From cbc82b17263877ea5d21e84c58ce03f0292458a1 Mon Sep 17 00:00:00 2001 From: Peter P Waskiewicz Jr Date: Fri, 23 Jan 2015 18:45:43 +0000 Subject: [PATCH] x86: Add support for Intel Cache QoS Monitoring (CQM) detection This patch adds support for the new Cache QoS Monitoring (CQM) feature found in future Intel Xeon processors. It includes the new values to track CQM resources to the cpuinfo_x86 structure, plus the CPUID detection routines for CQM. CQM allows a process, or set of processes, to be tracked by the CPU to determine the cache usage of that task group. Using this data from the CPU, software can be written to extract this data and report cache usage and occupancy for a particular process, or group of processes. More information about Cache QoS Monitoring can be found in the Intel (R) x86 Architecture Software Developer Manual, section 17.14. Signed-off-by: Peter P Waskiewicz Jr Signed-off-by: Matt Fleming Signed-off-by: Peter Zijlstra (Intel) Cc: Andy Lutomirski Cc: Arnaldo Carvalho de Melo Cc: Borislav Petkov Cc: Chris Webb Cc: Dave Hansen Cc: Fenghua Yu Cc: H. Peter Anvin Cc: Igor Mammedov Cc: Jacob Shin Cc: Jan Beulich Cc: Jiri Olsa Cc: Kanaka Juvva Cc: Linus Torvalds Cc: Steven Honeyman Cc: Steven Rostedt Cc: Vikas Shivappa Link: http://lkml.kernel.org/r/1422038748-21397-5-git-send-email-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar --- arch/x86/include/asm/cpufeature.h | 9 ++++++- arch/x86/include/asm/processor.h | 3 +++ arch/x86/kernel/cpu/common.c | 39 +++++++++++++++++++++++++++++++ 3 files changed, 50 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 90a54851aedc..361922dcc9b1 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -12,7 +12,7 @@ #include #endif -#define NCAPINTS 11 /* N 32-bit words worth of info */ +#define NCAPINTS 13 /* N 32-bit words worth of info */ #define NBUGINTS 1 /* N 32-bit bug flags */ /* @@ -226,6 +226,7 @@ #define X86_FEATURE_ERMS ( 9*32+ 9) /* Enhanced REP MOVSB/STOSB */ #define X86_FEATURE_INVPCID ( 9*32+10) /* Invalidate Processor Context ID */ #define X86_FEATURE_RTM ( 9*32+11) /* Restricted Transactional Memory */ +#define X86_FEATURE_CQM ( 9*32+12) /* Cache QoS Monitoring */ #define X86_FEATURE_MPX ( 9*32+14) /* Memory Protection Extension */ #define X86_FEATURE_AVX512F ( 9*32+16) /* AVX-512 Foundation */ #define X86_FEATURE_RDSEED ( 9*32+18) /* The RDSEED instruction */ @@ -242,6 +243,12 @@ #define X86_FEATURE_XGETBV1 (10*32+ 2) /* XGETBV with ECX = 1 */ #define X86_FEATURE_XSAVES (10*32+ 3) /* XSAVES/XRSTORS */ +/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (edx), word 11 */ +#define X86_FEATURE_CQM_LLC (11*32+ 1) /* LLC QoS if 1 */ + +/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */ +#define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring if 1 */ + /* * BUG word(s) */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index ec1c93588cef..a12d50e04d7a 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -109,6 +109,9 @@ struct cpuinfo_x86 { /* in KB - valid for CPUS which support this call: */ int x86_cache_size; int x86_cache_alignment; /* In bytes */ + /* Cache QoS architectural values: */ + int x86_cache_max_rmid; /* max index */ + int x86_cache_occ_scale; /* scale to bytes */ int x86_power; unsigned long loops_per_jiffy; /* cpuid returned max cores value: */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 07f2fc3c13a4..9fa00b2ea0ee 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -645,6 +645,30 @@ void get_cpu_cap(struct cpuinfo_x86 *c) c->x86_capability[10] = eax; } + /* Additional Intel-defined flags: level 0x0000000F */ + if (c->cpuid_level >= 0x0000000F) { + u32 eax, ebx, ecx, edx; + + /* QoS sub-leaf, EAX=0Fh, ECX=0 */ + cpuid_count(0x0000000F, 0, &eax, &ebx, &ecx, &edx); + c->x86_capability[11] = edx; + if (cpu_has(c, X86_FEATURE_CQM_LLC)) { + /* will be overridden if occupancy monitoring exists */ + c->x86_cache_max_rmid = ebx; + + /* QoS sub-leaf, EAX=0Fh, ECX=1 */ + cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx); + c->x86_capability[12] = edx; + if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) { + c->x86_cache_max_rmid = ecx; + c->x86_cache_occ_scale = ebx; + } + } else { + c->x86_cache_max_rmid = -1; + c->x86_cache_occ_scale = -1; + } + } + /* AMD-defined flags: level 0x80000001 */ xlvl = cpuid_eax(0x80000000); c->extended_cpuid_level = xlvl; @@ -833,6 +857,20 @@ static void generic_identify(struct cpuinfo_x86 *c) detect_nopl(c); } +static void x86_init_cache_qos(struct cpuinfo_x86 *c) +{ + /* + * The heavy lifting of max_rmid and cache_occ_scale are handled + * in get_cpu_cap(). Here we just set the max_rmid for the boot_cpu + * in case CQM bits really aren't there in this CPU. + */ + if (c != &boot_cpu_data) { + boot_cpu_data.x86_cache_max_rmid = + min(boot_cpu_data.x86_cache_max_rmid, + c->x86_cache_max_rmid); + } +} + /* * This does the hard work of actually picking apart the CPU stuff... */ @@ -922,6 +960,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) init_hypervisor(c); x86_init_rdrand(c); + x86_init_cache_qos(c); /* * Clear/Set all flags overriden by options, need do it -- 2.39.5