From 456797da792fa7cbf6698febf275fe9b36691f78 Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Fri, 15 Jul 2022 18:51:55 +0100 Subject: [PATCH 01/10] arm64: topology: move store_cpu_topology() to shared code arm64's method of defining a default cpu topology requires only minimal changes to apply to RISC-V also. The current arm64 implementation exits early in a uniprocessor configuration by reading MPIDR & claiming that uniprocessor can rely on the default values. This is appears to be a hangover from prior to '3102bc0e6ac7 ("arm64: topology: Stop using MPIDR for topology information")', because the current code just assigns default values for multiprocessor systems. With the MPIDR references removed, store_cpu_topolgy() can be moved to the common arch_topology code. Reviewed-by: Sudeep Holla Acked-by: Catalin Marinas Reviewed-by: Atish Patra Signed-off-by: Conor Dooley --- arch/arm64/kernel/topology.c | 40 ------------------------------------ drivers/base/arch_topology.c | 19 +++++++++++++++++ 2 files changed, 19 insertions(+), 40 deletions(-) diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 869ffc4d4484..7889a00f5487 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -22,46 +22,6 @@ #include #include -void store_cpu_topology(unsigned int cpuid) -{ - struct cpu_topology *cpuid_topo = &cpu_topology[cpuid]; - u64 mpidr; - - if (cpuid_topo->package_id != -1) - goto topology_populated; - - mpidr = read_cpuid_mpidr(); - - /* Uniprocessor systems can rely on default topology values */ - if (mpidr & MPIDR_UP_BITMASK) - return; - - /* - * This would be the place to create cpu topology based on MPIDR. - * - * However, it cannot be trusted to depict the actual topology; some - * pieces of the architecture enforce an artificial cap on Aff0 values - * (e.g. GICv3's ICC_SGI1R_EL1 limits it to 15), leading to an - * artificial cycling of Aff1, Aff2 and Aff3 values. IOW, these end up - * having absolutely no relationship to the actual underlying system - * topology, and cannot be reasonably used as core / package ID. - * - * If the MT bit is set, Aff0 *could* be used to define a thread ID, but - * we still wouldn't be able to obtain a sane core ID. This means we - * need to entirely ignore MPIDR for any topology deduction. - */ - cpuid_topo->thread_id = -1; - cpuid_topo->core_id = cpuid; - cpuid_topo->package_id = cpu_to_node(cpuid); - - pr_debug("CPU%u: cluster %d core %d thread %d mpidr %#016llx\n", - cpuid, cpuid_topo->package_id, cpuid_topo->core_id, - cpuid_topo->thread_id, mpidr); - -topology_populated: - update_siblings_masks(cpuid); -} - #ifdef CONFIG_ACPI static bool __init acpi_cpu_is_threaded(int cpu) { diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 0424b59b695e..0e2c6b30dd69 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -841,4 +841,23 @@ void __init init_cpu_topology(void) return; } } + +void store_cpu_topology(unsigned int cpuid) +{ + struct cpu_topology *cpuid_topo = &cpu_topology[cpuid]; + + if (cpuid_topo->package_id != -1) + goto topology_populated; + + cpuid_topo->thread_id = -1; + cpuid_topo->core_id = cpuid; + cpuid_topo->package_id = cpu_to_node(cpuid); + + pr_debug("CPU%u: package %d core %d thread %d\n", + cpuid, cpuid_topo->package_id, cpuid_topo->core_id, + cpuid_topo->thread_id); + +topology_populated: + update_siblings_masks(cpuid); +} #endif From fbd92809997a391f28075f1c8b5ee314c225557c Mon Sep 17 