linux-stable/drivers/cxl/core/hdm.c

// SPDX-License-Identifier: GPL-2.0-only
/* Copyright(c) 2022 Intel Corporation. All rights reserved. */
#include <linux/io-64-nonatomic-hi-lo.h>
#include <linux/seq_file.h>
#include <linux/device.h>
#include <linux/delay.h>

#include "cxlmem.h"
#include "core.h"

/**
 * DOC: cxl core hdm
 *
 * Compute Express Link Host Managed Device Memory, starting with the
 * CXL 2.0 specification, is managed by an array of HDM Decoder register
 * instances per CXL port and per CXL endpoint. Define common helpers
 * for enumerating these registers and capabilities.
 */

static DECLARE_RWSEM(cxl_dpa_rwsem);

static int add_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld,
			   int *target_map)
{
	int rc;

	rc = cxl_decoder_add_locked(cxld, target_map);
	if (rc) {
		put_device(&cxld->dev);
		dev_err(&port->dev, "Failed to add decoder\n");
		return rc;
	}

	rc = cxl_decoder_autoremove(&port->dev, cxld);
	if (rc)
		return rc;

	dev_dbg(&cxld->dev, "Added to port %s\n", dev_name(&port->dev));

	return 0;
}

/*
 * Per the CXL specification (8.2.5.12 CXL HDM Decoder Capability Structure)
 * single ported host-bridges need not publish a decoder capability when a
 * passthrough decode can be assumed, i.e. all transactions that the uport sees
 * are claimed and passed to the single dport. Disable the range until the first
 * CXL region is enumerated / activated.
 */
int devm_cxl_add_passthrough_decoder(struct cxl_port *port)
{
	struct cxl_switch_decoder *cxlsd;
	struct cxl_dport *dport;
	int single_port_map[1];

	cxlsd = cxl_switch_decoder_alloc(port, 1);
	if (IS_ERR(cxlsd))
		return PTR_ERR(cxlsd);

	device_lock_assert(&port->dev);

	dport = list_first_entry(&port->dports, typeof(*dport), list);
	single_port_map[0] = dport->port_id;

	return add_hdm_decoder(port, &cxlsd->cxld, single_port_map);
}
EXPORT_SYMBOL_NS_GPL(devm_cxl_add_passthrough_decoder, CXL);

static void parse_hdm_decoder_caps(struct cxl_hdm *cxlhdm)
{
	u32 hdm_cap;

	hdm_cap = readl(cxlhdm->regs.hdm_decoder + CXL_HDM_DECODER_CAP_OFFSET);
	cxlhdm->decoder_count = cxl_hdm_decoder_count(hdm_cap);
	cxlhdm->target_count =
		FIELD_GET(CXL_HDM_DECODER_TARGET_COUNT_MASK, hdm_cap);
	if (FIELD_GET(CXL_HDM_DECODER_INTERLEAVE_11_8, hdm_cap))
		cxlhdm->interleave_mask |= GENMASK(11, 8);
	if (FIELD_GET(CXL_HDM_DECODER_INTERLEAVE_14_12, hdm_cap))
		cxlhdm->interleave_mask |= GENMASK(14, 12);
}

static void __iomem *map_hdm_decoder_regs(struct cxl_port *port,
					  void __iomem *crb)
{
	struct cxl_component_reg_map map;

	cxl_probe_component_regs(&port->dev, crb, &map);
	if (!map.hdm_decoder.valid) {
		dev_err(&port->dev, "HDM decoder registers invalid\n");
		return IOMEM_ERR_PTR(-ENXIO);
	}

	return crb + map.hdm_decoder.offset;
}

/**
 * devm_cxl_setup_hdm - map HDM decoder component registers
 * @port: cxl_port to map
 */
struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port)
{
	struct device *dev = &port->dev;
	void __iomem *crb, *hdm;
	struct cxl_hdm *cxlhdm;

	cxlhdm = devm_kzalloc(dev, sizeof(*cxlhdm), GFP_KERNEL);
	if (!cxlhdm)
		return ERR_PTR(-ENOMEM);

	cxlhdm->port = port;
	crb = devm_cxl_iomap_block(dev, port->component_reg_phys,
				   CXL_COMPONENT_REG_BLOCK_SIZE);
	if (!crb) {
		dev_err(dev, "No component registers mapped\n");
		return ERR_PTR(-ENXIO);
	}

