RE: [PATCH v5 5/7] ocxl: Expose the thread_id needed for wait on POWER9

-----Original Message-----
From: Frederic Barrat <redacted>
Sent: Friday, 11 May 2018 7:25 PM
To: Alastair D'Silva <redacted>; =

linuxppc-dev@lists.ozlabs.org

Cc: linux-kernel@vger.kernel.org; linux-doc@vger.kernel.org;
mikey@neuling.org; vaibhav@linux.vnet.ibm.com;
aneesh.kumar@linux.vnet.ibm.com; malat@debian.org;
felix@linux.vnet.ibm.com; pombredanne@nexb.com;
sukadev@linux.vnet.ibm.com; npiggin@gmail.com;
gregkh@linuxfoundation.org; arnd@arndb.de;
andrew.donnellan@au1.ibm.com; fbarrat@linux.vnet.ibm.com;
corbet@lwn.net; Alastair D'Silva [off-list ref]
Subject: Re: [PATCH v5 5/7] ocxl: Expose the thread_id needed for wait =

on

POWER9
=20
=20
=20
Le 11/05/2018 =C3=A0 08:13, Alastair D'Silva a =C3=A9crit :

quoted

From: Alastair D'Silva <redacted>

In order to successfully issue as_notify, an AFU needs to know the =

TID

quoted

to notify, which in turn means that this information should be
available in userspace so it can be communicated to the AFU.

Signed-off-by: Alastair D'Silva <redacted>
---

=20
Ok, so we keep the limitation of having only one thread per context =

able to

call 'wait', even though we don't have to worry about depleting the =

pool of

TIDs any more. I think that's acceptable, though we don't really have =

a reason

to justify it any more. Any reason you want to keep it that way?
=20

No strong reason, just trying to minimise the amount of changes. We can =
always expand the scope later, if we have a use-case for it.

   Fred
=20
=20

quoted

  drivers/misc/ocxl/context.c       |  5 ++-
  drivers/misc/ocxl/file.c          | 53 =

+++++++++++++++++++++++++++++++

quoted

  drivers/misc/ocxl/link.c          | 36 +++++++++++++++++++++
  drivers/misc/ocxl/ocxl_internal.h |  1 +
  include/misc/ocxl.h               |  9 ++++++
  include/uapi/misc/ocxl.h          |  8 +++++
  6 files changed, 111 insertions(+), 1 deletion(-)

diff --git a/drivers/misc/ocxl/context.c =

b/drivers/misc/ocxl/context.c

quoted

index 909e8807824a..95f74623113e 100644

--- a/drivers/misc/ocxl/context.c
+++ b/drivers/misc/ocxl/context.c

@@ -34,6 +34,8 @@ int ocxl_context_init(struct ocxl_context *ctx, =

struct

ocxl_afu *afu,

quoted

  	mutex_init(&ctx->xsl_error_lock);
  	mutex_init(&ctx->irq_lock);
  	idr_init(&ctx->irq_idr);
+	ctx->tidr =3D 0;
+
  	/*
  	 * Keep a reference on the AFU to make sure it's valid for the
  	 * duration of the life of the context @@ -65,6 +67,7 @@ int
ocxl_context_attach(struct ocxl_context *ctx, u64 amr)
  {
  	int rc;

+	// Locks both status & tidr
  	mutex_lock(&ctx->status_mutex);
  	if (ctx->status !=3D OPENED) {
  		rc =3D -EIO;

@@ -72,7 +75,7 @@ int ocxl_context_attach(struct ocxl_context *ctx, =

u64

amr)

quoted

  	}

  	rc =3D ocxl_link_add_pe(ctx->afu->fn->link, ctx->pasid,
-			current->mm->context.id, 0, amr, current->mm,
+			current->mm->context.id, ctx->tidr, amr, current-
mm,
  			xsl_fault_error, ctx);
  	if (rc)
  		goto out;

diff --git a/drivers/misc/ocxl/file.c b/drivers/misc/ocxl/file.c =

index

quoted

038509e5d031..eb409a469f21 100644

--- a/drivers/misc/ocxl/file.c
+++ b/drivers/misc/ocxl/file.c

@@ -5,6 +5,8 @@
  #include <linux/sched/signal.h>
  #include <linux/uaccess.h>
  #include <uapi/misc/ocxl.h>
+#include <asm/reg.h>
+#include <asm/switch_to.h>
  #include "ocxl_internal.h"

