;
}
else
{
p2mt = p2m_populate_on_demand;
goto out;
}
}
if ( p2m_is_valid(p2mt) || p2m_is_grant(p2mt) )
mfn = _mfn(l1e_mfn);
else
/* XXX see above */
p2mt = p2m_mmio_dm;
}
if ( page_order )
*page_order = PAGE_ORDER_4K;
out:
*t = p2mt;
return mfn;
}
/*
* Handle possibly necessary P2M type re-calculation (U flag clear for a
* present entry) for the entries in the page table hierarchy for the given
* GFN. Propagate the re-calculation flag down to the next page table level
* for entries not involved in the translation of the given GFN.
*/
static int do_recalc(struct p2m_domain *p2m, unsigned long gfn)
{
void *table;
unsigned long gfn_remainder = gfn;
unsigned int level = 4;
l1_pgentry_t *pent;
int err = 0;
table = map_domain_page(pagetable_get_mfn(p2m_get_pagetable(p2m)));
while ( --level )
{
unsigned long remainder = gfn_remainder;
pent = p2m_find_entry(table, &remainder, gfn,
level * PAGETABLE_ORDER, 1 << PAGETABLE_ORDER);
if ( !pent || !(l1e_get_flags(*pent) & _PAGE_PRESENT) )
goto out;
if ( l1e_get_flags(*pent) & _PAGE_PSE )
{
unsigned long mask = ~0UL << (level * PAGETABLE_ORDER);
if ( !needs_recalc(l1, *pent) ||
!p2m_is_changeable(p2m_flags_to_type(l1e_get_flags(*pent))) ||
p2m_is_logdirty_range(p2m, gfn & mask, gfn | ~mask) >= 0 )
break;
}
err = p2m_next_level(p2m, &table, &gfn_remainder, gfn,
level * PAGETABLE_ORDER, 1 << PAGETABLE_ORDER,
pgt[level - 1], 0);
if ( err )
goto out;
if ( needs_recalc(l1, *pent) )
{
l1_pgentry_t e = *pent, *ptab = table;
unsigned int i;
if ( !valid_recalc(l1, e) )
P2M_DEBUG("bogus recalc state at d%d:%lx:%u\n",
p2m->domain->domain_id, gfn, level);
remainder = gfn_remainder;
for ( i = 0; i < (1 << PAGETABLE_ORDER); ++i )
{
l1_pgentry_t ent = ptab[i];
if ( (l1e_get_flags(ent) & _PAGE_PRESENT) &&
!needs_recalc(l1, ent) )
{
set_recalc(l1, ent);
p2m->write_p2m_entry(p2m, gfn - remainder, &ptab[i],
ent, level);
}
remainder -= 1UL << ((level - 1) * PAGETABLE_ORDER);
}
smp_wmb();
clear_recalc(l1, e);
p2m->write_p2m_entry(p2m, gfn, pent, e, level + 1);
}
unmap_domain_page((void *)((unsigned long)pent & PAGE_MASK));
}
pent = p2m_find_entry(table, &gfn_remainder, gfn,
level * PAGETABLE_ORDER, 1 << PAGETABLE_ORDER);
if ( pent && (l1e_get_flags(*pent) & _PAGE_PRESENT) &&
needs_recalc(l1, *pent) )
{
l1_pgentry_t e = *pent;
if ( !valid_recalc(l1, e) )
P2M_DEBUG("bogus recalc leaf at d%d:%lx:%u\n",
p2m->domain->domain_id, gfn, level);
if ( p2m_is_changeable(p2m_flags_to_type(l1e_get_flags(e))) )
{
unsigned long mask = ~0UL << (level * PAGETABLE_ORDER);
p2m_type_t p2mt = p2m_is_logdirty_range(p2m, gfn & mask, gfn | ~mask)
? p2m_ram_logdirty : p2m_ram_rw;
unsigned long mfn = l1e_get_pfn(e);
unsigned long flags = p2m_type_to_flags(p2mt, _mfn(mfn));
if ( level )
{
if ( flags & _PAGE_PAT )
{
BUILD_BUG_ON(_PAGE_PAT != _PAGE_PSE);
mfn |= _PAGE_PSE_PAT >> PAGE_SHIFT;
}
else
mfn &= ~(_PAGE_PSE_PAT >> PAGE_SHIFT);
flags |= _PAGE_PSE;
}
/* Returns: 0 for success, -errno for failure */
static int
p2m_next_level(struct p2m_domain *p2m, void **table,
unsigned long *gfn_remainder, unsigned long gfn, u32 shift,
u32 max, unsigned long type, bool_t unmap)
{
l1_pgentry_t *l1_entry;
l1_pgentry_t *p2m_entry;
l1_pgentry_t new_entry;
void *next;
int i;
if ( !(p2m_entry = p2m_find_entry(*table, gfn_remainder, gfn,
shift, max)) )
return -ENOENT;
/* PoD/paging: Not present doesn't imply empty. */
if ( !l1e_get_flags(*p2m_entry) )
{
struct page_info *pg;
pg = p2m_alloc_ptp(p2m, type);
if ( pg == NULL )
return -ENOMEM;
new_entry = l1e_from_pfn(mfn_x(page_to_mfn(pg)),
P2M_BASE_FLAGS | _PAGE_RW);
switch ( type ) {
case PGT_l3_page_table:
p2m_add_iommu_flags(&new_entry, 3, IOMMUF_readable|IOMMUF_writable);
p2m->write_p2m_entry(p2m, gfn, p2m_entry, new_entry, 4);
break;
case PGT_l2_page_table:
p2m_add_iommu_flags(&new_entry, 2, IOMMUF_readable|IOMMUF_writable);
p2m->write_p2m_entry(p2m, gfn, p2m_entry, new_entry, 3);
break;
case PGT_l1_page_table:
p2m_add_iommu_flags(&new_entry, 1, IOMMUF_readable|IOMMUF_writable);
p2m->write_p2m_entry(p2m, gfn, p2m_entry, new_entry, 2);
break;
default:
BUG();
break;
}
}
ASSERT(l1e_get_flags(*p2m_entry) & (_PAGE_PRESENT|_PAGE_PSE));
/* split 1GB pages into 2MB pages */
if ( type == PGT_l2_page_table && (l1e_get_flags(*p2m_entry) & _PAGE_PSE) )
{
unsigned long flags, pfn;
struct page_info *pg;
pg = p2m_alloc_ptp(p2m, PGT_l2_page_table);
if ( pg == NULL )
return -ENOMEM;
flags = l1e_get_flags(*p2m_entry);
pfn = l1e_get_pfn(*p2m_entry);
l1_entry = __map_domain_page(pg);
for ( i = 0; i < L2_PAGETABLE_ENTRIES; i++ )
{
new_entry = l1e_from_pfn(pfn + (i * L1_PAGETABLE_ENTRIES), flags);
p2m_add_iommu_flags(&new_entry, 1, IOMMUF_readable|IOMMUF_writable);
p2m->write_p2m_entry(p2m, gfn, l1_entry + i, new_entry, 2);
}
unmap_domain_page(l1_entry);
new_entry = l1e_from_pfn(mfn_x(page_to_mfn(pg)),
P2M_BASE_FLAGS | _PAGE_RW); /* disable PSE */
p2m_add_iommu_flags(&new_entry, 2, IOMMUF_readable|IOMMUF_writable);
