Commit 9c4bc1c2 authored by Linus Torvalds's avatar Linus Torvalds

Merge branch 'stable/gntdev' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen

* 'stable/gntdev' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen:
  xen/p2m: Fix module linking error.
  xen p2m: clear the old pte when adding a page to m2p_override
  xen gntdev: use gnttab_map_refs and gnttab_unmap_refs
  xen: introduce gnttab_map_refs and gnttab_unmap_refs
  xen p2m: transparently change the p2m mappings in the m2p override
  xen/gntdev: Fix circular locking dependency
  xen/gntdev: stop using "token" argument
  xen: gntdev: move use of GNTMAP_contains_pte next to the map_op
  xen: add m2p override mechanism
  xen: move p2m handling to separate file
  xen/gntdev: add VM_PFNMAP to vma
  xen/gntdev: allow usermode to map granted pages
  xen: define gnttab_set_map_op/unmap_op

Fix up trivial conflict in drivers/xen/Kconfig
parents 2c0076d8 e1b478e4
......@@ -42,6 +42,11 @@ extern unsigned int machine_to_phys_order;
extern unsigned long get_phys_to_machine(unsigned long pfn);
extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn);
extern int m2p_add_override(unsigned long mfn, struct page *page);
extern int m2p_remove_override(struct page *page);
extern struct page *m2p_find_override(unsigned long mfn);
extern unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn);
static inline unsigned long pfn_to_mfn(unsigned long pfn)
{
unsigned long mfn;
......@@ -72,9 +77,6 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn)
if (xen_feature(XENFEAT_auto_translated_physmap))
return mfn;
if (unlikely((mfn >> machine_to_phys_order) != 0))
return ~0;
pfn = 0;
/*
* The array access can fail (e.g., device space beyond end of RAM).
......@@ -83,6 +85,14 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn)
*/
__get_user(pfn, &machine_to_phys_mapping[mfn]);
/*
* If this appears to be a foreign mfn (because the pfn
* doesn't map back to the mfn), then check the local override
* table to see if there's a better pfn to use.
*/
if (get_phys_to_machine(pfn) != mfn)
pfn = m2p_find_override_pfn(mfn, pfn);
return pfn;
}
......
......@@ -12,7 +12,8 @@ CFLAGS_mmu.o := $(nostackp)
obj-y := enlighten.o setup.o multicalls.o mmu.o irq.o \
time.o xen-asm.o xen-asm_$(BITS).o \
grant-table.o suspend.o platform-pci-unplug.o
grant-table.o suspend.o platform-pci-unplug.o \
p2m.o
obj-$(CONFIG_SMP) += smp.o
obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o
......
......@@ -173,371 +173,6 @@ DEFINE_PER_CPU(unsigned long, xen_current_cr3); /* actual vcpu cr3 */
*/
#define USER_LIMIT ((STACK_TOP_MAX + PGDIR_SIZE - 1) & PGDIR_MASK)
/*
* Xen leaves the responsibility for maintaining p2m mappings to the
* guests themselves, but it must also access and update the p2m array
* during suspend/resume when all the pages are reallocated.
*
* The p2m table is logically a flat array, but we implement it as a
* three-level tree to allow the address space to be sparse.
*
* Xen
* |
* p2m_top p2m_top_mfn
* / \ / \
* p2m_mid p2m_mid p2m_mid_mfn p2m_mid_mfn
* / \ / \ / /
* p2m p2m p2m p2m p2m p2m p2m ...
*
* The p2m_mid_mfn pages are mapped by p2m_top_mfn_p.
*
* The p2m_top and p2m_top_mfn levels are limited to 1 page, so the
* maximum representable pseudo-physical address space is:
* P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE pages
*
* P2M_PER_PAGE depends on the architecture, as a mfn is always
* unsigned long (8 bytes on 64-bit, 4 bytes on 32), leading to
* 512 and 1024 entries respectively.
