Merge branches 'stable/p2m-identity.v4.9.1' and 'stable/e820' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen
* 'stable/p2m-identity.v4.9.1' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen:
xen/m2p: Check whether the MFN has IDENTITY_FRAME bit set..
xen/m2p: No need to catch exceptions when we know that there is no RAM
xen/debug: WARN_ON when identity PFN has no _PAGE_IOMAP flag set.
xen/debugfs: Add 'p2m' file for printing out the P2M layout.
xen/setup: Set identity mapping for non-RAM E820 and E820 gaps.
xen/mmu: WARN_ON when racing to swap middle leaf.
xen/mmu: Set _PAGE_IOMAP if PFN is an identity PFN.
xen/mmu: Add the notion of identity (1-1) mapping.
xen: Mark all initial reserved pages for the balloon as INVALID_P2M_ENTRY.
* 'stable/e820' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen:
xen/e820: Don't mark balloon memory as E820_UNUSABLE when running as guest and fix overflow.
xen/setup: Inhibit resource API from using System RAM E820 gaps as PCI mem gaps.
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index f25bdf2..c61934f 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -29,8 +29,10 @@
/**** MACHINE <-> PHYSICAL CONVERSION MACROS ****/
#define INVALID_P2M_ENTRY (~0UL)
-#define FOREIGN_FRAME_BIT (1UL<<31)
+#define FOREIGN_FRAME_BIT (1UL<<(BITS_PER_LONG-1))
+#define IDENTITY_FRAME_BIT (1UL<<(BITS_PER_LONG-2))
#define FOREIGN_FRAME(m) ((m) | FOREIGN_FRAME_BIT)
+#define IDENTITY_FRAME(m) ((m) | IDENTITY_FRAME_BIT)
/* Maximum amount of memory we can handle in a domain in pages */
#define MAX_DOMAIN_PAGES \
@@ -41,12 +43,18 @@
extern unsigned long get_phys_to_machine(unsigned long pfn);
extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn);
+extern bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
+extern unsigned long set_phys_range_identity(unsigned long pfn_s,
+ unsigned long pfn_e);
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);
+#ifdef CONFIG_XEN_DEBUG_FS
+extern int p2m_dump_show(struct seq_file *m, void *v);
+#endif
static inline unsigned long pfn_to_mfn(unsigned long pfn)
{
unsigned long mfn;
@@ -57,7 +65,7 @@
mfn = get_phys_to_machine(pfn);
if (mfn != INVALID_P2M_ENTRY)
- mfn &= ~FOREIGN_FRAME_BIT;
+ mfn &= ~(FOREIGN_FRAME_BIT | IDENTITY_FRAME_BIT);
return mfn;
}
@@ -73,25 +81,44 @@
static inline unsigned long mfn_to_pfn(unsigned long mfn)
{
unsigned long pfn;
+ int ret = 0;
if (xen_feature(XENFEAT_auto_translated_physmap))
return mfn;
+ if (unlikely((mfn >> machine_to_phys_order) != 0)) {
+ pfn = ~0;
+ goto try_override;
+ }
pfn = 0;
/*
* The array access can fail (e.g., device space beyond end of RAM).
* In such cases it doesn't matter what we return (we return garbage),
* but we must handle the fault without crashing!
*/
- __get_user(pfn, &machine_to_phys_mapping[mfn]);
+ ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
+try_override:
+ /* ret might be < 0 if there are no entries in the m2p for mfn */
+ if (ret < 0)
+ pfn = ~0;
+ else if (get_phys_to_machine(pfn) != 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.
+ *
+ * m2p_find_override_pfn returns ~0 if it doesn't find anything.
+ */
+ pfn = m2p_find_override_pfn(mfn, ~0);
- /*
- * 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.
+ /*
+ * pfn is ~0 if there are no entries in the m2p for mfn or if the
+ * entry doesn't map back to the mfn and m2p_override doesn't have a
+ * valid entry for it.