p2m->write_p2m_entry(p2m, gfn, p2m_entry, new_entry, 3);
}
/* split single 2MB large page into 4KB page in P2M table */
if ( type == PGT_l1_page_table && (l1e_get_flags(*p2m_entry) & _PAGE_PSE) )
{
unsigned long flags, pfn;
struct page_info *pg;
pg = p2m_alloc_ptp(p2m, PGT_l1_page_table);
if ( pg == NULL )
return -ENOMEM;
/* New splintered mappings inherit the flags of the old superpage,
* with a little reorganisation for the _PAGE_PSE_PAT bit. */
flags = l1e_get_flags(*p2m_entry);
pfn = l1e_get_pfn(*p2m_entry);
if ( pfn & 1 ) /* ==> _PAGE_PSE_PAT was set */
pfn -= 1; /* Clear it; _PAGE_PSE becomes _PAGE_PAT */
else
flags &= ~_PAGE_PSE; /* Clear _PAGE_PSE (== _PAGE_PAT) */
l1_entry = __map_domain_page(pg);
for ( i = 0; i < L1_PAGETABLE_ENTRIES; i++ )
{
new_entry = l1e_from_pfn(pfn + i, flags);
p2m_add_iommu_flags(&new_entry, 0, 0);
p2m->write_p2m_entry(p2m, gfn, l1_entry + i, new_entry, 1);
}
unmap_domain_page(l1_entry);
new_entry = l1e_from_pfn(mfn_x(page_to_mfn(pg)),
P2M_BASE_FLAGS | _PAGE_RW);
p2m_add_iommu_flags(&new_entry, 1, IOMMUF_readable|IOMMUF_writable);
p2m->write_p2m_entry(p2m, gfn, p2m_entry, new_entry, 2);
}
next = map_domain_page(_mfn(l1e_get_pfn(*p2m_entry)));
if ( unmap )
unmap_domain_page(*table);
*table = next;
return 0;
}
void
mc_memerr_dhandler(struct mca_binfo *binfo,
enum mce_result *result,
struct cpu_user_regs *regs)
{
struct mcinfo_bank *bank = binfo->mib;
struct mcinfo_global *global = binfo->mig;
struct domain *d;
unsigned long mfn, gfn;
uint32_t status;
int vmce_vcpuid;
if (!mc_check_addr(bank->mc_status, bank->mc_misc, MC_ADDR_PHYSICAL)) {
dprintk(XENLOG_WARNING,
"No physical address provided for memory error\n");
return;
}
mfn = bank->mc_addr >> PAGE_SHIFT;
if (offline_page(mfn, 1, &status))
{
dprintk(XENLOG_WARNING,
"Failed to offline page %lx for MCE error\n", mfn);
return;
}
mci_action_add_pageoffline(binfo->bank, binfo->mi, mfn, status);
/* This is free page */
if (status & PG_OFFLINE_OFFLINED)
*result = MCER_RECOVERED;
else if (status & PG_OFFLINE_AGAIN)
*result = MCER_CONTINUE;
else if (status & PG_OFFLINE_PENDING) {
/* This page has owner */
if (status & PG_OFFLINE_OWNED) {
bank->mc_domid = status >> PG_OFFLINE_OWNER_SHIFT;
mce_printk(MCE_QUIET, "MCE: This error page is ownded"
" by DOM %d\n", bank->mc_domid);
/* XXX: Cannot handle shared pages yet
* (this should identify all domains and gfn mapping to
* the mfn in question) */
BUG_ON( bank->mc_domid == DOMID_COW );
if ( bank->mc_domid != DOMID_XEN ) {
d = get_domain_by_id(bank->mc_domid);
ASSERT(d);
gfn = get_gpfn_from_mfn((bank->mc_addr) >> PAGE_SHIFT);
if ( !is_vmce_ready(bank, d) )
{
printk("DOM%d not ready for vMCE\n", d->domain_id);
goto vmce_failed;
}
if ( unmmap_broken_page(d, _mfn(mfn), gfn) )
{
printk("Unmap broken memory %lx for DOM%d failed\n",
mfn, d->domain_id);
goto vmce_failed;
}
bank->mc_addr = gfn << PAGE_SHIFT |
(bank->mc_addr & (PAGE_SIZE -1 ));
if ( fill_vmsr_data(bank, d,
global->mc_gstatus) == -1 )
{
mce_printk(MCE_QUIET, "Fill vMCE# data for DOM%d "
"failed\n", bank->mc_domid);
goto vmce_failed;
}
if ( boot_cpu_data.x86_vendor == X86_VENDOR_INTEL )
vmce_vcpuid = VMCE_INJECT_BROADCAST;
else
vmce_vcpuid = global->mc_vcpuid;
/* We will inject vMCE to DOMU*/
if ( inject_vmce(d, vmce_vcpuid) < 0 )
{
mce_printk(MCE_QUIET, "inject vMCE to DOM%d"
" failed\n", d->domain_id);
goto vmce_failed;
}
/* Impacted domain go on with domain's recovery job
* if the domain has its own MCA handler.
* For xen, it has contained the error and finished
* its own recovery job.
*/
*result = MCER_RECOVERED;
put_domain(d);
return;
vmce_failed:
put_domain(d);
domain_crash(d);
}
}
int
guest_physmap_add_entry(struct domain *d, unsigned long gfn,
unsigned long mfn, unsigned int page_order,
p2m_type_t t)
{
struct p2m_domain *p2m = p2m_get_hostp2m(d);
unsigned long i, ogfn;
p2m_type_t ot;
p2m_access_t a;
mfn_t omfn;
int pod_count = 0;
int rc = 0;
if ( !paging_mode_translate(d) )
{
if ( need_iommu(d) && t == p2m_ram_rw )
{
for ( i = 0; i < (1 << page_order); i++ )
{
rc = iommu_map_page(
d, mfn + i, mfn + i, IOMMUF_readable|IOMMUF_writable);
if ( rc != 0 )
{
while ( i-- > 0 )
iommu_unmap_page(d, mfn + i);
return rc;
}
}
}
return 0;
}
p2m_lock(p2m);
P2M_DEBUG("adding gfn=%#lx mfn=%#lx\n", gfn, mfn);
/* First, remove m->p mappings for existing p->m mappings */
for ( i = 0; i < (1UL << page_order); i++ )
{
omfn = p2m->get_entry(p2m, gfn + i, &ot, &a, 0, NULL);
if ( p2m_is_shared(ot) )
{
/* Do an unshare to cleanly take care of all corner
* cases. */
int rc;
rc = mem_sharing_unshare_page(p2m->domain, gfn + i, 0);
if ( rc )
{
p2m_unlock(p2m);
/* NOTE: Should a guest domain bring this upon itself,
* there is not a whole lot we can do. We are buried
* deep in locks from most code paths by now. So, fail
* the call and don't try to sleep on a wait queue
* while placing the mem event.
*
* However, all current (changeset 3432abcf9380) code
* paths avoid this unsavoury situation. For now.
