Skip to contentSkip to conversation

x86/resctrl: Misc cleanup

PATCH Superseded James Morse 3 participants 16 messages May 18, 2020 – May 22, 2020

Subsystems (2)

v3 of 5 Superseded Latest is v5 →

lore
Share & tools
lore

James Morse

author reviewer
#0 lore raw

v3 cover x86/resctrl: Misc cleanup

Hello!

These are the miscellaneous cleanup patches that floated to the top of the MPAM tree.

The only interesting thing are the patches to make the AMD/Intel differences something resctrl understands, instead of just 'happening' because of the different function pointers.
This will become more important once MPAM support is added. parse_bw() and friends are what enforces resctrl's ABI resctrl. Allowing an architecture/platform to provide a subtly different function here would be bad for user-space.

MPAM would set arch_has_sparse_bitmaps and arch_has_empty_bitmap, but not arch_needs_linear.

Since [v2], arch_has_empty_bitmap has been added, and some typos fixed.

Since [v1], I've picked up all the review feedback and collected the tags.

Nothing in this series should change any behaviour.
This series is based on tip's x86/cache branch: v5.7-rc4-7-g0c4d5ba1b998 and can be retrieved from:
git://linux-arm.org/linux-jm.git mpam/cleanup/v3

Thanks,

James

[v2] https://lore.kernel.org/lkml/[email protected]/
[v1] https://lore.kernel.org/lkml/[email protected]/

James Morse (10):
x86/resctrl: Nothing uses struct mbm_state chunks_bw x86/resctrl: Remove max_delay
x86/resctrl: Fix stale comment
x86/resctrl: use container_of() in delayed_work handlers x86/resctrl: Include pid.h
x86/resctrl: Use is_closid_match() in more places x86/resctrl: Add arch_needs_linear to explain AMD/Intel MBA difference x86/resctrl: Merge AMD/Intel parse_bw() calls
x86/resctrl: Add arch_has_{sparse,empty}_bitmaps to explain CAT
differences
cacheinfo: Move resctrl's get_cache_id() to the cacheinfo header file

 arch/x86/kernel/cpu/resctrl/core.c        | 45 +++++------
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 92 ++++-------------------
 arch/x86/kernel/cpu/resctrl/internal.h    | 21 ++----
 arch/x86/kernel/cpu/resctrl/monitor.c     | 16 +---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c    | 32 ++++----
 include/linux/cacheinfo.h                 | 21 ++++++
 include/linux/resctrl.h                   |  2 +
 7 files changed, 80 insertions(+), 149 deletions(-)
Signature · 1 line
2.19.1
author reviewer
#1 lore raw

PATCH v3 1/10 x86/resctrl: Nothing uses struct mbm_state chunks_bw

Nothing reads struct mbm_states's chunks_bw value, its a copy of chunks. Remove it.

---
 arch/x86/kernel/cpu/resctrl/internal.h | 2 --
 arch/x86/kernel/cpu/resctrl/monitor.c  | 3 +--
 2 files changed, 1 insertion(+), 4 deletions(-)
arch/x86/kernel/cpu/resctrl/internal.h +0 -2
index f20a47d120b1..1bb81cbdad5f 100644
@@ -282,7 +282,6 @@ struct rftype {
  * struct mbm_state - status for each MBM counter in each domain
  * @chunks:	Total data moved (multiply by rdt_group.mon_scale to get bytes)
  * @prev_msr	Value of IA32_QM_CTR for this RMID last time we read it
- * @chunks_bw	Total local data moved. Used for bandwidth calculation
  * @prev_bw_msr:Value of previous IA32_QM_CTR for bandwidth counting
  * @prev_bw	The most recent bandwidth in MBps
  * @delta_bw	Difference between the current and previous bandwidth
@@ -291,7 +290,6 @@ struct rftype {
 struct mbm_state {
 	u64	chunks;
 	u64	prev_msr;
-	u64	chunks_bw;
 	u64	prev_bw_msr;
 	u32	prev_bw;
 	u32	delta_bw;
arch/x86/kernel/cpu/resctrl/monitor.c +1 -2
index 837d7d012b7b..d6b92d7487a7 100644
@@ -279,8 +279,7 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr)
 		return;
 
 	chunks = mbm_overflow_count(m->prev_bw_msr, tval, rr->r->mbm_width);
-	m->chunks_bw += chunks;
-	m->chunks = m->chunks_bw;
+	m->chunks += chunks;
 	cur_bw = (chunks * r->mon_scale) >> 20;
 
 	if (m->delta_comp)
Signature · 1 line
2.19.1
author reviewer
#2 lore raw

PATCH v3 2/10 x86/resctrl: Remove max_delay

In reply to James Morse

max_delay is used by x86's __get_mem_config_intel() as a local variable. Remove it, replacing it with a local variable.

---
 arch/x86/kernel/cpu/resctrl/core.c     | 8 ++++----
 arch/x86/kernel/cpu/resctrl/internal.h | 3 ---
 2 files changed, 4 insertions(+), 7 deletions(-)
arch/x86/kernel/cpu/resctrl/core.c +4 -4
index 12f967c6b603..e1fed3928b59 100644
@@ -254,16 +254,16 @@ static bool __get_mem_config_intel(struct rdt_resource *r)
 {
 	union cpuid_0x10_3_eax eax;
 	union cpuid_0x10_x_edx edx;
-	u32 ebx, ecx;
+	u32 ebx, ecx, max_delay;
 
 	cpuid_count(0x00000010, 3, &eax.full, &ebx, &ecx, &edx.full);
 	r->num_closid = edx.split.cos_max + 1;
-	r->membw.max_delay = eax.split.max_delay + 1;
+	max_delay = eax.split.max_delay + 1;
 	r->default_ctrl = MAX_MBA_BW;
 	if (ecx & MBA_IS_LINEAR) {
 		r->membw.delay_linear = true;
-		r->membw.min_bw = MAX_MBA_BW - r->membw.max_delay;
-		r->membw.bw_gran = MAX_MBA_BW - r->membw.max_delay;
+		r->membw.min_bw = MAX_MBA_BW - max_delay;
+		r->membw.bw_gran = MAX_MBA_BW - max_delay;
 	} else {
 		if (!rdt_get_mb_table(r))
 			return false;
arch/x86/kernel/cpu/resctrl/internal.h +0 -3
index 1bb81cbdad5f..dd51e23e346b 100644
@@ -368,8 +368,6 @@ struct rdt_cache {
 
 /**
  * struct rdt_membw - Memory bandwidth allocation related data
- * @max_delay:		Max throttle delay. Delay is the hardware
- *			representation for memory bandwidth.
  * @min_bw:		Minimum memory bandwidth percentage user can request
  * @bw_gran:		Granularity at which the memory bandwidth is allocated
  * @delay_linear:	True if memory B/W delay is in linear scale
@@ -377,7 +375,6 @@ struct rdt_cache {
  * @mb_map:		Mapping of memory B/W percentage to memory B/W delay
  */
 struct rdt_membw {
-	u32		max_delay;
 	u32		min_bw;
 	u32		bw_gran;
 	u32		delay_linear;
Signature · 1 line
2.19.1
author reviewer
#3 lore raw

PATCH v3 3/10 x86/resctrl: Fix stale comment

In reply to James Morse

The comment in rdtgroup_init() refers to the non existent function rdt_mount(), which has now been renamed rdt_get_tree(). Fix the comment.

