Merge http://gkernel.bkbits.net/misc-2.5

into penguin.transmeta.com:/home/penguin/torvalds/repositories/kernel/linux

Documentation/devices.txt

@@ -2667,7 +2667,7 @@ under /dev.  These special filesystems provide kernel interfaces that
 cannot be provided with standard device nodes.
 
 /dev/pts	devpts		PTY slave filesystem
-/dev/shm	shmfs		POSIX shared memory maintenance access
+/dev/shm	tmpfs		POSIX shared memory maintenance access
 
  ****	TERMINAL DEVICES
 

Documentation/filesystems/tmpfs.txt

@@ -47,10 +47,9 @@ tmpfs has the following uses:
    shared memory)
 
 3) Some people (including me) find it very convenient to mount it
-   e.g. on /tmp and /var/tmp and have a big swap partition. But be
-   aware: loop mounts of tmpfs files do not work due to the internal
-   design. So mkinitrd shipped by most distributions will fail with a
-   tmpfs /tmp.
+   e.g. on /tmp and /var/tmp and have a big swap partition. And now
+   loop mounts of tmpfs files do work, so mkinitrd shipped by most
+   distributions should succeed with a tmpfs /tmp.
 
 4) And probably a lot more I do not know about :-)
 
@@ -90,13 +89,9 @@ TODOs:
    size=50% the tmpfs instance should be able to grow to 50 percent of
    RAM + swap. So the instance should adapt automatically if you add
    or remove swap space.
-2) loop mounts: This is difficult since loop.c relies on the readpage
-   operation. This operation gets a page from the caller to be filled
-   with the content of the file at that position. But tmpfs always has
-   the page and thus cannot copy the content to the given page. So it
-   cannot provide this operation. The VM had to be changed seriously
-   to achieve this.
-3) Show the number of tmpfs RAM pages. (As shared?)
+2) Show the number of tmpfs RAM pages. (As shared?)
 
 Author:
    Christoph Rohland <cr@sap.com>, 1.12.01
+Updated:
+   Hugh Dickins <hugh@veritas.com>, 17 Oct 2002

arch/i386/kernel/i386_ksyms.c

@@ -72,7 +72,9 @@ EXPORT_SYMBOL(pfn_to_nid);
 #ifdef CONFIG_X86_NUMAQ
 EXPORT_SYMBOL(xquad_portio);
 #endif
+#ifndef CONFIG_X86_WP_WORKS_OK
 EXPORT_SYMBOL(__verify_write);
+#endif
 EXPORT_SYMBOL(dump_thread);
 EXPORT_SYMBOL(dump_fpu);
 EXPORT_SYMBOL(dump_extended_fpu);

arch/i386/kernel/ptrace.c

@@ -375,12 +375,8 @@ asmlinkage int sys_ptrace(long request, long pid, long addr, long data)
 			break;
 		}
 		ret = 0;
-		if ( !child->used_math ) {
-			/* Simulate an empty FPU. */
-			set_fpu_cwd(child, 0x037f);
-			set_fpu_swd(child, 0x0000);
-			set_fpu_twd(child, 0xffff);
-		}
+		if (!child->used_math)
+			init_fpu(child);
 		get_fpregs((struct user_i387_struct *)data, child);
 		break;
 	}
@@ -403,13 +399,8 @@ asmlinkage int sys_ptrace(long request, long pid, long addr, long data)
 			ret = -EIO;
 			break;
 		}
-		if ( !child->used_math ) {
-			/* Simulate an empty FPU. */
-			set_fpu_cwd(child, 0x037f);
-			set_fpu_swd(child, 0x0000);
-			set_fpu_twd(child, 0xffff);
-			set_fpu_mxcsr(child, 0x1f80);
-		}
+		if (!child->used_math)
+			init_fpu(child);
 		ret = get_fpxregs((struct user_fxsr_struct *)data, child);
 		break;
 	}

arch/i386/kernel/suspend.c

@@ -54,10 +54,10 @@ static inline void save_processor_context (void)
 	/*
 	 * descriptor tables
 	 */
-	asm volatile ("sgdt (%0)" : "=m" (saved_context.gdt_limit));
-	asm volatile ("sidt (%0)" : "=m" (saved_context.idt_limit));
-	asm volatile ("sldt (%0)" : "=m" (saved_context.ldt));
-	asm volatile ("str (%0)"  : "=m" (saved_context.tr));
+	asm volatile ("sgdt %0" : "=m" (saved_context.gdt_limit));
+	asm volatile ("sidt %0" : "=m" (saved_context.idt_limit));
+	asm volatile ("sldt %0" : "=m" (saved_context.ldt));
+	asm volatile ("str %0"  : "=m" (saved_context.tr));
 