	hdm = map_hdm_decoder_regs(port, crb);
	if (IS_ERR(hdm))
		return ERR_CAST(hdm);
	cxlhdm->regs.hdm_decoder = hdm;

	parse_hdm_decoder_caps(cxlhdm);
	if (cxlhdm->decoder_count == 0) {
		dev_err(dev, "Spec violation. Caps invalid\n");
		return ERR_PTR(-ENXIO);
	}

	return cxlhdm;
}
EXPORT_SYMBOL_NS_GPL(devm_cxl_setup_hdm, CXL);

static void __cxl_dpa_debug(struct seq_file *file, struct resource *r, int depth)
{
	unsigned long long start = r->start, end = r->end;

	seq_printf(file, "%*s%08llx-%08llx : %s\n", depth * 2, "", start, end,
		   r->name);
}

void cxl_dpa_debug(struct seq_file *file, struct cxl_dev_state *cxlds)
{
	struct resource *p1, *p2;

	down_read(&cxl_dpa_rwsem);
	for (p1 = cxlds->dpa_res.child; p1; p1 = p1->sibling) {
		__cxl_dpa_debug(file, p1, 0);
		for (p2 = p1->child; p2; p2 = p2->sibling)
			__cxl_dpa_debug(file, p2, 1);
	}
	up_read(&cxl_dpa_rwsem);
}
EXPORT_SYMBOL_NS_GPL(cxl_dpa_debug, CXL);

/*
 * Must be called in a context that synchronizes against this decoder's
 * port ->remove() callback (like an endpoint decoder sysfs attribute)
 */
static void __cxl_dpa_release(struct cxl_endpoint_decoder *cxled)
{
	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
	struct cxl_port *port = cxled_to_port(cxled);
	struct cxl_dev_state *cxlds = cxlmd->cxlds;
	struct resource *res = cxled->dpa_res;
	resource_size_t skip_start;

	lockdep_assert_held_write(&cxl_dpa_rwsem);

	/* save @skip_start, before @res is released */
	skip_start = res->start - cxled->skip;
	__release_region(&cxlds->dpa_res, res->start, resource_size(res));
	if (cxled->skip)
		__release_region(&cxlds->dpa_res, skip_start, cxled->skip);
	cxled->skip = 0;
	cxled->dpa_res = NULL;
	port->hdm_end--;
}

static void cxl_dpa_release(void *cxled)
{
	down_write(&cxl_dpa_rwsem);
	__cxl_dpa_release(cxled);
	up_write(&cxl_dpa_rwsem);
}

/*
 * Must be called from context that will not race port device
 * unregistration, like decoder sysfs attribute methods
 */
static void devm_cxl_dpa_release(struct cxl_endpoint_decoder *cxled)
{
	struct cxl_port *port = cxled_to_port(cxled);

	lockdep_assert_held_write(&cxl_dpa_rwsem);
	devm_remove_action(&port->dev, cxl_dpa_release, cxled);
	__cxl_dpa_release(cxled);
}

static int __cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
			     resource_size_t base, resource_size_t len,
			     resource_size_t skipped)
{
	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
	struct cxl_port *port = cxled_to_port(cxled);
	struct cxl_dev_state *cxlds = cxlmd->cxlds;
	struct device *dev = &port->dev;
	struct resource *res;

	lockdep_assert_held_write(&cxl_dpa_rwsem);

	if (!len)
		return 0;

	if (cxled->dpa_res) {
		dev_dbg(dev, "decoder%d.%d: existing allocation %pr assigned\n",
			port->id, cxled->cxld.id, cxled->dpa_res);
		return -EBUSY;
	}

	if (port->hdm_end + 1 != cxled->cxld.id) {
		/*
		 * Assumes alloc and commit order is always in hardware instance
		 * order per expectations from 8.2.5.12.20 Committing Decoder
		 * Programming that enforce decoder[m] committed before
		 * decoder[m+1] commit start.
		 */
		dev_dbg(dev, "decoder%d.%d: expected decoder%d.%d\n", port->id,
			cxled->cxld.id, port->id, port->hdm_end + 1);
		return -EBUSY;
	}

