qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Richard Henderson <richard.henderson@linaro.org>
To: qemu-devel@nongnu.org
Cc: qemu-arm@nongnu.org, Peter Maydell <peter.maydell@linaro.org>
Subject: [PULL 16/20] target/arm: Implement FEAT_PMUv3p5 cycle counter disable bits
Date: Wed, 14 Sep 2022 12:52:13 +0100	[thread overview]
Message-ID: <20220914115217.117532-18-richard.henderson@linaro.org> (raw)
In-Reply-To: <20220914115217.117532-1-richard.henderson@linaro.org>

From: Peter Maydell <peter.maydell@linaro.org>

FEAT_PMUv3p5 introduces new bits which disable the cycle
counter from counting:
 * MDCR_EL2.HCCD disables the counter when in EL2
 * MDCR_EL3.SCCD disables the counter when Secure

Add the code to support these bits.

(Note that there is a third documented counter-disable
bit, MDCR_EL3.MCCD, which disables the counter when in
EL3. This is not present until FEAT_PMUv3p7, so is
out of scope for now.)

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20220822132358.3524971-9-peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/cpu.h    | 20 ++++++++++++++++++++
 target/arm/helper.c | 21 +++++++++++++++++----
 2 files changed, 37 insertions(+), 4 deletions(-)

diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index d86e51992a..41e74df104 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -1334,6 +1334,8 @@ FIELD(CPTR_EL3, TTA, 20, 1)
 FIELD(CPTR_EL3, TAM, 30, 1)
 FIELD(CPTR_EL3, TCPAC, 31, 1)
 
+#define MDCR_SCCD     (1U << 23)  /* MDCR_EL3 */
+#define MDCR_HCCD     (1U << 23)  /* MDCR_EL2 */
 #define MDCR_EPMAD    (1U << 21)
 #define MDCR_EDAD     (1U << 20)
 #define MDCR_SPME     (1U << 17)  /* MDCR_EL3 */
@@ -3726,6 +3728,13 @@ static inline bool isar_feature_aa32_pmuv3p4(const ARMISARegisters *id)
         FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) != 0xf;
 }
 
+static inline bool isar_feature_aa32_pmuv3p5(const ARMISARegisters *id)
+{
+    /* 0xf means "non-standard IMPDEF PMU" */
+    return FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) >= 6 &&
+        FIELD_EX32(id->id_dfr0, ID_DFR0, PERFMON) != 0xf;
+}
+
 static inline bool isar_feature_aa32_hpd(const ARMISARegisters *id)
 {
     return FIELD_EX32(id->id_mmfr4, ID_MMFR4, HPDS) != 0;
@@ -4050,6 +4059,12 @@ static inline bool isar_feature_aa64_pmuv3p4(const ARMISARegisters *id)
         FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) != 0xf;
 }
 
+static inline bool isar_feature_aa64_pmuv3p5(const ARMISARegisters *id)
+{
+    return FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) >= 6 &&
+        FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) != 0xf;
+}
+
 static inline bool isar_feature_aa64_rcpc_8_3(const ARMISARegisters *id)
 {
     return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) != 0;
@@ -4223,6 +4238,11 @@ static inline bool isar_feature_any_pmuv3p4(const ARMISARegisters *id)
     return isar_feature_aa64_pmuv3p4(id) || isar_feature_aa32_pmuv3p4(id);
 }
 
+static inline bool isar_feature_any_pmuv3p5(const ARMISARegisters *id)
+{
+    return isar_feature_aa64_pmuv3p5(id) || isar_feature_aa32_pmuv3p5(id);
+}
+
 static inline bool isar_feature_any_ccidx(const ARMISARegisters *id)
 {
     return isar_feature_aa64_ccidx(id) || isar_feature_aa32_ccidx(id);
diff --git a/target/arm/helper.c b/target/arm/helper.c
index 987ac19fe8..0d1f23de09 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -1084,8 +1084,8 @@ static CPAccessResult pmreg_access_ccntr(CPUARMState *env,
  * We use these to decide whether we need to wrap a write to MDCR_EL2
  * or MDCR_EL3 in pmu_op_start()/pmu_op_finish() calls.
  */
-#define MDCR_EL2_PMU_ENABLE_BITS (MDCR_HPME | MDCR_HPMD | MDCR_HPMN)
-#define MDCR_EL3_PMU_ENABLE_BITS (MDCR_SPME)
+#define MDCR_EL2_PMU_ENABLE_BITS (MDCR_HPME | MDCR_HPMD | MDCR_HPMN | MDCR_HCCD)
+#define MDCR_EL3_PMU_ENABLE_BITS (MDCR_SPME | MDCR_SCCD)
 
