ChangeSet 1.1296, 2005/04/14 21:53:24+01:00, kaf24@firebug.cl.cam.ac.uk
Manual merge.
b/xen/arch/x86/mm.c | 2946 +++++++++++++++++++++++++++++++++++++++++++
b/xen/common/grant_table.c | 940 +++++++++++--
b/xen/include/asm-x86/page.h | 240 +--
xen/arch/x86/memory.c | 2399 -----------------------------------
4 files changed, 3824 insertions(+), 2701 deletions(-)
diff -Nru a/xen/arch/x86/memory.c b/xen/arch/x86/memory.c
--- a/xen/arch/x86/memory.c 2005-04-14 17:03:22 -04:00
+++ /dev/null Wed Dec 31 16:00:00 196900
@@ -1,2399 +0,0 @@
-/******************************************************************************
- * arch/x86/memory.c
- *
- * Copyright (c) 2002-2004 K A Fraser
- * Copyright (c) 2004 Christian Limpach
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
- */
-
-/*
- * A description of the x86 page table API:
- *
- * Domains trap to do_mmu_update with a list of update requests.
- * This is a list of (ptr, val) pairs, where the requested operation
- * is *ptr = val.
- *
- * Reference counting of pages:
- * ----------------------------
- * Each page has two refcounts: tot_count and type_count.
- *
- * TOT_COUNT is the obvious reference count. It counts all uses of a
- * physical page frame by a domain, including uses as a page directory,
- * a page table, or simple mappings via a PTE. This count prevents a
- * domain from releasing a frame back to the free pool when it still holds
- * a reference to it.
- *
- * TYPE_COUNT is more subtle. A frame can be put to one of three
- * mutually-exclusive uses: it might be used as a page directory, or a
- * page table, or it may be mapped writable by the domain [.of course, a
- * frame may not be used in any of these three ways!].
- * So, type_count is a count of the number of times a frame is being
- * referred to in its current incarnation. Therefore, a page can only
- * change its type when its type count is zero.
- *
- * Pinning the page type:
- * ----------------------
- * The type of a page can be pinned/unpinned with the commands
- * MMUEXT_[UN]PIN_L?_TABLE. Each page can be pinned exactly once (that is,
- * pinning is not reference counted, so it can't be nested).
- * This is useful to prevent a page's type count falling to zero, at which
- * point safety checks would need to be carried out next time the count
- * is increased again.
- *
- * A further note on writable page mappings:
- * -----------------------------------------
- * For simplicity, the count of writable mappings for a page may not
- * correspond to reality. The 'writable count' is incremented for every
- * PTE which maps the page with the _PAGE_RW flag set. However, for
- * write access to be possible the page directory entry must also have
- * its _PAGE_RW bit set. We do not check this as it complicates the
- * reference counting considerably [.consider the case of multiple
- * directory entries referencing a single page table, some with the RW
- * bit set, others not -- it starts getting a bit messy].
- * In normal use, this simplification shouldn't be a problem.
- * However, the logic can be added if required.
- *
- * One more note on read-only page mappings:
- * -----------------------------------------
- * We want domains to be able to map pages for read-only access. The
- * main reason is that page tables and directories should be readable
- * by a domain, but it would not be safe for them to be writable.
- * However, domains have free access to rings 1 & 2 of the Intel
- * privilege model. In terms of page protection, these are considered
- * to be part of 'supervisor mode'. The WP bit in CR0 controls whether
- * read-only restrictions are respected in supervisor mode -- if the
- * bit is clear then any mapped page is writable.
- *
- * We get round this by always setting the WP bit and disallowing
- * updates to it. This is very unlikely to cause a problem for guest
- * OS's, which will generally use the WP bit to simplify copy-on-write
- * implementation (in that case, OS wants a fault when it writes to
- * an application-supplied buffer).
- */
-
-#include <xen/config.h>
-#include <xen/init.h>
-#include <xen/kernel.h>
-#include <xen/lib.h>
-#include <xen/mm.h>
-#include <xen/sched.h>
-#include <xen/errno.h>
-#include <xen/perfc.h>
-#include <xen/irq.h>
-#include <xen/softirq.h>
-#include <asm/shadow.h>
-#include <asm/page.h>
-#include <asm/flushtlb.h>
-#include <asm/io.h>
-#include <asm/uaccess.h>
-#include <asm/domain_page.h>
-#include <asm/ldt.h>
-#include <asm/e820.h>
-
-#ifdef VERBOSE
-#define MEM_LOG(_f, _a...) \
- printk("DOM%u: (file=memory.c, line=%d) " _f "\n", \
- current->id , __LINE__ , ## _a )
-#else
-#define MEM_LOG(_f, _a...) ((void)0)
-#endif
-
-static int alloc_l2_table(struct pfn_info *page);
-static int alloc_l1_table(struct pfn_info *page);
-static int get_page_from_pagenr(unsigned long page_nr, struct domain *d);
-static int get_page_and_type_from_pagenr(unsigned long page_nr,
- u32 type,
- struct domain *d);
-
-static void free_l2_table(struct pfn_info *page);
-static void free_l1_table(struct pfn_info *page);
-
-static int mod_l2_entry(l2_pgentry_t *, l2_pgentry_t, unsigned long);
-static int mod_l1_entry(l1_pgentry_t *, l1_pgentry_t);
-
-/* Used to defer flushing of memory structures. */
-static struct {
-#define DOP_FLUSH_TLB (1<<0) /* Flush the TLB. */
-#define DOP_RELOAD_LDT (1<<1) /* Reload the LDT shadow mapping. */
- unsigned long deferred_ops;
- /* If non-NULL, specifies a foreign subject domain for some operations. */
- struct domain *foreign;
-} __cacheline_aligned percpu_info[NR_CPUS];
-
-/*
- * Returns the current foreign domain; defaults to the currently-executing
- * domain if a foreign override hasn't been specified.
