From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 6528714A4E9 for ; Wed, 3 Apr 2024 15:48:55 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1712159335; cv=none; b=Hea1muie+QsKZrWNwEUw7wMKIGrE53biJ49IKFdz54CTRMGdrX0QLOKZnEDcWlt2dGqCvYdYksxzuxtLw1YvvITZCYnpV/+LYuBozlbBjbryCN9t+jO7lr9NgYudBhfJC3NwDYWdCnP24uVjQcoiERVkDmaP16mZD+Rafph8XeI= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1712159335; c=relaxed/simple; bh=nJNFKlv73g0DT9py/HgjU/6jc7XHeNQgoNWKfJOhUOA=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=RFkw0WS3oMUtC22DFICL9J/xL9UJyNrzJUoQ7guiaQk0SxZBAh9jLYRhL2ig4AyN2Tv/herUblICo60NDc/NbrdHn4gfOaHCtXCFxf8ZLZRPmjJ0eorcLbSJyn4pueL6oUW7vk74WdyTAZmYOnvlJJtirBkdNCuSxNOA4NHK6Qw= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 Received: by smtp.kernel.org (Postfix) with ESMTPSA id E1E18C433F1; Wed, 3 Apr 2024 15:48:54 +0000 (UTC) From: Dave Jiang To: linux-cxl@vger.kernel.org Cc: dan.j.williams@intel.com, ira.weiny@intel.com, vishal.l.verma@intel.com, alison.schofield@intel.com, Jonathan.Cameron@huawei.com, dave@stgolabs.net Subject: [PATCH v7 4/5] cxl: Consolidate dport access_coordinate ->hb_coord and ->sw_coord into ->coord Date: Wed, 3 Apr 2024 08:47:15 -0700 Message-ID: <20240403154844.3403859-5-dave.jiang@intel.com> X-Mailer: git-send-email 2.44.0 In-Reply-To: <20240403154844.3403859-1-dave.jiang@intel.com> References: <20240403154844.3403859-1-dave.jiang@intel.com> Precedence: bulk X-Mailing-List: linux-cxl@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit The driver stores access_coordinate for host bridge in ->hb_coord and switch CDAT access_coordinate in ->sw_coord. Since neither of these access_coordinate clobber each other, the variable name can be consolidated into ->coord to simplify the code. Reviewed-by: Jonathan Cameron Reviewed-by: Davidlohr Bueso Reviewed-by: Dan Williams Signed-off-by: Dave Jiang --- v7: - Adjusted based on code changes from pervious patches --- drivers/cxl/acpi.c | 2 +- drivers/cxl/core/cdat.c | 74 +++++++++++++++++++++++------------- drivers/cxl/core/port.c | 48 +++++++++++++++++------ drivers/cxl/cxl.h | 6 +-- drivers/cxl/cxlmem.h | 2 +- tools/testing/cxl/test/cxl.c | 10 +++-- 6 files changed, 94 insertions(+), 48 deletions(-) diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c index 566c387d4385..cb8c155a2c9b 100644 --- a/drivers/cxl/acpi.c +++ b/drivers/cxl/acpi.c @@ -529,7 +529,7 @@ static int get_genport_coordinates(struct device *dev, struct cxl_dport *dport) if (kstrtou32(acpi_device_uid(hb), 0, &uid)) return -EINVAL; - return acpi_get_genport_coordinates(uid, dport->hb_coord); + return acpi_get_genport_coordinates(uid, dport->coord); } static int add_host_bridge_dport(struct device *match, void *arg) diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c index 48704976693e..4b717d2f5a9d 100644 --- a/drivers/cxl/core/cdat.c +++ b/drivers/cxl/core/cdat.c @@ -14,7 +14,7 @@ struct dsmas_entry { struct range dpa_range; u8 handle; - struct access_coordinate coord; + struct access_coordinate coord[ACCESS_COORDINATE_MAX]; int entries; int qos_class; @@ -83,8 +83,8 @@ static int cdat_dsmas_handler(union acpi_subtable_headers *header, void *arg, return 0; } -static void cxl_access_coordinate_set(struct access_coordinate *coord, - int access, unsigned