 	/*
 	 * save the general registers.
@@ -67,22 +67,22 @@ static inline void save_processor_context (void)
 	 * It's really not necessary, and kinda fishy (check the assembly output),
 	 * so it's avoided. 
 	 */
-	asm volatile ("movl %%esp, (%0)" : "=m" (saved_context.esp));
-	asm volatile ("movl %%eax, (%0)" : "=m" (saved_context.eax));
-	asm volatile ("movl %%ebx, (%0)" : "=m" (saved_context.ebx));
-	asm volatile ("movl %%ecx, (%0)" : "=m" (saved_context.ecx));
-	asm volatile ("movl %%edx, (%0)" : "=m" (saved_context.edx));
-	asm volatile ("movl %%ebp, (%0)" : "=m" (saved_context.ebp));
-	asm volatile ("movl %%esi, (%0)" : "=m" (saved_context.esi));
-	asm volatile ("movl %%edi, (%0)" : "=m" (saved_context.edi));
-
+	asm volatile ("movl %%esp, %0" : "=m" (saved_context.esp));
+	asm volatile ("movl %%eax, %0" : "=m" (saved_context.eax));
+	asm volatile ("movl %%ebx, %0" : "=m" (saved_context.ebx));
+	asm volatile ("movl %%ecx, %0" : "=m" (saved_context.ecx));
+	asm volatile ("movl %%edx, %0" : "=m" (saved_context.edx));
+	asm volatile ("movl %%ebp, %0" : "=m" (saved_context.ebp));
+	asm volatile ("movl %%esi, %0" : "=m" (saved_context.esi));
+	asm volatile ("movl %%edi, %0" : "=m" (saved_context.edi));
+	/* FIXME: Need to save XMM0..XMM15? */
 	/*
 	 * segment registers
 	 */
-	asm volatile ("movw %%es, %0" : "=r" (saved_context.es));
-	asm volatile ("movw %%fs, %0" : "=r" (saved_context.fs));
-	asm volatile ("movw %%gs, %0" : "=r" (saved_context.gs));
-	asm volatile ("movw %%ss, %0" : "=r" (saved_context.ss));
+	asm volatile ("movw %%es, %0" : "=m" (saved_context.es));
+	asm volatile ("movw %%fs, %0" : "=m" (saved_context.fs));
+	asm volatile ("movw %%gs, %0" : "=m" (saved_context.gs));
+	asm volatile ("movw %%ss, %0" : "=m" (saved_context.ss));
 
 	/*
 	 * control registers 
@@ -95,7 +95,7 @@ static inline void save_processor_context (void)
 	/*
 	 * eflags
 	 */
-	asm volatile ("pushfl ; popl (%0)" : "=m" (saved_context.eflags));
+	asm volatile ("pushfl ; popl %0" : "=m" (saved_context.eflags));
 }
 
 static void
@@ -125,9 +125,7 @@ static inline void restore_processor_context (void)
 	/*
 	 * first restore %ds, so we can access our data properly
 	 */
-	asm volatile (".align 4");
-	asm volatile ("movw %0, %%ds" :: "r" ((u16)__KERNEL_DS));
-
+	asm volatile ("movw %0, %%ds" :: "r" (__KERNEL_DS));
 
 	/*
 	 * control registers
@@ -167,9 +165,9 @@ static inline void restore_processor_context (void)
 	 * now restore the descriptor tables to their proper values
 	 * ltr is done i fix_processor_context().
 	 */
-	asm volatile ("lgdt (%0)" :: "m" (saved_context.gdt_limit));
-	asm volatile ("lidt (%0)" :: "m" (saved_context.idt_limit));
-	asm volatile ("lldt (%0)" :: "m" (saved_context.ldt));
+	asm volatile ("lgdt %0" :: "m" (saved_context.gdt_limit));
+	asm volatile ("lidt %0" :: "m" (saved_context.idt_limit));
+	asm volatile ("lldt %0" :: "m" (saved_context.ldt));
 
 	fix_processor_context();
 

arch/i386/mm/fault.c

@@ -30,17 +30,20 @@ extern void die(const char *,struct pt_regs *,long);
 
 extern int console_loglevel;
 
+#ifndef CONFIG_X86_WP_WORKS_OK
 /*
  * Ugly, ugly, but the goto's result in better assembly..
  */
 int __verify_write(const void * addr, unsigned long size)
 {
+	struct mm_struct *mm = current->mm;
 	struct vm_area_struct * vma;
 	unsigned long start = (unsigned long) addr;
 
-	if (!size)
+	if (!size || segment_eq(get_fs(),KERNEL_DS))
 		return 1;
 
+	down_read(&mm->mmap_sem);
 	vma = find_vma(current->mm, start);
 	if (!vma)
 		goto bad_area;
@@ -80,6 +83,13 @@ int __verify_write(const void * addr, unsigned long size)
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;;
 	}
+	/*
+	 * We really need to hold mmap_sem over the whole access to
+	 * userspace, else another thread could change permissions.
+	 * This is unfixable, so don't use i386-class machines for
+	 * critical servers.
+	 */
+	up_read(&mm->mmap_sem);
 	return 1;
 
 check_stack:
@@ -89,6 +99,7 @@ int __verify_write(const void * addr, unsigned long size)
 		goto good_area;
 
 bad_area:
+	up_read(&mm->mmap_sem);
 	return 0;
 
 out_of_memory:
@@ -98,6 +109,7 @@ int __verify_write(const void * addr, unsigned long size)
 	}
 	goto bad_area;
 }
+#endif
 
 /*
  * Unlock any spinlocks which will prevent us from getting the

arch/i386/mm/init.c

@@ -378,15 +378,10 @@ void __init paging_init(void)
  * This function cannot be __init, since exceptions don't work in that
  * section.
  */
-static int do_test_wp_bit(unsigned long vaddr);
+static int do_test_wp_bit(void);
 
 void __init test_wp_bit(void)
 {
-	const unsigned long vaddr = PAGE_OFFSET;
-	pgd_t *pgd;
-	pmd_t *pmd;
-	pte_t *pte, old_pte;
-
 	if (cpu_has_pse) {
 		/* Ok, all PSE-capable CPUs are definitely handling the WP bit right. */
 		boot_cpu_data.wp_works_ok = 1;
@@ -395,17 +390,10 @@ void __init test_wp_bit(void)
 
 	printk("Checking if this processor honours the WP bit even in supervisor mode... ");
 
