[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <TYAPR01MB6330514612396E190106A8CF8B50A@TYAPR01MB6330.jpnprd01.prod.outlook.com>
Date: Thu, 8 Jun 2023 07:52:43 +0000
From: "Shaopeng Tan (Fujitsu)" <tan.shaopeng@...itsu.com>
To: 'James Morse' <james.morse@....com>,
"x86@...nel.org" <x86@...nel.org>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
CC: Fenghua Yu <fenghua.yu@...el.com>,
Reinette Chatre <reinette.chatre@...el.com>,
Thomas Gleixner <tglx@...utronix.de>,
Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
H Peter Anvin <hpa@...or.com>,
Babu Moger <Babu.Moger@....com>,
"shameerali.kolothum.thodi@...wei.com"
<shameerali.kolothum.thodi@...wei.com>,
D Scott Phillips OS <scott@...amperecomputing.com>,
"carl@...amperecomputing.com" <carl@...amperecomputing.com>,
"lcherian@...vell.com" <lcherian@...vell.com>,
"bobo.shaobowang@...wei.com" <bobo.shaobowang@...wei.com>,
"xingxin.hx@...nanolis.org" <xingxin.hx@...nanolis.org>,
"baolin.wang@...ux.alibaba.com" <baolin.wang@...ux.alibaba.com>,
Jamie Iles <quic_jiles@...cinc.com>,
Xin Hao <xhao@...ux.alibaba.com>,
"peternewman@...gle.com" <peternewman@...gle.com>,
"dfustini@...libre.com" <dfustini@...libre.com>
Subject: RE: [PATCH v4 02/24] x86/resctrl: Access per-rmid structures by index
Hello James,
> Because of the differences between Intel RDT/AMD QoS and Arm's MPAM
> monitors, RMID values on arm64 are not unique unless the CLOSID is also
> included. Bitmaps like rmid_busy_llc need to be sized by the number of unique
> entries for this resource.
>
> Add helpers to encode/decode the CLOSID and RMID to an index. The
> domain's rmid_busy_llc and rmid_ptrs[] are then sized by index, as are the
> domain mbm_local and mbm_total arrays.
> On x86, the index is always just the RMID, so all these structures remain the
> same size.
>
> The index gives resctrl a unique value it can use to store monitor values, and
> allows MPAM to decode the CLOSID when reading the hardware counters.
>
> Tested-by: Shaopeng Tan <tan.shaopeng@...itsu.com>
> Signed-off-by: James Morse <james.morse@....com>
> ---
> Changes since v1:
> * Added X86_BAD_CLOSID macro to make it clear what this value means
> * Added second WARN_ON() for closid checking, and made both _ONCE()
>
> Changes since v2:
> * Added RESCTRL_RESERVED_CLOSID
> * Removed a newline
> * Repharsed some comments
> * Renamed a variable 'ignore'd
> * Moved X86_RESCTRL_BAD_CLOSID to a previous patch
>
> Changes since v3:
> * Changed a variable name
> * Fixed various typos
> ---
> arch/x86/include/asm/resctrl.h | 17 ++++++
> arch/x86/kernel/cpu/resctrl/core.c | 2 +-
> arch/x86/kernel/cpu/resctrl/internal.h | 1 +
> arch/x86/kernel/cpu/resctrl/monitor.c | 84
> +++++++++++++++++---------
> arch/x86/kernel/cpu/resctrl/rdtgroup.c | 7 ++-
> include/linux/resctrl.h | 3 +
> 6 files changed, 83 insertions(+), 31 deletions(-)
>
> diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h
> index e906070285fb..dd9b638d43c8 100644
> --- a/arch/x86/include/asm/resctrl.h
> +++ b/arch/x86/include/asm/resctrl.h
> @@ -101,6 +101,23 @@ static inline void resctrl_sched_in(struct task_struct
> *tsk)
> __resctrl_sched_in(tsk);
> }
>
> +static inline u32 resctrl_arch_system_num_rmid_idx(void)
> +{
> + /* RMID are independent numbers for x86. num_rmid_idx ==
> num_rmid */
> + return boot_cpu_data.x86_cache_max_rmid + 1; }
> +
> +static inline void resctrl_arch_rmid_idx_decode(u32 idx, u32 *closid,
> +u32 *rmid) {
> + *rmid = idx;
> + *closid = X86_RESCTRL_BAD_CLOSID;
> +}
> +
> +static inline u32 resctrl_arch_rmid_idx_encode(u32 ignored, u32 rmid) {
> + return rmid;
> +}
> +
> void resctrl_cpu_detect(struct cpuinfo_x86 *c);
>
> #else
> diff --git a/arch/x86/kernel/cpu/resctrl/core.c
> b/arch/x86/kernel/cpu/resctrl/core.c
> index 030d3b409768..4bea032d072e 100644
> --- a/arch/x86/kernel/cpu/resctrl/core.c
> +++ b/arch/x86/kernel/cpu/resctrl/core.c
