All of lore.kernel.org
 help / color / mirror / Atom feed
From: James Morse <james.morse@arm.com>
To: 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>, Babu Moger <Babu.Moger@amd.com>,
	James Morse <james.morse@arm.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, David Hildenbrand <david@redhat.com>,
	Rex Nie <rex.nie@jaguarmicro.com>,
	Dave Martin <dave.martin@arm.com>,
	Dave Martin <Dave.Martin@arm.com>,
	Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Subject: [PATCH v5 09/40] x86/resctrl: Add helper for setting CPU default properties
Date: Fri,  4 Oct 2024 18:03:16 +0000	[thread overview]
Message-ID: <20241004180347.19985-10-james.morse@arm.com> (raw)
In-Reply-To: <20241004180347.19985-1-james.morse@arm.com>

rdtgroup_rmdir_ctrl() and rdtgroup_rmdir_mon() set the per-CPU
pqr_state for CPUs that were part of the rmdir()'d group.

Another architecture might not have a 'pqr_state', its hardware may
need the values in a different format. MPAM's equivalent of RMID values
are not unique, and always need the CLOSID to be provided too.

There is only one caller that modifies a single value,
(rdtgroup_rmdir_mon()). MPAM always needs both CLOSID and RMID
for the hardware value as these are written to the same system
register.

As rdtgroup_rmdir_mon() has the CLOSID on hand, only provide a
helper to set both values. These values are read by
__resctrl_sched_in(), but may be written by a different CPU without
any locking, add READ/WRTE_ONCE() to avoid torn values.

Co-developed-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: James Morse <james.morse@arm.com>
Tested-by: Carl Worth <carl@os.amperecomputing.com> # arm64
Tested-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Reviewed-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
---
Changes since v1:
 * In rdtgroup_rmdir_mon(), (re)set CPU default closid based on the
   parent control group, to avoid the appearance of referencing
   something that we're in the process of destroying (even if it
   doesn't make a difference because the victim mon group necessarily
   has the same closid as the parent control group).

   Update comment to match.

   No (intentional) functional change.
---
 arch/x86/include/asm/resctrl.h         | 14 +++++++++++---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 20 ++++++++++++++------
 2 files changed, 25 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h
index 8b1b6ce1e51b..6908cd0e6e40 100644
--- a/arch/x86/include/asm/resctrl.h
+++ b/arch/x86/include/asm/resctrl.h
@@ -4,8 +4,9 @@
 
 #ifdef CONFIG_X86_CPU_RESCTRL
 
-#include <linux/sched.h>
 #include <linux/jump_label.h>
+#include <linux/percpu.h>
+#include <linux/sched.h>
 
 /*
  * This value can never be a valid CLOSID, and is used when mapping a
@@ -96,8 +97,8 @@ static inline void resctrl_arch_disable_mon(void)
 static inline void __resctrl_sched_in(struct task_struct *tsk)
 {
 	struct resctrl_pqr_state *state = this_cpu_ptr(&pqr_state);
-	u32 closid = state->default_closid;
-	u32 rmid = state->default_rmid;
+	u32 closid = READ_ONCE(state->default_closid);
+	u32 rmid = READ_ONCE(state->default_rmid);
 	u32 tmp;
 
 	/*
@@ -132,6 +133,13 @@ static inline unsigned int resctrl_arch_round_mon_val(unsigned int val)
 	return val * scale;
 }
 
+static inline void resctrl_arch_set_cpu_default_closid_rmid(int cpu, u32 closid,
+							    u32 rmid)
+{
+	WRITE_ONCE(per_cpu(pqr_state.default_closid, cpu), closid);
+	WRITE_ONCE(per_cpu(pqr_state.default_rmid, cpu), rmid);
+}
+
 static inline void resctrl_arch_set_closid_rmid(struct task_struct *tsk,
 						u32 closid, u32 rmid)
 {
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index de2c169a1678..b430f4465cbf 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -3713,14 +3713,21 @@ static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
 static int rdtgroup_rmdir_mon(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
 {
 	struct rdtgroup *prdtgrp = rdtgrp->mon.parent;
+	u32 closid, rmid;
 	int cpu;
 