*/
- if (get_phys_to_machine(pfn) != mfn)
- pfn = m2p_find_override_pfn(mfn, pfn);
+ if (pfn == ~0 &&
+ get_phys_to_machine(mfn) == IDENTITY_FRAME(mfn))
+ pfn = mfn;
return pfn;
}
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 5b54892..e4343fe 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -48,3 +48,11 @@
help
Enable statistics output and various tuning options in debugfs.
Enabling this option may incur a significant performance overhead.
+
+config XEN_DEBUG
+ bool "Enable Xen debug checks"
+ depends on XEN
+ default n
+ help
+ Enable various WARN_ON checks in the Xen MMU code.
+ Enabling this option WILL incur a significant performance overhead.
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index f608942..832765c 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -46,6 +46,7 @@
#include <linux/module.h>
#include <linux/gfp.h>
#include <linux/memblock.h>
+#include <linux/seq_file.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
@@ -416,8 +417,12 @@
if (val & _PAGE_PRESENT) {
unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
pteval_t flags = val & PTE_FLAGS_MASK;
- unsigned long mfn = pfn_to_mfn(pfn);
+ unsigned long mfn;
+ if (!xen_feature(XENFEAT_auto_translated_physmap))
+ mfn = get_phys_to_machine(pfn);
+ else
+ mfn = pfn;
/*
* If there's no mfn for the pfn, then just create an
* empty non-present pte. Unfortunately this loses
@@ -427,8 +432,18 @@
if (unlikely(mfn == INVALID_P2M_ENTRY)) {
mfn = 0;
flags = 0;
+ } else {
+ /*
+ * Paramount to do this test _after_ the
+ * INVALID_P2M_ENTRY as INVALID_P2M_ENTRY &
+ * IDENTITY_FRAME_BIT resolves to true.
+ */
+ mfn &= ~FOREIGN_FRAME_BIT;
+ if (mfn & IDENTITY_FRAME_BIT) {
+ mfn &= ~IDENTITY_FRAME_BIT;
+ flags |= _PAGE_IOMAP;
+ }
}
-
val = ((pteval_t)mfn << PAGE_SHIFT) | flags;
}
@@ -532,6 +547,41 @@
}
PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte);
+#ifdef CONFIG_XEN_DEBUG
+pte_t xen_make_pte_debug(pteval_t pte)
+{
+ phys_addr_t addr = (pte & PTE_PFN_MASK);
+ phys_addr_t other_addr;
+ bool io_page = false;
+ pte_t _pte;
+
+ if (pte & _PAGE_IOMAP)
+ io_page = true;
+
+ _pte = xen_make_pte(pte);
+
+ if (!addr)
+ return _pte;
+
+ if (io_page &&
+ (xen_initial_domain() || addr >= ISA_END_ADDRESS)) {
+ other_addr = pfn_to_mfn(addr >> PAGE_SHIFT) << PAGE_SHIFT;
+ WARN(addr != other_addr,
+ "0x%lx is using VM_IO, but it is 0x%lx!\n",
+ (unsigned long)addr, (unsigned long)other_addr);
+ } else {
+ pteval_t iomap_set = (_pte.pte & PTE_FLAGS_MASK) & _PAGE_IOMAP;
+ other_addr = (_pte.pte & PTE_PFN_MASK);
+ WARN((addr == other_addr) && (!io_page) && (!iomap_set),
+ "0x%lx is missing VM_IO (and wasn't fixed)!\n",
+ (unsigned long)addr);
+ }
+
+ return _pte;
+}
+PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_debug);
+#endif
+
pgd_t xen_make_pgd(pgdval_t pgd)
{
pgd = pte_pfn_to_mfn(pgd);
@@ -1940,6 +1990,9 @@
static __init void xen_post_allocator_init(void)
{
+#ifdef CONFIG_XEN_DEBUG
+ pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte_debug);
+#endif
pv_mmu_ops.set_pte = xen_set_pte;
pv_mmu_ops.set_pmd = xen_set_pmd;
pv_mmu_ops.set_pud = xen_set_pud;
@@ -2072,7 +2125,7 @@
in_frames[i] = virt_to_mfn(vaddr);
MULTI_update_va_mapping(mcs.mc, vaddr, VOID_PTE, 0);
- set_phys_to_machine(virt_to_pfn(vaddr), INVALID_P2M_ENTRY);
