arch/x86: AMD QoS support
Subsystems (3)
v7 cover arch/x86: AMD QoS support
This series adds support for AMD64 architectural extensions for Platform Quality of Service. These extensions are intended to provide for the monitoring of the usage of certain system resources by one or more processors and for the separate allocation and enforcement of limits on the use of certain system resources by one or more processors.
The monitoring and enforcement are not necessarily applied across the entire system, but in general apply to a QOS domain which corresponds to some shared system resource. The set of resources which are monitored and the set for which the enforcement of limits is provided are implementation dependent. Platform QOS features are implemented on a logical processor basis. Therefore, multiple hardware threads of a single physical CPU core may have independent resource monitoring and enforcement configurations.
AMD's next generation of processors support following QoS sub-features.
- L3 Cache allocation enforcement
- L3 Cache occupancy monitoring
- L3 Code-Data Prioritization support
- Memory Bandwidth Enforcement(Allocation)
The public specification for this feature is available at
https://developer.amd.com/wp-content/resources/56375.pdf
Obviously, there are multiple ways we can go about these changes. We felt it is appropriate to rename and re-organize the code little bit before making the functional changes. The first few patches(1-10) renames and re-organizes the sources in preparation. Rest of the patches(7-11) adds support for AMD QoS features.
Please review.
Changes from v6 -> v7:
a. Mainly addressed the comments from Mattew Wilcox. Removed both
CONFIG_INTEL_RDT and CONFIG_AMD_QOS config parameter. We dont need to use two separate config parameter to enable this feature. The final code will be same in both the cases. So, used the new vendor neutral parameter CONFIG_RESCTRL to enable resource control feature for both Intel and AMD
Changes from v5 -> v6:
https://lore.kernel.org/lkml/[email protected]/
a. Addressed comments from Fenghua Yu. Added vendor check while
detecting MBA software controller support.
a. Rebased again on top of
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/cache
Changes from v4 -> v5:
https://lore.kernel.org/lkml/[email protected]/
a. Addressed comments from Fenghua Yu.
b. The functions update_mba_bw and set_mba_sc is not required for AMD.
Removed all the changes related to these functions.
Changes from v3 -> v4:
https://lore.kernel.org/lkml/[email protected]/
a. Addressed comments from Reinette Chatre and Borislav Petkov. b. Removed X86 dependency for CONFIG_AMD_QOS. Implicitly is it already
dependent on X86.
c. Updated the MAINTAINER file for name changes.
d. Addressed most of "checkpatch.pl --strict" issues.
d. Updated Documentation/x86/resctrl_ui.txt(previously
intel_rdt_ui.txt) file with AMD specific details. Changed few names to resctrl from intel_rdt.
Changes from v2 -> v3:
https://lore.kernel.org/lkml/[email protected]/
a. Rebased the patches on top of below branch as suggested by Thomas Gleixner.
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/cache
b. Addressed comments from Reinette Chatre, Fenghua Yu and Borislav Petkov. c. Main changes are related to renaming the files and functions.
Renamed from intel_rdt to more generic resctrl(patches 1 to 3).
d. Config parameter changed from PLATFORM_QOS to more generic RESCTRL. e. Fixed minor indentation issues.
Changes from v1 -> v2:
https://lore.kernel.org/lkml/[email protected]/
a. Removed RFC from subject header. Based on the discussion so far,
plan is to go ahead with these patches and eventually re-structure the code to make arch and non-arch separate.
b. Addressed comments from Reinette Chatre and Fenghua Yu. c. Separated quirks and MBA from rdt init code. Kept the rest of the
code as is.
d. Added _intel suffixes all the Intel only code just like AMD code. e. Added one more patch to bring the macros into header file. f. Few minor text changes.
v1:
https://lore.kernel.org/lkml/[email protected]/
Babu Moger (12):
arch/x86: Start renaming the rdt files to more generic names arch/x86: Rename the RDT functions and definitions arch/x86: Re-arrange RDT init code
arch/x86: Bring all the macros to resctrl.h
arch/x86: Rename config parameter INTEL_RDT to RESCTRL arch/x86: Initialize the resource functions that are different arch/x86: Bring cbm_validate function into the resource structure arch/x86: Add vendor check for MBA software controller arch/x86: Update the RESCTRL config parameter arch/x86: Introduce QOS feature for AMD Documentation/x86: Rename and update intel_rdt_ui.txt
MAINTAINERS: Update the file and documentation names in arch/x86
Sherry Hurwitz (1):
arch/x86: Add AMD feature bit X86_FEATURE_MBA in cpuid bits array
.../x86/{intel_rdt_ui.txt => resctrl_ui.txt} | 9 +-
MAINTAINERS | 6 +-
arch/x86/Kconfig | 23 ++-
.../{intel_rdt_sched.h => resctrl_sched.h} | 28 +--
arch/x86/kernel/cpu/Makefile | 6 +-
.../x86/kernel/cpu/{intel_rdt.c => resctrl.c} | 168 +++++++++++++++---
.../x86/kernel/cpu/{intel_rdt.h => resctrl.h} | 37 ++--
...dt_ctrlmondata.c => resctrl_ctrlmondata.c} | 80 ++++++++-
...{intel_rdt_monitor.c => resctrl_monitor.c} | 20 +--
...dt_pseudo_lock.c => resctrl_pseudo_lock.c} | 6 +-
...ck_event.h => resctrl_pseudo_lock_event.h} | 2 +-
...ntel_rdt_rdtgroup.c => resctrl_rdtgroup.c} | 19 +-
arch/x86/kernel/cpu/scattered.c | 7 +-
arch/x86/kernel/process_32.c | 4 +-
arch/x86/kernel/process_64.c | 4 +-
include/linux/sched.h | 2 +-
16 files changed, 318 insertions(+), 103 deletions(-)
rename Documentation/x86/{intel_rdt_ui.txt => resctrl_ui.txt} (99%)
rename arch/x86/include/asm/{intel_rdt_sched.h => resctrl_sched.h} (77%)
rename arch/x86/kernel/cpu/{intel_rdt.c => resctrl.c} (85%)
rename arch/x86/kernel/cpu/{intel_rdt.h => resctrl.h} (94%)
rename arch/x86/kernel/cpu/{intel_rdt_ctrlmondata.c => resctrl_ctrlmondata.c} (86%)
rename arch/x86/kernel/cpu/{intel_rdt_monitor.c => resctrl_monitor.c} (97%)
rename arch/x86/kernel/cpu/{intel_rdt_pseudo_lock.c => resctrl_pseudo_lock.c} (99%)
rename arch/x86/kernel/cpu/{intel_rdt_pseudo_lock_event.h => resctrl_pseudo_lock_event.h} (95%)
rename arch/x86/kernel/cpu/{intel_rdt_rdtgroup.c => resctrl_rdtgroup.c} (99%)Signature · 1 line
2.17.1
PATCH v7 1/13 arch/x86: Start renaming the rdt files to more generic names
New generation of AMD processors start supporting RDT(or QOS) features. With more than one vendors supporting these features, it seems more appropriate to rename these files.
Changed intel_rdt to resctrl where applicable.