-	pgd = swapper_pg_dir + __pgd_offset(vaddr);
-	pmd = pmd_offset(pgd, vaddr);
-	pte = pte_offset_kernel(pmd, vaddr);
-	old_pte = *pte;
-	*pte = pfn_pte(0, PAGE_READONLY);
-	local_flush_tlb();
-
-	boot_cpu_data.wp_works_ok = do_test_wp_bit(vaddr);
-
-	*pte = old_pte;
-	local_flush_tlb();
+	/* Any page-aligned address will do, the test is non-destructive */
+	__set_fixmap(FIX_WP_TEST, __pa(&swapper_pg_dir), PAGE_READONLY);
+	boot_cpu_data.wp_works_ok = do_test_wp_bit();
+	clear_fixmap(FIX_WP_TEST);
 
 	if (!boot_cpu_data.wp_works_ok) {
 		printk("No.\n");
@@ -550,7 +538,7 @@ void __init pgtable_cache_init(void)
 #endif
 
 /* Put this after the callers, so that it cannot be inlined */
-static int do_test_wp_bit(unsigned long vaddr)
+static int do_test_wp_bit(void)
 {
 	char tmp_reg;
 	int flag;
@@ -564,7 +552,7 @@ static int do_test_wp_bit(unsigned long vaddr)
 		"	.align 4	\n"
 		"	.long 1b,2b	\n"
 		".previous		\n"
-		:"=m" (*(char *) vaddr),
+		:"=m" (*(char *)fix_to_virt(FIX_WP_TEST)),
 		 "=q" (tmp_reg),
 		 "=r" (flag)
 		:"2" (1)

arch/i386/mm/ioremap.c

@@ -289,7 +289,7 @@ void __init bt_iounmap(void *addr, unsigned long size)
 
 	idx = FIX_BTMAP_BEGIN;
 	while (nrpages > 0) {
-		__set_fixmap(idx, 0, __pgprot(0));
+		clear_fixmap(idx);
 		--idx;
 		--nrpages;
 	}

arch/sh/mm/fault.c

@@ -29,58 +29,6 @@
 
 extern void die(const char *,struct pt_regs *,long);
 
-/*
- * Ugly, ugly, but the goto's result in better assembly..
- */
-int __verify_write(const void * addr, unsigned long size)
-{
-	struct vm_area_struct * vma;
-	unsigned long start = (unsigned long) addr;
-
-	if (!size)
-		return 1;
-
-	vma = find_vma(current->mm, start);
-	if (!vma)
-		goto bad_area;
-	if (vma->vm_start > start)
-		goto check_stack;
-
-good_area:
-	if (!(vma->vm_flags & VM_WRITE))
-		goto bad_area;
-	size--;
-	size += start & ~PAGE_MASK;
-	size >>= PAGE_SHIFT;
-	start &= PAGE_MASK;
-
-	for (;;) {
-		if (handle_mm_fault(current->mm, vma, start, 1) <= 0)
-			goto bad_area;
-		if (!size)
-			break;
-		size--;
-		start += PAGE_SIZE;
-		if (start < vma->vm_end)
-			continue;
-		vma = vma->vm_next;
-		if (!vma || vma->vm_start != start)
-			goto bad_area;
-		if (!(vma->vm_flags & VM_WRITE))
-			goto bad_area;;
-	}
-	return 1;
-
-check_stack:
-	if (!(vma->vm_flags & VM_GROWSDOWN))
-		goto bad_area;
-	if (expand_stack(vma, start) == 0)
-		goto good_area;
-
-bad_area:
-	return 0;
-}
-
 /*
  * This routine handles page faults.  It determines the address,
  * and the problem, and then passes it off to one of the appropriate

drivers/block/rd.c

@@ -432,7 +432,7 @@ static int __init rd_init (void)
 		disk->first_minor = i;
 		disk->fops = &rd_bd_op;
 		disk->queue = &rd_queue;
-		sprintf(disk->disk_name, "rd%d", i);
+		sprintf(disk->disk_name, "ram%d", i);
 		set_capacity(disk, rd_size * 2);
 	}
 	devfs_handle = devfs_mk_dir (NULL, "rd", NULL);

drivers/cdrom/cm206.c

@@ -1497,7 +1497,7 @@ int __init cm206_init(void)
 		goto out_disk;
 	disk->major = MAJOR_NR;
 	disk->first_minor = 0;
-	sprintf(disk->disk_name, "cm206");
+	sprintf(disk->disk_name, "cm206cd");
 	disk->fops = &cm206_bdops;
 	disk->flags = GENHD_FL_CD;
 	cm206_gendisk = disk;

drivers/md/md.c

@@ -3287,13 +3287,13 @@ static int __init md_setup(char *str)
 	return 1;
 }
 
-extern kdev_t name_to_kdev_t(char *line) __init;
+extern dev_t name_to_dev_t(char *line) __init;
 void __init md_setup_drive(void)
 {
 	int minor, i;
-	kdev_t dev;
+	dev_t dev;
 	mddev_t*mddev;
-	kdev_t devices[MD_SB_DISKS+1];
+	dev_t devices[MD_SB_DISKS+1];
 
 	for (minor = 0; minor < MAX_MD_DEVS; minor++) {
 		int err = 0;
@@ -3312,16 +3312,17 @@ void __init md_setup_drive(void)
 			if (p)
 				*p++ = 0;
 
