Merge tag 'powerpc-5.2-1' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Slightly delayed due to the issue with printk() calling
  probe_kernel_read() interacting with our new user access prevention
  stuff, but all fixed now.

  The only out-of-area changes are the addition of a cpuhp_state, small
  additions to Documentation and MAINTAINERS updates.

  Highlights:

   - Support for Kernel Userspace Access/Execution Prevention (like
     SMAP/SMEP/PAN/PXN) on some 64-bit and 32-bit CPUs. This prevents
     the kernel from accidentally accessing userspace outside
     copy_to/from_user(), or ever executing userspace.

   - KASAN support on 32-bit.

   - Rework of where we map the kernel, vmalloc, etc. on 64-bit hash to
     use the same address ranges we use with the Radix MMU.

   - A rewrite into C of large parts of our idle handling code for
     64-bit Book3S (ie. power8 & power9).

   - A fast path entry for syscalls on 32-bit CPUs, for a 12-17% speedup
     in the null_syscall benchmark.

   - On 64-bit bare metal we have support for recovering from errors
     with the time base (our clocksource), however if that fails
     currently we hang in __delay() and never crash. We now have support
     for detecting that case and short circuiting __delay() so we at
     least panic() and reboot.

   - Add support for optionally enabling the DAWR on Power9, which had
     to be disabled by default due to a hardware erratum. This has the
     effect of enabling hardware breakpoints for GDB, the downside is a
     badly behaved program could crash the machine by pointing the DAWR
     at cache inhibited memory. This is opt-in obviously.

   - xmon, our crash handler, gets support for a read only mode where
     operations that could change memory or otherwise disturb the system
     are disabled.

  Plus many clean-ups, reworks and minor fixes etc.

  Thanks to: Christophe Leroy, Akshay Adiga, Alastair D'Silva, Alexey
  Kardashevskiy, Andrew Donnellan, Aneesh Kumar K.V, Anju T Sudhakar,
  Anton Blanchard, Ben Hutchings, Bo YU, Breno Leitao, Cédric Le Goater,
  Christopher M. Riedl, Christoph Hellwig, Colin Ian King, David Gibson,
  Ganesh Goudar, Gautham R. Shenoy, George Spelvin, Greg Kroah-Hartman,
  Greg Kurz, Horia Geantă, Jagadeesh Pagadala, Joel Stanley, Joe
  Perches, Julia Lawall, Laurentiu Tudor, Laurent Vivier, Lukas Bulwahn,
  Madhavan Srinivasan, Mahesh Salgaonkar, Mathieu Malaterre, Michael
  Neuling, Mukesh Ojha, Nathan Fontenot, Nathan Lynch, Nicholas Piggin,
  Nick Desaulniers, Oliver O'Halloran, Peng Hao, Qian Cai, Ravi
  Bangoria, Rick Lindsley, Russell Currey, Sachin Sant, Stewart Smith,
  Sukadev Bhattiprolu, Thomas Huth, Tobin C. Harding, Tyrel Datwyler,
  Valentin Schneider, Wei Yongjun, Wen Yang, YueHaibing"

* tag 'powerpc-5.2-1' of ssh://gitolite.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (205 commits)
  powerpc/64s: Use early_mmu_has_feature() in set_kuap()
  powerpc/book3s/64: check for NULL pointer in pgd_alloc()
  powerpc/mm: Fix hugetlb page initialization
  ocxl: Fix return value check in afu_ioctl()
  powerpc/mm: fix section mismatch for setup_kup()
  powerpc/mm: fix redundant inclusion of pgtable-frag.o in Makefile
  powerpc/mm: Fix makefile for KASAN
  powerpc/kasan: add missing/lost Makefile
  selftests/powerpc: Add a signal fuzzer selftest
  powerpc/booke64: set RI in default MSR
  ocxl: Provide global MMIO accessors for external drivers
  ocxl: move event_fd handling to frontend
  ocxl: afu_irq only deals with IRQ IDs, not offsets
  ocxl: Allow external drivers to use OpenCAPI contexts
  ocxl: Create a clear delineation between ocxl backend & frontend
  ocxl: Don't pass pci_dev around
  ocxl: Split pci.c
  ocxl: Remove some unused exported symbols
  ocxl: Remove superfluous 'extern' from headers
  ocxl: read_pasid never returns an error, so make it void
  ...

13 files changed, 1150 insertions, 758 deletions

diff --git a/drivers/misc/cxl/fault.c b/drivers/misc/cxl/fault.c
index dc7b34174f85..a4d17a5a9763 100644
--- a/drivers/misc/cxl/fault.c
+++ b/drivers/misc/cxl/fault.c
@@ -168,7 +168,7 @@ int cxl_handle_mm_fault(struct mm_struct *mm, u64 dsisr, u64 dar)
 		if (dsisr & CXL_PSL_DSISR_An_S)
 			access |= _PAGE_WRITE;
 
-		if (!mm && (REGION_ID(dar) != USER_REGION_ID))
+		if (!mm && (get_region_id(dar) != USER_REGION_ID))
 			access |= _PAGE_PRIVILEGED;
 
 		if (dsisr & DSISR_NOHPTE)
diff --git a/drivers/misc/ocxl/Makefile b/drivers/misc/ocxl/Makefile
index 5229dcda8297..d07d1bb8e8d4 100644
--- a/drivers/misc/ocxl/Makefile
+++ b/drivers/misc/ocxl/Makefile
@@ -1,8 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0+
 ccflags-$(CONFIG_PPC_WERROR)	+= -Werror
 
