Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755345AbbESACG (ORCPT ); Mon, 18 May 2015 20:02:06 -0400 Received: from www.linutronix.de ([62.245.132.108]:51786 "EHLO Galois.linutronix.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755116AbbESAAr (ORCPT ); Mon, 18 May 2015 20:00:47 -0400 Message-Id: <20150518235150.240899319@linutronix.de> User-Agent: quilt/0.63-1 Date: Tue, 19 May 2015 00:00:58 -0000 From: Thomas Gleixner To: LKML Cc: Peter Zijlstra , Vikas Shivappa , x86@kernel.org, Matt Fleming , Will Auld , Kanaka Juvva Subject: [patch 6/6] x86, perf, cqm: Add storage for closid and cleanup struct intel_pqr_state References: <20150518234114.574556332@linutronix.de> MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-15 Content-Disposition: inline; filename=x86-perf-cqm-add-storage-for-closid.patch X-Linutronix-Spam-Score: -1.0 X-Linutronix-Spam-Level: - X-Linutronix-Spam-Status: No , -1.0 points, 5.0 required, ALL_TRUSTED=-1,SHORTCIRCUIT=-0.0001,URIBL_BLOCKED=0.001 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4544 Lines: 139 closid (CLass Of Service ID) is used for the Class based Cache Allocation Technology (CAT). Add explicit storage to the per cpu cache for it, so it can be used later with the CAT support (requires to move the per cpu data). While at it: - Rename the structure to intel_pqr_state which reflects the actual purpose of the struct: Cache values which go into the PQR MSR - Rename 'cnt' to rmid_usecnt which reflects the actual purpose of the counter. - Document the structure and the struct members. Signed-off-by: Thomas Gleixner --- arch/x86/kernel/cpu/perf_event_intel_cqm.c | 50 +++++++++++++++-------------- 1 file changed, 27 insertions(+), 23 deletions(-) Index: linux/arch/x86/kernel/cpu/perf_event_intel_cqm.c =================================================================== --- linux.orig/arch/x86/kernel/cpu/perf_event_intel_cqm.c +++ linux/arch/x86/kernel/cpu/perf_event_intel_cqm.c @@ -16,18 +16,32 @@ static unsigned int cqm_max_rmid = -1; static unsigned int cqm_l3_scale; /* supposedly cacheline size */ -struct intel_cqm_state { +/** + * struct intel_pqr_state - State cache for the PQR MSR + * @rmid: The cached Resource Monitoring ID + * @closid: The cached Class Of Service ID + * @usecnt: The usage counter for rmid + * + * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the + * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always + * contains both parts, so we need to cache them. + * + * The cache also helps to avoid pointless updates if the value does + * not change. + */ +struct intel_pqr_state { u32 rmid; - int cnt; + u32 closid; + int rmid_usecnt; }; /* - * The cached intel_cqm_state is strictly per cpu and can never be + * The cached intel_pqr_state is strictly per cpu and can never be * updated from a remote cpu. Both functions which modify the state * (intel_cqm_event_start and intel_cqm_event_stop) are called with * interrupts disabled, which is sufficient for the protection. */ -static DEFINE_PER_CPU(struct intel_cqm_state, cqm_state); +static DEFINE_PER_CPU(struct intel_pqr_state, pqr_state); /* * Protects cache_cgroups and cqm_rmid_free_lru and cqm_rmid_limbo_lru. @@ -966,7 +980,7 @@ out: static void intel_cqm_event_start(struct perf_event *event, int mode) { - struct intel_cqm_state *state = this_cpu_ptr(&cqm_state); + struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); u32 rmid = event->hw.cqm_rmid; if (!(event->hw.cqm_state & PERF_HES_STOPPED)) @@ -974,7 +988,7 @@ static void intel_cqm_event_start(struct event->hw.cqm_state &= ~PERF_HES_STOPPED; - if (state->cnt++) { + if (state->rmid_usecnt++) { if (!WARN_ON_ONCE(state->rmid != rmid)) return; } else { @@ -982,17 +996,12 @@ static void intel_cqm_event_start(struct } state->rmid = rmid; - /* - * This is actually wrong, as the upper 32 bit MSR contain the - * closid which is used for configuring the Cache Allocation - * Technology component. - */ - wrmsr(MSR_IA32_PQR_ASSOC, rmid, 0); + wrmsr(MSR_IA32_PQR_ASSOC, rmid, state->closid); } static void intel_cqm_event_stop(struct perf_event *event, int mode) { - struct intel_cqm_state *state = this_cpu_ptr(&cqm_state); + struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); if (event->hw.cqm_state & PERF_HES_STOPPED) return; @@ -1001,15 +1010,9 @@ static void intel_cqm_event_stop(struct intel_cqm_event_read(event); - if (!--state->cnt) { + if (!--state->rmid_usecnt) { state->rmid = 0; - /* - * This is actually wrong, as the upper 32 bit of the - * MSR contain the closid which is used for - * configuring the Cache Allocation Technology - * component. - */ - wrmsr(MSR_IA32_PQR_ASSOC, 0, 0); + wrmsr(MSR_IA32_PQR_ASSOC, 0, state->closid); } else { WARN_ON_ONCE(!state->rmid); } @@ -1247,11 +1250,12 @@ static inline void cqm_pick_event_reader static void intel_cqm_cpu_prepare(unsigned int cpu) { - struct intel_cqm_state *state = &per_cpu(cqm_state, cpu); + struct intel_pqr_state *state = &per_cpu(pqr_state, cpu); struct cpuinfo_x86 *c = &cpu_data(cpu); state->rmid = 0; - state->cnt = 0; + state->closid = 0; + state->rmid_usecnt = 0; WARN_ON(c->x86_cache_max_rmid != cqm_max_rmid); WARN_ON(c->x86_cache_occ_scale != cqm_l3_scale); -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/