	if (skipped) {
		res = __request_region(&cxlds->dpa_res, base - skipped, skipped,
				       dev_name(&cxled->cxld.dev), 0);
		if (!res) {
			dev_dbg(dev,
				"decoder%d.%d: failed to reserve skipped space\n",
				port->id, cxled->cxld.id);
			return -EBUSY;
		}
	}
	res = __request_region(&cxlds->dpa_res, base, len,
			       dev_name(&cxled->cxld.dev), 0);
	if (!res) {
		dev_dbg(dev, "decoder%d.%d: failed to reserve allocation\n",
			port->id, cxled->cxld.id);
		if (skipped)
			__release_region(&cxlds->dpa_res, base - skipped,
					 skipped);
		return -EBUSY;
	}
	cxled->dpa_res = res;
	cxled->skip = skipped;

	if (resource_contains(&cxlds->pmem_res, res))
		cxled->mode = CXL_DECODER_PMEM;
	else if (resource_contains(&cxlds->ram_res, res))
		cxled->mode = CXL_DECODER_RAM;
	else {
		dev_dbg(dev, "decoder%d.%d: %pr mixed\n", port->id,
			cxled->cxld.id, cxled->dpa_res);
		cxled->mode = CXL_DECODER_MIXED;
	}
	port->hdm_end++;

	return 0;
}

static int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
				resource_size_t base, resource_size_t len,
				resource_size_t skipped)
{
	struct cxl_port *port = cxled_to_port(cxled);
	int rc;

	down_write(&cxl_dpa_rwsem);
	rc = __cxl_dpa_reserve(cxled, base, len, skipped);
	up_write(&cxl_dpa_rwsem);

	if (rc)
		return rc;

	return devm_add_action_or_reset(&port->dev, cxl_dpa_release, cxled);
}

resource_size_t cxl_dpa_size(struct cxl_endpoint_decoder *cxled)
{
	resource_size_t size = 0;

	down_read(&cxl_dpa_rwsem);
	if (cxled->dpa_res)
		size = resource_size(cxled->dpa_res);
	up_read(&cxl_dpa_rwsem);

	return size;
}

resource_size_t cxl_dpa_resource_start(struct cxl_endpoint_decoder *cxled)
{
	resource_size_t base = -1;

	down_read(&cxl_dpa_rwsem);
	if (cxled->dpa_res)
		base = cxled->dpa_res->start;
	up_read(&cxl_dpa_rwsem);

	return base;
}

int cxl_dpa_free(struct cxl_endpoint_decoder *cxled)
{
	struct cxl_port *port = cxled_to_port(cxled);
	struct device *dev = &cxled->cxld.dev;
	int rc;

	down_write(&cxl_dpa_rwsem);
	if (!cxled->dpa_res) {
		rc = 0;
		goto out;
	}
	if (cxled->cxld.flags & CXL_DECODER_F_ENABLE) {
		dev_dbg(dev, "decoder enabled\n");
		rc = -EBUSY;
		goto out;
	}
	if (cxled->cxld.id != port->hdm_end) {
		dev_dbg(dev, "expected decoder%d.%d\n", port->id,
			port->hdm_end);
		rc = -EBUSY;
		goto out;
	}
	devm_cxl_dpa_release(cxled);
	rc = 0;
out:
	up_write(&cxl_dpa_rwsem);
	return rc;
}

int cxl_dpa_set_mode(struct cxl_endpoint_decoder *cxled,
		     enum cxl_decoder_mode mode)
{
	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
	struct cxl_dev_state *cxlds = cxlmd->cxlds;
	struct device *dev = &cxled->cxld.dev;
	int rc;

	switch (mode) {
	case CXL_DECODER_RAM:
	case CXL_DECODER_PMEM:
		break;
	default:
		dev_dbg(dev, "unsupported mode: %d\n", mode);
		return -EINVAL;
	}

	down_write(&cxl_dpa_rwsem);
	if (cxled->cxld.flags & CXL_DECODER_F_ENABLE) {
		rc = -EBUSY;
		goto out;
	}

