From: Dietmar Hahn <dietmar.hahn@ts.fujitsu.com>
To: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: kevin.tian@intel.com, JBeulich@suse.com,
andrew.cooper3@citrix.com, xen-devel@lists.xen.org,
Aravind.Gopalakrishnan@amd.com, suravee.suthikulpanit@amd.com,
dgdegra@tycho.nsa.gov
Subject: Re: [PATCH v25 10/15] x86/VPMU: Use pre-computed masks when checking validity of MSRs
Date: Wed, 08 Jul 2015 08:49:01 +0200 [thread overview]
Message-ID: <12732850.VbxlCXgAhA@amur> (raw)
In-Reply-To: <1434739486-1611-11-git-send-email-boris.ostrovsky@oracle.com>
Am Freitag 19 Juni 2015, 14:44:41 schrieb Boris Ostrovsky:
> No need to compute those masks on every MSR access.
>
> Also, when checking MSR_P6_EVNTSELx registers make sure that bit 21
> (which is a reserved bit) is not set.
>
> Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
> Acked-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Dietmar Hahn <dietmar.hahn@ts.fujitsu.com>
> ---
> xen/arch/x86/hvm/vmx/vpmu_core2.c | 28 ++++++++++++++++++----------
> 1 file changed, 18 insertions(+), 10 deletions(-)
>
> diff --git a/xen/arch/x86/hvm/vmx/vpmu_core2.c b/xen/arch/x86/hvm/vmx/vpmu_core2.c
> index 089154e..166277a 100644
> --- a/xen/arch/x86/hvm/vmx/vpmu_core2.c
> +++ b/xen/arch/x86/hvm/vmx/vpmu_core2.c
> @@ -80,9 +80,16 @@ static bool_t __read_mostly full_width_write;
> #define FIXED_CTR_CTRL_BITS 4
> #define FIXED_CTR_CTRL_MASK ((1 << FIXED_CTR_CTRL_BITS) - 1)
>
> +#define ARCH_CNTR_ENABLED (1ULL << 22)
> +
> /* Number of general-purpose and fixed performance counters */
> static unsigned int __read_mostly arch_pmc_cnt, fixed_pmc_cnt;
>
> +/* Masks used for testing whether and MSR is valid */
> +#define ARCH_CTRL_MASK (~((1ull << 32) - 1) | (1ull << 21))
> +static uint64_t __read_mostly fixed_ctrl_mask, fixed_counters_mask;
> +static uint64_t __read_mostly global_ovf_ctrl_mask;
> +
> /*
> * QUIRK to workaround an issue on various family 6 cpus.
> * The issue leads to endless PMC interrupt loops on the processor.
> @@ -479,9 +486,7 @@ static int core2_vpmu_do_wrmsr(unsigned int msr, uint64_t msr_content,
>
> ASSERT(!supported);
>
> - if ( type == MSR_TYPE_COUNTER &&
> - (msr_content &
> - ~((1ull << core2_get_bitwidth_fix_count()) - 1)) )
> + if ( (type == MSR_TYPE_COUNTER) && (msr_content & fixed_counters_mask) )
> /* Writing unsupported bits to a fixed counter */
> return -EINVAL;
>
> @@ -490,9 +495,7 @@ static int core2_vpmu_do_wrmsr(unsigned int msr, uint64_t msr_content,
> switch ( msr )
> {
> case MSR_CORE_PERF_GLOBAL_OVF_CTRL:
> - if ( msr_content & ~(0xC000000000000000 |
> - (((1ULL << fixed_pmc_cnt) - 1) << 32) |
> - ((1ULL << arch_pmc_cnt) - 1)) )
> + if ( msr_content & global_ovf_ctrl_mask )
> return -EINVAL;
> core2_vpmu_cxt->global_status &= ~msr_content;
> wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, msr_content);
> @@ -526,8 +529,7 @@ static int core2_vpmu_do_wrmsr(unsigned int msr, uint64_t msr_content,
> core2_vpmu_cxt->global_ctrl = msr_content;
> break;
> case MSR_CORE_PERF_FIXED_CTR_CTRL:
> - if ( msr_content &
> - ( ~((1ull << (fixed_pmc_cnt * FIXED_CTR_CTRL_BITS)) - 1)) )
> + if ( msr_content & fixed_ctrl_mask )
> return -EINVAL;
>
> if ( has_hvm_container_vcpu(v) )
> @@ -556,7 +558,7 @@ static int core2_vpmu_do_wrmsr(unsigned int msr, uint64_t msr_content,
> struct xen_pmu_cntr_pair *xen_pmu_cntr_pair =
> vpmu_reg_pointer(core2_vpmu_cxt, arch_counters);
>
> - if ( msr_content & (~((1ull << 32) - 1)) )
> + if ( msr_content & ARCH_CTRL_MASK )
> return -EINVAL;
>
> if ( has_hvm_container_vcpu(v) )
> @@ -565,7 +567,7 @@ static int core2_vpmu_do_wrmsr(unsigned int msr, uint64_t msr_content,
> else
> rdmsrl(MSR_CORE_PERF_GLOBAL_CTRL, core2_vpmu_cxt->global_ctrl);
