From 107c55005fbd5243ee31fb13b6f166cde9e3ade1 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Sun, 26 Jul 2020 13:51:55 +1000 Subject: [PATCH] powerpc/pseries: Add KVM guest doorbell restrictions MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit KVM guests have certain restrictions and performance quirks when using doorbells. This patch moves the EPAPR KVM guest test so it can be shared with PSERIES, and uses that in doorbell setup code to apply the KVM guest quirks and improves IPI performance for two cases: - PowerVM guests may now use doorbells even if they are secure. - KVM guests no longer use doorbells if XIVE is available. There is a valid complaint that "KVM guest" is not a very reasonable thing to test for, it's preferable for the hypervisor to advertise particular behaviours to the guest so they could change if the hypervisor implementation or configuration changes. However in this case we were already assuming a KVM guest worst case, so this patch is about containing those quirks. If KVM later advertises fast doorbells, we should test for that and override the quirks. Signed-off-by: Nicholas Piggin Tested-by: Cédric Le Goater Signed-off-by: Michael Ellerman Link: https://lore.kernel.org/r/20200726035155.1424103-4-npiggin@gmail.com --- arch/powerpc/include/asm/firmware.h | 6 +++++ arch/powerpc/include/asm/kvm_para.h | 26 +++---------------- arch/powerpc/kernel/Makefile | 5 ++-- arch/powerpc/kernel/firmware.c | 19 ++++++++++++++ arch/powerpc/platforms/pseries/smp.c | 38 +++++++++++++++++----------- 5 files changed, 53 insertions(+), 41 deletions(-) diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h index 6003c2e533a0..f67efbaba17f 100644 --- a/arch/powerpc/include/asm/firmware.h +++ b/arch/powerpc/include/asm/firmware.h @@ -132,6 +132,12 @@ extern int ibm_nmi_interlock_token; extern unsigned int __start___fw_ftr_fixup, __stop___fw_ftr_fixup; +#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_KVM_GUEST) +bool is_kvm_guest(void); +#else +static inline bool is_kvm_guest(void) { return false; } +#endif + #ifdef CONFIG_PPC_PSERIES void pseries_probe_fw_features(void); #else diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h index 9c1f6b4b9bbf..744612054c94 100644 --- a/arch/powerpc/include/asm/kvm_para.h +++ b/arch/powerpc/include/asm/kvm_para.h @@ -8,35 +8,15 @@ #ifndef __POWERPC_KVM_PARA_H__ #define __POWERPC_KVM_PARA_H__ +#include + #include -#ifdef CONFIG_KVM_GUEST - -#include - static inline int kvm_para_available(void) { - struct device_node *hyper_node; - - hyper_node = of_find_node_by_path("/hypervisor"); - if (!hyper_node) - return 0; - - if (!of_device_is_compatible(hyper_node, "linux,kvm")) - return 0; - - return 1; + return IS_ENABLED(CONFIG_KVM_GUEST) && is_kvm_guest(); } -#else - -static inline int kvm_para_available(void) -{ - return 0; -} - -#endif - static inline unsigned int kvm_arch_para_features(void) { unsigned long r; diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile index c5211bdcf1b6..d4d5946224f8 100644 --- a/arch/powerpc/kernel/Makefile +++ b/arch/powerpc/kernel/Makefile @@ -45,11 +45,10 @@ obj-y := cputable.o syscalls.o \ signal.o sysfs.o cacheinfo.o time.o \ prom.o traps.o setup-common.o \ udbg.o misc.o io.o misc_$(BITS).o \ - of_platform.o prom_parse.o + of_platform.o prom_parse.o firmware.o obj-y += ptrace/ obj-$(CONFIG_PPC64) += setup_64.o \ - paca.o nvram_64.o firmware.o note.o \ - syscall_64.o + paca.o nvram_64.o note.o syscall_64.o obj-$(CONFIG_COMPAT) += sys_ppc32.o signal_32.o obj-$(CONFIG_VDSO32) += vdso32/ obj-$(CONFIG_PPC_WATCHDOG) += watchdog.o diff --git a/arch/powerpc/kernel/firmware.c b/arch/powerpc/kernel/firmware.c index cc4a5e3f51f1..fe48d319d490 100644 --- a/arch/powerpc/kernel/firmware.c +++ b/arch/powerpc/kernel/firmware.c @@ -11,8 +11,27 @@ #include #include +#include #include +#ifdef CONFIG_PPC64 unsigned long powerpc_firmware_features __read_mostly; EXPORT_SYMBOL_GPL(powerpc_firmware_features); +#endif + +#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_KVM_GUEST) +bool is_kvm_guest(void) +{ + struct device_node *hyper_node; + + hyper_node = of_find_node_by_path("/hypervisor"); + if (!hyper_node) + return 0; + + if (!of_device_is_compatible(hyper_node, "linux,kvm")) + return 0; + + return 1; +} +#endif diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c index a1cb861154e9..92922491a81c 100644 --- a/arch/powerpc/platforms/pseries/smp.c +++ b/arch/powerpc/platforms/pseries/smp.c @@ -210,24 +210,32 @@ static __init void pSeries_smp_probe(void) if (!cpu_has_feature(CPU_FTR_SMT)) return; - /* - * KVM emulates doorbells by disabling FSCR[MSGP] so msgsndp faults - * to the hypervisor which then reads the instruction from guest - * memory. This can't be done if the guest is secure, so don't use - * doorbells in secure guests. - * - * Under PowerVM, FSCR[MSGP] is enabled so doorbells could be used - * by secure guests if we distinguished this from KVM. - */ - if (is_secure_guest()) - return; + if (is_kvm_guest()) { + /* + * KVM emulates doorbells by disabling FSCR[MSGP] so msgsndp + * faults to the hypervisor which then reads the instruction + * from guest memory, which tends to be slower than using XIVE. + */ + if (xive_enabled()) + return; + + /* + * XICS hcalls aren't as fast, so we can use msgsndp (which + * also helps exercise KVM emulation), however KVM can't + * emulate secure guests because it can't read the instruction + * out of their memory. + */ + if (is_secure_guest()) + return; + } /* - * The guest can use doobells for SMT sibling IPIs, which stay in - * the core rather than going to the interrupt controller. This - * tends to be slower under KVM where doorbells are emulated, but - * faster for PowerVM where they're enabled. + * Under PowerVM, FSCR[MSGP] is enabled as guest vCPU siblings are + * gang scheduled on the same physical core, so doorbells are always + * faster than the interrupt controller, and they can be used by + * secure guests. */ + ic_cause_ipi = smp_ops->cause_ipi; smp_ops->cause_ipi = dbell_or_ic_cause_ipi; }