Merge with Linux 2.4.0-test10.

3 files changed, 82 insertions, 50 deletions

diff --git a/arch/i386/mm/fault.c b/arch/i386/mm/fault.c
index b88c4a422..946d1f40a 100644
--- a/arch/i386/mm/fault.c
+++ b/arch/i386/mm/fault.c
@@ -77,31 +77,6 @@ bad_area:
 	return 0;
 }
 
-static void __init handle_wp_test (void)
-{
-	const unsigned long vaddr = PAGE_OFFSET;
-	pgd_t *pgd;
-	pmd_t *pmd;
-	pte_t *pte;
-
-	/*
-	 * make it read/writable temporarily, so that the fault
-	 * can be handled.
-	 */
-	pgd = swapper_pg_dir + __pgd_offset(vaddr);
-	pmd = pmd_offset(pgd, vaddr);
-	pte = pte_offset(pmd, vaddr);
-	*pte = mk_pte_phys(0, PAGE_KERNEL);
-	__flush_tlb_all();
-
-	boot_cpu_data.wp_works_ok = 1;
-	/*
-	 * Beware: Black magic here. The printk is needed here to flush
-	 * CPU state on certain buggy processors.
-	 */
-	printk("Ok");
-}
-
 asmlinkage void do_invalid_op(struct pt_regs *, unsigned long);
 extern unsigned long idt;
 
@@ -130,6 +105,19 @@ asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	__asm__("movl %%cr2,%0":"=r" (address));
 
 	tsk = current;
+
+	/*
+	 * We fault-in kernel-space virtual memory on-demand. The
+	 * 'reference' page table is init_mm.pgd.
+	 *
+	 * NOTE! We MUST NOT take any locks for this case. We may
+	 * be in an interrupt or a critical region, and should
+	 * only copy the information from the master page table,
+	 * nothing more.
+	 */
+	if (address >= TASK_SIZE)
+		goto vmalloc_fault;
+
 	mm = tsk->mm;
 	info.si_code = SEGV_MAPERR;
 
@@ -223,6 +211,7 @@ good_area:
 bad_area:
 	up(&mm->mmap_sem);
 
+bad_area_nosemaphore:
 	/* User mode accesses just cause a SIGSEGV */
 	if (error_code & 4) {
 		tsk->thread.cr2 = address;
@@ -260,14 +249,7 @@ no_context:
 /*
  * Oops. The kernel tried to access some bad page. We'll have to
  * terminate things with extreme prejudice.
- *
- * First we check if it was the bootup rw-test, though..
  */
-	if (boot_cpu_data.wp_works_ok < 0 &&
-			address == PAGE_OFFSET && (error_code & 1)) {
-		handle_wp_test();
-		return;
-	}
 
 	if (address < PAGE_SIZE)
 		printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference");
@@ -318,4 +300,34 @@ do_sigbus:
 	/* Kernel mode? Handle exceptions or die */
 	if (!(error_code & 4))
 		goto no_context;
+	return;
+
+vmalloc_fault:
+	{
+		/*
+		 * Synchronize this task's top level page-table
+		 * with the 'reference' page table.
+		 */
+		int offset = __pgd_offset(address);
+		pgd_t *pgd, *pgd_k;
+		pmd_t *pmd, *pmd_k;
+
+		pgd = tsk->active_mm->pgd + offset;
+		pgd_k = init_mm.pgd + offset;
+
+		if (!pgd_present(*pgd)) {
+			if (!pgd_present(*pgd_k))
+				goto bad_area_nosemaphore;
+			set_pgd(pgd, *pgd_k);
+			return;
+		}
+
+		pmd = pmd_offset(pgd, address);
+		pmd_k = pmd_offset(pgd_k, address);
+
+		if (pmd_present(*pmd) || !pmd_present(*pmd_k))
+			goto bad_area_nosemaphore;
+		set_pmd(pmd, *pmd_k);
+		return;
+	}
 }
diff --git a/arch/i386/mm/init.c b/arch/i386/mm/init.c
index 9ba2baa31..39a6ce0f8 100644
--- a/arch/i386/mm/init.c
+++ b/arch/i386/mm/init.c
@@ -37,8 +37,8 @@
 #include <asm/apic.h>
 
 unsigned long highstart_pfn, highend_pfn;
-static unsigned long totalram_pages = 0;
-static unsigned long totalhigh_pages = 0;
+static unsigned long totalram_pages;
+static unsigned long totalhigh_pages;
 