---
arch/x86/include/asm/{intel_rdt_sched.h => resctrl_sched.h} | 0
arch/x86/kernel/cpu/Makefile | 6 +++---
arch/x86/kernel/cpu/{intel_rdt.c => resctrl.c} | 4 ++--
arch/x86/kernel/cpu/{intel_rdt.h => resctrl.h} | 6 +++---
.../cpu/{intel_rdt_ctrlmondata.c => resctrl_ctrlmondata.c} | 2 +-
.../kernel/cpu/{intel_rdt_monitor.c => resctrl_monitor.c} | 2 +-
.../cpu/{intel_rdt_pseudo_lock.c => resctrl_pseudo_lock.c} | 6 +++---
..._rdt_pseudo_lock_event.h => resctrl_pseudo_lock_event.h} | 2 +-
.../kernel/cpu/{intel_rdt_rdtgroup.c => resctrl_rdtgroup.c} | 4 ++--
arch/x86/kernel/process_32.c | 2 +-
arch/x86/kernel/process_64.c | 2 +-
11 files changed, 18 insertions(+), 18 deletions(-)
rename arch/x86/include/asm/{intel_rdt_sched.h => resctrl_sched.h} (100%)
rename arch/x86/kernel/cpu/{intel_rdt.c => resctrl.c} (99%)
rename arch/x86/kernel/cpu/{intel_rdt.h => resctrl.h} (99%)
rename arch/x86/kernel/cpu/{intel_rdt_ctrlmondata.c => resctrl_ctrlmondata.c} (99%)
rename arch/x86/kernel/cpu/{intel_rdt_monitor.c => resctrl_monitor.c} (99%)
rename arch/x86/kernel/cpu/{intel_rdt_pseudo_lock.c => resctrl_pseudo_lock.c} (99%)
rename arch/x86/kernel/cpu/{intel_rdt_pseudo_lock_event.h => resctrl_pseudo_lock_event.h} (95%)
rename arch/x86/kernel/cpu/{intel_rdt_rdtgroup.c => resctrl_rdtgroup.c} (99%)arch/x86/include/asm/resctrl_sched.h renamed from arch/x86/include/asm/intel_rdt_sched.h +0 -0
arch/x86/kernel/cpu/Makefile +3 -3
@@ -35,9 +35,9 @@ obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o obj-$(CONFIG_CPU_SUP_TRANSMETA_32) += transmeta.o obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o -obj-$(CONFIG_INTEL_RDT) += intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_monitor.o -obj-$(CONFIG_INTEL_RDT) += intel_rdt_ctrlmondata.o intel_rdt_pseudo_lock.o -CFLAGS_intel_rdt_pseudo_lock.o = -I$(src) +obj-$(CONFIG_INTEL_RDT) += resctrl.o resctrl_rdtgroup.o resctrl_monitor.o +obj-$(CONFIG_INTEL_RDT) += resctrl_ctrlmondata.o resctrl_pseudo_lock.o +CFLAGS_resctrl_pseudo_lock.o = -I$(src) obj-$(CONFIG_X86_MCE) += mcheck/ obj-$(CONFIG_MTRR) += mtrr/
arch/x86/kernel/cpu/resctrl.c renamed from arch/x86/kernel/cpu/intel_rdt.c +2 -2
@@ -30,8 +30,8 @@#include <linux/cpuhotplug.h> #include <asm/intel-family.h> -#include <asm/intel_rdt_sched.h> -#include "intel_rdt.h" +#include <asm/resctrl_sched.h> +#include "resctrl.h" #define MBA_IS_LINEAR 0x4#define MBA_MAX_MBPS U32_MAX
arch/x86/kernel/cpu/resctrl.h renamed from arch/x86/kernel/cpu/intel_rdt.h +3 -3
@@ -1,6 +1,6 @@/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_X86_INTEL_RDT_H -#define _ASM_X86_INTEL_RDT_H +#ifndef _ASM_X86_RESCTRL_H +#define _ASM_X86_RESCTRL_H#include <linux/sched.h> #include <linux/kernfs.h>
@@ -568,4 +568,4 @@ void cqm_handle_limbo(struct work_struct *work);bool has_busy_rmid (struct rdt_resource *r,struct rdt_domain *d);void __check_limbo (struct rdt_domain *d,bool force_free); -#endif /* _ASM_X86_INTEL_RDT_H */ +#endif /* _ASM_X86_RESCTRL_H */
arch/x86/kernel/cpu/resctrl_ctrlmondata.c renamed from arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c +1 -1
@@ -26,7 +26,7 @@#include <linux/kernfs.h> #include <linux/seq_file.h> #include <linux/slab.h> -#include "intel_rdt.h" +#include "resctrl.h" /* * Check whether MBA bandwidth percentage value is correct. The value is
arch/x86/kernel/cpu/resctrl_monitor.c renamed from arch/x86/kernel/cpu/intel_rdt_monitor.c +1 -1
@@ -26,7 +26,7 @@#include <linux/module.h> #include <linux/slab.h> #include <asm/cpu_device_id.h> -#include "intel_rdt.h" +#include "resctrl.h" #define MSR_IA32_QM_CTR 0x0c8e#define MSR_IA32_QM_EVTSEL 0x0c8d
arch/x86/kernel/cpu/resctrl_pseudo_lock.c renamed from arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c +3 -3
@@ -24,14 +24,14 @@#include <asm/cacheflush.h> #include <asm/intel-family.h> -#include <asm/intel_rdt_sched.h> +#include <asm/resctrl_sched.h> #include <asm/perf_event.h> #include "../../events/perf_event.h" /* For X86_CONFIG() */ -#include "intel_rdt.h" +#include "resctrl.h" #define CREATE_TRACE_POINTS -#include "intel_rdt_pseudo_lock_event.h" +#include "resctrl_pseudo_lock_event.h" /* * MSR_MISC_FEATURE_CONTROL register enables the modification of hardware
arch/x86/kernel/cpu/resctrl_pseudo_lock_event.h renamed from arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h +1 -1
@@ -39,5 +39,5 @@ TRACE_EVENT(pseudo_lock_l3,#undef TRACE_INCLUDE_PATH#define TRACE_INCLUDE_PATH . -#define TRACE_INCLUDE_FILE intel_rdt_pseudo_lock_event +#define TRACE_INCLUDE_FILE resctrl_pseudo_lock_event#include <trace/define_trace.h>
arch/x86/kernel/cpu/resctrl_rdtgroup.c renamed from arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +2 -2
@@ -35,8 +35,8 @@#include <uapi/linux/magic.h> -#include <asm/intel_rdt_sched.h> -#include "intel_rdt.h" +#include <asm/resctrl_sched.h> +#include "resctrl.h" DEFINE_STATIC_KEY_FALSE (rdt_enable_key);DEFINE_STATIC_KEY_FALSE (rdt_mon_enable_key);
arch/x86/kernel/process_32.c +1 -1
@@ -56,7 +56,7 @@#include <asm/debugreg.h> #include <asm/switch_to.h> #include <asm/vm86.h> -#include <asm/intel_rdt_sched.h> +#include <asm/resctrl_sched.h> #include <asm/proto.h> void __show_regs (struct pt_regs *regs,enum show_regs_mode mode)
arch/x86/kernel/process_64.c +1 -1
@@ -52,7 +52,7 @@#include <asm/switch_to.h> #include <asm/xen/hypervisor.h> #include <asm/vdso.h> -#include <asm/intel_rdt_sched.h> +#include <asm/resctrl_sched.h> #include <asm/unistd.h> #ifdef CONFIG_IA32_EMULATION /* Not included via unistd.h */
Signature · 1 line
2.17.1
Re: [PATCH v7 01/13] arch/x86: Start renaming the rdt files to more generic names
Subject: [PATCH v7 01/13] arch/x86: Start renaming the rdt files to more generic names
I guess the subject prefix for all those should be "arch/resctrl:" or so now.
Quoted 20 lines · Babu
New generation of AMD processors start supporting RDT(or QOS) features. With more than one vendors supporting these features, it seems more appropriate to rename these files.
Changed
intel_rdtto resctrl where applicable.Signed-off-by Babu Moger <[email protected]>--- arch/x86/include/asm/{intel_rdt_sched.h => resctrl_sched.h} | 0 arch/x86/kernel/cpu/Makefile | 6 +++--- arch/x86/kernel/cpu/{intel_rdt.c => resctrl.c} | 4 ++-- arch/x86/kernel/cpu/{intel_rdt.h => resctrl.h} | 6 +++--- .../cpu/{intel_rdt_ctrlmondata.c => resctrl_ctrlmondata.c} | 2 +- .../kernel/cpu/{intel_rdt_monitor.c => resctrl_monitor.c} | 2 +- .../cpu/{intel_rdt_pseudo_lock.c => resctrl_pseudo_lock.c} | 6 +++--- ..._rdt_pseudo_lock_event.h => resctrl_pseudo_lock_event.h} | 2 +- .../kernel/cpu/{intel_rdt_rdtgroup.c => resctrl_rdtgroup.c} | 4 ++-- arch/x86/kernel/process_32.c | 2 +- arch/x86/kernel/process_64.c | 2 +- 11 files changed, 18 insertions(+), 18 deletions(-)
Quoted 8 lines
rename arch/x86/include/asm/{intel_rdt_sched.h => resctrl_sched.h} (100%)
rename arch/x86/kernel/cpu/{intel_rdt.c => resctrl.c} (99%)
rename arch/x86/kernel/cpu/{intel_rdt.h => resctrl.h} (99%)
rename arch/x86/kernel/cpu/{intel_rdt_ctrlmondata.c => resctrl_ctrlmondata.c} (99%)
rename arch/x86/kernel/cpu/{intel_rdt_monitor.c => resctrl_monitor.c} (99%)
rename arch/x86/kernel/cpu/{intel_rdt_pseudo_lock.c => resctrl_pseudo_lock.c} (99%)
rename arch/x86/kernel/cpu/{intel_rdt_pseudo_lock_event.h => resctrl_pseudo_lock_event.h} (95%)
rename arch/x86/kernel/cpu/{intel_rdt_rdtgroup.c => resctrl_rdtgroup.c} (99%)Other than that and FWIW:
Signature · 4 lines
Regards/Gruss,
Boris.
Good mailing practices for 400: avoid top-posting and trim the reply.Re: [PATCH v7 01/13] arch/x86: Start renaming the rdt files to more generic names
Quoted 4 lines · Borislav Petkov
Subject: [PATCH v7 01/13]
arch/x86: Start renaming the rdt files to more generic namesI guess the subject prefix for all those should be "
arch/resctrl:" or so now.
Ok. Will change it.
Quoted 31 lines · Babu
Quoted 20 lines
New generation of AMD processors start supporting RDT(or QOS) features. With more than one vendors supporting these features, it seems more appropriate to rename these files.
Changed
intel_rdtto resctrl where applicable.Signed-off-by Babu Moger <[email protected]>--- arch/x86/include/asm/{intel_rdt_sched.h => resctrl_sched.h} | 0 arch/x86/kernel/cpu/Makefile | 6 +++--- arch/x86/kernel/cpu/{intel_rdt.c => resctrl.c} | 4 ++-- arch/x86/kernel/cpu/{intel_rdt.h => resctrl.h} | 6 +++--- .../cpu/{intel_rdt_ctrlmondata.c => resctrl_ctrlmondata.c} | 2 +- .../kernel/cpu/{intel_rdt_monitor.c => resctrl_monitor.c} | 2 +- .../cpu/{intel_rdt_pseudo_lock.c => resctrl_pseudo_lock.c} | 6 +++--- ..._rdt_pseudo_lock_event.h => resctrl_pseudo_lock_event.h} | 2 +- .../kernel/cpu/{intel_rdt_rdtgroup.c => resctrl_rdtgroup.c} | 4 ++-- arch/x86/kernel/process_32.c | 2 +- arch/x86/kernel/process_64.c | 2 +- 11 files changed, 18 insertions(+), 18 deletions(-)Quoted 8 lines
rename arch/x86/include/asm/{intel_rdt_sched.h => resctrl_sched.h} (100%) rename arch/x86/kernel/cpu/{intel_rdt.c => resctrl.c} (99%) rename arch/x86/kernel/cpu/{intel_rdt.h => resctrl.h} (99%) rename arch/x86/kernel/cpu/{intel_rdt_ctrlmondata.c => resctrl_ctrlmondata.c} (99%) rename arch/x86/kernel/cpu/{intel_rdt_monitor.c => resctrl_monitor.c} (99%) rename arch/x86/kernel/cpu/{intel_rdt_pseudo_lock.c => resctrl_pseudo_lock.c} (99%) rename arch/x86/kernel/cpu/{intel_rdt_pseudo_lock_event.h => resctrl_pseudo_lock_event.h} (95%) rename arch/x86/kernel/cpu/{intel_rdt_rdtgroup.c => resctrl_rdtgroup.c} (99%)
Quoted 4 lines
Other than that and FWIW:
Reviewed-by Borislav Petkov <[email protected]>
Thanks
RE: [PATCH v7 01/13] arch/x86: Start renaming the rdt files to more generic names
In reply to Borislav PetkovQuoted 5 lines
From: Borislav Petkov [mailto:[email protected]]
Subject: [PATCH v7 01/13]arch/x86: Start renaming the rdt files to more
generic namesI guess the subject prefix for all those should be "
arch/resctrl:" or so now.