*
* Foreign domains are okay to place an event as they
* won't go to sleep. */
(void)mem_sharing_notify_enomem(p2m->domain, gfn + i, 0);
return rc;
}
omfn = p2m->get_entry(p2m, gfn + i, &ot, &a, 0, NULL);
ASSERT(!p2m_is_shared(ot));
}
if ( p2m_is_grant(ot) )
{
/* Really shouldn't be unmapping grant maps this way */
domain_crash(d);
p2m_unlock(p2m);
return -EINVAL;
}
else if ( p2m_is_ram(ot) && !p2m_is_paged(ot) )
{
ASSERT(mfn_valid(omfn));
set_gpfn_from_mfn(mfn_x(omfn), INVALID_M2P_ENTRY);
}
else if ( ot == p2m_populate_on_demand )
{
/* Count how man PoD entries we'll be replacing if successful */
pod_count++;
}
else if ( p2m_is_paging(ot) && (ot != p2m_ram_paging_out) )
{
/* We're plugging a hole in the physmap where a paged out page was */
atomic_dec(&d->paged_pages);
}
}
/* Then, look for m->p mappings for this range and deal with them */
for ( i = 0; i < (1UL << page_order); i++ )
{
if ( page_get_owner(mfn_to_page(_mfn(mfn + i))) == dom_cow )
{
/* This is no way to add a shared page to your physmap! */
gdprintk(XENLOG_ERR, "Adding shared mfn %lx directly to dom %hu "
"physmap not allowed.\n", mfn+i, d->domain_id);
p2m_unlock(p2m);
return -EINVAL;
}
if ( page_get_owner(mfn_to_page(_mfn(mfn + i))) != d )
continue;
ogfn = mfn_to_gfn(d, _mfn(mfn+i));
if ( (ogfn != INVALID_M2P_ENTRY) && (ogfn != gfn + i) )
{
/* This machine frame is already mapped at another physical
* address */
P2M_DEBUG("aliased! mfn=%#lx, old gfn=%#lx, new gfn=%#lx\n",
mfn + i, ogfn, gfn + i);
omfn = p2m->get_entry(p2m, ogfn, &ot, &a, 0, NULL);
if ( p2m_is_ram(ot) && !p2m_is_paged(ot) )
{
ASSERT(mfn_valid(omfn));
P2M_DEBUG("old gfn=%#lx -> mfn %#lx\n",
ogfn , mfn_x(omfn));
if ( mfn_x(omfn) == (mfn + i) )
p2m_remove_page(p2m, ogfn, mfn + i, 0);
}
}
}
/* Now, actually do the two-way mapping */
if ( mfn_valid(_mfn(mfn)) )
{
if ( !set_p2m_entry(p2m, gfn, _mfn(mfn), page_order, t, p2m->default_access) )
{
rc = -EINVAL;
goto out; /* Failed to update p2m, bail without updating m2p. */
}
if ( !p2m_is_grant(t) )
{
for ( i = 0; i < (1UL << page_order); i++ )
set_gpfn_from_mfn(mfn+i, gfn+i);
}
}
else
{
gdprintk(XENLOG_WARNING, "Adding bad mfn to p2m map (%#lx -> %#lx)\n",
gfn, mfn);
if ( !set_p2m_entry(p2m, gfn, _mfn(INVALID_MFN), page_order,
p2m_invalid, p2m->default_access) )
rc = -EINVAL;
else
{
pod_lock(p2m);
p2m->pod.entry_count -= pod_count;
BUG_ON(p2m->pod.entry_count < 0);
pod_unlock(p2m);
}
}
out:
p2m_unlock(p2m);
return rc;
}
static void populate_physmap(struct memop_args *a)
{
struct page_info *page;
unsigned int i, j;
xen_pfn_t gpfn, mfn;
struct domain *d = a->domain;
if ( !guest_handle_subrange_okay(a->extent_list, a->nr_done,
a->nr_extents-1) )
return;
if ( a->extent_order > (a->memflags & MEMF_populate_on_demand ? MAX_ORDER :
max_order(current->domain)) )
return;
for ( i = a->nr_done; i < a->nr_extents; i++ )
{
if ( i != a->nr_done && hypercall_preempt_check() )
{
a->preempted = 1;
goto out;
}
if ( unlikely(__copy_from_guest_offset(&gpfn, a->extent_list, i, 1)) )
goto out;
if ( a->memflags & MEMF_populate_on_demand )
{
if ( guest_physmap_mark_populate_on_demand(d, gpfn,
a->extent_order) < 0 )
goto out;
}
else
{
if ( is_domain_direct_mapped(d) )
{
mfn = gpfn;
for ( j = 0; j < (1U << a->extent_order); j++, mfn++ )
{
if ( !mfn_valid(mfn) )
{
gdprintk(XENLOG_INFO, "Invalid mfn %#"PRI_xen_pfn"\n",
mfn);
goto out;
}
page = mfn_to_page(mfn);
if ( !get_page(page, d) )
{
gdprintk(XENLOG_INFO,
"mfn %#"PRI_xen_pfn" doesn't belong to d%d\n",
mfn, d->domain_id);
goto out;
}
put_page(page);
}
mfn = gpfn;
page = mfn_to_page(mfn);
}
else
{
page = alloc_domheap_pages(d, a->extent_order, a->memflags);
if ( unlikely(!page) )
{
if ( !tmem_enabled() || a->extent_order )
gdprintk(XENLOG_INFO,
"Could not allocate order=%u extent: id=%d memflags=%#x (%u of %u)\n",
a->extent_order, d->domain_id, a->memflags,
i, a->nr_extents);
goto out;
}
mfn = page_to_mfn(page);
}
guest_physmap_add_page(d, _gfn(gpfn), _mfn(mfn), a->extent_order);
if ( !paging_mode_translate(d) )
{
for ( j = 0; j < (1U << a->extent_order); j++ )
set_gpfn_from_mfn(mfn + j, gpfn + j);
/* Inform the domain of the new page's machine address. */
if ( unlikely(__copy_to_guest_offset(a->extent_list, i, &mfn, 1)) )
goto out;
}
}
}
out:
a->nr_done = i;
}
void dump_pt_walk(paddr_t ttbr, paddr_t addr,
unsigned int root_level,
unsigned int nr_root_tables)
{
static const char *level_strs[4] = { "0TH", "1ST", "2ND", "3RD" };
const unsigned long root_pfn = paddr_to_pfn(ttbr);
const unsigned int offsets[4] = {
zeroeth_table_offset(addr),
first_table_offset(addr),
second_table_offset(addr),
third_table_offset(addr)
};
lpae_t pte, *mapping;
unsigned int level, root_table;
#ifdef CONFIG_ARM_32
BUG_ON(root_level < 1);
#endif
BUG_ON(root_level > 3);
if ( nr_root_tables > 1 )
{
/*
* Concatenated root-level tables. The table number will be
* the offset at the previous level. It is not possible to
* concatenate a level-0 root.