+ __set_phys_to_machine(virt_to_pfn(vaddr), INVALID_P2M_ENTRY);
if (out_frames)
out_frames[i] = virt_to_pfn(vaddr);
@@ -2351,6 +2404,18 @@
#ifdef CONFIG_XEN_DEBUG_FS
+static int p2m_dump_open(struct inode *inode, struct file *filp)
+{
+ return single_open(filp, p2m_dump_show, NULL);
+}
+
+static const struct file_operations p2m_dump_fops = {
+ .open = p2m_dump_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
static struct dentry *d_mmu_debug;
static int __init xen_mmu_debugfs(void)
@@ -2406,6 +2471,7 @@
debugfs_create_u32("prot_commit_batched", 0444, d_mmu_debug,
&mmu_stats.prot_commit_batched);
+ debugfs_create_file("p2m", 0600, d_mmu_debug, NULL, &p2m_dump_fops);
return 0;
}
fs_initcall(xen_mmu_debugfs);
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index fd12d7c..00fe560 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -23,6 +23,129 @@
* 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.
+ *
+ * In short, these structures contain the Machine Frame Number (MFN) of the PFN.
+ *
+ * However not all entries are filled with MFNs. Specifically for all other
+ * leaf entries, or for the top root, or middle one, for which there is a void
+ * entry, we assume it is "missing". So (for example)
+ * pfn_to_mfn(0x90909090)=INVALID_P2M_ENTRY.
+ *
+ * We also have the possibility of setting 1-1 mappings on certain regions, so
+ * that:
+ * pfn_to_mfn(0xc0000)=0xc0000
+ *
+ * The benefit of this is, that we can assume for non-RAM regions (think
+ * PCI BARs, or ACPI spaces), we can create mappings easily b/c we
+ * get the PFN value to match the MFN.
+ *
+ * For this to work efficiently we have one new page p2m_identity and
+ * allocate (via reserved_brk) any other pages we need to cover the sides
+ * (1GB or 4MB boundary violations). All entries in p2m_identity are set to
+ * INVALID_P2M_ENTRY type (Xen toolstack only recognizes that and MFNs,
+ * no other fancy value).
+ *
+ * On lookup we spot that the entry points to p2m_identity and return the
+ * identity value instead of dereferencing and returning INVALID_P2M_ENTRY.
+ * If the entry points to an allocated page, we just proceed as before and
+ * return the PFN. If the PFN has IDENTITY_FRAME_BIT set we unmask that in
+ * appropriate functions (pfn_to_mfn).
+ *
+ * The reason for having the IDENTITY_FRAME_BIT instead of just returning the
+ * PFN is that we could find ourselves where pfn_to_mfn(pfn)==pfn for a
+ * non-identity pfn. To protect ourselves against we elect to set (and get) the
+ * IDENTITY_FRAME_BIT on all identity mapped PFNs.
+ *
+ * This simplistic diagram is used to explain the more subtle piece of code.
+ * There is also a digram of the P2M at the end that can help.
+ * Imagine your E820 looking as so:
+ *
+ * 1GB 2GB
+ * /-------------------+---------\/----\ /----------\ /---+-----\
+ * | System RAM | Sys RAM ||ACPI| | reserved | | Sys RAM |
+ * \-------------------+---------/\----/ \----------/ \---+-----/
+ * ^- 1029MB ^- 2001MB
+ *
+ * [1029MB = 263424 (0x40500), 2001MB = 512256 (0x7D100),
+ * 2048MB = 524288 (0x80000)]
+ *
+ * And dom0_mem=max:3GB,1GB is passed in to the guest, meaning memory past 1GB
+ * is actually not present (would have to kick the balloon driver to put it in).