00:00:00 2001 From: Conor Dooley Date: Fri, 15 Jul 2022 18:51:56 +0100 Subject: [PATCH 02/10] riscv: topology: fix default topology reporting RISC-V has no sane defaults to fall back on where there is no cpu-map in the devicetree. Without sane defaults, the package, core and thread IDs are all set to -1. This causes user-visible inaccuracies for tools like hwloc/lstopo which rely on the sysfs cpu topology files to detect a system's topology. On a PolarFire SoC, which should have 4 harts with a thread each, lstopo currently reports: Machine (793MB total) Package L#0 NUMANode L#0 (P#0 793MB) Core L#0 L1d L#0 (32KB) + L1i L#0 (32KB) + PU L#0 (P#0) L1d L#1 (32KB) + L1i L#1 (32KB) + PU L#1 (P#1) L1d L#2 (32KB) + L1i L#2 (32KB) + PU L#2 (P#2) L1d L#3 (32KB) + L1i L#3 (32KB) + PU L#3 (P#3) Adding calls to store_cpu_topology() in {boot,smp} hart bringup code results in the correct topolgy being reported: Machine (793MB total) Package L#0 NUMANode L#0 (P#0 793MB) L1d L#0 (32KB) + L1i L#0 (32KB) + Core L#0 + PU L#0 (P#0) L1d L#1 (32KB) + L1i L#1 (32KB) + Core L#1 + PU L#1 (P#1) L1d L#2 (32KB) + L1i L#2 (32KB) + Core L#2 + PU L#2 (P#2) L1d L#3 (32KB) + L1i L#3 (32KB) + Core L#3 + PU L#3 (P#3) CC: stable@vger.kernel.org # 456797da792f: arm64: topology: move store_cpu_topology() to shared code Fixes: 03f11f03dbfe ("RISC-V: Parse cpu topology during boot.") Reported-by: Brice Goglin Link: https://github.com/open-mpi/hwloc/issues/536 Reviewed-by: Sudeep Holla Reviewed-by: Atish Patra Signed-off-by: Conor Dooley --- arch/riscv/Kconfig | 2 +- arch/riscv/kernel/smpboot.c | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index ed66c31e4655..d557cc50295d 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -52,7 +52,7 @@ config RISCV select COMMON_CLK select CPU_PM if CPU_IDLE select EDAC_SUPPORT - select GENERIC_ARCH_TOPOLOGY if SMP + select GENERIC_ARCH_TOPOLOGY select GENERIC_ATOMIC64 if !64BIT select GENERIC_CLOCKEVENTS_BROADCAST if SMP select GENERIC_EARLY_IOREMAP diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c index a752c7b41683..3373df413c88 100644 --- a/arch/riscv/kernel/smpboot.c +++ b/arch/riscv/kernel/smpboot.c @@ -49,6 +49,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) unsigned int curr_cpuid; curr_cpuid = smp_processor_id(); + store_cpu_topology(curr_cpuid); numa_store_cpu_info(curr_cpuid); numa_add_cpu(curr_cpuid); @@ -162,9 +163,9 @@ asmlinkage __visible void smp_callin(void) mmgrab(mm); current->active_mm = mm; + store_cpu_topology(curr_cpuid); notify_cpu_starting(curr_cpuid); numa_add_cpu(curr_cpuid); - update_siblings_masks(curr_cpuid); set_cpu_online(curr_cpuid, 1); /* From 82c75dca6f95c9ac4649031a493456156ddfec2f Mon Sep 17 00:00:00 2001 From: Heinrich Schuchardt Date: Fri, 12 Aug 2022 22:08:53 +0200 Subject: [PATCH 03/10] riscv: enable CD-ROM file systems in defconfig CD-ROM images are still commonly used for installer images and other data exchange. These file systems should be supported on RISC-V by default like they are on x86_64. Signed-off-by: Heinrich Schuchardt Link: https://lore.kernel.org/r/20220812200853.311474-1-heinrich.schuchardt@canonical.com Signed-off-by: Palmer Dabbelt --- arch/riscv/configs/defconfig | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig index aed332a9d4ea..05fd5fcf24f9 100644 --- a/arch/riscv/configs/defconfig +++ b/arch/riscv/configs/defconfig @@ -166,6 +166,9 @@ CONFIG_BTRFS_FS=m