*/
BUG_ON(root_level == 0);
root_table = offsets[root_level - 1];
printk("Using concatenated root table %u\n", root_table);
if ( root_table >= nr_root_tables )
{
printk("Invalid root table offset\n");
return;
}
}
else
root_table = 0;
mapping = map_domain_page(_mfn(root_pfn + root_table));
for ( level = root_level; ; level++ )
{
if ( offsets[level] > LPAE_ENTRIES )
break;
pte = mapping[offsets[level]];
printk("%s[0x%x] = 0x%"PRIpaddr"\n",
level_strs[level], offsets[level], pte.bits);
if ( level == 3 || !pte.walk.valid || !pte.walk.table )
break;
/* For next iteration */
unmap_domain_page(mapping);
mapping = map_domain_page(_mfn(pte.walk.base));
}
unmap_domain_page(mapping);
}
long p2m_pt_audit_p2m(struct p2m_domain *p2m)
{
unsigned long entry_count = 0, pmbad = 0;
unsigned long mfn, gfn, m2pfn;
int test_linear;
struct domain *d = p2m->domain;
ASSERT(p2m_locked_by_me(p2m));
ASSERT(pod_locked_by_me(p2m));
test_linear = ( (d == current->domain)
&& !pagetable_is_null(current->arch.monitor_table) );
if ( test_linear )
flush_tlb_local();
/* Audit part one: walk the domain's p2m table, checking the entries. */
if ( pagetable_get_pfn(p2m_get_pagetable(p2m)) != 0 )
{
l2_pgentry_t *l2e;
l1_pgentry_t *l1e;
int i1, i2;
#if CONFIG_PAGING_LEVELS == 4
l4_pgentry_t *l4e;
l3_pgentry_t *l3e;
int i4, i3;
l4e = map_domain_page(mfn_x(pagetable_get_mfn(p2m_get_pagetable(p2m))));
#else /* CONFIG_PAGING_LEVELS == 3 */
l3_pgentry_t *l3e;
int i3;
l3e = map_domain_page(mfn_x(pagetable_get_mfn(p2m_get_pagetable(p2m))));
#endif
gfn = 0;
#if CONFIG_PAGING_LEVELS >= 4
for ( i4 = 0; i4 < L4_PAGETABLE_ENTRIES; i4++ )
{
if ( !(l4e_get_flags(l4e[i4]) & _PAGE_PRESENT) )
{
gfn += 1 << (L4_PAGETABLE_SHIFT - PAGE_SHIFT);
continue;
}
l3e = map_domain_page(mfn_x(_mfn(l4e_get_pfn(l4e[i4]))));
#endif
for ( i3 = 0;
i3 < ((CONFIG_PAGING_LEVELS==4) ? L3_PAGETABLE_ENTRIES : 8);
i3++ )
{
if ( !(l3e_get_flags(l3e[i3]) & _PAGE_PRESENT) )
{
gfn += 1 << (L3_PAGETABLE_SHIFT - PAGE_SHIFT);
continue;
}
/* check for 1GB super page */
if ( l3e_get_flags(l3e[i3]) & _PAGE_PSE )
{
mfn = l3e_get_pfn(l3e[i3]);
ASSERT(mfn_valid(_mfn(mfn)));
/* we have to cover 512x512 4K pages */
for ( i2 = 0;
i2 < (L2_PAGETABLE_ENTRIES * L1_PAGETABLE_ENTRIES);
i2++)
{
m2pfn = get_gpfn_from_mfn(mfn+i2);
if ( m2pfn != (gfn + i2) )
{
pmbad++;
P2M_PRINTK("mismatch: gfn %#lx -> mfn %#lx"
" -> gfn %#lx\n", gfn+i2, mfn+i2,
m2pfn);
BUG();
}
gfn += 1 << (L3_PAGETABLE_SHIFT - PAGE_SHIFT);
continue;
}
}
l2e = map_domain_page(mfn_x(_mfn(l3e_get_pfn(l3e[i3]))));
for ( i2 = 0; i2 < L2_PAGETABLE_ENTRIES; i2++ )
{
if ( !(l2e_get_flags(l2e[i2]) & _PAGE_PRESENT) )
{
if ( (l2e_get_flags(l2e[i2]) & _PAGE_PSE)
&& ( p2m_flags_to_type(l2e_get_flags(l2e[i2]))
== p2m_populate_on_demand ) )
entry_count+=SUPERPAGE_PAGES;
gfn += 1 << (L2_PAGETABLE_SHIFT - PAGE_SHIFT);
continue;
}
/* check for super page */
if ( l2e_get_flags(l2e[i2]) & _PAGE_PSE )
{
mfn = l2e_get_pfn(l2e[i2]);
ASSERT(mfn_valid(_mfn(mfn)));
for ( i1 = 0; i1 < L1_PAGETABLE_ENTRIES; i1++)
{
m2pfn = get_gpfn_from_mfn(mfn+i1);
/* Allow shared M2Ps */
if ( (m2pfn != (gfn + i1)) &&
(m2pfn != SHARED_M2P_ENTRY) )
{
pmbad++;
P2M_PRINTK("mismatch: gfn %#lx -> mfn %#lx"
" -> gfn %#lx\n", gfn+i1, mfn+i1,
m2pfn);
BUG();
}
}
gfn += 1 << (L2_PAGETABLE_SHIFT - PAGE_SHIFT);
continue;
}
l1e = map_domain_page(mfn_x(_mfn(l2e_get_pfn(l2e[i2]))));
for ( i1 = 0; i1 < L1_PAGETABLE_ENTRIES; i1++, gfn++ )
{
p2m_type_t type;
type = p2m_flags_to_type(l1e_get_flags(l1e[i1]));
if ( !(l1e_get_flags(l1e[i1]) & _PAGE_PRESENT) )
{
if ( type == p2m_populate_on_demand )
entry_count++;
continue;
}
mfn = l1e_get_pfn(l1e[i1]);
ASSERT(mfn_valid(_mfn(mfn)));
m2pfn = get_gpfn_from_mfn(mfn);
if ( m2pfn != gfn &&
type != p2m_mmio_direct &&
!p2m_is_grant(type) &&
!p2m_is_shared(type) )
{
pmbad++;
printk("mismatch: gfn %#lx -> mfn %#lx"
" -> gfn %#lx\n", gfn, mfn, m2pfn);
P2M_PRINTK("mismatch: gfn %#lx -> mfn %#lx"
" -> gfn %#lx\n", gfn, mfn, m2pfn);
BUG();
}
}
unmap_domain_page(l1e);
}
unmap_domain_page(l2e);
}
#if CONFIG_PAGING_LEVELS >= 4
unmap_domain_page(l3e);
}
#endif
#if CONFIG_PAGING_LEVELS == 4
unmap_domain_page(l4e);
#else /* CONFIG_PAGING_LEVELS == 3 */
unmap_domain_page(l3e);
#endif
}
if ( entry_count != p2m->pod.entry_count )
{
printk("%s: refcounted entry count %ld, audit count %lu!\n",
__func__,
p2m->pod.entry_count,
entry_count);
BUG();
}
return pmbad;
}
int guest_remove_page(struct domain *d, unsigned long gmfn)
{
struct page_info *page;
#ifdef CONFIG_X86
p2m_type_t p2mt;
#endif
unsigned long mfn;
#ifdef CONFIG_X86
mfn = mfn_x(get_gfn_query(d, gmfn, &p2mt));
if ( unlikely(p2m_is_paging(p2mt)) )
{
guest_physmap_remove_page(d, gmfn, mfn, 0);
put_gfn(d, gmfn);
/* If the page hasn't yet been paged out, there is an
* actual page that needs to be released. */
if ( p2mt == p2m_ram_paging_out )
{
ASSERT(mfn_valid(mfn));
page = mfn_to_page(mfn);
if ( test_and_clear_bit(_PGC_allocated, &page->count_info) )
put_page(page);
}
p2m_mem_paging_drop_page(d, gmfn, p2mt);
return 1;
}
if ( p2mt == p2m_mmio_direct )
{
clear_mmio_p2m_entry(d, gmfn, _mfn(mfn));
put_gfn(d, gmfn);
return 1;
}
#else
mfn = gmfn_to_mfn(d, gmfn);
#endif
if ( unlikely(!mfn_valid(mfn)) )
{
put_gfn(d, gmfn);
gdprintk(XENLOG_INFO, "Domain %u page number %lx invalid\n",
d->domain_id, gmfn);
return 0;
}
#ifdef CONFIG_X86
if ( p2m_is_shared(p2mt) )
{
/* Unshare the page, bail out on error. We unshare because
* we might be the only one using this shared page, and we
* need to trigger proper cleanup. Once done, this is
* like any other page. */
if ( mem_sharing_unshare_page(d, gmfn, 0) )
{
put_gfn(d, gmfn);
(void)mem_sharing_notify_enomem(d, gmfn, 0);
return 0;
}
/* Maybe the mfn changed */
mfn = mfn_x(get_gfn_query_unlocked(d, gmfn, &p2mt));
ASSERT(!p2m_is_shared(p2mt));
}
#endif /* CONFIG_X86 */
page = mfn_to_page(mfn);
if ( unlikely(!get_page(page, d)) )
{
put_gfn(d, gmfn);
gdprintk(XENLOG_INFO, "Bad page free for domain %u\n", d->domain_id);
return 0;
}
if ( test_and_clear_bit(_PGT_pinned, &page->u.inuse.type_info) )
put_page_and_type(page);
/*
* With the lack of an IOMMU on some platforms, domains with DMA-capable
* device must retrieve the same pfn when the hypercall populate_physmap
* is called.