-ocxl-y				+= main.o pci.o config.o file.o pasid.o
+ocxl-y				+= main.o pci.o config.o file.o pasid.o mmio.o
 ocxl-y				+= link.o context.o afu_irq.o sysfs.o trace.o
+ocxl-y				+= core.o
 obj-$(CONFIG_OCXL)		+= ocxl.o
 
 # For tracepoints to include our trace.h from tracepoint infrastructure:
diff --git a/drivers/misc/ocxl/afu_irq.c b/drivers/misc/ocxl/afu_irq.c
index 11ab996657a2..70f8f1c3929d 100644
--- a/drivers/misc/ocxl/afu_irq.c
+++ b/drivers/misc/ocxl/afu_irq.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0+
 // Copyright 2017 IBM Corp.
 #include <linux/interrupt.h>
-#include <linux/eventfd.h>
+#include <asm/pnv-ocxl.h>
 #include "ocxl_internal.h"
 #include "trace.h"
 
@@ -11,27 +11,59 @@ struct afu_irq {
 	unsigned int virq;
 	char *name;
 	u64 trigger_page;
-	struct eventfd_ctx *ev_ctx;
+	irqreturn_t (*handler)(void *private);
+	void (*free_private)(void *private);
+	void *private;
 };
 
-static int irq_offset_to_id(struct ocxl_context *ctx, u64 offset)
+int ocxl_irq_offset_to_id(struct ocxl_context *ctx, u64 offset)
 {
 	return (offset - ctx->afu->irq_base_offset) >> PAGE_SHIFT;
 }
 
-static u64 irq_id_to_offset(struct ocxl_context *ctx, int id)
+u64 ocxl_irq_id_to_offset(struct ocxl_context *ctx, int irq_id)
 {
-	return ctx->afu->irq_base_offset + (id << PAGE_SHIFT);
+	return ctx->afu->irq_base_offset + (irq_id << PAGE_SHIFT);
 }
 
+int ocxl_irq_set_handler(struct ocxl_context *ctx, int irq_id,
+		irqreturn_t (*handler)(void *private),
+		void (*free_private)(void *private),
+		void *private)
+{
+	struct afu_irq *irq;
+	int rc;
+
+	mutex_lock(&ctx->irq_lock);
+	irq = idr_find(&ctx->irq_idr, irq_id);
+	if (!irq) {
+		rc = -EINVAL;
+		goto unlock;
+	}
+
+	irq->handler = handler;
+	irq->private = private;
+	irq->free_private = free_private;
+
+	rc = 0;
+	// Fall through to unlock
+
+unlock:
+	mutex_unlock(&ctx->irq_lock);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(ocxl_irq_set_handler);
+
 static irqreturn_t afu_irq_handler(int virq, void *data)
 {
 	struct afu_irq *irq = (struct afu_irq *) data;
 
 	trace_ocxl_afu_irq_receive(virq);
-	if (irq->ev_ctx)
-		eventfd_signal(irq->ev_ctx, 1);
-	return IRQ_HANDLED;
+
+	if (irq->handler)
+		return irq->handler(irq->private);
+
+	return IRQ_HANDLED; // Just drop it on the ground
 }
 
 static int setup_afu_irq(struct ocxl_context *ctx, struct afu_irq *irq)
@@ -69,7 +101,7 @@ static void release_afu_irq(struct afu_irq *irq)
 	kfree(irq->name);
 }
 
-int ocxl_afu_irq_alloc(struct ocxl_context *ctx, u64 *irq_offset)
+int ocxl_afu_irq_alloc(struct ocxl_context *ctx, int *irq_id)
 {
 	struct afu_irq *irq;
 	int rc;
@@ -101,11 +133,11 @@ int ocxl_afu_irq_alloc(struct ocxl_context *ctx, u64 *irq_offset)
 	if (rc)
 		goto err_alloc;
 
-	*irq_offset = irq_id_to_offset(ctx, irq->id);
-
-	trace_ocxl_afu_irq_alloc(ctx->pasid, irq->id, irq->virq, irq->hw_irq,
-				*irq_offset);
+	trace_ocxl_afu_irq_alloc(ctx->pasid, irq->id, irq->virq, irq->hw_irq);
 	mutex_unlock(&ctx->irq_lock);
+
+	*irq_id = irq->id;
+
 	return 0;
 
 err_alloc:
@@ -117,29 +149,29 @@ err_unlock:
 	kfree(irq);
 	return rc;
 }
+EXPORT_SYMBOL_GPL(ocxl_afu_irq_alloc);
 
 static void afu_irq_free(struct afu_irq *irq, struct ocxl_context *ctx)
 {
 	trace_ocxl_afu_irq_free(ctx->pasid, irq->id);
 	if (ctx->mapping)
 		unmap_mapping_range(ctx->mapping,
-				irq_id_to_offset(ctx, irq->id),
+				ocxl_irq_id_to_offset(ctx, irq->id),
 				1 << PAGE_SHIFT, 1);
 	release_afu_irq(irq);
-	if (irq->ev_ctx)
-		eventfd_ctx_put(irq->ev_ctx);
+	if (irq->free_private)
+		irq->free_private(irq->private);
 	ocxl_link_free_irq(ctx->afu->fn->link, irq->hw_irq);
 	kfree(irq);
 }
 