-			dev = name_to_kdev_t(devname);
-			handle = devfs_get_handle(NULL, devname, major(dev), minor(dev),
+			dev = name_to_dev_t(devname);
+			handle = devfs_get_handle(NULL, devname,
+						MAJOR(dev), MINOR(dev),
 						DEVFS_SPECIAL_BLK, 1);
 			if (handle != 0) {
 				unsigned major, minor;
 				devfs_get_maj_min(handle, &major, &minor);
-				dev = mk_kdev(major, minor);
+				dev = MKDEV(major, minor);
 				devfs_put(handle);
 			}
-			if (kdev_none(dev)) {
+			if (!dev) {
 				printk(KERN_WARNING "md: Unknown device name: %s\n", devname);
 				break;
 			}
@@ -3331,7 +3332,7 @@ void __init md_setup_drive(void)
 
 			devname = p;
 		}
-		devices[i] = to_kdev_t(0);
+		devices[i] = 0;
 
 		if (!md_setup_args.device_set[minor])
 			continue;
@@ -3375,13 +3376,13 @@ void __init md_setup_drive(void)
 			err = set_array_info(mddev, &ainfo);
 			for (i = 0; !err && i <= MD_SB_DISKS; i++) {
 				dev = devices[i];
-				if (kdev_none(dev))
+				if (!dev)
 					break;
 				dinfo.number = i;
 				dinfo.raid_disk = i;
 				dinfo.state = (1<<MD_DISK_ACTIVE)|(1<<MD_DISK_SYNC);
-				dinfo.major = major(dev);
-				dinfo.minor = minor(dev);
+				dinfo.major = MAJOR(dev);
+				dinfo.minor = MINOR(dev);
 				mddev->raid_disks++;
 				err = add_new_disk (mddev, &dinfo);
 			}
@@ -3389,10 +3390,10 @@ void __init md_setup_drive(void)
 			/* persistent */
 			for (i = 0; i <= MD_SB_DISKS; i++) {
 				dev = devices[i];
-				if (kdev_none(dev))
+				if (!dev)
 					break;
-				dinfo.major = major(dev);
-				dinfo.minor = minor(dev);
+				dinfo.major = MAJOR(dev);
+				dinfo.minor = MINOR(dev);
 				add_new_disk (mddev, &dinfo);
 			}
 		}

drivers/mtd/devices/blkmtd.c

@@ -1044,7 +1044,7 @@ static int __init calc_erase_regions(struct mtd_erase_region_info *info, size_t
 }
 
 
-extern kdev_t name_to_kdev_t(char *line) __init;
+extern dev_t name_to_dev_t(char *line) __init;
 
 /* Startup */
 static int __init init_blkmtd(void)
@@ -1059,7 +1059,7 @@ static int __init init_blkmtd(void)
   loff_t size;
   int readonly = 0;
   int erase_size = CONFIG_MTD_BLKDEV_ERASESIZE;
-  kdev_t rdev;
+  dev_t rdev;
   struct block_device *bdev;
   int err;
   int mode;
@@ -1107,17 +1107,17 @@ static int __init init_blkmtd(void)
     filp_close(file, NULL);
     return 1;
   }
-  rdev = inode->i_rdev;
+  rdev = inode->i_bdev->bd_dev;
   filp_close(file, NULL);
 #else
-  rdev = name_to_kdev_t(device);
+  rdev = name_to_dev_t(device);
 #endif
 
-  maj = major(rdev);
-  min = minor(rdev);
+  maj = MAJOR(rdev);
+  min = MINOR(rdev);
   DEBUG(1, "blkmtd: found a block device major = %d, minor = %d\n", maj, min);
 
-  if(kdev_none(rdev)) {
+  if(!rdev) {
     printk("blkmtd: bad block device: `%s'\n", device);
     return 1;
   }

fs/xfs/xfs_mount.c

@@ -1792,9 +1792,6 @@ xfs_alloc_buftarg(
 	case EVMS_MAJOR:
 		btp->pbr_flags = PBR_ALIGNED_ONLY;
 		break;
-	case LVM_BLK_MAJOR:
-		btp->pbr_flags = PBR_SECTOR_ONLY;
-		break;
 	}
 
 	return btp;

include/asm-i386/fixmap.h

@@ -41,13 +41,6 @@
  * TLB entries of such buffers will not be flushed across
  * task switches.
  */
-
-/*
- * on UP currently we will have no trace of the fixmap mechanizm,
- * no page table allocations, etc. This might change in the
- * future, say framebuffers for the console driver(s) could be
- * fix-mapped?
- */
 enum fixed_addresses {
 #ifdef CONFIG_X86_LOCAL_APIC
 	FIX_APIC_BASE,	/* local (CPU) APIC) -- required for SMP or not */
@@ -81,6 +74,7 @@ enum fixed_addresses {
 #define NR_FIX_BTMAPS	16
 	FIX_BTMAP_END = __end_of_permanent_fixed_addresses,
 	FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS - 1,
+	FIX_WP_TEST,
 	__end_of_fixed_addresses
 };
 
