linux-kernel - Re: [PATCH v2 1/5] iommu/amd: Switch amd_iommu_update_ga() to use modify_irte

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Mon, 22 May 2023 17:02:49 -0700
From:   Jerry Snitselaar <jsnitsel@...hat.com>
To:     Suravee Suthikulpanit <suravee.suthikulpanit@....com>
Cc:     linux-kernel@...r.kernel.org, iommu@...ts.linux.dev,
        joro@...tes.org, joao.m.martins@...cle.com,
        alejandro.j.jimenez@...cle.com, boris.ostrovsky@...cle.com,
        jon.grimm@....com, santosh.shukla@....com, vasant.hegde@....com,
        kishon.vijayabraham@....com
Subject: Re: [PATCH v2 1/5] iommu/amd: Switch amd_iommu_update_ga() to use
 modify_irte_ga()

On Thu, May 18, 2023 at 08:55:25PM -0400, Suravee Suthikulpanit wrote:
> From: Joao Martins <joao.m.martins@...cle.com>
> 
> The modify_irte_ga() uses cmpxchg_double() to update the IRTE in one shot,
> which is necessary when adding IRTE cache disabling support since
> the driver no longer need to flush the IRT for hardware to take effect.
> 
> Please note that there is a functional change where the IsRun and
> Destination bits of IRTE are now cached in the struct amd_ir_data.entry.
> 
> Signed-off-by: Joao Martins <joao.m.martins@...cle.com>
> Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@....com>

Reviewed-by: Jerry Snitselaar <jsnitsel@...hat.com>

> ---
>  drivers/iommu/amd/iommu.c | 38 ++++++++++----------------------------
>  1 file changed, 10 insertions(+), 28 deletions(-)
> 
> diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
> index ebb155bfef15..4a3a7346ab21 100644
> --- a/drivers/iommu/amd/iommu.c
> +++ b/drivers/iommu/amd/iommu.c
> @@ -3700,44 +3700,26 @@ int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
>  
>  int amd_iommu_update_ga(int cpu, bool is_run, void *data)
>  {
> -	unsigned long flags;
> -	struct amd_iommu *iommu;
> -	struct irq_remap_table *table;
>  	struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
> -	int devid = ir_data->irq_2_irte.devid;
>  	struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
> -	struct irte_ga *ref = (struct irte_ga *) ir_data->ref;
>  
>  	if (!AMD_IOMMU_GUEST_IR_VAPIC(amd_iommu_guest_ir) ||
> -	    !ref || !entry || !entry->lo.fields_vapic.guest_mode)
> +	    !entry || !entry->lo.fields_vapic.guest_mode)
>  		return 0;
>  
> -	iommu = ir_data->iommu;
> -	if (!iommu)
> -		return -ENODEV;
> -
> -	table = get_irq_table(iommu, devid);
> -	if (!table)
> +	if (!ir_data->iommu)
>  		return -ENODEV;
>  
> -	raw_spin_lock_irqsave(&table->lock, flags);
> -
> -	if (ref->lo.fields_vapic.guest_mode) {
> -		if (cpu >= 0) {
> -			ref->lo.fields_vapic.destination =
> -						APICID_TO_IRTE_DEST_LO(cpu);
> -			ref->hi.fields.destination =
> -						APICID_TO_IRTE_DEST_HI(cpu);
> -		}
> -		ref->lo.fields_vapic.is_run = is_run;
> -		barrier();
> +	if (cpu >= 0) {
> +		entry->lo.fields_vapic.destination =
> +					APICID_TO_IRTE_DEST_LO(cpu);
> +		entry->hi.fields.destination =
> +					APICID_TO_IRTE_DEST_HI(cpu);
>  	}
> +	entry->lo.fields_vapic.is_run = is_run;
>  
> -	raw_spin_unlock_irqrestore(&table->lock, flags);
> -
> -	iommu_flush_irt(iommu, devid);
> -	iommu_completion_wait(iommu);
> -	return 0;
> +	return modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
> +			      ir_data->irq_2_irte.index, entry, ir_data);
>  }
>  EXPORT_SYMBOL(amd_iommu_update_ga);
>  #endif
> -- 
> 2.31.1
>