-int ocxl_afu_irq_free(struct ocxl_context *ctx, u64 irq_offset)
+int ocxl_afu_irq_free(struct ocxl_context *ctx, int irq_id)
 {
 	struct afu_irq *irq;
-	int id = irq_offset_to_id(ctx, irq_offset);
 
 	mutex_lock(&ctx->irq_lock);
 
-	irq = idr_find(&ctx->irq_idr, id);
+	irq = idr_find(&ctx->irq_idr, irq_id);
 	if (!irq) {
 		mutex_unlock(&ctx->irq_lock);
 		return -EINVAL;
@@ -149,6 +181,7 @@ int ocxl_afu_irq_free(struct ocxl_context *ctx, u64 irq_offset)
 	mutex_unlock(&ctx->irq_lock);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(ocxl_afu_irq_free);
 
 void ocxl_afu_irq_free_all(struct ocxl_context *ctx)
 {
@@ -161,41 +194,16 @@ void ocxl_afu_irq_free_all(struct ocxl_context *ctx)
 	mutex_unlock(&ctx->irq_lock);
 }
 
-int ocxl_afu_irq_set_fd(struct ocxl_context *ctx, u64 irq_offset, int eventfd)
-{
-	struct afu_irq *irq;
-	struct eventfd_ctx *ev_ctx;
-	int rc = 0, id = irq_offset_to_id(ctx, irq_offset);
-
-	mutex_lock(&ctx->irq_lock);
-	irq = idr_find(&ctx->irq_idr, id);
-	if (!irq) {
-		rc = -EINVAL;
-		goto unlock;
-	}
-
-	ev_ctx = eventfd_ctx_fdget(eventfd);
-	if (IS_ERR(ev_ctx)) {
-		rc = -EINVAL;
-		goto unlock;
-	}
-
-	irq->ev_ctx = ev_ctx;
-unlock:
-	mutex_unlock(&ctx->irq_lock);
-	return rc;
-}
-
-u64 ocxl_afu_irq_get_addr(struct ocxl_context *ctx, u64 irq_offset)
+u64 ocxl_afu_irq_get_addr(struct ocxl_context *ctx, int irq_id)
 {
 	struct afu_irq *irq;
-	int id = irq_offset_to_id(ctx, irq_offset);
 	u64 addr = 0;
 
 	mutex_lock(&ctx->irq_lock);
-	irq = idr_find(&ctx->irq_idr, id);
+	irq = idr_find(&ctx->irq_idr, irq_id);
 	if (irq)
 		addr = irq->trigger_page;
 	mutex_unlock(&ctx->irq_lock);
 	return addr;
 }
+EXPORT_SYMBOL_GPL(ocxl_afu_irq_get_addr);
diff --git a/drivers/misc/ocxl/config.c b/drivers/misc/ocxl/config.c
index 8f2c5d8bd2ee..5e65acb8e134 100644
--- a/drivers/misc/ocxl/config.c
+++ b/drivers/misc/ocxl/config.c
@@ -2,8 +2,8 @@
 // Copyright 2017 IBM Corp.
 #include <linux/pci.h>
 #include <asm/pnv-ocxl.h>
-#include <misc/ocxl.h>
 #include <misc/ocxl-config.h>
+#include "ocxl_internal.h"
 
 #define EXTRACT_BIT(val, bit) (!!(val & BIT(bit)))
 #define EXTRACT_BITS(val, s, e) ((val & GENMASK(e, s)) >> s)
@@ -68,7 +68,7 @@ static int find_dvsec_afu_ctrl(struct pci_dev *dev, u8 afu_idx)
 	return 0;
 }
 
-static int read_pasid(struct pci_dev *dev, struct ocxl_fn_config *fn)
+static void read_pasid(struct pci_dev *dev, struct ocxl_fn_config *fn)
 {
 	u16 val;
 	int pos;
@@ -89,7 +89,6 @@ static int read_pasid(struct pci_dev *dev, struct ocxl_fn_config *fn)
 out:
 	dev_dbg(&dev->dev, "PASID capability:\n");
 	dev_dbg(&dev->dev, "  Max PASID log = %d\n", fn->max_pasid_log);
-	return 0;
 }
 
 static int read_dvsec_tl(struct pci_dev *dev, struct ocxl_fn_config *fn)
@@ -205,11 +204,7 @@ int ocxl_config_read_function(struct pci_dev *dev, struct ocxl_fn_config *fn)
 {
 	int rc;
 
