riscv: Idle thread using Zawrs extension
Subsystems (2)
v2 cover riscv: Idle thread using Zawrs extension
This is the second version of idle thread based on Zawrs extension. We rebased our code on Andrew's patch series[1] which provides basic support for Zawrs as well as optimization for spinlock.
This patch series introduces a new implementation of idle thread using Zawrs extension.
The Zawrs[0] extension introduces two new instructions named WRS.STO and WRS.NTO in RISC-V. When software registers a reservation set using LR instruction, a subsequent WRS.STO or WRS.NTO instruction will cause the hart to stall in a low-power state until a store happens to the reservation set or an interrupt becomes pending. The difference between these two instructions is that WRS.STO will terminate stall after an implementation-defined timeout while WRS.NTO won't.
This patch series implements idle thread using WRS.NTO instruction. Besides, we found there is no need to send a real IPI to wake up an idle CPU. Instead, we write IPI information to the reservation set of an idle CPU to wake it up and let it handle IPI quickly, without going through tranditional interrupt handling routine.
[0] https://github.com/riscv/riscv-zawrs/blob/main/zawrs.adoc
[1] https://github.com/jones-drew/linux/commits/riscv/zawrs-v3
Xu Lu (2):
riscv: process: Introduce idle thread using Zawrs extension
riscv: Use Zawrs to accelerate IPI to idle cpu
arch/riscv/Kconfig | 10 +++ arch/riscv/include/asm/cpuidle.h | 11 +--- arch/riscv/include/asm/processor.h | 32 +++++++++ arch/riscv/include/asm/smp.h | 14 ++++ arch/riscv/kernel/cpu.c | 5 ++ arch/riscv/kernel/process.c | 102 ++++++++++++++++++++++++++++- arch/riscv/kernel/smp.c | 39 +++++++---- 7 files changed, 190 insertions(+), 23 deletions(-)
Signature · 1 line
2.20.1
RFC v2 1/2 riscv: process: Introduce idle thread using Zawrs extension
The Zawrs extension introduces a new instruction WRS.NTO, which will register a reservation set and causes the hart to temporarily stall execution in a low-power state until a store occurs to the reservation set or an interrupt is observed.
This commit implements new version of idle thread for RISC-V via Zawrs extension.
--- arch/riscv/Kconfig | 10 ++++++++ arch/riscv/include/asm/cpuidle.h | 11 +------- arch/riscv/include/asm/processor.h | 18 +++++++++++++ arch/riscv/kernel/cpu.c | 5 ++++ arch/riscv/kernel/process.c | 41 +++++++++++++++++++++++++++++- 5 files changed, 74 insertions(+), 11 deletions(-)
arch/riscv/Kconfig +10 -0
@@ -19,6 +19,7 @@ config RISCV select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2 select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE select ARCH_HAS_BINFMT_FLAT + select ARCH_HAS_CPU_FINALIZE_INIT select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VIRTUAL if MMU select ARCH_HAS_DEBUG_VM_PGTABLE
@@ -1081,6 +1082,15 @@ endmenu # "Power management options" menu "CPU Power Management" +config RISCV_ZAWRS_IDLE + bool "Idle thread using ZAWRS extensions" + depends on RISCV_ISA_ZAWRS + default y + help + Adds support to implement idle thread using ZAWRS extension. + + If you don't know what to do here, say Y. + source "drivers/cpuidle/Kconfig" source "drivers/cpufreq/Kconfig"
arch/riscv/include/asm/cpuidle.h +1 -10
@@ -10,15 +10,6 @@#include <asm/barrier.h> #include <asm/processor.h> -static inline void cpu_do_idle (void ) -{ -/* -* Add mb() here to ensure that all -* IO/MEM accesses are completed prior -* to entering WFI. -*/ -mb (); -wait_for_interrupt (); -} +void cpu_do_idle (void );#endif