*
* For this purpose (and to match populate_physmap() behavior), the page
* is kept allocated.
*/
if ( !is_domain_direct_mapped(d) &&
test_and_clear_bit(_PGC_allocated, &page->count_info) )
put_page(page);
guest_physmap_remove_page(d, gmfn, mfn, 0);
put_page(page);
put_gfn(d, gmfn);
return 1;
}
static mfn_t
p2m_pt_get_entry(struct p2m_domain *p2m, unsigned long gfn,
p2m_type_t *t, p2m_access_t *a, p2m_query_t q,
unsigned int *page_order)
{
mfn_t mfn;
paddr_t addr = ((paddr_t)gfn) << PAGE_SHIFT;
l2_pgentry_t *l2e;
l1_pgentry_t *l1e;
unsigned long l1e_flags;
p2m_type_t l1t;
ASSERT(paging_mode_translate(p2m->domain));
/* XXX This is for compatibility with the old model, where anything not
* XXX marked as RAM was considered to be emulated MMIO space.
* XXX Once we start explicitly registering MMIO regions in the p2m
* XXX we will return p2m_invalid for unmapped gfns */
*t = p2m_mmio_dm;
/* Not implemented except with EPT */
*a = p2m_access_rwx;
if ( gfn > p2m->max_mapped_pfn )
/* This pfn is higher than the highest the p2m map currently holds */
return _mfn(INVALID_MFN);
mfn = pagetable_get_mfn(p2m_get_pagetable(p2m));
{
l4_pgentry_t *l4e = map_domain_page(mfn_x(mfn));
l4e += l4_table_offset(addr);
if ( (l4e_get_flags(*l4e) & _PAGE_PRESENT) == 0 )
{
unmap_domain_page(l4e);
return _mfn(INVALID_MFN);
}
mfn = _mfn(l4e_get_pfn(*l4e));
unmap_domain_page(l4e);
}
{
l3_pgentry_t *l3e = map_domain_page(mfn_x(mfn));
l3e += l3_table_offset(addr);
pod_retry_l3:
if ( (l3e_get_flags(*l3e) & _PAGE_PRESENT) == 0 )
{
if ( p2m_flags_to_type(l3e_get_flags(*l3e)) == p2m_populate_on_demand )
{
if ( q & P2M_ALLOC )
{
if ( !p2m_pod_demand_populate(p2m, gfn, PAGE_ORDER_1G, q) )
goto pod_retry_l3;
gdprintk(XENLOG_ERR, "%s: Allocate 1GB failed!\n", __func__);
}
else
*t = p2m_populate_on_demand;
}
unmap_domain_page(l3e);
return _mfn(INVALID_MFN);
}
else if ( (l3e_get_flags(*l3e) & _PAGE_PSE) )
{
mfn = _mfn(l3e_get_pfn(*l3e) +
l2_table_offset(addr) * L1_PAGETABLE_ENTRIES +
l1_table_offset(addr));
*t = p2m_flags_to_type(l3e_get_flags(*l3e));
unmap_domain_page(l3e);
ASSERT(mfn_valid(mfn) || !p2m_is_ram(*t));
if ( page_order )
*page_order = PAGE_ORDER_1G;
return (p2m_is_valid(*t)) ? mfn : _mfn(INVALID_MFN);
}
mfn = _mfn(l3e_get_pfn(*l3e));
unmap_domain_page(l3e);
}
l2e = map_domain_page(mfn_x(mfn));
l2e += l2_table_offset(addr);
pod_retry_l2:
if ( (l2e_get_flags(*l2e) & _PAGE_PRESENT) == 0 )
{
/* PoD: Try to populate a 2-meg chunk */
if ( p2m_flags_to_type(l2e_get_flags(*l2e)) == p2m_populate_on_demand )
{
if ( q & P2M_ALLOC ) {
if ( !p2m_pod_demand_populate(p2m, gfn, PAGE_ORDER_2M, q) )
goto pod_retry_l2;
} else
*t = p2m_populate_on_demand;
}
unmap_domain_page(l2e);
return _mfn(INVALID_MFN);
}
else if ( (l2e_get_flags(*l2e) & _PAGE_PSE) )
{
mfn = _mfn(l2e_get_pfn(*l2e) + l1_table_offset(addr));
*t = p2m_flags_to_type(l2e_get_flags(*l2e));
unmap_domain_page(l2e);
ASSERT(mfn_valid(mfn) || !p2m_is_ram(*t));
if ( page_order )
*page_order = PAGE_ORDER_2M;
return (p2m_is_valid(*t)) ? mfn : _mfn(INVALID_MFN);
}
mfn = _mfn(l2e_get_pfn(*l2e));
unmap_domain_page(l2e);
l1e = map_domain_page(mfn_x(mfn));
l1e += l1_table_offset(addr);
pod_retry_l1:
l1e_flags = l1e_get_flags(*l1e);
l1t = p2m_flags_to_type(l1e_flags);
if ( ((l1e_flags & _PAGE_PRESENT) == 0) && (!p2m_is_paging(l1t)) )
{
/* PoD: Try to populate */
if ( l1t == p2m_populate_on_demand )
{
if ( q & P2M_ALLOC ) {
if ( !p2m_pod_demand_populate(p2m, gfn, PAGE_ORDER_4K, q) )
goto pod_retry_l1;
} else
*t = p2m_populate_on_demand;
}
unmap_domain_page(l1e);
return _mfn(INVALID_MFN);
}
mfn = _mfn(l1e_get_pfn(*l1e));
*t = l1t;
unmap_domain_page(l1e);
ASSERT(mfn_valid(mfn) || !p2m_is_ram(*t) || p2m_is_paging(*t));
if ( page_order )
*page_order = PAGE_ORDER_4K;
return (p2m_is_valid(*t) || p2m_is_grant(*t)) ? mfn : _mfn(INVALID_MFN);
}
unsigned long hap_p2m_ga_to_gfn(GUEST_PAGING_LEVELS)(
struct vcpu *v, struct p2m_domain *p2m, unsigned long cr3,
paddr_t ga, uint32_t *pfec, unsigned int *page_order)
{
uint32_t missing;
mfn_t top_mfn;
void *top_map;
p2m_type_t p2mt;
walk_t gw;
unsigned long top_gfn;
struct page_info *top_page;
/* Get the top-level table's MFN */
top_gfn = cr3 >> PAGE_SHIFT;
top_page = get_page_from_gfn_p2m(p2m->domain, p2m, top_gfn,
&p2mt, NULL, P2M_ALLOC | P2M_UNSHARE);
if ( p2m_is_paging(p2mt) )
{
ASSERT(p2m_is_hostp2m(p2m));
pfec[0] = PFEC_page_paged;
if ( top_page )
put_page(top_page);
p2m_mem_paging_populate(p2m->domain, cr3 >> PAGE_SHIFT);
return gfn_x(INVALID_GFN);
}
if ( p2m_is_shared(p2mt) )
{
pfec[0] = PFEC_page_shared;
if ( top_page )
put_page(top_page);
return gfn_x(INVALID_GFN);
}
if ( !top_page )
{
pfec[0] &= ~PFEC_page_present;
goto out_tweak_pfec;
}
top_mfn = _mfn(page_to_mfn(top_page));
/* Map the top-level table and call the tree-walker */
ASSERT(mfn_valid(top_mfn));
top_map = map_domain_page(top_mfn);
#if GUEST_PAGING_LEVELS == 3
top_map += (cr3 & ~(PAGE_MASK | 31));
#endif
missing = guest_walk_tables(v, p2m, ga, &gw, pfec[0], top_mfn, top_map);
unmap_domain_page(top_map);
put_page(top_page);
/* Interpret the answer */
if ( missing == 0 )
{
gfn_t gfn = guest_walk_to_gfn(&gw);
struct page_info *page;
page = get_page_from_gfn_p2m(p2m->domain, p2m, gfn_x(gfn), &p2mt,
NULL, P2M_ALLOC | P2M_UNSHARE);
if ( page )
put_page(page);
if ( p2m_is_paging(p2mt) )
{
ASSERT(p2m_is_hostp2m(p2m));
pfec[0] = PFEC_page_paged;
p2m_mem_paging_populate(p2m->domain, gfn_x(gfn));
return gfn_x(INVALID_GFN);
}
if ( p2m_is_shared(p2mt) )
{
pfec[0] = PFEC_page_shared;
return gfn_x(INVALID_GFN);
}
if ( page_order )
*page_order = guest_walk_to_page_order(&gw);
return gfn_x(gfn);
}
if ( missing & _PAGE_PRESENT )
pfec[0] &= ~PFEC_page_present;
if ( missing & _PAGE_INVALID_BITS )
pfec[0] |= PFEC_reserved_bit;
if ( missing & _PAGE_PKEY_BITS )
pfec[0] |= PFEC_prot_key;
if ( missing & _PAGE_PAGED )
pfec[0] = PFEC_page_paged;
if ( missing & _PAGE_SHARED )
pfec[0] = PFEC_page_shared;
out_tweak_pfec:
/*
* SDM Intel 64 Volume 3, Chapter Paging, PAGE-FAULT EXCEPTIONS:
* The PFEC_insn_fetch flag is set only when NX or SMEP are enabled.