-	rc = read_pasid(dev, fn);
-	if (rc) {
-		dev_err(&dev->dev, "Invalid PASID configuration: %d\n", rc);
-		return -ENODEV;
-	}
+	read_pasid(dev, fn);
 
 	rc = read_dvsec_tl(dev, fn);
 	if (rc) {
@@ -304,7 +299,6 @@ int ocxl_config_check_afu_index(struct pci_dev *dev,
 	}
 	return 1;
 }
-EXPORT_SYMBOL_GPL(ocxl_config_check_afu_index);
 
 static int read_afu_name(struct pci_dev *dev, struct ocxl_fn_config *fn,
 			struct ocxl_afu_config *afu)
@@ -540,7 +534,6 @@ int ocxl_config_get_pasid_info(struct pci_dev *dev, int *count)
 {
 	return pnv_ocxl_get_pasid_count(dev, count);
 }
-EXPORT_SYMBOL_GPL(ocxl_config_get_pasid_info);
 
 void ocxl_config_set_afu_pasid(struct pci_dev *dev, int pos, int pasid_base,
 			u32 pasid_count_log)
diff --git a/drivers/misc/ocxl/context.c b/drivers/misc/ocxl/context.c
index c10a940e3b38..bab9c9364184 100644
--- a/drivers/misc/ocxl/context.c
+++ b/drivers/misc/ocxl/context.c
@@ -4,15 +4,17 @@
 #include "trace.h"
 #include "ocxl_internal.h"
 
-struct ocxl_context *ocxl_context_alloc(void)
-{
-	return kzalloc(sizeof(struct ocxl_context), GFP_KERNEL);
-}
-
-int ocxl_context_init(struct ocxl_context *ctx, struct ocxl_afu *afu,
+int ocxl_context_alloc(struct ocxl_context **context, struct ocxl_afu *afu,
 		struct address_space *mapping)
 {
 	int pasid;
+	struct ocxl_context *ctx;
+
+	*context = kzalloc(sizeof(struct ocxl_context), GFP_KERNEL);
+	if (!*context)
+		return -ENOMEM;
+
+	ctx = *context;
 
 	ctx->afu = afu;
 	mutex_lock(&afu->contexts_lock);
@@ -43,6 +45,7 @@ int ocxl_context_init(struct ocxl_context *ctx, struct ocxl_afu *afu,
 	ocxl_afu_get(afu);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(ocxl_context_alloc);
 
 /*
  * Callback for when a translation fault triggers an error
@@ -63,7 +66,7 @@ static void xsl_fault_error(void *data, u64 addr, u64 dsisr)
 	wake_up_all(&ctx->events_wq);
 }
 
-int ocxl_context_attach(struct ocxl_context *ctx, u64 amr)
+int ocxl_context_attach(struct ocxl_context *ctx, u64 amr, struct mm_struct *mm)
 {
 	int rc;
 
@@ -75,7 +78,7 @@ int ocxl_context_attach(struct ocxl_context *ctx, u64 amr)
 	}
 
 	rc = ocxl_link_add_pe(ctx->afu->fn->link, ctx->pasid,
-			current->mm->context.id, ctx->tidr, amr, current->mm,
+			mm->context.id, ctx->tidr, amr, mm,
 			xsl_fault_error, ctx);
 	if (rc)
 		goto out;
@@ -85,13 +88,15 @@ out:
 	mutex_unlock(&ctx->status_mutex);
 	return rc;
 }
+EXPORT_SYMBOL_GPL(ocxl_context_attach);
 
 static vm_fault_t map_afu_irq(struct vm_area_struct *vma, unsigned long address,
 		u64 offset, struct ocxl_context *ctx)
 {
 	u64 trigger_addr;
+	int irq_id = ocxl_irq_offset_to_id(ctx, offset);
 
-	trigger_addr = ocxl_afu_irq_get_addr(ctx, offset);
+	trigger_addr = ocxl_afu_irq_get_addr(ctx, irq_id);
 	if (!trigger_addr)
 		return VM_FAULT_SIGBUS;
 
@@ -151,12 +156,14 @@ static const struct vm_operations_struct ocxl_vmops = {
 static int check_mmap_afu_irq(struct ocxl_context *ctx,
 			struct vm_area_struct *vma)
 {
+	int irq_id = ocxl_irq_offset_to_id(ctx, vma->vm_pgoff << PAGE_SHIFT);
+
 	/* only one page */
 	if (vma_pages(vma) != 1)
 		return -EINVAL;
 
 	/* check offset validty */
-	if (!ocxl_afu_irq_get_addr(ctx, vma->vm_pgoff << PAGE_SHIFT))
+	if (!ocxl_afu_irq_get_addr(ctx, irq_id))
 		return -EINVAL;
 
 	/*
@@ -238,11 +245,12 @@ int ocxl_context_detach(struct ocxl_context *ctx)
 	}
 	rc = ocxl_link_remove_pe(ctx->afu->fn->link, ctx->pasid);
 	if (rc) {
-		dev_warn(&ctx->afu->dev,
+		dev_warn(&dev->dev,
 			"Couldn't remove PE entry cleanly: %d\n", rc);
 	}
 	return 0;
 }
+EXPORT_SYMBOL_GPL(ocxl_context_detach);
 
