bitkeeper revision 1.994.1.3 (40d7ff06C_ErgacoeY2JZXnEr4soPQ)

Remove PAGE_IO/pte_io hack from Linux.

7 files changed, 25 insertions, 406 deletions

diff --git a/.rootkeys b/.rootkeys
index dffa81d6d4..f8f629df37 100644
--- a/.rootkeys
+++ b/.rootkeys
@@ -151,7 +151,6 @@
 3e5a4e681xMPdF9xCMwpyfuYMySU5g linux-2.4.26-xen-sparse/mm/mremap.c
 409ba2e7akOFqQUg6Qyg2s28xcXiMg linux-2.4.26-xen-sparse/mm/page_alloc.c
 3e5a4e683HKVU-sxtagrDasRB8eBVw linux-2.4.26-xen-sparse/mm/swapfile.c
-3f108af81Thhb242EmKjGCYkjx-GJA linux-2.4.26-xen-sparse/mm/vmalloc.c
 3f776bd1Hy9rn69ntXBhPReUFw9IEA tools/Makefile
 3e6377b24eQqYMsDi9XrFkIgTzZ47A tools/balloon/Makefile
 3e6377d6eiFjF1hHIS6JEIOFk62xSA tools/balloon/README
diff --git a/linux-2.4.26-xen-sparse/arch/xen/drivers/dom0/core.c b/linux-2.4.26-xen-sparse/arch/xen/drivers/dom0/core.c
index 5412a28572..99f84d99fd 100644
--- a/linux-2.4.26-xen-sparse/arch/xen/drivers/dom0/core.c
+++ b/linux-2.4.26-xen-sparse/arch/xen/drivers/dom0/core.c
@@ -157,10 +157,10 @@ static int privcmd_ioctl(struct inode *inode, struct file *file,
         addr = m.addr;
         for ( i = 0; i < m.num; i++, addr += PAGE_SIZE, p++ )
         {
-            if ( get_user(mfn, p) ) return -EFAULT;
+            if ( get_user(mfn, p) )
+                return -EFAULT;
 
-            v->val = (mfn << PAGE_SHIFT) | pgprot_val(vma->vm_page_prot) |
-                _PAGE_IO;
+            v->val = (mfn << PAGE_SHIFT) | pgprot_val(vma->vm_page_prot);
 
             __direct_remap_area_pages(vma->vm_mm,
                                       addr, 
diff --git a/linux-2.4.26-xen-sparse/arch/xen/mm/ioremap.c b/linux-2.4.26-xen-sparse/arch/xen/mm/ioremap.c
index a9b0faa41d..1eaee72f48 100644
--- a/linux-2.4.26-xen-sparse/arch/xen/mm/ioremap.c
+++ b/linux-2.4.26-xen-sparse/arch/xen/mm/ioremap.c
@@ -150,7 +150,7 @@ int direct_remap_area_pages(struct mm_struct *mm,
          * Fill in the machine address: PTE ptr is done later by
          * __direct_remap_area_pages(). 
          */
-        v->val = (machine_addr & PAGE_MASK) | pgprot_val(prot) | _PAGE_IO;
+        v->val = (machine_addr & PAGE_MASK) | pgprot_val(prot);
 
         machine_addr += PAGE_SIZE;
         address += PAGE_SIZE; 
@@ -262,8 +262,7 @@ void __init *bt_ioremap(unsigned long machine_addr, unsigned long size)
          */
         idx = FIX_BTMAP_BEGIN;
         while (nrpages > 0) {
-                __set_fixmap(idx, machine_addr, 
-                             __pgprot(__PAGE_KERNEL|_PAGE_IO));
+                __set_fixmap(idx, machine_addr, PAGE_KERNEL);
                 machine_addr += PAGE_SIZE;
                 --idx;
                 --nrpages;
diff --git a/linux-2.4.26-xen-sparse/include/asm-xen/pgtable-2level.h b/linux-2.4.26-xen-sparse/include/asm-xen/pgtable-2level.h
index 162ba1fbed..e6845abc86 100644
--- a/linux-2.4.26-xen-sparse/include/asm-xen/pgtable-2level.h
+++ b/linux-2.4.26-xen-sparse/include/asm-xen/pgtable-2level.h
@@ -48,7 +48,26 @@ static inline pmd_t * pmd_offset(pgd_t * dir, unsigned long address)
 }
 