+ *
+ * When we are told to set the PFNs for identity mapping (see patch: "xen/setup:
+ * Set identity mapping for non-RAM E820 and E820 gaps.") we pass in the start
+ * of the PFN and the end PFN (263424 and 512256 respectively). The first step
+ * is to reserve_brk a top leaf page if the p2m[1] is missing. The top leaf page
+ * covers 512^2 of page estate (1GB) and in case the start or end PFN is not
+ * aligned on 512^2*PAGE_SIZE (1GB) we loop on aligned 1GB PFNs from start pfn
+ * to end pfn. We reserve_brk top leaf pages if they are missing (means they
+ * point to p2m_mid_missing).
+ *
+ * With the E820 example above, 263424 is not 1GB aligned so we allocate a
+ * reserve_brk page which will cover the PFNs estate from 0x40000 to 0x80000.
+ * Each entry in the allocate page is "missing" (points to p2m_missing).
+ *
+ * Next stage is to determine if we need to do a more granular boundary check
+ * on the 4MB (or 2MB depending on architecture) off the start and end pfn's.
+ * We check if the start pfn and end pfn violate that boundary check, and if
+ * so reserve_brk a middle (p2m[x][y]) leaf page. This way we have a much finer
+ * granularity of setting which PFNs are missing and which ones are identity.
+ * In our example 263424 and 512256 both fail the check so we reserve_brk two
+ * pages. Populate them with INVALID_P2M_ENTRY (so they both have "missing"
+ * values) and assign them to p2m[1][2] and p2m[1][488] respectively.
+ *
+ * At this point we would at minimum reserve_brk one page, but could be up to
+ * three. Each call to set_phys_range_identity has at maximum a three page
+ * cost. If we were to query the P2M at this stage, all those entries from
+ * start PFN through end PFN (so 1029MB -> 2001MB) would return
+ * INVALID_P2M_ENTRY ("missing").
+ *
+ * The next step is to walk from the start pfn to the end pfn setting
+ * the IDENTITY_FRAME_BIT on each PFN. This is done in set_phys_range_identity.
+ * If we find that the middle leaf is pointing to p2m_missing we can swap it
+ * over to p2m_identity - this way covering 4MB (or 2MB) PFN space. At this
+ * point we do not need to worry about boundary aligment (so no need to
+ * reserve_brk a middle page, figure out which PFNs are "missing" and which
+ * ones are identity), as that has been done earlier. If we find that the
+ * middle leaf is not occupied by p2m_identity or p2m_missing, we dereference
+ * that page (which covers 512 PFNs) and set the appropriate PFN with
+ * IDENTITY_FRAME_BIT. In our example 263424 and 512256 end up there, and we
+ * set from p2m[1][2][256->511] and p2m[1][488][0->256] with
+ * IDENTITY_FRAME_BIT set.
+ *
+ * All other regions that are void (or not filled) either point to p2m_missing
+ * (considered missing) or have the default value of INVALID_P2M_ENTRY (also
+ * considered missing). In our case, p2m[1][2][0->255] and p2m[1][488][257->511]
+ * contain the INVALID_P2M_ENTRY value and are considered "missing."