@@ -123,11 +125,55 @@ static long afu_ioctl_get_metadata(struct

ocxl_context *ctx,

quoted

  	return 0;
  }

+#ifdef CONFIG_PPC64
+static long afu_ioctl_enable_p9_wait(struct ocxl_context *ctx,
+		struct ocxl_ioctl_p9_wait __user *uarg) {
+	struct ocxl_ioctl_p9_wait arg;
+
+	memset(&arg, 0, sizeof(arg));
+
+	if (cpu_has_feature(CPU_FTR_P9_TIDR)) {
+		enum ocxl_context_status status;
+
+		// Locks both status & tidr
+		mutex_lock(&ctx->status_mutex);
+		if (!ctx->tidr) {
+			if (set_thread_tidr(current))
+				return -ENOENT;
+
+			ctx->tidr =3D current->thread.tidr;
+		}
+
+		status =3D ctx->status;
+		mutex_unlock(&ctx->status_mutex);
+
+		if (status =3D=3D ATTACHED) {
+			int rc;
+			struct link *link =3D ctx->afu->fn->link;
+
+			rc =3D ocxl_link_update_pe(link, ctx->pasid, ctx->tidr);
+			if (rc)
+				return rc;
+		}
+
+		arg.thread_id =3D ctx->tidr;
+	} else
+		return -ENOENT;
+
+	if (copy_to_user(uarg, &arg, sizeof(arg)))
+		return -EFAULT;
+
+	return 0;
+}
+#endif
+
  #define CMD_STR(x) (x =3D=3D OCXL_IOCTL_ATTACH ? "ATTACH" :

		\

quoted

  			x =3D=3D OCXL_IOCTL_IRQ_ALLOC ? "IRQ_ALLOC" :	\
  			x =3D=3D OCXL_IOCTL_IRQ_FREE ? "IRQ_FREE" :

	\

quoted

  			x =3D=3D OCXL_IOCTL_IRQ_SET_FD ? "IRQ_SET_FD" :

	\

quoted

  			x =3D=3D OCXL_IOCTL_GET_METADATA ?

"GET_METADATA" :	\

quoted

+			x =3D=3D OCXL_IOCTL_ENABLE_P9_WAIT ?

"ENABLE_P9_WAIT" :	\

quoted

  			"UNKNOWN")

  static long afu_ioctl(struct file *file, unsigned int cmd, @@ =

-186,6

quoted

+232,13 @@ static long afu_ioctl(struct file *file, unsigned int =

cmd,

quoted

  				(struct ocxl_ioctl_metadata __user *) args);
  		break;

+#ifdef CONFIG_PPC64
+	case OCXL_IOCTL_ENABLE_P9_WAIT:
+		rc =3D afu_ioctl_enable_p9_wait(ctx,
+				(struct ocxl_ioctl_p9_wait __user *) args);
+		break;
+#endif
+
  	default:
  		rc =3D -EINVAL;
  	}

diff --git a/drivers/misc/ocxl/link.c b/drivers/misc/ocxl/link.c =

index

quoted

656e8610eec2..88876ae8f330 100644

--- a/drivers/misc/ocxl/link.c
+++ b/drivers/misc/ocxl/link.c

@@ -544,6 +544,42 @@ int ocxl_link_add_pe(void *link_handle, int =

pasid,

u32 pidr, u32 tidr,

quoted

  }
  EXPORT_SYMBOL_GPL(ocxl_link_add_pe);

