Menu
▾
▴
[LV-kern-commit] CVS: kernel-2.4/arch/i386/mm extable.c,1.1.1.2,1.2 fault.c,1.1.1.2,1.2 init.c,1.1.1.2,1.2 ioremap.c,1.1.1.1,1.2
|
From: Andy P. <at...@us...> - 2002-04-10 18:37:40
|
Update of /cvsroot/linux-vax/kernel-2.4/arch/i386/mm
In directory usw-pr-cvs1:/tmp/cvs-serv10929/i386/mm
Modified Files:
extable.c fault.c init.c ioremap.c
Log Message:
synch 2.4.15 commit 35
Index: extable.c
===================================================================
RCS file: /cvsroot/linux-vax/kernel-2.4/arch/i386/mm/extable.c,v
retrieving revision 1.1.1.2
retrieving revision 1.2
diff -u -r1.1.1.2 -r1.2
--- extable.c 25 Feb 2001 23:15:16 -0000 1.1.1.2
+++ extable.c 10 Apr 2002 14:23:22 -0000 1.2
@@ -37,19 +37,19 @@
search_exception_table(unsigned long addr)
{
unsigned long ret = 0;
- unsigned long flags;
#ifndef CONFIG_MODULES
/* There is only the kernel to search. */
ret = search_one_table(__start___ex_table, __stop___ex_table-1, addr);
return ret;
#else
+ unsigned long flags;
/* The kernel is the last "module" -- no need to treat it special. */
struct module *mp;
spin_lock_irqsave(&modlist_lock, flags);
for (mp = module_list; mp != NULL; mp = mp->next) {
- if (mp->ex_table_start == NULL)
+ if (mp->ex_table_start == NULL || !(mp->flags&(MOD_RUNNING|MOD_INITIALIZING)))
continue;
ret = search_one_table(mp->ex_table_start,
mp->ex_table_end - 1, addr);
Index: fault.c
===================================================================
RCS file: /cvsroot/linux-vax/kernel-2.4/arch/i386/mm/fault.c,v
retrieving revision 1.1.1.2
retrieving revision 1.2
diff -u -r1.1.1.2 -r1.2
--- fault.c 25 Feb 2001 23:15:16 -0000 1.1.1.2
+++ fault.c 10 Apr 2002 14:23:22 -0000 1.2
@@ -17,6 +17,8 @@
#include <linux/smp_lock.h>
#include <linux/interrupt.h>
#include <linux/init.h>
+#include <linux/tty.h>
+#include <linux/vt_kern.h> /* For unblank_screen() */
#include <asm/system.h>
#include <asm/uaccess.h>
@@ -25,6 +27,8 @@
extern void die(const char *,struct pt_regs *,long);
+extern int console_loglevel;
+
/*
* Ugly, ugly, but the goto's result in better assembly..
*/
@@ -51,8 +55,14 @@
start &= PAGE_MASK;
for (;;) {
- if (handle_mm_fault(current->mm, vma, start, 1) <= 0)
- goto bad_area;
+ survive:
+ {
+ int fault = handle_mm_fault(current->mm, vma, start, 1);
+ if (!fault)
+ goto bad_area;
+ if (fault < 0)
+ goto out_of_memory;
+ }
if (!size)
break;
size--;
@@ -75,19 +85,52 @@
bad_area:
return 0;
+
+out_of_memory:
+ if (current->pid == 1) {
+ current->policy |= SCHED_YIELD;
+ schedule();
+ goto survive;
+ }
+ goto bad_area;
}
-extern spinlock_t console_lock, timerlist_lock;
+extern spinlock_t timerlist_lock;
/*
* Unlock any spinlocks which will prevent us from getting the
* message out (timerlist_lock is acquired through the
* console unblank code)
*/
-void bust_spinlocks(void)
+void bust_spinlocks(int yes)
{
- spin_lock_init(&console_lock);
spin_lock_init(&timerlist_lock);
+ if (yes) {
+ oops_in_progress = 1;
+#ifdef CONFIG_SMP
+ global_irq_lock = 0; /* Many serial drivers do __global_cli() */
+#endif
+ } else {
+ int loglevel_save = console_loglevel;
+#ifdef CONFIG_VT
+ unblank_screen();
+#endif
+ oops_in_progress = 0;
+ /*
+ * OK, the message is on the console. Now we call printk()
+ * without oops_in_progress set so that printk will give klogd
+ * a poke. Hold onto your hats...