+ *
+ * This is what the p2m ends up looking (for the E820 above) with this
+ * fabulous drawing:
+ *
+ * p2m /--------------\
+ * /-----\ | &mfn_list[0],| /-----------------\
+ * | 0 |------>| &mfn_list[1],| /---------------\ | ~0, ~0, .. |
+ * |-----| | ..., ~0, ~0 | | ~0, ~0, [x]---+----->| IDENTITY [@256] |
+ * | 1 |---\ \--------------/ | [p2m_identity]+\ | IDENTITY [@257] |
+ * |-----| \ | [p2m_identity]+\\ | .... |
+ * | 2 |--\ \-------------------->| ... | \\ \----------------/
+ * |-----| \ \---------------/ \\
+ * | 3 |\ \ \\ p2m_identity
+ * |-----| \ \-------------------->/---------------\ /-----------------\
+ * | .. +->+ | [p2m_identity]+-->| ~0, ~0, ~0, ... |
+ * \-----/ / | [p2m_identity]+-->| ..., ~0 |
+ * / /---------------\ | .... | \-----------------/
+ * / | IDENTITY[@0] | /-+-[x], ~0, ~0.. |
+ * / | IDENTITY[@256]|<----/ \---------------/
+ * / | ~0, ~0, .... |
+ * | \---------------/
+ * |
+ * p2m_missing p2m_missing
+ * /------------------\ /------------\
+ * | [p2m_mid_missing]+---->| ~0, ~0, ~0 |
+ * | [p2m_mid_missing]+---->| ..., ~0 |
+ * \------------------/ \------------/
+ *
+ * where ~0 is INVALID_P2M_ENTRY. IDENTITY is (PFN | IDENTITY_BIT)
*/
#include <linux/init.h>
@@ -30,6 +153,7 @@
#include <linux/list.h>
#include <linux/hash.h>
#include <linux/sched.h>
+#include <linux/seq_file.h>
#include <asm/cache.h>
#include <asm/setup.h>
@@ -59,9 +183,15 @@
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);
+static RESERVE_BRK_ARRAY(unsigned long, p2m_identity, P2M_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)));
+/* We might hit two boundary violations at the start and end, at max each
+ * boundary violation will require three middle nodes. */
+RESERVE_BRK(p2m_mid_identity, PAGE_SIZE * 2 * 3);
+
static inline unsigned p2m_top_index(unsigned long pfn)
{
BUG_ON(pfn >= MAX_P2M_PFN);
@@ -221,6 +351,9 @@
p2m_top = extend_brk(PAGE_SIZE, PAGE_SIZE);
p2m_top_init(p2m_top);
+ p2m_identity = extend_brk(PAGE_SIZE, PAGE_SIZE);
+ p2m_init(p2m_identity);
+
/*
* The domain builder gives us a pre-constructed p2m array in
* mfn_list for all the pages initially given to us, so we just
@@ -266,6 +399,14 @@
mididx = p2m_mid_index(pfn);
idx = p2m_index(pfn);
+ /*
+ * The INVALID_P2M_ENTRY is filled in both p2m_*identity
+ * and in p2m_*missing, so returning the INVALID_P2M_ENTRY
+ * would be wrong.
+ */
+ if (p2m_top[topidx][mididx] == p2m_identity)
+ return IDENTITY_FRAME(pfn);
+
return p2m_top[topidx][mididx][idx];
}
EXPORT_SYMBOL_GPL(get_phys_to_machine);
@@ -335,9 +476,11 @@
p2m_top_mfn_p[topidx] = mid_mfn;
}
- if (p2m_top[topidx][mididx] == p2m_missing) {
+ if (p2m_top[topidx][mididx] == p2m_identity ||
+ p2m_top[topidx][mididx] == p2m_missing) {
/* p2m leaf page is missing */
unsigned long *p2m;
+ unsigned long *p2m_orig = p2m_top[topidx][mididx];
p2m = alloc_p2m_page();
if (!p2m)
@@ -345,7 +488,7 @@
p2m_init(p2m);
- if (cmpxchg(&mid[mididx], p2m_missing, p2m) != p2m_missing)
+ if (cmpxchg(&mid[mididx], p2m_orig, p2m) != p2m_orig)
free_p2m_page(p2m);
else
mid_mfn[mididx] = virt_to_mfn(p2m);
@@ -354,11 +497,91 @@
return true;
}
+bool __early_alloc_p2m(unsigned long pfn)
+{
+ unsigned topidx, mididx, idx;
+
+ topidx = p2m_top_index(pfn);
+ mididx = p2m_mid_index(pfn);
+ idx = p2m_index(pfn);
+
+ /* Pfff.. No boundary cross-over, lets get out. */
+ if (!idx)
+ return false;
+
+ WARN(p2m_top[topidx][mididx] == p2m_identity,
+ "P2M[%d][%d] == IDENTITY, should be MISSING (or alloced)!\n",
+ topidx, mididx);
+
+ /*
+ * Could be done by xen_build_dynamic_phys_to_machine..