+int ocxl_link_update_pe(void *link_handle, int pasid, __u16 tid) {
+	struct link *link =3D (struct link *) link_handle;
+	struct spa *spa =3D link->spa;
+	struct ocxl_process_element *pe;
+	int pe_handle, rc;
+
+	if (pasid > SPA_PASID_MAX)
+		return -EINVAL;
+
+	pe_handle =3D pasid & SPA_PE_MASK;
+	pe =3D spa->spa_mem + pe_handle;
+
+	mutex_lock(&spa->spa_lock);
+
+	pe->tid =3D tid;
+
+	/*
+	 * The barrier makes sure the PE is updated
+	 * before we clear the NPU context cache below, so that the
+	 * old PE cannot be reloaded erroneously.
+	 */
+	mb();
+
+	/*
+	 * hook to platform code
+	 * On powerpc, the entry needs to be cleared from the context
+	 * cache of the NPU.
+	 */
+	rc =3D pnv_ocxl_spa_remove_pe_from_cache(link->platform_data,

pe_handle);

quoted

+	WARN_ON(rc);
+
+	mutex_unlock(&spa->spa_lock);
+	return rc;
+}
+
  int ocxl_link_remove_pe(void *link_handle, int pasid)
  {
  	struct link *link =3D (struct link *) link_handle; diff --git
a/drivers/misc/ocxl/ocxl_internal.h
b/drivers/misc/ocxl/ocxl_internal.h
index 5d421824afd9..a32f2151029f 100644

--- a/drivers/misc/ocxl/ocxl_internal.h
+++ b/drivers/misc/ocxl/ocxl_internal.h

@@ -77,6 +77,7 @@ struct ocxl_context {
  	struct ocxl_xsl_error xsl_error;
  	struct mutex irq_lock;
  	struct idr irq_idr;
+	u16 tidr; // Thread ID used for P9 wait implementation
  };

  struct ocxl_process_element {

diff --git a/include/misc/ocxl.h b/include/misc/ocxl.h index

51ccf76db293..9ff6ddc28e22 100644

--- a/include/misc/ocxl.h
+++ b/include/misc/ocxl.h

@@ -188,6 +188,15 @@ extern int ocxl_link_add_pe(void *link_handle, =

int

pasid, u32 pidr, u32 tidr,

quoted

  		void (*xsl_err_cb)(void *data, u64 addr, u64 dsisr),
  		void *xsl_err_data);

+/**
+ * Update values within a Process Element
+ *
+ * link_handle: the link handle associated with the process element
+ * pasid: the PASID for the AFU context
+ * tid: the new thread id for the process element  */ extern int
+ocxl_link_update_pe(void *link_handle, int pasid, __u16 tid);
+
  /*
   * Remove a Process Element from the Shared Process Area for a =

link

quoted

   */

diff --git a/include/uapi/misc/ocxl.h b/include/uapi/misc/ocxl.h =

index

quoted

0af83d80fb3e..561e6f0dfcb7 100644

--- a/include/uapi/misc/ocxl.h
+++ b/include/uapi/misc/ocxl.h

@@ -48,6 +48,13 @@ struct ocxl_ioctl_metadata {
  	__u64 reserved[13]; // Total of 16*u64
  };

+struct ocxl_ioctl_p9_wait {
+	__u16 thread_id; // The thread ID required to wake this thread
+	__u16 reserved1;
+	__u32 reserved2;
+	__u64 reserved3[3];
+};
+
  struct ocxl_ioctl_irq_fd {
  	__u64 irq_offset;
  	__s32 eventfd;

@@ -62,5 +69,6 @@ struct ocxl_ioctl_irq_fd {
  #define OCXL_IOCTL_IRQ_FREE	_IOW(OCXL_MAGIC, 0x12, __u64)
  #define OCXL_IOCTL_IRQ_SET_FD	_IOW(OCXL_MAGIC, 0x13, struct

ocxl_ioctl_irq_fd)

quoted

  #define OCXL_IOCTL_GET_METADATA _IOR(OCXL_MAGIC, 0x14, struct
ocxl_ioctl_metadata)
+#define OCXL_IOCTL_ENABLE_P9_WAIT	_IOR(OCXL_MAGIC, 0x15,

struct ocxl_ioctl_p9_wait)

quoted

  #endif /* _UAPI_MISC_OCXL_H */

=20
=20
---
This email has been checked for viruses by AVG.
http://www.avg.com