 /*
  * BAD_PAGE is the page that is used for page faults when linux
@@ -491,16 +491,21 @@ void __init paging_init(void)
  * before and after the test are here to work-around some nasty CPU bugs.
  */
 
+/*
+ * This function cannot be __init, since exceptions don't work in that
+ * section.
+ */
+static int do_test_wp_bit(unsigned long vaddr);
+
 void __init test_wp_bit(void)
 {
 /*
- * Ok, all PAE-capable CPUs are definitely handling the WP bit right.
+ * Ok, all PSE-capable CPUs are definitely handling the WP bit right.
  */
 	const unsigned long vaddr = PAGE_OFFSET;
 	pgd_t *pgd;
 	pmd_t *pmd;
 	pte_t *pte, old_pte;
-	char tmp_reg;
 
 	printk("Checking if this processor honours the WP bit even in supervisor mode... ");
 
@@ -511,27 +516,19 @@ void __init test_wp_bit(void)
 	*pte = mk_pte_phys(0, PAGE_READONLY);
 	local_flush_tlb();
 
-	__asm__ __volatile__(
-		"jmp 1f; 1:\n"
-		"movb %0,%1\n"
-		"movb %1,%0\n"
-		"jmp 1f; 1:\n"
-		:"=m" (*(char *) vaddr),
-		 "=q" (tmp_reg)
-		:/* no inputs */
-		:"memory");
+	boot_cpu_data.wp_works_ok = do_test_wp_bit(vaddr);
 
 	*pte = old_pte;
 	local_flush_tlb();
 
-	if (boot_cpu_data.wp_works_ok < 0) {
-		boot_cpu_data.wp_works_ok = 0;
+	if (!boot_cpu_data.wp_works_ok) {
 		printk("No.\n");
 #ifdef CONFIG_X86_WP_WORKS_OK
 		panic("This kernel doesn't support CPU's with broken WP. Recompile it for a 386!");
 #endif
-	} else
-		printk(".\n");
+	} else {
+		printk("Ok.\n");
+	}
 }
 
 static inline int page_is_ram (unsigned long pagenr)
@@ -634,6 +631,30 @@ void __init mem_init(void)
 
 }
 
+/* Put this after the callers, so that it cannot be inlined */
+static int do_test_wp_bit(unsigned long vaddr)
+{
+	char tmp_reg;
+	int flag;
+
+	__asm__ __volatile__(
+		"	movb %0,%1	\n"
+		"1:	movb %1,%0	\n"
+		"	xorl %2,%2	\n"
+		"2:			\n"
+		".section __ex_table,\"a\"\n"
+		"	.align 4	\n"
+		"	.long 1b,2b	\n"
+		".previous		\n"
+		:"=m" (*(char *) vaddr),
+		 "=q" (tmp_reg),
+		 "=r" (flag)
+		:"2" (1)
+		:"memory");
+	
+	return flag;
+}
+
 void free_initmem(void)
 {
 	unsigned long addr;
diff --git a/arch/i386/mm/ioremap.c b/arch/i386/mm/ioremap.c
index 66f846925..bb72da8c8 100644
--- a/arch/i386/mm/ioremap.c
+++ b/arch/i386/mm/ioremap.c
@@ -78,7 +78,6 @@ static int remap_area_pages(unsigned long address, unsigned long phys_addr,
 		if (remap_area_pmd(pmd, address, end - address,
 					 phys_addr + address, flags))
 			return -ENOMEM;
-		set_pgdir(address, *dir);
 		address = (address + PGDIR_SIZE) & PGDIR_MASK;
 		dir++;
 	} while (address && (address < end));