CONFIG_BTRFS_FS_POSIX_ACL=y CONFIG_AUTOFS4_FS=y CONFIG_OVERLAY_FS=m +CONFIG_ISO9660_FS=y +CONFIG_JOLIET=y +CONFIG_ZISOFS=y CONFIG_MSDOS_FS=y CONFIG_VFAT_FS=y CONFIG_TMPFS=y From 1537bf26e212ffcf007d0590958025f6bfdd4ac8 Mon Sep 17 00:00:00 2001 From: Sergey Matyukevich Date: Tue, 30 Aug 2022 18:53:05 +0300 Subject: [PATCH 04/10] perf: RISC-V: exclude invalid pmu counters from SBI calls SBI firmware may not provide information for some counters in response to SBI_EXT_PMU_COUNTER_GET_INFO call. Exclude such counters from the subsequent SBI requests. For this purpose use global mask to keep track of fully specified counters. Signed-off-by: Sergey Matyukevich Reviewed-by: Atish Patra Link: https://lore.kernel.org/r/20220830155306.301714-3-geomatsi@gmail.com Signed-off-by: Palmer Dabbelt --- drivers/perf/riscv_pmu_legacy.c | 4 ++-- drivers/perf/riscv_pmu_sbi.c | 27 ++++++++++++++++----------- include/linux/perf/riscv_pmu.h | 2 +- 3 files changed, 19 insertions(+), 14 deletions(-) diff --git a/drivers/perf/riscv_pmu_legacy.c b/drivers/perf/riscv_pmu_legacy.c index 342778782359..7d7131c47bc0 100644 --- a/drivers/perf/riscv_pmu_legacy.c +++ b/drivers/perf/riscv_pmu_legacy.c @@ -14,7 +14,6 @@ #define RISCV_PMU_LEGACY_CYCLE 0 #define RISCV_PMU_LEGACY_INSTRET 1 -#define RISCV_PMU_LEGACY_NUM_CTR 2 static bool pmu_init_done; @@ -83,7 +82,8 @@ static void pmu_legacy_init(struct riscv_pmu *pmu) { pr_info("Legacy PMU implementation is available\n"); - pmu->num_counters = RISCV_PMU_LEGACY_NUM_CTR; + pmu->cmask = BIT(RISCV_PMU_LEGACY_CYCLE) | + BIT(RISCV_PMU_LEGACY_INSTRET); pmu->ctr_start = pmu_legacy_ctr_start; pmu->ctr_stop = NULL; pmu->event_map = pmu_legacy_event_map; diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 6f6681bbfd36..1d05aff88c58 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -271,7 +271,6 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event) struct sbiret ret; int idx; uint64_t cbase = 0; - uint64_t cmask = GENMASK_ULL(rvpmu->num_counters - 1, 0); unsigned long cflags = 0; if (event->attr.exclude_kernel) @@ -281,11 +280,12 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event) /* retrieve the available counter index */ #if defined(CONFIG_32BIT) - ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, cmask, - cflags, hwc->event_base, hwc->config, hwc->config >> 32); + ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, + rvpmu->cmask, cflags, hwc->event_base, hwc->config, + hwc->config >> 32); #else - ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, cmask, - cflags, hwc->event_base, hwc->config, 0); + ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_CFG_MATCH, cbase, + rvpmu->cmask, cflags, hwc->event_base, hwc->config, 0); #endif if (ret.error) { pr_debug("Not able to find a counter for event %lx config %llx\n", @@ -294,7 +294,7 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event) } idx = ret.value; - if (idx >= rvpmu->num_counters || !pmu_ctr_list[idx].value) + if (!test_bit(idx, &rvpmu->cmask) || !pmu_ctr_list[idx].value) return -ENOENT; /* Additional sanity check for the counter id */ @@ -463,7 +463,7 @@ static int pmu_sbi_find_num_ctrs(void) return sbi_err_map_linux_errno(ret.error); } -static int pmu_sbi_get_ctrinfo(int nctr) +static int pmu_sbi_get_ctrinfo(int nctr, unsigned long *mask) { struct sbiret ret; int i, num_hw_ctr = 0, num_fw_ctr = 0; @@ -478,6 +478,9 @@ static int