arch/riscv/include/asm/processor.h +18 -0
@@ -12,6 +12,7 @@#include <vdso/processor.h> +#include <asm/insn-def.h> #include <asm/ptrace.h> /*
@@ -157,6 +158,21 @@ static inline void wait_for_interrupt(void) __asm__ __volatile__ ("wfi" ); } +static inline void wrs_nto (unsigned long *addr) +{ +int val; + + __asm__ __volatile__( +#ifdef CONFIG_64BIT + "lr.d %[p], %[v]\n\t" +#else +"lr.w %[p], %[v]\n\t" +#endif +ZAWRS_WRS_NTO "\n\t" + : [p]"=&r" (val), [v]"+A" (*addr) + : :"memory" ); +} +extern phys_addr_t dma32_phys_limit;struct device_node ;
@@ -183,6 +199,8 @@ extern int set_unalign_ctl(struct task_struct *tsk, unsigned int val);#define GET_UNALIGN_CTL (tsk, addr) get_unalign_ctl((tsk), (addr))#define SET_UNALIGN_CTL (tsk, val) set_unalign_ctl((tsk), (val)) +extern void select_idle_routine (void ); +#endif /* __ASSEMBLY__ */ #endif /* _ASM_RISCV_PROCESSOR_H */
arch/riscv/kernel/cpu.c +5 -0
@@ -22,6 +22,11 @@ bool arch_match_cpu_phys_id(int cpu, u64 phys_id)return phys_id ==cpuid_to_hartid_map (cpu); } +void __init arch_cpu_finalize_init (void ) +{ +select_idle_routine (); +} +/* * Returns the hart ID of the given device tree node, or -ENODEV if the node * isn't an enabled and valid RISC-V hart node.
arch/riscv/kernel/process.c +40 -1
57 lines not on this page · raw message
Signature · 1 line
2.20.1
RFC v2 2/2 riscv: Use Zawrs to accelerate IPI to idle cpu
In reply to Xu LuWhen sending IPI to a cpu which has entered idle state using Zawrs extension, there is no need to send a physical software interrupt. Instead, we can write the IPI information to the address reserved by target cpu, which will wake it from WRS.NTO. Then the target cpu can handle the IPI directly without falling into traditional interrupt handling routine.
--- arch/riscv/include/asm/processor.h | 14 +++++++ arch/riscv/include/asm/smp.h | 14 +++++++ arch/riscv/kernel/process.c | 65 +++++++++++++++++++++++++++++- arch/riscv/kernel/smp.c | 39 ++++++++++++------ 4 files changed, 118 insertions(+), 14 deletions(-)
arch/riscv/include/asm/processor.h +14 -0
@@ -173,6 +173,20 @@ static inline void wrs_nto(unsigned long *addr) : : "memory"); } +static inline void wrs_nto_if (int *addr,int val) +{ +int prev; + + __asm__ __volatile__( +"lr.w %[p], %[a]\n\t" +"bne %[p], %[v], 1f\n\t" +ZAWRS_WRS_NTO "\n\t" +"1:\n\t" + : [p]"=&r" (prev), [a]"+A" (*addr) + : [v]"r" (val) + :"memory" ); +} +extern phys_addr_t dma32_phys_limit;struct device_node ;
arch/riscv/include/asm/smp.h +14 -0
@@ -19,6 +19,20 @@ extern unsigned long boot_cpu_hartid;#include <linux/jump_label.h> +enum ipi_message_type { +IPI_RESCHEDULE , +IPI_CALL_FUNC , +IPI_CPU_STOP , +IPI_CPU_CRASH_STOP , +IPI_IRQ_WORK , +IPI_TIMER , +IPI_MAX +}; + +int ipi_virq_base_get (void ); + +irqreturn_t handle_IPI (int irq,void *data); +/* * Mapping between linux logical cpu index and hartid. */
arch/riscv/kernel/process.c +63 -2
110 lines not on this page · raw message
arch/riscv/kernel/smp.c +27 -12
@@ -26,16 +26,6 @@#include <asm/cacheflush.h> #include <asm/cpu_ops.h> -enum ipi_message_type { -IPI_RESCHEDULE , -IPI_CALL_FUNC , -IPI_CPU_STOP , -IPI_CPU_CRASH_STOP , -IPI_IRQ_WORK , -IPI_TIMER , -IPI_MAX -}; -unsigned long __cpuid_to_hartid_map[NR_CPUS ]__ro_after_init = { [0 ...NR_CPUS -1 ] =INVALID_HARTID };
