All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Moger, Babu" <babu.moger@amd.com>
To: James Morse <james.morse@arm.com>,
	x86@kernel.org, linux-kernel@vger.kernel.org
Cc: Fenghua Yu <fenghua.yu@intel.com>,
	Reinette Chatre <reinette.chatre@intel.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
	H Peter Anvin <hpa@zytor.com>,
	shameerali.kolothum.thodi@huawei.com,
	D Scott Phillips OS <scott@os.amperecomputing.com>,
	carl@os.amperecomputing.com, lcherian@marvell.com,
	bobo.shaobowang@huawei.com, tan.shaopeng@fujitsu.com,
	baolin.wang@linux.alibaba.com,
	Jamie Iles <quic_jiles@quicinc.com>,
	Xin Hao <xhao@linux.alibaba.com>,
	peternewman@google.com, dfustini@baylibre.com,
	amitsinght@marvell.com
Subject: Re: [PATCH v7 15/24] x86/resctrl: Allow arch to allocate memory needed in resctrl_arch_rmid_read()
Date: Thu, 9 Nov 2023 14:47:37 -0600	[thread overview]
Message-ID: <876af164-c326-4b26-ab56-790f9a36902e@amd.com> (raw)
In-Reply-To: <20231025180345.28061-16-james.morse@arm.com>

Hi James,

On 10/25/23 13:03, James Morse wrote:
> Depending on the number of monitors available, Arm's MPAM may need to
> allocate a monitor prior to reading the counter value. Allocating a
> contended resource may involve sleeping.
> 
> add_rmid_to_limbo() calls resctrl_arch_rmid_read() for multiple domains,
> the allocation should be valid for all domains.

This above sentence does not look correct after your previous patch [patch
14].  You removed  resctrl_arch_rmid_read() from add_rmid_to_limbo().

Otherwise looks good.

> 
> __check_limbo() and mon_event_count() each make multiple calls to
> resctrl_arch_rmid_read(), to avoid extra work on contended systems,
> the allocation should be valid for multiple invocations of
> resctrl_arch_rmid_read().
> 
> Add arch hooks for this allocation, which need calling before
> resctrl_arch_rmid_read(). The allocated monitor is passed to
> resctrl_arch_rmid_read(), then freed again afterwards. The helper
> can be called on any CPU, and can sleep.
> 
> Tested-by: Shaopeng Tan <tan.shaopeng@fujitsu.com>
> Tested-by: Peter Newman <peternewman@google.com>
> Reviewed-by: Shaopeng Tan <tan.shaopeng@fujitsu.com>
> Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
> Signed-off-by: James Morse <james.morse@arm.com>

Reviewed-by: Babu Moger <babu.moger@amd.com>

> ---
> Changes since v3:
>  * Expanded comment.
>  * Removed stray header include.
>  * Reworded commit message.
>  * Made ctx a void * instead of an int.
> 
> Changes since v4:
>  * Used IS_ERR() in more places.
> 
> Changes since v5:
>  * Pass the error back from mon_event_read() as -EINVAL/Unavailable.
>  * Add some ratelimited warnings when failing to allocate a mon context
> 
> Changes since v6:
>  * Added a newline.
> ---
>  arch/x86/include/asm/resctrl.h            | 11 +++++++
>  arch/x86/kernel/cpu/resctrl/ctrlmondata.c |  7 +++++
>  arch/x86/kernel/cpu/resctrl/internal.h    |  1 +
>  arch/x86/kernel/cpu/resctrl/monitor.c     | 35 +++++++++++++++++++++--
>  include/linux/resctrl.h                   |  5 +++-
>  5 files changed, 55 insertions(+), 4 deletions(-)
> 
> diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h
> index 1d274dbabc44..29c4cc343787 100644
> --- a/arch/x86/include/asm/resctrl.h
> +++ b/arch/x86/include/asm/resctrl.h
> @@ -136,6 +136,17 @@ static inline u32 resctrl_arch_rmid_idx_encode(u32 ignored, u32 rmid)
>  	return rmid;
>  }
>  
> +/* x86 can always read an rmid, nothing needs allocating */
> +struct rdt_resource;
> +static inline void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r, int evtid)
> +{
> +	might_sleep();
> +	return NULL;
> +};
> +
> +static inline void resctrl_arch_mon_ctx_free(struct rdt_resource *r, int evtid,
> +					     void *ctx) { };
> +
>  void resctrl_cpu_detect(struct cpuinfo_x86 *c);
>  
>  #else
> diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
> index d07f99245851..a033e8e32108 100644
> --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
> +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
> @@ -546,6 +546,11 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
>  	rr->d = d;
>  	rr->val = 0;
>  	rr->first = first;
> +	rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evtid);
> +	if (IS_ERR(rr->arch_mon_ctx)) {
> +		rr->err = -EINVAL;
> +		return;
> +	}
>  
>  	cpu = cpumask_any_housekeeping(&d->cpu_mask);
>  
> @@ -559,6 +564,8 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
>  		smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1);
>  	else
>  		smp_call_on_cpu(cpu, smp_mon_event_count, rr, false);
> +
> +	resctrl_arch_mon_ctx_free(r, evtid, rr->arch_mon_ctx);
>  }
>  
>  int rdtgroup_mondata_show(struct seq_file *m, void *arg)
> diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
> index 33e24fcc8dd0..bb07b9b01e36 100644
> --- a/arch/x86/kernel/cpu/resctrl/internal.h
> +++ b/arch/x86/kernel/cpu/resctrl/internal.h
> @@ -138,6 +138,7 @@ struct rmid_read {
>  	bool			first;
>  	int			err;
>  	u64			val;
> +	void			*arch_mon_ctx;
>  };
>  
>  extern bool rdt_alloc_capable;
> diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
> index 409817b0ae2c..1ca8db8c82cc 100644
> --- a/arch/x86/kernel/cpu/resctrl/monitor.c
> +++ b/arch/x86/kernel/cpu/resctrl/monitor.c
> @@ -269,7 +269,7 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width)
>  
>  int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
>  			   u32 unused, u32 rmid, enum resctrl_event_id eventid,
> -			   u64 *val)
> +			   u64 *val, void *ignored)
>  {
>  	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r);
>  	struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d);
> @@ -324,9 +324,17 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
>  	u32 idx_limit = resctrl_arch_system_num_rmid_idx();
>  	struct rmid_entry *entry;
>  	u32 idx, cur_idx = 1;
> +	void *arch_mon_ctx;
>  	bool rmid_dirty;
>  	u64 val = 0;
>  
> +	arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, QOS_L3_OCCUP_EVENT_ID);
> +	if (IS_ERR(arch_mon_ctx)) {
> +		pr_warn_ratelimited("Failed to allocate monitor context: %ld",
> +				    PTR_ERR(arch_mon_ctx));
> +		return;
> +	}
> +
>  	/*
>  	 * Skip RMID 0 and start from RMID 1 and check all the RMIDs that
>  	 * are marked as busy for occupancy < threshold. If the occupancy
> @@ -340,7 +348,8 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
>  
>  		entry = __rmid_entry(idx);
>  		if (resctrl_arch_rmid_read(r, d, entry->closid, entry->rmid,
> -					   QOS_L3_OCCUP_EVENT_ID, &val)) {
> +					   QOS_L3_OCCUP_EVENT_ID, &val,
> +					   arch_mon_ctx)) {
>  			rmid_dirty = true;
>  		} else {
>  			rmid_dirty = (val >= resctrl_rmid_realloc_threshold);
> @@ -353,6 +362,8 @@ void __check_limbo(struct rdt_domain *d, bool force_free)
>  		}
>  		cur_idx = idx + 1;
>  	}
> +
> +	resctrl_arch_mon_ctx_free(r, QOS_L3_OCCUP_EVENT_ID, arch_mon_ctx);
>  }
>  
>  bool has_busy_rmid(struct rdt_domain *d)
> @@ -533,7 +544,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
>  	}
>  
>  	rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid, rr->evtid,
> -					 &tval);
> +					 &tval, rr->arch_mon_ctx);
>  	if (rr->err)
>  		return rr->err;
>  
> @@ -744,11 +755,27 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d,
>  	if (is_mbm_total_enabled()) {
>  		rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID;
>  		rr.val = 0;
> +		rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
> +		if (IS_ERR(rr.arch_mon_ctx)) {
> +			pr_warn_ratelimited("Failed to allocate monitor context: %ld",
> +					    PTR_ERR(rr.arch_mon_ctx));
> +			return;
> +		}
> +
>  		__mon_event_count(closid, rmid, &rr);
> +
> +		resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
>  	}
>  	if (is_mbm_local_enabled()) {
>  		rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID;
>  		rr.val = 0;
> +		rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
> +		if (IS_ERR(rr.arch_mon_ctx)) {
> +			pr_warn_ratelimited("Failed to allocate monitor context: %ld",
> +					    PTR_ERR(rr.arch_mon_ctx));
> +			return;
> +		}
> +
>  		__mon_event_count(closid, rmid, &rr);
>  
>  		/*
> @@ -758,6 +785,8 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d,
>  		 */
>  		if (is_mba_sc(NULL))
>  			mbm_bw_count(closid, rmid, &rr);
> +
> +		resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
>  	}
>  }
>  
> diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
> index 8649fc84aac2..bf460c912bf5 100644
> --- a/include/linux/resctrl.h
> +++ b/include/linux/resctrl.h
> @@ -235,6 +235,9 @@ void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d);
>   * @rmid:		rmid of the counter to read.
>   * @eventid:		eventid to read, e.g. L3 occupancy.
>   * @val:		result of the counter read in bytes.
> + * @arch_mon_ctx:	An architecture specific value from
> + *			resctrl_arch_mon_ctx_alloc(), for MPAM this identifies
> + *			the hardware monitor allocated for this read request.
>   *
>   * Some architectures need to sleep when first programming some of the counters.
>   * (specifically: arm64's MPAM cache occupancy counters can return 'not ready'
> @@ -248,7 +251,7 @@ void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d);
>   */
>  int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d,
>  			   u32 closid, u32 rmid, enum resctrl_event_id eventid,
> -			   u64 *val);
> +			   u64 *val, void *arch_mon_ctx);
>  
>  /**
>   * resctrl_arch_rmid_read_context_check()  - warn about invalid contexts