pmu_sbi_get_ctrinfo(int nctr) if (ret.error) /* The logical counter ids are not expected to be contiguous */ continue; + + *mask |= BIT(i); + cinfo.value = ret.value; if (cinfo.type == SBI_PMU_CTR_TYPE_FW) num_fw_ctr++; @@ -498,7 +501,7 @@ static inline void pmu_sbi_stop_all(struct riscv_pmu *pmu) * which may include counters that are not enabled yet. */ sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, - 0, GENMASK_ULL(pmu->num_counters - 1, 0), 0, 0, 0, 0); + 0, pmu->cmask, 0, 0, 0, 0); } static inline void pmu_sbi_stop_hw_ctrs(struct riscv_pmu *pmu) @@ -788,8 +791,9 @@ static void riscv_pmu_destroy(struct riscv_pmu *pmu) static int pmu_sbi_device_probe(struct platform_device *pdev) { struct riscv_pmu *pmu = NULL; - int num_counters; + unsigned long cmask = 0; int ret = -ENODEV; + int num_counters; pr_info("SBI PMU extension is available\n"); pmu = riscv_pmu_alloc(); @@ -803,7 +807,7 @@ static int pmu_sbi_device_probe(struct platform_device *pdev) } /* cache all the information about counters now */ - if (pmu_sbi_get_ctrinfo(num_counters)) + if (pmu_sbi_get_ctrinfo(num_counters, &cmask)) goto out_free; ret = pmu_sbi_setup_irqs(pmu, pdev); @@ -812,8 +816,9 @@ static int pmu_sbi_device_probe(struct platform_device *pdev) pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT; pmu->pmu.capabilities |= PERF_PMU_CAP_NO_EXCLUDE; } + pmu->pmu.attr_groups = riscv_pmu_attr_groups; - pmu->num_counters = num_counters; + pmu->cmask = cmask; pmu->ctr_start = pmu_sbi_ctr_start; pmu->ctr_stop = pmu_sbi_ctr_stop; pmu->event_map = pmu_sbi_event_map; diff --git a/include/linux/perf/riscv_pmu.h b/include/linux/perf/riscv_pmu.h index bf66fe011fa8..e17e86ad6f3a 100644 --- a/include/linux/perf/riscv_pmu.h +++ b/include/linux/perf/riscv_pmu.h @@ -45,7 +45,7 @@ struct riscv_pmu { irqreturn_t (*handle_irq)(int irq_num, void *dev); - int num_counters; + unsigned long cmask; u64 (*ctr_read)(struct perf_event *event); int (*ctr_get_idx)(struct perf_event *event); int (*ctr_get_width)(int idx); From 096b52fd2bb4996fd68d22b3b7ad21a1296db9d3 Mon Sep 17 00:00:00 2001 From: Sergey Matyukevich Date: Tue, 30 Aug 2022 18:53:06 +0300 Subject: [PATCH 05/10] perf: RISC-V: throttle perf events Call perf_sample_event_took() to report time spent in overflow interrupts. Perf core uses these measurements to throttle perf events properly. Signed-off-by: Sergey Matyukevich Reviewed-by: Atish Patra Link: https://lore.kernel.org/r/20220830155306.301714-4-geomatsi@gmail.com Signed-off-by: Palmer Dabbelt --- drivers/perf/riscv_pmu_sbi.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 1d05aff88c58..3e8179359933 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -18,6 +18,7 @@ #include #include #include +#include #include #include @@ -570,6 +571,7 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev) unsigned long overflow; unsigned long overflowed_ctrs = 0; struct cpu_hw_events *cpu_hw_evt = dev; + u64 start_clock = sched_clock(); if (WARN_ON_ONCE(!cpu_hw_evt)) return IRQ_NONE; @@ -638,7 +640,9 @@ static irqreturn_t pmu_sbi_ovf_handler(int irq, void *dev) perf_event_overflow(event, &data, regs); } } + pmu_sbi_start_overflow_mask(pmu, overflowed_ctrs); + perf_sample_event_took(sched_clock() - start_clock); return IRQ_HANDLED; } From cfadbb9df8c4dc917787da4458327e5ec14743d4 Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Mon, 18 Jul 2022 14:15:53 +0530 Subject: [PATCH 06/10] cpuidle: riscv-sbi: Fix CPU_PM_CPU_IDLE_ENTER_xyz() macro usage Currently, we are using CPU_PM_CPU_IDLE_ENTER_PARAM() for all SBI HSM suspend types so retentive suspend types are also treated non-retentive and kernel will do redundant additional work for these states. The BIT[31] of SBI HSM suspend types allows us to differentiate between retentive and non-retentive suspend types so we should use this BIT to call appropriate CPU_PM_CPU_IDLE_ENTER_xyz() macro. Fixes: 6abf32f1d9c5 ("cpuidle: Add RISC-V SBI CPU idle driver") Signed-off-by: Anup Patel Link: https://lore.kernel.org/r/20220718084553.2056169-1-apatel@ventanamicro.com/ Reviewed-by: Andrew Jones Signed-off-by: Palmer Dabbelt --- drivers/cpuidle/cpuidle-riscv-sbi.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/cpuidle/cpuidle-riscv-sbi.c b/drivers/cpuidle/cpuidle-riscv-sbi.c index 862a2876f1c9..05fe2902df9a 100644 --- a/drivers/cpuidle/cpuidle-riscv-sbi.c +++ b/drivers/cpuidle/cpuidle-riscv-sbi.c @@ -97,8 +97,13 @@ static int sbi_cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, int idx) { u32 *states = __this_cpu_read(sbi_cpuidle_data.states); + u32 state = states[idx]; - return CPU_PM_CPU_IDLE_ENTER_PARAM(sbi_suspend, idx, states[idx]); + if (state & SBI_HSM_SUSP_NON_RET_BIT) + return CPU_PM_CPU_IDLE_ENTER_PARAM(sbi_suspend, idx, state); + else + return CPU_PM_CPU_IDLE_ENTER_RETENTION_PARAM(sbi_suspend, + idx, state); } static int __sbi_enter_domain_idle_state(struct cpuidle_device *dev, From e623715f3d67ad10985b2c10cf7edd9ad85db372 Mon Sep 17 00:00:00 2001 From: Anup Patel Date: Wed, 20 Apr 2022 16:54:08 +0530 Subject: [PATCH 07/10] RISC-V: Increase range and default value of NR_CPUS Currently, the range and default value of NR_CPUS is too restrictive for high-end RISC-V systems with large number of HARTs. The latest QEMU virt machine supports upto 512 CPUs so the current NR_CPUS is restrictive for QEMU as well. Other major architectures (such as ARM64, x86_64, MIPS, etc) have a much higher range and default value of NR_CPUS. This patch increases NR_CPUS range to 2-512 and default value to XLEN (i.e. 32 for RV32 and 64 for RV64). Signed-off-by: Anup Patel Reviewed-by: Heinrich Schuchardt Link: https://lore.kernel.org/r/20220420112408.155561-1-apatel@ventanamicro.com/ Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index d557cc50295d..f06ce10a589b 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -309,10 +309,13 @@ config SMP If you don't know what to do here, say N. config NR_CPUS - int "Maximum number of CPUs (2-32)" - range 2 32 + int "Maximum number of CPUs (2-512)" depends on SMP - default "8" + range 2 512 if !SBI_V01 + range 2 32 if SBI_V01 && 32BIT + range 2 64 if SBI_V01 && 64BIT + default "32" if 32BIT + default "64" if 64BIT config HOTPLUG_CPU bool "Support for hot-pluggable CPUs" From 542d353e25520e7db11d2cdb31d19c50ed921812 Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Sun, 21 Aug 2022 22:18:19 +0800 Subject: [PATCH 08/10] riscv: compat: s/failed/unsupported if compat mode isn't supported When compat mode isn't supported(I believe this is the most case now), kernel will emit somthing as: [ 0.050407] riscv: ELF compat mode failed This msg may make users think there's something wrong with the kernel itself, replace "failed" with "unsupported" to make it clear. In fact this is the real compat_mode_supported meaning. After the patch, the msg would be: [ 0.050407] riscv: ELF compat mode unsupported Signed-off-by: Jisheng Zhang Acked-by: Guo Ren Link: https://lore.kernel.org/r/20220821141819.3804-1-jszhang@kernel.org/ Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/process.