@@ -94,14 +84,34 @@ static inline void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs) }#endif +#if defined(CONFIG_RISCV_ZAWRS_IDLE ) && defined(CONFIG_SMP ) +DECLARE_PER_CPU (atomic_t, idle_ipi_mask); +#endif +static void send_ipi_mask (const struct cpumask *mask,enum ipi_message_type op) { +#if defined(CONFIG_RISCV_ZAWRS_IDLE ) && defined(CONFIG_SMP ) +int cpu, val; + +for_each_cpu (cpu, mask) { + val =atomic_fetch_or_relaxed (BIT (op),per_cpu_ptr (&idle_ipi_mask, cpu)); +if (likely (!(val &BIT (IPI_MAX )))) +__ipi_send_mask (ipi_desc[op],cpumask_of (cpu)); + } +#else __ipi_send_mask (ipi_desc[op], mask); +#endif }static void send_ipi_single (int cpu,enum ipi_message_type op) { -__ipi_send_mask (ipi_desc[op],cpumask_of (cpu)); +#if defined(CONFIG_RISCV_ZAWRS_IDLE ) && defined(CONFIG_SMP ) +int val; + + val =atomic_fetch_or_relaxed (BIT (op),per_cpu_ptr (&idle_ipi_mask, cpu)); + if (likely(!(val & BIT(IPI_MAX)))) +#endif +__ipi_send_mask (ipi_desc[op],cpumask_of (cpu)); }#ifdef CONFIG_IRQ_WORK
@@ -111,7 +121,7 @@ void arch_irq_work_raise(void) }#endif -static irqreturn_t handle_IPI (int irq,void *data) +irqreturn_t handle_IPI (int irq,void *data) {int ipi = irq - ipi_virq_base;
@@ -332,3 +342,8 @@ void arch_smp_send_reschedule(int cpu)send_ipi_single (cpu,IPI_RESCHEDULE ); }EXPORT_SYMBOL_GPL (arch_smp_send_reschedule); + +int ipi_virq_base_get (void ) +{ +return ipi_virq_base; +}
Signature · 1 line
2.20.1
v2 cover riscv: Idle thread using Zawrs extension
In reply to Xu LuQuoted 3 lines
This is the second version of idle thread based on Zawrs extension. We rebased our code on Andrew's patch series[1] which provides basic support for Zawrs as well as optimization for spinlock.
There's some feedback on Andrew's v2 [1] which seems to equally apply to the later, mentioned series/submission, and hence to the series in question (although only indirectly admittedly).
As an additional comment, please do add linux-kernel at vger.kernel.org (the LKML) to your Cc: list on patch submission (again, this applies to both Andrew's and the present submissions).
Andrea
[1] https://lore.kernel.org/linux-riscv/ZiWCP6f6zZ3dKXfN at andrea/
v2 cover riscv: Idle thread using Zawrs extension
Quoted 11 lines · Andrea Parri
Quoted 3 lines
This is the second version of idle thread based on Zawrs extension. We rebased our code on Andrew's patch series[1] which provides basic support for Zawrs as well as optimization for spinlock.
There's some feedback on Andrew's v2 [1] which seems to equally apply to the later, mentioned series/submission, and hence to the series in question (although only indirectly admittedly).
As an additional comment, please do add linux-kernel at vger.kernel.org (the LKML) to your Cc: list on patch submission (again, this applies to both Andrew's and the present submissions).
Ah, yes, and possibly people mentioned in the changelog! :-) + Andrew
Andrea
Quoted 9 lines · On Fri, Jun 21, 2024 at 7:17?PM Andrea Parri <[email protected]> wrote:
Quoted 4 lines
This is the second version of idle thread based on Zawrs extension. We rebased our code on Andrew's patch series[1] which provides basic support for Zawrs as well as optimization for spinlock.
There's some feedback on Andrew's v2 [1] which seems to equally apply to the later, mentioned series/submission, and hence to the series in question (although only indirectly admittedly).
Quoted 7 lines
As an additional comment, please do add linux-kernel at vger.kernel.org (the LKML) to your Cc: list on patch submission (again, this applies to both Andrew's and the present submissions).
Andrea
[1] https://lore.kernel.org/linux-riscv/ZiWCP6f6zZ3dKXfN at andrea/
Hi Andrea,
Thanks a lot for your reminder. I will check the feedback and add this email in the next patch series!
Xu Lu