-- 
Thanks
Babu Moger

  reply	other threads:[~2023-11-09 20:47 UTC|newest]

Thread overview: 103+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-10-25 18:03 [PATCH v7 00/24] x86/resctrl: monitored closid+rmid together, separate arch/fs locking James Morse
2023-10-25 18:03 ` [PATCH v7 01/24] tick/nohz: Move tick_nohz_full_mask declaration outside the #ifdef James Morse
2023-10-25 18:03 ` [PATCH v7 02/24] x86/resctrl: kfree() rmid_ptrs from rdtgroup_exit() James Morse
2023-11-09 17:39   ` Reinette Chatre
2023-12-13 18:03     ` James Morse
2023-12-13 23:27       ` Reinette Chatre
2023-12-14 18:28         ` James Morse
2023-12-14 19:06           ` Reinette Chatre
2023-12-15 17:40             ` James Morse
2023-11-09 20:28   ` Moger, Babu
2023-12-13 18:03     ` James Morse
2023-10-25 18:03 ` [PATCH v7 03/24] x86/resctrl: Create helper for RMID allocation and mondata dir creation James Morse
2023-11-09 17:40   ` Reinette Chatre
2023-11-09 20:28   ` Moger, Babu
2023-12-13 18:03     ` James Morse
2023-10-25 18:03 ` [PATCH v7 04/24] x86/resctrl: Move rmid allocation out of mkdir_rdt_prepare() James Morse
2023-11-09 20:29   ` Moger, Babu
2023-12-13 18:03     ` James Morse
2023-10-25 18:03 ` [PATCH v7 05/24] x86/resctrl: Track the closid with the rmid James Morse
2023-11-09 17:41   ` Reinette Chatre
2023-12-13 18:03     ` James Morse
2023-11-09 20:31   ` Moger, Babu
2023-12-13 18:04     ` James Morse
2023-10-25 18:03 ` [PATCH v7 06/24] x86/resctrl: Access per-rmid structures by index James Morse
2023-10-31  7:43   ` [EXT] " Amit Singh Tomar
2023-12-11 14:33     ` James Morse
2024-01-21 10:27       ` Amit Singh Tomar
2024-01-22 18:07         ` James Morse
2023-11-09 17:42   ` Reinette Chatre
2023-12-13 18:04     ` James Morse
2023-11-09 20:32   ` Moger, Babu
2023-10-25 18:03 ` [PATCH v7 07/24] x86/resctrl: Allow RMID allocation to be scoped by CLOSID James Morse
2023-11-09 17:42   ` Reinette Chatre
2023-11-09 20:32   ` Moger, Babu
2023-10-25 18:03 ` [PATCH v7 08/24] x86/resctrl: Track the number of dirty RMID a CLOSID has James Morse
2023-11-09 17:43   ` Reinette Chatre
2023-12-13 18:04     ` James Morse
2023-11-09 20:38   ` Moger, Babu
2023-12-13 18:04     ` James Morse
2023-10-25 18:03 ` [PATCH v7 09/24] x86/resctrl: Use __set_bit()/__clear_bit() instead of open coding James Morse
2023-11-09 17:44   ` Reinette Chatre
2023-12-13 18:05     ` James Morse
2023-11-09 20:38   ` Moger, Babu
2023-12-13 18:05     ` James Morse
2023-10-25 18:03 ` [PATCH v7 10/24] x86/resctrl: Allocate the cleanest CLOSID by searching closid_num_dirty_rmid James Morse
2023-11-09 17:46   ` Reinette Chatre
2023-12-14 11:36     ` James Morse
2023-11-09 20:39   ` Moger, Babu
2023-12-14 11:37     ` James Morse
2023-10-25 18:03 ` [PATCH v7 11/24] x86/resctrl: Move CLOSID/RMID matching and setting to use helpers James Morse
2023-11-09 20:39   ` Moger, Babu
2023-12-14 11:37     ` James Morse
2023-11-09 20:39   ` Moger, Babu
2023-10-25 18:03 ` [PATCH v7 12/24] x86/resctrl: Add cpumask_any_housekeeping() for limbo/overflow James Morse
2023-11-09 17:46   ` Reinette Chatre
2023-11-09 20:40   ` Moger, Babu
2023-10-25 18:03 ` [PATCH v7 13/24] x86/resctrl: Queue mon_event_read() instead of sending an IPI James Morse
2023-11-09 17:46   ` Reinette Chatre
2023-11-09 20:40   ` Moger, Babu
