From: Marc Zyngier <marc.zyngier@arm.com> To: linux-arm-kernel@lists.infradead.org, kvm@vger.kernel.org, kvmarm@lists.cs.columbia.edu Cc: Shannon Zhao <shannon.zhao@linaro.org> Subject: [PATCH v2 0/9] arm64: KVM: Fix PMU exception generation Date: Mon, 27 Mar 2017 17:03:36 +0100 [thread overview] Message-ID: <20170327160345.12402-1-marc.zyngier@arm.com> (raw) Running the following code: root@zomby-woof:~# cat test-pmu.c int main(int argc, char *argv[]) { unsigned int val; asm ("mrc p15, 0, %0, c9, c13, 0\n" : "=r" (val)); return val; } in a 32bit guest (or a 64bit guest with a 32bit userspace) results in this surprising result: [ 120.347497] kvm [1150]: Unsupported guest CP15 access at: ab0945ae [ 120.353689] kvm [1142]: { Op0( 0), Op1( 0), CRn( 9), CRm(13), Op2( 0), func_read }, which is weird, because the guest behaves correctly: root@zomby-woof:~# ./test-pmu [ 16.184422] test-pmu[740]: undefined instruction: pc=00000000ab0945ae [ 16.186043] Code: 00340001 b4800000 af00b085 60396078 (3f1dee19) Illegal instruction It gets the expected UNDEF, and all is fine. So what? It turns out that the PMU emulation code is a bit lazy, and tells the rest of KVM that the emulation has failed, so that an exception gets delivered. Subtle differences in the 32bit vs 64bit handling make it spit an "Unsupported..." error. This series tries to set things straight: - Make all PMU illegal accesses inject an UNDEF - Make these illegal accesses a successful emulation w.r.t the rest of KVM. In the process, we also squash an interesting bug in the 64bit CP access. Similar treatment is applied to the 32bit kernel, except that we don't ever inject an exception there (no PMU support yet). * From v1: - Got rid of the original sideband information, and declared that an emulation can never fail. The return value now indicates whether or not we should advance the PC. - Sanitized read_from_write_only/write_to_read_only. - Implemented similar semantics on 32bit (although unaffected so far). Marc Zyngier (9): arm64: KVM: PMU: Refactor pmu_*_el0_disabled arm64: KVM: PMU: Inject UNDEF exception on illegal register access arm64: KVM: PMU: Inject UNDEF on non-privileged accesses arm64: KVM: Make unexpected reads from WO registers inject an undef arm64: KVM: PMU: Inject UNDEF on read access to PMSWINC_EL0 arm64: KVM: Treat sysreg accessors returning false as successful arm64: KVM: Do not corrupt registers on failed 64bit CP read arm: KVM: Make unexpected register accesses inject an undef arm: KVM: Treat CP15 accessors returning false as successful arch/arm/kvm/coproc.c | 24 +++++++-- arch/arm/kvm/coproc.h | 18 ------- arch/arm64/kvm/sys_regs.c | 131 ++++++++++++++++++++++++---------------------- arch/arm64/kvm/sys_regs.h | 18 ------- 4 files changed, 88 insertions(+), 103 deletions(-) -- 2.11.0
WARNING: multiple messages have this Message-ID (diff)
From: marc.zyngier@arm.com (Marc Zyngier) To: linux-arm-kernel@lists.infradead.org Subject: [PATCH v2 0/9] arm64: KVM: Fix PMU exception generation Date: Mon, 27 Mar 2017 17:03:36 +0100 [thread overview] Message-ID: <20170327160345.12402-1-marc.zyngier@arm.com> (raw) Running the following code: root at zomby-woof:~# cat test-pmu.c int main(int argc, char *argv[]) { unsigned int val; asm ("mrc p15, 0, %0, c9, c13, 0\n" : "=r" (val)); return val; } in a 32bit guest (or a 64bit guest with a 32bit userspace) results in this surprising result: [ 120.347497] kvm [1150]: Unsupported guest CP15 access at: ab0945ae [ 120.353689] kvm [1142]: { Op0( 0), Op1( 0), CRn( 9), CRm(13), Op2( 0), func_read }, which is weird, because the guest behaves correctly: root at zomby-woof:~# ./test-pmu [ 16.184422] test-pmu[740]: undefined instruction: pc=00000000ab0945ae [ 16.186043] Code: 00340001 b4800000 af00b085 60396078 (3f1dee19) Illegal instruction It gets the expected UNDEF, and all is fine. So what? It turns out that the PMU emulation code is a bit lazy, and tells the rest of KVM that the emulation has failed, so that an exception gets delivered. Subtle differences in the 32bit vs 64bit handling make it spit an "Unsupported..." error. This series tries to set things straight: - Make all PMU illegal accesses inject an UNDEF - Make these illegal accesses a successful emulation