diff options
Diffstat (limited to 'drivers/cxl/core/region.c')
-rw-r--r-- | drivers/cxl/core/region.c | 266 |
1 files changed, 155 insertions, 111 deletions
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c index 6d63b8798c29..56e575c79bb4 100644 --- a/drivers/cxl/core/region.c +++ b/drivers/cxl/core/region.c @@ -28,12 +28,6 @@ * 3. Decoder targets */ -/* - * All changes to the interleave configuration occur with this lock held - * for write. - */ -static DECLARE_RWSEM(cxl_region_rwsem); - static struct cxl_region *to_cxl_region(struct device *dev); static ssize_t uuid_show(struct device *dev, struct device_attribute *attr, @@ -129,7 +123,7 @@ static int cxl_region_invalidate_memregion(struct cxl_region *cxlr) { if (!cpu_cache_has_invalidate_memregion()) { if (IS_ENABLED(CONFIG_CXL_REGION_INVALIDATION_TEST)) { - dev_warn_once( + dev_info_once( &cxlr->dev, "Bypassing cpu_cache_invalidate_memregion() for testing!\n"); return 0; @@ -294,7 +288,7 @@ static ssize_t commit_store(struct device *dev, struct device_attribute *attr, */ rc = cxl_region_invalidate_memregion(cxlr); if (rc) - return rc; + goto out; if (commit) { rc = cxl_region_decode_commit(cxlr); @@ -1133,7 +1127,14 @@ static int cxl_port_setup_targets(struct cxl_port *port, } if (is_cxl_root(parent_port)) { - parent_ig = cxlrd->cxlsd.cxld.interleave_granularity; + /* + * Root decoder IG is always set to value in CFMWS which + * may be different than this region's IG. We can use the + * region's IG here since interleave_granularity_store() + * does not allow interleaved host-bridges with + * root IG != region IG. + */ + parent_ig = p->interleave_granularity; parent_iw = cxlrd->cxlsd.cxld.interleave_ways; /* * For purposes of address bit routing, use power-of-2 math for @@ -1195,6 +1196,14 @@ static int cxl_port_setup_targets(struct cxl_port *port, return rc; } + if (iw > 8 || iw > cxlsd->nr_targets) { + dev_dbg(&cxlr->dev, + "%s:%s:%s: ways: %d overflows targets: %d\n", + dev_name(port->uport_dev), dev_name(&port->dev), + dev_name(&cxld->dev), iw, cxlsd->nr_targets); + return -ENXIO; + } + if (test_bit(CXL_REGION_F_AUTO, &cxlr->flags)) { if (cxld->interleave_ways != iw || cxld->interleave_granularity != ig || @@ -1480,6 +1489,14 @@ static int cxl_region_attach_auto(struct cxl_region *cxlr, return 0; } +static int cmp_interleave_pos(const void *a, const void *b) +{ + struct cxl_endpoint_decoder *cxled_a = *(typeof(cxled_a) *)a; + struct cxl_endpoint_decoder *cxled_b = *(typeof(cxled_b) *)b; + + return cxled_a->pos - cxled_b->pos; +} + static struct cxl_port *next_port(struct cxl_port *port) { if (!port->parent_dport) @@ -1487,119 +1504,127 @@ static struct cxl_port *next_port(struct cxl_port *port) return port->parent_dport->port; } -static int decoder_match_range(struct device *dev, void *data) +static int match_switch_decoder_by_range(struct device *dev, void *data) { - struct cxl_endpoint_decoder *cxled = data; struct cxl_switch_decoder *cxlsd; + struct range *r1, *r2 = data; if (!is_switch_decoder(dev)) return 0; cxlsd = to_cxl_switch_decoder(dev); - return range_contains(&cxlsd->cxld.hpa_range, &cxled->cxld.hpa_range); -} - -static void find_positions(const struct cxl_switch_decoder *cxlsd, - const struct cxl_port *iter_a, - const struct cxl_port *iter_b, int *a_pos, - int *b_pos) -{ - int i; + r1 = &cxlsd->cxld.hpa_range; - for (i = 0, *a_pos = -1, *b_pos = -1; i < cxlsd->nr_targets; i++) { - if (cxlsd->target[i] == iter_a->parent_dport) - *a_pos = i; - else if (cxlsd->target[i] == iter_b->parent_dport) - *b_pos = i; - if (*a_pos >= 0 && *b_pos >= 0) - break; - } + if (is_root_decoder(dev)) + return range_contains(r1, r2); + return (r1->start == r2->start && r1->end == r2->end); } -static int cmp_decode_pos(const void *a, const void *b) +static int find_pos_and_ways(struct cxl_port *port, struct range *range, + int *pos, int *ways) { - struct cxl_endpoint_decoder *cxled_a = *(typeof(cxled_a) *)a; - struct cxl_endpoint_decoder *cxled_b = *(typeof(cxled_b) *)b; - struct cxl_memdev *cxlmd_a = cxled_to_memdev(cxled_a); - struct cxl_memdev *cxlmd_b = cxled_to_memdev(cxled_b); - struct cxl_port *port_a = cxled_to_port(cxled_a); - struct cxl_port *port_b = cxled_to_port(cxled_b); - struct cxl_port *iter_a, *iter_b, *port = NULL; struct cxl_switch_decoder *cxlsd; + struct cxl_port *parent; struct device *dev; - int a_pos, b_pos; - unsigned int seq; - - /* Exit early if any prior sorting failed */ - if (cxled_a->pos < 0 || cxled_b->pos < 0) - return 0; + int rc = -ENXIO; - /* - * Walk up the hierarchy to find a shared port, find the decoder that - * maps the range, compare the relative position of those dport - * mappings. - */ - for (iter_a = port_a; iter_a; iter_a = next_port(iter_a)) { - struct cxl_port *next_a, *next_b; + parent = next_port(port); + if (!parent) + return rc; - next_a = next_port(iter_a); - if (!next_a) - break; + dev = device_find_child(&parent->dev, range, + match_switch_decoder_by_range); + if (!dev) { + dev_err(port->uport_dev, + "failed to find decoder mapping %#llx-%#llx\n", + range->start, range->end); + return rc; + } + cxlsd = to_cxl_switch_decoder(dev); + *ways = cxlsd->cxld.interleave_ways; - for (iter_b = port_b; iter_b; iter_b = next_port(iter_b)) { - next_b = next_port(iter_b); - if (next_a != next_b) - continue; - port = next_a; + for (int i = 0; i < *ways; i++) { + if (cxlsd->target[i] == port->parent_dport) { + *pos = i; + rc = 0; break; } - - if (port) - break; } + put_device(dev); - if (!port) { - dev_err(cxlmd_a->dev.parent, - "failed to find shared port with %s\n", - dev_name(cxlmd_b->dev.parent)); - goto err; - } + return rc; +} - dev = device_find_child(&port->dev, cxled_a, decoder_match_range); - if (!dev) { - struct range *range = &cxled_a->cxld.hpa_range; +/** + * cxl_calc_interleave_pos() - calculate an endpoint position in a region + * @cxled: endpoint decoder member of given region + * + * The endpoint position is calculated by traversing the topology from + * the endpoint to the root decoder and iteratively applying this + * calculation: + * + * position = position * parent_ways + parent_pos; + * + * ...where @position is inferred from switch and root decoder target lists. + * + * Return: position >= 0 on success + * -ENXIO on failure + */ +static int cxl_calc_interleave_pos(struct cxl_endpoint_decoder *cxled) +{ + struct cxl_port *iter, *port = cxled_to_port(cxled); + struct cxl_memdev *cxlmd = cxled_to_memdev(cxled); + struct range *range = &cxled->cxld.hpa_range; + int parent_ways = 0, parent_pos = 0, pos = 0; + int rc; - dev_err(port->uport_dev, - "failed to find decoder that maps %#llx-%#llx\n", - range->start, range->end); - goto err; - } + /* + * Example: the expected interleave order of the 4-way region shown + * below is: mem0, mem2, mem1, mem3 + * + * root_port + * / \ + * host_bridge_0 host_bridge_1 + * | | | | + * mem0 mem1 mem2 mem3 + * + * In the example the calculator will iterate twice. The first iteration + * uses the mem position in the host-bridge and the ways of the host- + * bridge to generate the first, or local, position. The second + * iteration uses the host-bridge position in the root_port and the ways + * of the root_port to refine the position. + * + * A trace of the calculation per endpoint looks like this: + * mem0: pos = 0 * 2 + 0 mem2: pos = 0 * 2 + 0 + * pos = 0 * 2 + 0 pos = 0 * 2 + 1 + * pos: 0 pos: 1 + * + * mem1: pos = 0 * 2 + 1 mem3: pos = 0 * 2 + 1 + * pos = 1 * 2 + 0 pos = 1 * 2 + 1 + * pos: 2 pos = 3 + * + * Note that while this example is simple, the method applies to more + * complex topologies, including those with switches. + */ - cxlsd = to_cxl_switch_decoder(dev); - do { - seq = read_seqbegin(&cxlsd->target_lock); - find_positions(cxlsd, iter_a, iter_b, &a_pos, &b_pos); - } while (read_seqretry(&cxlsd->target_lock, seq)); + /* Iterate from endpoint to root_port refining the position */ + for (iter = port; iter; iter = next_port(iter)) { + if (is_cxl_root(iter)) + break; - put_device(dev); + rc = find_pos_and_ways(iter, range, &parent_pos, &parent_ways); + if (rc) + return rc; - if (a_pos < 0 || b_pos < 0) { - dev_err(port->uport_dev, - "failed to find shared decoder for %s and %s\n", - dev_name(cxlmd_a->dev.parent), - dev_name(cxlmd_b->dev.parent)); - goto err; + pos = pos * parent_ways + parent_pos; } - dev_dbg(port->uport_dev, "%s comes %s %s\n", - dev_name(cxlmd_a->dev.parent), - a_pos - b_pos < 0 ? "before" : "after", - dev_name(cxlmd_b->dev.parent)); + dev_dbg(&cxlmd->dev, + "decoder:%s parent:%s port:%s range:%#llx-%#llx pos:%d\n", + dev_name(&cxled->cxld.dev), dev_name(cxlmd->dev.parent), + dev_name(&port->dev), range->start, range->end, pos); - return a_pos - b_pos; -err: - cxled_a->pos = -1; - return 0; + return pos; } static int cxl_region_sort_targets(struct cxl_region *cxlr) @@ -1607,22 +1632,21 @@ static int cxl_region_sort_targets(struct cxl_region *cxlr) struct cxl_region_params *p = &cxlr->params; int i, rc = 0; - sort(p->targets, p->nr_targets, sizeof(p->targets[0]), cmp_decode_pos, - NULL); - for (i = 0; i < p->nr_targets; i++) { struct cxl_endpoint_decoder *cxled = p->targets[i]; + cxled->pos = cxl_calc_interleave_pos(cxled); /* - * Record that sorting failed, but still continue to restore - * cxled->pos with its ->targets[] position so that follow-on - * code paths can reliably do p->targets[cxled->pos] to - * self-reference their entry. + * Record that sorting failed, but still continue to calc + * cxled->pos so that follow-on code paths can reliably + * do p->targets[cxled->pos] to self-reference their entry. */ if (cxled->pos < 0) rc = -ENXIO; - cxled->pos = i; } + /* Keep the cxlr target list in interleave position order */ + sort(p->targets, p->nr_targets, sizeof(p->targets[0]), + cmp_interleave_pos, NULL); dev_dbg(&cxlr->dev, "region sort %s\n", rc ? "failed" : "successful"); return rc; @@ -1658,6 +1682,12 @@ static int cxl_region_attach(struct cxl_region *cxlr, return -ENXIO; } + if (p->nr_targets >= p->interleave_ways) { + dev_dbg(&cxlr->dev, "region already has %d endpoints\n", + p->nr_targets); + return -EINVAL; + } + ep_port = cxled_to_port(cxled); root_port = cxlrd_to_port(cxlrd); dport = cxl_find_dport_by_dev(root_port, ep_port->host_bridge); @@ -1750,7 +1780,7 @@ static int cxl_region_attach(struct cxl_region *cxlr, if (p->nr_targets == p->interleave_ways) { rc = cxl_region_setup_targets(cxlr); if (rc) - goto err_decrement; + return rc; p->state = CXL_CONFIG_ACTIVE; } @@ -1761,13 +1791,27 @@ static int cxl_region_attach(struct cxl_region *cxlr, .end = p->res->end, }; - return 0; + if (p->nr_targets != p->interleave_ways) + return 0; -err_decrement: - p->nr_targets--; - cxled->pos = -1; - p->targets[pos] = NULL; - return rc; + /* + * Test the auto-discovery position calculator function + * against this successfully created user-defined region. + * A fail message here means that this interleave config + * will fail when presented as CXL_REGION_F_AUTO. + */ + for (int i = 0; i < p->nr_targets; i++) { + struct cxl_endpoint_decoder *cxled = p->targets[i]; + int test_pos; + + test_pos = cxl_calc_interleave_pos(cxled); + dev_dbg(&cxled->cxld.dev, + "Test cxl_calc_interleave_pos(): %s test_pos:%d cxled->pos:%d\n", + (test_pos == cxled->pos) ? "success" : "fail", + test_pos, cxled->pos); + } + + return 0; } static int cxl_region_detach(struct cxl_endpoint_decoder *cxled) @@ -2696,7 +2740,7 @@ err: return rc; } -static int match_decoder_by_range(struct device *dev, void *data) +static int match_root_decoder_by_range(struct device *dev, void *data) { struct range *r1, *r2 = data; struct cxl_root_decoder *cxlrd; @@ -2827,7 +2871,7 @@ int cxl_add_to_region(struct cxl_port *root, struct cxl_endpoint_decoder *cxled) int rc; cxlrd_dev = device_find_child(&root->dev, &cxld->hpa_range, - match_decoder_by_range); + match_root_decoder_by_range); if (!cxlrd_dev) { dev_err(cxlmd->dev.parent, "%s:%s no CXL window for range %#llx:%#llx\n", |