Revert "xen/mmu: Add workaround "x86-64, mm: Put early page table high""

This reverts commit a38647837a.

It does not work with certain AMD machines.

last_pfn = 0x100000 max_arch_pfn = 0x400000000
initial memory mapped : 0 - 02c3a000
Base memory trampoline at [ffff88000009b000] 9b000 size 20480
init_memory_mapping: 0000000000000000-0000000100000000
 0000000000 - 0100000000 page 4k
kernel direct mapping tables up to 100000000 @ ff7fb000-100000000
init_memory_mapping: 0000000100000000-00000001e0800000
 0100000000 - 01e0800000 page 4k
kernel direct mapping tables up to 1e0800000 @ 1df0f3000-1e0000000
xen: setting RW the range fffdc000 - 100000000
RAMDISK: 0203b000 - 02c3a000
No NUMA configuration found
Faking a node at 0000000000000000-00000001e0800000
NUMA: Using 63 for the hash shift.
Initmem setup node 0 0000000000000000-00000001e0800000
  NODE_DATA [00000001dfffb000 - 00000001dfffffff]
BUG: unable to handle kernel NULL pointer dereference at           (null)
IP: [<ffffffff81cf6a75>] setup_node_bootmem+0x18a/0x1ea
PGD 0
Oops: 0003 [#1] SMP
last sysfs file:
CPU 0
Modules linked in:

Pid: 0, comm: swapper Not tainted 2.6.39-0-virtual #6~smb1
RIP: e030:[<ffffffff81cf6a75>]  [<ffffffff81cf6a75>] setup_node_bootmem+0x18a/0x1ea
RSP: e02b:ffffffff81c01e38  EFLAGS: 00010046
RAX: 0000000000000000 RBX: 00000001e0800000 RCX: 0000000000001040
RDX: 0000000000004100 RSI: 0000000000000000 RDI: ffff8801dfffb000
RBP: ffffffff81c01e58 R08: 0000000000000020 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000000
R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000bfe400
FS:  0000000000000000(0000) GS:ffffffff81cca000(0000) knlGS:0000000000000000
CS:  e033 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000000000000000 CR3: 0000000001c03000 CR4: 0000000000000660
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
Process swapper (pid: 0, threadinfo ffffffff81c00000, task ffffffff81c0b020)
Stack:
 0000000000000040 0000000000000001 0000000000000000 ffffffffffffffff
 ffffffff81c01e88 ffffffff81cf6c25 0000000000000000 0000000000000000
 ffffffff81cf687f 0000000000000000 ffffffff81c01ea8 ffffffff81cf6e45
Call Trace:
 [<ffffffff81cf6c25>] numa_register_memblks.constprop.3+0x150/0x181
 [<ffffffff81cf687f>] ? numa_add_memblk+0x7c/0x7c
 [<ffffffff81cf6e45>] numa_init.part.2+0x1c/0x7c
 [<ffffffff81cf687f>] ? numa_add_memblk+0x7c/0x7c
 [<ffffffff81cf6f67>] numa_init+0x6c/0x70
 [<ffffffff81cf7057>] initmem_init+0x39/0x3b
 [<ffffffff81ce5865>] setup_arch+0x64e/0x769
 [<ffffffff815e43c1>] ? printk+0x51/0x53
 [<ffffffff81cdf92b>] start_kernel+0xd4/0x3f3
 [<ffffffff81cdf388>] x86_64_start_reservations+0x132/0x136
 [<ffffffff81ce2ed4>] xen_start_kernel+0x588/0x58f
Code: 41 00 00 48 8b 3c c5 a0 24 cc 81 31 c0 40 f6 c7 01 74 05 aa 66 ba ff 40 40 f6 c7 02 74 05 66 ab 83 ea 02 89 d1 c1 e9 02 f6 c2 02 <f3> ab 74 02 66 ab 80 e2 01 74 01 aa 49 63 c4 48 c1 eb 0c 44 89
RIP  [<ffffffff81cf6a75>] setup_node_bootmem+0x18a/0x1ea
 RSP <ffffffff81c01e38>
CR2: 0000000000000000
---[ end trace a7919e7f17c0a725 ]---
Kernel panic - not syncing: Attempted to kill the idle task!
Pid: 0, comm: swapper Tainted: G      D     2.6.39-0-virtual #6~smb1

Reported-by: Stefan Bader <stefan.bader@canonical.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
This commit is contained in:
Konrad Rzeszutek Wilk 2011-05-05 13:50:43 -04:00
parent 0ee5623f9a
commit 92bdaef7b2
1 changed files with 0 additions and 123 deletions