Is "x86/resctrl" a better subject prefix?
Thanks.
-Fenghua
Borislav Petkov
maintainerRe: [PATCH v7 01/13] arch/x86: Start renaming the rdt files to more generic names
Quoted 1 line · Fenghua
Is "x86/resctrl" a better subject prefix?
Doh, of course. Diffstat is all arch/x86/.
Thx.
Signature · 4 lines
Regards/Gruss,
Boris.
Good mailing practices for 400: avoid top-posting and trim the reply.PATCH v7 2/13 arch/x86: Rename the RDT functions and definitions
In reply to Moger, BabuAs AMD is starting to support RDT(or QOS) features, rename the RDT functions and definitions to more generic names.
Replace intel_rdt to resctrl where applicable.
--- arch/x86/include/asm/resctrl_sched.h | 24 ++++++++++++------------ arch/x86/kernel/cpu/resctrl.c | 26 +++++++++++++------------- arch/x86/kernel/cpu/resctrl.h | 2 +- arch/x86/kernel/cpu/resctrl_monitor.c | 11 ++++++----- arch/x86/kernel/cpu/resctrl_rdtgroup.c | 10 +++++----- arch/x86/kernel/process_32.c | 2 +- arch/x86/kernel/process_64.c | 2 +- 7 files changed, 39 insertions(+), 38 deletions(-)
arch/x86/include/asm/resctrl_sched.h +12 -12
@@ -1,6 +1,6 @@/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_X86_INTEL_RDT_SCHED_H -#define _ASM_X86_INTEL_RDT_SCHED_H +#ifndef _ASM_X86_RESCTRL_SCHED_H +#define _ASM_X86_RESCTRL_SCHED_H#ifdef CONFIG_INTEL_RDT
@@ -10,7 +10,7 @@#define IA32_PQR_ASSOC 0x0c8f/** -* struct intel_pqr_state - State cache for the PQR MSR +* struct resctrl_pqr_state - State cache for the PQR MSR * @cur_rmid: The cached Resource Monitoring ID * @cur_closid: The cached Class Of Service ID * @default_rmid: The user assigned Resource Monitoring ID
@@ -24,21 +24,21 @@* The cache also helps to avoid pointless updates if the value does * not change. */ -struct intel_pqr_state { +struct resctrl_pqr_state {u32 cur_rmid;u32 cur_closid;u32 default_rmid;u32 default_closid; }; -DECLARE_PER_CPU(struct intel_pqr_state, pqr_state); +DECLARE_PER_CPU(struct resctrl_pqr_state, pqr_state);DECLARE_STATIC_KEY_FALSE (rdt_enable_key);DECLARE_STATIC_KEY_FALSE (rdt_alloc_enable_key);DECLARE_STATIC_KEY_FALSE (rdt_mon_enable_key);/* -* __intel_rdt_sched_in() - Writes the task's CLOSid/RMID to IA32_PQR_MSR +* __resctrl_sched_in() - Writes the task's CLOSid/RMID to IA32_PQR_MSR * * Following considerations are made so that this has minimal impact * on scheduler hot path:
@@ -51,9 +51,9 @@ DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key);* simple as possible. * Must be called with preemption disabled. */ -static void __intel_rdt_sched_in (void ) +static void __resctrl_sched_in (void ) { -struct intel_pqr_state *state =this_cpu_ptr (&pqr_state); +struct resctrl_pqr_state *state =this_cpu_ptr (&pqr_state);u32 closid = state->default_closid;u32 rmid = state->default_rmid;
@@ -78,16 +78,16 @@ static void __intel_rdt_sched_in(void) } } -static inline void intel_rdt_sched_in (void ) +static inline void resctrl_sched_in (void ) {if (static_branch_likely (&rdt_enable_key)) -__intel_rdt_sched_in (); +__resctrl_sched_in (); }#else -static inline void intel_rdt_sched_in (void ) {} +static inline void resctrl_sched_in (void ) {}#endif /* CONFIG_INTEL_RDT */ -#endif /* _ASM_X86_INTEL_RDT_SCHED_H */ +#endif /* _ASM_X86_RESCTRL_SCHED_H */
arch/x86/kernel/cpu/resctrl.c +13 -13
@@ -40,12 +40,12 @@DEFINE_MUTEX (rdtgroup_mutex);/* -* The cached intel_pqr_state is strictly per CPU and can never be +* The cached resctrl_pqr_state is strictly per CPU and can never be * updated from a remote CPU. Functions which modify the state * are called with interrupts disabled and no preemption, which * is sufficient for the protection. */ -DEFINE_PER_CPU(struct intel_pqr_state, pqr_state); +DEFINE_PER_CPU(struct resctrl_pqr_state, pqr_state);/* * Used to store the max resource name width and max resource data width
@@ -639,7 +639,7 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)static void clear_closid_rmid (int cpu) { -struct intel_pqr_state *state =this_cpu_ptr (&pqr_state); +struct resctrl_pqr_state *state =this_cpu_ptr (&pqr_state); state->default_closid =0 ; state->default_rmid =0 ;
@@ -648,7 +648,7 @@ static void clear_closid_rmid(int cpu)wrmsr (IA32_PQR_ASSOC ,0 ,0 ); } -static int intel_rdt_online_cpu (unsigned int cpu) +static int resctrl_online_cpu (unsigned int cpu) {struct rdt_resource *r;
@@ -674,7 +674,7 @@ static void clear_childcpus(struct rdtgroup *r, unsigned int cpu) } } -static int intel_rdt_offline_cpu (unsigned int cpu) +static int resctrl_offline_cpu (unsigned int cpu) {struct rdtgroup *rdtgrp;struct rdt_resource *r;
@@ -866,7 +866,7 @@ static __init bool get_rdt_resources(void)static enum cpuhp_state rdt_online; -static int __init intel_rdt_late_init (void ) +static int __init resctrl_late_init (void ) {struct rdt_resource *r;int state, ret;
@@ -877,8 +877,8 @@ static int __init intel_rdt_late_init(void)rdt_init_padding (); state =cpuhp_setup_state (CPUHP_AP_ONLINE_DYN , -"x86/rdt/cat:online:" , - intel_rdt_online_cpu, intel_rdt_offline_cpu); +"x86/resctrl/cat:online:" , + resctrl_online_cpu, resctrl_offline_cpu);if (state <0 )return state;
@@ -890,20 +890,20 @@ static int __init intel_rdt_late_init(void) rdt_online = state;for_each_alloc_capable_rdt_resource (r) -pr_info ("Intel RDT %s allocation detected\n" , r->name); +pr_info ("%s allocation detected\n" , r->name);for_each_mon_capable_rdt_resource (r) -pr_info ("Intel RDT %s monitoring detected\n" , r->name); +pr_info ("%s monitoring detected\n" , r->name);return 0 ; } -late_initcall (intel_rdt_late_init); +late_initcall (resctrl_late_init); -static void __exit intel_rdt_exit(void) +static void __exit resctrl_exit(void) {cpuhp_remove_state (rdt_online);rdtgroup_exit (); } -__exitcall (intel_rdt_exit); +__exitcall (resctrl_exit);
arch/x86/kernel/cpu/resctrl.h +1 -1
@@ -69,7 +69,7 @@ struct rmid_read {u64 val; }; -extern unsigned int intel_cqm_threshold; +extern unsigned int resctrl_cqm_threshold;extern bool rdt_alloc_capable;extern bool rdt_mon_capable;extern unsigned int rdt_mon_features;
arch/x86/kernel/cpu/resctrl_monitor.c +6 -5
@@ -73,7 +73,7 @@ unsigned int rdt_mon_features;* This is the threshold cache occupancy at which we will consider an * RMID available for re-allocation. */ -unsigned int intel_cqm_threshold; +unsigned int resctrl_cqm_threshold;static inline struct rmid_entry *__rmid_entry (u32 rmid) {
@@ -107,7 +107,7 @@ static bool rmid_dirty(struct rmid_entry *entry) {u64 val =__rmid_read (entry->rmid,QOS_L3_OCCUP_EVENT_ID ); -return val >= intel_cqm_threshold; +return val >= resctrl_cqm_threshold; }/*
@@ -187,7 +187,7 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)list_for_each_entry (d, &r->domains, list) {if (cpumask_test_cpu (cpu, &d->cpu_mask)) { val =__rmid_read (entry->rmid,QOS_L3_OCCUP_EVENT_ID ); -if (val <= intel_cqm_threshold) +if (val <= resctrl_cqm_threshold)continue ; }
@@ -637,10 +637,11 @@ int rdt_get_mon_l3_config(struct rdt_resource *r)* * For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC. */ - intel_cqm_threshold = boot_cpu_data.x86_cache_size *1024 / r->num_rmid; + resctrl_cqm_threshold = boot_cpu_data.x86_cache_size *1024 / + r->num_rmid;/* h/w works in units of "boot_cpu_data.x86_cache_occ_scale" */ - intel_cqm_threshold /= r->mon_scale; + resctrl_cqm_threshold /= r->mon_scale; ret =dom_data_init (r);if (ret)
arch/x86/kernel/cpu/resctrl_rdtgroup.c +5 -5
@@ -298,7 +298,7 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of, }/* -* This is safe against intel_rdt_sched_in() called from __switch_to() +* This is safe against resctrl_sched_in() called from __switch_to() * because __switch_to() is executed with interrupts disabled. A local call * from update_closid_rmid() is proteced against __switch_to() because * preemption is disabled.
