From f05fd4ce99635975caa3e6a0eeb02118637f72a3 Mon Sep 17 00:00:00 2001 From: Maciej Wieczor-Retman Date: Wed, 11 Oct 2023 08:48:42 +0200 Subject: [PATCH 01/14] x86/resctrl: Fix remaining kernel-doc warnings The kernel test robot reported kernel-doc warnings here: arch/x86/kernel/cpu/resctrl/rdtgroup.c:915: warning: Function parameter or member 'of' not described in 'rdt_bit_usage_show' arch/x86/kernel/cpu/resctrl/rdtgroup.c:915: warning: Function parameter or member 'seq' not described in 'rdt_bit_usage_show' arch/x86/kernel/cpu/resctrl/rdtgroup.c:915: warning: Function parameter or member 'v' not described in 'rdt_bit_usage_show' arch/x86/kernel/cpu/resctrl/rdtgroup.c:1144: warning: Function parameter or member 'type' not described in '__rdtgroup_cbm_overlaps' arch/x86/kernel/cpu/resctrl/rdtgroup.c:1224: warning: Function parameter or member 'rdtgrp' not described in 'rdtgroup_mode_test_exclusive' arch/x86/kernel/cpu/resctrl/rdtgroup.c:1261: warning: Function parameter or member 'of' not described in 'rdtgroup_mode_write' arch/x86/kernel/cpu/resctrl/rdtgroup.c:1261: warning: Function parameter or member 'buf' not described in 'rdtgroup_mode_write' arch/x86/kernel/cpu/resctrl/rdtgroup.c:1261: warning: Function parameter or member 'nbytes' not described in 'rdtgroup_mode_write' arch/x86/kernel/cpu/resctrl/rdtgroup.c:1261: warning: Function parameter or member 'off' not described in 'rdtgroup_mode_write' arch/x86/kernel/cpu/resctrl/rdtgroup.c:1370: warning: Function parameter or member 'of' not described in 'rdtgroup_size_show' arch/x86/kernel/cpu/resctrl/rdtgroup.c:1370: warning: Function parameter or member 's' not described in 'rdtgroup_size_show' arch/x86/kernel/cpu/resctrl/rdtgroup.c:1370: warning: Function parameter or member 'v' not described in 'rdtgroup_size_show' The first two functions are missing an argument description while the other three are file callbacks and don't require a kernel-doc comment. Closes: https://lore.kernel.org/oe-kbuild-all/202310070434.mD8eRNAz-lkp@intel.com/ Reported-by: kernel test robot Signed-off-by: Maciej Wieczor-Retman Signed-off-by: Ingo Molnar Cc: Peter Newman Cc: Borislav Petkov Cc: Reinette Chatre Link: https://lore.kernel.org/r/20231011064843.246592-1-maciej.wieczor-retman@intel.com --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 725344048f85..a52cdf97c21c 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -895,7 +895,7 @@ static int rdt_shareable_bits_show(struct kernfs_open_file *of, return 0; } -/** +/* * rdt_bit_usage_show - Display current usage of resources * * A domain is a shared resource that can now be allocated differently. Here @@ -1123,6 +1123,7 @@ static enum resctrl_conf_type resctrl_peer_type(enum resctrl_conf_type my_type) * @d: The domain instance for which @closid is being tested. * @cbm: Capacity bitmask being tested. * @closid: Intended closid for @cbm. + * @type: CDP type of @r. * @exclusive: Only check if overlaps with exclusive resource groups * * Checks if provided @cbm intended to be used for @closid on domain @@ -1209,6 +1210,7 @@ bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_domain *d, /** * rdtgroup_mode_test_exclusive - Test if this resource group can be exclusive + * @rdtgrp: Resource group identified through its closid. * * An exclusive resource group implies that there should be no sharing of * its allocated resources. At the time this group is considered to be @@ -1251,9 +1253,8 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) return true; } -/** +/* * rdtgroup_mode_write - Modify the resource group's mode - * */ static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) @@ -1357,12 +1358,11 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, return size; } -/** +/* * rdtgroup_size_show - Display size in bytes of allocated regions * * The "size" file mirrors the layout of the "schemata" file, printing the * size in bytes of each region instead of the capacity bitmask. - * */ static int rdtgroup_size_show(struct kernfs_open_file *of, struct seq_file *s, void *v) From 39c6eed1f61594f737160e498d29673edbd9eefd Mon Sep 17 00:00:00 2001 From: Maciej Wieczor-Retman Date: Tue, 10 Oct 2023 12:42:36 +0200 Subject: [PATCH 02/14] x86/resctrl: Rename arch_has_sparse_bitmaps MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Rename arch_has_sparse_bitmaps to arch_has_sparse_bitmasks to ensure consistent terminology throughout resctrl. Suggested-by: Reinette Chatre Signed-off-by: Maciej Wieczor-Retman Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Ilpo Järvinen Reviewed-by: Peter Newman Reviewed-by: Reinette Chatre Reviewed-by: Babu Moger Tested-by: Peter Newman Link: https://lore.kernel.org/r/e330fcdae873ef1a831e707025a4b70fa346666e.1696934091.git.maciej.wieczor-retman@intel.com --- arch/x86/kernel/cpu/resctrl/core.c | 4 ++-- arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 4 ++-- include/linux/resctrl.h | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 030d3b409768..c09e4fdded3c 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -872,7 +872,7 @@ static __init void rdt_init_res_defs_intel(void) if (r->rid == RDT_RESOURCE_L3 || r->rid == RDT_RESOURCE_L2) { - r->cache.arch_has_sparse_bitmaps = false; + r->cache.arch_has_sparse_bitmasks = false; r->cache.arch_has_per_cpu_cfg = false; r->cache.min_cbm_bits = 1; } else if (r->rid == RDT_RESOURCE_MBA) { @@ -892,7 +892,7 @@ static __init void rdt_init_res_defs_amd(void) if (r->rid == RDT_RESOURCE_L3 || r->rid == RDT_RESOURCE_L2) { - r->cache.arch_has_sparse_bitmaps = true; + r->cache.arch_has_sparse_bitmasks = true; r->cache.arch_has_per_cpu_cfg = true; r->cache.min_cbm_bits = 0; } else if (r->rid == RDT_RESOURCE_MBA) { diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index b44c487727d4..ab45012288bb 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -113,8 +113,8 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) first_bit = find_first_bit(&val, cbm_len); zero_bit = find_next_zero_bit(&val, cbm_len, first_bit); - /* Are non-contiguous bitmaps allowed? */ - if (!r->cache.arch_has_sparse_bitmaps && + /* Are non-contiguous bitmasks allowed? */ + if (!r->cache.arch_has_sparse_bitmasks && (find_next_bit(&val, cbm_len, zero_bit) < cbm_len)) { rdt_last_cmd_printf("The mask %lx has