w.r.t the rest of KVM. In the process, we also squash an interesting bug in the 64bit CP access. Similar treatment is applied to the 32bit kernel, except that we don't ever inject an exception there (no PMU support yet). * From v1: - Got rid of the original sideband information, and declared that an emulation can never fail. The return value now indicates whether or not we should advance the PC. - Sanitized read_from_write_only/write_to_read_only. - Implemented similar semantics on 32bit (although unaffected so far). Marc Zyngier (9): arm64: KVM: PMU: Refactor pmu_*_el0_disabled arm64: KVM: PMU: Inject UNDEF exception on illegal register access arm64: KVM: PMU: Inject UNDEF on non-privileged accesses arm64: KVM: Make unexpected reads from WO registers inject an undef arm64: KVM: PMU: Inject UNDEF on read access to PMSWINC_EL0 arm64: KVM: Treat sysreg accessors returning false as successful arm64: KVM: Do not corrupt registers on failed 64bit CP read arm: KVM: Make unexpected register accesses inject an undef arm: KVM: Treat CP15 accessors returning false as successful arch/arm/kvm/coproc.c | 24 +++++++-- arch/arm/kvm/coproc.h | 18 ------- arch/arm64/kvm/sys_regs.c | 131 ++++++++++++++++++++++++---------------------- arch/arm64/kvm/sys_regs.h | 18 ------- 4 files changed, 88 insertions(+), 103 deletions(-) -- 2.11.0
next reply other threads:[~2017-03-27 16:03 UTC|newest] Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top 2017-03-27 16:03 Marc Zyngier [this message] 2017-03-27 16:03 ` [PATCH v2 0/9] arm64: KVM: Fix PMU exception generation Marc Zyngier 2017-03-27 16:03 ` [PATCH v2 1/9] arm64: KVM: PMU: Refactor pmu_*_el0_disabled Marc Zyngier 2017-03-27 16:03 ` Marc Zyngier 2017-03-27 17:03 ` Suzuki K Poulose 2017-03-27 17:03 ` Suzuki K Poulose 2017-03-27 17:11 ` Marc Zyngier 2017-03-27 17:11 ` Marc Zyngier 2017-03-28 12:46 ` Christoffer Dall 2017-03-28 12:46 ` Christoffer Dall 2017-03-28 13:21 ` Marc Zyngier 2017-03-28 13:21 ` Marc Zyngier 2017-03-27 16:03 ` [PATCH v2 2/9] arm64: KVM: PMU: Inject UNDEF exception on illegal register access Marc Zyngier 2017-03-27 16:03 ` Marc Zyngier 2017-03-28 12:44 ` Christoffer Dall 2017-03-28 12:44 ` Christoffer Dall 2017-03-27 16:03 ` [PATCH v2 3/9] arm64: KVM: PMU: Inject UNDEF on non-privileged accesses Marc Zyngier 2017-03-27 16:03 ` Marc Zyngier 2017-03-28 12:45 ` Christoffer Dall 2017-03-28 12:45 ` Christoffer Dall 2017-03-27 16:03 ` [PATCH v2 4/9] arm64: KVM: Make unexpected reads from WO registers inject an undef Marc Zyngier 2017-03-27 16:03 ` Marc Zyngier 2017-03-28 12:45 ` Christoffer Dall 2017-03-28 12:45 ` Christoffer Dall 2017-03-27 16:03 ` [PATCH v2 5/9] arm64: KVM: PMU: Inject UNDEF on read access to PMSWINC_EL0 Marc Zyngier 2017-03-27 16:03 ` Marc Zyngier 2017-03-28 12:45 ` Christoffer Dall 2017-03-28 12:45 ` Christoffer Dall 2017-03-27 16:03 ` [PATCH v2 6/9] arm64: KVM: Treat sysreg accessors returning false as successful Marc Zyngier 2017-03-27 16:03 ` Marc Zyngier 2017-03-28 12:45 ` Christoffer Dall 2017-03-28 12:45 ` Christoffer Dall 2017-03-27 16:03 ` [PATCH v2 7/9] arm64: KVM: Do not corrupt registers on failed 64bit CP read Marc Zyngier 2017-03-27 16:03 ` Marc Zyngier 2017-03-28 12:46 ` Christoffer Dall 2017-03-28 12:46 ` Christoffer Dall 2017-03-28 13:24 ` Marc Zyngier 2017-03-28 13:24 ` Marc Zyngier 2017-03-27 16:03 ` [PATCH v2 8/9] arm: KVM: Make unexpected register accesses inject an undef Marc Zyngier 2017-03-27 16:03 ` Marc Zyngier 2017-03-28 12:46 ` Christoffer Dall 2017-03-28 12:46 ` Christoffer Dall 2017-03-27 16:03 ` [PATCH v2 9/9] arm: KVM: Treat CP15 accessors returning false as successful Marc Zyngier 2017-03-27 16:03 ` Marc Zyngier 2017-03-28 12:46 ` Christoffer Dall 2017-03-28 12:46 ` Christoffer Dall 2017-03-28 13:37 ` [PATCH v2 0/9] arm64: KVM: Fix PMU exception generation Christoffer Dall 2017-03-28 13:37 ` Christoffer Dall
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=20170327160345.12402-1-marc.zyngier@arm.com \ --to=marc.zyngier@arm.com \ --cc=kvm@vger.kernel.org \ --cc=kvmarm@lists.cs.columbia.edu \ --cc=linux-arm-kernel@lists.infradead.org \ --cc=shannon.zhao@linaro.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: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.