@@ -317,7 +317,7 @@ static void update_cpu_closid_rmid(void *info)* executing task might have its own closid selected. Just reuse * the context switch code. */ -intel_rdt_sched_in (); +resctrl_sched_in (); }/*
@@ -542,7 +542,7 @@ static void move_myself(struct callback_head *head)preempt_disable ();/* update PQR_ASSOC MSR to make resource group go into effect */ -intel_rdt_sched_in (); +resctrl_sched_in ();preempt_enable ();kfree (callback);
@@ -926,7 +926,7 @@ static int max_threshold_occ_show(struct kernfs_open_file *of, {struct rdt_resource *r = of->kn->parent->priv; -seq_printf (seq,"%u\n" , intel_cqm_threshold * r->mon_scale); +seq_printf (seq,"%u\n" , resctrl_cqm_threshold * r->mon_scale);return 0 ; }
@@ -945,7 +945,7 @@ static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,if (bytes > (boot_cpu_data.x86_cache_size *1024 ))return -EINVAL ; - intel_cqm_threshold = bytes / r->mon_scale; + resctrl_cqm_threshold = bytes / r->mon_scale;return nbytes; }
arch/x86/kernel/process_32.c +1 -1
@@ -302,7 +302,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)this_cpu_write (current_task, next_p);/* Load the Intel cache allocation PQR MSR. */ -intel_rdt_sched_in (); +resctrl_sched_in ();return prev_p; }
arch/x86/kernel/process_64.c +1 -1
@@ -536,7 +536,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) }/* Load the Intel cache allocation PQR MSR. */ -intel_rdt_sched_in (); +resctrl_sched_in ();return prev_p; }
Signature · 1 line
2.17.1
Re: [PATCH v7 02/13] arch/x86: Rename the RDT functions and definitions
Quoted 6 lines · Babu
As AMD is starting to support RDT(or QOS) features, rename the RDT functions and definitions to more generic names.
Replace
intel_rdtto resctrl where applicable.Signed-off-by Babu Moger <[email protected]>
Quoted 9 lines
--- arch/x86/include/asm/resctrl_sched.h | 24 ++++++++++++------------ arch/x86/kernel/cpu/resctrl.c | 26 +++++++++++++------------- arch/x86/kernel/cpu/resctrl.h | 2 +- arch/x86/kernel/cpu/resctrl_monitor.c | 11 ++++++----- arch/x86/kernel/cpu/resctrl_rdtgroup.c | 10 +++++----- arch/x86/kernel/process_32.c | 2 +- arch/x86/kernel/process_64.c | 2 +- 7 files changed, 39 insertions(+), 38 deletions(-)
As with patch 1, pls fix subject prefix.
arch/x86/kernel/cpu/resctrl_monitor.c int rdt_get_mon_l3_config(struct rdt_resource *r) · line 641
Quoted 7 lines
arch/x86/kernel/cpu/resctrl_monitor.c +2
-1@@ -637,10 +637,11 @@ int rdt_get_mon_l3_config(struct rdt_resource *r)* * For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC. */ - intel_cqm_threshold = boot_cpu_data.x86_cache_size *1024 / r->num_rmid; + resctrl_cqm_threshold = boot_cpu_data.x86_cache_size *1024 / + r->num_rmid;
No need to break that line here.
With that addressed and FWIW:
Signature · 4 lines
Regards/Gruss,
Boris.
Good mailing practices for 400: avoid top-posting and trim the reply.Re: [PATCH v7 02/13] arch/x86: Rename the RDT functions and definitions
Boris,
Quoted 17 lines · Borislav Petkov
Quoted 6 lines · Babu
As AMD is starting to support RDT(or QOS) features, rename the RDT functions and definitions to more generic names.
Replace
intel_rdtto resctrl where applicable.Signed-off-by Babu Moger <[email protected]>Quoted 9 lines
--- arch/x86/include/asm/resctrl_sched.h | 24 ++++++++++++------------ arch/x86/kernel/cpu/resctrl.c | 26 +++++++++++++------------- arch/x86/kernel/cpu/resctrl.h | 2 +- arch/x86/kernel/cpu/resctrl_monitor.c | 11 ++++++----- arch/x86/kernel/cpu/resctrl_rdtgroup.c | 10 +++++----- arch/x86/kernel/process_32.c | 2 +- arch/x86/kernel/process_64.c | 2 +- 7 files changed, 39 insertions(+), 38 deletions(-)
Quoted 2 lines
As with patch 1, pls fix subject prefix.
Ok. Sure.
Quoted 9 lines
arch/x86/kernel/cpu/resctrl_monitor.c int rdt_get_mon_l3_config(struct rdt_resource *r) · line 641
Quoted 7 lines
arch/x86/kernel/cpu/resctrl_monitor.c +2
-1@@ -637,10 +637,11 @@ int rdt_get_mon_l3_config(struct rdt_resource *r)* * For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC. */ - intel_cqm_threshold = boot_cpu_data.x86_cache_size *1024 / r->num_rmid; + resctrl_cqm_threshold = boot_cpu_data.x86_cache_size *1024 / + r->num_rmid;No need to break that line here.
Without the line break, checkpatch complains for "line over 80 characters". Do you think we can ignore those?
Quoted 5 lines
With that addressed and FWIW:
Reviewed-by Borislav Petkov <[email protected]>
Borislav Petkov
maintainerRe: [PATCH v7 02/13] arch/x86: Rename the RDT functions and definitions
Quoted 10 lines · Babu
Quoted 9 lines
arch/x86/kernel/cpu/resctrl_monitor.c int rdt_get_mon_l3_config(struct rdt_resource *r) · line 641
Quoted 7 lines
arch/x86/kernel/cpu/resctrl_monitor.c +2
-1@@ -637,10 +637,11 @@ int rdt_get_mon_l3_config(struct rdt_resource *r)* * For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC. */ - intel_cqm_threshold = boot_cpu_data.x86_cache_size *1024 / r->num_rmid; + resctrl_cqm_threshold = boot_cpu_data.x86_cache_size *1024 / + r->num_rmid;No need to break that line here.
Quoted 2 lines
Without the line break, checkpatch complains for "line over 80 characters". Do you think we can ignore those?
To quote from the tip handbook which is in preparation right now:
"+The 80 character rule is not a strict rule, so please use common sense when
+breaking lines."
In this particular case, it is more readable IMO to leave the line unbroken:
resctrl_cqm_threshold = boot_cpu_data.x86_cache_size * 1024 / r->num_rmid;
What is even more readable though is:
unsigned int cl_size = boot_cpu_data.x86_cache_size; ... resctrl_cqm_threshold = cl_size * 1024 / r->num_rmid;
and now you have a win-win situation. :)
Thx.
Signature · 4 lines
Regards/Gruss,
Boris.
Good mailing practices for 400: avoid top-posting and trim the reply.Re: [PATCH v7 02/13] arch/x86: Rename the RDT functions and definitions
Quoted 25 lines · Borislav Petkov
Quoted 10 lines · Babu
Quoted 9 lines
arch/x86/kernel/cpu/resctrl_monitor.c int rdt_get_mon_l3_config(struct rdt_resource *r) · line 641
Quoted 7 lines
arch/x86/kernel/cpu/resctrl_monitor.c +2
-1@@ -637,10 +637,11 @@ int rdt_get_mon_l3_config(struct rdt_resource *r)* * For a 35MB LLC and 56 RMIDs, this is ~1.8% of the LLC. */ - intel_cqm_threshold = boot_cpu_data.x86_cache_size *1024 / r->num_rmid; + resctrl_cqm_threshold = boot_cpu_data.x86_cache_size *1024 / + r->num_rmid;No need to break that line here.
Quoted 2 lines
Without the line break, checkpatch complains for "line over 80 characters". Do you think we can ignore those?
To quote from the tip handbook which is in preparation right now:
"+The 80 character rule is not a strict rule, so please use common sense when
+breaking lines."In this particular case, it is more readable IMO to leave the line unbroken:
resctrl_cqm_threshold = boot_cpu_data.x86_cache_size * 1024 / r->num_rmid;What is even more readable though is:
Quoted 7 lines
unsigned int cl_size = boot_cpu_data.x86_cache_size; ... resctrl_cqm_threshold = cl_size * 1024 / r->num_rmid;and now you have a win-win situation. :)
Yes. Makes sense. Thanks
Quoted 3 lines
Thx.
PATCH v7 3/13 arch/x86: Re-arrange RDT init code
In reply to Moger, BabuSeparate the call sequence for rdt_quirks and MBA feature. This is in preparation to handle vendor differences in these call sequences.