---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/x86/kernel/cpu/resctrl/rdtgroup.c +1 -1
index d7cb5ab0d1f0..24bdb52446aa 100644
@@ -3195,7 +3195,7 @@ int __init rdtgroup_init(void)
 	 * It may also be ok since that would enable debugging of RDT before
 	 * resctrl is mounted.
 	 * The reason why the debugfs directory is created here and not in
-	 * rdt_mount() is because rdt_mount() takes rdtgroup_mutex and
+	 * rdt_get_tree() is because rdt_get_tree() takes rdtgroup_mutex and
 	 * during the debugfs directory creation also &sb->s_type->i_mutex_key
 	 * (the lockdep class of inode->i_rwsem). Other filesystem
 	 * interactions (eg. SyS_getdents) have the lock ordering:
Signature · 1 line
2.19.1
author reviewer
#4 lore raw

PATCH v3 4/10 x86/resctrl: use container_of() in delayed_work handlers

In reply to James Morse

mbm_handle_overflow() and cqm_handle_limbo() are both provided with the domain's work_struct when called, but use get_domain_from_cpu() to find the domain, along with the appropriate error handling.

container_of() saves some list walking and bitmap testing, use that instead.

---
 arch/x86/kernel/cpu/resctrl/monitor.c | 13 ++-----------
 1 file changed, 2 insertions(+), 11 deletions(-)
arch/x86/kernel/cpu/resctrl/monitor.c +2 -11
index d6b92d7487a7..54dffe574e67 100644
@@ -477,19 +477,13 @@ void cqm_handle_limbo(struct work_struct *work)
 	mutex_lock(&rdtgroup_mutex);
 
 	r = &rdt_resources_all[RDT_RESOURCE_L3];
-	d = get_domain_from_cpu(cpu, r);
-
-	if (!d) {
-		pr_warn_once("Failure to get domain for limbo worker\n");
-		goto out_unlock;
-	}
+	d = container_of(work, struct rdt_domain, cqm_limbo.work);
 
 	__check_limbo(d, false);
 
 	if (has_busy_rmid(r, d))
 		schedule_delayed_work_on(cpu, &d->cqm_limbo, delay);
 
-out_unlock:
 	mutex_unlock(&rdtgroup_mutex);
 }
 
@@ -519,10 +513,7 @@ void mbm_handle_overflow(struct work_struct *work)
 		goto out_unlock;
 
 	r = &rdt_resources_all[RDT_RESOURCE_L3];
-
-	d = get_domain_from_cpu(cpu, r);
-	if (!d)
-		goto out_unlock;
+	d = container_of(work, struct rdt_domain, mbm_over.work);
 
 	list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
 		mbm_update(r, d, prgrp->mon.rmid);
Signature · 1 line
2.19.1
author reviewer
#5 lore raw

PATCH v3 5/10 x86/resctrl: Include pid.h

In reply to James Morse

We are about to disturb the header soup. This header uses struct pid and struct pid_namespace. Include their header.

---
 include/linux/resctrl.h | 2 ++
 1 file changed, 2 insertions(+)
include/linux/resctrl.h +2 -0
index daf5cf64c6a6..9b05af9b3e28 100644
@@ -2,6 +2,8 @@
 #ifndef _RESCTRL_H
 #define _RESCTRL_H
 
+#include <linux/pid.h>
+
 #ifdef CONFIG_PROC_CPU_RESCTRL
 
 int proc_resctrl_show(struct seq_file *m,
Signature · 1 line
2.19.1
author reviewer
#6 lore raw

PATCH v3 6/10 x86/resctrl: Use is_closid_match() in more places

In reply to James Morse

rdtgroup_tasks_assigned() and show_rdt_tasks() loop over threads testing for a CTRL/MON group match by closid/rmid with the provided rdtgrp. Further down the file are helpers to do this, move these further up and make use of them here.

These helpers additionally check for alloc/mon capable. This is harmless as rdtgroup_mkdir() tests these capable flags before allowing the config directories to be created.

---
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 30 ++++++++++++--------------
 1 file changed, 14 insertions(+), 16 deletions(-)
arch/x86/kernel/cpu/resctrl/rdtgroup.c +14 -16
index 24bdb52446aa..d3aa55e1380f 100644
@@ -592,6 +592,18 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
 	return ret;
 }
 
+static bool is_closid_match(struct task_struct *t, struct rdtgroup *r)
+{
+	return (rdt_alloc_capable &&
+	       (r->type == RDTCTRL_GROUP) && (t->closid == r->closid));
+}
+
+static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r)
+{
+	return (rdt_mon_capable &&
+	       (r->type == RDTMON_GROUP) && (t->rmid == r->mon.rmid));
+}
+
 /**
  * rdtgroup_tasks_assigned - Test if tasks have been assigned to resource group
  * @r: Resource group
@@ -607,8 +619,7 @@ int rdtgroup_tasks_assigned(struct rdtgroup *r)
 
 	rcu_read_lock();
 	for_each_process_thread(p, t) {
-		if ((r->type == RDTCTRL_GROUP && t->closid == r->closid) ||
-		    (r->type == RDTMON_GROUP && t->rmid == r->mon.rmid)) {
+		if (is_closid_match(t, r) || is_rmid_match(t, r)) {
 			ret = 1;
 			break;
 		}
@@ -706,8 +717,7 @@ static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s)
 
 	rcu_read_lock();
 	for_each_process_thread(p, t) {
-		if ((r->type == RDTCTRL_GROUP && t->closid == r->closid) ||
-		    (r->type == RDTMON_GROUP && t->rmid == r->mon.rmid))
+		if (is_closid_match(t, r) || is_rmid_match(t, r))
 			seq_printf(s, "%d\n", t->pid);
 	}
 	rcu_read_unlock();
@@ -2244,18 +2254,6 @@ static int reset_all_ctrls(struct rdt_resource *r)
 	return 0;
 }
 
