cxl: Add kernel API to allow a context to operate with relocate disabled

cxl devices typically access memory using an MMU in much the same way as
the CPU, and each context includes a state register much like the MSR in
the CPU. Like the CPU, the state register includes a bit to enable
relocation, which we currently always enable.

In some cases, it may be desirable to allow a device to access memory
using real addresses instead of effective addresses, so this adds a new
API, cxl_set_translation_mode, that can be used to disable relocation
on a given kernel context. This can allow for the creation of a special
privileged context that the device can use if it needs relocation
disabled, and can use regular contexts at times when it needs relocation
enabled.

This interface is only available to users of the kernel API for obvious
reasons, and will never be supported in a virtualised environment.

This will be used by the upcoming cxl support in the mlx5 driver.

Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

5 files changed, 34 insertions, 2 deletions

diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index 8075823..6d228cc 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -183,6 +183,7 @@ int cxl_start_context(struct cxl_context *ctx, u64 wed,
 		ctx->pid = get_task_pid(task, PIDTYPE_PID);
 		ctx->glpid = get_task_pid(task->group_leader, PIDTYPE_PID);
 		kernel = false;
+		ctx->real_mode = false;
 	}
 
 	cxl_ctx_get();
@@ -219,6 +220,24 @@ void cxl_set_master(struct cxl_context *ctx)
 }
 EXPORT_SYMBOL_GPL(cxl_set_master);
 
+int cxl_set_translation_mode(struct cxl_context *ctx, bool real_mode)
+{
+	if (ctx->status == STARTED) {
+		/*
+		 * We could potentially update the PE and issue an update LLCMD
+		 * to support this, but it doesn't seem to have a good use case
+		 * since it's trivial to just create a second kernel context
+		 * with different translation modes, so until someone convinces
+		 * me otherwise:
+		 */
+		return -EBUSY;
+	}
+
+	ctx->real_mode = real_mode;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cxl_set_translation_mode);
+
 /* wrappers around afu_* file ops which are EXPORTED */
 int cxl_fd_open(struct inode *inode, struct file *file)
 {
diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index 2823fb3..9dd3a0e 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -514,6 +514,7 @@ struct cxl_context {
 	bool pe_inserted;
 	bool master;
 	bool kernel;
+	bool real_mode;
 	bool pending_irq;
 	bool pending_fault;
 	bool pending_afu_err;
diff --git a/drivers/misc/cxl/guest.c b/drivers/misc/cxl/guest.c
index 769971c..c2815b9 100644
--- a/drivers/misc/cxl/guest.c
+++ b/drivers/misc/cxl/guest.c
@@ -617,6 +617,9 @@ static int guest_attach_process(struct cxl_context *ctx, bool kernel, u64 wed, u
 {
 	pr_devel("in %s\n", __func__);
 
+	if (ctx->real_mode)
+		return -EPERM;
+
 	ctx->kernel = kernel;
 	if (ctx->afu->current_mode == CXL_MODE_DIRECTED)
 		return attach_afu_directed(ctx, wed, amr);
diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c
index 5d4fb9f..98f2cac 100644
--- a/drivers/misc/cxl/native.c
+++ b/drivers/misc/cxl/native.c
@@ -494,8 +494,9 @@ static u64 calculate_sr(struct cxl_context *ctx)
 	if (mfspr(SPRN_LPCR) & LPCR_TC)
 		sr |= CXL_PSL_SR_An_TC;
 	if (ctx->kernel) {
-		sr |= CXL_PSL_SR_An_R | (mfmsr() & MSR_SF);
-		sr |= CXL_PSL_SR_An_HV;
+		if (!ctx->real_mode)
+			sr |= CXL_PSL_SR_An_R;
+		sr |= (mfmsr() & MSR_SF) | CXL_PSL_SR_An_HV;
 	} else {
 		sr |= CXL_PSL_SR_An_PR | CXL_PSL_SR_An_R;
 		sr &= ~(CXL_PSL_SR_An_HV);
diff --git a/include/misc/cxl.h b/include/misc/cxl.h
index 7d5e261..56560c5 100644
--- a/include/misc/cxl.h
+++ b/include/misc/cxl.h
@@ -127,6 +127,14 @@ int cxl_afu_reset(struct cxl_context *ctx);
 void cxl_set_master(struct cxl_context *ctx);
 
 /*
+ * Sets the context to use real mode memory accesses to operate with
+ * translation disabled. Note that this only makes sense for kernel contexts
+ * under bare metal, and will not work with virtualisation. May only be
+ * performed on stopped contexts.
+ */
+int cxl_set_translation_mode(struct cxl_context *ctx, bool real_mode);
+
+/*
  * Map and unmap the AFU Problem Space area. The amount and location mapped
  * depends on if this context is a master or slave.
  */