2023-12-14 11:37     ` James Morse
2023-10-25 18:03 ` [PATCH v7 14/24] x86/resctrl: Allow resctrl_arch_rmid_read() to sleep James Morse
2023-11-09 17:47   ` Reinette Chatre
2023-12-14 11:37     ` James Morse
2023-12-14 18:52       ` Reinette Chatre
2023-11-09 20:42   ` Moger, Babu
2023-12-14 11:37     ` James Morse
2023-10-25 18:03 ` [PATCH v7 15/24] x86/resctrl: Allow arch to allocate memory needed in resctrl_arch_rmid_read() James Morse
2023-11-09 20:47   ` Moger, Babu [this message]
2023-12-14 11:38     ` James Morse
2023-10-25 18:03 ` [PATCH v7 16/24] x86/resctrl: Make resctrl_mounted checks explicit James Morse
2023-11-09 20:47   ` Moger, Babu
2023-12-14 11:38     ` James Morse
2023-10-25 18:03 ` [PATCH v7 17/24] x86/resctrl: Move alloc/mon static keys into helpers James Morse
2023-11-09 20:48   ` Moger, Babu
2023-10-25 18:03 ` [PATCH v7 18/24] x86/resctrl: Make rdt_enable_key the arch's decision to switch James Morse
2023-11-09 20:48   ` Moger, Babu
2023-10-25 18:03 ` [PATCH v7 19/24] x86/resctrl: Add helpers for system wide mon/alloc capable James Morse
2023-11-09 20:51   ` Moger, Babu
2023-12-14 11:38     ` James Morse
2023-10-25 18:03 ` [PATCH v7 20/24] x86/resctrl: Add CPU online callback for resctrl work James Morse
2023-11-09 20:51   ` Moger, Babu
2023-12-14 11:38     ` James Morse
2023-10-25 18:03 ` [PATCH v7 21/24] x86/resctrl: Allow overflow/limbo handlers to be scheduled on any-but cpu James Morse
2023-11-09 17:48   ` Reinette Chatre
2023-12-14 11:38     ` James Morse
2023-12-14 18:53       ` Reinette Chatre
2023-12-15 17:41         ` James Morse
2023-11-09 20:51   ` Moger, Babu
2023-12-14 11:38     ` James Morse
2023-10-25 18:03 ` [PATCH v7 22/24] x86/resctrl: Add CPU offline callback for resctrl work James Morse
2023-11-09 20:52   ` Moger, Babu
2023-12-14 11:39     ` James Morse
2023-10-25 18:03 ` [PATCH v7 23/24] x86/resctrl: Move domain helper migration into resctrl_offline_cpu() James Morse
2023-11-09 20:52   ` Moger, Babu
2023-10-25 18:03 ` [PATCH v7 24/24] x86/resctrl: Separate arch and fs resctrl locks James Morse
2023-11-09 17:48   ` Reinette Chatre
2023-12-14 11:39     ` James Morse
2023-11-09 20:52   ` Moger, Babu
2023-12-14 11:39     ` James Morse
2023-11-09 14:05 ` [PATCH v7 00/24] x86/resctrl: monitored closid+rmid together, separate arch/fs locking Moger, Babu
2023-12-14 11:39   ` James Morse
2023-11-13  1:54 ` Shaopeng Tan (Fujitsu)
2023-12-14 18:28   ` James Morse

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=876af164-c326-4b26-ab56-790f9a36902e@amd.com \
    --to=babu.moger@amd.com \
    --cc=amitsinght@marvell.com \
    --cc=baolin.wang@linux.alibaba.com \
    --cc=bobo.shaobowang@huawei.com \
    --cc=bp@alien8.de \
    --cc=carl@os.amperecomputing.com \
    --cc=dfustini@baylibre.com \
    --cc=fenghua.yu@intel.com \
    --cc=hpa@zytor.com \
    --cc=james.morse@arm.com \
    --cc=lcherian@marvell.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=peternewman@google.com \
    --cc=quic_jiles@quicinc.com \
    --cc=reinette.chatre@intel.com \
    --cc=scott@os.amperecomputing.com \
    --cc=shameerali.kolothum.thodi@huawei.com \
    --cc=tan.shaopeng@fujitsu.com \
    --cc=tglx@linutronix.de \
    --cc=x86@kernel.org \
    --cc=xhao@linux.alibaba.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.