 #define pte_same(a, b)		((a).pte_low == (b).pte_low)
-#define pte_page(x)		(mem_map+((unsigned long)((pte_val(x) >> PAGE_SHIFT))))
+
+/*                                 
+ * We detect special mappings in one of two ways:
+ *  1. If the MFN is an I/O page then Xen will set the m2p entry
+ *     to be outside our maximum possible pseudophys range.
+ *  2. If the MFN belongs to a different domain then we will certainly
+ *     not have MFN in our p2m table. Conversely, if the page is ours,
+ *     then we'll have p2m(m2p(MFN))==MFN.
+ * If we detect a special mapping then it doesn't have a 'struct page'.
+ * We force !VALID_PAGE() by returning an out-of-range pointer.
+ */
+#define pte_page(_pte)                                        \
+({                                                            \
+    unsigned long mfn = (_pte).pte_low >> PAGE_SHIFT;         \
+    unsigned long pfn = mfn_to_pfn(mfn);                      \
+    if ( (pfn >= max_mapnr) || (pfn_to_mfn(pfn) != mfn) )     \
+        pfn = max_mapnr; /* specia: force !VALID_PAGE() */    \
+    &mem_map[pfn];                                            \
+})
+
 #define pte_none(x)		(!(x).pte_low)
 #define __mk_pte(page_nr,pgprot) __pte(((page_nr) << PAGE_SHIFT) | pgprot_val(pgprot))
 
diff --git a/linux-2.4.26-xen-sparse/include/asm-xen/pgtable.h b/linux-2.4.26-xen-sparse/include/asm-xen/pgtable.h
index 38721e4cff..dc25864d2c 100644
--- a/linux-2.4.26-xen-sparse/include/asm-xen/pgtable.h
+++ b/linux-2.4.26-xen-sparse/include/asm-xen/pgtable.h
@@ -116,7 +116,6 @@ extern void * high_memory;
 #define _PAGE_BIT_DIRTY		6
 #define _PAGE_BIT_PSE		7	/* 4 MB (or 2MB) page, Pentium+, if present.. */
 #define _PAGE_BIT_GLOBAL	8	/* Global TLB entry PPro+ */
-#define _PAGE_BIT_IO            9
 
 #define _PAGE_PRESENT	0x001
 #define _PAGE_RW	0x002
@@ -127,7 +126,6 @@ extern void * high_memory;
 #define _PAGE_DIRTY	0x040
 #define _PAGE_PSE	0x080	/* 4 MB (or 2MB) page, Pentium+, if present.. */
 #define _PAGE_GLOBAL	0x100	/* Global TLB entry PPro+ */
-#define _PAGE_IO        0x200
 
 #define _PAGE_PROTNONE	0x080	/* If not present */
 
@@ -200,7 +198,6 @@ static inline int pte_exec(pte_t pte)		{ return (pte).pte_low & _PAGE_USER; }
 static inline int pte_dirty(pte_t pte)		{ return (pte).pte_low & _PAGE_DIRTY; }
 static inline int pte_young(pte_t pte)		{ return (pte).pte_low & _PAGE_ACCESSED; }
 static inline int pte_write(pte_t pte)		{ return (pte).pte_low & _PAGE_RW; }
-static inline int pte_io(pte_t pte)		{ return (pte).pte_low & _PAGE_IO; }
 
 static inline pte_t pte_rdprotect(pte_t pte)	{ (pte).pte_low &= ~_PAGE_USER; return pte; }
 static inline pte_t pte_exprotect(pte_t pte)	{ (pte).pte_low &= ~_PAGE_USER; return pte; }
@@ -212,7 +209,6 @@ static inline pte_t pte_mkexec(pte_t pte)	{ (pte).pte_low |= _PAGE_USER; return
 static inline pte_t pte_mkdirty(pte_t pte)	{ (pte).pte_low |= _PAGE_DIRTY; return pte; }
 static inline pte_t pte_mkyoung(pte_t pte)	{ (pte).pte_low |= _PAGE_ACCESSED; return pte; }
 static inline pte_t pte_mkwrite(pte_t pte)	{ (pte).pte_low |= _PAGE_RW; return pte; }
-static inline pte_t pte_mkio(pte_t pte)		{ (pte).pte_low |= _PAGE_IO; return pte; }
 