 	/* Give any tasks back to the parent group */
 	rdt_move_group_tasks(rdtgrp, prdtgrp, tmpmask);
 
-	/* Update per cpu rmid of the moved CPUs first */
+	/*
+	 * Update per cpu closid/rmid of the moved CPUs first.
+	 * Note: the closid will not change, but the arch code still needs it.
+	 */
+	closid = prdtgrp->closid;
+	rmid = prdtgrp->mon.rmid;
 	for_each_cpu(cpu, &rdtgrp->cpu_mask)
-		per_cpu(pqr_state.default_rmid, cpu) = prdtgrp->mon.rmid;
+		resctrl_arch_set_cpu_default_closid_rmid(cpu, closid, rmid);
+
 	/*
 	 * Update the MSR on moved CPUs and CPUs which have moved
 	 * task running on them.
@@ -3753,6 +3760,7 @@ static int rdtgroup_ctrl_remove(struct rdtgroup *rdtgrp)
 
 static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
 {
+	u32 closid, rmid;
 	int cpu;
 
 	/* Give any tasks back to the default group */
@@ -3763,10 +3771,10 @@ static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
 		   &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);
 
 	/* Update per cpu closid and rmid of the moved CPUs first */
-	for_each_cpu(cpu, &rdtgrp->cpu_mask) {
-		per_cpu(pqr_state.default_closid, cpu) = rdtgroup_default.closid;
-		per_cpu(pqr_state.default_rmid, cpu) = rdtgroup_default.mon.rmid;
-	}
+	closid = rdtgroup_default.closid;
+	rmid = rdtgroup_default.mon.rmid;
+	for_each_cpu(cpu, &rdtgrp->cpu_mask)
+		resctrl_arch_set_cpu_default_closid_rmid(cpu, closid, rmid);
 
 	/*
 	 * Update the MSR on moved CPUs and CPUs which have moved
-- 
2.39.2


  parent reply	other threads:[~2024-10-04 18:05 UTC|newest]

