From b6c295df3131c6fa25f8f29625ee0609506150ad Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Sat, 28 Mar 2015 14:21:02 +1100 Subject: KVM: PPC: Book3S HV: Accumulate timing information for real-mode code This reads the timebase at various points in the real-mode guest entry/exit code and uses that to accumulate total, minimum and maximum time spent in those parts of the code. Currently these times are accumulated per vcpu in 5 parts of the code: * rm_entry - time taken from the start of kvmppc_hv_entry() until just before entering the guest. * rm_intr - time from when we take a hypervisor interrupt in the guest until we either re-enter the guest or decide to exit to the host. This includes time spent handling hcalls in real mode. * rm_exit - time from when we decide to exit the guest until the return from kvmppc_hv_entry(). * guest - time spend in the guest * cede - time spent napping in real mode due to an H_CEDE hcall while other threads in the same vcore are active. These times are exposed in debugfs in a directory per vcpu that contains a file called "timings". This file contains one line for each of the 5 timings above, with the name followed by a colon and 4 numbers, which are the count (number of times the code has been executed), the total time, the minimum time, and the maximum time, all in nanoseconds. The overhead of the extra code amounts to about 30ns for an hcall that is handled in real mode (e.g. H_SET_DABR), which is about 25%. Since production environments may not wish to incur this overhead, the new code is conditional on a new config symbol, CONFIG_KVM_BOOK3S_HV_EXIT_TIMING. Signed-off-by: Paul Mackerras Signed-off-by: Alexander Graf --- arch/powerpc/kernel/asm-offsets.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'arch/powerpc/kernel/asm-offsets.c') diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 4717859fdd04..3fea721f0da5 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -458,6 +458,19 @@ int main(void) DEFINE(VCPU_SPRG1, offsetof(struct kvm_vcpu, arch.shregs.sprg1)); DEFINE(VCPU_SPRG2, offsetof(struct kvm_vcpu, arch.shregs.sprg2)); DEFINE(VCPU_SPRG3, offsetof(struct kvm_vcpu, arch.shregs.sprg3)); +#endif +#ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING + DEFINE(VCPU_TB_RMENTRY, offsetof(struct kvm_vcpu, arch.rm_entry)); + DEFINE(VCPU_TB_RMINTR, offsetof(struct kvm_vcpu, arch.rm_intr)); + DEFINE(VCPU_TB_RMEXIT, offsetof(struct kvm_vcpu, arch.rm_exit)); + DEFINE(VCPU_TB_GUEST, offsetof(struct kvm_vcpu, arch.guest_time)); + DEFINE(VCPU_TB_CEDE, offsetof(struct kvm_vcpu, arch.cede_time)); + DEFINE(VCPU_CUR_ACTIVITY, offsetof(struct kvm_vcpu, arch.cur_activity)); + DEFINE(VCPU_ACTIVITY_START, offsetof(struct kvm_vcpu, arch.cur_tb_start)); + DEFINE(TAS_SEQCOUNT, offsetof(struct kvmhv_tb_accumulator, seqcount)); + DEFINE(TAS_TOTAL, offsetof(struct kvmhv_tb_accumulator, tb_total)); + DEFINE(TAS_MIN, offsetof(struct kvmhv_tb_accumulator, tb_min)); + DEFINE(TAS_MAX, offsetof(struct kvmhv_tb_accumulator, tb_max)); #endif DEFINE(VCPU_SHARED_SPRG3, offsetof(struct kvm_vcpu_arch_shared, sprg3)); DEFINE(VCPU_SHARED_SPRG4, offsetof(struct kvm_vcpu_arch_shared, sprg4)); -- cgit v1.2.3 From 1f09c3ed86287d40fef90611cbbee055313f52cf Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Sat, 28 Mar 2015 14:21:04 +1100 Subject: KVM: PPC: Book3S HV: Minor cleanups * Remove unused kvmppc_vcore::n_busy field. * Remove setting of RMOR, since it was only used on PPC970 and the PPC970 KVM support has been removed. * Don't use r1 or r2 in setting the runlatch since they are conventionally reserved for other things; use r0 instead. * Streamline the code a little and remove the ext_interrupt_to_host label. * Add some comments about register usage. * hcall_try_real_mode doesn't need to be global, and can't be called from C code anyway. Signed-off-by: Paul Mackerras Signed-off-by: Alexander Graf --- arch/powerpc/kernel/asm-offsets.c | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/powerpc/kernel/asm-offsets.c') diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 3fea721f0da5..92ec3fcb3415 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -505,7 +505,6 @@ int main(void) DEFINE(KVM_NEED_FLUSH, offsetof(struct kvm, arch.need_tlb_flush.bits)); DEFINE(KVM_ENABLED_HCALLS, offsetof(struct kvm, arch.enabled_hcalls)); DEFINE(KVM_LPCR, offsetof(struct kvm, arch.lpcr)); - DEFINE(KVM_RMOR, offsetof(struct kvm, arch.rmor)); DEFINE(KVM_VRMA_SLB_V, offsetof(struct kvm, arch.vrma_slb_v)); DEFINE(VCPU_DSISR, offsetof(struct kvm_vcpu, arch.shregs.dsisr)); DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar)); -- cgit v1.2.3 From 5d5b99cd6818bdbea287d23ef055bba1a8a9e648 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Sat, 28 Mar 2015 14:21:06 +1100 Subject: KVM: PPC: Book3S HV: Get rid of vcore nap_count and n_woken We can tell when a secondary thread has finished running a guest by the fact that it