*/
if ( !hvm_nx_enabled(v) && !hvm_smep_enabled(v) )
pfec[0] &= ~PFEC_insn_fetch;
return gfn_x(INVALID_GFN);
}
/*
* Lookup the MFN corresponding to a domain's PFN.
*
* There are no processor functions to do a stage 2 only lookup therefore we
* do a a software walk.
*/
static paddr_t __p2m_lookup(struct domain *d, paddr_t paddr, p2m_type_t *t)
{
struct p2m_domain *p2m = &d->arch.p2m;
const unsigned int offsets[4] = {
zeroeth_table_offset(paddr),
first_table_offset(paddr),
second_table_offset(paddr),
third_table_offset(paddr)
};
const paddr_t masks[4] = {
ZEROETH_MASK, FIRST_MASK, SECOND_MASK, THIRD_MASK
};
lpae_t pte, *map;
paddr_t maddr = INVALID_PADDR;
paddr_t mask = 0;
p2m_type_t _t;
unsigned int level, root_table;
ASSERT(spin_is_locked(&p2m->lock));
BUILD_BUG_ON(THIRD_MASK != PAGE_MASK);
/* Allow t to be NULL */
t = t ?: &_t;
*t = p2m_invalid;
if ( P2M_ROOT_PAGES > 1 )
{
/*
* Concatenated root-level tables. The table number will be
* the offset at the previous level. It is not possible to
* concatenate a level-0 root.
*/
ASSERT(P2M_ROOT_LEVEL > 0);
root_table = offsets[P2M_ROOT_LEVEL - 1];
if ( root_table >= P2M_ROOT_PAGES )
goto err;
}
else
root_table = 0;
map = __map_domain_page(p2m->root + root_table);
ASSERT(P2M_ROOT_LEVEL < 4);
for ( level = P2M_ROOT_LEVEL ; level < 4 ; level++ )
{
mask = masks[level];
pte = map[offsets[level]];
if ( level == 3 && !p2m_table(pte) )
/* Invalid, clobber the pte */
pte.bits = 0;
if ( level == 3 || !p2m_table(pte) )
/* Done */
break;
ASSERT(level < 3);
/* Map for next level */
unmap_domain_page(map);
map = map_domain_page(_mfn(pte.p2m.base));
}
unmap_domain_page(map);
if ( p2m_valid(pte) )
{
ASSERT(mask);
ASSERT(pte.p2m.type != p2m_invalid);
maddr = (pte.bits & PADDR_MASK & mask) | (paddr & ~mask);
*t = pte.p2m.type;
}
err:
return maddr;
}
static mfn_t
p2m_gfn_to_mfn(struct p2m_domain *p2m, unsigned long gfn,
p2m_type_t *t, p2m_access_t *a, p2m_query_t q,
unsigned int *page_order)
{
mfn_t mfn;
paddr_t addr = ((paddr_t)gfn) << PAGE_SHIFT;
l2_pgentry_t *l2e;
l1_pgentry_t *l1e;
unsigned long l1e_flags;
p2m_type_t l1t;
ASSERT(paging_mode_translate(p2m->domain));
/* XXX This is for compatibility with the old model, where anything not
* XXX marked as RAM was considered to be emulated MMIO space.
* XXX Once we start explicitly registering MMIO regions in the p2m
* XXX we will return p2m_invalid for unmapped gfns */
*t = p2m_mmio_dm;
/* Not implemented except with EPT */
*a = p2m_access_rwx;
if ( gfn > p2m->max_mapped_pfn )
/* This pfn is higher than the highest the p2m map currently holds */
return _mfn(INVALID_MFN);
/* Use the fast path with the linear mapping if we can */
if ( p2m == p2m_get_hostp2m(current->domain) )
return p2m_gfn_to_mfn_current(p2m, gfn, t, a, q, page_order);
mfn = pagetable_get_mfn(p2m_get_pagetable(p2m));
#if CONFIG_PAGING_LEVELS >= 4
{
l4_pgentry_t *l4e = map_domain_page(mfn_x(mfn));
l4e += l4_table_offset(addr);
if ( (l4e_get_flags(*l4e) & _PAGE_PRESENT) == 0 )
{
unmap_domain_page(l4e);
return _mfn(INVALID_MFN);
}
mfn = _mfn(l4e_get_pfn(*l4e));
unmap_domain_page(l4e);
}
#endif
{
l3_pgentry_t *l3e = map_domain_page(mfn_x(mfn));
#if CONFIG_PAGING_LEVELS == 3
/* On PAE hosts the p2m has eight l3 entries, not four (see
* shadow_set_p2m_entry()) so we can't use l3_table_offset.