non-consecutive 1-bits\n", val); return false; diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index 8334eeacfec5..66942d7fba7f 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -94,7 +94,7 @@ struct rdt_domain { * zero CBM. * @shareable_bits: Bitmask of shareable resource with other * executing entities - * @arch_has_sparse_bitmaps: True if a bitmap like f00f is valid. + * @arch_has_sparse_bitmasks: True if a bitmask like f00f is valid. * @arch_has_per_cpu_cfg: True if QOS_CFG register for this cache * level has CPU scope. */ @@ -102,7 +102,7 @@ struct resctrl_cache { unsigned int cbm_len; unsigned int min_cbm_bits; unsigned int shareable_bits; - bool arch_has_sparse_bitmaps; + bool arch_has_sparse_bitmasks; bool arch_has_per_cpu_cfg; }; From 0e3cd31f6e9074886dea5a999bfcc563d144e7de Mon Sep 17 00:00:00 2001 From: Maciej Wieczor-Retman Date: Tue, 10 Oct 2023 12:42:37 +0200 Subject: [PATCH 03/14] x86/resctrl: Enable non-contiguous CBMs in Intel CAT MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The setting for non-contiguous 1s support in Intel CAT is hardcoded to false. On these systems, writing non-contiguous 1s into the schemata file will fail before resctrl passes the value to the hardware. In Intel CAT CPUID.0x10.1:ECX[3] and CPUID.0x10.2:ECX[3] stopped being reserved and now carry information about non-contiguous 1s value support for L3 and L2 cache respectively. The CAT capacity bitmask (CBM) supports a non-contiguous 1s value if the bit is set. The exception are Haswell systems where non-contiguous 1s value support needs to stay disabled since they can't make use of CPUID for Cache allocation. Originally-by: Fenghua Yu Signed-off-by: Maciej Wieczor-Retman Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Ilpo Järvinen Reviewed-by: Peter Newman Reviewed-by: Reinette Chatre Reviewed-by: Babu Moger Tested-by: Peter Newman Link: https://lore.kernel.org/r/1849b487256fe4de40b30f88450cba3d9abc9171.1696934091.git.maciej.wieczor-retman@intel.com --- arch/x86/kernel/cpu/resctrl/core.c | 9 ++++++--- arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 10 ++++++---- arch/x86/kernel/cpu/resctrl/internal.h | 9 +++++++++ 3 files changed, 21 insertions(+), 7 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index c09e4fdded3c..19e0681f0435 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -152,6 +152,7 @@ static inline void cache_alloc_hsw_probe(void) r->cache.cbm_len = 20; r->cache.shareable_bits = 0xc0000; r->cache.min_cbm_bits = 2; + r->cache.arch_has_sparse_bitmasks = false; r->alloc_capable = true; rdt_alloc_capable = true; @@ -267,15 +268,18 @@ static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r) { struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); union cpuid_0x10_1_eax eax; + union cpuid_0x10_x_ecx ecx; union cpuid_0x10_x_edx edx; - u32 ebx, ecx; + u32 ebx; - cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx, &edx.full); + cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx.full, &edx.full); hw_res->num_closid = edx.split.cos_max + 1; r->cache.cbm_len = eax.split.cbm_len + 1; r->default_ctrl = BIT_MASK(eax.split.cbm_len + 1) - 1; r->cache.shareable_bits = ebx & r->default_ctrl; r->data_width = (r->cache.cbm_len + 3) / 4; + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) + r->cache.arch_has_sparse_bitmasks = ecx.split.noncont; r->alloc_capable = true; } @@ -872,7 +876,6 @@ static __init void rdt_init_res_defs_intel(void) if (r->rid == RDT_RESOURCE_L3 || r->rid == RDT_RESOURCE_L2) { - r->cache.arch_has_sparse_bitmasks = false; r->cache.arch_has_per_cpu_cfg = false; r->cache.min_cbm_bits = 1; } else if (r->rid == RDT_RESOURCE_MBA) { diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index ab45012288bb..beccb0e87ba7 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -87,10 +87,12 @@ int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s, /* * Check whether a cache bit mask is valid. - * For Intel the SDM says: - * Please note that all (and only) contiguous '1' combinations - * are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.). - * Additionally Haswell requires at least two bits set. + * On Intel CPUs, non-contiguous 1s value support is indicated by CPUID: + * - CPUID.0x10.1:ECX[3]: L3 non-contiguous 1s value supported if 1 + * - CPUID.0x10.2:ECX[3]: L2 non-contiguous 1s value supported if 1 + * + * Haswell does not support a non-contiguous 1s value and additionally + * requires at least two bits set. * AMD allows non-contiguous bitmasks. */ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 85ceaf9a31ac..c47ef2f13e8e 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -492,6 +492,15 @@ union cpuid_0x10_3_eax { unsigned int full; }; +/* CPUID.(EAX=10H, ECX=ResID).ECX */ +union cpuid_0x10_x_ecx { + struct { + unsigned int reserved:3; + unsigned int noncont:1; + } split; + unsigned int full; +}; + /* CPUID.(EAX=10H, ECX=ResID).EDX */ union cpuid_0x10_x_edx { struct { From 4dba8f10b8fef9c5b0f9ed83dd1af91a1795ead1 Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Tue, 10 Oct 2023 12:42:38 +0200 Subject: [PATCH 04/14] x86/resctrl: Add sparse_masks file in info MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add the interface in resctrl FS to show if sparse cache allocation bit masks are supported on the platform. Reading the file returns either a "1" if non-contiguous 1s are supported and "0" otherwise. The file path is /sys/fs/resctrl/info/{resource}/sparse_masks, where {resource} can be either "L2" or "L3". Signed-off-by: Fenghua Yu Signed-off-by: Maciej Wieczor-Retman Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Ilpo Järvinen Reviewed-by: Peter Newman Reviewed-by: Reinette Chatre Reviewed-by: Babu Moger Tested-by: Peter Newman Link: https://lore.kernel.org/r/7300535160beba41fd8aa073749ec1ee29b4621f.1696934091.git.maciej.wieczor-retman@intel.com --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index a52cdf97c21c..09848ff11f7b 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -1117,6 +1117,17 @@ static enum resctrl_conf_type resctrl_peer_type(enum resctrl_conf_type my_type) } } +static int rdt_has_sparse_bitmasks_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct resctrl_schema *s = of->kn->parent->priv; + struct rdt_resource *r = s->res; + + seq_printf(seq, "%u\n", r->cache.arch_has_sparse_bitmasks); + + return 0; +} + /** * __rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other * @r: Resource to which domain instance @d belongs. @@ -1839,6 +1850,13 @@ static struct rftype res_common_files[] = { .seq_show = rdtgroup_size_show, .fflags = RF_CTRL_BASE, }, + { + .name = "sparse_masks", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_has_sparse_bitmasks_show, + .