Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754147AbaKAXBD (ORCPT ); Sat, 1 Nov 2014 19:01:03 -0400 Received: from shadbolt.e.decadent.org.uk ([88.96.1.126]:60010 "EHLO shadbolt.e.decadent.org.uk" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751043AbaKAWj1 (ORCPT ); Sat, 1 Nov 2014 18:39:27 -0400 Content-Type: text/plain; charset="UTF-8" Content-Disposition: inline Content-Transfer-Encoding: 8bit MIME-Version: 1.0 From: Ben Hutchings To: linux-kernel@vger.kernel.org, stable@vger.kernel.org CC: akpm@linux-foundation.org, "Paolo Bonzini" Date: Sat, 01 Nov 2014 22:28:03 +0000 Message-ID: X-Mailer: LinuxStableQueue (scripts by bwh) Subject: [PATCH 3.2 092/102] KVM: x86: use new CS.RPL as CPL during task switch In-Reply-To: X-SA-Exim-Connect-IP: 192.168.4.249 X-SA-Exim-Mail-From: ben@decadent.org.uk X-SA-Exim-Scanned: No (on shadbolt.decadent.org.uk); SAEximRunCond expanded to false Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 3.2.64-rc1 review patch. If anyone has any objections, please let me know. ------------------ From: Paolo Bonzini commit 2356aaeb2f58f491679dc0c38bc3f6dbe54e7ded upstream. During task switch, all of CS.DPL, CS.RPL, SS.DPL must match (in addition to all the other requirements) and will be the new CPL. So far this worked by carefully setting the CS selector and flag before doing the task switch; setting CS.selector will already change the CPL. However, this will not work once we get the CPL from SS.DPL, because then you will have to set the full segment descriptor cache to change the CPL. ctxt->ops->cpl(ctxt) will then return the old CPL during the task switch, and the check that SS.DPL == CPL will fail. Temporarily assume that the CPL comes from CS.RPL during task switch to a protected-mode task. This is the same approach used in QEMU's emulation code, which (until version 2.0) manually tracks the CPL. Signed-off-by: Paolo Bonzini [bwh: Backported to 3.2: - Adjust context - load_state_from_tss32() does not support VM86 mode] Signed-off-by: Ben Hutchings --- arch/x86/kvm/emulate.c | 60 +++++++++++++++++++++++++++----------------------- 1 file changed, 33 insertions(+), 27 deletions(-) --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -1233,11 +1233,11 @@ static int write_segment_descriptor(stru } /* Does not support long mode */ -static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, - u16 selector, int seg) +static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, + u16 selector, int seg, u8 cpl) { struct desc_struct seg_desc; - u8 dpl, rpl, cpl; + u8 dpl, rpl; unsigned err_vec = GP_VECTOR; u32 err_code = 0; bool null_selector = !(selector & ~0x3); /* 0000-0003 are null */ @@ -1286,7 +1286,6 @@ static int load_segment_descriptor(struc rpl = selector & 3; dpl = seg_desc.dpl; - cpl = ctxt->ops->cpl(ctxt); switch (seg) { case VCPU_SREG_SS: @@ -1349,6 +1348,13 @@ exception: return X86EMUL_PROPAGATE_FAULT; } +static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, + u16 selector, int seg) +{ + u8 cpl = ctxt->ops->cpl(ctxt); + return __load_segment_descriptor(ctxt, selector, seg, cpl); +} + static void write_register_operand(struct operand *op) { /* The 4-byte case *is* correct: in 64-bit mode we zero-extend. */ @@ -2213,6 +2219,7 @@ static int load_state_from_tss16(struct struct tss_segment_16 *tss) { int ret; + u8 cpl; ctxt->_eip = tss->ip; ctxt->eflags = tss->flag | 2; @@ -2235,23 +2242,25 @@ static int load_state_from_tss16(struct set_segment_selector(ctxt, tss->ss, VCPU_SREG_SS); set_segment_selector(ctxt, tss->ds, VCPU_SREG_DS); + cpl = tss->cs & 3; + /* * Now load segment descriptors. If fault happenes at this stage * it is handled in a context of new task */ - ret = load_segment_descriptor(ctxt, tss->ldt, VCPU_SREG_LDTR); + ret = __load_segment_descriptor(ctxt, tss->ldt, VCPU_SREG_LDTR, cpl); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES); + ret = __load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES, cpl); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS); + ret = __load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS, cpl); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS); + ret = __load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS, cpl); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS); + ret = __load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS, cpl); if (ret != X86EMUL_CONTINUE) return ret; @@ -2330,6 +2339,7 @@ static int load_state_from_tss32(struct struct tss_segment_32 *tss) { int ret; + u8 cpl; if (ctxt->ops->set_cr(ctxt, 3, tss->cr3)) return emulate_gp(ctxt, 0); @@ -2346,7 +2356,8 @@ static int load_state_from_tss32(struct /* * SDM says that segment selectors are loaded before segment - * descriptors + * descriptors. This is important because CPL checks will + * use CS.RPL. */ set_segment_selector(ctxt, tss->ldt_selector, VCPU_SREG_LDTR); set_segment_selector(ctxt, tss->es, VCPU_SREG_ES); @@ -2356,29 +2367,31 @@ static int load_state_from_tss32(struct set_segment_selector(ctxt, tss->fs, VCPU_SREG_FS); set_segment_selector(ctxt, tss->gs, VCPU_SREG_GS); + cpl = tss->cs & 3; + /* * Now load segment descriptors. If fault happenes at this stage * it is handled in a context of new task */ - ret = load_segment_descriptor(ctxt, tss->ldt_selector, VCPU_SREG_LDTR); + ret = __load_segment_descriptor(ctxt, tss->ldt_selector, VCPU_SREG_LDTR, cpl); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES); + ret = __load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES, cpl); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS); + ret = __load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS, cpl); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS); + ret = __load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS, cpl); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS); + ret = __load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS, cpl); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->fs, VCPU_SREG_FS); + ret = __load_segment_descriptor(ctxt, tss->fs, VCPU_SREG_FS, cpl); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->gs, VCPU_SREG_GS); + ret = __load_segment_descriptor(ctxt, tss->gs, VCPU_SREG_GS, cpl); if (ret != X86EMUL_CONTINUE) return ret; -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/