int val) +static void __cxl_access_coordinate_set(struct access_coordinate *coord, + int access, unsigned int val) { switch (access) { case ACPI_HMAT_ACCESS_LATENCY: @@ -110,6 +110,13 @@ static void cxl_access_coordinate_set(struct access_coordinate *coord, } } +static void cxl_access_coordinate_set(struct access_coordinate *coord, + int access, unsigned int val) +{ + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) + __cxl_access_coordinate_set(&coord[i], access, val); +} + static int cdat_dslbis_handler(union acpi_subtable_headers *header, void *arg, const unsigned long end) { @@ -151,7 +158,7 @@ static int cdat_dslbis_handler(union acpi_subtable_headers *header, void *arg, val = cdat_normalize(le16_to_cpu(le_val), le64_to_cpu(le_base), dslbis->data_type); - cxl_access_coordinate_set(&dent->coord, dslbis->data_type, val); + cxl_access_coordinate_set(dent->coord, dslbis->data_type, val); return 0; } @@ -185,13 +192,13 @@ static int cxl_cdat_endpoint_process(struct cxl_port *port, static int cxl_port_perf_data_calculate(struct cxl_port *port, struct xarray *dsmas_xa) { - struct access_coordinate ep_c; + struct access_coordinate ep_c[ACCESS_COORDINATE_MAX]; struct dsmas_entry *dent; int valid_entries = 0; unsigned long index; int rc; - rc = cxl_endpoint_get_perf_coordinates(port, &ep_c); + rc = cxl_endpoint_get_perf_coordinates(port, ep_c); if (rc) { dev_dbg(&port->dev, "Failed to retrieve ep perf coordinates.\n"); return rc; @@ -208,10 +215,11 @@ static int cxl_port_perf_data_calculate(struct cxl_port *port, xa_for_each(dsmas_xa, index, dent) { int qos_class; - cxl_coordinates_combine(&dent->coord, &dent->coord, &ep_c); + cxl_coordinates_combine(dent->coord, dent->coord, ep_c); dent->entries = 1; - rc = cxl_root->ops->qos_class(cxl_root, &dent->coord, 1, - &qos_class); + rc = cxl_root->ops->qos_class(cxl_root, + &dent->coord[ACCESS_COORDINATE_CPU], + 1, &qos_class); if (rc != 1) continue; @@ -228,14 +236,17 @@ static int cxl_port_perf_data_calculate(struct cxl_port *port, static void update_perf_entry(struct device *dev, struct dsmas_entry *dent, struct cxl_dpa_perf *dpa_perf) { + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) + dpa_perf->coord[i] = dent->coord[i]; dpa_perf->dpa_range = dent->dpa_range; - dpa_perf->coord = dent->coord; dpa_perf->qos_class = dent->qos_class; dev_dbg(dev, "DSMAS: dpa: %#llx qos: %d read_bw: %d write_bw %d read_lat: %d write_lat: %d\n", dent->dpa_range.start, dpa_perf->qos_class, - dent->coord.read_bandwidth, dent->coord.write_bandwidth, - dent->coord.read_latency, dent->coord.write_latency); + dent->coord[ACCESS_COORDINATE_CPU].read_bandwidth, + dent->coord[ACCESS_COORDINATE_CPU].write_bandwidth, + dent->coord[ACCESS_COORDINATE_CPU].read_latency, + dent->coord[ACCESS_COORDINATE_CPU].write_latency); } static void cxl_memdev_set_qos_class(struct cxl_dev_state *cxlds, @@ -472,10 +483,11 @@ static int cdat_sslbis_handler(union acpi_subtable_headers *header, void *arg, xa_for_each(&port->dports, index, dport) { if (dsp_id == ACPI_CDAT_SSLBIS_ANY_PORT || - dsp_id == dport->port_id) - cxl_access_coordinate_set(&dport->sw_coord, + dsp_id == dport->port_id) { + cxl_access_coordinate_set(dport->coord, sslbis->data_type, val); + } } } @@ -497,6 +509,21 @@ void cxl_switch_parse_cdat(struct