FEAT_TRF is a Coresight feature that allows trace capture to be completely filtered at different exception levels, unlike the existing TRCVICTLR controls which may still emit target addresses of branches, even if the following trace is filtered.
Without FEAT_TRF, it was possible to start a trace session on a host and also collect trace from the guest as TRCVICTLR was never programmed to exclude guests (and it could still emit target addresses even if it was). Now when FEAT_TRF is present, because we don't write to TRFCR_EL1, guest trace will be completely disabled.
This change fixes this issue, and also adds the ability to control it with the Perf exclude_host and exclude_guest flags.
The first commit moves the register to sysreg because I add the EL12 version in the second commit.
The test results have some single spurious EL2 addresses, but I don't think this is an issue with this patchset because it happens in the host-userspace case which maintains the existing programming of TRFCR. It's likely an issue with the model but I will follow it up separately.
The corresponding change for nVHE is here [1]. The nVHE behaviour is is reversed, currently guest trace is always generated because the host already writes to TRFCR_EL1. This is the same both with and without FEAT_TRF.
[1]: https://lore.kernel.org/kvmarm/20230804101317.460697-1-james.clark@arm.com/
---
Changes since v2:
* E0TRE -> E0HTRE in TRFCR_EL2 to match Arm ARM * Add missing USE_TRFCR_EL1_TS enum value
Changes since v1:
* Split new sysreg definitions into TRFCR_EL2 and TRFCR_ELx so that TRFCR_ELx doesn't include CX which TRFCR_EL1 doesn't have. * Mask out TS and CX before writing to TRFCR_EL1 because it doesn't have CX and TS has no effect. * Expand cover letter
James Clark (2): arm64/sysreg: Move TRFCR definitions to sysreg coresight: Allow guests to be traced when FEAT_TRF and VHE are present
arch/arm64/include/asm/sysreg.h | 12 ----- arch/arm64/tools/sysreg | 41 +++++++++++++++ .../coresight/coresight-etm4x-core.c | 51 ++++++++++++++++--- drivers/hwtracing/coresight/coresight-etm4x.h | 2 +- drivers/hwtracing/coresight/coresight-priv.h | 3 ++ 5 files changed, 90 insertions(+), 19 deletions(-)
Add separate definitions for ELx and EL2 as TRFCR_EL1 doesn't have CX. This also mirrors the previous definition so no code change is required.
Signed-off-by: James Clark james.clark@arm.com --- arch/arm64/include/asm/sysreg.h | 12 ----------- arch/arm64/tools/sysreg | 37 +++++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+), 12 deletions(-)
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index b481935e9314..fc9a5a09fa04 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -171,8 +171,6 @@ #define SYS_RGSR_EL1 sys_reg(3, 0, 1, 0, 5) #define SYS_GCR_EL1 sys_reg(3, 0, 1, 0, 6)
-#define SYS_TRFCR_EL1 sys_reg(3, 0, 1, 2, 1) - #define SYS_TCR_EL1 sys_reg(3, 0, 2, 0, 2)
#define SYS_APIAKEYLO_EL1 sys_reg(3, 0, 2, 1, 0) @@ -382,7 +380,6 @@ #define SYS_VTTBR_EL2 sys_reg(3, 4, 2, 1, 0) #define SYS_VTCR_EL2 sys_reg(3, 4, 2, 1, 2)
-#define SYS_TRFCR_EL2 sys_reg(3, 4, 1, 2, 1) #define SYS_HDFGRTR_EL2 sys_reg(3, 4, 3, 1, 4) #define SYS_HDFGWTR_EL2 sys_reg(3, 4, 3, 1, 5) #define SYS_HAFGRTR_EL2 sys_reg(3, 4, 3, 1, 6) @@ -640,15 +637,6 @@ /* Safe value for MPIDR_EL1: Bit31:RES1, Bit30:U:0, Bit24:MT:0 */ #define SYS_MPIDR_SAFE_VAL (BIT(31))