+ */
+ console_loglevel = 15; /* NMI oopser may have shut the console up */
+ printk(" ");
+ console_loglevel = loglevel_save;
+ }
+}
+
+void do_BUG(const char *file, int line)
+{
+ bust_spinlocks(1);
+ printk("kernel BUG at %s:%d!\n", file, line);
}
asmlinkage void do_invalid_op(struct pt_regs *, unsigned long);
@@ -117,6 +160,10 @@
/* get the address */
__asm__("movl %%cr2,%0":"=r" (address));
+ /* It's safe to allow irq's after cr2 has been saved */
+ if (regs->eflags & X86_EFLAGS_IF)
+ local_irq_enable();
+
tsk = current;
/*
@@ -127,8 +174,12 @@
* be in an interrupt or a critical region, and should
* only copy the information from the master page table,
* nothing more.
+ *
+ * This verifies that the fault happens in kernel space
+ * (error_code & 4) == 0, and that the fault was not a
+ * protection error (error_code & 1) == 0.
*/
- if (address >= TASK_SIZE)
+ if (address >= TASK_SIZE && !(error_code & 5))
goto vmalloc_fault;
mm = tsk->mm;
@@ -141,7 +192,7 @@
if (in_interrupt() || !mm)
goto no_context;
- down(&mm->mmap_sem);
+ down_read(&mm->mmap_sem);
vma = find_vma(mm, address);
if (!vma)
@@ -188,6 +239,7 @@
goto bad_area;
}
+ survive:
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
@@ -214,7 +266,7 @@
if (bit < 32)
tsk->thread.screen_bitmap |= 1 << bit;
}
- up(&mm->mmap_sem);
+ up_read(&mm->mmap_sem);
return;
/*
@@ -222,9 +274,8 @@
* Fix it, but check if it's kernel or user first..
*/
bad_area:
- up(&mm->mmap_sem);
+ up_read(&mm->mmap_sem);
-bad_area_nosemaphore:
/* User mode accesses just cause a SIGSEGV */
if (error_code & 4) {
tsk->thread.cr2 = address;
@@ -264,7 +315,7 @@
* terminate things with extreme prejudice.
*/
- bust_spinlocks();
+ bust_spinlocks(1);
if (address < PAGE_SIZE)
printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference");
@@ -283,6 +334,7 @@
printk(KERN_ALERT "*pte = %08lx\n", page);
}
die("Oops", regs, error_code);
+ bust_spinlocks(0);
do_exit(SIGKILL);
/*
@@ -290,14 +342,20 @@
* us unable to handle the page fault gracefully.
*/
out_of_memory:
- up(&mm->mmap_sem);
+ up_read(&mm->mmap_sem);
+ if (tsk->pid == 1) {
+ tsk->policy |= SCHED_YIELD;
+ schedule();
+ down_read(&mm->mmap_sem);
+ goto survive;
+ }
printk("VM: killing process %s\n", tsk->comm);
if (error_code & 4)
do_exit(SIGKILL);
goto no_context;
do_sigbus:
- up(&mm->mmap_sem);
+ up_read(&mm->mmap_sem);
/*
* Send a sigbus, regardless of whether we were in kernel
@@ -306,7 +364,7 @@
tsk->thread.cr2 = address;
tsk->thread.error_code = error_code;
tsk->thread.trap_no = 14;
- info.si_code = SIGBUS;
+ info.si_signo = SIGBUS;
info.si_errno = 0;
info.si_code = BUS_ADRERR;
info.si_addr = (void *)address;
@@ -322,27 +380,32 @@
/*
* Synchronize this task's top level page-table
* with the 'reference' page table.
+ *
+ * Do _not_ use "tsk" here. We might be inside
+ * an interrupt in the middle of a task switch..
*/
int offset = __pgd_offset(address);
pgd_t *pgd, *pgd_k;
pmd_t *pmd, *pmd_k;
+ pte_t *pte_k;
- pgd = tsk->active_mm->pgd + offset;
+ asm("movl %%cr3,%0":"=r" (pgd));
+ pgd = offset + (pgd_t *)__va(pgd);
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;
- }
-
+ if (!pgd_present(*pgd_k))
+ goto no_context;
+ set_pgd(pgd, *pgd_k);
+
pmd = pmd_offset(pgd, address);
pmd_k = pmd_offset(pgd_k, address);
-
- if (pmd_present(*pmd) || !pmd_present(*pmd_k))
- goto bad_area_nosemaphore;
+ if (!pmd_present(*pmd_k))
+ goto no_context;
set_pmd(pmd, *pmd_k);
+
+ pte_k = pte_offset(pmd_k, address);
+ if (!pte_present(*pte_k))
+ goto no_context;
return;
}
}
Index: init.c
===================================================================
RCS file: /cvsroot/linux-vax/kernel-2.4/arch/i386/mm/init.c,v
retrieving revision 1.1.1.2
retrieving revision 1.2
diff -u -r1.1.1.2 -r1.2
--- init.c 25 Feb 2001 23:15:16 -0000 1.1.1.2
+++ init.c 10 Apr 2002 14:23:22 -0000 1.2
@@ -35,137 +35,30 @@
#include <asm/fixmap.h>
#include <asm/e820.h>
#include <asm/apic.h>
+#include <asm/tlb.h>
+mmu_gather_t mmu_gathers[NR_CPUS];
unsigned long highstart_pfn, highend_pfn;
static unsigned long totalram_pages;
static unsigned long totalhigh_pages;
-/*
- * BAD_PAGE is the page that is used for page faults when linux
- * is out-of-memory. Older versions of linux just did a
- * do_exit(), but using this instead means there is less risk
- * for a process dying in kernel mode, possibly leaving an inode
- * unused etc..
