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

[Xen-changelog] [xen staging-4.11] x86/SMP: don't try to stop already stopped CPUs



commit c719519a4183d0630121f6abeba420f49dbc3229
Author:     Jan Beulich <jbeulich@xxxxxxxx>
AuthorDate: Fri Jul 5 10:32:41 2019 +0200
Commit:     Jan Beulich <jbeulich@xxxxxxxx>
CommitDate: Fri Jul 5 10:32:41 2019 +0200

    x86/SMP: don't try to stop already stopped CPUs
    
    In particular with an enabled IOMMU (but not really limited to this
    case), trying to invoke fixup_irqs() after having already done
    disable_IO_APIC() -> clear_IO_APIC() is a rather bad idea:
    
     RIP:    e008:[<ffff82d08026a036>] amd_iommu_read_ioapic_from_ire+0xde/0x113
     RFLAGS: 0000000000010006   CONTEXT: hypervisor (d0v0)
     rax: ffff8320291de00c   rbx: 0000000000000003   rcx: ffff832035000000
     rdx: 0000000000000000   rsi: 0000000000000000   rdi: ffff82d0805ca840
     rbp: ffff83009e8a79c8   rsp: ffff83009e8a79a8   r8:  0000000000000000
     r9:  0000000000000004   r10: 000000000008b9f9   r11: 0000000000000006
     r12: 0000000000010000   r13: 0000000000000003   r14: 0000000000000000
     r15: 00000000fffeffff   cr0: 0000000080050033   cr4: 00000000003406e0
     cr3: 0000002035d59000   cr2: ffff88824ccb4ee0
     fsb: 00007f2143f08840   gsb: ffff888256a00000   gss: 0000000000000000
     ds: 0000   es: 0000   fs: 0000   gs: 0000   ss: e010   cs: e008
     Xen code around <ffff82d08026a036> 
(amd_iommu_read_ioapic_from_ire+0xde/0x113):
      ff 07 00 00 39 d3 74 02 <0f> 0b 41 81 e4 00 f8 ff ff 8b 10 89 d0 25 00 00
     Xen stack trace from rsp=ffff83009e8a79a8:
     ...
     Xen call trace:
        [<ffff82d08026a036>] amd_iommu_read_ioapic_from_ire+0xde/0x113
        [<ffff82d08026bf7b>] iommu_read_apic_from_ire+0x10/0x12
        [<ffff82d08027f718>] io_apic.c#modify_IO_APIC_irq+0x5e/0x126
        [<ffff82d08027f9c5>] io_apic.c#unmask_IO_APIC_irq+0x2d/0x41
        [<ffff82d080289bc7>] fixup_irqs+0x320/0x40b
        [<ffff82d0802a82c4>] smp_send_stop+0x4b/0xa8
        [<ffff82d0802a7b2f>] machine_restart+0x98/0x288
        [<ffff82d080252242>] console_suspend+0/0x28
        [<ffff82d0802b01da>] do_general_protection+0x204/0x24e
        [<ffff82d080385a3d>] x86_64/entry.S#handle_exception_saved+0x68/0x94
        [<00000000aa5b526b>] 00000000aa5b526b
        [<ffff82d0802a7c7d>] machine_restart+0x1e6/0x288
        [<ffff82d080240f75>] hwdom_shutdown+0xa2/0x11d
        [<ffff82d08020baa2>] domain_shutdown+0x4f/0xd8
        [<ffff82d08023fe98>] do_sched_op+0x12f/0x42a
        [<ffff82d08037e404>] pv_hypercall+0x1e4/0x564
        [<ffff82d080385432>] lstar_enter+0x112/0x120
    
    Don't call fixup_irqs() and don't send any IPI if there's only one
    online CPU anyway, and don't call __stop_this_cpu() at all when the CPU
    we're on was already marked offline (by a prior invocation of
    __stop_this_cpu()).
    
    Reported-by: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
    Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>
    Reviewed-by: Roger Pau Monné <roger.pau@xxxxxxxxxx>
    Acked-by: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
    
    Extend this to the kexec/crash path as well.
    
    Signed-off-by: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
    Reviewed-by: Jan Beulich <jbeulich@xxxxxxxx>
    master commit: 6ff560f7f1f214fb89baaf97812c4c943e44a642
    master date: 2019-06-18 16:35:35 +0200
---
 xen/arch/x86/crash.c | 19 ++++++++++++-------
 xen/arch/x86/smp.c   | 34 +++++++++++++++++++++-------------
 2 files changed, 33 insertions(+), 20 deletions(-)

diff --git a/xen/arch/x86/crash.c b/xen/arch/x86/crash.c
index c9e483a9e5..d4fc136a86 100644
--- a/xen/arch/x86/crash.c
+++ b/xen/arch/x86/crash.c
@@ -172,15 +172,20 @@ static void nmi_shootdown_cpus(void)
      */
     iommu_crash_shutdown();
 
-    __stop_this_cpu();
+    if ( num_online_cpus() > 1 )
+    {
+        __stop_this_cpu();
 
-    /* This is a bit of a hack due to the problems with the x2apic_enabled
-     * variable, but we can't do any better without a significant refactoring
-     * of the APIC code */
-    x2apic_enabled = (current_local_apic_mode() == APIC_MODE_X2APIC);
+        /*
+         * This is a bit of a hack due to the problems with the x2apic_enabled
+         * variable, but we can't do any better without a significant
+         * refactoring of the APIC code
+         */
+        x2apic_enabled = (current_local_apic_mode() == APIC_MODE_X2APIC);
 
-    disable_IO_APIC();
-    hpet_disable();
+        disable_IO_APIC();
+        hpet_disable();
+    }
 }
 
 void machine_crash_shutdown(void)
diff --git a/xen/arch/x86/smp.c b/xen/arch/x86/smp.c
index 63e819ca38..4454224e0f 100644
--- a/xen/arch/x86/smp.c
+++ b/xen/arch/x86/smp.c
@@ -302,23 +302,31 @@ static void stop_this_cpu(void *dummy)
  */
 void smp_send_stop(void)
 {
-    int timeout = 10;
+    unsigned int cpu = smp_processor_id();
 
-    local_irq_disable();
-    fixup_irqs(cpumask_of(smp_processor_id()), 0);
-    local_irq_enable();
+    if ( num_online_cpus() > 1 )
+    {
+        int timeout = 10;
 
-    smp_call_function(stop_this_cpu, NULL, 0);
+        local_irq_disable();
+        fixup_irqs(cpumask_of(cpu), 0);
+        local_irq_enable();
 
-    /* Wait 10ms for all other CPUs to go offline. */
-    while ( (num_online_cpus() > 1) && (timeout-- > 0) )
-        mdelay(1);
+        smp_call_function(stop_this_cpu, NULL, 0);
 
-    local_irq_disable();
-    disable_IO_APIC();
-    hpet_disable();
-    __stop_this_cpu();
-    local_irq_enable();
+        /* Wait 10ms for all other CPUs to go offline. */
+        while ( (num_online_cpus() > 1) && (timeout-- > 0) )
+            mdelay(1);
+    }
+
+    if ( cpu_online(cpu) )
+    {
+        local_irq_disable();
+        disable_IO_APIC();
+        hpet_disable();
+        __stop_this_cpu();
+        local_irq_enable();
+    }
 }
 
 void smp_send_nmi_allbutself(void)
--
generated by git-patchbot for /home/xen/git/xen.git#staging-4.11

_______________________________________________
Xen-changelog mailing list
Xen-changelog@xxxxxxxxxxxxxxxxxxxx
https://lists.xenproject.org/xen-changelog

 


Rackspace

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