From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id F2DFAC433FE for ; Thu, 18 Nov 2021 14:22:24 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id D61E16124B for ; Thu, 18 Nov 2021 14:22:24 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233001AbhKROZY (ORCPT ); Thu, 18 Nov 2021 09:25:24 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:42158 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S232240AbhKROZX (ORCPT ); Thu, 18 Nov 2021 09:25:23 -0500 Received: from bombadil.infradead.org (bombadil.infradead.org [IPv6:2607:7c80:54:e::133]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 5F804C08EB20; Thu, 18 Nov 2021 06:22:23 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=infradead.org; s=bombadil.20210309; h=MIME-Version:Content-Type:References: In-Reply-To:Date:Cc:To:From:Subject:Message-ID:Sender:Reply-To: Content-Transfer-Encoding:Content-ID:Content-Description; bh=aNiLvRkFCX+rhjHO0KRWJfs3p2AxyJLKVRfBjNlJWww=; b=Eg9WCPGzLj2NoyL9rvyLF8bQ3L 7a/83/rvYwlEa0EOEXC3AKhDqLbea+lul2x+dFF/oLYOebDzSr4g4fOBcw2EGdq/uegfAkxm7FTXR iioonLM0cttXq329PnBrXI9ByVjVtXsiZt3O0qbfNwYeIe+h/xJqVC/Otbd+5VQLfLWTrnwLBdLt1 so6K/2CJTvfCMxlCDkgrhGvSV/X9vAXw9QTZ6LQf5qCmzeNHqumCsCJ4QO3MPdTVrA1ENMZhvZvDc 8WKUKFqYYGGWRfT6d+wlxsVbenM3H2sG4T8CuZXCO97X0eXPPmf4xzMqjBks2J/f6tNUtc/KCs81M +pVp/nyA==; Received: from [2001:8b0:10b:1:4a2a:e3ff:fe14:8625] (helo=u3832b3a9db3152.ant.amazon.com) by bombadil.infradead.org with esmtpsa (Exim 4.94.2 #2 (Red Hat Linux)) id 1mniIk-0085pb-8Y; Thu, 18 Nov 2021 14:22:10 +0000 Message-ID: <20b5952e76c54a3a5dfe5a898e3b835404ac6fb1.camel@infradead.org> Subject: Re: [PATCH v3 08/12] KVM: Propagate vcpu explicitly to mark_page_dirty_in_slot() From: David Woodhouse To: Paolo Bonzini Cc: kvm , Boris Ostrovsky , Joao Martins , "jmattson @ google . com" , "wanpengli @ tencent . com" , "seanjc @ google . com" , "vkuznets @ redhat . com" , "mtosatti @ redhat . com" , "joro @ 8bytes . org" , karahmed@amazon.com, Marc Zyngier , James Morse , Alexandru Elisei , Suzuki K Poulose , Catalin Marinas , Will Deacon , Huacai Chen , Aleksandar Markovic , Michael