"io_alloc" feature is a mechanism that enables direct insertion of data from I/O devices into the L3 cache. By directly caching data from I/O devices rather than first storing the I/O data in DRAM, it reduces the demands on DRAM bandwidth and reduces latency to the processor consuming the I/O data. io_alloc feature uses the highest CLOSID to route the traffic from I/O devices. Provide the interface to modify io_alloc CBMs (Capacity Bit Mask) when feature is enabled. Signed-off-by: Babu Moger <babu.moger@xxxxxxx> --- v4: Removed resctrl_io_alloc_parse_cbm and called parse_cbm() directly. v3: Minor changes due to changes in resctrl_arch_get_io_alloc_enabled() and resctrl_io_alloc_closid_get(). Taken care of handling the CBM update when CDP is enabled. Updated the commit log to make it generic. v2: Added more generic text in documentation. --- Documentation/arch/x86/resctrl.rst | 21 +++++ arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 4 +- arch/x86/kernel/cpu/resctrl/internal.h | 2 + arch/x86/kernel/cpu/resctrl/rdtgroup.c | 108 +++++++++++++++++++++- 4 files changed, 132 insertions(+), 3 deletions(-) diff --git a/Documentation/arch/x86/resctrl.rst b/Documentation/arch/x86/resctrl.rst index 7672c5c52c1a..6fdea77a1675 100644 --- a/Documentation/arch/x86/resctrl.rst +++ b/Documentation/arch/x86/resctrl.rst @@ -169,6 +169,27 @@ related to allocation: When CDP is enabled, io_alloc routes I/O traffic using the highest CLOSID allocated for the instruction cache (L3CODE). +"io_alloc_cbm": + Capacity Bit Masks (CBMs) available to supported IO devices which + can directly insert cache lines in L3 which can help to reduce the + latency. CBM can be configured by writing to the interface in the + following format:: + + <resource_name>:<cache_id0>=<cbm>;<cache_id1>=<cbm>;... + + Example:: + + # cat /sys/fs/resctrl/info/L3/io_alloc_cbm + L3:0=ffff;1=ffff + + # echo L3:1=FF > /sys/fs/resctrl/info/L3/io_alloc_cbm + # cat /sys/fs/resctrl/info/L3/io_alloc_cbm + L3:0=ffff;1=00ff + + When CDP is enabled, L3 control is divided into two separate resources: + L3CODE and L3DATA. However, the CBM can only be updated on the L3CODE + resource. + Memory bandwidth(MB) subdirectory contains the following files with respect to allocation: diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index e5d1e77e1995..315584415cc4 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -148,8 +148,8 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) * Read one cache bit mask (hex). Check that it is valid for the current * resource type. */ -static int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s, - struct rdt_ctrl_domain *d) +int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s, + struct rdt_ctrl_domain *d) { enum rdtgrp_mode mode = data->mode; struct resctrl_staged_config *cfg; diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 92246d2b91c8..1d3b60741a39 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -526,6 +526,8 @@ void rdt_staged_configs_clear(void); bool closid_allocated(unsigned int closid); int resctrl_find_cleanest_closid(void); void show_doms(struct seq_file *s, struct resctrl_schema *schema, int closid); +int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s, + struct rdt_ctrl_domain *d); #ifdef CONFIG_RESCTRL_FS_PSEUDO_LOCK int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp); diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 5633437ea85d..73532c363e57 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -2082,6 +2082,111 @@ static int resctrl_io_alloc_cbm_show(struct kernfs_open_file *of, return ret; } +static int resctrl_io_alloc_parse_line(char *line, struct rdt_resource *r, + struct resctrl_schema *s, u32 closid) +{ + struct rdt_parse_data data; + struct rdt_ctrl_domain *d; + char *dom = NULL, *id; + unsigned long dom_id; + +next: + if (!line || line[0] == '\0') + return 0; + + dom = strsep(&line, ";"); + id = strsep(&dom, "="); + if (!dom || kstrtoul(id, 10, &dom_id)) { + rdt_last_cmd_puts("Missing '=' or non-numeric domain\n"); + return -EINVAL; + } + + dom = strim(dom); + list_for_each_entry(d, &r->ctrl_domains, hdr.list) { + if (d->hdr.id == dom_id) { + data.buf = dom; + data.mode = RDT_MODE_SHAREABLE; + data.closid = closid; + if (parse_cbm(&data, s, d)) + return -EINVAL; + goto next; + } + } + return -EINVAL; +} + +static ssize_t resctrl_io_alloc_cbm_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct resctrl_schema *s = rdt_kn_parent_priv(of->kn); + struct rdt_resource *r = s->res; + u32 io_alloc_closid; + char *resname; + int ret = 0; + + /* Valid input requires a trailing newline */ + if (nbytes == 0 || buf[nbytes - 1] != '\n') + return -EINVAL; + + buf[nbytes - 1] = '\0'; + + if (!r->cache.io_alloc_capable || s->conf_type == CDP_DATA) { + rdt_last_cmd_puts("io_alloc feature is not supported on the resource\n"); + return -EINVAL; + } + + cpus_read_lock(); + mutex_lock(&rdtgroup_mutex); + + rdt_last_cmd_clear(); + rdt_staged_configs_clear(); + + if (!resctrl_arch_get_io_alloc_enabled(r)) { + rdt_last_cmd_puts("io_alloc feature is not enabled\n"); + ret = -EINVAL; + goto cbm_write_out; + } + + resname = strim(strsep(&buf, ":")); + if (!buf) { + rdt_last_cmd_puts("Missing ':'\n"); + ret = -EINVAL; + goto cbm_write_out; + } + + if (strcmp(resname, s->name)) { + rdt_last_cmd_printf("Unsupported resource name '%s'\n", resname); + ret = -EINVAL; + goto cbm_write_out; + } + + if (buf[0] == '\0') { + rdt_last_cmd_printf("Missing '%s' value\n", resname); + ret = -EINVAL; + goto cbm_write_out; + } + + io_alloc_closid = resctrl_io_alloc_closid_get(r, s); + if (io_alloc_closid < 0) { + rdt_last_cmd_puts("Max CLOSID to support io_alloc is not available\n"); + ret = -EINVAL; + goto cbm_write_out; + } + + ret = resctrl_io_alloc_parse_line(buf, r, s, io_alloc_closid); + if (ret) + goto cbm_write_out; + + ret = resctrl_arch_update_domains(r, io_alloc_closid); + +cbm_write_out: + rdt_staged_configs_clear(); + mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); + + return ret ?: nbytes; +} + /* rdtgroup information files for one cache resource. */ static struct rftype res_common_files[] = { { @@ -2243,9 +2348,10 @@ static struct rftype res_common_files[] = { }, { .name = "io_alloc_cbm", - .mode = 0444, + .mode = 0644, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = resctrl_io_alloc_cbm_show, + .write = resctrl_io_alloc_cbm_write, }, { .name = "mba_MBps_event", -- 2.34.1