 void ocxl_context_detach_all(struct ocxl_afu *afu)
 {
@@ -280,3 +288,4 @@ void ocxl_context_free(struct ocxl_context *ctx)
 	ocxl_afu_put(ctx->afu);
 	kfree(ctx);
 }
+EXPORT_SYMBOL_GPL(ocxl_context_free);
diff --git a/drivers/misc/ocxl/core.c b/drivers/misc/ocxl/core.c
new file mode 100644
index 000000000000..b7a09b21ab36
--- /dev/null
+++ b/drivers/misc/ocxl/core.c
@@ -0,0 +1,574 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright 2019 IBM Corp.
+#include <linux/idr.h>
+#include "ocxl_internal.h"
+
+static struct ocxl_fn *ocxl_fn_get(struct ocxl_fn *fn)
+{
+	return (get_device(&fn->dev) == NULL) ? NULL : fn;
+}
+
+static void ocxl_fn_put(struct ocxl_fn *fn)
+{
+	put_device(&fn->dev);
+}
+
+static struct ocxl_afu *alloc_afu(struct ocxl_fn *fn)
+{
+	struct ocxl_afu *afu;
+
+	afu = kzalloc(sizeof(struct ocxl_afu), GFP_KERNEL);
+	if (!afu)
+		return NULL;
+
+	kref_init(&afu->kref);
+	mutex_init(&afu->contexts_lock);
+	mutex_init(&afu->afu_control_lock);
+	idr_init(&afu->contexts_idr);
+	afu->fn = fn;
+	ocxl_fn_get(fn);
+	return afu;
+}
+
+static void free_afu(struct kref *kref)
+{
+	struct ocxl_afu *afu = container_of(kref, struct ocxl_afu, kref);
+
+	idr_destroy(&afu->contexts_idr);
+	ocxl_fn_put(afu->fn);
+	kfree(afu);
+}
+
+void ocxl_afu_get(struct ocxl_afu *afu)
+{
+	kref_get(&afu->kref);
+}
+EXPORT_SYMBOL_GPL(ocxl_afu_get);
+
+void ocxl_afu_put(struct ocxl_afu *afu)
+{
+	kref_put(&afu->kref, free_afu);
+}
+EXPORT_SYMBOL_GPL(ocxl_afu_put);
+
+static int assign_afu_actag(struct ocxl_afu *afu)
+{
+	struct ocxl_fn *fn = afu->fn;
+	int actag_count, actag_offset;
+	struct pci_dev *pci_dev = to_pci_dev(fn->dev.parent);
+
+	/*
+	 * if there were not enough actags for the function, each afu
+	 * reduces its count as well
+	 */
+	actag_count = afu->config.actag_supported *
+		fn->actag_enabled / fn->actag_supported;
+	actag_offset = ocxl_actag_afu_alloc(fn, actag_count);
+	if (actag_offset < 0) {
+		dev_err(&pci_dev->dev, "Can't allocate %d actags for AFU: %d\n",
+			actag_count, actag_offset);
+		return actag_offset;
+	}
+	afu->actag_base = fn->actag_base + actag_offset;
+	afu->actag_enabled = actag_count;
+
+	ocxl_config_set_afu_actag(pci_dev, afu->config.dvsec_afu_control_pos,
+				afu->actag_base, afu->actag_enabled);
+	dev_dbg(&pci_dev->dev, "actag base=%d enabled=%d\n",
+		afu->actag_base, afu->actag_enabled);
+	return 0;
+}
+
+static void reclaim_afu_actag(struct ocxl_afu *afu)
+{
+	struct ocxl_fn *fn = afu->fn;
+	int start_offset, size;
+
+	start_offset = afu->actag_base - fn->actag_base;
+	size = afu->actag_enabled;
+	ocxl_actag_afu_free(afu->fn, start_offset, size);
+}
+
+static int assign_afu_pasid(struct ocxl_afu *afu)
+{
+	struct ocxl_fn *fn = afu->fn;
+	int pasid_count, pasid_offset;
+	struct pci_dev *pci_dev = to_pci_dev(fn->dev.parent);
+
+	/*
+	 * We only support the case where the function configuration
+	 * requested enough PASIDs to cover all AFUs.
+	 */
+	pasid_count = 1 << afu->config.pasid_supported_log;
+	pasid_offset = ocxl_pasid_afu_alloc(fn, pasid_count);
+	if (pasid_offset < 0) {
+		dev_err(&pci_dev->dev, "Can't allocate %d PASIDs for AFU: %d\n",
+			pasid_count, pasid_offset);
+		return pasid_offset;
+	}
+	afu->pasid_base = fn->pasid_base + pasid_offset;
+	afu->pasid_count = 0;
+	afu->pasid_max = pasid_count;
+
+	ocxl_config_set_afu_pasid(pci_dev, afu->config.dvsec_afu_control_pos,
+				afu->pasid_base,
+				afu->config.pasid_supported_log);
+	dev_dbg(&pci_dev->dev, "PASID base=%d, enabled=%d\n",
+		afu->pasid_base, pasid_count);
+	return 0;
+}
+
+static void reclaim_afu_pasid(struct ocxl_afu *afu)
+{
+	struct ocxl_fn *fn = afu->fn;
+	int start_offset, size;
+
+	start_offset = afu->pasid_base - fn->pasid_base;
+	size = 1 << afu->config.pasid_supported_log;