*/
unsigned long xen_max_p2m_pfn __read_mostly;
#define P2M_PER_PAGE (PAGE_SIZE / sizeof(unsigned long))
#define P2M_MID_PER_PAGE (PAGE_SIZE / sizeof(unsigned long *))
#define P2M_TOP_PER_PAGE (PAGE_SIZE / sizeof(unsigned long **))
#define MAX_P2M_PFN (P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE)
/* Placeholders for holes in the address space */
static RESERVE_BRK_ARRAY(unsigned long, p2m_missing, P2M_PER_PAGE);
static RESERVE_BRK_ARRAY(unsigned long *, p2m_mid_missing, P2M_MID_PER_PAGE);
static RESERVE_BRK_ARRAY(unsigned long, p2m_mid_missing_mfn, P2M_MID_PER_PAGE);
static RESERVE_BRK_ARRAY(unsigned long **, p2m_top, P2M_TOP_PER_PAGE);
static RESERVE_BRK_ARRAY(unsigned long, p2m_top_mfn, P2M_TOP_PER_PAGE);
static RESERVE_BRK_ARRAY(unsigned long *, p2m_top_mfn_p, P2M_TOP_PER_PAGE);
RESERVE_BRK(p2m_mid, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
static inline unsigned p2m_top_index(unsigned long pfn)
{
BUG_ON(pfn >= MAX_P2M_PFN);
return pfn / (P2M_MID_PER_PAGE * P2M_PER_PAGE);
}
static inline unsigned p2m_mid_index(unsigned long pfn)
{
return (pfn / P2M_PER_PAGE) % P2M_MID_PER_PAGE;
}
static inline unsigned p2m_index(unsigned long pfn)
{
return pfn % P2M_PER_PAGE;
}
static void p2m_top_init(unsigned long ***top)
{
unsigned i;
for (i = 0; i < P2M_TOP_PER_PAGE; i++)
top[i] = p2m_mid_missing;
}
static void p2m_top_mfn_init(unsigned long *top)
{
unsigned i;
for (i = 0; i < P2M_TOP_PER_PAGE; i++)
top[i] = virt_to_mfn(p2m_mid_missing_mfn);
}
static void p2m_top_mfn_p_init(unsigned long **top)
{
unsigned i;
for (i = 0; i < P2M_TOP_PER_PAGE; i++)
top[i] = p2m_mid_missing_mfn;
}
static void p2m_mid_init(unsigned long **mid)
{
unsigned i;
for (i = 0; i < P2M_MID_PER_PAGE; i++)
mid[i] = p2m_missing;
}
static void p2m_mid_mfn_init(unsigned long *mid)
{
unsigned i;
for (i = 0; i < P2M_MID_PER_PAGE; i++)
mid[i] = virt_to_mfn(p2m_missing);
}
static void p2m_init(unsigned long *p2m)
{
unsigned i;
for (i = 0; i < P2M_MID_PER_PAGE; i++)
p2m[i] = INVALID_P2M_ENTRY;
}
/*
* Build the parallel p2m_top_mfn and p2m_mid_mfn structures
*
* This is called both at boot time, and after resuming from suspend:
* - At boot time we're called very early, and must use extend_brk()
* to allocate memory.
*
* - After resume we're called from within stop_machine, but the mfn
* tree should alreay be completely allocated.
*/
void xen_build_mfn_list_list(void)
{
unsigned long pfn;
/* Pre-initialize p2m_top_mfn to be completely missing */
if (p2m_top_mfn == NULL) {
p2m_mid_missing_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE);
p2m_mid_mfn_init(p2m_mid_missing_mfn);
p2m_top_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
p2m_top_mfn_p_init(p2m_top_mfn_p);
p2m_top_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE);
p2m_top_mfn_init(p2m_top_mfn);
} else {
/* Reinitialise, mfn's all change after migration */
p2m_mid_mfn_init(p2m_mid_missing_mfn);
}
for (pfn = 0; pfn < xen_max_p2m_pfn; pfn += P2M_PER_PAGE) {
unsigned topidx = p2m_top_index(pfn);
unsigned mididx = p2m_mid_index(pfn);
unsigned long **mid;
unsigned long *mid_mfn_p;
mid = p2m_top[topidx];
mid_mfn_p = p2m_top_mfn_p[topidx];
/* Don't bother allocating any mfn mid levels if
* they're just missing, just update the stored mfn,
* since all could have changed over a migrate.
*/
if (mid == p2m_mid_missing) {
BUG_ON(mididx);
BUG_ON(mid_mfn_p != p2m_mid_missing_mfn);
p2m_top_mfn[topidx] = virt_to_mfn(p2m_mid_missing_mfn);
pfn += (P2M_MID_PER_PAGE - 1) * P2M_PER_PAGE;
continue;
}
if (mid_mfn_p == p2m_mid_missing_mfn) {
/*
* XXX boot-time only! We should never find
* missing parts of the mfn tree after
* runtime. extend_brk() will BUG if we call
* it too late.
