Commit 70b565bb authored by Vaibhav Jain's avatar Vaibhav Jain Committed by Michael Ellerman
Browse files

cxl: Prevent adapter reset if an active context exists 



This patch prevents resetting the cxl adapter via sysfs in presence of
one or more active cxl_context on it. This protects against an
unrecoverable error caused by PSL owning a dirty cache line even after
reset and host tries to touch the same cache line. In case a force reset
of the card is required irrespective of any active contexts, the int
value -1 can be stored in the 'reset' sysfs attribute of the card.

The patch introduces a new atomic_t member named contexts_num inside
struct cxl that holds the number of active context attached to the card
, which is checked against '0' before proceeding with the reset. To
prevent against a race condition where a context is activated just after
reset check is performed, the contexts_num is atomically set to '-1'
after reset-check to indicate that no more contexts can be activated on
the card anymore.

Before activating a context we atomically test if contexts_num is
non-negative and if so, increment its value by one. In case the value of
contexts_num is negative then it indicates that the card is about to be
reset and context activation is error-ed out at that point.

Fixes: 62fa19d4 ("cxl: Add ability to reset the card")
Cc: stable@vger.kernel.org # v4.0+
Acked-by: default avatarFrederic Barrat <fbarrat@linux.vnet.ibm.com>
Reviewed-by: default avatarAndrew Donnellan <andrew.donnellan@au1.ibm.com>
Signed-off-by: default avatarVaibhav Jain <vaibhav@linux.vnet.ibm.com>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
parent 65bc3ece

Documentation/ABI/testing/sysfs-class-cxl

+5 −2
Original line number Diff line number Diff line
@@ -220,8 +220,11 @@ What: /sys/class/cxl/<card>/reset 
Date:           October 2014

Contact:        linuxppc-dev@lists.ozlabs.org

Description:    write only

                Writing 1 will issue a PERST to card which may cause the card

                to reload the FPGA depending on load_image_on_perst.

                Writing 1 will issue a PERST to card provided there are no

                contexts active on any one of the card AFUs. This may cause

                the card to reload the FPGA depending on load_image_on_perst.

                Writing -1 will do a force PERST irrespective of any active

                contexts on the card AFUs.

Users:		https://github.com/ibm-capi/libcxl



What:		/sys/class/cxl/<card>/perst_reloads_same_image (not in a guest)

drivers/misc/cxl/api.c

+9 −0
Original line number Diff line number Diff line
@@ -229,6 +229,14 @@ int cxl_start_context(struct cxl_context *ctx, u64 wed, 
	if (ctx->status == STARTED)

		goto out; /* already started */



	/*

	 * Increment the mapped context count for adapter. This also checks

	 * if adapter_context_lock is taken.

	 */

	rc = cxl_adapter_context_get(ctx->afu->adapter);

	if (rc)

		goto out;



	if (task) {

		ctx->pid = get_task_pid(task, PIDTYPE_PID);

		ctx->glpid = get_task_pid(task->group_leader, PIDTYPE_PID);
@@ -240,6 +248,7 @@ int cxl_start_context(struct cxl_context *ctx, u64 wed, 


	if ((rc = cxl_ops->attach_process(ctx, kernel, wed, 0))) {

		put_pid(ctx->pid);

		cxl_adapter_context_put(ctx->afu->adapter);

		cxl_ctx_put();

		goto out;

	}

drivers/misc/cxl/context.c

+3 −0
Original line number Diff line number Diff line
@@ -238,6 +238,9 @@ int __detach_context(struct cxl_context *ctx) 
	put_pid(ctx->glpid);



	cxl_ctx_put();



	/* Decrease the attached context count on the adapter */

	cxl_adapter_context_put(ctx->afu->adapter);

	return 0;

}

drivers/misc/cxl/cxl.h

+24 −0
Original line number Diff line number Diff line
@@ -618,6 +618,14 @@ struct cxl { 
	bool perst_select_user;

	bool perst_same_image;

	bool psl_timebase_synced;



	/*

	 * number of contexts mapped on to this card. Possible values are:

	 * >0: Number of contexts mapped and new one can be mapped.

	 *  0: No active contexts and new ones can be mapped.

	 * -1: No contexts mapped and new ones cannot be mapped.

	 */

	atomic_t contexts_num;

};



int cxl_pci_alloc_one_irq(struct cxl *adapter);
@@ -944,4 +952,20 @@ bool cxl_pci_is_vphb_device(struct pci_dev *dev); 


/* decode AFU error bits in the PSL register PSL_SERR_An */

void cxl_afu_decode_psl_serr(struct cxl_afu *afu, u64 serr);



/*

 * Increments the number of attached contexts on an adapter.

 * In case an adapter_context_lock is taken the return -EBUSY.

 */

int cxl_adapter_context_get(struct cxl *adapter);



/* Decrements the number of attached contexts on an adapter */

void cxl_adapter_context_put(struct cxl *adapter);



/* If no active contexts then prevents contexts from being attached */

int cxl_adapter_context_lock(struct cxl *adapter);



/* Unlock the contexts-lock if taken. Warn and force unlock otherwise */

void cxl_adapter_context_unlock(struct cxl *adapter);



#endif

drivers/misc/cxl/file.c

+11 −0
Original line number Diff line number Diff line
@@ -205,11 +205,22 @@ static long afu_ioctl_start_work(struct cxl_context *ctx, 
	ctx->pid = get_task_pid(current, PIDTYPE_PID);

	ctx->glpid = get_task_pid(current->group_leader, PIDTYPE_PID);



	/*

	 * Increment the mapped context count for adapter. This also checks

	 * if adapter_context_lock is taken.

	 */

	rc = cxl_adapter_context_get(ctx->afu->adapter);

	if (rc) {

		afu_release_irqs(ctx, ctx);

		goto out;

	}



	trace_cxl_attach(ctx, work.work_element_descriptor, work.num_interrupts, amr);



	if ((rc = cxl_ops->attach_process(ctx, false, work.work_element_descriptor,

							amr))) {

		afu_release_irqs(ctx, ctx);

		cxl_adapter_context_put(ctx->afu->adapter);

		goto out;

	}

CRA Git | Maintained and supported by SUSTech CRA and CCSE