- */
-#define FOREIGNDOM (percpu_info[smp_processor_id()].foreign ? : current)
-
-/* Private domain structs for DOMID_XEN and DOMID_IO. */
-static struct domain *dom_xen, *dom_io;
-
-/* Frame table and its size in pages. */
-struct pfn_info *frame_table;
-unsigned long frame_table_size;
-unsigned long max_page;
-
-void __init init_frametable(void)
-{
- unsigned long i, p;
-
- frame_table = (struct pfn_info *)FRAMETABLE_VIRT_START;
- frame_table_size = max_page * sizeof(struct pfn_info);
- frame_table_size = (frame_table_size + PAGE_SIZE - 1) & PAGE_MASK;
-
- for ( i = 0; i < frame_table_size; i += (4UL << 20) )
- {
- p = alloc_boot_pages(min(frame_table_size - i, 4UL << 20), 4UL << 20);
- if ( p == 0 )
- panic("Not enough memory for frame table\n");
- idle_pg_table[(FRAMETABLE_VIRT_START + i) >> L2_PAGETABLE_SHIFT] =
- mk_l2_pgentry(p | __PAGE_HYPERVISOR | _PAGE_PSE);
- }
-
- memset(frame_table, 0, frame_table_size);
-}
-
-void arch_init_memory(void)
-{
- unsigned long i, j, pfn, nr_pfns;
- struct pfn_info *page;
-
- /*
- * We are rather picky about the layout of 'struct pfn_info'. The
- * count_info and domain fields must be adjacent, as we perform atomic
- * 64-bit operations on them. Also, just for sanity, we assert the size
- * of the structure here.
- */
- if ( (offsetof(struct pfn_info, u.inuse.domain) !=
- (offsetof(struct pfn_info, count_info) + sizeof(u32))) ||
- (sizeof(struct pfn_info) != 24) )
- {
- printk("Weird pfn_info layout (%ld,%ld,%d)\n",
- offsetof(struct pfn_info, count_info),
- offsetof(struct pfn_info, u.inuse.domain),
- sizeof(struct pfn_info));
- for ( ; ; ) ;
- }
-
- memset(percpu_info, 0, sizeof(percpu_info));
-
- /* Initialise to a magic of 0x55555555 so easier to spot bugs later. */
- memset(machine_to_phys_mapping, 0x55, 4<<20);
-
- /*
- * Initialise our DOMID_XEN domain.
- * Any Xen-heap pages that we will allow to be mapped will have
- * their domain field set to dom_xen.
- */
- dom_xen = alloc_domain_struct();
- atomic_set(&dom_xen->refcnt, 1);
- dom_xen->id = DOMID_XEN;
-
- /*
- * Initialise our DOMID_IO domain.
- * This domain owns I/O pages that are within the range of the pfn_info
- * array. Mappings occur at the priv of the caller.
- */
- dom_io = alloc_domain_struct();
- atomic_set(&dom_io->refcnt, 1);
- dom_io->id = DOMID_IO;
-
- /* M2P table is mappable read-only by privileged domains. */
- for ( i = 0; i < 1024; i++ )
- {
- /* Ensure it's mapped read-only by guests (use GDT type). */
- page = &frame_table[m2p_start_mfn+i];
- page->count_info = PGC_allocated | 1;
- page->u.inuse.type_info = PGT_gdt_page | PGT_validated | 1;
- page->u.inuse.domain = dom_xen;
- }
-
- /* First 1MB of RAM is historically marked as I/O. */
- for ( i = 0; i < 0x100; i++ )
- {
- page = &frame_table[i];
- page->count_info = PGC_allocated | 1;
- page->u.inuse.type_info = PGT_writable_page | PGT_validated | 1;
- page->u.inuse.domain = dom_io;
- }
-
- /* Any non-RAM areas in the e820 map are considered to be for I/O. */
- for ( i = 0; i < e820.nr_map; i++ )
- {
- if ( e820.map[i].type == E820_RAM )
- continue;
- pfn = e820.map[i].addr >> PAGE_SHIFT;
- nr_pfns = (e820.map[i].size +
- (e820.map[i].addr & ~PAGE_MASK) +
- ~PAGE_MASK) >> PAGE_SHIFT;
- for ( j = 0; j < nr_pfns; j++ )
- {
- if ( !pfn_valid(pfn+j) )
- continue;
_______________________________________________
Xen-changelog mailing list
Xen-changelog@lists.xensource.com
http://lists.xensource.com/xen-changelog