+ */
+ if (p2m_top[topidx][mididx] != p2m_missing)
+ return false;
+
+ /* Boundary cross-over for the edges: */
+ if (idx) {
+ unsigned long *p2m = extend_brk(PAGE_SIZE, PAGE_SIZE);
+
+ p2m_init(p2m);
+
+ p2m_top[topidx][mididx] = p2m;
+
+ }
+ return idx != 0;
+}
+unsigned long set_phys_range_identity(unsigned long pfn_s,
+ unsigned long pfn_e)
+{
+ unsigned long pfn;
+
+ if (unlikely(pfn_s >= MAX_P2M_PFN || pfn_e >= MAX_P2M_PFN))
+ return 0;
+
+ if (unlikely(xen_feature(XENFEAT_auto_translated_physmap)))
+ return pfn_e - pfn_s;
+
+ if (pfn_s > pfn_e)
+ return 0;
+
+ for (pfn = (pfn_s & ~(P2M_MID_PER_PAGE * P2M_PER_PAGE - 1));
+ pfn < ALIGN(pfn_e, (P2M_MID_PER_PAGE * P2M_PER_PAGE));
+ pfn += P2M_MID_PER_PAGE * P2M_PER_PAGE)
+ {
+ unsigned topidx = p2m_top_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;
+ }
+ }
+
+ __early_alloc_p2m(pfn_s);
+ __early_alloc_p2m(pfn_e);
+
+ for (pfn = pfn_s; pfn < pfn_e; pfn++)
+ if (!__set_phys_to_machine(pfn, IDENTITY_FRAME(pfn)))
+ break;
+
+ if (!WARN((pfn - pfn_s) != (pfn_e - pfn_s),
+ "Identity mapping failed. We are %ld short of 1-1 mappings!\n",
+ (pfn_e - pfn_s) - (pfn - pfn_s)))
+ printk(KERN_DEBUG "1-1 mapping on %lx->%lx\n", pfn_s, pfn);
+
+ return pfn - pfn_s;
+}
+
/* 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(xen_feature(XENFEAT_auto_translated_physmap))) {
+ BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
+ return true;
+ }
if (unlikely(pfn >= MAX_P2M_PFN)) {
BUG_ON(mfn != INVALID_P2M_ENTRY);
return true;
@@ -368,6 +591,21 @@
mididx = p2m_mid_index(pfn);
idx = p2m_index(pfn);
+ /* For sparse holes were the p2m leaf has real PFN along with
+ * PCI holes, stick in the PFN as the MFN value.