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, + }, }; From aaa5fa35743ab9f0726568611a85e3e15349b9bf Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Tue, 10 Oct 2023 12:42:39 +0200 Subject: [PATCH 05/14] Documentation/x86: Document resctrl's new sparse_masks MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The documentation mentions that non-contiguous bit masks are not supported in Intel Cache Allocation Technology (CAT). Update the documentation on how to determine if sparse bit masks are allowed in L2 and L3 CAT. Signed-off-by: Fenghua Yu Signed-off-by: Maciej Wieczor-Retman Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Ilpo Järvinen Reviewed-by: Peter Newman Reviewed-by: Reinette Chatre Reviewed-by: Babu Moger Tested-by: Peter Newman Link: https://lore.kernel.org/r/3e9610997164f648e15c5c2e90d4944ce36504fe.1696934091.git.maciej.wieczor-retman@intel.com --- Documentation/arch/x86/resctrl.rst | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/Documentation/arch/x86/resctrl.rst b/Documentation/arch/x86/resctrl.rst index cb05d90111b4..4c6421e2aa31 100644 --- a/Documentation/arch/x86/resctrl.rst +++ b/Documentation/arch/x86/resctrl.rst @@ -124,6 +124,13 @@ related to allocation: "P": Corresponding region is pseudo-locked. No sharing allowed. +"sparse_masks": + Indicates if non-contiguous 1s value in CBM is supported. + + "0": + Only contiguous 1s value in CBM is supported. + "1": + Non-contiguous 1s value in CBM is supported. Memory bandwidth(MB) subdirectory contains the following files with respect to allocation: @@ -445,12 +452,13 @@ For cache resources we describe the portion of the cache that is available for allocation using a bitmask. The maximum value of the mask is defined by each cpu model (and may be different for different cache levels). It is found using CPUID, but is also provided in the "info" directory of -the resctrl file system in "info/{resource}/cbm_mask". Intel hardware +the resctrl file system in "info/{resource}/cbm_mask". Some Intel hardware requires that these masks have all the '1' bits in a contiguous block. So 0x3, 0x6 and 0xC are legal 4-bit masks with two bits set, but 0x5, 0x9 -and 0xA are not. On a system with a 20-bit mask each bit represents 5% -of the capacity of the cache. You could partition the cache into four -equal parts with masks: 0x1f, 0x3e0, 0x7c00, 0xf8000. +and 0xA are not. Check /sys/fs/resctrl/info/{resource}/sparse_masks +if non-contiguous 1s value is supported. On a system with a 20-bit mask +each bit represents 5% of the capacity of the cache. You could partition +the cache into four equal parts with masks: 0x1f, 0x3e0, 0x7c00, 0xf8000. Memory bandwidth Allocation and monitoring ========================================== From fe2a20ea0b0953189e57740debc7dcc789d1ea55 Mon Sep 17 00:00:00 2001 From: Babu Moger Date: Mon, 16 Oct 2023 19:23:00 -0500 Subject: [PATCH 06/14] x86/resctrl: Add multiple tasks to the resctrl group at once MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The resctrl task assignment for monitor or control group needs to be done one at a time. For example: $mount -t resctrl resctrl /sys/fs/resctrl/ $mkdir /sys/fs/resctrl/ctrl_grp1 $echo 123 > /sys/fs/resctrl/ctrl_grp1/tasks $echo 456 > /sys/fs/resctrl/ctrl_grp1/tasks $echo 789 > /sys/fs/resctrl/ctrl_grp1/tasks This is not user-friendly when dealing with hundreds of tasks. Support multiple task assignment in one command with tasks ids separated by commas. For example: $echo 123,456,789 > /sys/fs/resctrl/ctrl_grp1/tasks Signed-off-by: Babu Moger Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Peter Newman Reviewed-by: Tan Shaopeng Reviewed-by: Fenghua Yu Reviewed-by: Reinette Chatre Reviewed-by: Ilpo Järvinen Tested-by: Peter Newman Tested-by: Tan Shaopeng Link: https://lore.kernel.org/r/20231017002308.134480-2-babu.moger@amd.com --- Documentation/arch/x86/resctrl.rst | 9 ++++++++- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 25 ++++++++++++++++++++++--- 2 files changed, 30 insertions(+), 4 deletions(-) diff --git a/Documentation/arch/x86/resctrl.rst b/Documentation/arch/x86/resctrl.rst index 4c6421e2aa31..178ab1d8f747 100644 --- a/Documentation/arch/x86/resctrl.rst +++ b/Documentation/arch/x86/resctrl.rst @@ -306,7 +306,14 @@ All groups contain the following files: "tasks": Reading this file shows the list of all tasks that belong to this group. Writing a task id to the file will add a task to the - group. If the group is a CTRL_MON group the task is removed from + group. Multiple tasks can be added by separating the task ids + with commas. Tasks will be assigned sequentially. Multiple + failures are not supported. A single failure encountered while + attempting to assign a task will cause the operation to abort and + already added tasks before the failure will remain in the group. + Failures will be logged to /sys/fs/resctrl/info/last_cmd_status. + + If the group is a CTRL_MON group the task is removed from whichever previous CTRL_MON group owned the task and also from any MON group that owned the task. If the group is a MON group, then the task must already belong to the CTRL_MON parent of this diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 09848ff11f7b..fe239691628a 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -696,11 +696,10 @@ static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct rdtgroup *rdtgrp; + char *pid_str; int ret = 0; pid_t pid; - if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) - return -EINVAL; rdtgrp = rdtgroup_kn_lock_live(of->kn); if (!rdtgrp) { rdtgroup_kn_unlock(of->kn); @@ -715,7 +714,27 @@ static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of, goto unlock; } - ret = rdtgroup_move_task(pid, rdtgrp, of); + while (buf && buf[0] != '\0' && buf[0] != '\n') { + pid_str = strim(strsep(&buf, ",")); + + if (kstrtoint(pid_str, 0, &pid)) { + rdt_last_cmd_printf("Task list parsing error pid %s\n", pid_str); + ret = -EINVAL; + break; + } + + if (pid < 0) { + rdt_last_cmd_printf("Invalid pid %d\n", pid); + ret = -EINVAL; + break; + } + + ret = rdtgroup_move_task(pid, rdtgrp, of); + if (ret) { + rdt_last_cmd_printf("Error while processing task %d\n", pid); + break; + } + } unlock: rdtgroup_kn_unlock(of->kn); From 6846dc1a31d1894a7acf52d8442fe73b34091022 Mon Sep 17 00:00:00 2001 From: Babu Moger Date: Tue, 3 Oct 2023 18:54:22 -0500 Subject: [PATCH 07/14] x86/resctrl: Simplify rftype flag definitions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The rftype flags are bitmaps used for adding files under the resctrl filesystem. Some of these bitmap defines have one extra level of indirection which is not necessary. Drop the RF_* defines and simplify the macros. [ bp: Massage commit message. ] Signed-off-by: Babu Moger Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Peter Newman Reviewed-by: Tan Shaopeng Reviewed-by: Fenghua Yu Reviewed-by: Reinette Chatre Reviewed-by: Ilpo Järvinen Tested-by: Peter Newman Tested-by: Tan Shaopeng Link: https://lore.kernel.org/r/20231017002308.134480-3-babu.moger@amd.com --- arch/x86/kernel/cpu/resctrl/internal.h | 9 +++------ arch/x86/kernel/cpu/resctrl/rdtgroup.c | 6 +++++- 2 files changed, 8 insertions(+), 7 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index c47ef2f13e8e..0ad970c5c867 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -243,12 +243,9 @@ struct rdtgroup { */ #define RFTYPE_INFO BIT(0) #define RFTYPE_BASE BIT(1) -#define RF_CTRLSHIFT 4 -#define RF_MONSHIFT 5 -#define RF_TOPSHIFT 6 -#define RFTYPE_CTRL BIT(RF_CTRLSHIFT) -#define RFTYPE_MON BIT(RF_MONSHIFT) -#define RFTYPE_TOP BIT(RF_TOPSHIFT) +#define RFTYPE_CTRL BIT(4) +#define RFTYPE_MON BIT(5) +#define RFTYPE_TOP BIT(6) #define RFTYPE_RES_CACHE BIT(8) #define RFTYPE_RES_MB BIT(9) #define RF_CTRL_INFO (RFTYPE_INFO | RFTYPE_CTRL) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index fe239691628a..09141f1f0b96 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -3260,7 +3260,11 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, goto out_destroy; } - files = RFTYPE_BASE | BIT(RF_CTRLSHIFT + rtype); + if (rtype == RDTCTRL_GROUP) + files = RFTYPE_BASE | RFTYPE_CTRL; + else + files = RFTYPE_BASE | RFTYPE_MON; + ret = rdtgroup_add_files(kn, files); if (ret) { rdt_last_cmd_puts("kernfs fill error\n"); From d41592435cde9a658a1bd3b3fdfeb8db7b330d78 Mon Sep 17 00:00:00 2001 From: Babu Moger Date: Mon, 16 Oct 2023 19:23:02 -0500 Subject: [PATCH 08/14] x86/resctrl: Rename rftype flags for consistency MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit resctrl associates rftype flags with its files so that files can be chosen based on the resource, whether it is info or base, and if it is control or monitor type file. These flags use the RF_ as well as RFTYPE_ prefixes. Change the prefix to RFTYPE_ for all these flags to be consistent. Signed-off-by: Babu Moger Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Peter Newman Reviewed-by: Tan Shaopeng Reviewed-by: Fenghua Yu Reviewed-by: Reinette Chatre Reviewed-by: Ilpo Järvinen Tested-by: Peter Newman Tested-by: Tan Shaopeng Link: https://lore.kernel.org/r/20231017002308.134480-4-babu.moger@amd.com --- arch/x86/kernel/cpu/resctrl/internal.h | 10 +++--- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 44 +++++++++++++------------- 2 files changed, 27 insertions(+), 27 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 0ad970c5c867..ba4611111212 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -248,10 +248,10 @@ struct rdtgroup { #define RFTYPE_TOP BIT(6) #define RFTYPE_RES_CACHE BIT(8) #define RFTYPE_RES_MB BIT(9) -#define RF_CTRL_INFO (RFTYPE_INFO | RFTYPE_CTRL) -#define RF_MON_INFO (RFTYPE_INFO | RFTYPE_MON) -#define RF_TOP_INFO (RFTYPE_INFO | RFTYPE_TOP) -#define RF_CTRL_BASE (RFTYPE_BASE | RFTYPE_CTRL) +#define RFTYPE_CTRL_INFO (RFTYPE_INFO | RFTYPE_CTRL) +#define RFTYPE_MON_INFO (RFTYPE_INFO | RFTYPE_MON) +#define RFTYPE_TOP_INFO (RFTYPE_INFO | RFTYPE_TOP) +#define RFTYPE_CTRL_BASE (RFTYPE_BASE | RFTYPE_CTRL) /* List of all resource groups */ extern struct list_head rdt_all_groups; @@ -267,7 +267,7 @@ void __exit rdtgroup_exit(void); * @mode: Access mode * @kf_ops: File operations * @flags: File specific RFTYPE_FLAGS_* flags - * @fflags: File specific RF_* or RFTYPE_* flags + * @fflags: File specific RFTYPE_* flags * @seq_show: Show content of the file * @write: Write to the file */ diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 09141f1f0b96..125d12d8f4b9 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -1716,77 +1716,77 @@ static struct rftype res_common_files[] = { .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_last_cmd_status_show, - .fflags = RF_TOP_INFO, + .fflags = RFTYPE_TOP_INFO, }, { .name = "num_closids", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_num_closids_show, - .fflags = RF_CTRL_INFO, + .fflags = RFTYPE_CTRL_INFO, }, { .name = "mon_features", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_mon_features_show, - .fflags = RF_MON_INFO, + .fflags = RFTYPE_MON_INFO, }, { .name = "num_rmids", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_num_rmids_show, - .fflags = RF_MON_INFO, + .fflags = RFTYPE_MON_INFO, }, { .name = "cbm_mask", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_default_ctrl_show, - .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, + .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE, }, { .name = "min_cbm_bits", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_min_cbm_bits_show, - .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, + .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE, }, { .name = "shareable_bits", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_shareable_bits_show, - .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, + .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE, }, { .name = "bit_usage", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_bit_usage_show, - .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, + .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE, }, { .name = "min_bandwidth", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_min_bw_show, - .fflags = RF_CTRL_INFO | RFTYPE_RES_MB, + .