@@ -94,6 +88,10 @@ extern void __set_fixmap (enum fixed_addresses idx,
  */
 #define set_fixmap_nocache(idx, phys) \
 		__set_fixmap(idx, phys, PAGE_KERNEL_NOCACHE)
+
+#define clear_fixmap(idx) \
+		__set_fixmap(idx, 0, __pgprot(0))
+
 /*
  * used by vmalloc.c.
  *

include/asm-i386/suspend.h

@@ -15,22 +15,22 @@ arch_prepare_suspend(void)
 
 /* image of the saved processor state */
 struct saved_context {
-	u32 eax, ebx, ecx, edx;
-	u32 esp, ebp, esi, edi;
+	unsigned long eax, ebx, ecx, edx;
+	unsigned long esp, ebp, esi, edi;
   	u16 es, fs, gs, ss;
-	u32 cr0, cr2, cr3, cr4;
+	unsigned long cr0, cr2, cr3, cr4;
 	u16 gdt_pad;
 	u16 gdt_limit;
-	u32 gdt_base;
+	unsigned long gdt_base;
 	u16 idt_pad;
 	u16 idt_limit;
-	u32 idt_base;
+	unsigned long idt_base;
 	u16 ldt;
 	u16 tss;
-	u32 tr;
-	u32 safety;
-	u32 return_address;
-	u32 eflags;
+	unsigned long tr;
+	unsigned long safety;
+	unsigned long return_address;
+	unsigned long eflags;
 } __attribute__((packed));
 
 #define loaddebug(thread,register) \
@@ -52,11 +52,11 @@ extern unsigned long saved_edi;
 static inline void acpi_save_register_state(unsigned long return_point)
 {
 	saved_eip = return_point;
-	asm volatile ("movl %%esp,(%0)" : "=m" (saved_esp));
-	asm volatile ("movl %%ebp,(%0)" : "=m" (saved_ebp));
-	asm volatile ("movl %%ebx,(%0)" : "=m" (saved_ebx));
-	asm volatile ("movl %%edi,(%0)" : "=m" (saved_edi));
-	asm volatile ("movl %%esi,(%0)" : "=m" (saved_esi));
+	asm volatile ("movl %%esp,%0" : "=m" (saved_esp));
+	asm volatile ("movl %%ebp,%0" : "=m" (saved_ebp));
+	asm volatile ("movl %%ebx,%0" : "=m" (saved_ebx));
+	asm volatile ("movl %%edi,%0" : "=m" (saved_edi));
+	asm volatile ("movl %%esi,%0" : "=m" (saved_esi));
 }
 
 #define acpi_restore_register_state()  do {} while (0)

include/asm-i386/uaccess.h

@@ -64,7 +64,6 @@ int __verify_write(const void *, unsigned long);
 
 #define access_ok(type,addr,size) ( (__range_ok(addr,size) == 0) && \
 			 ((type) == VERIFY_READ || boot_cpu_data.wp_works_ok || \
-			 segment_eq(get_fs(),KERNEL_DS) || \
 			  __verify_write((void *)(addr),(size))))
 
 #endif

include/asm-sparc64/page.h

@@ -39,6 +39,7 @@ extern void _clear_page(void *page);
 #define clear_page(X)	_clear_page((void *)(X))
 struct page;
 extern void clear_user_page(void *addr, unsigned long vaddr, struct page *page);
+#define copy_page(X,Y)	__memcpy((void *)(X), (void *)(Y), PAGE_SIZE)
 extern void copy_user_page(void *to, void *from, unsigned long vaddr, struct page *topage);
 
 /* GROSS, defining this makes gcc pass these types as aggregates,

include/linux/fs.h

@@ -1239,6 +1239,7 @@ extern int sb_min_blocksize(struct super_block *, int);
 
 extern int generic_file_mmap(struct file *, struct vm_area_struct *);
 extern int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size);
+extern int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size);
 extern ssize_t generic_file_read(struct file *, char *, size_t, loff_t *);
 extern ssize_t generic_file_write(struct file *, const char *, size_t, loff_t *);
 extern ssize_t generic_file_aio_read(struct kiocb *, char *, size_t, loff_t);

include/linux/highmem.h

@@ -73,4 +73,15 @@ static inline void copy_user_highpage(struct page *to, struct page *from, unsign
 	kunmap_atomic(vto, KM_USER1);
 }
 
+static inline void copy_highpage(struct page *to, struct page *from)
+{
+	char *vfrom, *vto;
+
+	vfrom = kmap_atomic(from, KM_USER0);
+	vto = kmap_atomic(to, KM_USER1);
+	copy_page(vto, vfrom);
+	kunmap_atomic(vfrom, KM_USER0);
+	kunmap_atomic(vto, KM_USER1);
+}
+
 #endif /* _LINUX_HIGHMEM_H */

init/do_mounts.c

@@ -27,6 +27,7 @@ extern int get_filesystem_list(char * buf);
 extern asmlinkage long sys_mount(char *dev_name, char *dir_name, char *type,
 	 unsigned long flags, void *data);
 extern asmlinkage long sys_mkdir(const char *name, int mode);
+extern asmlinkage long sys_rmdir(const char *name);
 extern asmlinkage long sys_chdir(const char *name);
 extern asmlinkage long sys_fchdir(int fd);
 extern asmlinkage long sys_chroot(const char *name);
@@ -55,6 +56,7 @@ int __initdata rd_doload;	/* 1 = load RAM disk, 0 = don't load */
 
 int root_mountflags = MS_RDONLY | MS_VERBOSE;
 static char root_device_name[64];
+static char saved_root_name[64];
 