+ */
+ if (mfn != INVALID_P2M_ENTRY && (mfn & IDENTITY_FRAME_BIT)) {
+ if (p2m_top[topidx][mididx] == p2m_identity)
+ return true;
+
+ /* Swap over from MISSING to IDENTITY if needed. */
+ if (p2m_top[topidx][mididx] == p2m_missing) {
+ WARN_ON(cmpxchg(&p2m_top[topidx][mididx], p2m_missing,
+ p2m_identity) != p2m_missing);
+ return true;
+ }
+ }
+
if (p2m_top[topidx][mididx] == p2m_missing)
return mfn == INVALID_P2M_ENTRY;
@@ -378,11 +616,6 @@
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;
@@ -520,3 +753,80 @@
return ret;
}
EXPORT_SYMBOL_GPL(m2p_find_override_pfn);
+
+#ifdef CONFIG_XEN_DEBUG_FS
+
+int p2m_dump_show(struct seq_file *m, void *v)
+{
+ static const char * const level_name[] = { "top", "middle",
+ "entry", "abnormal" };
+ static const char * const type_name[] = { "identity", "missing",
+ "pfn", "abnormal"};
+#define TYPE_IDENTITY 0
+#define TYPE_MISSING 1
+#define TYPE_PFN 2
+#define TYPE_UNKNOWN 3
+ unsigned long pfn, prev_pfn_type = 0, prev_pfn_level = 0;
+ unsigned int uninitialized_var(prev_level);
+ unsigned int uninitialized_var(prev_type);
+
+ if (!p2m_top)
+ return 0;
+
+ for (pfn = 0; pfn < MAX_DOMAIN_PAGES; pfn++) {
+ unsigned topidx = p2m_top_index(pfn);
+ unsigned mididx = p2m_mid_index(pfn);
+ unsigned idx = p2m_index(pfn);
+ unsigned lvl, type;
+
+ lvl = 4;
+ type = TYPE_UNKNOWN;
+ if (p2m_top[topidx] == p2m_mid_missing) {
+ lvl = 0; type = TYPE_MISSING;
+ } else if (p2m_top[topidx] == NULL) {
+ lvl = 0; type = TYPE_UNKNOWN;
+ } else if (p2m_top[topidx][mididx] == NULL) {
+ lvl = 1; type = TYPE_UNKNOWN;
+ } else if (p2m_top[topidx][mididx] == p2m_identity) {
+ lvl = 1; type = TYPE_IDENTITY;
+ } else if (p2m_top[topidx][mididx] == p2m_missing) {
+ lvl = 1; type = TYPE_MISSING;
+ } else if (p2m_top[topidx][mididx][idx] == 0) {
+ lvl = 2; type = TYPE_UNKNOWN;
+ } else if (p2m_top[topidx][mididx][idx] == IDENTITY_FRAME(pfn)) {
+ lvl = 2; type = TYPE_IDENTITY;
+ } else if (p2m_top[topidx][mididx][idx] == INVALID_P2M_ENTRY) {
+ lvl = 2; type = TYPE_MISSING;
+ } else if (p2m_top[topidx][mididx][idx] == pfn) {
+ lvl = 2; type = TYPE_PFN;
+ } else if (p2m_top[topidx][mididx][idx] != pfn) {
+ lvl = 2; type = TYPE_PFN;
+ }
+ if (pfn == 0) {
+ prev_level = lvl;
+ prev_type = type;
+ }
+ if (pfn == MAX_DOMAIN_PAGES-1) {
+ lvl = 3;
+ type = TYPE_UNKNOWN;
+ }
+ if (prev_type != type) {
+ seq_printf(m, " [0x%lx->0x%lx] %s\n",
+ prev_pfn_type, pfn, type_name[prev_type]);
+ prev_pfn_type = pfn;
+ prev_type = type;
+ }
+ if (prev_level != lvl) {
+ seq_printf(m, " [0x%lx->0x%lx] level %s\n",
+ prev_pfn_level, pfn, level_name[prev_level]);
+ prev_pfn_level = pfn;
+ prev_level = lvl;
+ }
+ }
+ return 0;
+#undef TYPE_IDENTITY
+#undef TYPE_MISSING
+#undef TYPE_PFN
+#undef TYPE_UNKNOWN
+}
+#endif
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index a8a66a5..fa0269a 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -52,6 +52,8 @@
static __init void xen_add_extra_mem(unsigned long pages)
{
+ unsigned long pfn;
+
u64 size = (u64)pages * PAGE_SIZE;
u64 extra_start = xen_extra_mem_start + xen_extra_mem_size;
@@ -66,6 +68,9 @@
xen_extra_mem_size += size;
xen_max_p2m_pfn = PFN_DOWN(extra_start + size);
+
+ for (pfn = PFN_DOWN(extra_start); pfn <= xen_max_p2m_pfn; pfn++)