* Instead, just count the number of l3es from zero. It's safe
* to do this because we already checked that the gfn is within
* the bounds of the p2m. */
l3e += (addr >> L3_PAGETABLE_SHIFT);
#else
l3e += l3_table_offset(addr);
#endif
pod_retry_l3:
if ( (l3e_get_flags(*l3e) & _PAGE_PRESENT) == 0 )
{
if ( p2m_flags_to_type(l3e_get_flags(*l3e)) == p2m_populate_on_demand )
{
if ( q & P2M_ALLOC )
{
if ( !p2m_pod_demand_populate(p2m, gfn, PAGE_ORDER_1G, q) )
goto pod_retry_l3;
gdprintk(XENLOG_ERR, "%s: Allocate 1GB failed!\n", __func__);
}
else
*t = p2m_populate_on_demand;
}
unmap_domain_page(l3e);
return _mfn(INVALID_MFN);
}
else if ( (l3e_get_flags(*l3e) & _PAGE_PSE) )
{
mfn = _mfn(l3e_get_pfn(*l3e) +
l2_table_offset(addr) * L1_PAGETABLE_ENTRIES +
l1_table_offset(addr));
*t = p2m_flags_to_type(l3e_get_flags(*l3e));
unmap_domain_page(l3e);
ASSERT(mfn_valid(mfn) || !p2m_is_ram(*t));
if ( page_order )
*page_order = PAGE_ORDER_1G;
return (p2m_is_valid(*t)) ? mfn : _mfn(INVALID_MFN);
}
mfn = _mfn(l3e_get_pfn(*l3e));
unmap_domain_page(l3e);
}
l2e = map_domain_page(mfn_x(mfn));
l2e += l2_table_offset(addr);
pod_retry_l2:
if ( (l2e_get_flags(*l2e) & _PAGE_PRESENT) == 0 )
{
/* PoD: Try to populate a 2-meg chunk */
if ( p2m_flags_to_type(l2e_get_flags(*l2e)) == p2m_populate_on_demand )
{
if ( q & P2M_ALLOC ) {
if ( !p2m_pod_demand_populate(p2m, gfn, PAGE_ORDER_2M, q) )
goto pod_retry_l2;
} else
*t = p2m_populate_on_demand;
}
unmap_domain_page(l2e);
return _mfn(INVALID_MFN);
}
else if ( (l2e_get_flags(*l2e) & _PAGE_PSE) )
{
mfn = _mfn(l2e_get_pfn(*l2e) + l1_table_offset(addr));
*t = p2m_flags_to_type(l2e_get_flags(*l2e));
unmap_domain_page(l2e);
ASSERT(mfn_valid(mfn) || !p2m_is_ram(*t));
if ( page_order )
*page_order = PAGE_ORDER_2M;
return (p2m_is_valid(*t)) ? mfn : _mfn(INVALID_MFN);
}
mfn = _mfn(l2e_get_pfn(*l2e));
unmap_domain_page(l2e);
l1e = map_domain_page(mfn_x(mfn));
l1e += l1_table_offset(addr);
pod_retry_l1:
l1e_flags = l1e_get_flags(*l1e);
l1t = p2m_flags_to_type(l1e_flags);
if ( ((l1e_flags & _PAGE_PRESENT) == 0) && (!p2m_is_paging(l1t)) )
{
/* PoD: Try to populate */
if ( l1t == p2m_populate_on_demand )
{
if ( q & P2M_ALLOC ) {
if ( !p2m_pod_demand_populate(p2m, gfn, PAGE_ORDER_4K, q) )
goto pod_retry_l1;
} else
*t = p2m_populate_on_demand;
}
unmap_domain_page(l1e);
return _mfn(INVALID_MFN);
}
mfn = _mfn(l1e_get_pfn(*l1e));
*t = l1t;
unmap_domain_page(l1e);
ASSERT(mfn_valid(mfn) || !p2m_is_ram(*t) || p2m_is_paging(*t));
if ( page_order )
*page_order = PAGE_ORDER_4K;
return (p2m_is_valid(*t) || p2m_is_grant(*t)) ? mfn : _mfn(INVALID_MFN);
}
/* Walk the whole p2m table, changing any entries of the old type
* to the new type. This is used in hardware-assisted paging to
* quickly enable or diable log-dirty tracking */
static void p2m_change_type_global(struct p2m_domain *p2m,
p2m_type_t ot, p2m_type_t nt)
{
unsigned long mfn, gfn, flags;
l1_pgentry_t l1e_content;
l1_pgentry_t *l1e;
l2_pgentry_t *l2e;
mfn_t l1mfn, l2mfn, l3mfn;
unsigned long i1, i2, i3;
l3_pgentry_t *l3e;
#if CONFIG_PAGING_LEVELS == 4
l4_pgentry_t *l4e;
unsigned long i4;
#endif /* CONFIG_PAGING_LEVELS == 4 */
BUG_ON(p2m_is_grant(ot) || p2m_is_grant(nt));
BUG_ON(ot != nt && (ot == p2m_mmio_direct || nt == p2m_mmio_direct));
if ( !paging_mode_translate(p2m->domain) )
return;
if ( pagetable_get_pfn(p2m_get_pagetable(p2m)) == 0 )
return;
ASSERT(p2m_locked_by_me(p2m));
#if CONFIG_PAGING_LEVELS == 4
l4e = map_domain_page(mfn_x(pagetable_get_mfn(p2m_get_pagetable(p2m))));
#else /* CONFIG_PAGING_LEVELS == 3 */
l3mfn = _mfn(mfn_x(pagetable_get_mfn(p2m_get_pagetable(p2m))));
l3e = map_domain_page(mfn_x(pagetable_get_mfn(p2m_get_pagetable(p2m))));
#endif
#if CONFIG_PAGING_LEVELS >= 4
for ( i4 = 0; i4 < L4_PAGETABLE_ENTRIES; i4++ )
{
if ( !(l4e_get_flags(l4e[i4]) & _PAGE_PRESENT) )
{
continue;
}
l3mfn = _mfn(l4e_get_pfn(l4e[i4]));
l3e = map_domain_page(l4e_get_pfn(l4e[i4]));
#endif
for ( i3 = 0;
i3 < ((CONFIG_PAGING_LEVELS==4) ? L3_PAGETABLE_ENTRIES : 8);
i3++ )
{
if ( !(l3e_get_flags(l3e[i3]) & _PAGE_PRESENT) )
{
continue;
}
if ( (l3e_get_flags(l3e[i3]) & _PAGE_PSE) )
{
flags = l3e_get_flags(l3e[i3]);
if ( p2m_flags_to_type(flags) != ot )
continue;
mfn = l3e_get_pfn(l3e[i3]);
gfn = get_gpfn_from_mfn(mfn);
flags = p2m_type_to_flags(nt, _mfn(mfn));
l1e_content = l1e_from_pfn(mfn, flags | _PAGE_PSE);
p2m->write_p2m_entry(p2m, gfn,
(l1_pgentry_t *)&l3e[i3],
l3mfn, l1e_content, 3);
continue;
}
l2mfn = _mfn(l3e_get_pfn(l3e[i3]));
l2e = map_domain_page(l3e_get_pfn(l3e[i3]));
for ( i2 = 0; i2 < L2_PAGETABLE_ENTRIES; i2++ )
{
if ( !(l2e_get_flags(l2e[i2]) & _PAGE_PRESENT) )
{
continue;
}
if ( (l2e_get_flags(l2e[i2]) & _PAGE_PSE) )
{
flags = l2e_get_flags(l2e[i2]);
if ( p2m_flags_to_type(flags) != ot )
continue;
mfn = l2e_get_pfn(l2e[i2]);
/* Do not use get_gpfn_from_mfn because it may return
SHARED_M2P_ENTRY */
gfn = (i2 + (i3
#if CONFIG_PAGING_LEVELS >= 4
+ (i4 * L3_PAGETABLE_ENTRIES)
#endif
)
* L2_PAGETABLE_ENTRIES) * L1_PAGETABLE_ENTRIES;
flags = p2m_type_to_flags(nt, _mfn(mfn));
l1e_content = l1e_from_pfn(mfn, flags | _PAGE_PSE);
p2m->write_p2m_entry(p2m, gfn,
(l1_pgentry_t *)&l2e[i2],
l2mfn, l1e_content, 2);
continue;
}
