Generic Linux architectural discussions
 help / color / mirror / Atom feed
From: Will Deacon <will@kernel.org>
To: Marc Zyngier <maz@kernel.org>
Cc: Quentin Perret <qperret@google.com>,
	linux-arm-kernel@lists.infradead.org, linux-arch@vger.kernel.org,
	linux-kernel@vger.kernel.org,
	Catalin Marinas <catalin.marinas@arm.com>,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Morten Rasmussen <morten.rasmussen@arm.com>,
	Qais Yousef <qais.yousef@arm.com>,
	Suren Baghdasaryan <surenb@google.com>, Tejun Heo <tj@kernel.org>,
	Li Zefan <lizefan@huawei.com>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Ingo Molnar <mingo@redhat.com>,
	Juri Lelli <juri.lelli@redhat.com>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	kernel-team@android.com
Subject: Re: [PATCH v4 03/14] KVM: arm64: Kill 32-bit vCPUs on systems with mismatched EL0 support
Date: Wed, 2 Dec 2020 17:27:27 +0000	[thread overview]
Message-ID: <20201202172727.GC29813@willie-the-truck> (raw)
In-Reply-To: <5e59a8f5bc84403ce2c8f26aa874cb1b@kernel.org>

On Wed, Dec 02, 2020 at 08:18:03AM +0000, Marc Zyngier wrote:
> On 2020-12-01 16:57, Will Deacon wrote:
> > On Fri, Nov 27, 2020 at 06:16:35PM +0000, Marc Zyngier wrote:
> > > On 2020-11-27 17:24, Quentin Perret wrote:
> > > > On Friday 27 Nov 2020 at 17:14:11 (+0000), Marc Zyngier wrote:
> > > 
> > > [...]
> > > 
> > > > > Yeah, the sanitized read feels better, if only because that is
> > > > > what we are going to read in all the valid cases, unfortunately.
> > > > > read_sanitised_ftr_reg() is sadly not designed to be called on
> > > > > a fast path, meaning that 32bit guests will do a bsearch() on
> > > > > the ID-regs every time they exit...
> > > > >
> > > > > I guess we will have to evaluate how much we loose with this.
> > > >
> > > > Could we use the trick we have for arm64_ftr_reg_ctrel0 to speed this
> > > > up?
> > > 
> > > Maybe. I want to first verify whether this has any measurable impact.
> > > Another possibility would be to cache the last
> > > read_sanitised_ftr_reg()
> > > access, just to see if that helps. There shouldn't be that many code
> > > paths hammering it.
> > 
> > We don't have huge numbers of ID registers, so the bsearch shouldn't be
> > too expensive. However, I'd like to remind myself why we can't index
> > into
> > the feature register array directly as we _should_ know all of this
> > stuff
> > at compile time, right?
> 
> Simply because it's not indexed by ID reg. It's just an ordered collection,
> similar to the for sys_reg emulation in KVM. You can compute the index
> ahead of time, but just not at compile time. At least not with the
> way the arm64_ftr_regs array is built.

FWIW, if your testing shows that the bsearch() is costing us, I've hacked
up an interface to access the ID registers directly (see below) which I
can include with this series.

Will

--->8

diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index da250e4741bd..23766104d756 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -599,7 +599,49 @@ static inline bool id_aa64pfr0_sve(u64 pfr0)
 void __init setup_cpu_features(void);
 void check_local_cpu_capabilities(void);
 
+#define ARM64_FTR_REG2IDX(id)	id ## _IDX
+enum arm64_ftr_reg_idx {
+	ARM64_FTR_REG2IDX(SYS_ID_PFR0_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_PFR1_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_DFR0_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_MMFR0_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_MMFR1_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_MMFR2_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_MMFR3_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_ISAR0_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_ISAR1_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_ISAR2_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_ISAR3_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_ISAR4_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_ISAR5_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_MMFR4_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_ISAR6_EL1),
+	ARM64_FTR_REG2IDX(SYS_MVFR0_EL1),
+	ARM64_FTR_REG2IDX(SYS_MVFR1_EL1),
+	ARM64_FTR_REG2IDX(SYS_MVFR2_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_PFR2_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_DFR1_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_MMFR5_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_AA64PFR0_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_AA64PFR1_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_AA64ZFR0_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_AA64DFR0_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_AA64DFR1_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_AA64ISAR0_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_AA64ISAR1_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_AA64MMFR0_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_AA64MMFR1_EL1),
+	ARM64_FTR_REG2IDX(SYS_ID_AA64MMFR2_EL1),
+	ARM64_FTR_REG2IDX(SYS_ZCR_EL1),
+	ARM64_FTR_REG2IDX(SYS_CTR_EL0),
+	ARM64_FTR_REG2IDX(SYS_DCZID_EL0),
+	ARM64_FTR_REG2IDX(SYS_CNTFRQ_EL0),
+
+	ARM64_FTR_REG_IDX_MAX,
+};
+
 u64 read_sanitised_ftr_reg(u32 id);
+u64 read_sanitised_ftr_reg_by_idx(enum arm64_ftr_reg_idx idx);
 