View File

@ -1463,119 +1463,6 @@ static int xen_pgd_alloc(struct mm_struct *mm)
return ret;
}
#ifdef CONFIG_X86_64
static __initdata u64 __last_pgt_set_rw = 0;
static __initdata u64 __pgt_buf_start = 0;
static __initdata u64 __pgt_buf_end = 0;
static __initdata u64 __pgt_buf_top = 0;
/*
* As a consequence of the commit:
*
* commit 4b239f458c229de044d6905c2b0f9fe16ed9e01e
* Author: Yinghai Lu <yinghai@kernel.org>
* Date: Fri Dec 17 16:58:28 2010 -0800
*
* x86-64, mm: Put early page table high
*
* at some point init_memory_mapping is going to reach the pagetable pages
* area and map those pages too (mapping them as normal memory that falls
* in the range of addresses passed to init_memory_mapping as argument).
* Some of those pages are already pagetable pages (they are in the range
* pgt_buf_start-pgt_buf_end) therefore they are going to be mapped RO and
* everything is fine.
* Some of these pages are not pagetable pages yet (they fall in the range
* pgt_buf_end-pgt_buf_top; for example the page at pgt_buf_end) so they
* are going to be mapped RW. When these pages become pagetable pages and
* are hooked into the pagetable, xen will find that the guest has already
* a RW mapping of them somewhere and fail the operation.
* The reason Xen requires pagetables to be RO is that the hypervisor needs
* to verify that the pagetables are valid before using them. The validation
* operations are called "pinning".
*
* In order to fix the issue we mark all the pages in the entire range
* pgt_buf_start-pgt_buf_top as RO, however when the pagetable allocation
* is completed only the range pgt_buf_start-pgt_buf_end is reserved by
* init_memory_mapping. Hence the kernel is going to crash as soon as one
* of the pages in the range pgt_buf_end-pgt_buf_top is reused (b/c those
* ranges are RO).
*
* For this reason, 'mark_rw_past_pgt' is introduced which is called _after_
* the init_memory_mapping has completed (in a perfect world we would
* call this function from init_memory_mapping, but lets ignore that).
*
* Because we are called _after_ init_memory_mapping the pgt_buf_[start,
* end,top] have all changed to new values (b/c init_memory_mapping
* is called and setting up another new page-table). Hence, the first time
* we enter this function, we save away the pgt_buf_start value and update
* the pgt_buf_[end,top].
*
* When we detect that the "old" pgt_buf_start through pgt_buf_end
* PFNs have been reserved (so memblock_x86_reserve_range has been called),
* we immediately set out to RW the "old" pgt_buf_end through pgt_buf_top.
*
* And then we update those "old" pgt_buf_[end|top] with the new ones
* so that we can redo this on the next pagetable.
*/
static __init void mark_rw_past_pgt(void) {
if (pgt_buf_end > pgt_buf_start) {
u64 addr, size;
/* Save it away. */
if (!__pgt_buf_start) {
__pgt_buf_start = pgt_buf_start;
__pgt_buf_end = pgt_buf_end;
__pgt_buf_top = pgt_buf_top;
return;
}
/* If we get the range that starts at __pgt_buf_end that means
* the range is reserved, and that in 'init_memory_mapping'
* the 'memblock_x86_reserve_range' has been called with the
* outdated __pgt_buf_start, __pgt_buf_end (the "new"
* pgt_buf_[start|end|top] refer now to a new pagetable.
* Note: we are called _after_ the pgt_buf_[..] have been
* updated.*/
addr = memblock_x86_find_in_range_size(PFN_PHYS(__pgt_buf_start),
&size, PAGE_SIZE);
/* Still not reserved, meaning 'memblock_x86_reserve_range'
* hasn't been called yet. Update the _end and _top.*/
if (addr == PFN_PHYS(__pgt_buf_start)) {
__pgt_buf_end = pgt_buf_end;
__pgt_buf_top = pgt_buf_top;
return;
}
/* OK, the area is reserved, meaning it is time for us to
* set RW for the old end->top PFNs. */
/* ..unless we had already done this. */
if (__pgt_buf_end == __last_pgt_set_rw)
return;
addr = PFN_PHYS(__pgt_buf_end);
/* set as RW the rest */
printk(KERN_DEBUG "xen: setting RW the range %llx - %llx\n",
PFN_PHYS(__pgt_buf_end), PFN_PHYS(__pgt_buf_top));
while (addr < PFN_PHYS(__pgt_buf_top)) {
make_lowmem_page_readwrite(__va(addr));
addr += PAGE_SIZE;
}
/* And update everything so that we are ready for the next
* pagetable (the one created for regions past 4GB) */
__last_pgt_set_rw = __pgt_buf_end;
__pgt_buf_start = pgt_buf_start;
__pgt_buf_end = pgt_buf_end;
__pgt_buf_top = pgt_buf_top;
}
return;
}
#else
static __init void mark_rw_past_pgt(void) { }
#endif
static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd)
{
#ifdef CONFIG_X86_64
@ -1601,14 +1488,6 @@ static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte)
{
unsigned long pfn = pte_pfn(pte);
/*
* A bit of optimization. We do not need to call the workaround
* when xen_set_pte_init is called with a PTE with 0 as PFN.
* That is b/c the pagetable at that point are just being populated
* with empty values and we can save some cycles by not calling
* the 'memblock' code.*/
if (pfn)
mark_rw_past_pgt();
/*
* If the new pfn is within the range of the newly allocated
* kernel pagetable, and it isn't being mapped into an
@ -2118,8 +1997,6 @@ __init void xen_ident_map_ISA(void)
static __init void xen_post_allocator_init(void)
{
mark_rw_past_pgt();
#ifdef CONFIG_XEN_DEBUG
pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte_debug);
#endif