--- arch/x86/kernel/cpu/resctrl.c | 29 +++++++++++++++++++++++------ 1 file changed, 23 insertions(+), 6 deletions(-)
arch/x86/kernel/cpu/resctrl.c +23 -6
@@ -794,6 +794,16 @@ static bool __init rdt_cpu_has(int flag)return ret; } +static __init bool rdt_mba_config (void ) +{ +if (rdt_cpu_has (X86_FEATURE_MBA )) { +if (rdt_get_mem_config (&rdt_resources_all[RDT_RESOURCE_MBA ])) +return true; + } + +return false; +} +static __init bool get_rdt_alloc_resources (void ) {bool ret = false;
@@ -818,10 +828,9 @@ static __init bool get_rdt_alloc_resources(void) ret = true; } -if (rdt_cpu_has (X86_FEATURE_MBA )) { -if (rdt_get_mem_config (&rdt_resources_all[RDT_RESOURCE_MBA ])) - ret = true; - } +if (rdt_mba_config ()) + ret = true; +return ret; }
@@ -840,7 +849,7 @@ static __init bool get_rdt_mon_resources(void)return !rdt_get_mon_l3_config (&rdt_resources_all[RDT_RESOURCE_L3 ]); } -static __init void rdt_quirks (void ) +static __init void rdt_quirks_intel (void ) {switch (boot_cpu_data.x86_model) {case INTEL_FAM6_HASWELL_X :
@@ -855,9 +864,14 @@ static __init void rdt_quirks(void) } } +static __init void rdt_quirks (void ) +{ +if (boot_cpu_data.x86_vendor ==X86_VENDOR_INTEL ) +rdt_quirks_intel (); +} +static __init bool get_rdt_resources (void ) { -rdt_quirks (); rdt_alloc_capable =get_rdt_alloc_resources (); rdt_mon_capable =get_rdt_mon_resources ();
@@ -871,6 +885,9 @@ static int __init resctrl_late_init(void)struct rdt_resource *r;int state, ret; +/* Run quirks first */ +rdt_quirks (); +if (!get_rdt_resources ())return -ENODEV ;
Signature · 1 line
2.17.1
Borislav Petkov
maintainerRe: [PATCH v7 03/13] arch/x86: Re-arrange RDT init code
Quoted 14 lines · Babu
Separate the call sequence for
rdt_quirksand MBA feature. This is in preparation to handle vendor differences in these call sequences.Signed-off-by Babu Moger <[email protected]>--- arch/x86/kernel/cpu/resctrl.c | 29 +++++++++++++++++++++++------ 1 file changed, 23 insertions(+), 6 deletions(-)arch/x86/kernel/cpu/resctrl.c +0
-0
arch/x86/kernel/cpu/resctrl.c static bool __init rdt_cpu_has(int flag) · line 801
Quoted 8 lines
arch/x86/kernel/cpu/resctrl.c +5
-0@@ -794,6 +794,16 @@ static bool __init rdt_cpu_has(int flag)return ret; } +static __init bool rdt_mba_config (void ) +{ +if (rdt_cpu_has (X86_FEATURE_MBA )) { +if (rdt_get_mem_config (&rdt_resources_all[RDT_RESOURCE_MBA ])) +return true;
Or simpler:
if (rdt_cpu_has(X86_FEATURE_MBA))
return rdt_get_mem_config(&rdt_resources_all[RDT_RESOURCE_MBA]);
return false;as rdt_get_mem_config() already returns bool.
Signature · 4 lines
Regards/Gruss,
Boris.
Good mailing practices for 400: avoid top-posting and trim the reply.Re: [PATCH v7 03/13] arch/x86: Re-arrange RDT init code
Boris,
Quoted 26 lines · Borislav Petkov
Quoted 14 lines · Babu
Separate the call sequence for
rdt_quirksand MBA feature. This is in preparation to handle vendor differences in these call sequences.Signed-off-by Babu Moger <[email protected]>--- arch/x86/kernel/cpu/resctrl.c | 29 +++++++++++++++++++++++------ 1 file changed, 23 insertions(+), 6 deletions(-)arch/x86/kernel/cpu/resctrl.c +0
-0arch/x86/kernel/cpu/resctrl.c static bool __init rdt_cpu_has(int flag) · line 801
Quoted 8 lines
arch/x86/kernel/cpu/resctrl.c +5
-0@@ -794,6 +794,16 @@ static bool __init rdt_cpu_has(int flag)return ret; } +static __init bool rdt_mba_config (void ) +{ +if (rdt_cpu_has (X86_FEATURE_MBA )) { +if (rdt_get_mem_config (&rdt_resources_all[RDT_RESOURCE_MBA ])) +return true;Or simpler:
Quoted 7 lines
if (rdt_cpu_has(X86_FEATURE_MBA)) return rdt_get_mem_config(&rdt_resources_all[RDT_RESOURCE_MBA]); return false;as
rdt_get_mem_config()already returns bool.
Yes. We could do that. Will modify it.
PATCH v7 4/13 arch/x86: Bring all the macros to resctrl.h
In reply to Moger, BabuBring all the macros to resctrl.h and rename for consistency.
--- arch/x86/kernel/cpu/resctrl.c | 3 --- arch/x86/kernel/cpu/resctrl.h | 5 +++++ arch/x86/kernel/cpu/resctrl_monitor.c | 7 ++----- 3 files changed, 7 insertions(+), 8 deletions(-)
arch/x86/kernel/cpu/resctrl.c +0 -3
@@ -33,9 +33,6 @@#include <asm/resctrl_sched.h> #include "resctrl.h" -#define MBA_IS_LINEAR 0x4 -#define MBA_MAX_MBPS U32_MAX -/* Mutex to protect rdtgroup access. */ DEFINE_MUTEX (rdtgroup_mutex);
arch/x86/kernel/cpu/resctrl.h +5 -0
@@ -12,6 +12,9 @@#define IA32_L2_CBM_BASE 0xd10#define IA32_MBA_THRTL_BASE 0xd50 +#define IA32_QM_CTR 0x0c8e +#define IA32_QM_EVTSEL 0x0c8d +#define L3_QOS_CDP_ENABLE 0x01ULL#define L2_QOS_CDP_ENABLE 0x01ULL
@@ -29,6 +32,8 @@#define MBM_CNTR_WIDTH 24#define MBM_OVERFLOW_INTERVAL 1000#define MAX_MBA_BW 100u +#define MBA_IS_LINEAR 0x4 +#define MBA_MAX_MBPS U32_MAX#define RMID_VAL_ERROR BIT_ULL(63)#define RMID_VAL_UNAVAIL BIT_ULL(62)
arch/x86/kernel/cpu/resctrl_monitor.c +2 -5
@@ -28,9 +28,6 @@#include <asm/cpu_device_id.h> #include "resctrl.h" -#define MSR_IA32_QM_CTR 0x0c8e -#define MSR_IA32_QM_EVTSEL 0x0c8d -struct rmid_entry {u32 rmid;int busy;
@@ -97,8 +94,8 @@ static u64 __rmid_read(u32 rmid, u32 eventid)* IA32_QM_CTR.Error (bit 63) and IA32_QM_CTR.Unavailable (bit 62) * are error bits. */ -wrmsr (MSR_IA32_QM_EVTSEL , eventid, rmid); -rdmsrl (MSR_IA32_QM_CTR , val); +wrmsr (IA32_QM_EVTSEL , eventid, rmid); +rdmsrl (IA32_QM_CTR , val);return val; }
Signature · 1 line
2.17.1
PATCH v7 5/13 arch/x86: Rename config parameter INTEL_RDT to RESCTRL
In reply to Moger, BabuNow Resource control feature is supported by both Intel and AMD. Rename the INTEL_RDT to vendor neutral RESCTRL.
--- arch/x86/Kconfig | 4 ++-- arch/x86/include/asm/resctrl_sched.h | 4 ++-- arch/x86/kernel/cpu/Makefile | 4 ++-- include/linux/sched.h | 2 +- 4 files changed, 7 insertions(+), 7 deletions(-)
arch/x86/Kconfig +2 -2
@@ -445,8 +445,8 @@ config RETPOLINE code are eliminated. Since this includes the syscall entry path, it is not entirely pointless. -config INTEL_RDT - bool "Intel Resource Director Technology support" +config RESCTRL + bool "Resource Control feature support" default n depends on X86 && CPU_SUP_INTEL select KERNFS
arch/x86/include/asm/resctrl_sched.h +2 -2
@@ -2,7 +2,7 @@#ifndef _ASM_X86_RESCTRL_SCHED_H#define _ASM_X86_RESCTRL_SCHED_H -#ifdef CONFIG_INTEL_RDT +#ifdef CONFIG_RESCTRL #include <linux/sched.h> #include <linux/jump_label.h>
@@ -88,6 +88,6 @@ static inline void resctrl_sched_in(void)static inline void resctrl_sched_in (void ) {} -#endif /* CONFIG_INTEL_RDT */ +#endif /* CONFIG_RESCTRL */ #endif /* _ASM_X86_RESCTRL_SCHED_H */
arch/x86/kernel/cpu/Makefile +2 -2
@@ -35,8 +35,8 @@ obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o obj-$(CONFIG_CPU_SUP_TRANSMETA_32) += transmeta.o obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o -obj-$(CONFIG_INTEL_RDT) += resctrl.o resctrl_rdtgroup.o resctrl_monitor.o -obj-$(CONFIG_INTEL_RDT) += resctrl_ctrlmondata.o resctrl_pseudo_lock.o +obj-$(CONFIG_RESCTRL) += resctrl.o resctrl_rdtgroup.o resctrl_monitor.o +obj-$(CONFIG_RESCTRL) += resctrl_ctrlmondata.o resctrl_pseudo_lock.o CFLAGS_resctrl_pseudo_lock.o = -I$(src) obj-$(CONFIG_X86_MCE) += mcheck/
include/linux/sched.h +1 -1
@@ -985,7 +985,7 @@ struct task_struct {/* cg_list protected by css_set_lock and tsk->alloc_lock: */ struct list_head cg_list;#endif -#ifdef CONFIG_INTEL_RDT +#ifdef CONFIG_RESCTRL u32 closid;u32 rmid;#endif
Signature · 1 line
2.17.1
PATCH v7 6/13 arch/x86: Initialize the resource functions that are different
In reply to Moger, BabuInitialize the resource functions that are different between the vendors. Some features are initialized differently between the vendors. Add _intel suffix to Intel specific functions.
For example, MBA feature varies significantly between Intel and AMD. Separate the initialization of these resource functions. That way we can easily add AMD's functions later.