 static inline int ptep_test_and_clear_dirty(pte_t *ptep)
 {
diff --git a/linux-2.4.26-xen-sparse/mm/memory.c b/linux-2.4.26-xen-sparse/mm/memory.c
index 312dbfa7c0..6bdb08afe7 100644
--- a/linux-2.4.26-xen-sparse/mm/memory.c
+++ b/linux-2.4.26-xen-sparse/mm/memory.c
@@ -318,12 +318,6 @@ static inline int zap_pte_range(mmu_gather_t *tlb, pmd_t * pmd, unsigned long ad
 			continue;
 		if (pte_present(pte)) {
 			struct page *page = pte_page(pte);
-#if defined(CONFIG_XEN_PRIVILEGED_GUEST)
-			if (pte_io(pte)) {
-				queue_l1_entry_update(ptep, 0);
-				continue;
-			}
-#endif
 			if (VALID_PAGE(page) && !PageReserved(page))
 				freed ++;
 			/* This will eventually call __free_pte on the pte. */
diff --git a/linux-2.4.26-xen-sparse/mm/vmalloc.c b/linux-2.4.26-xen-sparse/mm/vmalloc.c
deleted file mode 100644
index b030270b42..0000000000
--- a/linux-2.4.26-xen-sparse/mm/vmalloc.c
+++ /dev/null
@@ -1,388 +0,0 @@
-/*
- *  linux/mm/vmalloc.c
- *
- *  Copyright (C) 1993  Linus Torvalds
- *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
- *  SMP-safe vmalloc/vfree/ioremap, Tigran Aivazian <tigran@veritas.com>, May 2000
- */
-
-#include <linux/config.h>
-#include <linux/slab.h>
-#include <linux/vmalloc.h>
-#include <linux/spinlock.h>
-#include <linux/highmem.h>
-#include <linux/smp_lock.h>
-
-#include <asm/uaccess.h>
-#include <asm/pgalloc.h>
-
-rwlock_t vmlist_lock = RW_LOCK_UNLOCKED;
-struct vm_struct * vmlist;
-
-static inline void free_area_pte(pmd_t * pmd, unsigned long address, unsigned long size)
-{
-	pte_t * pte;
-	unsigned long end;
-
-	if (pmd_none(*pmd))
-		return;
-	if (pmd_bad(*pmd)) {
-		pmd_ERROR(*pmd);
-		pmd_clear(pmd);
-		return;
-	}
-	pte = pte_offset(pmd, address);
-	address &= ~PMD_MASK;
-	end = address + size;
-	if (end > PMD_SIZE)
-		end = PMD_SIZE;
-	do {
-		pte_t page;
-		page = ptep_get_and_clear(pte);
-		address += PAGE_SIZE;
-		pte++;
-		if (pte_none(page))
-			continue;
-		if (pte_present(page)) {
-			struct page *ptpage = pte_page(page);
-#if defined(CONFIG_XEN_PRIVILEGED_GUEST)
-			if (pte_io(page))
-				continue;
-#endif
-			if (VALID_PAGE(ptpage) && (!PageReserved(ptpage)))
-				__free_page(ptpage);
-			continue;
-		}
-		printk(KERN_CRIT "Whee.. Swapped out page in kernel page table\n");
-	} while (address < end);
-}
-
-static inline void free_area_pmd(pgd_t * dir, unsigned long address, unsigned long size)
-{
-	pmd_t * pmd;
-	unsigned long end;
-
-	if (pgd_none(*dir))
-		return;
-	if (pgd_bad(*dir)) {
-		pgd_ERROR(*dir);
-		pgd_clear(dir);
-		return;
-	}
-	pmd = pmd_offset(dir, address);
-	address &= ~PGDIR_MASK;
-	end = address + size;
-	if (end > PGDIR_SIZE)
-		end = PGDIR_SIZE;
-	do {
-		free_area_pte(pmd, address, end - address);
-		address = (address + PMD_SIZE) & PMD_MASK;
-		pmd++;
-	} while (address < end);
-}
-
-void vmfree_area_pages(unsigned long address, unsigned long size)
-{
-	pgd_t * dir;
-	unsigned long end = address + size;
-
-	dir = pgd_offset_k(address);
-	flush_cache_all();
-	do {
-		free_area_pmd(dir, address, end - address);
-		address = (address + PGDIR_SIZE) & PGDIR_MASK;
-		dir++;
-	} while (address && (address < end));
-	flush_tlb_all();
-}
-
-static inline int alloc_area_pte (pte_t * pte, unsigned long address,