-static bool is_closid_match(struct task_struct *t, struct rdtgroup *r)
-{
-	return (rdt_alloc_capable &&
-		(r->type == RDTCTRL_GROUP) && (t->closid == r->closid));
-}
-
-static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r)
-{
-	return (rdt_mon_capable &&
-		(r->type == RDTMON_GROUP) && (t->rmid == r->mon.rmid));
-}
-
 /*
  * Move tasks from one to the other group. If @from is NULL, then all tasks
  * in the systems are moved unconditionally (used for teardown).
Signature · 1 line
2.19.1
author reviewer
#7 lore raw

PATCH v3 7/10 x86/resctrl: Add arch_needs_linear to explain AMD/Intel MBA difference

In reply to James Morse

The configuration values user-space provides to the resctrl filesystem are ABI. To make this work on another architecture we want to move all the ABI bits out of /arch/x86 and under /fs.

To do this, the differences between AMD and Intel CPUs needs to be explained to resctrl via resource properties, instead of function pointers that let the arch code accept subtly different values on different platforms/architectures.

For MBA, Intel CPUs reject configuration attempts for non-linear resources, whereas AMD ignore this field as its MBA resource is never linear. To merge the parse/validate functions we need to explain this difference.

Add arch_needs_linear to indicate the arch code needs the linear property to be true to configure this resource. AMD can set this and delay_linear to false. Intel can set arch_needs_linear to true to keep the existing "No support for non-linear MB domains" error message for affected platforms.

---
An alternative to this is for Intel non-linear MBA resources to clear alloc_capable as they can't be configured anyway.

---
 arch/x86/kernel/cpu/resctrl/core.c        | 3 +++
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 8 +++++++-
 arch/x86/kernel/cpu/resctrl/internal.h    | 2 ++
 3 files changed, 12 insertions(+), 1 deletion(-)
arch/x86/kernel/cpu/resctrl/core.c +3 -0
index e1fed3928b59..c6b73b0ee070 100644
@@ -260,6 +260,7 @@ static bool __get_mem_config_intel(struct rdt_resource *r)
 	r->num_closid = edx.split.cos_max + 1;
 	max_delay = eax.split.max_delay + 1;
 	r->default_ctrl = MAX_MBA_BW;
+	r->membw.arch_needs_linear = true;
 	if (ecx & MBA_IS_LINEAR) {
 		r->membw.delay_linear = true;
 		r->membw.min_bw = MAX_MBA_BW - max_delay;
@@ -267,6 +268,7 @@ static bool __get_mem_config_intel(struct rdt_resource *r)
 	} else {
 		if (!rdt_get_mb_table(r))
 			return false;
+		r->membw.arch_needs_linear = false;
 	}
 	r->data_width = 3;
 
@@ -288,6 +290,7 @@ static bool __rdt_get_mem_config_amd(struct rdt_resource *r)
 
 	/* AMD does not use delay */
 	r->membw.delay_linear = false;
+	r->membw.arch_needs_linear = false;
 
 	r->membw.min_bw = 0;
 	r->membw.bw_gran = 1;
arch/x86/kernel/cpu/resctrl/ctrlmondata.c +7 -1
index 934c8fb8a64a..e3bcd77add2b 100644
@@ -33,6 +33,12 @@ static bool bw_validate_amd(char *buf, unsigned long *data,
 	unsigned long bw;
 	int ret;
 
+	/* temporary: always false on AMD */
+	if (!r->membw.delay_linear && r->membw.arch_needs_linear) {
+		rdt_last_cmd_puts("No support for non-linear MB domains\n");
+		return false;
+	}
+
 	ret = kstrtoul(buf, 10, &bw);
 	if (ret) {
 		rdt_last_cmd_printf("Non-decimal digit in MB value %s\n", buf);
@@ -82,7 +88,7 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
 	/*
 	 * Only linear delay values is supported for current Intel SKUs.
 	 */
-	if (!r->membw.delay_linear) {
+	if (!r->membw.delay_linear && r->membw.arch_needs_linear) {
 		rdt_last_cmd_puts("No support for non-linear MB domains\n");
 		return false;
 	}
arch/x86/kernel/cpu/resctrl/internal.h +2 -0
index dd51e23e346b..0b288b6fefd9 100644
@@ -370,6 +370,7 @@ struct rdt_cache {
  * struct rdt_membw - Memory bandwidth allocation related data
  * @min_bw:		Minimum memory bandwidth percentage user can request
  * @bw_gran:		Granularity at which the memory bandwidth is allocated
+ * @arch_needs_linear:	True if we can't configure non-linear resources
  * @delay_linear:	True if memory B/W delay is in linear scale
  * @mba_sc:		True if MBA software controller(mba_sc) is enabled
  * @mb_map:		Mapping of memory B/W percentage to memory B/W delay
@@ -378,6 +379,7 @@ struct rdt_membw {
 	u32		min_bw;
 	u32		bw_gran;
 	u32		delay_linear;
+	bool		arch_needs_linear;
 	bool		mba_sc;
 	u32		*mb_map;
 };
Signature · 1 line
2.19.1
maintainer
#8 lore raw

Re: [PATCH v3 07/10] x86/resctrl: Add arch_needs_linear to explain AMD/Intel MBA difference

Hi James,

Quoted 14 lines · James Morse
arch/x86/kernel/cpu/resctrl/internal.h +1 -0
index dd51e23e346b..0b288b6fefd9 100644
@@ -370,6 +370,7 @@ struct rdt_cache {
  * struct rdt_membw - Memory bandwidth allocation related data
  * @min_bw:		Minimum memory bandwidth percentage user can request
  * @bw_gran:		Granularity at which the memory bandwidth is allocated
+ * @arch_needs_linear:	True if we can't configure non-linear resources
  * @delay_linear:	True if memory B/W delay is in linear scale
  * @mba_sc:		True if MBA software controller(mba_sc) is enabled
  * @mb_map:		Mapping of memory B/W percentage to memory B/W delay

arch/x86/kernel/cpu/resctrl/internal.h struct rdt_membw { · line 385

Quoted 7 lines
arch/x86/kernel/cpu/resctrl/internal.h +1 -0
@@ -378,6 +379,7 @@ struct rdt_membw {
 	u32		min_bw;
 	u32		bw_gran;
 	u32		delay_linear;
+	bool		arch_needs_linear;
 	bool		mba_sc;
 	u32		*mb_map;
 };

Sorry, I just noticed this while rebasing our respective changes to this area ... could the comments be in the same order as the fields in the struct?