-#define TRFCR_ELx_TS_SHIFT 5 -#define TRFCR_ELx_TS_MASK ((0x3UL) << TRFCR_ELx_TS_SHIFT) -#define TRFCR_ELx_TS_VIRTUAL ((0x1UL) << TRFCR_ELx_TS_SHIFT) -#define TRFCR_ELx_TS_GUEST_PHYSICAL ((0x2UL) << TRFCR_ELx_TS_SHIFT) -#define TRFCR_ELx_TS_PHYSICAL ((0x3UL) << TRFCR_ELx_TS_SHIFT) -#define TRFCR_EL2_CX BIT(3) -#define TRFCR_ELx_ExTRE BIT(1) -#define TRFCR_ELx_E0TRE BIT(0) - /* GIC Hypervisor interface registers */ /* ICH_MISR_EL2 bit definitions */ #define ICH_MISR_EOI (1 << 0) diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 65866bf819c3..757d41db0aed 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -2495,3 +2495,40 @@ Field 5 F Field 4 P Field 3:0 Align EndSysreg + +SysregFields TRFCR_EL2 +Res0 63:7 +UnsignedEnum 6:5 TS + 0b0000 USE_TRFCR_EL1_TS + 0b0001 VIRTUAL + 0b0010 GUEST_PHYSICAL + 0b0011 PHYSICAL +EndEnum +Res0 4 +Field 3 CX +Res0 2 +Field 1 E2TRE +Field 0 E0HTRE +EndSysregFields + +# TRFCR_EL1 doesn't have the CX bit so redefine it without CX instead of +# using a shared definition between TRFCR_EL2 and TRFCR_EL1 +SysregFields TRFCR_ELx +Res0 63:7 +UnsignedEnum 6:5 TS + 0b0001 VIRTUAL + 0b0010 GUEST_PHYSICAL + 0b0011 PHYSICAL +EndEnum +Res0 4:2 +Field 1 ExTRE +Field 0 E0TRE +EndSysregFields + +Sysreg TRFCR_EL1 3 0 1 2 1 +Fields TRFCR_ELx +EndSysreg + +Sysreg TRFCR_EL2 3 4 1 2 1 +Fields TRFCR_EL2 +EndSysreg
Currently the userspace and kernel filters for guests are never set, so no trace will be generated for them. Add it by writing to the guest filters when exclude_guest isn't set. By writing either E1TRE or E0TRE, filtering on either guest kernel or guest userspace is also supported.
Since TRFCR_EL1 access is trapped, this can't be modified by the guest.
This change also brings exclude_host support which is difficult to add as a separate commit without excess churn and resulting in no trace at all.
Testing =======
The addresses were counted with the following:
$ perf report -D | grep -Eo 'EL2|EL1|EL0' | sort | uniq -c
Guest kernel only:
$ perf record -e cs_etm//Gk -a -- true 535 EL1 1 EL2
Guest user only (0 addresses expected because the guest OS hasn't reached userspace yet):
$ perf record -e cs_etm//Gu -a -- true
Host kernel only:
$ perf record -e cs_etm//Hk -a -- true 3501 EL2
Host userspace only:
$ perf record -e cs_etm//Hu -a -- true 408 EL0 1 EL2
Reviewed-by: Mark Brown broonie@kernel.org (sysreg) Signed-off-by: James Clark james.clark@arm.com --- arch/arm64/tools/sysreg | 4 ++ .../coresight/coresight-etm4x-core.c | 51 ++++++++++++++++--- drivers/hwtracing/coresight/coresight-etm4x.h | 2 +- drivers/hwtracing/coresight/coresight-priv.h | 3 ++ 4 files changed, 53 insertions(+), 7 deletions(-)
diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 757d41db0aed..6a3aab04192f 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -2532,3 +2532,7 @@ EndSysreg Sysreg TRFCR_EL2 3 4 1 2 1 Fields TRFCR_EL2 EndSysreg + +Sysreg TRFCR_EL12 3 5 1 2 1 +Fields TRFCR_ELx +EndSysreg diff --git a/drivers/hwtracing/coresight/coresight-etm4x-core.c b/drivers/hwtracing/coresight/coresight-etm4x-core.c index 77b0271ce6eb..6c16a14d6fbe 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x-core.c +++ b/drivers/hwtracing/coresight/coresight-etm4x-core.c @@ -274,6 +274,18 @@ static void etm4x_prohibit_trace(struct etmv4_drvdata *drvdata) cpu_prohibit_trace(); }