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c index ceb9ebab6558..b0c63e8e867e 100644 --- a/arch/riscv/kernel/process.c +++ b/arch/riscv/kernel/process.c @@ -105,7 +105,7 @@ static int __init compat_mode_detect(void) csr_write(CSR_STATUS, tmp); pr_info("riscv: ELF compat mode %s", - compat_mode_supported ? "supported" : "failed"); + compat_mode_supported ? "supported" : "unsupported"); return 0; } From 61a41d16ad20657f93613229a8b17766c51dc849 Mon Sep 17 00:00:00 2001 From: Palmer Dabbelt Date: Tue, 20 Sep 2022 13:45:18 -0700 Subject: [PATCH 09/10] RISC-V: Print SSTC in canonical order This got out of order during a merge conflict, fix it by putting the entries in the correct order. Fixes: 7ab52f75a9cf ("RISC-V: Add Sstc extension support") Signed-off-by: Palmer Dabbelt Reviewed-by: Conor Dooley Reviewed-by: Heiko Stuebner Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220920204518.10988-1-palmer@rivosinc.com/ Signed-off-by: Palmer Dabbelt --- arch/riscv/kernel/cpu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c index 0be8a2403212..87455d12970f 100644 --- a/arch/riscv/kernel/cpu.c +++ b/arch/riscv/kernel/cpu.c @@ -92,10 +92,10 @@ int riscv_of_parent_hartid(struct device_node *node, unsigned long *hartid) */ static struct riscv_isa_ext_data isa_ext_arr[] = { __RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF), + __RISCV_ISA_EXT_DATA(sstc, RISCV_ISA_EXT_SSTC), __RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT), __RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM), __RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE), - __RISCV_ISA_EXT_DATA(sstc, RISCV_ISA_EXT_SSTC), __RISCV_ISA_EXT_DATA("", RISCV_ISA_EXT_MAX), }; From 87f81e66e2e84c7e6056413703d732a99c20c09b Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Mon, 29 Aug 2022 22:57:42 +0800 Subject: [PATCH 10/10] riscv: enable THP_SWAP for RV64 I have a Sipeed Lichee RV dock board which only has 512MB DDR, so memory optimizations such as swap on zram are helpful. As is seen in commit d0637c505f8a ("arm64: enable THP_SWAP for arm64") and commit bd4c82c22c367e ("mm, THP, swap: delay splitting THP after swapped out"), THP_SWAP can improve the swap throughput significantly. Enable THP_SWAP for RV64, testing the micro-benchmark which is introduced by commit d0637c505f8a ("arm64: enable THP_SWAP for arm64") shows below numbers on the Lichee RV dock board: swp out bandwidth w/o patch: 66908 bytes/ms (mean of 10 tests) swp out bandwidth w/ patch: 322638 bytes/ms (mean of 10 tests) Improved by 382%! Signed-off-by: Jisheng Zhang Reviewed-by: Andrew Jones Reviewed-by: Conor Dooley Link: https://lore.kernel.org/r/20220829145742.3139-1-jszhang@kernel.org/ Signed-off-by: Palmer Dabbelt --- arch/riscv/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index f06ce10a589b..0dd2595e3505 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -45,6 +45,7 @@ config RISCV select ARCH_WANT_FRAME_POINTERS select ARCH_WANT_GENERAL_HUGETLB select ARCH_WANT_HUGE_PMD_SHARE if 64BIT + select ARCH_WANTS_THP_SWAP if HAVE_ARCH_TRANSPARENT_HUGEPAGE select BINFMT_FLAT_NO_DATA_START_OFFSET if !MMU select BUILDTIME_TABLE_SORT if MMU select CLONE_BACKWARDS