Reinette

reviewer Reviewed-by on v3 7/10
#9 lore raw

RE: [PATCH v3 07/10] x86/resctrl: Add arch_needs_linear to explain AMD/Intel MBA difference

In reply to James Morse

Looks good.

Quoted 32 lines

-----Original Message-----
From: James Morse <[email protected]>
Sent: Monday, May 18, 2020 8:19 AM
To: [email protected]; [email protected]
Cc: Fenghua Yu <[email protected]>; Reinette Chatre <[email protected]>; Thomas Gleixner <[email protected]>; Ingo Molnar <[email protected]>; Borislav Petkov <[email protected]>; H Peter Anvin <[email protected]>; Moger, Babu <[email protected]>; James Morse <[email protected]>
Subject: [PATCH v3 07/10] x86/resctrl: Add arch_needs_linear to explain AMD/Intel MBA difference

The configuration values user-space provides to the resctrl filesystem are ABI. To make this work on another architecture we want to move all the ABI bits out of /arch/x86 and under /fs.

To do this, the differences between AMD and Intel CPUs needs to be explained to resctrl via resource properties, instead of function pointers that let the arch code accept subtly different values on different platforms/architectures.

For MBA, Intel CPUs reject configuration attempts for non-linear resources, whereas AMD ignore this field as its MBA resource is never linear. To merge the parse/validate functions we need to explain this difference.

Add arch_needs_linear to indicate the arch code needs the linear property to be true to configure this resource. AMD can set this and delay_linear to false. Intel can set arch_needs_linear to true to keep the existing "No support for non-linear MB domains" error message for affected platforms.

Quoted 3 lines
Quoted 96 lines

---
An alternative to this is for Intel non-linear MBA resources to clear alloc_capable as they can't be configured anyway.

---
 arch/x86/kernel/cpu/resctrl/core.c        | 3 +++
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 8 +++++++-
 arch/x86/kernel/cpu/resctrl/internal.h    | 2 ++
 3 files changed, 12 insertions(+), 1 deletion(-)
arch/x86/kernel/cpu/resctrl/core.c +1 -0
index e1fed3928b59..c6b73b0ee070 100644
@@ -260,6 +260,7 @@ static bool __get_mem_config_intel(struct rdt_resource
 *r)
 	r->num_closid = edx.split.cos_max + 1;
 	max_delay = eax.split.max_delay + 1;
 	r->default_ctrl = MAX_MBA_BW;
+	r->membw.arch_needs_linear = true;
 	if (ecx & MBA_IS_LINEAR) {
 		r->membw.delay_linear = true;
arch/x86/kernel/cpu/resctrl/core.c +2 -0
 		r->membw.min_bw = MAX_MBA_BW - max_delay;
@@ -267,6 +268,7 @@ static bool __get_mem_config_intel(struct rdt_resource
 *r)
 	} else {
 		if (!rdt_get_mb_table(r))
 			return false;
+		r->membw.arch_needs_linear = false;
 	}
 	r->data_width = 3;
@@ -288,6 +290,7 @@ static bool __rdt_get_mem_config_amd(struct
 rdt_resource *r)
 
 	/* AMD does not use delay */
 	r->membw.delay_linear = false;
+	r->membw.arch_needs_linear = false;
 
 	r->membw.min_bw = 0;
arch/x86/kernel/cpu/resctrl/core.c +0 -0
 	r->membw.bw_gran = 1;
arch/x86/kernel/cpu/resctrl/ctrlmondata.c +6 -0
index 934c8fb8a64a..e3bcd77add2b 100644
@@ -33,6 +33,12 @@ static bool bw_validate_amd(char *buf, unsigned long
 *data,
 	unsigned long bw;
 	int ret;
 
+	/* temporary: always false on AMD */
+	if (!r->membw.delay_linear && r->membw.arch_needs_linear) {
+		rdt_last_cmd_puts("No support for non-linear MB domains\n");
+		return false;
+	}
+
 	ret = kstrtoul(buf, 10, &bw);
 	if (ret) {
arch/x86/kernel/cpu/resctrl/ctrlmondata.c +1 -1
 		rdt_last_cmd_printf("Non-decimal digit in MB value %s\n", buf);
@@ -82,7 +88,7 @@ static bool bw_validate(char *buf, unsigned long *data,
 struct rdt_resource *r)
 	/*
 	 * Only linear delay values is supported for current Intel SKUs.
 	 */
-	if (!r->membw.delay_linear) {
+	if (!r->membw.delay_linear && r->membw.arch_needs_linear) {
 		rdt_last_cmd_puts("No support for non-linear MB domains\n");
 		return false;
arch/x86/kernel/cpu/resctrl/ctrlmondata.c +0 -0
 	}
arch/x86/kernel/cpu/resctrl/internal.h +0 -0
index dd51e23e346b..0b288b6fefd9 100644
@@ -370,6 +370,7 @@ struct rdt_cache {
  * struct rdt_membw - Memory bandwidth allocation related data
  * @min_bw:		Minimum memory bandwidth percentage user can

request
* @bw_gran: Granularity at which the memory bandwidth is allocated
+ * @arch_needs_linear: True if we can't configure non-linear resources
* @delay_linear: True if memory B/W delay is in linear scale
* @mba_sc: True if MBA software controller(mba_sc) is enabled
* @mb_map: Mapping of memory B/W percentage to memory B/W
delay

arch/x86/kernel/cpu/resctrl/internal.h +1 -1
@@ -378,6 +379,7 @@ struct rdt_membw {
 	u32		min_bw;
 	u32		bw_gran;
 	u32		delay_linear;
+	bool		arch_needs_linear;
 	bool		mba_sc;
 	u32		*mb_map;
 };
--

2.19.1

author reviewer
#10 lore raw

PATCH v3 8/10 x86/resctrl: Merge AMD/Intel parse_bw() calls

In reply to James Morse

Now that we've explained arch_needs_linear to resctrl, the parse_bw() calls are almost the same between AMD and Intel.

The difference is '!is_mba_sc()', which is not checked on AMD. This will always be true on AMD CPUs as mba_sc cannot be enabled as is_mba_linear() is false.

Removing this duplication means user-space visible behaviour and error messages are not validated or generated in different places.