+static u64 etm4x_get_kern_user_filter(struct etmv4_drvdata *drvdata) +{ + u64 trfcr = drvdata->trfcr; + + if (drvdata->config.mode & ETM_MODE_EXCL_KERN) + trfcr &= ~TRFCR_ELx_ExTRE; + if (drvdata->config.mode & ETM_MODE_EXCL_USER) + trfcr &= ~TRFCR_ELx_E0TRE; + + return trfcr; +} + /* * etm4x_allow_trace - Allow CPU tracing in the respective ELs, * as configured by the drvdata->config.mode for the current @@ -286,18 +298,39 @@ static void etm4x_prohibit_trace(struct etmv4_drvdata *drvdata) */ static void etm4x_allow_trace(struct etmv4_drvdata *drvdata) { - u64 trfcr = drvdata->trfcr; + u64 trfcr;
/* If the CPU doesn't support FEAT_TRF, nothing to do */ - if (!trfcr) + if (!drvdata->trfcr) return;
- if (drvdata->config.mode & ETM_MODE_EXCL_KERN) - trfcr &= ~TRFCR_ELx_ExTRE; - if (drvdata->config.mode & ETM_MODE_EXCL_USER) - trfcr &= ~TRFCR_ELx_E0TRE; + if (drvdata->config.mode & ETM_MODE_EXCL_HOST) + trfcr = drvdata->trfcr & ~(TRFCR_ELx_ExTRE | TRFCR_ELx_E0TRE); + else + trfcr = etm4x_get_kern_user_filter(drvdata);
write_trfcr(trfcr); + + /* + * Filters for EL1 and EL0 (when running a guest) are stored in + * TRFCR_EL1 so write it there for VHE. For nVHE, the filters in + * have to be re-applied when switching to the guest instead. + */ + if (!is_kernel_in_hyp_mode()) + return; + + if (drvdata->config.mode & ETM_MODE_EXCL_GUEST) + trfcr = drvdata->trfcr & ~(TRFCR_ELx_ExTRE | TRFCR_ELx_E0TRE); + else + trfcr = etm4x_get_kern_user_filter(drvdata); + + /* + * TRFCR_EL1 doesn't have CX and TRFCR_EL1.TS has no effect when TS is + * set in EL2 so mask them out. + */ + trfcr &= ~(TRFCR_ELx_TS_MASK | TRFCR_EL2_CX); + + write_sysreg_s(trfcr, SYS_TRFCR_EL12); }
#ifdef CONFIG_ETM4X_IMPDEF_FEATURE @@ -655,6 +688,12 @@ static int etm4_parse_event_config(struct coresight_device *csdev, if (attr->exclude_user) config->mode = ETM_MODE_EXCL_USER;
+ if (attr->exclude_host) + config->mode |= ETM_MODE_EXCL_HOST; + + if (attr->exclude_guest) + config->mode |= ETM_MODE_EXCL_GUEST; + /* Always start from the default config */ etm4_set_default_config(config);
diff --git a/drivers/hwtracing/coresight/coresight-etm4x.h b/drivers/hwtracing/coresight/coresight-etm4x.h index 20e2e4cb7614..3f170599822f 100644 --- a/drivers/hwtracing/coresight/coresight-etm4x.h +++ b/drivers/hwtracing/coresight/coresight-etm4x.h @@ -841,7 +841,7 @@ enum etm_impdef_type { * @s_ex_level: Secure ELs where tracing is supported. */ struct etmv4_config { - u32 mode; + u64 mode; u32 pe_sel; u32 cfg; u32 eventctrl0; diff --git a/drivers/hwtracing/coresight/coresight-priv.h b/drivers/hwtracing/coresight/coresight-priv.h index 767076e07970..727dd27ba800 100644 --- a/drivers/hwtracing/coresight/coresight-priv.h +++ b/drivers/hwtracing/coresight/coresight-priv.h @@ -39,6 +39,9 @@
#define ETM_MODE_EXCL_KERN BIT(30) #define ETM_MODE_EXCL_USER BIT(31) +#define ETM_MODE_EXCL_HOST BIT(32) +#define ETM_MODE_EXCL_GUEST BIT(33) + struct cs_pair_attribute { struct device_attribute attr; u32 lo_off;