>
> - if ( msr_content & (1ULL << 22) )
> + if ( msr_content & ARCH_CNTR_ENABLED )
> *enabled_cntrs |= 1ULL << tmp;
> else
> *enabled_cntrs &= ~(1ULL << tmp);
> @@ -915,6 +917,12 @@ int __init core2_vpmu_init(void)
> rdmsrl(MSR_IA32_PERF_CAPABILITIES, caps);
> full_width_write = (caps >> 13) & 1;
>
> + fixed_ctrl_mask = ~((1ull << (fixed_pmc_cnt * FIXED_CTR_CTRL_BITS)) - 1);
> + fixed_counters_mask = ~((1ull << core2_get_bitwidth_fix_count()) - 1);
> + global_ovf_ctrl_mask = ~(0xC000000000000000 |
> + (((1ULL << fixed_pmc_cnt) - 1) << 32) |
> + ((1ULL << arch_pmc_cnt) - 1));
> +
> check_pmc_quirk();
>
> if ( sizeof(struct xen_pmu_data) + sizeof(uint64_t) * fixed_pmc_cnt +
>
--
Company details: http://ts.fujitsu.com/imprint.html
next prev parent reply other threads:[~2015-07-08 6:49 UTC|newest]
Thread overview: 37+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-06-19 18:44 [PATCH v25 00/15] x86/PMU: Xen PMU PV(H) support Boris Ostrovsky
2015-06-19 18:44 ` [PATCH v25 01/15] common/symbols: Export hypervisor symbols to privileged guest Boris Ostrovsky
2015-06-19 18:44 ` [PATCH v25 02/15] x86/VPMU: Add public xenpmu.h Boris Ostrovsky
2015-06-19 18:44 ` [PATCH v25 03/15] x86/VPMU: Make vpmu not HVM-specific Boris Ostrovsky
2015-06-19 18:44 ` [PATCH v25 04/15] x86/VPMU: Interface for setting PMU mode and flags Boris Ostrovsky
2015-06-22 15:10 ` Jan Beulich
2015-06-22 16:10 ` Boris Ostrovsky
2015-06-23 8:26 ` Jan Beulich
2015-06-24 2:17 ` Boris Ostrovsky
2015-07-07 7:16 ` Dietmar Hahn
2015-07-09 1:27 ` Tian, Kevin
2015-06-19 18:44 ` [PATCH v25 05/15] x86/VPMU: Initialize VPMUs with __initcall Boris Ostrovsky
2015-07-08 11:48 ` Dietmar Hahn
2015-07-09 6:04 ` Tian, Kevin
2015-06-19 18:44 ` [PATCH v25 06/15] x86/VPMU: Initialize PMU for PV(H) guests Boris Ostrovsky
2015-07-08 12:20 ` Dietmar Hahn
2015-06-19 18:44 ` [PATCH v25 07/15] x86/VPMU: Save VPMU state for PV guests during context switch Boris Ostrovsky
2015-06-22 15:14 ` Jan Beulich
2015-07-08 5:51 ` Dietmar Hahn
2015-06-19 18:44 ` [PATCH v25 08/15] x86/VPMU: When handling MSR accesses, leave fault injection to callers Boris Ostrovsky
2015-07-08 6:11 ` Dietmar Hahn
2015-06-19 18:44 ` [PATCH v25 09/15] x86/VPMU: Add support for PMU register handling on PV guests Boris Ostrovsky
2015-06-19 18:44 ` [PATCH v25 10/15] x86/VPMU: Use pre-computed masks when checking validity of MSRs Boris Ostrovsky
2015-07-08 6:49 ` Dietmar Hahn [this message]
2015-06-19 18:44 ` [PATCH v25 11/15] VPMU/AMD: Check MSR values before writing to hardware Boris Ostrovsky
2015-07-08 15:35 ` Aravind Gopalakrishnan
2015-06-19 18:44 ` [PATCH v25 12/15] x86/VPMU: Handle PMU interrupts for PV(H) guests Boris Ostrovsky
2015-06-22 15:20 ` Jan Beulich
2015-07-09 12:19 ` Dietmar Hahn
2015-06-19 18:44 ` [PATCH v25 13/15] x86/VPMU: Merge vpmu_rdmsr and vpmu_wrmsr Boris Ostrovsky
2015-07-09 6:13 ` Tian, Kevin
2015-06-19 18:44 ` [PATCH v25 14/15] x86/VPMU: Add privileged PMU mode Boris Ostrovsky
2015-07-09 6:13 ` Tian, Kevin
2015-07-09 12:38 ` Dietmar Hahn
2015-06-19 18:44 ` [PATCH v25 15/15] x86/VPMU: Move VPMU files up from hvm/ directory Boris Ostrovsky
2015-07-08 8:03 ` [PATCH v25 00/15] x86/PMU: Xen PMU PV(H) support Jan Beulich
2015-07-10 9:13 ` Dietmar Hahn
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=12732850.VbxlCXgAhA@amur \
--to=dietmar.hahn@ts.fujitsu.com \
--cc=Aravind.Gopalakrishnan@amd.com \
--cc=JBeulich@suse.com \
--cc=andrew.cooper3@citrix.com \
--cc=boris.ostrovsky@oracle.com \
--cc=dgdegra@tycho.nsa.gov \
--cc=kevin.tian@intel.com \
--cc=suravee.suthikulpanit@amd.com \
--cc=xen-devel@lists.xen.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).