 /* Returns true if the counter (pass 31 for PMCCNTR) should count events using
  * the current EL, security state, and register configuration.
@@ -1120,8 +1120,21 @@ static bool pmu_counter_enabled(CPUARMState *env, uint8_t counter)
         prohibited = prohibited || !(env->cp15.mdcr_el3 & MDCR_SPME);
     }
 
-    if (prohibited && counter == 31) {
-        prohibited = env->cp15.c9_pmcr & PMCRDP;
+    if (counter == 31) {
+        /*
+         * The cycle counter defaults to running. PMCR.DP says "disable
+         * the cycle counter when event counting is prohibited".
+         * Some MDCR bits disable the cycle counter specifically.
+         */
+        prohibited = prohibited && env->cp15.c9_pmcr & PMCRDP;
+        if (cpu_isar_feature(any_pmuv3p5, env_archcpu(env))) {
+            if (secure) {
+                prohibited = prohibited || (env->cp15.mdcr_el3 & MDCR_SCCD);
+            }
+            if (el == 2) {
+                prohibited = prohibited || (mdcr_el2 & MDCR_HCCD);
+            }
+        }
     }
 
     if (counter == 31) {
-- 
2.34.1



  parent reply	other threads:[~2022-09-14 12:42 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-09-14 11:51 [PULL 00/20] target-arm.next patch queue Richard Henderson
2022-09-14 11:51 ` [PULL 01/20] target/arm: Add cortex-a35 Richard Henderson
2022-09-14 11:51 ` [PATCH] target/arm: Do alignment check when translation disabled Richard Henderson
2022-09-22 15:31   ` Peter Maydell
2022-09-28 15:52     ` Richard Henderson
2022-09-14 11:51 ` [PULL 02/20] hw/arm/bcm2835_property: Add support for RPI_FIRMWARE_FRAMEBUFFER_GET_NUM_DISPLAYS Richard Henderson
2022-09-14 11:52 ` [PULL 03/20] target/arm: Make cpregs 0, c0, c{3-15}, {0-7} correctly RAZ in v8 Richard Henderson
2022-09-14 11:52 ` [PULL 04/20] target/arm: Sort KVM reads of AArch32 ID registers into encoding order Richard Henderson
2022-09-14 11:52 ` [PULL 05/20] target/arm: Implement ID_MMFR5 Richard Henderson
2022-09-14 11:52 ` [PULL 06/20] target/arm: Implement ID_DFR1 Richard Henderson
2022-09-14 11:52 ` [PULL 07/20] target/arm: Advertise FEAT_ETS for '-cpu max' Richard Henderson
2022-09-14 11:52 ` [PULL 08/20] target/arm: Add missing space in comment Richard Henderson
2022-09-14 11:52 ` [PULL 09/20] target/arm: Don't corrupt high half of PMOVSR when cycle counter overflows Richard Henderson
2022-09-14 11:52 ` [PULL 10/20] target/arm: Correct value returned by pmu_counter_mask() Richard Henderson
2022-09-14 11:52 ` [PULL 11/20] target/arm: Don't mishandle count when enabling or disabling PMU counters Richard Henderson
2022-09-20 16:45   ` Thomas Huth
2022-09-23 10:50     ` Peter Maydell
2022-09-14 11:52 ` [PULL 12/20] target/arm: Ignore PMCR.D when PMCR.LC is set Richard Henderson
2022-09-14 11:52 ` [PULL 13/20] target/arm: Honour MDCR_EL2.HPMD in Secure EL2 Richard Henderson
2022-09-14 11:52 ` [PULL 14/20] target/arm: Detect overflow when calculating next PMU interrupt Richard Henderson
2022-09-14 11:52 ` [PULL 15/20] target/arm: Rename pmu_8_n feature test functions Richard Henderson
2022-09-14 11:52 ` Richard Henderson [this message]
2022-09-14 11:52 ` [PULL 17/20] target/arm: Support 64-bit event counters for FEAT_PMUv3p5 Richard Henderson
2022-09-14 11:52 ` [PULL 18/20] target/arm: Report FEAT_PMUv3p5 for TCG '-cpu max' Richard Henderson
2022-09-14 11:52 ` [PULL 19/20] target/arm: Remove useless TARGET_BIG_ENDIAN check in armv7m_load_kernel() Richard Henderson
2022-09-14 11:52 ` [PULL 20/20] target/arm: Make boards pass base address to armv7m_load_kernel() Richard Henderson
2022-09-17 20:13 ` [PULL 00/20] target-arm.next patch queue Stefan Hajnoczi
2022-09-20 13:06   ` Peter Maydell

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220914115217.117532-18-richard.henderson@linaro.org \
    --to=richard.henderson@linaro.org \
    --cc=peter.maydell@linaro.org \
    --cc=qemu-arm@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).