4 files changed, 28 insertions, 2 deletions

diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index 1a138c83f877..a0c44d16bf30 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -336,6 +336,10 @@ int cxl_start_context(struct cxl_context *ctx, u64 wed,
 			mmput(ctx->mm);
 	}
 
+	/*
+	 * Increment driver use count. Enables global TLBIs for hash
+	 * and callbacks to handle the segment table
+	 */
 	cxl_ctx_get();
 
 	if ((rc = cxl_ops->attach_process(ctx, kernel, wed, 0))) {
diff --git a/drivers/misc/cxl/fault.c b/drivers/misc/cxl/fault.c
index 6eed7d03e2b5..f17f72ea0545 100644
--- a/drivers/misc/cxl/fault.c
+++ b/drivers/misc/cxl/fault.c
@@ -138,6 +138,22 @@ int cxl_handle_mm_fault(struct mm_struct *mm, u64 dsisr, u64 dar)
 	int result;
 	unsigned long access, flags, inv_flags = 0;
 
+	/*
+	 * Add the fault handling cpu to task mm cpumask so that we
+	 * can do a safe lockless page table walk when inserting the
+	 * hash page table entry. This function get called with a
+	 * valid mm for user space addresses. Hence using the if (mm)
+	 * check is sufficient here.
+	 */
+	if (mm && !cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm))) {
+		cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
+		/*
+		 * We need to make sure we walk the table only after
+		 * we update the cpumask. The other side of the barrier
+		 * is explained in serialize_against_pte_lookup()
+		 */
+		smp_mb();
+	}
 	if ((result = copro_handle_mm_fault(mm, dar, dsisr, &flt))) {
 		pr_devel("copro_handle_mm_fault failed: %#x\n", result);
 		return result;
diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c
index 0761271d68c5..4bfad9f6dc9f 100644
--- a/drivers/misc/cxl/file.c
+++ b/drivers/misc/cxl/file.c
@@ -95,7 +95,6 @@ static int __afu_open(struct inode *inode, struct file *file, bool master)
 
 	pr_devel("afu_open pe: %i\n", ctx->pe);
 	file->private_data = ctx;
-	cxl_ctx_get();
 
 	/* indicate success */
 	rc = 0;
@@ -225,6 +224,12 @@ static long afu_ioctl_start_work(struct cxl_context *ctx,
 	if (ctx->mm)
 		mmput(ctx->mm);
 
+	/*
+	 * Increment driver use count. Enables global TLBIs for hash
+	 * and callbacks to handle the segment table
+	 */
+	cxl_ctx_get();
+
 	trace_cxl_attach(ctx, work.work_element_descriptor, work.num_interrupts, amr);
 
 	if ((rc = cxl_ops->attach_process(ctx, false, work.work_element_descriptor,
@@ -233,6 +238,7 @@ static long afu_ioctl_start_work(struct cxl_context *ctx,
 		cxl_adapter_context_put(ctx->afu->adapter);
 		put_pid(ctx->pid);
 		ctx->pid = NULL;
+		cxl_ctx_put();
 		cxl_context_mm_count_put(ctx);
 		goto out;
 	}
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index d18b3d9292fd..3ba04f371380 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -1279,7 +1279,7 @@ ssize_t cxl_pci_afu_read_err_buffer(struct cxl_afu *afu, char *buf,
 	}
 
 	/* use bounce buffer for copy */
-	tbuf = (void *)__get_free_page(GFP_TEMPORARY);
+	tbuf = (void *)__get_free_page(GFP_KERNEL);
 	if (!tbuf)
 		return -ENOMEM;