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB, }, { .name = "bandwidth_gran", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_bw_gran_show, - .fflags = RF_CTRL_INFO | RFTYPE_RES_MB, + .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB, }, { .name = "delay_linear", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_delay_linear_show, - .fflags = RF_CTRL_INFO | RFTYPE_RES_MB, + .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB, }, /* * Platform specific which (if any) capabilities are provided by @@ -1805,7 +1805,7 @@ static struct rftype res_common_files[] = { .kf_ops = &rdtgroup_kf_single_ops, .write = max_threshold_occ_write, .seq_show = max_threshold_occ_show, - .fflags = RF_MON_INFO | RFTYPE_RES_CACHE, + .fflags = RFTYPE_MON_INFO | RFTYPE_RES_CACHE, }, { .name = "mbm_total_bytes_config", @@ -1852,7 +1852,7 @@ static struct rftype res_common_files[] = { .kf_ops = &rdtgroup_kf_single_ops, .write = rdtgroup_schemata_write, .seq_show = rdtgroup_schemata_show, - .fflags = RF_CTRL_BASE, + .fflags = RFTYPE_CTRL_BASE, }, { .name = "mode", @@ -1860,21 +1860,21 @@ static struct rftype res_common_files[] = { .kf_ops = &rdtgroup_kf_single_ops, .write = rdtgroup_mode_write, .seq_show = rdtgroup_mode_show, - .fflags = RF_CTRL_BASE, + .fflags = RFTYPE_CTRL_BASE, }, { .name = "size", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdtgroup_size_show, - .fflags = RF_CTRL_BASE, + .fflags = RFTYPE_CTRL_BASE, }, { .name = "sparse_masks", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_has_sparse_bitmasks_show, - .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, + .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE, }, }; @@ -1931,7 +1931,7 @@ void __init thread_throttle_mode_init(void) if (!rft) return; - rft->fflags = RF_CTRL_INFO | RFTYPE_RES_MB; + rft->fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB; } void __init mbm_config_rftype_init(const char *config) @@ -1940,7 +1940,7 @@ void __init mbm_config_rftype_init(const char *config) rft = rdtgroup_get_rftype_by_name(config); if (rft) - rft->fflags = RF_MON_INFO | RFTYPE_RES_CACHE; + rft->fflags = RFTYPE_MON_INFO | RFTYPE_RES_CACHE; } /** @@ -2075,21 +2075,21 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) if (IS_ERR(kn_info)) return PTR_ERR(kn_info); - ret = rdtgroup_add_files(kn_info, RF_TOP_INFO); + ret = rdtgroup_add_files(kn_info, RFTYPE_TOP_INFO); if (ret) goto out_destroy; /* loop over enabled controls, these are all alloc_capable */ list_for_each_entry(s, &resctrl_schema_all, list) { r = s->res; - fflags = r->fflags | RF_CTRL_INFO; + fflags = r->fflags | RFTYPE_CTRL_INFO; ret = rdtgroup_mkdir_info_resdir(s, s->name, fflags); if (ret) goto out_destroy; } for_each_mon_capable_rdt_resource(r) { - fflags = r->fflags | RF_MON_INFO; + fflags = r->fflags | RFTYPE_MON_INFO; sprintf(name, "%s_MON", r->name); ret = rdtgroup_mkdir_info_resdir(r, name, fflags); if (ret) @@ -3727,7 +3727,7 @@ static int __init rdtgroup_setup_root(void) list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups); - ret = rdtgroup_add_files(kernfs_root_to_node(rdt_root), RF_CTRL_BASE); + ret = rdtgroup_add_files(kernfs_root_to_node(rdt_root), RFTYPE_CTRL_BASE); if (ret) { kernfs_destroy_root(rdt_root); goto out; From df5f3a1dd8a6d3ddb1f07a10817f735194717422 Mon Sep 17 00:00:00 2001 From: Babu Moger Date: Mon, 16 Oct 2023 19:23:03 -0500 Subject: [PATCH 09/14] x86/resctrl: Unwind properly from rdt_enable_ctx() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit rdt_enable_ctx() enables the features provided during resctrl mount. Additions to rdt_enable_ctx() are required to also modify error paths of rdt_enable_ctx() callers to ensure correct unwinding if errors are encountered after calling rdt_enable_ctx(). This is error prone. Introduce rdt_disable_ctx() to refactor the error unwinding of rdt_enable_ctx() to simplify future additions. This also simplifies cleanup in rdt_kill_sb(). Suggested-by: Reinette Chatre Signed-off-by: Babu Moger Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Peter Newman Reviewed-by: Tan Shaopeng Reviewed-by: Fenghua Yu Reviewed-by: Reinette Chatre Reviewed-by: Ilpo Järvinen Tested-by: Peter Newman Tested-by: Tan Shaopeng Link: https://lore.kernel.org/r/20231017002308.134480-5-babu.moger@amd.com --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 53 ++++++++++++++++---------- 1 file changed, 32 insertions(+), 21 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 125d12d8f4b9..d1b5fd70ccbb 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -2308,14 +2308,6 @@ int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable) return 0; } -static void cdp_disable_all(void) -{ - if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3)) - resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false); - if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2)) - resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false); -} - /* * We don't allow rdtgroup directories to be created anywhere * except the root directory. Thus when looking for the rdtgroup @@ -2395,19 +2387,42 @@ static int mkdir_mondata_all(struct kernfs_node *parent_kn, struct rdtgroup *prgrp, struct kernfs_node **mon_data_kn); +static void rdt_disable_ctx(void) +{ + resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false); + resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false); + set_mba_sc(false); +} + static int rdt_enable_ctx(struct rdt_fs_context *ctx) { int ret = 0; - if (ctx->enable_cdpl2) + if (ctx->enable_cdpl2) { ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, true); + if (ret) + goto out_done; + } - if (!ret && ctx->enable_cdpl3) + if (ctx->enable_cdpl3) { ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, true); + if (ret) + goto out_cdpl2; + } - if (!ret && ctx->enable_mba_mbps) + if (ctx->enable_mba_mbps) { ret = set_mba_sc(true); + if (ret) + goto out_cdpl3; + } + return 0; + +out_cdpl3: + resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false); +out_cdpl2: + resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false); +out_done: return ret; } @@ -2515,13 +2530,13 @@ static int rdt_get_tree(struct fs_context *fc) } ret = rdt_enable_ctx(ctx); - if (ret < 0) - goto out_cdp; + if (ret) + goto out; ret = schemata_list_create(); if (ret) { schemata_list_destroy(); - goto out_mba; + goto out_ctx; } closid_init(); @@ -2580,11 +2595,8 @@ static int rdt_get_tree(struct fs_context *fc) kernfs_remove(kn_info); out_schemata_free: schemata_list_destroy(); -out_mba: - if (ctx->enable_mba_mbps) - set_mba_sc(false); -out_cdp: - cdp_disable_all(); +out_ctx: + rdt_disable_ctx(); out: rdt_last_cmd_clear(); mutex_unlock(&rdtgroup_mutex); @@ -2816,12 +2828,11 @@ static void rdt_kill_sb(struct super_block *sb) cpus_read_lock(); mutex_lock(&rdtgroup_mutex); - set_mba_sc(false); + rdt_disable_ctx(); /*Put everything back to default values. */ for_each_alloc_capable_rdt_resource(r) reset_all_ctrls(r); - cdp_disable_all(); rmdir_all_sub(); rdt_pseudo_lock_release(); rdtgroup_default.mode = RDT_MODE_SHAREABLE; From d27567a0eb54be457b25e240593fdbd1c35c8618 Mon Sep 17 00:00:00 2001 From: Babu Moger Date: Mon, 16 Oct 2023 19:23:04 -0500 Subject: [PATCH 10/14] x86/resctrl: Move default group file creation to mount MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The default resource group and its files are created during kernel init time. Upcoming changes will make some resctrl files optional based on a mount parameter. If optional files are to be added to the default group based on the mount option, then each new file needs to be created separately and call kernfs_activate() again. Create all files of the default resource group during resctrl mount, destroyed during unmount, to avoid scattering resctrl file addition across two separate code flows. Signed-off-by: Babu Moger Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Peter Newman Reviewed-by: Tan Shaopeng Reviewed-by: Fenghua Yu Reviewed-by: Reinette Chatre Reviewed-by: Ilpo Järvinen Tested-by: Peter Newman Tested-by: Tan Shaopeng Link: https://lore.kernel.org/r/20231017002308.134480-6-babu.moger@amd.com --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 58 +++++++++++++++----------- 1 file changed, 34 insertions(+), 24 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index d1b5fd70ccbb..55da93b5ca53 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -54,6 +54,9 @@ static struct kernfs_node *kn_mondata; static struct seq_buf last_cmd_status; static char last_cmd_status_buf[512]; +static int rdtgroup_setup_root(struct rdt_fs_context *ctx); +static void rdtgroup_destroy_root(void); + struct dentry *debugfs_resctrl; void rdt_last_cmd_clear(void) @@ -2529,10 +2532,14 @@ static int rdt_get_tree(struct fs_context *fc) goto out; } - ret = rdt_enable_ctx(ctx); + ret = rdtgroup_setup_root(ctx); if (ret) goto out; + ret = rdt_enable_ctx(ctx); + if (ret) + goto out_root; + ret = schemata_list_create(); if (ret) { schemata_list_destroy(); @@ -2541,6 +2548,12 @@ static int rdt_get_tree(struct fs_context *fc) closid_init(); + ret = rdtgroup_add_files(rdtgroup_default.kn, RFTYPE_CTRL_BASE); + if (ret) + goto out_schemata_free; + + kernfs_activate(rdtgroup_default.kn); + ret = rdtgroup_create_info_dir(rdtgroup_default.kn); if (ret < 0) goto out_schemata_free; @@ -2597,6 +2610,8 @@ static int rdt_get_tree(struct fs_context *fc) schemata_list_destroy(); out_ctx: rdt_disable_ctx(); +out_root: + rdtgroup_destroy_root(); out: rdt_last_cmd_clear(); mutex_unlock(&rdtgroup_mutex); @@ -2667,7 +2682,6 @@ static int rdt_init_fs_context(struct fs_context *fc) if (!ctx) return -ENOMEM; - ctx->kfc.root = rdt_root; ctx->kfc.magic = RDTGROUP_SUPER_MAGIC; fc->fs_private = &ctx->kfc; fc->ops = &rdt_fs_context_ops; @@ -2837,6 +2851,7 @@ static void rdt_kill_sb(struct super_block *sb) rdt_pseudo_lock_release(); rdtgroup_default.mode = RDT_MODE_SHAREABLE; schemata_list_destroy(); + rdtgroup_destroy_root(); static_branch_disable_cpuslocked(&rdt_alloc_enable_key); static_branch_disable_cpuslocked(&rdt_mon_enable_key); static_branch_disable_cpuslocked(&rdt_enable_key); @@ -3718,10 +3733,8 @@ static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = { .show_options = rdtgroup_show_options, }; -static int __init rdtgroup_setup_root(void) +static int rdtgroup_setup_root(struct rdt_fs_context *ctx) { - int ret; - rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops, KERNFS_ROOT_CREATE_DEACTIVATED | KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK, @@ -3729,6 +3742,20 @@ static int __init rdtgroup_setup_root(void) if (IS_ERR(rdt_root)) return PTR_ERR(rdt_root); + ctx->kfc.root = rdt_root; + rdtgroup_default.kn = kernfs_root_to_node(rdt_root); + + return 0; +} + +static void rdtgroup_destroy_root(void) +{ + kernfs_destroy_root(rdt_root); + rdtgroup_default.kn = NULL; +} + +static void __init rdtgroup_setup_default(void) +{ mutex_lock(&rdtgroup_mutex); rdtgroup_default.closid = 0; @@ -3738,19 +3765,7 @@ static int __init rdtgroup_setup_root(void) list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups); - ret = rdtgroup_add_files(kernfs_root_to_node(rdt_root), RFTYPE_CTRL_BASE); - if (ret) { - kernfs_destroy_root(rdt_root); - goto out; - } - - rdtgroup_default.kn = kernfs_root_to_node(rdt_root); - kernfs_activate(rdtgroup_default.kn); - -out: mutex_unlock(&rdtgroup_mutex); - - return ret; } static void domain_destroy_mon_state(struct rdt_domain *d) @@ -3872,13 +3887,11 @@ int __init rdtgroup_init(void) seq_buf_init(&last_cmd_status, last_cmd_status_buf, sizeof(last_cmd_status_buf)); - ret = rdtgroup_setup_root(); - if (ret) - return ret; + rdtgroup_setup_default(); ret = sysfs_create_mount_point(fs_kobj, "resctrl"); if (ret) - goto cleanup_root; + return ret; ret = register_filesystem(&rdt_fs_type); if (ret) @@ -3911,8 +3924,6 @@ int __init rdtgroup_init(void) cleanup_mountpoint: sysfs_remove_mount_point(fs_kobj, "resctrl"); -cleanup_root: - kernfs_destroy_root(rdt_root); return ret; } @@ -3922,5 +3933,4 @@ void __exit rdtgroup_exit(void) debugfs_remove_recursive(debugfs_resctrl); unregister_filesystem(&rdt_fs_type); sysfs_remove_mount_point(fs_kobj, "resctrl"); - kernfs_destroy_root(rdt_root); } From cb07d71f01017b7c2885ed629da9b973cb56b1d2 Mon Sep 17 00:00:00 2001 From: Babu Moger Date: Mon, 16 Oct 2023 19:23:05 -0500 Subject: [PATCH 11/14] x86/resctrl: Introduce "-o debug" mount option MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add "-o debug" option