Date:   Mon, 8 Aug 2022 17:18:54 -0500
From:   Tom Lendacky <thomas.lendacky@....com>
To:     Dave Hansen <dave.hansen@...el.com>, linux-kernel@...r.kernel.org,
        x86@...nel.org
Cc:     Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
        Dave Hansen <dave.hansen@...ux.intel.com>,
        "Kirill A. Shutemov" <kirill@...temov.name>,
        "H. Peter Anvin" <hpa@...or.com>,
        Michael Roth <michael.roth@....com>,
        Joerg Roedel <jroedel@...e.de>,
        Andy Lutomirski <luto@...nel.org>,
        Peter Zijlstra <peterz@...radead.org>
Subject: Re: [PATCH v2 1/2] x86/sev: Put PSC struct on the stack in prep for
 unaccepted memory support

On 8/8/22 16:43, Dave Hansen wrote:
> On 8/8/22 10:16, Tom Lendacky wrote:
> ...
>> diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h
>> index b8357d6ecd47..6f7268a817fc 100644
>> --- a/arch/x86/include/asm/sev-common.h
>> +++ b/arch/x86/include/asm/sev-common.h
>> @@ -107,7 +107,7 @@ enum psc_op {
>>   #define GHCB_HV_FT_SNP_AP_CREATION	BIT_ULL(1)
>>   
>>   /* SNP Page State Change NAE event */
>> -#define VMGEXIT_PSC_MAX_ENTRY		253
>> +#define VMGEXIT_PSC_MAX_ENTRY		64
> 
> In general, the stack-based allocation looks fine.  It might be worth a
> comment in there to make it clear that this can consume stack space.

I'll add that.

> 
>>   struct psc_hdr {
>>   	u16 cur_entry;
>> diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c
>> index c05f0124c410..275aa890611f 100644
>> --- a/arch/x86/kernel/sev.c
>> +++ b/arch/x86/kernel/sev.c
>> @@ -66,6 +66,9 @@ static struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE);
>>    */
>>   static struct ghcb *boot_ghcb __section(".data");
>>   
>> +/* Flag to indicate when the first per-CPU GHCB is registered */
>> +static bool ghcb_percpu_ready __section(".data");
> 
> So, there's a code path that can't be entered until this is set?  Seems
> like the least we can do it annotate that path with a
> WARN_ON_ONCE(!ghcb_percpu_ready).

Sure, that can be added. Right now the only function that calls 
vmgexit_psc() is covered (set_pages_state()/__set_pages_state()) and is 
doing the right thing. But I guess if anything is added in the future, 
that will provide details on what happened.

> 
> Also, how does having _one_ global variable work for indicating the
> state of multiple per-cpu structures?  The code doesn't seem to delay
> setting this variable until after _all_ of the per-cpu state is ready.

All of the per-CPU GHCBs are allocated during the BSP boot, before any AP 
is started. The APs only ever run the kernel_exc_vmm_communication() #VC 
handler and only ever use the per-CPU version of the GHCB, never the early 
boot version. This is based on the initial_vc_handler being switched to 
the runtime #VC handler, kernel_exc_vmm_communication.

The trigger for the switch over for the BSP from the early boot GHCB to 
the per-CPU GHCB is during setup_ghcb() after the initial_vc_handler has 
been switched to kernel_exc_vmm_communication, which is just after the 
per-CPU allocations. By putting the setting of the ghcb_percpu_ready in 
setup_ghcb(), it indicates that the BSP per-CPU GHCB has been registered 
and can be used.

> 
>>   /* Bitmap of SEV features supported by the hypervisor */
>>   static u64 sev_hv_features __ro_after_init;
>>   
>> @@ -660,7 +663,7 @@ static void pvalidate_pages(unsigned long vaddr, unsigned int npages, bool valid
>>   	}
>>   }
>>   
>> -static void __init early_set_pages_state(unsigned long paddr, unsigned int npages, enum psc_op op)
>> +static void early_set_pages_state(unsigned long paddr, unsigned int npages, enum psc_op op)
>>   {
>>   	unsigned long paddr_end;
>>   	u64 val;
>> @@ -868,11 +871,16 @@ static void __set_pages_state(struct snp_psc_desc *data, unsigned long vaddr,
>>   static void set_pages_state(unsigned long vaddr, unsigned int npages, int op)
>>   {
>>   	unsigned long vaddr_end, next_vaddr;
>> -	struct snp_psc_desc *desc;
>> +	struct snp_psc_desc desc;
>> +
>> +	/*
>> +	 * Use the MSR protocol when the per-CPU GHCBs are not yet registered,
>> +	 * since vmgexit_psc() uses the per-CPU GHCB.
>> +	 */
>> +	if (!ghcb_percpu_ready)
>> +		return early_set_pages_state(__pa(vaddr), npages, op);
>>   
>> -	desc = kmalloc(sizeof(*desc), GFP_KERNEL_ACCOUNT);
>> -	if (!desc)
>> -		panic("SNP: failed to allocate memory for PSC descriptor\n");
>> +	memset(&desc, 0, sizeof(desc));
> 
> Why is this using memset()?  The compiler should be smart enough to
> delay initializing 'desc' until after the return with this kind of
> construct:
> 
> 	struct snp_psc_desc desc = {};
> 	if (foo)
> 		return;
> 	// use 'desc' here
> 
> The compiler *knows* there is no access to 'desc' before the if().

Yup, I can change that.

Thanks,
Tom

> 
> 
>>   	vaddr = vaddr & PAGE_MASK;
>>   	vaddr_end = vaddr + (npages << PAGE_SHIFT);
>> @@ -882,12 +890,10 @@ static void set_pages_state(unsigned long vaddr, unsigned int npages, int op)
>>   		next_vaddr = min_t(unsigned long, vaddr_end,
>>   				   (VMGEXIT_PSC_MAX_ENTRY * PAGE_SIZE) + vaddr);
>>   
>> -		__set_pages_state(desc, vaddr, next_vaddr, op);
>> +		__set_pages_state(&desc, vaddr, next_vaddr, op);
>>   
>>   		vaddr = next_vaddr;
>>   	}
>> -
>> -	kfree(desc);
>>   }
>>   
>>   void snp_set_memory_shared(unsigned long vaddr, unsigned int npages)
>> @@ -1254,6 +1260,8 @@ void setup_ghcb(void)
>>   		if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
>>   			snp_register_per_cpu_ghcb();
>>   
>> +		ghcb_percpu_ready = true;
>> +
>>   		return;
>>   	}
>>   
> 

Powered by blists - more mailing lists