- *
- * BAD_PAGETABLE is the accompanying page-table: it is initialized
- * to point to BAD_PAGE entries.
- *
- * ZERO_PAGE is a special page that is used for zero-initialized
- * data and COW.
- */
-
-/*
- * These are allocated in head.S so that we get proper page alignment.
- * If you change the size of these then change head.S as well.
- */
-extern char empty_bad_page[PAGE_SIZE];
-#if CONFIG_X86_PAE
-extern pmd_t empty_bad_pmd_table[PTRS_PER_PMD];
-#endif
-extern pte_t empty_bad_pte_table[PTRS_PER_PTE];
-
-/*
- * We init them before every return and make them writable-shared.
- * This guarantees we get out of the kernel in some more or less sane
- * way.
- */
-#if CONFIG_X86_PAE
-static pmd_t * get_bad_pmd_table(void)
-{
- pmd_t v;
- int i;
-
- set_pmd(&v, __pmd(_PAGE_TABLE + __pa(empty_bad_pte_table)));
-
- for (i = 0; i < PAGE_SIZE/sizeof(pmd_t); i++)
- empty_bad_pmd_table[i] = v;
-
- return empty_bad_pmd_table;
-}
-#endif
-
-static pte_t * get_bad_pte_table(void)
-{
- pte_t v;
- int i;
-
- v = pte_mkdirty(mk_pte_phys(__pa(empty_bad_page), PAGE_SHARED));
-
- for (i = 0; i < PAGE_SIZE/sizeof(pte_t); i++)
- empty_bad_pte_table[i] = v;
-
- return empty_bad_pte_table;
-}
-
-
-
-void __handle_bad_pmd(pmd_t *pmd)
-{
- pmd_ERROR(*pmd);
- set_pmd(pmd, __pmd(_PAGE_TABLE + __pa(get_bad_pte_table())));
-}
-
-void __handle_bad_pmd_kernel(pmd_t *pmd)
-{
- pmd_ERROR(*pmd);
- set_pmd(pmd, __pmd(_KERNPG_TABLE + __pa(get_bad_pte_table())));
-}
-
-pte_t *get_pte_kernel_slow(pmd_t *pmd, unsigned long offset)
-{
- pte_t *pte;
-
- pte = (pte_t *) __get_free_page(GFP_KERNEL);
- if (pmd_none(*pmd)) {
- if (pte) {
- clear_page(pte);
- set_pmd(pmd, __pmd(_KERNPG_TABLE + __pa(pte)));
- return pte + offset;
- }
- set_pmd(pmd, __pmd(_KERNPG_TABLE + __pa(get_bad_pte_table())));
- return NULL;
- }
- free_page((unsigned long)pte);
- if (pmd_bad(*pmd)) {
- __handle_bad_pmd_kernel(pmd);
- return NULL;
- }
- return (pte_t *) pmd_page(*pmd) + offset;
-}
-
-pte_t *get_pte_slow(pmd_t *pmd, unsigned long offset)
-{
- unsigned long pte;
-
- pte = (unsigned long) __get_free_page(GFP_KERNEL);
- if (pmd_none(*pmd)) {
- if (pte) {
- clear_page((void *)pte);
- set_pmd(pmd, __pmd(_PAGE_TABLE + __pa(pte)));
- return (pte_t *)pte + offset;
- }
- set_pmd(pmd, __pmd(_PAGE_TABLE + __pa(get_bad_pte_table())));
- return NULL;
- }
- free_page(pte);
- if (pmd_bad(*pmd)) {
- __handle_bad_pmd(pmd);
- return NULL;
- }
- return (pte_t *) pmd_page(*pmd) + offset;
-}
-
int do_check_pgt_cache(int low, int high)
{
int freed = 0;
if(pgtable_cache_size > high) {
do {
- if(pgd_quicklist)
- free_pgd_slow(get_pgd_fast()), freed++;
- if(pmd_quicklist)
- free_pmd_slow(get_pmd_fast()), freed++;
- if(pte_quicklist)
- free_pte_slow(get_pte_fast()), freed++;
+ if (pgd_quicklist) {
+ free_pgd_slow(get_pgd_fast());
+ freed++;
+ }
+ if (pmd_quicklist) {
+ pmd_free_slow(pmd_alloc_one_fast(NULL, 0));
+ freed++;
+ }
+ if (pte_quicklist) {
+ pte_free_slow(pte_alloc_one_fast(NULL, 0));
+ freed++;
+ }
} while(pgtable_cache_size > low);
}
return freed;
@@ -327,10 +220,8 @@
pgd_base = swapper_pg_dir;
#if CONFIG_X86_PAE
- for (i = 0; i < PTRS_PER_PGD; i++) {
- pgd = pgd_base + i;
- __pgd_clear(pgd);
- }
+ for (i = 0; i < PTRS_PER_PGD; i++)
+ set_pgd(pgd_base + i, __pgd(1 + __pa(empty_zero_page)));
#endif
i = __pgd_offset(PAGE_OFFSET);
pgd = pgd_base + i;
@@ -420,14 +311,11 @@
* Zap initial low-memory mappings.