Thread overview: 102+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-10-04 18:03 [PATCH v5 00/40] x86/resctrl: Move the resctrl filesystem code to /fs/resctrl James Morse
2024-10-04 18:03 ` [PATCH v5 01/40] x86/resctrl: Fix allocation of cleanest CLOSID on platforms with no monitors James Morse
2024-10-04 18:03 ` [PATCH v5 02/40] x86/resctrl: Add a helper to avoid reaching into the arch code resource list James Morse
2024-10-15 22:57   ` Tony Luck
2024-10-18 17:07     ` James Morse
2024-10-18 17:14       ` Luck, Tony
2024-10-23 21:03   ` Reinette Chatre
2024-10-04 18:03 ` [PATCH v5 03/40] x86/resctrl: Remove fflags from struct rdt_resource James Morse
2024-10-23 21:03   ` Reinette Chatre
2024-12-20 18:10     ` James Morse
2024-10-04 18:03 ` [PATCH v5 04/40] x86/resctrl: Use schema type to determine how to parse schema values James Morse
2024-10-15 23:15   ` Tony Luck
2024-10-18 17:07     ` James Morse
2024-10-23 21:14   ` Reinette Chatre
2024-12-20 18:10     ` James Morse
2024-10-04 18:03 ` [PATCH v5 05/40] x86/resctrl: Use schema type to determine the schema format string James Morse
2024-10-21 17:39   ` Reinette Chatre
2024-10-04 18:03 ` [PATCH v5 06/40] x86/resctrl: Remove data_width and the tabular format James Morse
2024-10-15 23:29   ` Tony Luck
2024-10-18 17:07     ` James Morse
2024-10-04 18:03 ` [PATCH v5 07/40] x86/resctrl: Add max_bw to struct resctrl_membw James Morse
2024-10-09 18:02   ` Tony Luck
2024-10-23 21:14   ` Reinette Chatre
2024-12-20 18:10     ` James Morse
2024-10-04 18:03 ` [PATCH v5 08/40] x86/resctrl: Generate default_ctrl instead of sharing it James Morse
2024-10-23 21:15   ` Reinette Chatre
2025-02-07 15:42     ` James Morse
2024-10-04 18:03 ` James Morse [this message]
2024-10-04 18:03 ` [PATCH v5 10/40] x86/resctrl: Remove rdtgroup from update_cpu_closid_rmid() James Morse
2024-10-04 18:03 ` [PATCH v5 11/40] x86/resctrl: Export resctrl fs's init function James Morse
2024-10-16 16:20   ` Tony Luck
2024-10-04 18:03 ` [PATCH v5 12/40] x86/resctrl: Wrap resctrl_arch_find_domain() around rdt_find_domain() James Morse
2024-10-23 21:16   ` Reinette Chatre
2025-02-07 15:42     ` James Morse
2024-10-04 18:03 ` [PATCH v5 13/40] x86/resctrl: Move resctrl types to a separate header James Morse
2024-10-04 18:03 ` [PATCH v5 14/40] x86/resctrl: Add a resctrl helper to reset all the resources James Morse
2024-10-23 21:32   ` Reinette Chatre
2025-02-07 15:43     ` James Morse
2025-02-13 23:52       ` Reinette Chatre
2024-10-04 18:03 ` [PATCH v5 15/40] x86/resctrl: Move monitor exit work to a resctrl exit call James Morse
2024-10-04 18:03 ` [PATCH v5 16/40] x86/resctrl: Move monitor init work to a resctrl init call James Morse
2024-10-04 18:03 ` [PATCH v5 17/40] x86/resctrl: Rewrite and move the for_each_*_rdt_resource() walkers James Morse
2024-10-08  0:00   ` Tony Luck
2024-10-08 16:40     ` Reinette Chatre
2024-10-18 17:07       ` James Morse
2024-10-23 21:51   ` Reinette Chatre
2025-02-07 15:44     ` James Morse
2024-10-04 18:03 ` [PATCH v5 18/40] x86/resctrl: Export the is_mbm_*_enabled() helpers to asm/resctrl.h James Morse
2024-10-23 22:00   ` Reinette Chatre
2025-02-07 15:44     ` James Morse
2024-10-04 18:03 ` [PATCH v5 19/40] x86/resctrl: Add resctrl_arch_is_evt_configurable() to abstract BMEC James Morse
2024-10-23 22:04   ` Reinette Chatre
2025-02-07 15:44     ` James Morse
2024-10-04 18:03 ` [PATCH v5 20/40] x86/resctrl: Slightly clean-up mbm_config_show() James Morse
2024-10-16 16:50   ` Tony Luck
2024-10-04 18:03 ` [PATCH v5 21/40] x86/resctrl: Change mon_event_config_{read,write}() to be arch helpers James Morse
2024-10-23 22:19   ` Reinette Chatre