-			unsigned long size, int gfp_mask,
-			pgprot_t prot, struct page ***pages)
-{
-	unsigned long end;
-
-	address &= ~PMD_MASK;
-	end = address + size;
-	if (end > PMD_SIZE)
-		end = PMD_SIZE;
-	do {
-		struct page * page;
-
-		if (!pages) {
-			spin_unlock(&init_mm.page_table_lock);
-			page = alloc_page(gfp_mask);
-			spin_lock(&init_mm.page_table_lock);
-		} else {
-			page = (**pages);
-			(*pages)++;
-
-			/* Add a reference to the page so we can free later */
-			if (page)
-				atomic_inc(&page->count);
-
-		}
-		if (!pte_none(*pte))
-			printk(KERN_ERR "alloc_area_pte: page already exists\n");
-		if (!page)
-			return -ENOMEM;
-		set_pte(pte, mk_pte(page, prot));
-		address += PAGE_SIZE;
-		pte++;
-	} while (address < end);
-	return 0;
-}
-
-static inline int alloc_area_pmd(pmd_t * pmd, unsigned long address,
-			unsigned long size, int gfp_mask,
-			pgprot_t prot, struct page ***pages)
-{
-	unsigned long end;
-
-	address &= ~PGDIR_MASK;
-	end = address + size;
-	if (end > PGDIR_SIZE)
-		end = PGDIR_SIZE;
-	do {
-		pte_t * pte = pte_alloc(&init_mm, pmd, address);
-		if (!pte)
-			return -ENOMEM;
-		if (alloc_area_pte(pte, address, end - address,
-					gfp_mask, prot, pages))
-			return -ENOMEM;
-		address = (address + PMD_SIZE) & PMD_MASK;
-		pmd++;
-	} while (address < end);
-	return 0;
-}
-
-static inline int __vmalloc_area_pages (unsigned long address,
-					unsigned long size,
-					int gfp_mask,
-					pgprot_t prot,
-					struct page ***pages)
-{
-	pgd_t * dir;
-	unsigned long start = address;
-	unsigned long end = address + size;
-
-	dir = pgd_offset_k(address);
-	spin_lock(&init_mm.page_table_lock);
-	do {
-		pmd_t *pmd;
-		
-		pmd = pmd_alloc(&init_mm, dir, address);
-		if (!pmd)
-			goto err;
-
-		if (alloc_area_pmd(pmd, address, end - address, gfp_mask, prot, pages))
-			goto err;	// The kernel NEVER reclaims pmds, so no need to undo pmd_alloc() here
-
-		address = (address + PGDIR_SIZE) & PGDIR_MASK;
-		dir++;
-	} while (address && (address < end));
-	spin_unlock(&init_mm.page_table_lock);
-	flush_cache_all();
-	return 0;
-err:
-	spin_unlock(&init_mm.page_table_lock);
-	flush_cache_all();
-	if (address > start)
-		vmfree_area_pages(start, address - start);
-	return -ENOMEM;
-}
-
-int vmalloc_area_pages(unsigned long address, unsigned long size,
-		       int gfp_mask, pgprot_t prot)
-{
-	return __vmalloc_area_pages(address, size, gfp_mask, prot, NULL);
-}
-
-struct vm_struct * get_vm_area(unsigned long size, unsigned long flags)
-{
-	unsigned long addr, next;
-	struct vm_struct **p, *tmp, *area;
-
-	area = (struct vm_struct *) kmalloc(sizeof(*area), GFP_KERNEL);
-	if (!area)
-		return NULL;
-
-	size += PAGE_SIZE;
-	if (!size) {
-		kfree (area);
-		return NULL;
-	}
-
-	addr = VMALLOC_START;
-	write_lock(&vmlist_lock);
-	for (p = &vmlist; (tmp = *p) ; p = &tmp->next) {
-		if ((size + addr) < addr)
-			goto out;
-		if (size + addr <= (unsigned long) tmp->addr)
-			break;
-		next = tmp->size + (unsigned long) tmp->addr;
-		if (next > addr) 
-			addr = next;
-		if (addr > VMALLOC_END-size)
-			goto out;
-	}
-	area->flags = flags;
-	area->addr = (void *)addr;
-	area->size = size;
-	area->next = *p;
-	*p = area;
-	write_unlock(&vmlist_lock);