 static inline bool cpu_supports_mixed_endian_el0(void)
 {
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 6f36c4f62f69..05223352db5d 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -546,16 +546,18 @@ static const struct arm64_ftr_bits ftr_raz[] = {
 	ARM64_FTR_END,
 };
 
-#define ARM64_FTR_REG(id, table) {		\
-	.sys_id = id,				\
-	.reg = 	&(struct arm64_ftr_reg){	\
-		.name = #id,			\
-		.ftr_bits = &((table)[0]),	\
-	}}
+#define ARM64_FTR_REG(id, table)					\
+	[id ## _IDX] = {							\
+		.sys_id = id,						\
+		.reg	= &(struct arm64_ftr_reg) {			\
+			.name		= #id,				\
+			.ftr_bits	= &((table)[0]),		\
+		}							\
+	}
 
 static const struct __ftr_reg_entry {
 	u32			sys_id;
-	struct arm64_ftr_reg 	*reg;
+	struct arm64_ftr_reg	*reg;
 } arm64_ftr_regs[] = {
 
 	/* Op1 = 0, CRn = 0, CRm = 1 */
@@ -607,7 +609,7 @@ static const struct __ftr_reg_entry {
 	ARM64_FTR_REG(SYS_ZCR_EL1, ftr_zcr),
 
 	/* Op1 = 3, CRn = 0, CRm = 0 */
-	{ SYS_CTR_EL0, &arm64_ftr_reg_ctrel0 },
+	[ARM64_FTR_REG2IDX(SYS_CTR_EL0)] = { SYS_CTR_EL0, &arm64_ftr_reg_ctrel0 },
 	ARM64_FTR_REG(SYS_DCZID_EL0, ftr_dczid),
 
 	/* Op1 = 3, CRn = 14, CRm = 0 */
@@ -1116,6 +1118,18 @@ u64 read_sanitised_ftr_reg(u32 id)
 }
 EXPORT_SYMBOL_GPL(read_sanitised_ftr_reg);
 
+u64 read_sanitised_ftr_reg_by_idx(enum arm64_ftr_reg_idx idx)
+{
+	struct arm64_ftr_reg *regp;
+
+	if (WARN_ON((unsigned)idx >= ARM64_FTR_REG_IDX_MAX))
+		return 0;
+
+	regp = arm64_ftr_regs[idx].reg;
+	return regp->sys_val;
+}
+EXPORT_SYMBOL_GPL(read_sanitised_ftr_reg_by_idx);
+
 #define read_sysreg_case(r)	\
 	case r:		return read_sysreg_s(r)
 
-- 
2.29.2.576.ga3fc446d84-goog


  reply	other threads:[~2020-12-02 17:28 UTC|newest]

