linux-kernel - [PATCH v2] RISC-V: Probe misaligned access speed in parallel

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <20230920193801.3035093-1-evan@rivosinc.com>
Date:   Wed, 20 Sep 2023 12:38:01 -0700
From:   Evan Green <evan@...osinc.com>
To:     Palmer Dabbelt <palmer@...osinc.com>
Cc:     Jisheng Zhang <jszhang@...nel.org>,
        David Laight <David.Laight@...lab.com>,
        Evan Green <evan@...osinc.com>,
        Andrew Jones <ajones@...tanamicro.com>,
        Albert Ou <aou@...s.berkeley.edu>,
        Anup Patel <apatel@...tanamicro.com>,
        Conor Dooley <conor.dooley@...rochip.com>,
        Greentime Hu <greentime.hu@...ive.com>,
        Heiko Stuebner <heiko@...ech.de>,
        Marc Zyngier <maz@...nel.org>,
        Palmer Dabbelt <palmer@...belt.com>,
        Paul Walmsley <paul.walmsley@...ive.com>,
        Sunil V L <sunilvl@...tanamicro.com>,
        linux-kernel@...r.kernel.org, linux-riscv@...ts.infradead.org
Subject: [PATCH v2] RISC-V: Probe misaligned access speed in parallel

Probing for misaligned access speed takes about 0.06 seconds. On a
system with 64 cores, doing this in smp_callin() means it's done
serially, extending boot time by 3.8 seconds. That's a lot of boot time.

Instead of measuring each CPU serially, let's do the measurements on
all CPUs in parallel. If we disable preemption on all CPUs, the
jiffies stop ticking, so we can do this in stages of 1) everybody
except core 0, then 2) core 0.

The measurement call in smp_callin() stays around, but is now
conditionalized to only run if a new CPU shows up after the round of
in-parallel measurements has run. The goal is to have the measurement
call not run during boot or suspend/resume, but only on a hotplug
addition.

Reported-by: Jisheng Zhang <jszhang@...nel.org>
Closes: https://lore.kernel.org/all/mhng-9359993d-6872-4134-83ce-c97debe1cf9a@palmer-ri-x1c9/T/#mae9b8f40016f9df428829d33360144dc5026bcbf
Fixes: 584ea6564bca ("RISC-V: Probe for unaligned access speed")
Signed-off-by: Evan Green <evan@...osinc.com>
Reviewed-by: Andrew Jones <ajones@...tanamicro.com>
Tested-by: Andrew Jones <ajones@...tanamicro.com>

---

Changes in v2:
 - Removed new global, used system_state == SYSTEM_RUNNING instead
   (Jisheng)
 - Added tags

 arch/riscv/include/asm/cpufeature.h |  2 +-
 arch/riscv/kernel/cpufeature.c      | 22 +++++++++++++++++-----
 arch/riscv/kernel/smpboot.c         | 11 ++++++++++-
 3 files changed, 28 insertions(+), 7 deletions(-)

diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h
index d0345bd659c9..b139796392d0 100644
--- a/arch/riscv/include/asm/cpufeature.h
+++ b/arch/riscv/include/asm/cpufeature.h
@@ -30,6 +30,6 @@ DECLARE_PER_CPU(long, misaligned_access_speed);
 /* Per-cpu ISA extensions. */
 extern struct riscv_isainfo hart_isa[NR_CPUS];
 
-void check_unaligned_access(int cpu);
+int check_unaligned_access(void *unused);
 
 #endif
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 1cfbba65d11a..40bb854fcb96 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -556,8 +556,9 @@ unsigned long riscv_get_elf_hwcap(void)
 	return hwcap;
 }
 
-void check_unaligned_access(int cpu)
+int check_unaligned_access(void *unused)
 {
+	int cpu = smp_processor_id();
 	u64 start_cycles, end_cycles;
 	u64 word_cycles;
 	u64 byte_cycles;
@@ -571,7 +572,7 @@ void check_unaligned_access(int cpu)
 	page = alloc_pages(GFP_NOWAIT, get_order(MISALIGNED_BUFFER_SIZE));
 	if (!page) {
 		pr_warn("Can't alloc pages to measure memcpy performance");
-		return;
+		return 0;
 	}
 
 	/* Make an unaligned destination buffer. */
@@ -643,15 +644,26 @@ void check_unaligned_access(int cpu)
 
 out:
 	__free_pages(page, get_order(MISALIGNED_BUFFER_SIZE));
+	return 0;
+}
+
+static void check_unaligned_access_nonboot_cpu(void *param)
+{
+	if (smp_processor_id() != 0)
+		check_unaligned_access(param);
 }
 
-static int check_unaligned_access_boot_cpu(void)
+static int check_unaligned_access_all_cpus(void)
 {
-	check_unaligned_access(0);
+	/* Check everybody except 0, who stays behind to tend jiffies. */
+	on_each_cpu(check_unaligned_access_nonboot_cpu, NULL, 1);
+
+	/* Check core 0. */
+	smp_call_on_cpu(0, check_unaligned_access, NULL, true);
 	return 0;
 }
 
-arch_initcall(check_unaligned_access_boot_cpu);
+arch_initcall(check_unaligned_access_all_cpus);
 
 #ifdef CONFIG_RISCV_ALTERNATIVE
 /*
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index 1b8da4e40a4d..a014955b8699 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -27,6 +27,7 @@
 #include <linux/sched/mm.h>
 #include <asm/cpu_ops.h>
 #include <asm/cpufeature.h>
+#include <asm/hwprobe.h>
 #include <asm/irq.h>
 #include <asm/mmu_context.h>
 #include <asm/numa.h>
@@ -246,7 +247,15 @@ asmlinkage __visible void smp_callin(void)
 
 	numa_add_cpu(curr_cpuid);
 	set_cpu_online(curr_cpuid, 1);
-	check_unaligned_access(curr_cpuid);
+
+	/*
+	 * Boot-time misaligned access speed measurements are done in parallel
+	 * in an initcall. Only measure here for hotplug.
+	 */
+	if ((system_state == SYSTEM_RUNNING) &&
+	    (per_cpu(misaligned_access_speed, curr_cpuid) == RISCV_HWPROBE_MISALIGNED_UNKNOWN)) {
+		check_unaligned_access(NULL);
+	}
 
 	if (has_vector()) {
 		if (riscv_v_setup_vsize())
-- 
2.34.1