*
* Note that "pgd_clear()" doesn't do it for
- * us in this case, because pgd_clear() is a
- * no-op in the 2-level case (pmd_clear() is
- * the thing that clears the page-tables in
- * that case).
+ * us, because pgd_clear() is a no-op on i386.
*/
for (i = 0; i < USER_PTRS_PER_PGD; i++)
#if CONFIG_X86_PAE
- pgd_clear(swapper_pg_dir+i);
+ set_pgd(swapper_pg_dir+i, __pgd(1 + __pa(empty_zero_page)));
#else
set_pgd(swapper_pg_dir+i, __pgd(0));
#endif
@@ -551,13 +439,24 @@
return 0;
}
+static inline int page_kills_ppro(unsigned long pagenr)
+{
+ if(pagenr >= 0x70000 && pagenr <= 0x7003F)
+ return 1;
+ return 0;
+}
+
void __init mem_init(void)
{
+ extern int ppro_with_ram_bug(void);
int codesize, reservedpages, datasize, initsize;
int tmp;
+ int bad_ppro;
if (!mem_map)
BUG();
+
+ bad_ppro = ppro_with_ram_bug();
#ifdef CONFIG_HIGHMEM
highmem_start_page = mem_map + highstart_pfn;
@@ -585,6 +484,11 @@
struct page *page = mem_map + tmp;
if (!page_is_ram(tmp)) {
+ SetPageReserved(page);
+ continue;
+ }
+ if (bad_ppro && page_kills_ppro(tmp))
+ {
SetPageReserved(page);
continue;
}
Index: ioremap.c
===================================================================
RCS file: /cvsroot/linux-vax/kernel-2.4/arch/i386/mm/ioremap.c,v
retrieving revision 1.1.1.1
retrieving revision 1.2
diff -u -r1.1.1.1 -r1.2
--- ioremap.c 14 Jan 2001 19:20:04 -0000 1.1.1.1
+++ ioremap.c 10 Apr 2002 14:23:22 -0000 1.2
@@ -49,7 +49,7 @@
if (address >= end)
BUG();
do {
- pte_t * pte = pte_alloc_kernel(pmd, address);
+ pte_t * pte = pte_alloc(&init_mm, pmd, address);
if (!pte)
return -ENOMEM;
remap_area_pte(pte, address, end - address, address + phys_addr, flags);
@@ -62,6 +62,7 @@
static int remap_area_pages(unsigned long address, unsigned long phys_addr,
unsigned long size, unsigned long flags)
{
+ int error;
pgd_t * dir;
unsigned long end = address + size;
@@ -70,19 +71,23 @@
flush_cache_all();
if (address >= end)
BUG();
+ spin_lock(&init_mm.page_table_lock);
do {
pmd_t *pmd;
- pmd = pmd_alloc_kernel(dir, address);
+ pmd = pmd_alloc(&init_mm, dir, address);
+ error = -ENOMEM;
if (!pmd)
- return -ENOMEM;
+ break;
if (remap_area_pmd(pmd, address, end - address,
phys_addr + address, flags))
- return -ENOMEM;
+ break;
+ error = 0;
address = (address + PGDIR_SIZE) & PGDIR_MASK;
dir++;
} while (address && (address < end));
+ spin_unlock(&init_mm.page_table_lock);
flush_tlb_all();
- return 0;
+ return error;
}
/*
|