--- arch/x86/kernel/cpu/resctrl.c | 34 +++++++++++++++++++---- arch/x86/kernel/cpu/resctrl.h | 8 ++++-- arch/x86/kernel/cpu/resctrl_ctrlmondata.c | 4 +-- 3 files changed, 37 insertions(+), 9 deletions(-)
arch/x86/kernel/cpu/resctrl.c +29 -5
@@ -57,7 +57,8 @@ int max_name_width, max_data_width;bool rdt_alloc_capable;static void -mba_wrmsr (struct rdt_domain *d,struct msr_param *m,struct rdt_resource *r); +mba_wrmsr_intel (struct rdt_domain *d,struct msr_param *m, +struct rdt_resource *r);static void cat_wrmsr (struct rdt_domain *d,struct msr_param *m,struct rdt_resource *r);
@@ -171,10 +172,7 @@ struct rdt_resource rdt_resources_all[] = { .rid = RDT_RESOURCE_MBA, .name = "MB", .domains = domain_init(RDT_RESOURCE_MBA), - .msr_base = IA32_MBA_THRTL_BASE, - .msr_update = mba_wrmsr, .cache_level = 3, - .parse_ctrlval = parse_bw, .format_str = "%d=%*u", .fflags = RFTYPE_RES_MB, },
@@ -356,7 +354,8 @@ u32 delay_bw_map(unsigned long bw, struct rdt_resource *r) }static void -mba_wrmsr (struct rdt_domain *d,struct msr_param *m,struct rdt_resource *r) +mba_wrmsr_intel (struct rdt_domain *d,struct msr_param *m, +struct rdt_resource *r) {unsigned int i;
@@ -875,6 +874,25 @@ static __init bool get_rdt_resources(void)return (rdt_mon_capable || rdt_alloc_capable); } +static __init void rdt_init_res_defs_intel (void ) +{ +struct rdt_resource *r; + +for_each_rdt_resource (r) { +if (r->rid ==RDT_RESOURCE_MBA ) { + r->msr_base =IA32_MBA_THRTL_BASE ; + r->msr_update = mba_wrmsr_intel; + r->parse_ctrlval = parse_bw_intel; + } + } +} + +static __init void rdt_init_res_defs (void ) +{ +if (boot_cpu_data.x86_vendor ==X86_VENDOR_INTEL ) +rdt_init_res_defs_intel (); +} +static enum cpuhp_state rdt_online;static int __init resctrl_late_init (void )
@@ -882,6 +900,12 @@ static int __init resctrl_late_init(void)struct rdt_resource *r;int state, ret; +/* +* Initialize functions(or definitions) that are different +* between vendors here. +*/ +rdt_init_res_defs (); +/* Run quirks first */ rdt_quirks ();
arch/x86/kernel/cpu/resctrl.h +6 -2
@@ -444,8 +444,8 @@ struct rdt_resource {int parse_cbm (struct rdt_parse_data *data,struct rdt_resource *r,struct rdt_domain *d); -int parse_bw (struct rdt_parse_data *data,struct rdt_resource *r, -struct rdt_domain *d); +int parse_bw_intel (struct rdt_parse_data *data,struct rdt_resource *r, +struct rdt_domain *d);extern struct mutex rdtgroup_mutex;
@@ -468,6 +468,10 @@ enum { RDT_NUM_RESOURCES, }; +#define for_each_rdt_resource (r) \ + for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ + r++) +#define for_each_capable_rdt_resource (r) \ for (r = rdt_resources_all; r < rdt_resources_all + RDT_NUM_RESOURCES;\ r++) \
arch/x86/kernel/cpu/resctrl_ctrlmondata.c +2 -2
@@ -64,8 +64,8 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)return true; } -int parse_bw (struct rdt_parse_data *data,struct rdt_resource *r, -struct rdt_domain *d) +int parse_bw_intel (struct rdt_parse_data *data,struct rdt_resource *r, +struct rdt_domain *d) {unsigned long bw_val;
Signature · 1 line
2.17.1
PATCH v7 7/13 arch/x86: Bring cbm_validate function into the resource structure
In reply to Moger, BabuIdea is to bring all the functions that are different between the vendors into resource structure and initialize them dynamically. Add _intel suffix to Intel specific functions.
Following function is implemented separately for each vendors. cbm_validate : Cache bitmask validate function. AMD allows
non-contiguous masks. So, use separate functions for Intel and AMD.
--- arch/x86/kernel/cpu/resctrl.c | 9 ++++++++- arch/x86/kernel/cpu/resctrl.h | 11 +++++++---- arch/x86/kernel/cpu/resctrl_ctrlmondata.c | 4 ++-- 3 files changed, 17 insertions(+), 7 deletions(-)
arch/x86/kernel/cpu/resctrl.c +8 -1
@@ -879,7 +879,14 @@ static __init void rdt_init_res_defs_intel(void)struct rdt_resource *r;for_each_rdt_resource (r) { -if (r->rid ==RDT_RESOURCE_MBA ) { +if (r->rid ==RDT_RESOURCE_L3 || + r->rid ==RDT_RESOURCE_L3DATA || + r->rid ==RDT_RESOURCE_L3CODE || + r->rid ==RDT_RESOURCE_L2 || + r->rid ==RDT_RESOURCE_L2DATA || + r->rid ==RDT_RESOURCE_L2CODE ) + r->cbm_validate = cbm_validate_intel; +else if (r->rid ==RDT_RESOURCE_MBA ) { r->msr_base =IA32_MBA_THRTL_BASE ; r->msr_update = mba_wrmsr_intel; r->parse_ctrlval = parse_bw_intel;
arch/x86/kernel/cpu/resctrl.h +7 -4
@@ -410,10 +410,11 @@ struct rdt_parse_data {* @cache: Cache allocation related data * @format_str: Per resource format string to show domain value * @parse_ctrlval: Per resource function pointer to parse control values -* @evt_list: List of monitoring events -* @num_rmid: Number of RMIDs available -* @mon_scale: cqm counter * mon_scale = occupancy in bytes -* @fflags: flags to choose base and info files +* @cbm_validate Cache bitmask validate function +* @evt_list: List of monitoring events +* @num_rmid: Number of RMIDs available +* @mon_scale: cqm counter * mon_scale = occupancy in bytes +* @fflags: flags to choose base and info files */ struct rdt_resource {int rid;
@@ -436,6 +437,7 @@ struct rdt_resource {int (*parse_ctrlval)(struct rdt_parse_data *data,struct rdt_resource *r,struct rdt_domain *d); +bool (*cbm_validate)(char *buf,u32 *data,struct rdt_resource *r);struct list_head evt_list;int num_rmid;unsigned int mon_scale;
@@ -576,5 +578,6 @@ void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms);void cqm_handle_limbo (struct work_struct *work);bool has_busy_rmid (struct rdt_resource *r,struct rdt_domain *d);void __check_limbo (struct rdt_domain *d,bool force_free); +bool cbm_validate_intel (char *buf,u32 *data,struct rdt_resource *r);#endif /* _ASM_X86_RESCTRL_H */
arch/x86/kernel/cpu/resctrl_ctrlmondata.c +2 -2
@@ -88,7 +88,7 @@ int parse_bw_intel(struct rdt_parse_data *data, struct rdt_resource *r,* are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.). * Additionally Haswell requires at least two bits set. */ -static bool cbm_validate (char *buf,u32 *data,struct rdt_resource *r) +bool cbm_validate_intel (char *buf,u32 *data,struct rdt_resource *r) {unsigned long first_bit, zero_bit, val;unsigned int cbm_len = r->cache.cbm_len;
@@ -148,7 +148,7 @@ int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,return -EINVAL ; } -if (!cbm_validate (data->buf, &cbm_val, r)) +if (r->cbm_validate && !r->cbm_validate (data->buf, &cbm_val, r))return -EINVAL ; if ((rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
Signature · 1 line
2.17.1
PATCH v7 8/13 arch/x86: Add vendor check for MBA software controller
In reply to Moger, BabuMBA software controller support is available only on Intel.
--- arch/x86/kernel/cpu/resctrl_rdtgroup.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)
arch/x86/kernel/cpu/resctrl_rdtgroup.c +4 -1
@@ -1878,7 +1878,10 @@ static int parse_rdtgroupfs_options(char *data)if (ret) goto out; }else if (!strcmp (token,"mba_MBps" )) { - ret =set_mba_sc (true); +if (boot_cpu_data.x86_vendor ==X86_VENDOR_INTEL ) + ret =set_mba_sc (true); +else + ret = -EINVAL ;if (ret) goto out; }else {
Signature · 1 line
2.17.1
PATCH v7 9/13 arch/x86: Update the RESCTRL config parameter
In reply to Moger, BabuCONFIG_RESCTRL will be used for both Intel and AMD to enable Resource Control feature. Update the details and condition accordingly.
--- arch/x86/Kconfig | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-)
arch/x86/Kconfig +14 -5
@@ -448,13 +448,22 @@ config RETPOLINE config RESCTRL bool "Resource Control feature support" default n - depends on X86 && CPU_SUP_INTEL + depends on X86 && (CPU_SUP_INTEL || CPU_SUP_AMD) select KERNFS help - Select to enable resource allocation and monitoring which are - sub-features of Intel Resource Director Technology(RDT). More - information about RDT can be found in the Intel x86 - Architecture Software Developer Manual. + Select to enable Resource Control feature support. + + These features are intended to provide the support for the allocation + and monitoring the usage of certain system resources by one or more + processors. + + Intel refers this feature as Intel Resource Director Technology + (Intel(R) RDT). More information about RDT can be found in the + Intel x86 Architecture Software Developer Manual. + + AMD refers this feature as AMD Platform Quality of Service(AMD QoS). + More information about AMD QoS can be found in AMD64 Technology + Platform Quality of Service Extensions manual. Say N if unsure.
Signature · 1 line
2.17.1
PATCH v7 10/13 arch/x86: Add AMD feature bit X86_FEATURE_MBA in cpuid bits array
In reply to Moger, BabuFrom: Sherry Hurwitz <[email protected]>
The feature bit X86_FEATURE_MBA is detected via CPUID leaf 0x80000008 EBX Bit 06. This bit indicates the support of AMD's MBA feature.