Ellerman , Benjamin Herrenschmidt , Anup Patel , Christian Borntraeger , kvmarm@lists.cs.columbia.edu, linux-arm-kernel , linux-mips@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, kvm-riscv@lists.infradead.org, linux-s390@vger.kernel.org Date: Thu, 18 Nov 2021 14:22:04 +0000 In-Reply-To: <4c48546b-eb4a-dff7-cc38-5df54f73f5d4@redhat.com> References: <20211117174003.297096-1-dwmw2@infradead.org> <20211117174003.297096-9-dwmw2@infradead.org> <85d9fec17f32c3eb9e100e56b91af050.squirrel@twosheds.infradead.org> <4c48546b-eb4a-dff7-cc38-5df54f73f5d4@redhat.com> Content-Type: multipart/signed; micalg="sha-256"; protocol="application/pkcs7-signature"; boundary="=-z4ZhwAp7QHQwy5q5gRo1" User-Agent: Evolution 3.36.5-0ubuntu1 MIME-Version: 1.0 X-SRS-Rewrite: SMTP reverse-path rewritten from by bombadil.infradead.org. See http://www.infradead.org/rpr.html Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org --=-z4ZhwAp7QHQwy5q5gRo1 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable On Thu, 2021-11-18 at 13:04 +0100, Paolo Bonzini wrote: > On 11/17/21 22:09, David Woodhouse wrote: > > > { > > > - struct kvm_vcpu *vcpu =3D kvm_get_running_vcpu(); > > > + struct kvm_vcpu *running_vcpu =3D kvm_get_running_vcpu(); > > >=20 > > > + WARN_ON_ONCE(vcpu && vcpu !=3D running_vcpu); > > > WARN_ON_ONCE(vcpu->kvm !=3D kvm); > > Ah, that one needs to be changed to check running_vcpu instead. Or this > > needs to go first: > >=20 > > I think I prefer making the vCPU a required argument. If anyone's going= to > > pull a vCPU pointer out of their posterior, let the caller do it. > >=20 >=20 > I understand that feeling, but still using the running vCPU is by far=20 > the common case, and it's not worth adding a new function parameter to= =20 > all call sites. >=20 > What about using a separate function, possibly __-prefixed, for the case= =20 > where you have a very specific vCPU? We could certainly do a kvm_vcpu_mark_page_dirty_in_slot() and reduce the collateral damage. I think this patch wouldn't need to touch anything outside virt/kvm/ if we did that. But bikeshedding aside, it