2025-02-07 15:45     ` James Morse
2024-10-04 18:03 ` [PATCH v5 22/40] x86/resctrl: Move mbm_cfg_mask to struct rdt_resource James Morse
2024-10-23 22:42   ` Reinette Chatre
2024-10-04 18:03 ` [PATCH v5 23/40] x86/resctrl: Add resctrl_arch_ prefix to pseudo lock functions James Morse
2024-10-23 22:44   ` Reinette Chatre
2025-02-07 15:45     ` James Morse
2024-10-04 18:03 ` [PATCH v5 24/40] x86/resctrl: Allow an architecture to disable pseudo lock James Morse
2024-10-04 18:03 ` [PATCH v5 25/40] x86/resctrl: Make prefetch_disable_bits belong to the arch code James Morse
2024-10-23 22:53   ` Reinette Chatre
2025-02-07 15:46     ` James Morse
2024-10-04 18:03 ` [PATCH v5 26/40] x86/resctrl: Make resctrl_arch_pseudo_lock_fn() take a plr James Morse
2024-10-04 18:03 ` [PATCH v5 27/40] x86/resctrl: Move thread_throttle_mode_init() to be managed by resctrl James Morse
2024-10-23 22:59   ` Reinette Chatre
2025-02-10 13:22     ` James Morse
2024-10-04 18:03 ` [PATCH v5 28/40] x86/resctrl: Move get_config_index() to a header James Morse
2024-10-04 18:03 ` [PATCH v5 29/40] x86/resctrl: Claim get_{mon,ctrl}_domain_from_cpu() helpers for resctrl James Morse
2024-10-23 23:02   ` Reinette Chatre
2024-10-04 18:03 ` [PATCH v5 30/40] x86/resctrl: Describe resctrl's bitmap size assumptions James Morse
2024-10-08 18:50   ` Tony Luck
2025-02-07 15:46     ` James Morse
2024-10-04 18:03 ` [PATCH v5 31/40] x86/resctrl: Rename resctrl_sched_in() to begin with "resctrl_arch_" James Morse
2024-10-04 18:03 ` [PATCH v5 32/40] x86/resctrl: resctrl_exit() teardown resctrl but leave the mount point James Morse
2024-10-23 23:50   ` Reinette Chatre
2025-02-07 15:54     ` James Morse
2024-10-04 18:03 ` [PATCH v5 33/40] x86/resctrl: Drop __init/__exit on assorted symbols James Morse
2024-10-23 23:56   ` Reinette Chatre
2025-02-07 15:54     ` James Morse
2024-10-04 18:03 ` [PATCH v5 34/40] x86/resctrl: Move is_mba_sc() out of core.c James Morse
2024-10-04 18:03 ` [PATCH v5 35/40] x86/resctrl: Add end-marker to the resctrl_event_id enum James Morse
2024-10-04 18:03 ` [PATCH v5 36/40] x86/resctrl: Remove a newline to avoid confusing the code move script James Morse
2024-10-04 18:03 ` [PATCH v5 37/40] x86/resctrl: Split trace.h James Morse
2024-10-04 18:03 ` [PATCH v5 38/40] fs/resctrl: Add boiler plate for external resctrl code James Morse
2024-10-08 23:03   ` Tony Luck
2024-10-24  0:08   ` Reinette Chatre
2025-02-07 15:54     ` James Morse
2024-10-04 18:03 ` [PATCH v5 39/40] x86/resctrl: Move the filesystem bits to headers visible to fs/resctrl James Morse
2024-10-04 18:03 ` [PATCH v5 40/40] x86/resctrl: Add python script to move resctrl code to /fs/resctrl James Morse
2024-10-08 23:08   ` Tony Luck
2024-10-24  0:17     ` Reinette Chatre
2025-02-07 15:55       ` James Morse
2024-10-04 21:18 ` [PATCH v5 00/40] x86/resctrl: Move the resctrl filesystem " Reinette Chatre
2024-10-07 17:29   ` James Morse
2024-10-08 23:24 ` Tony Luck
2024-10-17 17:43 ` Tony Luck
2024-12-06  7:17 ` Shaopeng Tan (Fujitsu)

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=20241004180347.19985-10-james.morse@arm.com \
    --to=james.morse@arm.com \
    --cc=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=dave.martin@arm.com \
    --cc=david@redhat.com \
    --cc=dfustini@baylibre.com \
    --cc=fenghua.yu@intel.com \
    --cc=hpa@zytor.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=rex.nie@jaguarmicro.com \
    --cc=scott@os.amperecomputing.com \
    --cc=shameerali.kolothum.thodi@huawei.com \
    --cc=tan.shaopeng@fujitsu.com \
    --cc=tan.shaopeng@jp.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.