l1mfn = _mfn(l2e_get_pfn(l2e[i2]));
l1e = map_domain_page(mfn_x(l1mfn));
for ( i1 = 0; i1 < L1_PAGETABLE_ENTRIES; i1++, gfn++ )
{
flags = l1e_get_flags(l1e[i1]);
if ( p2m_flags_to_type(flags) != ot )
continue;
mfn = l1e_get_pfn(l1e[i1]);
gfn = i1 + (i2 + (i3
#if CONFIG_PAGING_LEVELS >= 4
+ (i4 * L3_PAGETABLE_ENTRIES)
#endif
)
* L2_PAGETABLE_ENTRIES) * L1_PAGETABLE_ENTRIES;
/* create a new 1le entry with the new type */
flags = p2m_type_to_flags(nt, _mfn(mfn));
l1e_content = p2m_l1e_from_pfn(mfn, flags);
p2m->write_p2m_entry(p2m, gfn, &l1e[i1],
l1mfn, l1e_content, 1);
}
unmap_domain_page(l1e);
}
unmap_domain_page(l2e);
}
#if CONFIG_PAGING_LEVELS >= 4
unmap_domain_page(l3e);
}
#endif
#if CONFIG_PAGING_LEVELS == 4
unmap_domain_page(l4e);
#else /* CONFIG_PAGING_LEVELS == 3 */
unmap_domain_page(l3e);
#endif
}
unsigned long hap_p2m_ga_to_gfn(GUEST_PAGING_LEVELS)(
struct vcpu *v, struct p2m_domain *p2m, unsigned long cr3,
paddr_t ga, uint32_t *pfec, unsigned int *page_order)
{
uint32_t missing;
mfn_t top_mfn;
void *top_map;
p2m_type_t p2mt;
walk_t gw;
unsigned long top_gfn;
struct page_info *top_page;
/* Get the top-level table's MFN */
top_gfn = cr3 >> PAGE_SHIFT;
top_page = get_page_from_gfn_p2m(p2m->domain, p2m, top_gfn,
&p2mt, NULL, P2M_ALLOC | P2M_UNSHARE);
if ( p2m_is_paging(p2mt) )
{
ASSERT(p2m_is_hostp2m(p2m));
pfec[0] = PFEC_page_paged;
if ( top_page )
put_page(top_page);
p2m_mem_paging_populate(p2m->domain, cr3 >> PAGE_SHIFT);
return INVALID_GFN;
}
if ( p2m_is_shared(p2mt) )
{
pfec[0] = PFEC_page_shared;
if ( top_page )
put_page(top_page);
return INVALID_GFN;
}
if ( !top_page )
{
pfec[0] &= ~PFEC_page_present;
return INVALID_GFN;
}
top_mfn = _mfn(page_to_mfn(top_page));
/* Map the top-level table and call the tree-walker */
ASSERT(mfn_valid(mfn_x(top_mfn)));
top_map = map_domain_page(mfn_x(top_mfn));
#if GUEST_PAGING_LEVELS == 3
top_map += (cr3 & ~(PAGE_MASK | 31));
#endif
missing = guest_walk_tables(v, p2m, ga, &gw, pfec[0], top_mfn, top_map);
unmap_domain_page(top_map);
put_page(top_page);
/* Interpret the answer */
if ( missing == 0 )
{
gfn_t gfn = guest_l1e_get_gfn(gw.l1e);
struct page_info *page;
page = get_page_from_gfn_p2m(p2m->domain, p2m, gfn_x(gfn), &p2mt,
NULL, P2M_ALLOC | P2M_UNSHARE);
if ( page )
put_page(page);
if ( p2m_is_paging(p2mt) )
{
ASSERT(p2m_is_hostp2m(p2m));
pfec[0] = PFEC_page_paged;
p2m_mem_paging_populate(p2m->domain, gfn_x(gfn));
return INVALID_GFN;
}
if ( p2m_is_shared(p2mt) )
{
pfec[0] = PFEC_page_shared;
return INVALID_GFN;
}
if ( page_order )
*page_order = guest_walk_to_page_order(&gw);
return gfn_x(gfn);
}
if ( missing & _PAGE_PRESENT )
pfec[0] &= ~PFEC_page_present;
if ( missing & _PAGE_INVALID_BITS )
pfec[0] |= PFEC_reserved_bit;
if ( missing & _PAGE_PAGED )
pfec[0] = PFEC_page_paged;
if ( missing & _PAGE_SHARED )
pfec[0] = PFEC_page_shared;
return INVALID_GFN;
}
/*
* pgd3val: this is the value of init_mm.pgd[3] in a PV guest. It is optional.
* This to assist debug of modules in the guest. The kernel address
* space seems is always mapped, but modules are not necessarily
* mapped in any arbitraty guest cr3 that we pick if pgd3val is 0.
* Modules should always be addressible if we use cr3 from init_mm.
* Since pgd3val is already a pgd value, cr3->pgd[3], we just need to
* do 2 level lookups.
*
* NOTE: 4 level paging works for 32 PAE guests also because cpu runs in IA32-e
* mode.
* Returns: mfn for the given (pv guest) vaddr
*/
static mfn_t
dbg_pv_va2mfn(dbgva_t vaddr, struct domain *dp, uint64_t pgd3val)
{
l4_pgentry_t l4e, *l4t;
l3_pgentry_t l3e, *l3t;
l2_pgentry_t l2e, *l2t;
l1_pgentry_t l1e, *l1t;
unsigned long cr3 = (pgd3val ? pgd3val : dp->vcpu[0]->arch.cr3);
mfn_t mfn = _mfn(cr3 >> PAGE_SHIFT);
DBGP2("vaddr:%lx domid:%d cr3:%lx pgd3:%lx\n", vaddr, dp->domain_id,
cr3, pgd3val);
if ( pgd3val == 0 )
{
l4t = map_domain_page(mfn);
l4e = l4t[l4_table_offset(vaddr)];
unmap_domain_page(l4t);
mfn = _mfn(l4e_get_pfn(l4e));
DBGP2("l4t:%p l4to:%lx l4e:%lx mfn:%#"PRI_mfn"\n", l4t,
l4_table_offset(vaddr), l4e, mfn_x(mfn));
if ( !(l4e_get_flags(l4e) & _PAGE_PRESENT) )
{
DBGP1("l4 PAGE not present. vaddr:%lx cr3:%lx\n", vaddr, cr3);
return INVALID_MFN;
}
l3t = map_domain_page(mfn);
l3e = l3t[l3_table_offset(vaddr)];
unmap_domain_page(l3t);
mfn = _mfn(l3e_get_pfn(l3e));
DBGP2("l3t:%p l3to:%lx l3e:%lx mfn:%#"PRI_mfn"\n", l3t,
l3_table_offset(vaddr), l3e, mfn_x(mfn));
if ( !(l3e_get_flags(l3e) & _PAGE_PRESENT) ||
(l3e_get_flags(l3e) & _PAGE_PSE) )
{
DBGP1("l3 PAGE not present. vaddr:%lx cr3:%lx\n", vaddr, cr3);
return INVALID_MFN;
}
}
l2t = map_domain_page(mfn);
l2e = l2t[l2_table_offset(vaddr)];
unmap_domain_page(l2t);
mfn = _mfn(l2e_get_pfn(l2e));
DBGP2("l2t:%p l2to:%lx l2e:%lx mfn:%#"PRI_mfn"\n",
l2t, l2_table_offset(vaddr), l2e, mfn_x(mfn));
if ( !(l2e_get_flags(l2e) & _PAGE_PRESENT) ||
(l2e_get_flags(l2e) & _PAGE_PSE) )
{
DBGP1("l2 PAGE not present. vaddr:%lx cr3:%lx\n", vaddr, cr3);
return INVALID_MFN;
}
l1t = map_domain_page(mfn);
l1e = l1t[l1_table_offset(vaddr)];
unmap_domain_page(l1t);
mfn = _mfn(l1e_get_pfn(l1e));
DBGP2("l1t:%p l1to:%lx l1e:%lx mfn:%#"PRI_mfn"\n", l1t, l1_table_offset(vaddr),
l1e, mfn_x(mfn));
return mfn_valid(mfn_x(mfn)) ? mfn : INVALID_MFN;
}