Thread overview: 61+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-11-24 15:50 [PATCH v4 00/14] An alternative series for asymmetric AArch32 systems Will Deacon
2020-11-24 15:50 ` [PATCH v4 01/14] arm64: cpuinfo: Split AArch32 registers out into a separate struct Will Deacon
2020-11-24 15:50 ` [PATCH v4 02/14] arm64: Allow mismatched 32-bit EL0 support Will Deacon
2020-11-27 10:25   ` Marc Zyngier
2020-11-27 11:50     ` Will Deacon
2020-11-27 13:09   ` Qais Yousef
2020-12-01 16:56     ` Will Deacon
2020-12-02 13:16       ` Qais Yousef
2020-11-24 15:50 ` [PATCH v4 03/14] KVM: arm64: Kill 32-bit vCPUs on systems with mismatched " Will Deacon
2020-11-27 10:26   ` Marc Zyngier
2020-11-27 11:53     ` Will Deacon
2020-11-27 17:14       ` Marc Zyngier
2020-11-27 17:24         ` Quentin Perret
2020-11-27 18:16           ` Marc Zyngier
2020-12-01 16:57             ` Will Deacon
2020-12-02  8:18               ` Marc Zyngier
2020-12-02 17:27                 ` Will Deacon [this message]
2020-11-24 15:50 ` [PATCH v4 04/14] arm64: Kill 32-bit applications scheduled on 64-bit-only CPUs Will Deacon
2020-11-27 13:12   ` Qais Yousef
2020-12-01 16:56     ` Will Deacon
2020-12-02 13:52       ` Qais Yousef
2020-12-02 17:42         ` Will Deacon
2020-11-24 15:50 ` [PATCH v4 05/14] arm64: Advertise CPUs capable of running 32-bit applications in sysfs Will Deacon
2020-11-24 15:50 ` [PATCH v4 06/14] arm64: Hook up cmdline parameter to allow mismatched 32-bit EL0 Will Deacon
2020-11-27 13:17   ` Qais Yousef
2020-12-01 16:56     ` Will Deacon
2020-11-24 15:50 ` [PATCH v4 07/14] sched: Introduce restrict_cpus_allowed_ptr() to limit task CPU affinity Will Deacon
2020-11-27  9:49   ` Quentin Perret
2020-11-27 13:19   ` Qais Yousef
2020-12-01 16:56     ` Will Deacon
2020-12-02 13:06       ` Qais Yousef
2020-11-24 15:50 ` [PATCH v4 08/14] arm64: exec: Adjust affinity for compat tasks with mismatched 32-bit EL0 Will Deacon
2020-11-27 10:01   ` Quentin Perret
2020-11-27 13:23   ` Qais Yousef
2020-12-01 16:55     ` Will Deacon
2020-12-02 14:07       ` Qais Yousef
2020-11-24 15:50 ` [PATCH v4 09/14] cpuset: Don't use the cpu_possible_mask as a last resort for cgroup v1 Will Deacon
2020-11-27 13:32   ` Qais Yousef
2020-11-30 17:05     ` Qais Yousef
2020-11-30 17:36       ` Quentin Perret
2020-12-01 11:58         ` Qais Yousef
2020-12-01 12:37           ` Quentin Perret
2020-12-01 14:11             ` Qais Yousef
2020-12-01 15:56               ` Quentin Perret
2020-12-01 22:30                 ` Will Deacon
2020-12-02 11:34                   ` Qais Yousef
2020-12-02 11:33                 ` Qais Yousef
2020-11-24 15:50 ` [PATCH v4 10/14] sched: Introduce arch_task_cpu_possible_mask() to limit fallback rq selection Will Deacon
2020-11-24 15:50 ` [PATCH v4 11/14] sched: Reject CPU affinity changes based on arch_task_cpu_possible_mask() Will Deacon
2020-11-27  9:54   ` Quentin Perret
2020-11-24 15:50 ` [PATCH v4 12/14] arm64: Prevent offlining first CPU with 32-bit EL0 on mismatched system Will Deacon
2020-11-27 13:41   ` Qais Yousef
2020-12-01 22:13     ` Will Deacon
2020-12-02 12:59       ` Qais Yousef
2020-12-02 17:42         ` Will Deacon
2020-12-02 18:08           ` Qais Yousef
2020-11-24 15:50 ` [PATCH v4 13/14] arm64: Implement arch_task_cpu_possible_mask() Will Deacon
2020-11-27 13:41   ` Qais Yousef
2020-11-24 15:50 ` [PATCH v4 14/14] arm64: Remove logic to kill 32-bit tasks on 64-bit-only cores Will Deacon
2020-11-27 13:58 ` [PATCH v4 00/14] An alternative series for asymmetric AArch32 systems Qais Yousef
2020-12-05 20:43 ` Pavel Machek

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=20201202172727.GC29813@willie-the-truck \
    --to=will@kernel.org \
    --cc=catalin.marinas@arm.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=hannes@cmpxchg.org \
    --cc=juri.lelli@redhat.com \
    --cc=kernel-team@android.com \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lizefan@huawei.com \
    --cc=maz@kernel.org \
    --cc=mingo@redhat.com \
    --cc=morten.rasmussen@arm.com \
    --cc=peterz@infradead.org \
    --cc=qais.yousef@arm.com \
    --cc=qperret@google.com \
    --cc=surenb@google.com \
    --cc=tj@kernel.org \
    --cc=vincent.guittot@linaro.org \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox