Re: [crash, bisected] Re: [PATCH 3/4] x86_64: Fold pda into per cpuarea

[Mike Travis]

Jeremy Fitzhardinge wrote:
> Mike Travis wrote:
>>... The first is in
>>
>> arch/x86/xen/smp.c:xen_cpu_up()
>>
>> 287 #ifdef CONFIG_X86_64
>> 288         /* Allocate node local memory for AP pdas */
>> 289         WARN_ON(cpu == 0);
>> 290         if (cpu > 0) {
>> 291                 rc = get_local_pda(cpu);
>> 292                 if (rc)
>> 293                         return rc;
>> 294         }
>> 295 #endif
>>
>> and the second is at:
>>
>> arch/x86/xen/enlighten.c:xen_start_kernel()
>>
>> 1748 #ifdef CONFIG_X86_64
>> 1749         /* Disable until direct per-cpu data access. */
>> 1750         have_vcpu_info_placement = 0;
>> 1751         x86_64_init_pda();
>> 1752 #endif
>>
>> I believe with the pda folded into the percpu area, get_local_pda()
>> and x86_64_init_pda() have been removed, so these are no longer
>> required, yes?
>>   
> 
> Well, presumably they need to be replaced with whatever setup you need
> to do now.
> 
> xen_start_kernel() is the first function called after a Xen kernel boot,
> and so it must make sure the early percpu setup is done before it can
> start using percpu variables.

Is this for the boot cpu (0), or for all cpus?  For the boot cpu, I have
this now in arch/x86/kernel/setup_percpu.c:

+#ifdef CONFIG_HAVE_ZERO_BASED_PER_CPU
+
+/* Initialize percpu offset for boot cpu (0) */
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly = {
+       [0] = (unsigned long)__per_cpu_load
+};
+#else
 unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
+#endif

So this should apply as well to the xen startup?

> 
> xen_cpu_up() needs to do whatever initialization needed for a new cpu's
> percpu area (presumably whatever do_boot_cpu() does).
> 

Does the startup include executing arch/x86/kernel/head_64.S:startup_64() ?
I see arch/x86/xen/xen-head.S:startup_xen() so I'm guessing not?

For the real startup, I do the following two things.  But I'm not comfortable
enough with xen to think I'll get it right putting this in xen-head.S.

-       lgdt    early_gdt_descr(%rip)
+
+#ifdef CONFIG_SMP
+        /*
+        * For zero-based percpu variables, the base (__per_cpu_load) must
+        * be added to the offset of per_cpu__gdt_page.  This is only needed
+        * for the boot cpu but we can't do this prior to secondary_startup_64.
+        * So we use a NULL gdt adrs to indicate that we are starting up the
+        * boot cpu and not the secondary cpus.  do_boot_cpu() will fixup
+        * the gdt adrs for those cpus.
+        */
+#define PER_CPU_GDT_PAGE       0
+       movq    early_gdt_descr_base(%rip), %rax
+       testq   %rax, %rax
+       jnz     1f
+       movq    $__per_cpu_load, %rax
+       addq    $per_cpu__gdt_page, %rax
+       movq    %rax, early_gdt_descr_base(%rip)
+#else
+#define PER_CPU_GDT_PAGE       per_cpu__gdt_page
+#endif
+1:     lgdt    early_gdt_descr(%rip)

and:

+        * Setup up the real PDA.
+        *
+        * For SMP, the boot cpu (0) uses the static pda which is the first
+        * element in the percpu area (@__per_cpu_load).  This pda is moved
+        * to the real percpu area once that is allocated.  Secondary cpus
+        * will use the initial_pda value setup in do_boot_cpu().
         */
        movl    $MSR_GS_BASE,%ecx
-       movq    $empty_zero_page,%rax
+       movq    initial_pda(%rip), %rax
        movq    %rax,%rdx
        shrq    $32,%rdx
        wrmsr
+#ifdef CONFIG_SMP
+       movq    %rax, %gs:pda_data_offset
+#endif

+       ENTRY(initial_pda)
+#ifdef CONFIG_SMP
+       .quad   __per_cpu_load          # Overwritten for secondary CPUs
+#else
+       .quad   per_cpu__pda
+#endif


Thanks!
Mike
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/