---
 arch/x86/kernel/cpu/resctrl/core.c        |  3 +-
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 57 +----------------------
 arch/x86/kernel/cpu/resctrl/internal.h    |  6 +--
 3 files changed, 5 insertions(+), 61 deletions(-)
arch/x86/kernel/cpu/resctrl/core.c +1 -2
index c6b73b0ee070..223e5b90bcfd 100644
@@ -168,6 +168,7 @@ struct rdt_resource rdt_resources_all[] = {
 		.name			= "MB",
 		.domains		= domain_init(RDT_RESOURCE_MBA),
 		.cache_level		= 3,
+		.parse_ctrlval		= parse_bw,
 		.format_str		= "%d=%*u",
 		.fflags			= RFTYPE_RES_MB,
 	},
@@ -926,7 +927,6 @@ static __init void rdt_init_res_defs_intel(void)
 		else if (r->rid == RDT_RESOURCE_MBA) {
 			r->msr_base = MSR_IA32_MBA_THRTL_BASE;
 			r->msr_update = mba_wrmsr_intel;
-			r->parse_ctrlval = parse_bw_intel;
 		}
 	}
 }
@@ -946,7 +946,6 @@ static __init void rdt_init_res_defs_amd(void)
 		else if (r->rid == RDT_RESOURCE_MBA) {
 			r->msr_base = MSR_IA32_MBA_BW_BASE;
 			r->msr_update = mba_wrmsr_amd;
-			r->parse_ctrlval = parse_bw_amd;
 		}
 	}
 }
arch/x86/kernel/cpu/resctrl/ctrlmondata.c +2 -55

69 lines not on this page · raw message

arch/x86/kernel/cpu/resctrl/internal.h +2 -4
index 0b288b6fefd9..5919aae946ba 100644
@@ -470,10 +470,8 @@ struct rdt_resource {
 
 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);
+int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r,
+	     struct rdt_domain *d);
 
 extern struct mutex rdtgroup_mutex;
 
Signature · 1 line
2.19.1
reviewer Reviewed-by on v3 8/10
#11 lore raw

RE: [PATCH v3 08/10] x86/resctrl: Merge AMD/Intel parse_bw() calls

Quoted 20 lines

-----Original Message-----
From: James Morse <[email protected]>
Sent: Monday, May 18, 2020 8:19 AM
To: [email protected]; [email protected]
Cc: Fenghua Yu <[email protected]>; Reinette Chatre <[email protected]>; Thomas Gleixner <[email protected]>; Ingo Molnar <[email protected]>; Borislav Petkov <[email protected]>; H Peter Anvin <[email protected]>; Moger, Babu <[email protected]>; James Morse <[email protected]>
Subject: [PATCH v3 08/10] x86/resctrl: Merge AMD/Intel parse_bw() calls

Now that we've explained arch_needs_linear to resctrl, the parse_bw() calls are almost the same between AMD and Intel.

The difference is '!is_mba_sc()', which is not checked on AMD. This will always be true on AMD CPUs as mba_sc cannot be enabled as is_mba_linear() is false.

Quoted 6 lines

Removing this duplication means user-space visible behaviour and error messages are not validated or generated in different places.

Quoted 133 lines
---
 arch/x86/kernel/cpu/resctrl/core.c        |  3 +-
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 57 +----------------------
 arch/x86/kernel/cpu/resctrl/internal.h    |  6 +--
 3 files changed, 5 insertions(+), 61 deletions(-)
arch/x86/kernel/cpu/resctrl/core.c +1 -2
index c6b73b0ee070..223e5b90bcfd 100644
@@ -168,6 +168,7 @@ struct rdt_resource rdt_resources_all[] = {
 		.name			= "MB",
 		.domains		= domain_init(RDT_RESOURCE_MBA),
 		.cache_level		= 3,
+		.parse_ctrlval		= parse_bw,
 		.format_str		= "%d=%*u",
 		.fflags			= RFTYPE_RES_MB,
 	},
@@ -926,7 +927,6 @@ static __init void rdt_init_res_defs_intel(void)
 		else if (r->rid == RDT_RESOURCE_MBA) {
 			r->msr_base = MSR_IA32_MBA_THRTL_BASE;
 			r->msr_update = mba_wrmsr_intel;
-			r->parse_ctrlval = parse_bw_intel;
 		}
 	}
 }
@@ -946,7 +946,6 @@ static __init void rdt_init_res_defs_amd(void)
 		else if (r->rid == RDT_RESOURCE_MBA) {
 			r->msr_base = MSR_IA32_MBA_BW_BASE;
 			r->msr_update = mba_wrmsr_amd;
-			r->parse_ctrlval = parse_bw_amd;
 		}
 	}
 }
arch/x86/kernel/cpu/resctrl/ctrlmondata.c +0 -53
index e3bcd77add2b..b0e24cb6f85c 100644
@@ -21,59 +21,6 @@
 #include <linux/slab.h>
 #include "internal.h"
 
-/*
- * Check whether MBA bandwidth percentage value is correct. The value is
- * checked against the minimum and maximum bandwidth values specified by
- * the hardware. The allocated bandwidth percentage is rounded to the next
- * control step available on the hardware.
- */
-static bool bw_validate_amd(char *buf, unsigned long *data,
-			    struct rdt_resource *r)
-{
-	unsigned long bw;
-	int ret;
-
-	/* temporary: always false on AMD */
-	if (!r->membw.delay_linear && r->membw.arch_needs_linear) {
-		rdt_last_cmd_puts("No support for non-linear MB domains\n");
-		return false;
-	}
-
-	ret = kstrtoul(buf, 10, &bw);
-	if (ret) {
-		rdt_last_cmd_printf("Non-decimal digit in MB value %s\n", buf);
-		return false;
-	}
-
-	if (bw < r->membw.min_bw || bw > r->default_ctrl) {
-		rdt_last_cmd_printf("MB value %ld out of range [%d,%d]\n",
 bw,
-				    r->membw.min_bw, r->default_ctrl);
-		return false;
-	}
-
-	*data = roundup(bw, (unsigned long)r->membw.bw_gran);
-	return true;
-}
-
-int parse_bw_amd(struct rdt_parse_data *data, struct rdt_resource *r,
-		 struct rdt_domain *d)
-{
-	unsigned long bw_val;
-
-	if (d->have_new_ctrl) {
-		rdt_last_cmd_printf("Duplicate domain %d\n", d->id);
-		return -EINVAL;
-	}
-
-	if (!bw_validate_amd(data->buf, &bw_val, r))
-		return -EINVAL;
-
-	d->new_ctrl = bw_val;
-	d->have_new_ctrl = true;
-
-	return 0;
-}
-
 /*
  * Check whether MBA bandwidth percentage value is correct. The value is

