Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Subject: Re: [PATCH v2] ocxl: Allow contexts to be attached with a NULL mm
To:     "Alastair D'Silva" <alastair@au1.ibm.com>, alastair@d-silva.org
Cc:     Benjamin Herrenschmidt <benh@kernel.crashing.org>,
        Paul Mackerras <paulus@samba.org>,
        Michael Ellerman <mpe@ellerman.id.au>,
        Frederic Barrat <fbarrat@linux.ibm.com>,
        Arnd Bergmann <arnd@arndb.de>,
        Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        Nicholas Piggin <npiggin@gmail.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Masahiro Yamada <yamada.masahiro@socionext.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Suraj Jitindar Singh <sjitindarsingh@gmail.com>,
        linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org
References: <20190620041203.12274-1-alastair@au1.ibm.com>
From:   Andrew Donnellan <ajd@linux.ibm.com>
Date:   Fri, 21 Jun 2019 10:22:26 +1000
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:60.0) Gecko/20100101
 Thunderbird/60.7.0
MIME-Version: 1.0
In-Reply-To: <20190620041203.12274-1-alastair@au1.ibm.com>
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Language: en-AU
Content-Transfer-Encoding: 7bit
Message-Id: <a4e6b156-0dce-53e3-786f-cc954ebe08fa@linux.ibm.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On 20/6/19 2:12 pm, Alastair D'Silva wrote:
> From: Alastair D'Silva <alastair@d-silva.org>
> 
> If an OpenCAPI context is to be used directly by a kernel driver, there
> may not be a suitable mm to use.
> 
> The patch makes the mm parameter to ocxl_context_attach optional.
> 
> Signed-off-by: Alastair D'Silva <alastair@d-silva.org>

Acked-by: Andrew Donnellan <ajd@linux.ibm.com>

> ---
>   arch/powerpc/mm/book3s64/radix_tlb.c |  5 +++++
>   drivers/misc/ocxl/context.c          |  9 ++++++---
>   drivers/misc/ocxl/link.c             | 28 ++++++++++++++++++++++++----
>   3 files changed, 35 insertions(+), 7 deletions(-)
> 
> diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
> index bb9835681315..ce8a77fae6a7 100644
> --- a/arch/powerpc/mm/book3s64/radix_tlb.c
> +++ b/arch/powerpc/mm/book3s64/radix_tlb.c
> @@ -666,6 +666,11 @@ EXPORT_SYMBOL(radix__flush_tlb_page);
>   #define radix__flush_all_mm radix__local_flush_all_mm
>   #endif /* CONFIG_SMP */
>   
> +/*
> + * If kernel TLBIs ever become local rather than global, then
> + * drivers/misc/ocxl/link.c:ocxl_link_add_pe will need some work, as it
> + * assumes kernel TLBIs are global.
> + */
>   void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end)
>   {
>   	_tlbie_pid(0, RIC_FLUSH_ALL);
> diff --git a/drivers/misc/ocxl/context.c b/drivers/misc/ocxl/context.c
> index bab9c9364184..994563a078eb 100644
> --- a/drivers/misc/ocxl/context.c
> +++ b/drivers/misc/ocxl/context.c
> @@ -69,6 +69,7 @@ static void xsl_fault_error(void *data, u64 addr, u64 dsisr)
>   int ocxl_context_attach(struct ocxl_context *ctx, u64 amr, struct mm_struct *mm)
>   {
>   	int rc;
> +	unsigned long pidr = 0;
>   
>   	// Locks both status & tidr
>   	mutex_lock(&ctx->status_mutex);
> @@ -77,9 +78,11 @@ int ocxl_context_attach(struct ocxl_context *ctx, u64 amr, struct mm_struct *mm)
>   		goto out;
>   	}
>   
> -	rc = ocxl_link_add_pe(ctx->afu->fn->link, ctx->pasid,
> -			mm->context.id, ctx->tidr, amr, mm,
> -			xsl_fault_error, ctx);
> +	if (mm)
> +		pidr = mm->context.id;
> +
> +	rc = ocxl_link_add_pe(ctx->afu->fn->link, ctx->pasid, pidr, ctx->tidr,
> +			      amr, mm, xsl_fault_error, ctx);
>   	if (rc)
>   		goto out;
>   
> diff --git a/drivers/misc/ocxl/link.c b/drivers/misc/ocxl/link.c
> index cce5b0d64505..58d111afd9f6 100644
> --- a/drivers/misc/ocxl/link.c
> +++ b/drivers/misc/ocxl/link.c
> @@ -224,6 +224,17 @@ static irqreturn_t xsl_fault_handler(int irq, void *data)
>   		ack_irq(spa, ADDRESS_ERROR);
>   		return IRQ_HANDLED;
>   	}
> +
> +	if (!pe_data->mm) {
> +		/*
> +		 * translation fault from a kernel context - an OpenCAPI
> +		 * device tried to access a bad kernel address
> +		 */
> +		rcu_read_unlock();
> +		pr_warn("Unresolved OpenCAPI xsl fault in kernel context\n");
> +		ack_irq(spa, ADDRESS_ERROR);
> +		return IRQ_HANDLED;
> +	}
>   	WARN_ON(pe_data->mm->context.id != pid);
>   
>   	if (mmget_not_zero(pe_data->mm)) {
> @@ -523,7 +534,13 @@ int ocxl_link_add_pe(void *link_handle, int pasid, u32 pidr, u32 tidr,
>   	pe->amr = cpu_to_be64(amr);
>   	pe->software_state = cpu_to_be32(SPA_PE_VALID);
>   
> -	mm_context_add_copro(mm);
> +	/*
> +	 * For user contexts, register a copro so that TLBIs are seen
> +	 * by the nest MMU. If we have a kernel context, TLBIs are
> +	 * already global.
> +	 */
> +	if (mm)
> +		mm_context_add_copro(mm);
>   	/*
>   	 * Barrier is to make sure PE is visible in the SPA before it
>   	 * is used by the device. It also helps with the global TLBI
> @@ -546,7 +563,8 @@ int ocxl_link_add_pe(void *link_handle, int pasid, u32 pidr, u32 tidr,
>   	 * have a reference on mm_users. Incrementing mm_count solves
>   	 * the problem.
>   	 */
> -	mmgrab(mm);
> +	if (mm)
> +		mmgrab(mm);
>   	trace_ocxl_context_add(current->pid, spa->spa_mem, pasid, pidr, tidr);
>   unlock:
>   	mutex_unlock(&spa->spa_lock);
> @@ -652,8 +670,10 @@ int ocxl_link_remove_pe(void *link_handle, int pasid)
>   	if (!pe_data) {
>   		WARN(1, "Couldn't find pe data when removing PE\n");
>   	} else {
> -		mm_context_remove_copro(pe_data->mm);
> -		mmdrop(pe_data->mm);
> +		if (pe_data->mm) {
> +			mm_context_remove_copro(pe_data->mm);
> +			mmdrop(pe_data->mm);
> +		}
>   		kfree_rcu(pe_data, rcu);
>   	}
>   unlock:
> 

-- 
Andrew Donnellan              OzLabs, ADL Canberra
ajd@linux.ibm.com             IBM Australia Limited