[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Xen-devel] crash on boot with 4.6.1 on fedora 24



:-(

On Wed, 1 Jun 2016, Martin Cerveny wrote:
I hit probably the same error with released "XenServer 7.0".
- I have Xen4.6.1 (commit d77bac5c064ffb9dbb5b89b55b89853f1b784ebf - update Xen version to 4.6.1)
- XS7 (Dundee) beta3 (kernel-3.10.96-479.383024.x86_64.rpm) work OK
- XS7 release (kernel-3.10.96-484.383030.x86_64.rpm) crash
- patch does not work, arch/x86/xen/mmu.c is very old in 3.10
- Can someone verify error ?

Thanks, Martin Cerveny

Crash (kernel-3.10.96-479.383024.x86_64.rpm):
         ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
correction: kernel-3.10.96-484.383030.x86_64.rpm

about to get started...
(XEN) d0v0: unhandled page fault (ec=0000)
(XEN) Pagetable walk from ffff88010278b080:
(XEN)  L4[0x110] = 0000000439a0d067 0000000000001a0d
(XEN)  L3[0x004] = 0000000000000000 ffffffffffffffff
(XEN) domain_crash_sync called from entry.S: fault at ffff82d08022b2c3 create_bounce_frame+0x12b/0x13a
(XEN) Domain 0 (vcpu#0) crashed on cpu#0:
(XEN) ----[ Xen-4.6.1-vgpu  x86_64  debug=n  Not tainted ]----
(XEN) CPU:    0
(XEN) RIP:    e033:[<ffffffff81005dea>]
(XEN) RFLAGS: 0000000000000282   EM: 1   CONTEXT: pv guest (d0v0)
(XEN) rax: ffff88010278b080   rbx: ffffffff81a10000   rcx: ffff880000000080
(XEN) rdx: 00003ffffffff000   rsi: ffffffff81a01de4   rdi: 000000043a95c067
(XEN) rbp: ffffffff81a01df8   rsp: ffffffff81a01da0   r8:  00003ffffffff000
(XEN) r9:  ffff880000000000   r10: 0000000000000001   r11: 0000000000000001
(XEN) r12: ffffffff80000000   r13: ffffffff81a10000   r14: 0000000000000000
(XEN) r15: 0000000000000082   cr0: 000000008005003b   cr4: 00000000001526e0
(XEN) cr3: 0000000439a0c000   cr2: ffff88010278b080
(XEN) ds: 0000   es: 0000   fs: 0000   gs: 0000   ss: e02b   cs: e033
(XEN) Guest stack trace from rsp=ffffffff81a01da0:
(XEN)    ffff880000000080 0000000000000001 0000000000000000 ffffffff81005dea
(XEN)    000000010000e030 0000000000010082 ffffffff81a01de0 000000000000e02b
(XEN)    0000000181a10000 ffffffff81a10000 ffffffff80000000 ffffffff81a01e40
(XEN)    ffffffff810067f6 0000000000000001 0000000000000001 ffffffff81a10000
(XEN)    ffffffff80000000 ffffffff83d7a000 0000000000000000 ffffffff81dfffff
(XEN)    ffffffff81a01e78 ffffffff81aedf2d 000000000114b000 0000000001000000
(XEN)    0000000000000000 0000000000000000 0000000000000000 ffffffff81a01ef0
(XEN)    ffffffff81add76b 0000000000000000 0000000000000000 ffffffff81a01ef0
(XEN)    ffffffff81a01f08 ffffffff00000010 ffffffff81a01f00 ffffffff81a01ec0
(XEN)    0000000000000000 ffffffffffffffff ffffffff81b69900 0000000000000000
(XEN)    0000000000000000 0000000000000000 ffffffff81a01f30 ffffffff81ad5bb9
(XEN)    0000000000000000 ffffffff81b732c0 ffffffff81a01f60 00000000ffffffff
(XEN)    0000000000000000 0000000000000000 ffffffff81a01f40 ffffffff81ad55ee
(XEN)    ffffffff81a01ff8 ffffffff81ad8b48 000306e400000000 0000000100200800
(XEN)    0300000100000032 0000000000000005 0000000000000020 0000000000000000
(XEN)    0000000000000000 0000000000000000 0000000000000000 0000000000000000
(XEN)    0000000000000000 0000000000000000 0000000000000000 0000000000000000
(XEN)    0000000000000000 0000000000000000 0000000000000000 0000000000000000
(XEN)    0000000000000000 0000000000000000 0000000000000000 0000000000000000
(XEN)    0f00000060c0c748 ccccccccccccc305 cccccccccccccccc cccccccccccccccc
(XEN) Hardware Dom0 crashed: rebooting machine in 5 seconds.
(XEN) Resetting with ACPI MEMORY or I/O RESET_REG.