* checked against the minimum and max bandwidth values specified by the

arch/x86/kernel/cpu/resctrl/ctrlmondata.c +2 -2
@@ -110,8 +57,8 @@ static bool bw_validate(char *buf, unsigned long *data,
 struct rdt_resource *r)
 	return true;
 }
 
-int parse_bw_intel(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)
 {
 	unsigned long bw_val;
arch/x86/kernel/cpu/resctrl/internal.h +2 -5
index 0b288b6fefd9..5919aae946ba 100644
@@ -470,10 +470,8 @@ struct rdt_resource {
 
 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);
+int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r,
+	     struct rdt_domain *d);
 
 extern struct mutex rdtgroup_mutex;
 
--

2.19.1

author reviewer
#12 lore raw

PATCH v3 9/10 x86/resctrl: Add arch_has_{sparse,empty}_bitmaps to explain CAT differences

In reply to James Morse

Intel CPUs expect the cache bitmap provided by user-space to have on a single span of 1s, whereas AMD can support bitmaps like 0xf00f. Arm's MPAM support also allows sparse bitmaps.

Similarly, Intel CPUs check at least one bit set, whereas AMD CPUs are quite happy with an empty bitmap. Arm's MPAM allows an empty bitmap.

To move resctrl out to /fs/ we need to explain platform differences like this. Add two resource properties arch_has_{empty,sparse}_bitmaps. Test these around the relevant parts of cbm_validate().

Merging the validate calls causes AMD to gain the min_cbm_bits test needed for Haswell, but as it always sets this value to 1, it will never match.

CC Babu Moger <[email protected]>
CC Reinette Chatre <[email protected]>
---
 arch/x86/kernel/cpu/resctrl/core.c        | 14 ++++----
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 39 ++++++-----------------
 arch/x86/kernel/cpu/resctrl/internal.h    |  8 ++---
 3 files changed, 22 insertions(+), 39 deletions(-)
arch/x86/kernel/cpu/resctrl/core.c +8 -6
index 223e5b90bcfd..587f9791d2a6 100644
@@ -922,9 +922,10 @@ static __init void rdt_init_res_defs_intel(void)
 		    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->rid == RDT_RESOURCE_L2CODE) {
+			r->cache.arch_has_sparse_bitmaps = false;
+			r->cache.arch_has_empty_bitmaps = false;
+		} else if (r->rid == RDT_RESOURCE_MBA) {
 			r->msr_base = MSR_IA32_MBA_THRTL_BASE;
 			r->msr_update = mba_wrmsr_intel;
 		}
@@ -941,9 +942,10 @@ static __init void rdt_init_res_defs_amd(void)
 		    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->rid == RDT_RESOURCE_L2CODE) {
+			r->cache.arch_has_sparse_bitmaps = true;
+			r->cache.arch_has_empty_bitmaps = true;
+		} else if (r->rid == RDT_RESOURCE_MBA) {
 			r->msr_base = MSR_IA32_MBA_BW_BASE;
 			r->msr_update = mba_wrmsr_amd;
 		}
arch/x86/kernel/cpu/resctrl/ctrlmondata.c +10 -29
index b0e24cb6f85c..cc854bb369c9 100644
@@ -76,12 +76,14 @@ int parse_bw(struct rdt_parse_data *data, struct rdt_resource *r,
 }
 
 /*
- * Check whether a cache bit mask is valid. The SDM says:
+ * Check whether a cache bit mask is valid.
+ * For Intel the SDM says:
  *	Please note that all (and only) contiguous '1' combinations
  *	are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.).
  * Additionally Haswell requires at least two bits set.
+ * AMD allows non-contiguous bitmasks.
  */
-bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r)
+static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
 {
 	unsigned long first_bit, zero_bit, val;
 	unsigned int cbm_len = r->cache.cbm_len;
@@ -93,7 +95,8 @@ bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r)
 		return false;
 	}
 
-	if (val == 0 || val > r->default_ctrl) {
+	if ((!r->cache.arch_has_empty_bitmaps && val == 0) ||
+	    (val > r->default_ctrl)) {
 		rdt_last_cmd_puts("Mask out of range\n");
 		return false;
 	}
@@ -101,7 +104,9 @@ bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r)
 	first_bit = find_first_bit(&val, cbm_len);
 	zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
 
-	if (find_next_bit(&val, cbm_len, zero_bit) < cbm_len) {
+	/* Are non-contiguous bitmaps allowed? */
+	if (!r->cache.arch_has_sparse_bitmaps &&
+	    (find_next_bit(&val, cbm_len, zero_bit) < cbm_len)) {
 		rdt_last_cmd_printf("The mask %lx has non-consecutive 1-bits\n", val);
 		return false;
 	}
@@ -116,30 +121,6 @@ bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r)
 	return true;
 }
 
-/*
- * Check whether a cache bit mask is valid. AMD allows non-contiguous
- * bitmasks
- */
-bool cbm_validate_amd(char *buf, u32 *data, struct rdt_resource *r)
-{
-	unsigned long val;
-	int ret;
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret) {
-		rdt_last_cmd_printf("Non-hex character in the mask %s\n", buf);
-		return false;
-	}
-
-	if (val > r->default_ctrl) {
-		rdt_last_cmd_puts("Mask out of range\n");
-		return false;
-	}
-
-	*data = val;
-	return true;
-}
-
 /*
  * Read one cache bit mask (hex). Check that it is valid for the current
  * resource type.
@@ -165,7 +146,7 @@ int parse_cbm(struct rdt_parse_data *data, struct rdt_resource *r,
 		return -EINVAL;
 	}
 
-	if (!r->cbm_validate(data->buf, &cbm_val, r))
+	if (!cbm_validate(data->buf, &cbm_val, r))
 		return -EINVAL;
 
 	if ((rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
arch/x86/kernel/cpu/resctrl/internal.h +4 -4
index 5919aae946ba..35f8137c4dce 100644
@@ -357,6 +357,8 @@ struct msr_param {
  *			in a cache bit mask
  * @shareable_bits:	Bitmask of shareable resource with other
  *			executing entities
+ * @arch_has_sparse_bitmaps:	True if a bitmap like f00f is valid.
+ * @arch_has_empty_bitmaps:	True if the '0' bitmap is valid.
  */
 struct rdt_cache {
 	unsigned int	cbm_len;
@@ -364,6 +366,8 @@ struct rdt_cache {
 	unsigned int	cbm_idx_mult;
 	unsigned int	cbm_idx_offset;
 	unsigned int	shareable_bits;
+	bool		arch_has_sparse_bitmaps;
+	bool		arch_has_empty_bitmaps;
 };
 
 /**
@@ -433,7 +437,6 @@ 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
- * @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
@@ -460,7 +463,6 @@ 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;
@@ -603,8 +605,6 @@ 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);
-bool cbm_validate_amd(char *buf, u32 *data, struct rdt_resource *r);
 void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
 
 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */
Signature · 1 line
2.19.1
maintainer
#13 lore raw

Re: [PATCH v3 09/10] x86/resctrl: Add arch_has_{sparse,empty}_bitmaps to explain CAT differences

Hi James,

Thank you very much for adding the handling of empty bitmaps. This looks good to me, just one comment ...

