Re: %u-order allocation failed

[Mikulas Patocka <mikulas@xxxxxxxxxxxxxxxxxxxxxxxx>]

On Sat, 6 Oct 2001, Mikulas Patocka wrote:

> On Sat, 6 Oct 2001, Rik van Riel wrote:
> 
> > On Sat, 6 Oct 2001, Mikulas Patocka wrote:
> > 
> > > Buddy allocator is broken - kill it. Or at least do not misuse it for
> > > anything except kernel or driver initialization.
> > 
> > Please send patches to get rid of the buddy allocator while
> > still making it possible to allocate contiguous chunks of
> > memory.
> > 
> > If you have any idea on how to fix things, this would be a
> > good time to let us know.
> 
> Here goes the fix. (note that I didn't try to compile it so there may be
> bugs, but you see the point). 
> 
> kmalloc should be fixed too (used badly for example in select.c - and yes
> - I have seen real world bugreports for poll randomly failing with
> ENOMEM), but it will be hard to audit all drivers that they do not try to
> use dma on kmallocated memory. 

This is enhanced version of a patch that fixes select and poll as well.
Again - not compiled, not tried. 

Mikulas

diff -u -r linux-orig/fs/select.c linux/fs/select.c
--- linux-orig/fs/select.c      Sat Oct  6 16:20:45 2001
+++ linux/fs/select.c   Sat Oct  6 16:54:44 2001
@@ -236,7 +236,7 @@
 
 static void *select_bits_alloc(int size)
 {
-       return kmalloc(6 * size, GFP_KERNEL);
+       return kmalloc(6 * size, GFP_KERNEL | __GFP_VMALLOC);
 }
 
 static void select_bits_free(void *bits, int size)
@@ -438,7 +438,7 @@
        if (nfds != 0) {
                fds = (struct pollfd **)kmalloc(
                        (1 + (nfds - 1) / POLLFD_PER_PAGE) * sizeof(struct 
pollfd *),
-                       GFP_KERNEL);
+                       GFP_KERNEL | __GFP_VMALLOC);
                if (fds == NULL)
                        goto out;
        }
diff -u -r linux-orig/include/asm-i386/processor.h 
linux/include/asm-i386/processor.h
--- linux-orig/include/asm-i386/processor.h     Sat Oct  6 16:21:50 2001
+++ linux/include/asm-i386/processor.h  Sat Oct  6 16:31:15 2001
@@ -448,7 +448,7 @@
 #define KSTK_ESP(tsk)  (((unsigned long *)(4096+(unsigned long)(tsk)))[1022])
 
 #define THREAD_SIZE (2*PAGE_SIZE)
-#define alloc_task_struct() ((struct task_struct *) 
__get_free_pages(GFP_KERNEL,1))
+#define alloc_task_struct() ((struct task_struct *) 
__get_free_pages(GFP_KERNEL | __GFP_VMALLOC,1))
 #define free_task_struct(p) free_pages((unsigned long) (p), 1)
 #define get_task_struct(tsk)      atomic_inc(&virt_to_page(tsk)->count)
 
diff -u -r linux-orig/include/linux/mm.h linux/include/linux/mm.h
--- linux-orig/include/linux/mm.h       Sat Oct  6 16:21:59 2001
+++ linux/include/linux/mm.h    Sat Oct  6 16:28:12 2001
@@ -550,6 +550,7 @@
 #define __GFP_IO       0x40    /* Can start low memory physical IO? */
 #define __GFP_HIGHIO   0x80    /* Can start high mem physical IO? */
 #define __GFP_FS       0x100   /* Can call down to low-level FS? */
+#define __GFP_VMALLOC  0x200   /* Can vmalloc pages if buddy allocator fails */
 
 #define GFP_NOHIGHIO   (__GFP_HIGH | __GFP_WAIT | __GFP_IO)
 #define GFP_NOIO       (__GFP_HIGH | __GFP_WAIT)
diff -u -r linux-orig/mm/page_alloc.c linux/mm/page_alloc.c
--- linux-orig/mm/page_alloc.c  Sat Oct  6 16:21:47 2001
+++ linux/mm/page_alloc.c       Sat Oct  6 16:36:28 2001
@@ -18,6 +18,7 @@
 #include <linux/bootmem.h>
 #include <linux/slab.h>
 #include <linux/compiler.h>
+#include <linux/vmalloc.h>
 
 int nr_swap_pages;
 int nr_active_pages;
@@ -421,9 +422,9 @@
        struct page * page;
 
        page = alloc_pages(gfp_mask, order);
-       if (!page)
-               return 0;
-       return (unsigned long) page_address(page);
+       if (page) return (unsigned long) page_address(page);
+       if (gfp_mask & __GFP_VMALLOC) return (unsigned long)__vmalloc(PAGE_SIZE 
<< order, gfp_mask, PAGE_KERNEL);
+       return 0;
 }
 
 unsigned long get_zeroed_page(unsigned int gfp_mask)
@@ -447,6 +448,10 @@
 
 void free_pages(unsigned long addr, unsigned int order)
 {
+       if (addr >= VMALLOC_START && addr < VMALLOC_END) {
+               vfree((void *)addr);
+               return;
+       }
        if (addr != 0)
                __free_pages(virt_to_page(addr), order);
 }
diff -u -r linux-orig/mm/slab.c linux/mm/slab.c
--- linux-orig/mm/slab.c        Sat Oct  6 16:21:48 2001
+++ linux/mm/slab.c     Sat Oct  6 17:04:37 2001
@@ -73,6 +73,7 @@
 #include       <linux/interrupt.h>
 #include       <linux/init.h>
 #include       <linux/compiler.h>
+#include       <linux/vmalloc.h>
 #include       <asm/uaccess.h>
 
 /*
@@ -1536,10 +1537,14 @@
        cache_sizes_t *csizep = cache_sizes;
 
        for (; csizep->cs_size; csizep++) {
+               void *p;
                if (size > csizep->cs_size)
                        continue;
-               return __kmem_cache_alloc(flags & GFP_DMA ?
-                        csizep->cs_dmacachep : csizep->cs_cachep, flags);
+               if ((p = __kmem_cache_alloc(flags & GFP_DMA ?
+                        csizep->cs_dmacachep : csizep->cs_cachep, flags & 
~__GFP_VMALLOC)))
+                               return p;
+               if (flags & __GFP_VMALLOC) return __vmalloc(size, flags, 
PAGE_KERNEL);
+               return NULL;
        }
        return NULL;
 }
@@ -1580,6 +1585,10 @@
 
        if (!objp)
                return;
+       if ((unsigned long)objp >= VMALLOC_START && (unsigned long)obj < 
VMALLOC_END) {
+               vfree(objp);
+               return;
+       }
        local_irq_save(flags);
        CHECK_PAGE(virt_to_page(objp));
        c = GET_PAGE_CACHE(virt_to_page(objp));