This feature is supported by both Intel and AMD. But they are detected in different CPUID leaves.
--- arch/x86/kernel/cpu/scattered.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)
arch/x86/kernel/cpu/scattered.c +6 -1
@@ -17,7 +17,11 @@ struct cpuid_bit {u32 sub_leaf; }; -/* Please keep the leaf sorted by cpuid_bit.level for faster search. */ +/* +* Please keep the leaf sorted by cpuid_bit.level for faster search. +* X86_FEATURE_MBA supported by both Intel and AMD. But the cpuid +* levels are different. Add a separate enty for each. +*/ static const struct cpuid_bit cpuid_bits[] = { {X86_FEATURE_APERFMPERF ,CPUID_ECX ,0 ,0x00000006 ,0 }, {X86_FEATURE_EPB ,CPUID_ECX ,3 ,0x00000006 ,0 },
@@ -29,6 +33,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_HW_PSTATE, CPUID_EDX, 7, 0x80000007, 0 }, { X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 }, { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, + { X86_FEATURE_MBA, CPUID_EBX, 6, 0x80000008, 0 }, { X86_FEATURE_SME, CPUID_EAX, 0, 0x8000001f, 0 }, { X86_FEATURE_SEV, CPUID_EAX, 1, 0x8000001f, 0 }, { 0, 0, 0, 0, 0 }
Signature · 1 line
2.17.1
PATCH v7 11/13 arch/x86: Introduce QOS feature for AMD
In reply to Moger, BabuEnables QOS feature on AMD.
Following QoS sub-features are supported in AMD if the underlying hardware supports it.
- L3 Cache allocation enforcement
- L3 Cache occupancy monitoring
- L3 Code-Data Prioritization support
- Memory Bandwidth Enforcement(Allocation)
The specification for this feature is available at
https://developer.amd.com/wp-content/resources/56375.pdf
There are differences in the way some of the features are implemented. Separate those functions and add those as vendor specific functions. The major difference is in MBA feature.
- AMD uses CPUID leaf 0x80000020 to initialize the MBA features.
- AMD uses direct bandwidth value instead of delay based on bandwidth values.
- MSR register base addresses are different for MBA.
- Also AMD allows non-contiguous L3 cache bit masks.
Adds following functions to take care of the differences. rdt_get_mem_config_amd : MBA initialization function parse_bw_amd : Bandwidth parsingmba_wrmsr_amd: Writes bandwidth value cbm_validate_amd : L3 cache bitmask validation
--- arch/x86/kernel/cpu/resctrl.c | 69 +++++++++++++++++++++- arch/x86/kernel/cpu/resctrl.h | 5 ++ arch/x86/kernel/cpu/resctrl_ctrlmondata.c | 70 +++++++++++++++++++++++ 3 files changed, 142 insertions(+), 2 deletions(-)
arch/x86/kernel/cpu/resctrl.c +67 -2
@@ -61,6 +61,9 @@ mba_wrmsr_intel(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r);static void cat_wrmsr (struct rdt_domain *d,struct msr_param *m,struct rdt_resource *r); +static void +mba_wrmsr_amd (struct rdt_domain *d,struct msr_param *m, +struct rdt_resource *r);#define domain_init (id) LIST_HEAD_INIT(rdt_resources_all[id].domains)
@@ -280,6 +283,31 @@ static bool rdt_get_mem_config(struct rdt_resource *r)return true; } +static bool rdt_get_mem_config_amd (struct rdt_resource *r) +{ +union cpuid_0x10_3_eax eax; +union cpuid_0x10_x_edx edx; +u32 ebx, ecx; + +cpuid_count (0x80000020 ,1 , &eax.full, &ebx, &ecx, &edx.full); + r->num_closid = edx.split.cos_max +1 ; + r->default_ctrl =MAX_MBA_BW_AMD ; + +/* AMD does not use delay. Set delay_linear to false by default */ + r->membw.delay_linear = false; + +/* FIX ME - May need to be read from MSR */ + r->membw.min_bw =0 ; + r->membw.bw_gran =1 ; +/* Max value is 2048, Data width should be 4 in decimal */ + r->data_width =4 ; + + r->alloc_capable = true; + r->alloc_enabled = true; + +return true; +} +static void rdt_get_cache_alloc_cfg (int idx,struct rdt_resource *r) {union cpuid_0x10_1_eax eax;
@@ -339,6 +367,16 @@ static int get_cache_id(int cpu, int level)return -1 ; } +static void +mba_wrmsr_amd (struct rdt_domain *d,struct msr_param *m,struct rdt_resource *r) +{ +unsigned int i; + +/* Write the bw values for mba. */ +for (i = m->low; i < m->high; i++) +wrmsrl (r->msr_base + i, d->ctrl_val[i]); +} +/* * Map the memory b/w percentage value to delay values * that can be written to QOS_MSRs.
@@ -793,8 +831,13 @@ static bool __init rdt_cpu_has(int flag)static __init bool rdt_mba_config (void ) {if (rdt_cpu_has (X86_FEATURE_MBA )) { -if (rdt_get_mem_config (&rdt_resources_all[RDT_RESOURCE_MBA ])) -return true; +if (boot_cpu_data.x86_vendor ==X86_VENDOR_INTEL ) { +if (rdt_get_mem_config (&rdt_resources_all[RDT_RESOURCE_MBA ])) +return true; + }else if (boot_cpu_data.x86_vendor ==X86_VENDOR_AMD ) { +if (rdt_get_mem_config_amd (&rdt_resources_all[RDT_RESOURCE_MBA ])) +return true; + } }return false;
@@ -894,10 +937,32 @@ static __init void rdt_init_res_defs_intel(void) } } +static __init void rdt_init_res_defs_amd (void ) +{ +struct rdt_resource *r; + +for_each_rdt_resource (r) { +if (r->rid ==RDT_RESOURCE_L3 || + r->rid ==RDT_RESOURCE_L3DATA || + r->rid ==RDT_RESOURCE_L3CODE || + r->rid ==RDT_RESOURCE_L2 || + r->rid ==RDT_RESOURCE_L2DATA || + r->rid ==RDT_RESOURCE_L2CODE ) + r->cbm_validate = cbm_validate_amd; +else if (r->rid ==RDT_RESOURCE_MBA ) { + r->msr_base =IA32_MBA_BW_BASE ; + r->msr_update = mba_wrmsr_amd; + r->parse_ctrlval = parse_bw_amd; + } + } +} +static __init void rdt_init_res_defs (void ) {if (boot_cpu_data.x86_vendor ==X86_VENDOR_INTEL )rdt_init_res_defs_intel (); +else if (boot_cpu_data.x86_vendor ==X86_VENDOR_AMD ) +rdt_init_res_defs_amd (); }static enum cpuhp_state rdt_online;
arch/x86/kernel/cpu/resctrl.h +5 -0
@@ -11,6 +11,7 @@#define IA32_L3_CBM_BASE 0xc90#define IA32_L2_CBM_BASE 0xd10#define IA32_MBA_THRTL_BASE 0xd50 +#define IA32_MBA_BW_BASE 0xc0000200#define IA32_QM_CTR 0x0c8e#define IA32_QM_EVTSEL 0x0c8d
@@ -34,6 +35,7 @@#define MAX_MBA_BW 100u#define MBA_IS_LINEAR 0x4#define MBA_MAX_MBPS U32_MAX +#define MAX_MBA_BW_AMD 0x800#define RMID_VAL_ERROR BIT_ULL(63)#define RMID_VAL_UNAVAIL BIT_ULL(62)
@@ -448,6 +450,8 @@ int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r, struct rdt_domain *d);int parse_bw_intel (struct rdt_parse_data *data,struct rdt_resource *r,struct rdt_domain *d); +int parse_bw_amd (struct rdt_parse_data *data,struct rdt_resource *r, +struct rdt_domain *d);extern struct mutex rdtgroup_mutex;
@@ -579,5 +583,6 @@ void cqm_handle_limbo(struct work_struct *work);bool has_busy_rmid (struct rdt_resource *r,struct rdt_domain *d);void __check_limbo (struct rdt_domain *d,bool force_free);bool cbm_validate_intel (char *buf,u32 *data,struct rdt_resource *r); +bool cbm_validate_amd (char *buf,u32 *data,struct rdt_resource *r);#endif /* _ASM_X86_RESCTRL_H */
arch/x86/kernel/cpu/resctrl_ctrlmondata.c +70 -0
82 lines not on this page · raw message
Signature · 1 line
2.17.1
RE: [PATCH v7 11/13] arch/x86: Introduce QOS feature for AMD
arch/x86/kernel/cpu/resctrl_ctrlmondata.c bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r) · line 190
Quoted 10 lines
From: Moger, Babu [mailto:[email protected]]
Subject: [PATCH v7 11/13]arch/x86: Introduce QOS feature for AMD The specification for this feature is available at
https://developer.amd.com/wp-content/resources/56375.pdfarch/x86/kernel/cpu/resctrl_ctrlmondata.c +5
-0+bool cbm_validate_amd (char *buf,u32 *data,struct rdt_resource *r) { +if (val > r->default_ctrl) { +rdt_last_cmd_puts ("mask out of range\n" ); +return false; + }
If val is zero, then this closid cannot allocate any cache line.
I'm wondering: does that mean the tasks running with this closid directly access memory without cache? Is there any usage for this situation?
Thanks.