 /* this is initialized in init/main.c */
 dev_t ROOT_DEV;
@@ -87,169 +89,135 @@ static int __init readwrite(char *str)
 __setup("ro", readonly);
 __setup("rw", readwrite);
 
-static struct dev_name_struct {
-	const char *name;
-	const int num;
-} root_dev_names[] __initdata = {
-	{ "nfs",     0x00ff },
-	{ "hda",     0x0300 },
-	{ "hdb",     0x0340 },
-	{ "loop",    0x0700 },
-	{ "hdc",     0x1600 },
-	{ "hdd",     0x1640 },
-	{ "hde",     0x2100 },
-	{ "hdf",     0x2140 },
-	{ "hdg",     0x2200 },
-	{ "hdh",     0x2240 },
-	{ "hdi",     0x3800 },
-	{ "hdj",     0x3840 },
-	{ "hdk",     0x3900 },
-	{ "hdl",     0x3940 },
-	{ "hdm",     0x5800 },
-	{ "hdn",     0x5840 },
-	{ "hdo",     0x5900 },
-	{ "hdp",     0x5940 },
-	{ "hdq",     0x5A00 },
-	{ "hdr",     0x5A40 },
-	{ "hds",     0x5B00 },
-	{ "hdt",     0x5B40 },
-	{ "sda",     0x0800 },
-	{ "sdb",     0x0810 },
-	{ "sdc",     0x0820 },
-	{ "sdd",     0x0830 },
-	{ "sde",     0x0840 },
-	{ "sdf",     0x0850 },
-	{ "sdg",     0x0860 },
-	{ "sdh",     0x0870 },
-	{ "sdi",     0x0880 },
-	{ "sdj",     0x0890 },
-	{ "sdk",     0x08a0 },
-	{ "sdl",     0x08b0 },
-	{ "sdm",     0x08c0 },
-	{ "sdn",     0x08d0 },
-	{ "sdo",     0x08e0 },
-	{ "sdp",     0x08f0 },
-	{ "ada",     0x1c00 },
-	{ "adb",     0x1c10 },
-	{ "adc",     0x1c20 },
-	{ "add",     0x1c30 },
-	{ "ade",     0x1c40 },
-	{ "fd",      0x0200 },
-	{ "md",      0x0900 },	     
-	{ "xda",     0x0d00 },
-	{ "xdb",     0x0d40 },
-	{ "ram",     0x0100 },
-	{ "scd",     0x0b00 },
-	{ "mcd",     0x1700 },
-	{ "cdu535",  0x1800 },
-	{ "sonycd",  0x1800 },
-	{ "aztcd",   0x1d00 },
-	{ "cm206cd", 0x2000 },
-	{ "gscd",    0x1000 },
-	{ "sbpcd",   0x1900 },
-	{ "eda",     0x2400 },
-	{ "edb",     0x2440 },
-	{ "pda",	0x2d00 },
-	{ "pdb",	0x2d10 },
-	{ "pdc",	0x2d20 },
-	{ "pdd",	0x2d30 },
-	{ "pcd",	0x2e00 },
-	{ "pf",		0x2f00 },
-	{ "apblock", APBLOCK_MAJOR << 8},
-	{ "ddv", DDV_MAJOR << 8},
-	{ "jsfd",    JSFD_MAJOR << 8},
-#if defined(CONFIG_ARCH_S390)
-	{ "dasda", (DASD_MAJOR << MINORBITS) },
-	{ "dasdb", (DASD_MAJOR << MINORBITS) + (1 << 2) },
-	{ "dasdc", (DASD_MAJOR << MINORBITS) + (2 << 2) },
-	{ "dasdd", (DASD_MAJOR << MINORBITS) + (3 << 2) },
-	{ "dasde", (DASD_MAJOR << MINORBITS) + (4 << 2) },
-	{ "dasdf", (DASD_MAJOR << MINORBITS) + (5 << 2) },
-	{ "dasdg", (DASD_MAJOR << MINORBITS) + (6 << 2) },
-	{ "dasdh", (DASD_MAJOR << MINORBITS) + (7 << 2) },
-#endif
-#if defined(CONFIG_BLK_CPQ_DA) || defined(CONFIG_BLK_CPQ_DA_MODULE)
-	{ "ida/c0d0p",0x4800 },
-	{ "ida/c0d1p",0x4810 },
-	{ "ida/c0d2p",0x4820 },
-	{ "ida/c0d3p",0x4830 },