to mount resctrl filesystem in debug mode. When in debug mode resctrl displays files that have the new RFTYPE_DEBUG flag to help resctrl debugging. Signed-off-by: Babu Moger Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Peter Newman Reviewed-by: Tan Shaopeng Reviewed-by: Fenghua Yu Reviewed-by: Reinette Chatre Reviewed-by: Ilpo Järvinen Tested-by: Peter Newman Tested-by: Tan Shaopeng Link: https://lore.kernel.org/r/20231017002308.134480-7-babu.moger@amd.com --- Documentation/arch/x86/resctrl.rst | 5 ++++- arch/x86/kernel/cpu/resctrl/internal.h | 2 ++ arch/x86/kernel/cpu/resctrl/rdtgroup.c | 18 ++++++++++++++++++ 3 files changed, 24 insertions(+), 1 deletion(-) diff --git a/Documentation/arch/x86/resctrl.rst b/Documentation/arch/x86/resctrl.rst index 178ab1d8f747..68f11611f341 100644 --- a/Documentation/arch/x86/resctrl.rst +++ b/Documentation/arch/x86/resctrl.rst @@ -35,7 +35,7 @@ about the feature from resctrl's info directory. To use the feature mount the file system:: - # mount -t resctrl resctrl [-o cdp[,cdpl2][,mba_MBps]] /sys/fs/resctrl + # mount -t resctrl resctrl [-o cdp[,cdpl2][,mba_MBps][,debug]] /sys/fs/resctrl mount options are: @@ -46,6 +46,9 @@ mount options are: "mba_MBps": Enable the MBA Software Controller(mba_sc) to specify MBA bandwidth in MBps +"debug": + Make debug files accessible. Available debug files are annotated with + "Available only with debug option". L2 and L3 CDP are controlled separately. diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index ba4611111212..b816b902b5c0 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -59,6 +59,7 @@ struct rdt_fs_context { bool enable_cdpl2; bool enable_cdpl3; bool enable_mba_mbps; + bool enable_debug; }; static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc) @@ -248,6 +249,7 @@ struct rdtgroup { #define RFTYPE_TOP BIT(6) #define RFTYPE_RES_CACHE BIT(8) #define RFTYPE_RES_MB BIT(9) +#define RFTYPE_DEBUG BIT(10) #define RFTYPE_CTRL_INFO (RFTYPE_INFO | RFTYPE_CTRL) #define RFTYPE_MON_INFO (RFTYPE_INFO | RFTYPE_MON) #define RFTYPE_TOP_INFO (RFTYPE_INFO | RFTYPE_TOP) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 55da93b5ca53..84e0f45578dd 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -59,6 +59,8 @@ static void rdtgroup_destroy_root(void); struct dentry *debugfs_resctrl; +static bool resctrl_debug; + void rdt_last_cmd_clear(void) { lockdep_assert_held(&rdtgroup_mutex); @@ -1892,6 +1894,9 @@ static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags) lockdep_assert_held(&rdtgroup_mutex); + if (resctrl_debug) + fflags |= RFTYPE_DEBUG; + for (rft = rfts; rft < rfts + len; rft++) { if (rft->fflags && ((fflags & rft->fflags) == rft->fflags)) { ret = rdtgroup_add_file(kn, rft); @@ -2395,6 +2400,8 @@ static void rdt_disable_ctx(void) resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false); resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false); set_mba_sc(false); + + resctrl_debug = false; } static int rdt_enable_ctx(struct rdt_fs_context *ctx) @@ -2419,6 +2426,9 @@ static int rdt_enable_ctx(struct rdt_fs_context *ctx) goto out_cdpl3; } + if (ctx->enable_debug) + resctrl_debug = true; + return 0; out_cdpl3: @@ -2623,6 +2633,7 @@ enum rdt_param { Opt_cdp, Opt_cdpl2, Opt_mba_mbps, + Opt_debug, nr__rdt_params }; @@ -2630,6 +2641,7 @@ static const struct fs_parameter_spec rdt_fs_parameters[] = { fsparam_flag("cdp", Opt_cdp), fsparam_flag("cdpl2", Opt_cdpl2), fsparam_flag("mba_MBps", Opt_mba_mbps), + fsparam_flag("debug", Opt_debug), {} }; @@ -2655,6 +2667,9 @@ static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param) return -EINVAL; ctx->enable_mba_mbps = true; return 0; + case Opt_debug: + ctx->enable_debug = true; + return 0; } return -EINVAL; @@ -3723,6 +3738,9 @@ static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf) if (is_mba_sc(&rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl)) seq_puts(seq, ",mba_MBps"); + if (resctrl_debug) + seq_puts(seq, ",debug"); + return 0; } From ca8dad225e237493f19b1c5d4a8531f13a9b078f Mon Sep 17 00:00:00 2001 From: Babu Moger Date: Mon, 16 Oct 2023 19:23:06 -0500 Subject: [PATCH 12/14] x86/resctrl: Display CLOSID for resource group MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In x86, hardware uses CLOSID to identify a control group. When a user creates a control group this information is not visible to the user. It can help resctrl debugging. Add CLOSID(ctrl_hw_id) to the control groups display in the resctrl interface. Users can see this detail when resctrl is mounted with the "-o debug" option. Other architectures do not use "CLOSID". Use the names ctrl_hw_id to refer to "CLOSID" in an effort to keep the naming generic. For example: $cat /sys/fs/resctrl/ctrl_grp1/ctrl_hw_id 1 Signed-off-by: Babu Moger Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Peter Newman Reviewed-by: Tan Shaopeng Reviewed-by: Fenghua Yu Reviewed-by: Reinette Chatre Reviewed-by: Ilpo Järvinen Tested-by: Peter Newman Tested-by: Tan Shaopeng Link: https://lore.kernel.org/r/20231017002308.134480-8-babu.moger@amd.com --- Documentation/arch/x86/resctrl.rst | 4 ++++ arch/x86/kernel/cpu/resctrl/rdtgroup.c | 23 +++++++++++++++++++++++ 2 files changed, 27 insertions(+) diff --git a/Documentation/arch/x86/resctrl.rst b/Documentation/arch/x86/resctrl.rst index 68f11611f341..7412252f95a7 100644 --- a/Documentation/arch/x86/resctrl.rst +++ b/Documentation/arch/x86/resctrl.rst @@ -359,6 +359,10 @@ When control is enabled all CTRL_MON groups will also contain: file. On successful pseudo-locked region creation the mode will automatically change to "pseudo-locked". +"ctrl_hw_id": + Available only with debug option. The identifier used by hardware + for the control group. On x86 this is the CLOSID. + When monitoring is enabled all MON groups will also contain: "mon_data": diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 84e0f45578dd..5814a0bf3cea 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -779,6 +779,22 @@ static int rdtgroup_tasks_show(struct kernfs_open_file *of, return ret; } +static int rdtgroup_closid_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + int ret = 0; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (rdtgrp) + seq_printf(s, "%u\n", rdtgrp->closid); + else + ret = -ENOENT; + rdtgroup_kn_unlock(of->kn); + + return ret; +} + #ifdef CONFIG_PROC_CPU_RESCTRL /* @@ -1881,6 +1897,13 @@ static struct rftype res_common_files[] = { .seq_show = rdt_has_sparse_bitmasks_show, .