On Thu, 26 May 2016, David Vrabel wrote:

On 17/05/16 16:11, David Vrabel wrote:
On 11/05/16 11:16, David Vrabel wrote:

Why don't we get the RW bits correct when making the pteval when we
already have the pfn, instead trying to fix it up afterwards.

Kevin, can you try this patch.

David

8<-----------------
x86/xen: avoid m2p lookup when setting early page table entries

When page tables entries are set using xen_set_pte_init() during early
boot there is no page fault handler that could handle a fault when
performing an M2P lookup.

In 64 guest (usually dom0) early_ioremap() would fault in
xen_set_pte_init() because an M2P lookup faults because the MFN is in
MMIO space and not mapped in the M2P.  This lookup is done to see if
the PFN in in the range used for the initial page table pages, so that
the PTE may be set as read-only.

The M2P lookup can be avoided by moving the check (and clear of RW)
earlier when the PFN is still available.

[ Not entirely happy with this as the 32/64 bit paths diverge even
  more. Is there some way to unify them instead? ]

Boris, Juergen, any opinion on this patch?

David

--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1562,7 +1562,7 @@ static pte_t __init mask_rw_pte(pte_t *ptep, pte_t
pte)
        return pte;
 }
 #else /* CONFIG_X86_64 */
-static pte_t __init mask_rw_pte(pte_t *ptep, pte_t pte)
+static pteval_t __init mask_rw_pte(pteval_t pte)
 {
        unsigned long pfn;

@@ -1577,10 +1577,10 @@ static pte_t __init mask_rw_pte(pte_t *ptep,
pte_t pte)
         * page tables for mapping the p2m list, too, and page tables MUST be
         * mapped read-only.
         */
-       pfn = pte_pfn(pte);
+       pfn = (pte & PTE_PFN_MASK) >> PAGE_SHIFT;
        if (pfn >= xen_start_info->first_p2m_pfn &&
pfn < xen_start_info->first_p2m_pfn + xen_start_info->nr_p2m_frames)
-               pte = __pte_ma(pte_val_ma(pte) & ~_PAGE_RW);
+               pte &= ~_PAGE_RW;

        return pte;
 }
@@ -1600,13 +1600,26 @@ static pte_t __init mask_rw_pte(pte_t *ptep,
pte_t pte)
  * so always write the PTE directly and rely on Xen trapping and
  * emulating any updates as necessary.
  */
+__visible __init pte_t xen_make_pte_init(pteval_t pte)
+{
+#ifdef CONFIG_X86_64
+       pte = mask_rw_pte(pte);
+#endif
+       pte = pte_pfn_to_mfn(pte);
+
+       if ((pte & PTE_PFN_MASK) >> PAGE_SHIFT == INVALID_P2M_ENTRY)
+               pte = 0;
+
+       return native_make_pte(pte);
+}
+PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_init);
+
 static void __init xen_set_pte_init(pte_t *ptep, pte_t pte)
 {
+#ifdef CONFIG_X86_32
        if (pte_mfn(pte) != INVALID_P2M_ENTRY)
                pte = mask_rw_pte(ptep, pte);
-       else
-               pte = __pte_ma(0);
-
+#endif
        native_set_pte(ptep, pte);
 }

@@ -2407,6 +2420,7 @@ static void __init xen_post_allocator_init(void)
        pv_mmu_ops.alloc_pud = xen_alloc_pud;
        pv_mmu_ops.release_pud = xen_release_pud;
 #endif
+       pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte);

 #ifdef CONFIG_X86_64
        pv_mmu_ops.write_cr3 = &xen_write_cr3;
@@ -2455,7 +2469,7 @@ static const struct pv_mmu_ops xen_mmu_ops
__initconst = {
        .pte_val = PV_CALLEE_SAVE(xen_pte_val),
        .pgd_val = PV_CALLEE_SAVE(xen_pgd_val),

-       .make_pte = PV_CALLEE_SAVE(xen_make_pte),
+       .make_pte = PV_CALLEE_SAVE(xen_make_pte_init),
        .make_pgd = PV_CALLEE_SAVE(xen_make_pgd),

 #ifdef CONFIG_X86_PAE



_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel

 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.