PM: CXL: Disable suspend

The CXL specification claims S3 support at a hardware level, but at a
system software level there are some missing pieces. Section 9.4 (CXL
2.0) rightly claims that "CXL mem adapters may need aux power to retain
memory context across S3", but there is no enumeration mechanism for the
OS to determine if a given adapter has that support. Moreover the save
state and resume image for the system may inadvertantly end up in a CXL
device that needs to be restored before the save state is recoverable.
I.e. a circular dependency that is not resolvable without a third party
save-area.

Arrange for the cxl_mem driver to fail S3 attempts. This still nominaly
allows for suspend, but requires unbinding all CXL memory devices before
the suspend to ensure the typical DRAM flow is taken. The cxl_mem unbind
flow is intended to also tear down all CXL memory regions associated
with a given cxl_memdev.

It is reasonable to assume that any device participating in a System RAM
range published in the EFI memory map is covered by aux power and
save-area outside the device itself. So this restriction can be
minimized in the future once pre-existing region enumeration support
arrives, and perhaps a spec update to clarify if the EFI memory map is
sufficent for determining the range of devices managed by
platform-firmware for S3 support.

Per Rafael, if the CXL configuration prevents suspend then it should
fail early before tasks are frozen, and mem_sleep should stop showing
'mem' as an option [1]. Effectively CXL augments the platform suspend
->valid() op since, for example, the ACPI ops are not aware of the CXL /
PCI dependencies. Given the split role of platform firmware vs OS
provisioned CXL memory it is up to the cxl_mem driver to determine if
the CXL configuration has elements that platform firmware may not be
prepared to restore.

Link: https://lore.kernel.org/r/CAJZ5v0hGVN_=[e-mail] [1]
Cc: "Rafael J. Wysocki" <[e-mail]>
Cc: Pavel Machek <[e-mail]>
Cc: Len Brown <[e-mail]>
Reviewed-by: Rafael J. Wysocki <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Dan Williams <[e-mail]>

drivers/Makefile

···
 obj-y				+= base/ block/ misc/ mfd/ nfc/
 obj-$(CONFIG_LIBNVDIMM)		+= nvdimm/
 obj-$(CONFIG_DAX)		+= dax/
-obj-$(CONFIG_CXL_BUS)		+= cxl/
 obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf/
 obj-$(CONFIG_NUBUS)		+= nubus/
+obj-y				+= cxl/
 obj-y				+= macintosh/
 obj-y				+= scsi/
 obj-y				+= nvme/

drivers/cxl/Kconfig

···
 	default CXL_BUS
 	tristate
 
+config CXL_SUSPEND
+	def_bool y
+	depends on SUSPEND && CXL_MEM
+
 endif

drivers/cxl/Makefile

···
 # SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_CXL_BUS) += core/
+obj-y += core/
 obj-$(CONFIG_CXL_PCI) += cxl_pci.o
 obj-$(CONFIG_CXL_MEM) += cxl_mem.o
 obj-$(CONFIG_CXL_ACPI) += cxl_acpi.o

drivers/cxl/core/Makefile

···
 # SPDX-License-Identifier: GPL-2.0
 obj-$(CONFIG_CXL_BUS) += cxl_core.o
+obj-$(CONFIG_CXL_SUSPEND) += suspend.o
 
 ccflags-y += -I$(srctree)/drivers/cxl
 cxl_core-y := port.o

drivers/cxl/core/suspend.c

···
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2022 Intel Corporation. All rights reserved. */
+#include <linux/atomic.h>
+#include <linux/export.h>
+#include "cxlmem.h"
+
+static atomic_t mem_active;
+
+bool cxl_mem_active(void)
+{
+	return atomic_read(&mem_active) != 0;
+}
+
+void cxl_mem_active_inc(void)
+{
+	atomic_inc(&mem_active);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_mem_active_inc, CXL);
+
+void cxl_mem_active_dec(void)
+{
+	atomic_dec(&mem_active);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_mem_active_dec, CXL);

drivers/cxl/cxlmem.h

···
 struct cxl_dev_state *cxl_dev_state_create(struct device *dev);
 void set_exclusive_cxl_commands(struct cxl_dev_state *cxlds, unsigned long *cmds);
 void clear_exclusive_cxl_commands(struct cxl_dev_state *cxlds, unsigned long *cmds);
+#ifdef CONFIG_CXL_SUSPEND
+void cxl_mem_active_inc(void);
+void cxl_mem_active_dec(void);
+#else
+static inline void cxl_mem_active_inc(void)
+{
+}
+static inline void cxl_mem_active_dec(void)
+{
+}
+#endif
 
 struct cxl_hdm {
 	struct cxl_component_regs regs;

drivers/cxl/mem.c

···
 	return retval;
 }
 
+static void enable_suspend(void *data)
+{
+	cxl_mem_active_dec();
+}
+
 static int cxl_mem_probe(struct device *dev)
 {
 	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
···
 out:
 	cxl_device_unlock(&parent_port->dev);
 	put_device(&parent_port->dev);
-	return rc;
+
+	/*
+	 * The kernel may be operating out of CXL memory on this device,
+	 * there is no spec defined way to determine whether this device
+	 * preserves contents over suspend, and there is no simple way
+	 * to arrange for the suspend image to avoid CXL memory which
+	 * would setup a circular dependency between PCI resume and save
+	 * state restoration.
+	 *
+	 * TODO: support suspend when all the regions this device is
+	 * hosting are locked and covered by the system address map,
+	 * i.e. platform firmware owns restoring the HDM configuration
+	 * that it locked.
+	 */
+	cxl_mem_active_inc();
+	return devm_add_action_or_reset(dev, enable_suspend, NULL);
 }
 
 static struct cxl_driver cxl_mem_driver = {

include/linux/pm.h

···
 }
 #endif /* CONFIG_VT_CONSOLE_SLEEP */
 
+#ifdef CONFIG_CXL_SUSPEND
+bool cxl_mem_active(void);
+#else
+static inline bool cxl_mem_active(void)
+{
+	return false;
+}
+#endif
+
 /*
  * Device power management
  */

kernel/power/hibernate.c

···
 {
 	return nohibernate == 0 &&
 		!security_locked_down(LOCKDOWN_HIBERNATION) &&
-		!secretmem_active();
+		!secretmem_active() && !cxl_mem_active();
 }
 
 /**

kernel/power/main.c

···
 	char *s = buf;
 	suspend_state_t i;
 
-	for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++)
+	for (i = PM_SUSPEND_MIN; i < PM_SUSPEND_MAX; i++) {
+		if (i >= PM_SUSPEND_MEM && cxl_mem_active())
+			continue;
 		if (mem_sleep_states[i]) {
 			const char *label = mem_sleep_states[i];
 
···
 			else
 				s += sprintf(s, "%s ", label);
 		}
+	}
 
 	/* Convert the last space to a newline if needed. */
 	if (s != buf)

kernel/power/suspend.c

···
 
 static bool sleep_state_supported(suspend_state_t state)
 {
-	return state == PM_SUSPEND_TO_IDLE || valid_state(state);
+	return state == PM_SUSPEND_TO_IDLE ||
+	       (valid_state(state) && !cxl_mem_active());
 }
 
 static int platform_suspend_prepare(suspend_state_t state)