-Fenghua
RE: [PATCH v7 11/13] arch/x86: Introduce QOS feature for AMD
Fenghua,
Quoted 35 lines
-----Original Message-----
From: [email protected] <linux-kernel- [email protected]> On Behalf Of Yu, Fenghua
Sent: Tuesday, November 13, 2018 3:50 PM
To: Moger, Babu <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; Chatre, Reinette <[email protected]>; [email protected]; [email protected]; [email protected]; akpm@linux- foundation.org
Cc: [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Luck, Tony <[email protected]>; [email protected]; Shen, Xiaochen <[email protected]>; [email protected]; Singh, Brijesh <[email protected]>; Hurwitz, Sherry <[email protected]>; [email protected]; Lendacky, Thomas <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; linux- [email protected]; [email protected]; Yu, Fenghua <[email protected]>
Subject: RE: [PATCH v7 11/13]arch/x86: Introduce QOS feature for AMDarch/x86/kernel/cpu/resctrl_ctrlmondata.c bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r) · line 190
Quoted 10 lines
From: Moger, Babu [mailto:[email protected]]
Subject: [PATCH v7 11/13]arch/x86: Introduce QOS feature for AMD The specification for this feature is available at
https://developer.amd.com/wp-content/resources/56375.pdfarch/x86/kernel/cpu/resctrl_ctrlmondata.c +5
-0+bool cbm_validate_amd (char *buf,u32 *data,struct rdt_resource *r) { +if (val > r->default_ctrl) { +rdt_last_cmd_puts ("mask out of range\n" ); +return false; + }If val is zero, then this closid cannot allocate any cache line.
Quoted 2 lines
I'm wondering: does that mean the tasks running with this closid directly access memory without cache? Is there any usage for this situation?
I would think any memory access has to happen via cache only. But I am not sure about the usage of this situation. Will check on that. Will post if I get any more information. But I can say that it is allowed to have mask as zero. Looking at the specs
https://developer.amd.com/wp-content/resources/56375.pdf
The bits which are set in the various L3_MASK_n registers do not have to be contiguous and may overlap in any desired combination. If an L3_MASK_n register is programmed with all 0's, that COS will be prevented from allocating any lines in the L3 cache. At reset, all L3_MASK_n registers are initialized to all 1's, allowing all processors to use the entire L3 cache accessible to them.
Quoted 4 lines
Thanks.
-Fenghua
Re: [PATCH v7 11/13] arch/x86: Introduce QOS feature for AMD
Quoted 39 lines · Babu
Fenghua,
Quoted 37 lines
-----Original Message-----
From: [email protected] <linux-kernel- [email protected]> On Behalf Of Yu, Fenghua
Sent: Tuesday, November 13, 2018 3:50 PM
To: Moger, Babu <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; Chatre, Reinette <[email protected]>; [email protected]; [email protected]; [email protected]; akpm@linux- foundation.org
Cc: [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; Luck, Tony <[email protected]>; [email protected]; Shen, Xiaochen <[email protected]>; [email protected]; Singh, Brijesh <[email protected]>; Hurwitz, Sherry <[email protected]>; [email protected]; Lendacky, Thomas <[email protected]>; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; linux- [email protected]; [email protected]; Yu, Fenghua <[email protected]>
Subject: RE: [PATCH v7 11/13]arch/x86: Introduce QOS feature for AMDarch/x86/kernel/cpu/resctrl_ctrlmondata.c bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r) · line 190
Quoted 10 lines
From: Moger, Babu [mailto:[email protected]]
Subject: [PATCH v7 11/13]arch/x86: Introduce QOS feature for AMD The specification for this feature is available at
https://developer.amd.com/wp-content/resources/56375.pdfarch/x86/kernel/cpu/resctrl_ctrlmondata.c +5
-0+bool cbm_validate_amd (char *buf,u32 *data,struct rdt_resource *r) { +if (val > r->default_ctrl) { +rdt_last_cmd_puts ("mask out of range\n" ); +return false; + }If val is zero, then this closid cannot allocate any cache line.
I'm wondering: does that mean the tasks running with this closid directly access memory without cache? Is there any usage for this situation?
Here is the detailed answer to your question from Doug(in CC).
A closid with L3_MASK of all 0's will not use any of the L3 cache, but will still be able to use L2 cache. So, no, the processes in that closid will not "directly access memory" in the sense that they will use the L1 and L2 caches as normal. But if they miss the L2 then, yes, the access will go directly to memory. To be precise, none of the lines which are fetched by a process running with such a configuration will be installed in the L3 cache, so subsequent accesses which miss the L2 cache will not find the requested data in the L3 cache and will then go on to access memory.
- Doug
Quoted 17 lines
I would think any memory access has to happen via cache only. But I am not sure about the usage of this situation. Will check on that. Will post if I get any more information. But I can say that it is allowed to have mask as zero. Looking at the specs
https://developer.amd.com/wp-content/resources/56375.pdfThe bits which are set in the various
L3_MASK_nregisters do not have to be contiguous and may overlap in any desired combination. If anL3_MASK_nregister is programmed with all 0's, that COS will be prevented from allocating any lines in the L3 cache. At reset, allL3_MASK_nregisters are initialized to all 1's, allowing all processors to use the entire L3 cache accessible to them.Quoted 4 lines
Thanks.
-Fenghua
RE: [PATCH v7 11/13] arch/x86: Introduce QOS feature for AMD
Quoted 7 lines
From: Moger, Babu [mailto:[email protected]]
Quoted 2 lines
Quoted 2 lines
I'm wondering: does that mean the tasks running with this closid directly access memory without cache? Is there any usage for this
situation?
Here is the detailed answer to your question from Doug(in CC).
Quoted 8 lines
A closid with
L3_MASKof all 0's will not use any of the L3 cache, but will still be able to use L2 cache. So, no, the processes in that closid will not "directly access memory" in the sense that they will use the L1 and L2 caches as normal. But if they miss the L2 then, yes, the access will go directly to memory. To be precise, none of the lines which are fetched by a process running with such a configuration will be installed in the L3 cache, so subsequent accesses which miss the L2 cache will not find the requested data in the L3 cache and will then go on to access memory.
Seems all zeros CBM reduces the caches to L1 and L2. This might be useful in fast access to small data fitting in L2.
Thank you very much for your explanation!
-Fenghua
PATCH v7 12/13 Documentation/x86: Rename and update intel_rdt_ui.txt
In reply to Moger, BabuRename intel_rdt_ui.txt to generic resctrl_ui.txt and update the documentation for AMD.
---
Documentation/x86/{intel_rdt_ui.txt => resctrl_ui.txt} | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
rename Documentation/x86/{intel_rdt_ui.txt => resctrl_ui.txt} (99%)Documentation/x86/resctrl_ui.txt renamed from Documentation/x86/intel_rdt_ui.txt +6 -3
@@ -1,4 +1,7 @@ -User Interface for Resource Allocation in Intel Resource Director Technology +User Interface for Resource Control feature + +Intel refers to this feature as Intel Resource Director Technology(Intel(R) RDT). +AMD refers to this feature as AMD Platform Quality of Service(AMD QoS). Copyright (C) 2016 Intel Corporation
@@ -6,8 +9,8 @@ Fenghua Yu <[email protected]> Tony Luck <[email protected]> Vikas Shivappa <[email protected]> -This feature is enabled by the CONFIG_INTEL_RDT Kconfig and the -X86 /proc/cpuinfo flag bits: +This feature is enabled by the CONFIG_RESCTRL and the X86 /proc/cpuinfo +flag bits: RDT (Resource Director Technology) Allocation - "rdt_a" CAT (Cache Allocation Technology) - "cat_l3", "cat_l2" CDP (Code and Data Prioritization ) - "cdp_l3", "cdp_l2"
Signature · 1 line
2.17.1
PATCH v7 13/13 MAINTAINERS: Update the file and documentation names in arch/x86
In reply to Moger, BabuUpdate the MAINTAINERS to reflect the changed file(and documentation) names in arch/x86/kernel/cpu. The file names have changed from intel_rdt* to resctrl*.
--- MAINTAINERS | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
MAINTAINERS +3 -3
@@ -12267,9 +12267,9 @@ M: Fenghua Yu <[email protected]> M: Reinette Chatre <[email protected]> L: [email protected] S: Supported -F: arch/x86/kernel/cpu/intel_rdt* -F: arch/x86/include/asm/intel_rdt_sched.h -F: Documentation/x86/intel_rdt* +F: arch/x86/kernel/cpu/resctrl* +F: arch/x86/include/asm/resctrl_sched.h +F: Documentation/x86/resctrl* READ-COPY UPDATE (RCU) M: "Paul E. McKenney" <[email protected]>
Signature · 1 line
2.17.1
Hi!
Quoted 1 line
rename Documentation/x86/{intel_rdt_ui.txt => resctrl_ui.txt} (99%)Rest of files in that directory use - as a separator; and maybe qos.txt would be a better name then this?
Thanks,
Pavel
Signature · 2 lines
(english) http://www.livejournal.com/~pavelmachek (cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html
Quoted 5 lines
From: Pavel Machek [mailto:[email protected]]
Quoted 1 line
rename Documentation/x86/{intel_rdt_ui.txt => resctrl_ui.txt} (99%)Rest of files in that directory use - as a separator; and maybe qos.txt would be a better name then this?
Actually a few other files in the directory use "_" as a separator (e.g. intel_mpx.txt etc). "qos.txt" is not a good name because we want to use a generic file name. So "resctrl_ui.txt" should a good name AFAIK.
Thanks.
-Fenghua
Quoted 8 lines · Fenghua
Quoted 5 lines
From: Pavel Machek [mailto:[email protected]]
Quoted 1 line
rename Documentation/x86/{intel_rdt_ui.txt => resctrl_ui.txt} (99%)Rest of files in that directory use - as a separator; and maybe qos.txt would be a better name then this?
Actually a few other files in the directory use "_" as a separator (e.g. intel_mpx.txt etc). "qos.txt" is not a good name because we want to use a generic file name. So "resctrl_ui.txt" should a good name AFAIK.
Please do something with your email client. This is very confusing.
To be consistent with other names in the directory, name should be resctl-ui.txt at the very least.
Plus the "ui" part is redundant, and false. This is kernel-userspace interface. Not user interface. So resctl.txt would be a better name.
Pavel
Signature · 2 lines
(english) http://www.livejournal.com/~pavelmachek (cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html