+ __set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
}
static unsigned long __init xen_release_chunk(phys_addr_t start_addr,
@@ -104,7 +109,7 @@
WARN(ret != 1, "Failed to release memory %lx-%lx err=%d\n",
start, end, ret);
if (ret == 1) {
- set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
+ __set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
len++;
}
}
@@ -138,12 +143,55 @@
return released;
}
+static unsigned long __init xen_set_identity(const struct e820entry *list,
+ ssize_t map_size)
+{
+ phys_addr_t last = xen_initial_domain() ? 0 : ISA_END_ADDRESS;
+ phys_addr_t start_pci = last;
+ const struct e820entry *entry;
+ unsigned long identity = 0;
+ int i;
+
+ for (i = 0, entry = list; i < map_size; i++, entry++) {
+ phys_addr_t start = entry->addr;
+ phys_addr_t end = start + entry->size;
+
+ if (start < last)
+ start = last;
+
+ if (end <= start)
+ continue;
+
+ /* Skip over the 1MB region. */
+ if (last > end)
+ continue;
+
+ if (entry->type == E820_RAM) {
+ if (start > start_pci)
+ identity += set_phys_range_identity(
+ PFN_UP(start_pci), PFN_DOWN(start));
+
+ /* Without saving 'last' we would gooble RAM too
+ * at the end of the loop. */
+ last = end;
+ start_pci = end;
+ continue;
+ }
+ start_pci = min(start, start_pci);
+ last = end;
+ }
+ if (last > start_pci)
+ identity += set_phys_range_identity(
+ PFN_UP(start_pci), PFN_DOWN(last));
+ return identity;
+}
/**
* machine_specific_memory_setup - Hook for machine specific memory setup.
**/
char * __init xen_memory_setup(void)
{
static struct e820entry map[E820MAX] __initdata;
+ static struct e820entry map_raw[E820MAX] __initdata;
unsigned long max_pfn = xen_start_info->nr_pages;
unsigned long long mem_end;
@@ -151,6 +199,7 @@
struct xen_memory_map memmap;
unsigned long extra_pages = 0;
unsigned long extra_limit;
+ unsigned long identity_pages = 0;
int i;
int op;
@@ -176,6 +225,7 @@
}
BUG_ON(rc);
+ memcpy(map_raw, map, sizeof(map));
e820.nr_map = 0;
xen_extra_mem_start = mem_end;
for (i = 0; i < memmap.nr_entries; i++) {
@@ -194,6 +244,15 @@
end -= delta;
extra_pages += PFN_DOWN(delta);
+ /*
+ * Set RAM below 4GB that is not for us to be unusable.
+ * This prevents "System RAM" address space from being
+ * used as potential resource for I/O address (happens
+ * when 'allocate_resource' is called).
+ */
+ if (delta &&
+ (xen_initial_domain() && end < 0x100000000ULL))
+ e820_add_region(end, delta, E820_UNUSABLE);
}
if (map[i].size > 0 && end > xen_extra_mem_start)
@@ -251,6 +310,13 @@
xen_add_extra_mem(extra_pages);
+ /*
+ * Set P2M for all non-RAM pages and E820 gaps to be identity
+ * type PFNs. We supply it with the non-sanitized version
+ * of the E820.
+ */
+ identity_pages = xen_set_identity(map_raw, memmap.nr_entries);
+ printk(KERN_INFO "Set %ld page(s) to 1-1 mapping.\n", identity_pages);
return "Xen";
}
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 43f9f02..b1661cd 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -296,7 +296,7 @@
/* No more mappings: invalidate P2M and add to balloon. */
for (i = 0; i < nr_pages; i++) {
pfn = mfn_to_pfn(frame_list[i]);
- set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
+ __set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
balloon_append(pfn_to_page(pfn));
}