cxl_port *port) } EXPORT_SYMBOL_NS_GPL(cxl_switch_parse_cdat, CXL); +static void __cxl_coordinates_combine(struct access_coordinate *out, + struct access_coordinate *c1, + struct access_coordinate *c2) +{ + if (c1->write_bandwidth && c2->write_bandwidth) + out->write_bandwidth = min(c1->write_bandwidth, + c2->write_bandwidth); + out->write_latency = c1->write_latency + c2->write_latency; + + if (c1->read_bandwidth && c2->read_bandwidth) + out->read_bandwidth = min(c1->read_bandwidth, + c2->read_bandwidth); + out->read_latency = c1->read_latency + c2->read_latency; +} + /** * cxl_coordinates_combine - Combine the two input coordinates * @@ -508,15 +535,8 @@ void cxl_coordinates_combine(struct access_coordinate *out, struct access_coordinate *c1, struct access_coordinate *c2) { - if (c1->write_bandwidth && c2->write_bandwidth) - out->write_bandwidth = min(c1->write_bandwidth, - c2->write_bandwidth); - out->write_latency = c1->write_latency + c2->write_latency; - - if (c1->read_bandwidth && c2->read_bandwidth) - out->read_bandwidth = min(c1->read_bandwidth, - c2->read_bandwidth); - out->read_latency = c1->read_latency + c2->read_latency; + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) + __cxl_coordinates_combine(&out[i], &c1[i], &c2[i]); } MODULE_IMPORT_NS(CXL); @@ -553,12 +573,12 @@ void cxl_region_perf_data_calculate(struct cxl_region *cxlr, /* Get total bandwidth and the worst latency for the cxl region */ cxlr->coord[i].read_latency = max_t(unsigned int, cxlr->coord[i].read_latency, - perf->coord.read_latency); + perf->coord[i].read_latency); cxlr->coord[i].write_latency = max_t(unsigned int, cxlr->coord[i].write_latency, - perf->coord.write_latency); - cxlr->coord[i].read_bandwidth += perf->coord.read_bandwidth; - cxlr->coord[i].write_bandwidth += perf->coord.write_bandwidth; + perf->coord[i].write_latency); + cxlr->coord[i].read_bandwidth += perf->coord[i].read_bandwidth; + cxlr->coord[i].write_bandwidth += perf->coord[i].write_bandwidth; } } diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c index c7c00eb373af..801c4018a1dd 100644 --- a/drivers/cxl/core/port.c +++ b/drivers/cxl/core/port.c @@ -2133,6 +2133,29 @@ bool schedule_cxl_memdev_detach(struct cxl_memdev *cxlmd) } EXPORT_SYMBOL_NS_GPL(schedule_cxl_memdev_detach, CXL); +static void add_latency(struct access_coordinate *c, long latency) +{ + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) { + c[i].write_latency += latency; + c[i].read_latency += latency; + } +} + +static void set_min_bandwidth(struct access_coordinate *c, unsigned int bw) +{ + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) { + c[i].write_bandwidth = min(c[i].write_bandwidth, bw); + c[i].read_bandwidth = min(c[i].read_bandwidth, bw); + } +} + +static void set_access_coordinates(struct access_coordinate *out, + struct access_coordinate *in) +{ + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) + out[i] = in[i]; +} + static bool parent_port_is_cxl_root(struct cxl_port *port) { return is_cxl_root(to_cxl_port(port->dev.parent)); @@ -2149,9 +2172,15 @@ static bool parent_port_is_cxl_root(struct cxl_port *port) int cxl_endpoint_get_perf_coordinates(struct cxl_port *port, struct access_coordinate *coord) { - struct access_coordinate c = { - .read_bandwidth = UINT_MAX, - .write_bandwidth = UINT_MAX, + struct access_coordinate c[] = { + { + .read_bandwidth = UINT_MAX, + .write_bandwidth = UINT_MAX, + }, + { + .read_bandwidth = UINT_MAX, + .write_bandwidth = UINT_MAX, + }, }; struct cxl_port *iter = port; struct cxl_dport *dport; @@ -2178,14 +2207,13 @@ int cxl_endpoint_get_perf_coordinates(struct cxl_port *port, * have CDAT and therefore needs to be skipped. */ if (!is_cxl_root) - cxl_coordinates_combine(&c, &c, &dport->sw_coord); - c.write_latency += dport->link_latency; - c.read_latency += dport->link_latency; + cxl_coordinates_combine(c, c, dport->coord); + add_latency(c, dport->link_latency); } while (!is_cxl_root); dport = iter->parent_dport; /* Retrieve HB coords */ - cxl_coordinates_combine(&c, &c, dport->hb_coord); + cxl_coordinates_combine(c, c, dport->coord); /* Get the calculated PCI paths bandwidth */ pdev = to_pci_dev(port->uport_dev->parent); @@ -2194,10 +2222,8 @@ int cxl_endpoint_get_perf_coordinates(struct cxl_port *port, return -ENXIO; bw /= BITS_PER_BYTE; - c.write_bandwidth = min(c.write_bandwidth, bw); - c.read_bandwidth = min(c.read_bandwidth, bw); - - *coord = c; + set_min_bandwidth(c, bw); + set_access_coordinates(coord, c); return 0; } diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h index ed02373ce3d9..036d17db68e0 100644 --- a/drivers/cxl/cxl.h +++ b/drivers/cxl/cxl.h @@ -663,8 +663,7 @@ struct cxl_rcrb_info { * @rch: Indicate whether this dport was enumerated in RCH or VH mode * @port: reference to cxl_port that contains this downstream port * @regs: Dport parsed register blocks - * @sw_coord: access coordinates (performance) for switch from CDAT - * @hb_coord: access coordinates (performance) from ACPI generic port (host bridge) + * @coord: access coordinates (bandwidth and latency performance attributes) * @link_latency: calculated PCIe downstream latency */ struct cxl_dport { @@ -675,8 +674,7 @@ struct cxl_dport { bool rch; struct cxl_port *port; struct cxl_regs regs; - struct access_coordinate sw_coord; - struct access_coordinate hb_coord[ACCESS_COORDINATE_MAX]; + struct access_coordinate coord[ACCESS_COORDINATE_MAX]; long link_latency; }; diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index 20fb3b35e89e..36cee9c30ceb 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -401,7 +401,7 @@ enum cxl_devtype { */ struct cxl_dpa_perf { struct range dpa_range; - struct access_coordinate coord; + struct access_coordinate coord[ACCESS_COORDINATE_MAX]; int qos_class; }; diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c index 908e0d083936..61c69297e797 100644 --- a/tools/testing/cxl/test/cxl.c +++ b/tools/testing/cxl/test/cxl.c @@ -986,10 +986,12 @@ static void dpa_perf_setup(struct cxl_port *endpoint, struct range *range, { dpa_perf->qos_class = FAKE_QTG_ID; dpa_perf->dpa_range = *range; - dpa_perf->coord.read_latency = 500; - dpa_perf->coord.write_latency = 500; - dpa_perf->coord.read_bandwidth = 1000; - dpa_perf->coord.write_bandwidth = 1000; + for (int i = 0; i < ACCESS_COORDINATE_MAX; i++) { + dpa_perf->coord[i].read_latency = 500; + dpa_perf->coord[i].write_latency = 500; + dpa_perf->coord[i].read_bandwidth = 1000; + dpa_perf->coord[i].write_bandwidth = 1000; + } } static void mock_cxl_endpoint_parse_cdat(struct cxl_port *port) -- 2.44.0