*/
mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
p2m_mid_mfn_init(mid_mfn_p);
p2m_top_mfn_p[topidx] = mid_mfn_p;
}
p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p);
mid_mfn_p[mididx] = virt_to_mfn(mid[mididx]);
}
}
void xen_setup_mfn_list_list(void)
{
BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);
HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list =
virt_to_mfn(p2m_top_mfn);
HYPERVISOR_shared_info->arch.max_pfn = xen_max_p2m_pfn;
}
/* Set up p2m_top to point to the domain-builder provided p2m pages */
void __init xen_build_dynamic_phys_to_machine(void)
{
unsigned long *mfn_list = (unsigned long *)xen_start_info->mfn_list;
unsigned long max_pfn = min(MAX_DOMAIN_PAGES, xen_start_info->nr_pages);
unsigned long pfn;
xen_max_p2m_pfn = max_pfn;
p2m_missing = extend_brk(PAGE_SIZE, PAGE_SIZE);
p2m_init(p2m_missing);
p2m_mid_missing = extend_brk(PAGE_SIZE, PAGE_SIZE);
p2m_mid_init(p2m_mid_missing);
p2m_top = extend_brk(PAGE_SIZE, PAGE_SIZE);
p2m_top_init(p2m_top);
/*
* The domain builder gives us a pre-constructed p2m array in
* mfn_list for all the pages initially given to us, so we just
* need to graft that into our tree structure.
*/
for (pfn = 0; pfn < max_pfn; pfn += P2M_PER_PAGE) {
unsigned topidx = p2m_top_index(pfn);
unsigned mididx = p2m_mid_index(pfn);
if (p2m_top[topidx] == p2m_mid_missing) {
unsigned long **mid = extend_brk(PAGE_SIZE, PAGE_SIZE);
p2m_mid_init(mid);
p2m_top[topidx] = mid;
}
p2m_top[topidx][mididx] = &mfn_list[pfn];
}
}
unsigned long get_phys_to_machine(unsigned long pfn)
{
unsigned topidx, mididx, idx;
if (unlikely(pfn >= MAX_P2M_PFN))
return INVALID_P2M_ENTRY;
topidx = p2m_top_index(pfn);
mididx = p2m_mid_index(pfn);
idx = p2m_index(pfn);
return p2m_top[topidx][mididx][idx];
}
EXPORT_SYMBOL_GPL(get_phys_to_machine);
static void *alloc_p2m_page(void)
{
return (void *)__get_free_page(GFP_KERNEL | __GFP_REPEAT);
}
static void free_p2m_page(void *p)
{
free_page((unsigned long)p);
}
/*
* Fully allocate the p2m structure for a given pfn. We need to check
* that both the top and mid levels are allocated, and make sure the
* parallel mfn tree is kept in sync. We may race with other cpus, so
* the new pages are installed with cmpxchg; if we lose the race then
* simply free the page we allocated and use the one that's there.