occurs to me that I have a more substantial concern about this approach =E2=80=94 are we even *allowed* to touch the di= rty ring of another vCPU? It seems to be based on the assumption that it's entirely a per-cpu structure on the kernel side. Wouldn't we need a spinlock in kvm_dirty_ring_push() at the very least? At this point I'm somewhat tempted to remove the mark_page_dirty() call from gfn_to_pfn_cache_invalidate_start() and move it to the tail of=20 kvm_gfn_to_pfn_cache_refresh() instead, where it unpins and memunmaps the page. (We'd still tell the *kernel* by calling kvm_set_pfn_dirty() immediately in the invalidation, just defer the KVM mark_page_dirty() to be done in the context of an actual vCPU.) If I do that, I can drop this 'propagate vcpu' patch completely. I'm already happy enough that I'll fix the Xen shared_info page by *never* bothering to dirty_log for it, and I can wash my hands of that problem.... if I stop typing now. But... That leaves the one in TDP MMU handle_changed_spte_dirty_log() which AFAICT can trigger the same crash seen by butt3rflyh4ck =E2=80=94 can't tha= t happen from a thread where kvm_get_running_vcpu() is NULL too? For that one I'm not sure. --=-z4ZhwAp7QHQwy5q5gRo1 Content-Type: application/pkcs7-signature; name="smime.p7s" Content-Disposition: attachment; filename="smime.p7s" Content-Transfer-Encoding: base64 MIAGCSqGSIb3DQEHAqCAMIACAQExDzANBglghkgBZQMEAgEFADCABgkqhkiG9w0BBwEAAKCCECow ggUcMIIEBKADAgECAhEA4rtJSHkq7AnpxKUY8ZlYZjANBgkqhkiG9w0BAQsFADCBlzELMAkGA1UE BhMCR0IxGzAZBgNVBAgTEkdyZWF0ZXIgTWFuY2hlc3RlcjEQMA4GA1UEBxMHU2FsZm9yZDEaMBgG A1UEChMRQ09NT0RPIENBIExpbWl0ZWQxPTA7BgNVBAMTNENPTU9ETyBSU0EgQ2xpZW50IEF1dGhl bnRpY2F0aW9uIGFuZCBTZWN1cmUgRW1haWwgQ0EwHhcNMTkwMTAyMDAwMDAwWhcNMjIwMTAxMjM1 OTU5WjAkMSIwIAYJKoZIhvcNAQkBFhNkd213MkBpbmZyYWRlYWQub3JnMIIBIjANBgkqhkiG9w0B AQEFAAOCAQ8AMIIBCgKCAQEAsv3wObLTCbUA7GJqKj9vHGf+Fa+tpkO+ZRVve9EpNsMsfXhvFpb8 RgL8vD+L133wK6csYoDU7zKiAo92FMUWaY1Hy6HqvVr9oevfTV3xhB5rQO1RHJoAfkvhy+wpjo7Q cXuzkOpibq2YurVStHAiGqAOMGMXhcVGqPuGhcVcVzVUjsvEzAV9Po9K2rpZ52FE4rDkpDK1pBK+ uOAyOkgIg/cD8Kugav5tyapydeWMZRJQH1vMQ6OVT24CyAn2yXm2NgTQMS1mpzStP2ioPtTnszIQ Ih7ASVzhV6csHb8Yrkx8mgllOyrt9Y2kWRRJFm/FPRNEurOeNV6lnYAXOymVJwIDAQABo4IB0zCC Ac8wHwYDVR0jBBgwFoAUgq9sjPjF/pZhfOgfPStxSF7Ei8AwHQYDVR0OBBYEFLfuNf820LvaT4AK xrGK3EKx1DE7MA4GA1UdDwEB/wQEAwIFoDAMBgNVHRMBAf8EAjAAMB0GA1UdJQQWMBQGCCsGAQUF BwMEBggrBgEFBQcDAjBGBgNVHSAEPzA9MDsGDCsGAQQBsjEBAgEDBTArMCkGCCsGAQUFBwIBFh1o dHRwczovL3NlY3VyZS5jb21vZG8ubmV0L0NQUzBaBgNVHR8EUzBRME+gTaBLhklodHRwOi8vY3Js LmNvbW9kb2NhLmNvbS9DT01PRE9SU0FDbGllbnRBdXRoZW50aWNhdGlvbmFuZFNlY3VyZUVtYWls Q0EuY3JsMIGLBggrBgEFBQcBAQR/MH0wVQYIKwYBBQUHMAKGSWh0dHA6Ly9jcnQuY29tb2RvY2Eu Y29tL0NPTU9ET1JTQUNsaWVudEF1dGhlbnRpY2F0aW9uYW5kU2VjdXJlRW1haWxDQS5jcnQwJAYI KwYBBQUHMAGGGGh0dHA6Ly9vY3NwLmNvbW9kb2NhLmNvbTAeBgNVHREEFzAVgRNkd213MkBpbmZy YWRlYWQub3JnMA0GCSqGSIb3DQEBCwUAA4IBAQALbSykFusvvVkSIWttcEeifOGGKs7Wx2f5f45b nv2ghcxK5URjUvCnJhg+soxOMoQLG6+nbhzzb2rLTdRVGbvjZH0fOOzq0LShq0EXsqnJbbuwJhK+ PnBtqX5O23PMHutP1l88AtVN+Rb72oSvnD+dK6708JqqUx2MAFLMevrhJRXLjKb2Mm+/8XBpEw+B 7DisN4TMlLB/d55WnT9UPNHmQ+3KFL7QrTO8hYExkU849g58Dn3Nw3oCbMUgny81ocrLlB2Z5fFG Qu1AdNiBA+kg/UxzyJZpFbKfCITd5yX49bOriL692aMVDyqUvh8fP+T99PqorH4cIJP6OxSTdxKM MIIFHDCCBASgAwIBAgIRAOK7SUh5KuwJ6cSlGPGZWGYwDQYJKoZIhvcNAQELBQAwgZcxCzAJBgNV BAYTAkdCMRswGQYDVQQIExJHcmVhdGVyIE1hbmNoZXN0ZXIxEDAOBgNVBAcTB1NhbGZvcmQxGjAY BgNVBAoTEUNPTU9ETyBDQSBMaW1pdGVkMT0wOwYDVQQDEzRDT01PRE8gUlNBIENsaWVudCBBdXRo ZW50aWNhdGlvbiBhbmQgU2VjdXJlIEVtYWlsIENBMB4XDTE5MDEwMjAwMDAwMFoXDTIyMDEwMTIz NTk1OVowJDEiMCAGCSqGSIb3DQEJARYTZHdtdzJAaW5mcmFkZWFkLm9yZzCCASIwDQYJKoZIhvcN AQEBBQADggEPADCCAQoCggEBALL98Dmy0wm1AOxiaio/bxxn/hWvraZDvmUVb3vRKTbDLH14bxaW /EYC/Lw/i9d98CunLGKA1O8yogKPdhTFFmmNR8uh6r1a/aHr301d8YQea0DtURyaAH5L4cvsKY6O 0HF7s5DqYm6tmLq1UrRwIhqgDjBjF4XFRqj7hoXFXFc1VI7LxMwFfT6PStq6WedhROKw5KQytaQS vrjgMjpICIP3A/CroGr+bcmqcnXljGUSUB9bzEOjlU9uAsgJ9sl5tjYE0DEtZqc0rT9oqD7U57My ECIewElc4VenLB2/GK5MfJoJZTsq7fWNpFkUSRZvxT0TRLqznjVepZ2AFzsplScCAwEAAaOCAdMw ggHPMB8GA1UdIwQYMBaAFIKvbIz4xf6WYXzoHz0rcUhexIvAMB0GA1UdDgQWBBS37jX/NtC72k+A CsaxitxCsdQxOzAOBgNVHQ8BAf8EBAMCBaAwDAYDVR0TAQH/BAIwADAdBgNVHSUEFjAUBggrBgEF BQcDBAYIKwYBBQUHAwIwRgYDVR0gBD8wPTA7BgwrBgEEAbIxAQIBAwUwKzApBggrBgEFBQcCARYd