> @@ -600,7 +600,7 @@ static void clear_closid_rmid(int cpu)
> state->default_rmid = 0;
> state->cur_closid = 0;
> state->cur_rmid = 0;
> - wrmsr(MSR_IA32_PQR_ASSOC, 0, 0);
> + wrmsr(MSR_IA32_PQR_ASSOC, 0, RESCTRL_RESERVED_CLOSID);
> }
>
> static int resctrl_online_cpu(unsigned int cpu) diff --git
> a/arch/x86/kernel/cpu/resctrl/internal.h
> b/arch/x86/kernel/cpu/resctrl/internal.h
> index f2da908bb079..d571da4848a4 100644
> --- a/arch/x86/kernel/cpu/resctrl/internal.h
> +++ b/arch/x86/kernel/cpu/resctrl/internal.h
> @@ -7,6 +7,7 @@
> #include <linux/kernfs.h>
> #include <linux/fs_context.h>
> #include <linux/jump_label.h>
> +#include <asm/resctrl.h>
>
> #define L3_QOS_CDP_ENABLE 0x01ULL
>
> diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c
> b/arch/x86/kernel/cpu/resctrl/monitor.c
> index 86574adedd64..bcc25f5339c0 100644
> --- a/arch/x86/kernel/cpu/resctrl/monitor.c
> +++ b/arch/x86/kernel/cpu/resctrl/monitor.c
> @@ -142,12 +142,29 @@ static inline u64 get_corrected_mbm_count(u32 rmid,
> unsigned long val)
> return val;
> }
>
> -static inline struct rmid_entry *__rmid_entry(u32 closid, u32 rmid)
> +/*
> + * x86 and arm64 differ in their handling of monitoring.
> + * x86's RMID are an independent number, there is only one source of
> +traffic
> + * with an RMID value of '1'.
> + * arm64's PMG extend the PARTID/CLOSID space, there are multiple
> +sources of
> + * traffic with a PMG value of '1', one for each CLOSID, meaning the
> +RMID
> + * value is no longer unique.
> + * To account for this, resctrl uses an index. On x86 this is just the
> +RMID,
> + * on arm64 it encodes the CLOSID and RMID. This gives a unique number.
> + *
> + * The domain's rmid_busy_llc and rmid_ptrs are sized by index. The
> +arch code
> + * must accept an attempt to read every index.
> + */
> +static inline struct rmid_entry *__rmid_entry(u32 idx)
> {
> struct rmid_entry *entry;
> + u32 closid, rmid;
>
> - entry = &rmid_ptrs[rmid];
> - WARN_ON(entry->rmid != rmid);
> + entry = &rmid_ptrs[idx];
> + resctrl_arch_rmid_idx_decode(idx, &closid, &rmid);
> +
> + WARN_ON_ONCE(entry->closid != closid);
> + WARN_ON_ONCE(entry->rmid != rmid);
>
> return entry;
> }
> @@ -277,8 +294,9 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct
> rdt_domain *d, void __check_limbo(struct rdt_domain *d, bool force_free) {
> struct rdt_resource *r =
> &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
> + u32 idx_limit = resctrl_arch_system_num_rmid_idx();
> struct rmid_entry *entry;
> - u32 crmid = 1, nrmid;
> + u32 idx, cur_idx = 1;
> bool rmid_dirty;
> u64 val = 0;
>
> @@ -289,12 +307,11 @@ void __check_limbo(struct rdt_domain *d, bool
> force_free)
> * RMID and move it to the free list when the counter reaches 0.
> */
> for (;;) {
> - nrmid = find_next_bit(d->rmid_busy_llc, r->num_rmid,
> crmid);
> - if (nrmid >= r->num_rmid)
> + idx = find_next_bit(d->rmid_busy_llc, idx_limit, cur_idx);
> + if (idx >= idx_limit)
> break;
>
> - entry = __rmid_entry(X86_RESCTRL_BAD_CLOSID, nrmid);//
> temporary
> -
> + entry = __rmid_entry(idx);
> if (resctrl_arch_rmid_read(r, d, entry->closid, entry->rmid,
> QOS_L3_OCCUP_EVENT_ID,
> &val)) {
> rmid_dirty = true;
> @@ -303,19 +320,21 @@ void __check_limbo(struct rdt_domain *d, bool
> force_free)
> }
>
> if (force_free || !rmid_dirty) {
> - clear_bit(entry->rmid, d->rmid_busy_llc);
> + clear_bit(idx, d->rmid_busy_llc);
> if (!--entry->busy) {
> rmid_limbo_count--;
> list_add_tail(&entry->list, &rmid_free_lru);
> }
> }
> - crmid = nrmid + 1;
> + cur_idx = idx + 1;
> }
> }
>
> bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d) {
> - return find_first_bit(d->rmid_busy_llc, r->num_rmid) !=
> r->num_rmid;
> + u32 idx_limit = resctrl_arch_system_num_rmid_idx();
> +
> + return find_first_bit(d->rmid_busy_llc, idx_limit) != idx_limit;
> }
"struct rdt_resource *r" is not used in this function.
Best regards,
Shaopeng TAN
Powered by blists - more mailing lists