clears its kvm_hstate.kvm_vcpu pointer, so there is no real need for the nap_count field in the kvmppc_vcore struct. This changes kvmppc_wait_for_nap to poll the kvm_hstate.kvm_vcpu pointers of the secondary threads rather than polling vc->nap_count. Besides reducing the size of the kvmppc_vcore struct by 8 bytes, this also means that we can tell which secondary threads have got stuck and thus print a more informative error message. Signed-off-by: Paul Mackerras Signed-off-by: Alexander Graf --- arch/powerpc/kernel/asm-offsets.c | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/powerpc/kernel/asm-offsets.c') diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 92ec3fcb3415..8aa824681d76 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -563,7 +563,6 @@ int main(void) DEFINE(VCPU_WORT, offsetof(struct kvm_vcpu, arch.wort)); DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1)); DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_count)); - DEFINE(VCORE_NAP_COUNT, offsetof(struct kvmppc_vcore, nap_count)); DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest)); DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads)); DEFINE(VCORE_KVM, offsetof(struct kvmppc_vcore, kvm)); -- cgit v1.2.3 From 7d6c40da198ac18bd5dd2cd18628d5b4c615d842 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Sat, 28 Mar 2015 14:21:09 +1100 Subject: KVM: PPC: Book3S HV: Use bitmap of active threads rather than count Currently, the entry_exit_count field in the kvmppc_vcore struct contains two 8-bit counts, one of the threads that have started entering the guest, and one of the threads that have started exiting the guest. This changes it to an entry_exit_map field which contains two bitmaps of 8 bits each. The advantage of doing this is that it gives us a bitmap of which threads need to be signalled when exiting the guest. That means that we no longer need to use the trick of setting the HDEC to 0 to pull the other threads out of the guest, which led in some cases to a spurious HDEC interrupt on the next guest entry. Signed-off-by: Paul Mackerras Signed-off-by: Alexander Graf --- arch/powerpc/kernel/asm-offsets.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/powerpc/kernel/asm-offsets.c') diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 8aa824681d76..0d07efbe3fa7 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -562,7 +562,7 @@ int main(void) DEFINE(VCPU_ACOP, offsetof(struct kvm_vcpu, arch.acop)); DEFINE(VCPU_WORT, offsetof(struct kvm_vcpu, arch.wort)); DEFINE(VCPU_SHADOW_SRR1, offsetof(struct kvm_vcpu, arch.shadow_srr1)); - DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_count)); + DEFINE(VCORE_ENTRY_EXIT, offsetof(struct kvmppc_vcore, entry_exit_map)); DEFINE(VCORE_IN_GUEST, offsetof(struct kvmppc_vcore, in_guest)); DEFINE(VCORE_NAPPING_THREADS, offsetof(struct kvmppc_vcore, napping_threads)); DEFINE(VCORE_KVM, offsetof(struct kvmppc_vcore, kvm)); -- cgit v1.2.3 From 66feed61cdf6ee65fd551d3460b1efba6bee55b8 Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Sat, 28 Mar 2015 14:21:12 +1100 Subject: KVM: PPC: Book3S HV: Use msgsnd for signalling threads on POWER8 This uses msgsnd where possible for signalling other threads within the same core on POWER8 systems, rather than IPIs through the XICS interrupt controller. This includes waking secondary threads to run the guest, the interrupts generated by the virtual XICS, and the interrupts to bring the other threads out of the guest when exiting. Aggregated statistics from debugfs across vcpus for a guest with 32 vcpus, 8 threads/vcore, running on a POWER8, show this before the change: rm_entry: 3387.6ns (228 - 86600, 1008969 samples) rm_exit: 4561.5ns (12 - 3477452, 1009402 samples) rm_intr: 1660.0ns (12 - 553050, 3600051 samples) and this after the change: rm_entry: 3060.1ns (212 - 65138, 953873 samples) rm_exit: 4244.1ns (12 - 9693408, 954331 samples) rm_intr: 1342.3ns (12 - 1104718, 3405326 samples) for a test of booting Fedora 20 big-endian to the login prompt. The time taken for a H_PROD hcall (which is handled in the host kernel) went down from about 35 microseconds to about 16 microseconds with this change. The noinline added to kvmppc_run_core turned out to be necessary for good performance, at least with gcc 4.9.2 as packaged with Fedora 21 and a little-endian POWER8 host. Signed-off-by: Paul Mackerras Signed-off-by: Alexander Graf --- arch/powerpc/kernel/asm-offsets.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'arch/powerpc/kernel/asm-offsets.c') diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 0d07efbe3fa7..0034b6b3556a 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -37,6 +37,7 @@ #include #include #include +#include #ifdef CONFIG_PPC64 #include #include @@ -759,5 +760,7 @@ int main(void) offsetof(struct paca_struct, subcore_sibling_mask)); #endif + DEFINE(PPC_DBELL_SERVER, PPC_DBELL_SERVER); + return 0; } -- cgit v1.2.3