-	{ "ida/c0d4p",0x4840 },
-	{ "ida/c0d5p",0x4850 },
-	{ "ida/c0d6p",0x4860 },
-	{ "ida/c0d7p",0x4870 },
-	{ "ida/c0d8p",0x4880 },
-	{ "ida/c0d9p",0x4890 },
-	{ "ida/c0d10p",0x48A0 },
-	{ "ida/c0d11p",0x48B0 },
-	{ "ida/c0d12p",0x48C0 },
-	{ "ida/c0d13p",0x48D0 },
-	{ "ida/c0d14p",0x48E0 },
-	{ "ida/c0d15p",0x48F0 },
-#endif
-#if defined(CONFIG_BLK_CPQ_CISS_DA) || defined(CONFIG_BLK_CPQ_CISS_DA_MODULE)
-	{ "cciss/c0d0p",0x6800 },
-	{ "cciss/c0d1p",0x6810 },
-	{ "cciss/c0d2p",0x6820 },
-	{ "cciss/c0d3p",0x6830 },
-	{ "cciss/c0d4p",0x6840 },
-	{ "cciss/c0d5p",0x6850 },
-	{ "cciss/c0d6p",0x6860 },
-	{ "cciss/c0d7p",0x6870 },
-	{ "cciss/c0d8p",0x6880 },
-	{ "cciss/c0d9p",0x6890 },
-	{ "cciss/c0d10p",0x68A0 },
-	{ "cciss/c0d11p",0x68B0 },
-	{ "cciss/c0d12p",0x68C0 },
-	{ "cciss/c0d13p",0x68D0 },
-	{ "cciss/c0d14p",0x68E0 },
-	{ "cciss/c0d15p",0x68F0 },
-#endif
-	{ "nftla", 0x5d00 },
-	{ "nftlb", 0x5d10 },
-	{ "nftlc", 0x5d20 },
-	{ "nftld", 0x5d30 },
-	{ "ftla", 0x2c00 },
-	{ "ftlb", 0x2c08 },
-	{ "ftlc", 0x2c10 },
-	{ "ftld", 0x2c18 },
-	{ "mtdblock", 0x1f00 },
-	{ NULL, 0 }
-};
-
-kdev_t __init name_to_kdev_t(char *line)
-{
-	int base = 0;
-
-	if (strncmp(line,"/dev/",5) == 0) {
-		struct dev_name_struct *dev = root_dev_names;
-		line += 5;
-		do {
-			int len = strlen(dev->name);
-			if (strncmp(line,dev->name,len) == 0) {
-				line += len;
-				base = dev->num;
-				break;
-			}
-			dev++;
-		} while (dev->name);
-	}
-	return to_kdev_t(base + simple_strtoul(line,NULL,base?10:16));
+static __init dev_t try_name(char *name, int part)
+{
+	char path[64];
+	char buf[32];
+	int range;
+	dev_t res;
+	char *s;
+	int len;
+	int fd;
+
+	/* read device number from .../dev */
+
+	sprintf(path, "/sys/bus/block/devices/%s/dev", name);
+	fd = open(path, 0, 0);
+	if (fd < 0)
+		goto fail;
+	len = read(fd, buf, 32);
+	close(fd);
+	if (len <= 0 || len == 32 || buf[len - 1] != '\n')
+		goto fail;
+	buf[len - 1] = '\0';
+	res = (dev_t) simple_strtoul(buf, &s, 16);
+	if (*s)
+		goto fail;
+
+	/* if it's there and we are not looking for a partition - that's it */
+	if (!part)
+		return res;
+
+	/* otherwise read range from .../range */
+	sprintf(path, "/sys/bus/block/devices/%s/range", name);
+	fd = open(path, 0, 0);
+	if (fd < 0)
+		goto fail;
+	len = read(fd, buf, 32);
+	close(fd);
+	if (len <= 0 || len == 32 || buf[len - 1] != '\n')
+		goto fail;
+	buf[len - 1] = '\0';
+	range = simple_strtoul(buf, &s, 10);
+	if (*s)
+		goto fail;
+
+	/* if partition is within range - we got it */
+	if (part < range)
+		return res + part;
+fail:
+	return (dev_t) 0;
 }
 