*/
static bool alloc_p2m(unsigned long pfn)
{
unsigned topidx, mididx;
unsigned long ***top_p, **mid;
unsigned long *top_mfn_p, *mid_mfn;
topidx = p2m_top_index(pfn);
mididx = p2m_mid_index(pfn);
top_p = &p2m_top[topidx];
mid = *top_p;
if (mid == p2m_mid_missing) {
/* Mid level is missing, allocate a new one */
mid = alloc_p2m_page();
if (!mid)
return false;
p2m_mid_init(mid);
if (cmpxchg(top_p, p2m_mid_missing, mid) != p2m_mid_missing)
free_p2m_page(mid);
}
top_mfn_p = &p2m_top_mfn[topidx];
mid_mfn = p2m_top_mfn_p[topidx];
BUG_ON(virt_to_mfn(mid_mfn) != *top_mfn_p);
if (mid_mfn == p2m_mid_missing_mfn) {
/* Separately check the mid mfn level */
unsigned long missing_mfn;
unsigned long mid_mfn_mfn;
mid_mfn = alloc_p2m_page();
if (!mid_mfn)
return false;
p2m_mid_mfn_init(mid_mfn);
missing_mfn = virt_to_mfn(p2m_mid_missing_mfn);
mid_mfn_mfn = virt_to_mfn(mid_mfn);
if (cmpxchg(top_mfn_p, missing_mfn, mid_mfn_mfn) != missing_mfn)
free_p2m_page(mid_mfn);
else
p2m_top_mfn_p[topidx] = mid_mfn;
}
if (p2m_top[topidx][mididx] == p2m_missing) {
/* p2m leaf page is missing */
unsigned long *p2m;
p2m = alloc_p2m_page();
if (!p2m)
return false;
p2m_init(p2m);
if (cmpxchg(&mid[mididx], p2m_missing, p2m) != p2m_missing)
free_p2m_page(p2m);
else
mid_mfn[mididx] = virt_to_mfn(p2m);
}
return true;
}
/* Try to install p2m mapping; fail if intermediate bits missing */
bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
{
unsigned topidx, mididx, idx;
if (unlikely(pfn >= MAX_P2M_PFN)) {
BUG_ON(mfn != INVALID_P2M_ENTRY);
return true;
}
topidx = p2m_top_index(pfn);
mididx = p2m_mid_index(pfn);
idx = p2m_index(pfn);
if (p2m_top[topidx][mididx] == p2m_missing)
return mfn == INVALID_P2M_ENTRY;
p2m_top[topidx][mididx][idx] = mfn;
return true;
}
bool set_phys_to_machine(unsigned long pfn, unsigned long mfn)
{
if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) {
BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
return true;
}
if (unlikely(!__set_phys_to_machine(pfn, mfn))) {
if (!alloc_p2m(pfn))
return false;
if (!__set_phys_to_machine(pfn, mfn))
return false;
}
return true;
}
unsigned long arbitrary_virt_to_mfn(void *vaddr)
{
xmaddr_t maddr = arbitrary_virt_to_machine(vaddr);
......
/*
* Xen leaves the responsibility for maintaining p2m mappings to the
* guests themselves, but it must also access and update the p2m array
* during suspend/resume when all the pages are reallocated.
*
* The p2m table is logically a flat array, but we implement it as a
* three-level tree to allow the address space to be sparse.
*
* Xen
* |
* p2m_top p2m_top_mfn
* / \ / \
* p2m_mid p2m_mid p2m_mid_mfn p2m_mid_mfn
* / \ / \ / /
* p2m p2m p2m p2m p2m p2m p2m ...
*
* The p2m_mid_mfn pages are mapped by p2m_top_mfn_p.
*
* The p2m_top and p2m_top_mfn levels are limited to 1 page, so the
* maximum representable pseudo-physical address space is:
* P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE pages
*
* P2M_PER_PAGE depends on the architecture, as a mfn is always
* unsigned long (8 bytes on 64-bit, 4 bytes on 32), leading to
* 512 and 1024 entries respectively.
*/
#include <linux/init.h>
#include <linux/module.h>
#include <linux/list.h>
#include <linux/hash.h>
#include <linux/sched.h>
#include <asm/cache.h>
#include <asm/setup.h>
#include <asm/xen/page.h>
#include <asm/xen/hypercall.h>
#include <asm/xen/hypervisor.h>
#include "xen-ops.h"
static void __init m2p_override_init(void);
unsigned long xen_max_p2m_pfn __read_mostly;
#define P2M_PER_PAGE (PAGE_SIZE / sizeof(unsigned long))
#define P2M_MID_PER_PAGE (PAGE_SIZE / sizeof(unsigned long *))
#define P2M_TOP_PER_PAGE (PAGE_SIZE / sizeof(unsigned long **))
#define MAX_P2M_PFN (P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE)
/* Placeholders for holes in the address space */
static RESERVE_BRK_ARRAY(unsigned long, p2m_missing, P2M_PER_PAGE);
