arch: arm64: add early_param idle=<wfi|yield|nop>

Overriding the idle mechanism might be useful for debugging and performance
testing. Add a cmdline parameter for it, similar to the existing idle=
parameter already present for the x86 and ppc architectures.

It is also useful on platforms where the WFI instruction misbehaves,
such as Apple Silicon SoCs. Generally, a misbehaving instruction should
be treated as an erratum and patched using the alternatives framework.
However, in the Apple Silicon case we need more flexibility because it is
difficult to detect whether the erratum applies. For example, Linux VMs
inside macOS have the same MIDR and may even seem like they're running
in EL2 in the case of NV, but should continue using WFI (it's trapped and
handled correctly by the hypervisor there). Thus, we prefer to
let the m1n1 bootloader add the idle=nop parameter[1].

Link[1]: https://lore.kernel.org/all/99b69262-e54b-424e-baa2-96ef7013b87a@kernel.org/
Suggested-by: Will Deacon <will@kernel.org>
Signed-off-by: Yureka Lilian <yureka@cyberchaos.dev>
Signed-off-by: Will Deacon <will@kernel.org>

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index b5493a7f8f22812833308b22f2cc35b0a42e55b2..7e9cc49b90a9163951b573436d857a4ac9e2d605 100644 (file)
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2236,6 +2236,29 @@ Kernel parameters
 
                        idle=nomwait: Disable mwait for CPU C-states
 
+                       [ARM64,EARLY]
+                       Format: idle=wfi, idle=yield, idle=nop
+
+                       idle=wfi: Use the WFI (Wait For Interrupt) hint
+                       instruction in the idle loop. This is the default and
+                       allows the CPU to enter a low-power state until an
+                       interrupt arrives.
+
+                       idle=yield: Use the YIELD hint instruction instead of
+                       WFI. CPUs supporting simultaneous multi-threading (SMT),
+                       can continue executing another thread when the current
+                       thread reaches the idle loop. This will make the CPUs
+                       eat more power, but may be useful to get slightly better
+                       performance in some applications, since the CPUs will
+                       not enter a low-power state.
+
+                       idle=nop: Do not execute any idle instruction in the
+                       idle loop. This is useful on platforms where WFI
+                       misbehaves, leading to system instability or loss of CPU
+                       state. This will make the CPUs eat more power, but may
+                       give slightly better performance in some applications,
+                       since the CPUs will not enter a low-power state.
+
        idxd.sva=       [HW]
                        Format: <bool>
                        Allow force disabling of Shared Virtual Memory (SVA)

diff --git a/arch/arm64/kernel/idle.c b/arch/arm64/kernel/idle.c
index 05cfb347ec2679e262574e2763a7a79b47318f65..42c5543f9589c15d7a3a73992f3083f6fdba5007 100644 (file)
--- a/arch/arm64/kernel/idle.c
+++ b/arch/arm64/kernel/idle.c
@@ -11,6 +11,29 @@
 #include <asm/cpufeature.h>
 #include <asm/sysreg.h>
 
+enum {
+    ARM64_IDLE_WFI,
+    ARM64_IDLE_YIELD,
+    ARM64_IDLE_NOP,
+} idle = ARM64_IDLE_WFI;
+
+static int __init setup_idle(char *arg)
+{
+       if (!arg)
+               return -1;
+       else if (!strcmp(arg, "wfi"))
+               idle = ARM64_IDLE_WFI;
+       else if (!strcmp(arg, "yield"))
+               idle = ARM64_IDLE_YIELD;
+       else if (!strcmp(arg, "nop"))
+               idle = ARM64_IDLE_NOP;
+       else
+               return -1;
+
+       return 0;
+}
+early_param("idle", setup_idle);
+
 /*
  *     cpu_do_idle()
  *
@@ -26,8 +49,13 @@ void __cpuidle cpu_do_idle(void)
 
        arm_cpuidle_save_irq_context(&context);
 
-       dsb(sy);
-       wfi();
+       if (likely(idle == ARM64_IDLE_WFI)) {
+               dsb(sy);
+               wfi();
+       } else if (idle == ARM64_IDLE_YIELD) {
+               dsb(sy);
+               asm volatile("yield" ::: "memory");
+       }
 
        arm_cpuidle_restore_irq_context(&context);
 }