+	ocxl_pasid_afu_free(afu->fn, start_offset, size);
+}
+
+static int reserve_fn_bar(struct ocxl_fn *fn, int bar)
+{
+	struct pci_dev *dev = to_pci_dev(fn->dev.parent);
+	int rc, idx;
+
+	if (bar != 0 && bar != 2 && bar != 4)
+		return -EINVAL;
+
+	idx = bar >> 1;
+	if (fn->bar_used[idx]++ == 0) {
+		rc = pci_request_region(dev, bar, "ocxl");
+		if (rc)
+			return rc;
+	}
+	return 0;
+}
+
+static void release_fn_bar(struct ocxl_fn *fn, int bar)
+{
+	struct pci_dev *dev = to_pci_dev(fn->dev.parent);
+	int idx;
+
+	if (bar != 0 && bar != 2 && bar != 4)
+		return;
+
+	idx = bar >> 1;
+	if (--fn->bar_used[idx] == 0)
+		pci_release_region(dev, bar);
+	WARN_ON(fn->bar_used[idx] < 0);
+}
+
+static int map_mmio_areas(struct ocxl_afu *afu)
+{
+	int rc;
+	struct pci_dev *pci_dev = to_pci_dev(afu->fn->dev.parent);
+
+	rc = reserve_fn_bar(afu->fn, afu->config.global_mmio_bar);
+	if (rc)
+		return rc;
+
+	rc = reserve_fn_bar(afu->fn, afu->config.pp_mmio_bar);
+	if (rc) {
+		release_fn_bar(afu->fn, afu->config.global_mmio_bar);
+		return rc;
+	}
+
+	afu->global_mmio_start =
+		pci_resource_start(pci_dev, afu->config.global_mmio_bar) +
+		afu->config.global_mmio_offset;
+	afu->pp_mmio_start =
+		pci_resource_start(pci_dev, afu->config.pp_mmio_bar) +
+		afu->config.pp_mmio_offset;
+
+	afu->global_mmio_ptr = ioremap(afu->global_mmio_start,
+				afu->config.global_mmio_size);
+	if (!afu->global_mmio_ptr) {
+		release_fn_bar(afu->fn, afu->config.pp_mmio_bar);
+		release_fn_bar(afu->fn, afu->config.global_mmio_bar);
+		dev_err(&pci_dev->dev, "Error mapping global mmio area\n");
+		return -ENOMEM;
+	}
+
+	/*
+	 * Leave an empty page between the per-process mmio area and
+	 * the AFU interrupt mappings
+	 */
+	afu->irq_base_offset = afu->config.pp_mmio_stride + PAGE_SIZE;
+	return 0;
+}
+
+static void unmap_mmio_areas(struct ocxl_afu *afu)
+{
+	if (afu->global_mmio_ptr) {
+		iounmap(afu->global_mmio_ptr);
+		afu->global_mmio_ptr = NULL;
+	}
+	afu->global_mmio_start = 0;
+	afu->pp_mmio_start = 0;
+	release_fn_bar(afu->fn, afu->config.pp_mmio_bar);
+	release_fn_bar(afu->fn, afu->config.global_mmio_bar);
+}
+
+static int configure_afu(struct ocxl_afu *afu, u8 afu_idx, struct pci_dev *dev)
+{
+	int rc;
+
+	rc = ocxl_config_read_afu(dev, &afu->fn->config, &afu->config, afu_idx);
+	if (rc)
+		return rc;
+
+	rc = assign_afu_actag(afu);
+	if (rc)
+		return rc;
+
+	rc = assign_afu_pasid(afu);
+	if (rc)
+		goto err_free_actag;
+
+	rc = map_mmio_areas(afu);
+	if (rc)
+		goto err_free_pasid;
+
+	return 0;
+
+err_free_pasid:
+	reclaim_afu_pasid(afu);
+err_free_actag:
+	reclaim_afu_actag(afu);
+	return rc;
+}
+
+static void deconfigure_afu(struct ocxl_afu *afu)
+{
+	unmap_mmio_areas(afu);
+	reclaim_afu_pasid(afu);
+	reclaim_afu_actag(afu);
+}
+
+static int activate_afu(struct pci_dev *dev, struct ocxl_afu *afu)
+{
+	ocxl_config_set_afu_state(dev, afu->config.dvsec_afu_control_pos, 1);
+
+	return 0;
+}
+
+static void deactivate_afu(struct ocxl_afu *afu)
+{
+	struct pci_dev *dev = to_pci_dev(afu->fn->dev.parent);
+
+	ocxl_config_set_afu_state(dev, afu->config.dvsec_afu_control_pos, 0);
+}
+
+static int init_afu(struct pci_dev *dev, struct ocxl_fn *fn, u8 afu_idx)
+{
+	int rc;
+	struct ocxl_afu *afu;
+
+	afu = alloc_afu(fn);
+	if (!afu)
+		return -ENOMEM;
+
+	rc = configure_afu(afu, afu_idx, dev);
+	if (rc) {
+		ocxl_afu_put(afu);
+		return rc;
+	}
+
+	rc = activate_afu(dev, afu);
+	if (rc) {
+		deconfigure_afu(afu);
+		ocxl_afu_put(afu);
+		return rc;
+	}
+
+	list_add_tail(&afu->list, &fn->afu_list);
+
+	return 0;
+}
+
+static void remove_afu(struct ocxl_afu *afu)
+{
+	list_del(&afu->list);
+	ocxl_context_detach_all(afu);
+	deactivate_afu(afu);
+	deconfigure_afu(afu);
+	ocxl_afu_put(afu); // matches the implicit get in alloc_afu