	/*
	 * Only allow modes that are supported by the current partition
	 * configuration
	 */
	if (mode == CXL_DECODER_PMEM && !resource_size(&cxlds->pmem_res)) {
		dev_dbg(dev, "no available pmem capacity\n");
		rc = -ENXIO;
		goto out;
	}
	if (mode == CXL_DECODER_RAM && !resource_size(&cxlds->ram_res)) {
		dev_dbg(dev, "no available ram capacity\n");
		rc = -ENXIO;
		goto out;
	}

	cxled->mode = mode;
	rc = 0;
out:
	up_write(&cxl_dpa_rwsem);

	return rc;
}

int cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, unsigned long long size)
{
	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
	resource_size_t free_ram_start, free_pmem_start;
	struct cxl_port *port = cxled_to_port(cxled);
	struct cxl_dev_state *cxlds = cxlmd->cxlds;
	struct device *dev = &cxled->cxld.dev;
	resource_size_t start, avail, skip;
	struct resource *p, *last;
	int rc;

	down_write(&cxl_dpa_rwsem);
	if (cxled->cxld.flags & CXL_DECODER_F_ENABLE) {
		dev_dbg(dev, "decoder enabled\n");
		rc = -EBUSY;
		goto out;
	}

	for (p = cxlds->ram_res.child, last = NULL; p; p = p->sibling)
		last = p;
	if (last)
		free_ram_start = last->end + 1;
	else
		free_ram_start = cxlds->ram_res.start;

	for (p = cxlds->pmem_res.child, last = NULL; p; p = p->sibling)
		last = p;
	if (last)
		free_pmem_start = last->end + 1;
	else
		free_pmem_start = cxlds->pmem_res.start;

	if (cxled->mode == CXL_DECODER_RAM) {
		start = free_ram_start;
		avail = cxlds->ram_res.end - start + 1;
		skip = 0;
	} else if (cxled->mode == CXL_DECODER_PMEM) {
		resource_size_t skip_start, skip_end;

		start = free_pmem_start;
		avail = cxlds->pmem_res.end - start + 1;
		skip_start = free_ram_start;
		skip_end = start - 1;
		skip = skip_end - skip_start + 1;
	} else {
		dev_dbg(dev, "mode not set\n");
		rc = -EINVAL;
		goto out;
	}

	if (size > avail) {
		dev_dbg(dev, "%pa exceeds available %s capacity: %pa\n", &size,
			cxled->mode == CXL_DECODER_RAM ? "ram" : "pmem",
			&avail);
		rc = -ENOSPC;
		goto out;
	}

	rc = __cxl_dpa_reserve(cxled, start, size, skip);
out:
	up_write(&cxl_dpa_rwsem);

	if (rc)
		return rc;

	return devm_add_action_or_reset(&port->dev, cxl_dpa_release, cxled);
}

static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld,
			    int *target_map, void __iomem *hdm, int which,
			    u64 *dpa_base)
{
	struct cxl_endpoint_decoder *cxled = NULL;
	u64 size, base, skip, dpa_size;
	bool committed;
	u32 remainder;
	int i, rc;
	u32 ctrl;
	union {
		u64 value;
		unsigned char target_id[8];
	} target_list;

	if (is_endpoint_decoder(&cxld->dev))
		cxled = to_cxl_endpoint_decoder(&cxld->dev);

	ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(which));
	base = ioread64_hi_lo(hdm + CXL_HDM_DECODER0_BASE_LOW_OFFSET(which));
	size = ioread64_hi_lo(hdm + CXL_HDM_DECODER0_SIZE_LOW_OFFSET(which));
	committed = !!(ctrl & CXL_HDM_DECODER0_CTRL_COMMITTED);

	if (!committed)
		size = 0;
	if (base == U64_MAX || size == U64_MAX) {
		dev_warn(&port->dev, "decoder%d.%d: Invalid resource range\n",
			 port->id, cxld->id);
		return -ENXIO;
	}

	cxld->hpa_range = (struct range) {
		.start = base,
		.end = base + size - 1,
	};

	/* decoders are enabled if committed */
	if (committed) {
		cxld->flags |= CXL_DECODER_F_ENABLE;
		if (ctrl & CXL_HDM_DECODER0_CTRL_LOCK)
			cxld->flags |= CXL_DECODER_F_LOCK;
		if (FIELD_GET(CXL_HDM_DECODER0_CTRL_TYPE, ctrl))
			cxld->target_type = CXL_DECODER_EXPANDER;
		else
			cxld->target_type = CXL_DECODER_ACCELERATOR;
	} else {
		/* unless / until type-2 drivers arrive, assume type-3 */
		if (FIELD_GET(CXL_HDM_DECODER0_CTRL_TYPE, ctrl) == 0) {
			ctrl |= CXL_HDM_DECODER0_CTRL_TYPE;
			writel(ctrl, hdm + CXL_HDM_DECODER0_CTRL_OFFSET(which));
		}
		cxld->target_type = CXL_DECODER_EXPANDER;
	}
	rc = cxl_to_ways(FIELD_GET(CXL_HDM_DECODER0_CTRL_IW_MASK, ctrl),
			 &cxld->interleave_ways);
	if (rc) {
		dev_warn(&port->dev,
			 "decoder%d.%d: Invalid interleave ways (ctrl: %#x)\n",
			 port->id, cxld->id, ctrl);
		return rc;
	}
	rc = cxl_to_granularity(FIELD_GET(CXL_HDM_DECODER0_CTRL_IG_MASK, ctrl),
				&cxld->interleave_granularity);
	if (rc)
		return rc;