Quoted 6 lines · James Morse
arch/x86/kernel/cpu/resctrl/ctrlmondata.c +1 -1
-bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r)
+static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
 {
 	unsigned long first_bit, zero_bit, val;
 	unsigned int cbm_len = r->cache.cbm_len;

arch/x86/kernel/cpu/resctrl/ctrlmondata.c bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r) · line 101

Quoted 8 lines
arch/x86/kernel/cpu/resctrl/ctrlmondata.c +2 -1
@@ -93,7 +95,8 @@ bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r)
 		return false;
 	}
 
-	if (val == 0 || val > r->default_ctrl) {
+	if ((!r->cache.arch_has_empty_bitmaps && val == 0) ||
+	    (val > r->default_ctrl)) {
 		rdt_last_cmd_puts("Mask out of range\n");
 		return false;

There is unnecessary parentheses around 'val > r->default_ctrl'

Reinette

reviewer Reviewed-by on v3 9/10
#14 lore raw

RE: [PATCH v3 09/10] x86/resctrl: Add arch_has_{sparse,empty}_bitmaps to explain CAT differences

In reply to James Morse
Quoted 26 lines

-----Original Message-----
From: James Morse <[email protected]>
Sent: Monday, May 18, 2020 8:19 AM
To: [email protected]; [email protected]
Cc: Fenghua Yu <[email protected]>; Reinette Chatre <[email protected]>; Thomas Gleixner <[email protected]>; Ingo Molnar <[email protected]>; Borislav Petkov <[email protected]>; H Peter Anvin <[email protected]>; Moger, Babu <[email protected]>; James Morse <[email protected]>
Subject: [PATCH v3 09/10] x86/resctrl: Add arch_has_{sparse,empty}_bitmaps to explain CAT differences

Intel CPUs expect the cache bitmap provided by user-space to have on a single span of 1s, whereas AMD can support bitmaps like 0xf00f. Arm's MPAM support also allows sparse bitmaps.

Similarly, Intel CPUs check at least one bit set, whereas AMD CPUs are quite happy with an empty bitmap. Arm's MPAM allows an empty bitmap.

To move resctrl out to /fs/ we need to explain platform differences like this. Add two resource properties arch_has_{empty,sparse}_bitmaps. Test these around the relevant parts of cbm_validate().

Quoted 7 lines

Merging the validate calls causes AMD to gain the min_cbm_bits test needed for Haswell, but as it always sets this value to 1, it will never match.

CC Babu Moger <[email protected]>
CC Reinette Chatre <[email protected]>
Quoted 181 lines
---
 arch/x86/kernel/cpu/resctrl/core.c        | 14 ++++----
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 39 ++++++-----------------
 arch/x86/kernel/cpu/resctrl/internal.h    |  8 ++---
 3 files changed, 22 insertions(+), 39 deletions(-)
arch/x86/kernel/cpu/resctrl/core.c +8 -6
index 223e5b90bcfd..587f9791d2a6 100644
@@ -922,9 +922,10 @@ static __init void rdt_init_res_defs_intel(void)
 		    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->rid == RDT_RESOURCE_L2CODE) {
+			r->cache.arch_has_sparse_bitmaps = false;
+			r->cache.arch_has_empty_bitmaps = false;
+		} else if (r->rid == RDT_RESOURCE_MBA) {
 			r->msr_base = MSR_IA32_MBA_THRTL_BASE;
 			r->msr_update = mba_wrmsr_intel;
 		}
@@ -941,9 +942,10 @@ static __init void rdt_init_res_defs_amd(void)
 		    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->rid == RDT_RESOURCE_L2CODE) {
+			r->cache.arch_has_sparse_bitmaps = true;
+			r->cache.arch_has_empty_bitmaps = true;
+		} else if (r->rid == RDT_RESOURCE_MBA) {
 			r->msr_base = MSR_IA32_MBA_BW_BASE;
 			r->msr_update = mba_wrmsr_amd;
 		}
arch/x86/kernel/cpu/resctrl/ctrlmondata.c +4 -2
index b0e24cb6f85c..cc854bb369c9 100644
@@ -76,12 +76,14 @@ int parse_bw(struct rdt_parse_data *data, struct
 rdt_resource *r,
 }
 
 /*
- * Check whether a cache bit mask is valid. The SDM says:
+ * Check whether a cache bit mask is valid.
+ * For Intel the SDM says:
  *	Please note that all (and only) contiguous '1' combinations
  *	are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.).
  * Additionally Haswell requires at least two bits set.
+ * AMD allows non-contiguous bitmasks.
  */
-bool cbm_validate_intel(char *buf, u32 *data, struct rdt_resource *r)
+static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
 {
 	unsigned long first_bit, zero_bit, val;
arch/x86/kernel/cpu/resctrl/ctrlmondata.c +2 -1
 	unsigned int cbm_len = r->cache.cbm_len;
@@ -93,7 +95,8 @@ bool cbm_validate_intel(char *buf, u32 *data, struct
 rdt_resource *r)
 		return false;
 	}
 
-	if (val == 0 || val > r->default_ctrl) {
+	if ((!r->cache.arch_has_empty_bitmaps && val == 0) ||
+	    (val > r->default_ctrl)) {
 		rdt_last_cmd_puts("Mask out of range\n");
 		return false;
arch/x86/kernel/cpu/resctrl/ctrlmondata.c +3 -1
 	}
@@ -101,7 +104,9 @@ bool cbm_validate_intel(char *buf, u32 *data, struct
 rdt_resource *r)
 	first_bit = find_first_bit(&val, cbm_len);
 	zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
 