+}
+
+static struct ocxl_fn *alloc_function(void)
+{
+	struct ocxl_fn *fn;
+
+	fn = kzalloc(sizeof(struct ocxl_fn), GFP_KERNEL);
+	if (!fn)
+		return NULL;
+
+	INIT_LIST_HEAD(&fn->afu_list);
+	INIT_LIST_HEAD(&fn->pasid_list);
+	INIT_LIST_HEAD(&fn->actag_list);
+
+	return fn;
+}
+
+static void free_function(struct ocxl_fn *fn)
+{
+	WARN_ON(!list_empty(&fn->afu_list));
+	WARN_ON(!list_empty(&fn->pasid_list));
+	kfree(fn);
+}
+
+static void free_function_dev(struct device *dev)
+{
+	struct ocxl_fn *fn = container_of(dev, struct ocxl_fn, dev);
+
+	free_function(fn);
+}
+
+static int set_function_device(struct ocxl_fn *fn, struct pci_dev *dev)
+{
+	int rc;
+
+	fn->dev.parent = &dev->dev;
+	fn->dev.release = free_function_dev;
+	rc = dev_set_name(&fn->dev, "ocxlfn.%s", dev_name(&dev->dev));
+	if (rc)
+		return rc;
+	return 0;
+}
+
+static int assign_function_actag(struct ocxl_fn *fn)
+{
+	struct pci_dev *dev = to_pci_dev(fn->dev.parent);
+	u16 base, enabled, supported;
+	int rc;
+
+	rc = ocxl_config_get_actag_info(dev, &base, &enabled, &supported);
+	if (rc)
+		return rc;
+
+	fn->actag_base = base;
+	fn->actag_enabled = enabled;
+	fn->actag_supported = supported;
+
+	ocxl_config_set_actag(dev, fn->config.dvsec_function_pos,
+			fn->actag_base,	fn->actag_enabled);
+	dev_dbg(&fn->dev, "actag range starting at %d, enabled %d\n",
+		fn->actag_base, fn->actag_enabled);
+	return 0;
+}
+
+static int set_function_pasid(struct ocxl_fn *fn)
+{
+	struct pci_dev *dev = to_pci_dev(fn->dev.parent);
+	int rc, desired_count, max_count;
+
+	/* A function may not require any PASID */
+	if (fn->config.max_pasid_log < 0)
+		return 0;
+
+	rc = ocxl_config_get_pasid_info(dev, &max_count);
+	if (rc)
+		return rc;
+
+	desired_count = 1 << fn->config.max_pasid_log;
+
+	if (desired_count > max_count) {
+		dev_err(&fn->dev,
+			"Function requires more PASIDs than is available (%d vs. %d)\n",
+			desired_count, max_count);
+		return -ENOSPC;
+	}
+
+	fn->pasid_base = 0;
+	return 0;
+}
+
+static int configure_function(struct ocxl_fn *fn, struct pci_dev *dev)
+{
+	int rc;
+
+	rc = pci_enable_device(dev);
+	if (rc) {
+		dev_err(&dev->dev, "pci_enable_device failed: %d\n", rc);
+		return rc;
+	}
+
+	/*
+	 * Once it has been confirmed to work on our hardware, we
+	 * should reset the function, to force the adapter to restart
+	 * from scratch.
+	 * A function reset would also reset all its AFUs.
+	 *
+	 * Some hints for implementation:
+	 *
+	 * - there's not status bit to know when the reset is done. We
+	 *   should try reading the config space to know when it's
+	 *   done.
+	 * - probably something like:
+	 *	Reset
+	 *	wait 100ms
+	 *	issue config read
+	 *	allow device up to 1 sec to return success on config
+	 *	read before declaring it broken
+	 *
+	 * Some shared logic on the card (CFG, TLX) won't be reset, so
+	 * there's no guarantee that it will be enough.
+	 */
+	rc = ocxl_config_read_function(dev, &fn->config);
+	if (rc)
+		return rc;
+
+	rc = set_function_device(fn, dev);
+	if (rc)
+		return rc;
+
+	rc = assign_function_actag(fn);
+	if (rc)
+		return rc;
+
+	rc = set_function_pasid(fn);
+	if (rc)
+		return rc;
+
+	rc = ocxl_link_setup(dev, 0, &fn->link);
+	if (rc)
+		return rc;
+
+	rc = ocxl_config_set_TL(dev, fn->config.dvsec_tl_pos);
+	if (rc) {
+		ocxl_link_release(dev, fn->link);
+		return rc;
+	}
+	return 0;
+}
+
+static void deconfigure_function(struct ocxl_fn *fn)
+{
+	struct pci_dev *dev = to_pci_dev(fn->dev.parent);
+
+	ocxl_link_release(dev, fn->link);
+	pci_disable_device(dev);
+}
+
+static struct ocxl_fn *init_function(struct pci_dev *dev)
+{
+	struct ocxl_fn *fn;
+	int rc;
+
+	fn = alloc_function();
+	if (!fn)
+		return ERR_PTR(-ENOMEM);
+
+	rc = configure_function(fn, dev);
+	if (rc) {
+		free_function(fn);