-	return area;
-
-out:
-	write_unlock(&vmlist_lock);
-	kfree(area);
-	return NULL;
-}
-
-void __vfree(void * addr, int free_area_pages)
-{
-	struct vm_struct **p, *tmp;
-
-	if (!addr)
-		return;
-	if ((PAGE_SIZE-1) & (unsigned long) addr) {
-		printk(KERN_ERR "Trying to vfree() bad address (%p)\n", addr);
-		return;
-	}
-	write_lock(&vmlist_lock);
-	for (p = &vmlist ; (tmp = *p) ; p = &tmp->next) {
-		if (tmp->addr == addr) {
-			*p = tmp->next;
-			if (free_area_pages)
-			    vmfree_area_pages(VMALLOC_VMADDR(tmp->addr), tmp->size);
-			write_unlock(&vmlist_lock);
-			kfree(tmp);
-			return;
-		}
-	}
-	write_unlock(&vmlist_lock);
-	printk(KERN_ERR "Trying to vfree() nonexistent vm area (%p)\n", addr);
-}
-
-void vfree(void * addr)
-{
-	__vfree(addr,1);
-}
-
-void * __vmalloc (unsigned long size, int gfp_mask, pgprot_t prot)
-{
-	void * addr;
-	struct vm_struct *area;
-
-	size = PAGE_ALIGN(size);
-	if (!size || (size >> PAGE_SHIFT) > num_physpages)
-		return NULL;
-	area = get_vm_area(size, VM_ALLOC);
-	if (!area)
-		return NULL;
-	addr = area->addr;
-	if (__vmalloc_area_pages(VMALLOC_VMADDR(addr), size, gfp_mask,
-				 prot, NULL)) {
-		__vfree(addr, 0);
-		return NULL;
-	}
-	return addr;
-}
-
-void * vmap(struct page **pages, int count,
-	    unsigned long flags, pgprot_t prot)
-{
-	void * addr;
-	struct vm_struct *area;
-	unsigned long size = count << PAGE_SHIFT;
-
-	if (!size || size > (max_mapnr << PAGE_SHIFT))
-		return NULL;
-	area = get_vm_area(size, flags);
-	if (!area) {
-		return NULL;
-	}
-	addr = area->addr;
-	if (__vmalloc_area_pages(VMALLOC_VMADDR(addr), size, 0,
-				 prot, &pages)) {
-		__vfree(addr, 0);
-		return NULL;
-	}
-	return addr;
-}
-
-long vread(char *buf, char *addr, unsigned long count)
-{
-	struct vm_struct *tmp;
-	char *vaddr, *buf_start = buf;
-	unsigned long n;
-
-	/* Don't allow overflow */
-	if ((unsigned long) addr + count < count)
-		count = -(unsigned long) addr;
-
-	read_lock(&vmlist_lock);
-	for (tmp = vmlist; tmp; tmp = tmp->next) {
-		vaddr = (char *) tmp->addr;
-		if (addr >= vaddr + tmp->size - PAGE_SIZE)
-			continue;
-		while (addr < vaddr) {
-			if (count == 0)
-				goto finished;
-			*buf = '\0';
-			buf++;
-			addr++;
-			count--;
-		}
-		n = vaddr + tmp->size - PAGE_SIZE - addr;
-		do {
-			if (count == 0)
-				goto finished;
-			*buf = *addr;
-			buf++;
-			addr++;
-			count--;
-		} while (--n > 0);
-	}
-finished:
-	read_unlock(&vmlist_lock);
-	return buf - buf_start;
-}
-
-long vwrite(char *buf, char *addr, unsigned long count)
-{
-	struct vm_struct *tmp;
-	char *vaddr, *buf_start = buf;
-	unsigned long n;
-
-	/* Don't allow overflow */
-	if ((unsigned long) addr + count < count)
-		count = -(unsigned long) addr;
-
-	read_lock(&vmlist_lock);
-	for (tmp = vmlist; tmp; tmp = tmp->next) {
-		vaddr = (char *) tmp->addr;
-		if (addr >= vaddr + tmp->size - PAGE_SIZE)
-			continue;
-		while (addr < vaddr) {
-			if (count == 0)
-				goto finished;
-			buf++;
-			addr++;
-			count--;
-		}
-		n = vaddr + tmp->size - PAGE_SIZE - addr;
-		do {
-			if (count == 0)
-				goto finished;
-			*addr = *buf;
-			buf++;
-			addr++;
-			count--;
-		} while (--n > 0);
-	}
-finished:
-	read_unlock(&vmlist_lock);
-	return buf - buf_start;
-}