static RESERVE_BRK_ARRAY(unsigned long *, p2m_mid_missing, P2M_MID_PER_PAGE);
static RESERVE_BRK_ARRAY(unsigned long, p2m_mid_missing_mfn, P2M_MID_PER_PAGE);
static RESERVE_BRK_ARRAY(unsigned long **, p2m_top, P2M_TOP_PER_PAGE);
static RESERVE_BRK_ARRAY(unsigned long, p2m_top_mfn, P2M_TOP_PER_PAGE);
static RESERVE_BRK_ARRAY(unsigned long *, p2m_top_mfn_p, P2M_TOP_PER_PAGE);
RESERVE_BRK(p2m_mid, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
static inline unsigned p2m_top_index(unsigned long pfn)
{
BUG_ON(pfn >= MAX_P2M_PFN);
return pfn / (P2M_MID_PER_PAGE * P2M_PER_PAGE);
}
static inline unsigned p2m_mid_index(unsigned long pfn)
{
return (pfn / P2M_PER_PAGE) % P2M_MID_PER_PAGE;
}
static inline unsigned p2m_index(unsigned long pfn)
{
return pfn % P2M_PER_PAGE;
}
static void p2m_top_init(unsigned long ***top)
{
unsigned i;
for (i = 0; i < P2M_TOP_PER_PAGE; i++)
top[i] = p2m_mid_missing;
}
static void p2m_top_mfn_init(unsigned long *top)
{
unsigned i;
for (i = 0; i < P2M_TOP_PER_PAGE; i++)
top[i] = virt_to_mfn(p2m_mid_missing_mfn);
}
static void p2m_top_mfn_p_init(unsigned long **top)
{
unsigned i;
for (i = 0; i < P2M_TOP_PER_PAGE; i++)
top[i] = p2m_mid_missing_mfn;
}
static void p2m_mid_init(unsigned long **mid)
{
unsigned i;
for (i = 0; i < P2M_MID_PER_PAGE; i++)
mid[i] = p2m_missing;
}
static void p2m_mid_mfn_init(unsigned long *mid)
{
unsigned i;
for (i = 0; i < P2M_MID_PER_PAGE; i++)
mid[i] = virt_to_mfn(p2m_missing);
}
static void p2m_init(unsigned long *p2m)
{
unsigned i;
for (i = 0; i < P2M_MID_PER_PAGE; i++)
p2m[i] = INVALID_P2M_ENTRY;
}
/*
* Build the parallel p2m_top_mfn and p2m_mid_mfn structures
*
* This is called both at boot time, and after resuming from suspend:
* - At boot time we're called very early, and must use extend_brk()
* to allocate memory.
*
* - After resume we're called from within stop_machine, but the mfn
* tree should alreay be completely allocated.
*/
void xen_build_mfn_list_list(void)
{
unsigned long pfn;
/* Pre-initialize p2m_top_mfn to be completely missing */
if (p2m_top_mfn == NULL) {
p2m_mid_missing_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE);
p2m_mid_mfn_init(p2m_mid_missing_mfn);
p2m_top_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
p2m_top_mfn_p_init(p2m_top_mfn_p);
p2m_top_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE);
p2m_top_mfn_init(p2m_top_mfn);
} else {
/* Reinitialise, mfn's all change after migration */
p2m_mid_mfn_init(p2m_mid_missing_mfn);
}
for (pfn = 0; pfn < xen_max_p2m_pfn; pfn += P2M_PER_PAGE) {
unsigned topidx = p2m_top_index(pfn);
unsigned mididx = p2m_mid_index(pfn);
unsigned long **mid;
unsigned long *mid_mfn_p;
mid = p2m_top[topidx];
mid_mfn_p = p2m_top_mfn_p[topidx];
/* Don't bother allocating any mfn mid levels if
* they're just missing, just update the stored mfn,
* since all could have changed over a migrate.
*/
if (mid == p2m_mid_missing) {
BUG_ON(mididx);
BUG_ON(mid_mfn_p != p2m_mid_missing_mfn);
p2m_top_mfn[topidx] = virt_to_mfn(p2m_mid_missing_mfn);
pfn += (P2M_MID_PER_PAGE - 1) * P2M_PER_PAGE;
continue;
}
if (mid_mfn_p == p2m_mid_missing_mfn) {
/*
* XXX boot-time only! We should never find
* missing parts of the mfn tree after
* runtime. extend_brk() will BUG if we call
* it too late.
*/
mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
p2m_mid_mfn_init(mid_mfn_p);
p2m_top_mfn_p[topidx] = mid_mfn_p;
}
p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p);
mid_mfn_p[mididx] = virt_to_mfn(mid[mididx]);
}
}
void xen_setup_mfn_list_list(void)
{
BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);
HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list =
virt_to_mfn(p2m_top_mfn);
HYPERVISOR_shared_info->arch.max_pfn = xen_max_p2m_pfn;
}
/* Set up p2m_top to point to the domain-builder provided p2m pages */
void __init xen_build_dynamic_phys_to_machine(void)
{
unsigned long *