+		return ERR_PTR(rc);
+	}
+
+	rc = device_register(&fn->dev);
+	if (rc) {
+		deconfigure_function(fn);
+		put_device(&fn->dev);
+		return ERR_PTR(rc);
+	}
+	return fn;
+}
+
+// Device detection & initialisation
+
+struct ocxl_fn *ocxl_function_open(struct pci_dev *dev)
+{
+	int rc, afu_count = 0;
+	u8 afu;
+	struct ocxl_fn *fn;
+
+	if (!radix_enabled()) {
+		dev_err(&dev->dev, "Unsupported memory model (hash)\n");
+		return ERR_PTR(-ENODEV);
+	}
+
+	fn = init_function(dev);
+	if (IS_ERR(fn)) {
+		dev_err(&dev->dev, "function init failed: %li\n",
+			PTR_ERR(fn));
+		return fn;
+	}
+
+	for (afu = 0; afu <= fn->config.max_afu_index; afu++) {
+		rc = ocxl_config_check_afu_index(dev, &fn->config, afu);
+		if (rc > 0) {
+			rc = init_afu(dev, fn, afu);
+			if (rc) {
+				dev_err(&dev->dev,
+					"Can't initialize AFU index %d\n", afu);
+				continue;
+			}
+			afu_count++;
+		}
+	}
+	dev_info(&dev->dev, "%d AFU(s) configured\n", afu_count);
+	return fn;
+}
+EXPORT_SYMBOL_GPL(ocxl_function_open);
+
+struct list_head *ocxl_function_afu_list(struct ocxl_fn *fn)
+{
+	return &fn->afu_list;
+}
+EXPORT_SYMBOL_GPL(ocxl_function_afu_list);
+
+struct ocxl_afu *ocxl_function_fetch_afu(struct ocxl_fn *fn, u8 afu_idx)
+{
+	struct ocxl_afu *afu;
+
+	list_for_each_entry(afu, &fn->afu_list, list) {
+		if (afu->config.idx == afu_idx)
+			return afu;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(ocxl_function_fetch_afu);
+
+const struct ocxl_fn_config *ocxl_function_config(struct ocxl_fn *fn)
+{
+	return &fn->config;
+}
+EXPORT_SYMBOL_GPL(ocxl_function_config);
+
+void ocxl_function_close(struct ocxl_fn *fn)
+{
+	struct ocxl_afu *afu, *tmp;
+
+	list_for_each_entry_safe(afu, tmp, &fn->afu_list, list) {
+		remove_afu(afu);
+	}
+
+	deconfigure_function(fn);
+	device_unregister(&fn->dev);
+}
+EXPORT_SYMBOL_GPL(ocxl_function_close);
+
+// AFU Metadata
+
+struct ocxl_afu_config *ocxl_afu_config(struct ocxl_afu *afu)
+{
+	return &afu->config;
+}
+EXPORT_SYMBOL_GPL(ocxl_afu_config);
+
+void ocxl_afu_set_private(struct ocxl_afu *afu, void *private)
+{
+	afu->private = private;
+}
+EXPORT_SYMBOL_GPL(ocxl_afu_set_private);
+
+void *ocxl_afu_get_private(struct ocxl_afu *afu)
+{
+	if (afu)
+		return afu->private;
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(ocxl_afu_get_private);
diff --git a/drivers/misc/ocxl/file.c b/drivers/misc/ocxl/file.c
index e6a607488f8a..2870c25da166 100644
--- a/drivers/misc/ocxl/file.c
+++ b/drivers/misc/ocxl/file.c
@@ -3,6 +3,7 @@
 #include <linux/fs.h>
 #include <linux/poll.h>
 #include <linux/sched/signal.h>
+#include <linux/eventfd.h>
 #include <linux/uaccess.h>
 #include <uapi/misc/ocxl.h>
 #include <asm/reg.h>
@@ -17,70 +18,56 @@ static struct class *ocxl_class;
 static struct mutex minors_idr_lock;
 static struct idr minors_idr;
 
-static struct ocxl_afu *find_and_get_afu(dev_t devno)
+static struct ocxl_file_info *find_file_info(dev_t devno)
 {
-	struct ocxl_afu *afu;
-	int afu_minor;
+	struct ocxl_file_info *info;
 
-	afu_minor = MINOR(devno);
 	/*
 	 * We don't declare an RCU critical section here, as our AFU
 	 * is protected by a reference counter on the device. By the time the
-	 * minor number of a device is removed from the idr, the ref count of
+	 * info reference is removed from the idr, the ref count of
 	 * the device is already at 0, so no user API will access that AFU and
 	 * this function can't return it.
 	 */
-	afu = idr_find(&minors_idr, afu_minor);
-	if (afu)
-		ocxl_afu_get(afu);
-	return afu;
+	info = idr_find(&minors_idr, MINOR(devno));
+	return info;
 }
 
-static int allocate_afu_minor(struct ocxl_afu *afu)
+static int allocate_minor(struct ocxl_file_info *info)
 {
 	int minor;
 
 	mutex_lock(&minors_idr_lock);
-	minor = idr_alloc(&minors_idr,