-static int __init root_dev_setup(char *line)
+/*
+ *	Convert a name into device number.  We accept the following variants:
+ *
+ *	1) device number in hexadecimal	represents itself
+ *	2) /dev/nfs represents Root_NFS (0xff)
+ *	3) /dev/<disk_name> represents the device number of disk
+ *	4) /dev/<disk_name><decimal> represents the device number
+ *         of partition - device number of disk plus the partition number
+ *	5) /dev/<disk_name>p<decimal> - same as the above, that form is
+ *	   used when disk name of partitioned disk ends on a digit.
+ *
+ *	If name doesn't have fall into the categories above, we return 0.
+ *	Driverfs is used to check if something is a disk name - it has
+ *	all known disks under bus/block/devices.  If the disk name
+ *	contains slashes, name of driverfs node has them replaced with
+ *	dots.  try_name() does the actual checks, assuming that driverfs
+ *	is mounted on rootfs /sys.
+ */
+
+__init dev_t name_to_dev_t(char *name)
 {
-	int i;
-	char ch;
+	char s[32];
+	char *p;
+	dev_t res = 0;
+	int part;
 
-	ROOT_DEV = kdev_t_to_nr(name_to_kdev_t(line));
-	memset (root_device_name, 0, sizeof root_device_name);
-	if (strncmp (line, "/dev/", 5) == 0) line += 5;
-	for (i = 0; i < sizeof root_device_name - 1; ++i)
-	{
-	    ch = line[i];
-	    if ( isspace (ch) || (ch == ',') || (ch == '\0') ) break;
-	    root_device_name[i] = ch;
+	sys_mkdir("/sys", 0700);
+	if (sys_mount("driverfs", "/sys", "driverfs", 0, NULL) < 0)
+		goto out;
+
+	if (strncmp(name, "/dev/", 5) != 0) {
+		res = (dev_t) simple_strtoul(name, &p, 16);
+		if (*p)
+			goto fail;
+		goto done;
 	}
+	name += 5;
+	res = Root_NFS;
+	if (strcmp(name, "nfs") == 0)
+		goto done;
+
+	if (strlen(name) > 31)
+		goto fail;
+	strcpy(s, name);
+	for (p = s; *p; p++)
+		if (*p == '/')
+			*p = '.';
+	res = try_name(s, 0);
+	if (res)
+		goto done;
+
+	while (p > s && isdigit(p[-1]))
+		p--;
+	if (p == s || !*p || *p == '0')
+		goto fail;
+	part = simple_strtoul(p, NULL, 10);
+	*p = '\0';
+	res = try_name(s, part);
+	if (res)
+		goto done;
+
+	if (p < s + 2 || !isdigit(p[-2]) || p[-1] != 'p')
+		goto fail;
+	p[-1] = '\0';
+	res = try_name(s, part);
+done:
+	sys_umount("/sys", 0);
+out:
+	sys_rmdir("/sys");
+	return res;
+fail:
+	res = (dev_t) 0;
+	goto done;
+}
+
+static int __init root_dev_setup(char *line)
+{
+	strncpy(saved_root_name, line, 64);
+	saved_root_name[63] = '\0';
 	return 1;
 }
 
@@ -768,6 +736,13 @@ static int __init initrd_load(void)
 void prepare_namespace(void)
 {
 	int is_floppy = MAJOR(ROOT_DEV) == FLOPPY_MAJOR;
+	if (saved_root_name[0]) {
+		char *p = saved_root_name;
+		ROOT_DEV = name_to_dev_t(p);
+		if (strncmp(p, "/dev/", 5) == 0)
+			p += 5;
+		strcpy(root_device_name, p);
+	}
 #ifdef CONFIG_BLK_DEV_INITRD
 	if (!initrd_start)
 		mount_initrd = 0;

kernel/suspend.c

@@ -57,12 +57,13 @@
 #include <linux/pm.h>
 #include <linux/device.h>
 #include <linux/buffer_head.h>
+#include <linux/swapops.h>
+#include <linux/bootmem.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/io.h>
-#include <linux/swapops.h>
 
 extern void signal_wake_up(struct task_struct *t);
 extern int sys_sync(void);
@@ -225,7 +226,7 @@ int freeze_processes(void)
 			todo++;
 		} while_each_thread(g, p);
 		read_unlock(&tasklist_lock);
-		yield();
+		yield();			/* Yield is okay here */
 		if (time_after(jiffies, start_time + TIMEOUT)) {
 			printk( "\n" );
 			printk(KERN_ERR " stopping tasks failed (%d tasks remaining)\n", todo );
@@ -309,6 +310,9 @@ static void mark_swapfiles(swp_entry_t prev, int mode)
 	union diskpage *cur;
 	struct page *page;
 
+	if (root_swap == 0xFFFF)  /* ignored */
+		return;
+
 	page = alloc_page(GFP_ATOMIC);
 	if (!page)
 		panic("Out of memory in mark_swapfiles");
@@ -474,9 +478,9 @@ static int count_and_copy_data_pages(struct pbe *pagedir_p)
 #ifdef CONFIG_DISCONTIGMEM
 	panic("Discontingmem not supported");
 #else
-	BUG_ON (max_mapnr != num_physpages);
+	BUG_ON (max_pfn != num_physpages);
 #endif
-	for (pfn = 0; pfn < max_mapnr; pfn++) {
+	for (pfn = 0; pfn < max_pfn; pfn++) {
 		page = pfn_to_page(pfn);
 		if (PageHighMem(page))
 			panic("Swsusp not supported on highmem boxes. Send 1GB of RAM to <pavel@ucw.cz> and try again ;-).");
@@ -686,6 +690,7 @@ static int suspend_save_image(void)
 	if(nr_free_pages() < nr_needed_pages) {
 		printk(KERN_CRIT "%sCouldn't get enough free pages, on %d pages short\n",
 		       name_suspend, nr_needed_pages-nr_free_pages());
+		root_swap = 0xFFFF;
 		spin_unlock_irq(&suspend_pagedir_lock);
 		return 1;
 	}
@@ -1042,7 +1047,7 @@ static int bdev_write_page(struct block_device *bdev, long pos, void *buf)
 	return 0;
 }
 
-extern kdev_t __init name_to_kdev_t(const char *line);
+extern dev_t __init name_to_dev_t(const char *line);
 
 static int __read_suspend_image(struct block_device *bdev, union diskpage *cur, int noresume)
 {
@@ -1138,7 +1143,7 @@ static int read_suspend_image(const char * specialfile, int noresume)
 	unsigned long scratch_page = 0;
 	int error;
 
-	resume_device = name_to_kdev_t(specialfile);
+	resume_device = to_kdev_t(name_to_dev_t(specialfile));
 	scratch_page = get_zeroed_page(GFP_ATOMIC);
 	cur = (void *) scratch_page;
 	if (cur) {

mm/filemap.c

@@ -916,7 +916,7 @@ generic_file_read(struct file *filp, char *buf, size_t count, loff_t *ppos)
 	return ret;
 }
 
-static int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size)
+int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size)
 {
 	ssize_t written;
 	unsigned long count = desc->count;