-	if (find_next_bit(&val, cbm_len, zero_bit) < cbm_len) {
+	/* Are non-contiguous bitmaps allowed? */
+	if (!r->cache.arch_has_sparse_bitmaps &&
+	    (find_next_bit(&val, cbm_len, zero_bit) < cbm_len)) {
 		rdt_last_cmd_printf("The mask %lx has non-consecutive 1-
 bits\n", val);
arch/x86/kernel/cpu/resctrl/ctrlmondata.c +0 -24
 		return false;
 	}
@@ -116,30 +121,6 @@ bool cbm_validate_intel(char *buf, u32 *data, struct
 rdt_resource *r)
 	return true;
 }
 
-/*
- * Check whether a cache bit mask is valid. AMD allows non-contiguous
- * bitmasks
- */
-bool cbm_validate_amd(char *buf, u32 *data, struct rdt_resource *r)
-{
-	unsigned long val;
-	int ret;
-
-	ret = kstrtoul(buf, 16, &val);
-	if (ret) {
-		rdt_last_cmd_printf("Non-hex character in the mask %s\n",
 buf);
-		return false;
-	}
-
-	if (val > r->default_ctrl) {
-		rdt_last_cmd_puts("Mask out of range\n");
-		return false;
-	}
-
-	*data = val;
-	return true;
-}
-
 /*

* Read one cache bit mask (hex). Check that it is valid for the current
* resource type.

arch/x86/kernel/cpu/resctrl/ctrlmondata.c +1 -1
@@ -165,7 +146,7 @@ int parse_cbm(struct rdt_parse_data *data, struct
 rdt_resource *r,
 		return -EINVAL;
 	}
 
-	if (!r->cbm_validate(data->buf, &cbm_val, r))
+	if (!cbm_validate(data->buf, &cbm_val, r))
 		return -EINVAL;
 
arch/x86/kernel/cpu/resctrl/ctrlmondata.c +0 -0
 	if ((rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
arch/x86/kernel/cpu/resctrl/internal.h +4 -0
index 5919aae946ba..35f8137c4dce 100644
@@ -357,6 +357,8 @@ struct msr_param {
  *			in a cache bit mask
  * @shareable_bits:	Bitmask of shareable resource with other
  *			executing entities
+ * @arch_has_sparse_bitmaps:	True if a bitmap like f00f is valid.
+ * @arch_has_empty_bitmaps:	True if the '0' bitmap is valid.
  */
 struct rdt_cache {
 	unsigned int	cbm_len;
@@ -364,6 +366,8 @@ struct rdt_cache {
 	unsigned int	cbm_idx_mult;
 	unsigned int	cbm_idx_offset;
 	unsigned int	shareable_bits;
+	bool		arch_has_sparse_bitmaps;
+	bool		arch_has_empty_bitmaps;
 };
 
 /**
@@ -433,7 +437,6 @@ 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
- * @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

arch/x86/kernel/cpu/resctrl/internal.h +0 -3
@@ -460,7 +463,6 @@ 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;
@@ -603,8 +605,6 @@ 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);
-bool cbm_validate_amd(char *buf, u32 *data, struct rdt_resource *r);
 void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
 

#endif /* _ASM_X86_RESCTRL_INTERNAL_H */
--
2.19.1

author reviewer
#15 lore raw

PATCH v3 10/10 cacheinfo: Move resctrl's get_cache_id() to the cacheinfo header file

In reply to James Morse

resctrl/core.c defines get_cache_id() for use in its cpu-hotplug callbacks. This gets the id attribute of the cache at the corresponding level of a cpu.

Later rework means this private function needs to be shared. Move it to the header file.

The name conflicts with a different definition in intel_cacheinfo.c, name it get_cpu_cacheinfo_id() to show its relation with get_cpu_cacheinfo().

Now this is visible on other architectures, check the id attribute has actually been set.

---
 arch/x86/kernel/cpu/resctrl/core.c | 17 ++---------------
 include/linux/cacheinfo.h          | 21 +++++++++++++++++++++
 2 files changed, 23 insertions(+), 15 deletions(-)
arch/x86/kernel/cpu/resctrl/core.c +2 -15
index 587f9791d2a6..3cc0fe435d19 100644
@@ -350,19 +350,6 @@ static void rdt_get_cdp_l2_config(void)
 	rdt_get_cdp_config(RDT_RESOURCE_L2, RDT_RESOURCE_L2CODE);
 }
 
-static int get_cache_id(int cpu, int level)
-{
-	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu);
-	int i;
-
-	for (i = 0; i < ci->num_leaves; i++) {
-		if (ci->info_list[i].level == level)
-			return ci->info_list[i].id;
-	}
-
-	return -1;
-}
-
 static void
 mba_wrmsr_amd(struct rdt_domain *d, struct msr_param *m, struct rdt_resource *r)
 {
@@ -560,7 +547,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d)
  */
 static void domain_add_cpu(int cpu, struct rdt_resource *r)
 {
-	int id = get_cache_id(cpu, r->cache_level);
+	int id = get_cpu_cacheinfo_id(cpu, r->cache_level);
 	struct list_head *add_pos = NULL;
 	struct rdt_domain *d;
 
@@ -606,7 +593,7 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r)
 
 static void domain_remove_cpu(int cpu, struct rdt_resource *r)
 {
-	int id = get_cache_id(cpu, r->cache_level);
+	int id = get_cpu_cacheinfo_id(cpu, r->cache_level);
 	struct rdt_domain *d;
 
 	d = rdt_find_domain(r, id, NULL);
include/linux/cacheinfo.h +21 -0
index 46b92cd61d0c..4f72b47973c3 100644
@@ -3,6 +3,7 @@
 #define _LINUX_CACHEINFO_H
 
 #include <linux/bitops.h>
+#include <linux/cpu.h>
 #include <linux/cpumask.h>
 #include <linux/smp.h>
 
@@ -119,4 +120,24 @@ int acpi_find_last_cache_level(unsigned int cpu);
 
 const struct attribute_group *cache_get_priv_group(struct cacheinfo *this_leaf);
 
+/*
+ * Get the id of the cache associated with @cpu at level @level.
+ * cpuhp lock must be held.
+ */
+static inline int get_cpu_cacheinfo_id(int cpu, int level)
+{
+	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu);
+	int i;
+
+	for (i = 0; i < ci->num_leaves; i++) {
+		if (ci->info_list[i].level == level) {
+			if (ci->info_list[i].attributes & CACHE_ID)
+				return ci->info_list[i].id;
+			return -1;
+		}
+	}
+
+	return -1;
+}
+
 #endif /* _LINUX_CACHEINFO_H */
Signature · 1 line
2.19.1