aHR0cHM6Ly9zZWN1cmUuY29tb2RvLm5ldC9DUFMwWgYDVR0fBFMwUTBPoE2gS4ZJaHR0cDovL2Ny bC5jb21vZG9jYS5jb20vQ09NT0RPUlNBQ2xpZW50QXV0aGVudGljYXRpb25hbmRTZWN1cmVFbWFp bENBLmNybDCBiwYIKwYBBQUHAQEEfzB9MFUGCCsGAQUFBzAChklodHRwOi8vY3J0LmNvbW9kb2Nh LmNvbS9DT01PRE9SU0FDbGllbnRBdXRoZW50aWNhdGlvbmFuZFNlY3VyZUVtYWlsQ0EuY3J0MCQG CCsGAQUFBzABhhhodHRwOi8vb2NzcC5jb21vZG9jYS5jb20wHgYDVR0RBBcwFYETZHdtdzJAaW5m cmFkZWFkLm9yZzANBgkqhkiG9w0BAQsFAAOCAQEAC20spBbrL71ZEiFrbXBHonzhhirO1sdn+X+O W579oIXMSuVEY1LwpyYYPrKMTjKECxuvp24c829qy03UVRm742R9Hzjs6tC0oatBF7KpyW27sCYS vj5wbal+TttzzB7rT9ZfPALVTfkW+9qEr5w/nSuu9PCaqlMdjABSzHr64SUVy4ym9jJvv/FwaRMP gew4rDeEzJSwf3eeVp0/VDzR5kPtyhS+0K0zvIWBMZFPOPYOfA59zcN6AmzFIJ8vNaHKy5QdmeXx RkLtQHTYgQPpIP1Mc8iWaRWynwiE3ecl+PWzq4i+vdmjFQ8qlL4fHz/k/fT6qKx+HCCT+jsUk3cS jDCCBeYwggPOoAMCAQICEGqb4Tg7/ytrnwHV2binUlYwDQYJKoZIhvcNAQEMBQAwgYUxCzAJBgNV BAYTAkdCMRswGQYDVQQIExJHcmVhdGVyIE1hbmNoZXN0ZXIxEDAOBgNVBAcTB1NhbGZvcmQxGjAY BgNVBAoTEUNPTU9ETyBDQSBMaW1pdGVkMSswKQYDVQQDEyJDT01PRE8gUlNBIENlcnRpZmljYXRp b24gQXV0aG9yaXR5MB4XDTEzMDExMDAwMDAwMFoXDTI4MDEwOTIzNTk1OVowgZcxCzAJBgNVBAYT AkdCMRswGQYDVQQIExJHcmVhdGVyIE1hbmNoZXN0ZXIxEDAOBgNVBAcTB1NhbGZvcmQxGjAYBgNV BAoTEUNPTU9ETyBDQSBMaW1pdGVkMT0wOwYDVQQDEzRDT01PRE8gUlNBIENsaWVudCBBdXRoZW50 aWNhdGlvbiBhbmQgU2VjdXJlIEVtYWlsIENBMIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKC AQEAvrOeV6wodnVAFsc4A5jTxhh2IVDzJXkLTLWg0X06WD6cpzEup/Y0dtmEatrQPTRI5Or1u6zf +bGBSyD9aH95dDSmeny1nxdlYCeXIoymMv6pQHJGNcIDpFDIMypVpVSRsivlJTRENf+RKwrB6vcf WlP8dSsE3Rfywq09N0ZfxcBa39V0wsGtkGWC+eQKiz4pBZYKjrc5NOpG9qrxpZxyb4o4yNNwTqza aPpGRqXB7IMjtf7tTmU2jqPMLxFNe1VXj9XB1rHvbRikw8lBoNoSWY66nJN/VCJv5ym6Q0mdCbDK CMPybTjoNCQuelc0IAaO4nLUXk0BOSxSxt8kCvsUtQIDAQABo4IBPDCCATgwHwYDVR0jBBgwFoAU u69+Aj36pvE8hI6t7jiY7NkyMtQwHQYDVR0OBBYEFIKvbIz4xf6WYXzoHz0rcUhexIvAMA4GA1Ud DwEB/wQEAwIBhjASBgNVHRMBAf8ECDAGAQH/AgEAMBEGA1UdIAQKMAgwBgYEVR0gADBMBgNVHR8E RTBDMEGgP6A9hjtodHRwOi8vY3JsLmNvbW9kb2NhLmNvbS9DT01PRE9SU0FDZXJ0aWZpY2F0aW9u QXV0aG9yaXR5LmNybDBxBggrBgEFBQcBAQRlMGMwOwYIKwYBBQUHMAKGL2h0dHA6Ly9jcnQuY29t b2RvY2EuY29tL0NPTU9ET1JTQUFkZFRydXN0Q0EuY3J0MCQGCCsGAQUFBzABhhhodHRwOi8vb2Nz