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE, }, + { + .name = "ctrl_hw_id", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdtgroup_closid_show, + .fflags = RFTYPE_CTRL_BASE | RFTYPE_DEBUG, + }, }; From 918f211b5e4e709e91acf856967a850569c96b71 Mon Sep 17 00:00:00 2001 From: Babu Moger Date: Mon, 16 Oct 2023 19:23:07 -0500 Subject: [PATCH 13/14] x86/resctrl: Add support for the files of MON groups only MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Files unique to monitoring groups have the RFTYPE_MON flag. When a new monitoring group is created the resctrl files with flags RFTYPE_BASE (files common to all resource groups) and RFTYPE_MON (files unique to monitoring groups) are created to support interacting with the new monitoring group. A resource group can support both monitoring and control, also termed a CTRL_MON resource group. CTRL_MON groups should get both monitoring and control resctrl files but that is not the case. Only the RFTYPE_BASE and RFTYPE_CTRL files are created for CTRL_MON groups. Ensure that files with the RFTYPE_MON flag are created for CTRL_MON groups. Signed-off-by: Babu Moger Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Peter Newman Reviewed-by: Tan Shaopeng Reviewed-by: Fenghua Yu Reviewed-by: Ilpo Järvinen Reviewed-by: Reinette Chatre Tested-by: Peter Newman Tested-by: Tan Shaopeng Link: https://lore.kernel.org/r/20231017002308.134480-9-babu.moger@amd.com --- arch/x86/kernel/cpu/resctrl/rdtgroup.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 5814a0bf3cea..5f6d6ba63a2e 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -2551,6 +2551,7 @@ static void schemata_list_destroy(void) static int rdt_get_tree(struct fs_context *fc) { struct rdt_fs_context *ctx = rdt_fc2context(fc); + unsigned long flags = RFTYPE_CTRL_BASE; struct rdt_domain *dom; struct rdt_resource *r; int ret; @@ -2581,7 +2582,10 @@ static int rdt_get_tree(struct fs_context *fc) closid_init(); - ret = rdtgroup_add_files(rdtgroup_default.kn, RFTYPE_CTRL_BASE); + if (rdt_mon_capable) + flags |= RFTYPE_MON; + + ret = rdtgroup_add_files(rdtgroup_default.kn, flags); if (ret) goto out_schemata_free; @@ -3271,8 +3275,8 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, enum rdt_group_type rtype, struct rdtgroup **r) { struct rdtgroup *prdtgrp, *rdtgrp; + unsigned long files = 0; struct kernfs_node *kn; - uint files = 0; int ret; prdtgrp = rdtgroup_kn_lock_live(parent_kn); @@ -3324,10 +3328,13 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, goto out_destroy; } - if (rtype == RDTCTRL_GROUP) + if (rtype == RDTCTRL_GROUP) { files = RFTYPE_BASE | RFTYPE_CTRL; - else + if (rdt_mon_capable) + files |= RFTYPE_MON; + } else { files = RFTYPE_BASE | RFTYPE_MON; + } ret = rdtgroup_add_files(kn, files); if (ret) { From 4cee14bcb14881aae81d60f106a335c68553ac1f Mon Sep 17 00:00:00 2001 From: Babu Moger Date: Mon, 16 Oct 2023 19:23:08 -0500 Subject: [PATCH 14/14] x86/resctrl: Display RMID of resource group MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In x86, hardware uses RMID to identify a monitoring group. When a user creates a monitor group these details are not visible. These details can help resctrl debugging. Add RMID(mon_hw_id) to the monitor groups display in the resctrl interface. Users can see these details when resctrl is mounted with "-o debug" option. Add RFTYPE_MON_BASE that complements existing RFTYPE_CTRL_BASE and represents files belonging to monitoring groups. Other architectures do not use "RMID". Use the name mon_hw_id to refer to "RMID" in an effort to keep the naming generic. For example: $cat /sys/fs/resctrl/mon_groups/mon_grp1/mon_hw_id 3 Signed-off-by: Babu Moger Signed-off-by: Borislav Petkov (AMD) Reviewed-by: Peter Newman Reviewed-by: Tan Shaopeng Reviewed-by: Fenghua Yu Reviewed-by: Reinette Chatre Reviewed-by: Ilpo Järvinen Tested-by: Peter Newman Tested-by: Tan Shaopeng Link: https://lore.kernel.org/r/20231017002308.134480-10-babu.moger@amd.com --- Documentation/arch/x86/resctrl.rst | 4 ++++ arch/x86/kernel/cpu/resctrl/internal.h | 1 + arch/x86/kernel/cpu/resctrl/rdtgroup.c | 23 +++++++++++++++++++++++ 3 files changed, 28 insertions(+) diff --git a/Documentation/arch/x86/resctrl.rst b/Documentation/arch/x86/resctrl.rst index 7412252f95a7..a6279df64a9d 100644 --- a/Documentation/arch/x86/resctrl.rst +++ b/Documentation/arch/x86/resctrl.rst @@ -376,6 +376,10 @@ When monitoring is enabled all MON groups will also contain: the sum for all tasks in the CTRL_MON group and all tasks in MON groups. Please see example section for more details on usage. +"mon_hw_id": + Available only with debug option. The identifier used by hardware + for the monitor group. On x86 this is the RMID. + Resource allocation rules ------------------------- diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index b816b902b5c0..a4f1aa15f0a2 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -254,6 +254,7 @@ struct rdtgroup { #define RFTYPE_MON_INFO (RFTYPE_INFO | RFTYPE_MON) #define RFTYPE_TOP_INFO (RFTYPE_INFO | RFTYPE_TOP) #define RFTYPE_CTRL_BASE (RFTYPE_BASE | RFTYPE_CTRL) +#define RFTYPE_MON_BASE (RFTYPE_BASE | RFTYPE_MON) /* List of all resource groups */ extern struct list_head rdt_all_groups; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 5f6d6ba63a2e..69a1de92384a 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -795,6 +795,22 @@ static int rdtgroup_closid_show(struct kernfs_open_file *of, return ret; } +static int rdtgroup_rmid_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + int ret = 0; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (rdtgrp) + seq_printf(s, "%u\n", rdtgrp->mon.rmid); + else + ret = -ENOENT; + rdtgroup_kn_unlock(of->kn); + + return ret; +} + #ifdef CONFIG_PROC_CPU_RESCTRL /* @@ -1867,6 +1883,13 @@ static struct rftype res_common_files[] = { .seq_show = rdtgroup_tasks_show, .fflags = RFTYPE_BASE, }, + { + .name = "mon_hw_id", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdtgroup_rmid_show, + .fflags = RFTYPE_MON_BASE | RFTYPE_DEBUG, + }, { .name = "schemata", .mode = 0644,