Re: [PATCH v3 3/6] xen/PMU: Initialization code for Xen PMU

[Boris Ostrovsky <boris.ostrovsky@oracle.com>]

On 07/04/2014 06:52 AM, David Vrabel wrote:
> On 03/07/14 20:14, Boris Ostrovsky wrote:
>> Map shared data structure that will hold CPU registers, VPMU context, V/PCPU IDs
>> of the CPU interrupted by PMU interrupt. Hypervisor fills this information in
>> its handler and passes it to the guest for further processing.
>>
>> Set up PMU VIRQ.
>>
>> Now that perf infrastructure will assume that PMU is availble on a PV guest we
>> need to be careful and make sure that accesses via RDPMC instruction don't
>> cause fatal traps by the hypervisor. Provide a nop RDPMC handler.
>>
>> For the same reason avoid issuing a warning on a write to APIC's LVTPC.
>>
>> Both of these will be made functional in later patches.
> [...]
>> +int xen_pmu_init(int cpu)
>> +{
>> +	int ret = 0;
>> +	struct xen_pmu_params xp;
>> +	unsigned long pfn;
>> +	struct xen_pmu_data *xenpmu_data;
>> +
>> +	BUILD_BUG_ON(sizeof(struct xen_pmu_data) > PAGE_SIZE);
>> +	xenpmu_data = vzalloc(PAGE_SIZE);
> Why vzalloc() for something that is only a page in size?

I need it page-aligned and I don't think kmalloc() guarantees that (the 
implementation might, but not the interface itself). I can use 
__get_free_page(), I suppose.

-boris