	if (!cxled) {
		target_list.value =
			ioread64_hi_lo(hdm + CXL_HDM_DECODER0_TL_LOW(which));
		for (i = 0; i < cxld->interleave_ways; i++)
			target_map[i] = target_list.target_id[i];

		return 0;
	}

	if (!committed)
		return 0;

	dpa_size = div_u64_rem(size, cxld->interleave_ways, &remainder);
	if (remainder) {
		dev_err(&port->dev,
			"decoder%d.%d: invalid committed configuration size: %#llx ways: %d\n",
			port->id, cxld->id, size, cxld->interleave_ways);
		return -ENXIO;
	}
	skip = ioread64_hi_lo(hdm + CXL_HDM_DECODER0_SKIP_LOW(which));
	rc = devm_cxl_dpa_reserve(cxled, *dpa_base + skip, dpa_size, skip);
	if (rc) {
		dev_err(&port->dev,
			"decoder%d.%d: Failed to reserve DPA range %#llx - %#llx\n (%d)",
			port->id, cxld->id, *dpa_base,
			*dpa_base + dpa_size + skip - 1, rc);
		return rc;
	}
	*dpa_base += dpa_size + skip;
	return 0;
}

/**
 * devm_cxl_enumerate_decoders - add decoder objects per HDM register set
 * @cxlhdm: Structure to populate with HDM capabilities
 */
int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm)
{
	void __iomem *hdm = cxlhdm->regs.hdm_decoder;
	struct cxl_port *port = cxlhdm->port;
	int i, committed;
	u64 dpa_base = 0;
	u32 ctrl;

	/*
	 * Since the register resource was recently claimed via request_region()
	 * be careful about trusting the "not-committed" status until the commit
	 * timeout has elapsed.  The commit timeout is 10ms (CXL 2.0
	 * 8.2.5.12.20), but double it to be tolerant of any clock skew between
	 * host and target.
	 */
	for (i = 0, committed = 0; i < cxlhdm->decoder_count; i++) {
		ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(i));
		if (ctrl & CXL_HDM_DECODER0_CTRL_COMMITTED)
			committed++;
	}

	/* ensure that future checks of committed can be trusted */
	if (committed != cxlhdm->decoder_count)
		msleep(20);

	for (i = 0; i < cxlhdm->decoder_count; i++) {
		int target_map[CXL_DECODER_MAX_INTERLEAVE] = { 0 };
		int rc, target_count = cxlhdm->target_count;
		struct cxl_decoder *cxld;

		if (is_cxl_endpoint(port)) {
			struct cxl_endpoint_decoder *cxled;

			cxled = cxl_endpoint_decoder_alloc(port);
			if (IS_ERR(cxled)) {
				dev_warn(&port->dev,
					 "Failed to allocate the decoder\n");
				return PTR_ERR(cxled);
			}
			cxld = &cxled->cxld;
		} else {
			struct cxl_switch_decoder *cxlsd;

			cxlsd = cxl_switch_decoder_alloc(port, target_count);
			if (IS_ERR(cxlsd)) {
				dev_warn(&port->dev,
					 "Failed to allocate the decoder\n");
				return PTR_ERR(cxlsd);
			}
			cxld = &cxlsd->cxld;
		}

		rc = init_hdm_decoder(port, cxld, target_map, hdm, i, &dpa_base);
		if (rc) {
			put_device(&cxld->dev);
			return rc;
		}
		rc = add_hdm_decoder(port, cxld, target_map);
		if (rc) {
			dev_warn(&port->dev,
				 "Failed to add decoder to port\n");
			return rc;
		}
	}

	return 0;
}
EXPORT_SYMBOL_NS_GPL(devm_cxl_enumerate_decoders, CXL);