cC5jb21vZG9jYS5jb20wDQYJKoZIhvcNAQEMBQADggIBAHhcsoEoNE887l9Wzp+XVuyPomsX9vP2 SQgG1NgvNc3fQP7TcePo7EIMERoh42awGGsma65u/ITse2hKZHzT0CBxhuhb6txM1n/y78e/4ZOs 0j8CGpfb+SJA3GaBQ+394k+z3ZByWPQedXLL1OdK8aRINTsjk/H5Ns77zwbjOKkDamxlpZ4TKSDM KVmU/PUWNMKSTvtlenlxBhh7ETrN543j/Q6qqgCWgWuMAXijnRglp9fyadqGOncjZjaaSOGTTFB+ E2pvOUtY+hPebuPtTbq7vODqzCM6ryEhNhzf+enm0zlpXK7q332nXttNtjv7VFNYG+I31gnMrwfH M5tdhYF/8v5UY5g2xANPECTQdu9vWPoqNSGDt87b3gXb1AiGGaI06vzgkejL580ul+9hz9D0S0U4 jkhJiA7EuTecP/CFtR72uYRBcunwwH3fciPjviDDAI9SnC/2aPY8ydehzuZutLbZdRJ5PDEJM/1t yZR2niOYihZ+FCbtf3D9mB12D4ln9icgc7CwaxpNSCPt8i/GqK2HsOgkL3VYnwtx7cJUmpvVdZ4o gnzgXtgtdk3ShrtOS1iAN2ZBXFiRmjVzmehoMof06r1xub+85hFQzVxZx5/bRaTKTlL8YXLI8nAb R9HWdFqzcOoB/hxfEyIQpx9/s81rgzdEZOofSlZHynoSMYIDyjCCA8YCAQEwga0wgZcxCzAJBgNV BAYTAkdCMRswGQYDVQQIExJHcmVhdGVyIE1hbmNoZXN0ZXIxEDAOBgNVBAcTB1NhbGZvcmQxGjAY BgNVBAoTEUNPTU9ETyBDQSBMaW1pdGVkMT0wOwYDVQQDEzRDT01PRE8gUlNBIENsaWVudCBBdXRo ZW50aWNhdGlvbiBhbmQgU2VjdXJlIEVtYWlsIENBAhEA4rtJSHkq7AnpxKUY8ZlYZjANBglghkgB ZQMEAgEFAKCCAe0wGAYJKoZIhvcNAQkDMQsGCSqGSIb3DQEHATAcBgkqhkiG9w0BCQUxDxcNMjEx MTE4MTQyMjA0WjAvBgkqhkiG9w0BCQQxIgQg+ISqEkjxVQglcKIK/87tNBvzADTJpkMMJQkuJrdG oIEwgb4GCSsGAQQBgjcQBDGBsDCBrTCBlzELMAkGA1UEBhMCR0IxGzAZBgNVBAgTEkdyZWF0ZXIg TWFuY2hlc3RlcjEQMA4GA1UEBxMHU2FsZm9yZDEaMBgGA1UEChMRQ09NT0RPIENBIExpbWl0ZWQx PTA7BgNVBAMTNENPTU9ETyBSU0EgQ2xpZW50IEF1dGhlbnRpY2F0aW9uIGFuZCBTZWN1cmUgRW1h aWwgQ0ECEQDiu0lIeSrsCenEpRjxmVhmMIHABgsqhkiG9w0BCRACCzGBsKCBrTCBlzELMAkGA1UE BhMCR0IxGzAZBgNVBAgTEkdyZWF0ZXIgTWFuY2hlc3RlcjEQMA4GA1UEBxMHU2FsZm9yZDEaMBgG A1UEChMRQ09NT0RPIENBIExpbWl0ZWQxPTA7BgNVBAMTNENPTU9ETyBSU0EgQ2xpZW50IEF1dGhl bnRpY2F0aW9uIGFuZCBTZWN1cmUgRW1haWwgQ0ECEQDiu0lIeSrsCenEpRjxmVhmMA0GCSqGSIb3 DQEBAQUABIIBAJH1yb12MLsjgWetb0Jle3l64Ir5qFtm4S9oJdX3agqg687f6tBhtF50v1mIpANp c6vsvh7x/aUP3OAo1bT4TfJ6HZaijVYsaXyGJoDlK+YPM1sGwR6QTtE6LyVX2EZ20dZ8JJnTwNof PSKCHiHVgGmIQpa8RN27plDd3QbjP7x9uanI2YefbyScQOucK92qrw8CP2FVlsvbsqGbNjYqivBn uOGZvlKfdsWDCsbkNCMlwoqusZ9Hg341bqAEhb0qm0IUo6HcD8S1fOLxnifHRY5mTu8XLDMiIt0f e6WcYhHumsPQ7SU0/Z/+klywrXG3JnLzqY3DKoH4olaNdN/JZRIAAAAAAAA= --=-z4ZhwAp7QHQwy5q5gRo1--