Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S935336AbcCPXwl (ORCPT ); Wed, 16 Mar 2016 19:52:41 -0400 Received: from g4t3427.houston.hp.com ([15.201.208.55]:47348 "EHLO g4t3427.houston.hp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755986AbcCPXwj (ORCPT ); Wed, 16 Mar 2016 19:52:39 -0400 From: Toshi Kani To: mingo@kernel.org, bp@suse.de, hpa@zytor.com, tglx@linutronix.de Cc: mcgrof@suse.com, jgross@suse.com, paul.gortmaker@windriver.com, konrad.wilk@oracle.com, elliott@hpe.com, x86@kernel.org, xen-devel@lists.xenproject.org, linux-kernel@vger.kernel.org, Toshi Kani Subject: [PATCH v2 1/6] x86/mm/pat: Change PAT to support non-default PAT MSR Date: Wed, 16 Mar 2016 18:44:57 -0600 Message-Id: <1458175502-31936-2-git-send-email-toshi.kani@hpe.com> X-Mailer: git-send-email 2.5.0 In-Reply-To: <1458175502-31936-1-git-send-email-toshi.kani@hpe.com> References: <1458175502-31936-1-git-send-email-toshi.kani@hpe.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4725 Lines: 150 In preparation to fix a regression caused by 'commit 9cd25aac1f44 ("x86/mm/pat: Emulate PAT when it is disabled")', PAT needs to support a case that PAT MSR is initialized with a non-default value. When pat_init() is called in PAT disable state, it initializes PAT table with the BIOS default value. Xen, however, sets PAT MSR with a non-default value to enable WC. This causes inconsistency between PAT table and PAT MSR when PAT is set to disable on Xen. Change pat_init() to handle the PAT disable cases properly. Add pat_keep_handoff_state() to handle two cases when PAT is set to disable. 1. CPU supports PAT: Set PAT table to be consistent with PAT MSR. 2. CPU does not support PAT: Set PAT table to be consistent with PWT and PCD bits in a PTE. Signed-off-by: Toshi Kani Cc: Borislav Petkov Cc: Luis R. Rodriguez Cc: Juergen Gross Cc: Ingo Molnar Cc: H. Peter Anvin Cc: Thomas Gleixner --- arch/x86/mm/pat.c | 80 +++++++++++++++++++++++++++++++++++++++++------------ 1 file changed, 62 insertions(+), 18 deletions(-) diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 04e2e71..e0a34b0 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -207,9 +207,6 @@ static void pat_bsp_init(u64 pat) return; } - if (!pat_enabled()) - goto done; - rdmsrl(MSR_IA32_CR_PAT, tmp_pat); if (!tmp_pat) { pat_disable("PAT MSR is 0, disabled."); @@ -218,15 +215,11 @@ static void pat_bsp_init(u64 pat) wrmsrl(MSR_IA32_CR_PAT, pat); -done: pat_init_cache_modes(pat); } static void pat_ap_init(u64 pat) { - if (!pat_enabled()) - return; - if (!cpu_has_pat) { /* * If this happens we are on a secondary CPU, but switched to @@ -238,18 +231,43 @@ static void pat_ap_init(u64 pat) wrmsrl(MSR_IA32_CR_PAT, pat); } -void pat_init(void) +/** + * pat_keep_handoff_state - Set PAT table to the handoff state + * + * This function keeps PAT in the BIOS handoff state. When CPU supports + * PAT, it sets PAT table to be consistent with PAT MSR. When CPU does not + * support PAT, it emulates PAT by setting PAT table consistent with PWT + * and PCD bits in a PTE. + * + * The PAT table is global to all CPUs, which is initialized once at + * boot-time. Any subsequent calls to this function have no effect. + */ +static void pat_keep_handoff_state(void) { - u64 pat; - struct cpuinfo_x86 *c = &boot_cpu_data; + u64 pat = 0; + static int set_handoff_done; - if (!pat_enabled()) { + if (set_handoff_done) + return; + + if (boot_cpu_has(X86_FEATURE_PAT)) { + /* + * CPU supports PAT. Set PAT table to be consistent with + * PAT MSR. This case supports "nopat" boot option, and + * virtual machine environments which support PAT without + * MTRR. In specific, Xen has unique setup to PAT MSR. + * + * If PAT MSR returns 0, it is considered invalid and emulates + * as No PAT. + */ + rdmsrl(MSR_IA32_CR_PAT, pat); + } + + if (!pat) { /* * No PAT. Emulate the PAT table that corresponds to the two - * cache bits, PWT (Write Through) and PCD (Cache Disable). This - * setup is the same as the BIOS default setup when the system - * has PAT but the "nopat" boot option has been specified. This - * emulated PAT table is used when MSR_IA32_CR_PAT returns 0. + * cache bits, PWT (Write Through) and PCD (Cache Disable). + * This setup is also the same as the BIOS default setup. * * PTE encoding: * @@ -266,10 +284,36 @@ void pat_init(void) */ pat = PAT(0, WB) | PAT(1, WT) | PAT(2, UC_MINUS) | PAT(3, UC) | PAT(4, WB) | PAT(5, WT) | PAT(6, UC_MINUS) | PAT(7, UC); + } + + pat_init_cache_modes(pat); + + set_handoff_done = 1; +} + +/** + * pat_init - Initialize PAT MSR and PAT table + * + * This function initializes PAT MSR and PAT table with an OS-defined value + * to enable additional cache attributes, WC and WT. + * + * This function must be called on all CPUs with the specific sequence of + * operations defined in Intel SDM. mtrr_rendezvous_handler() provides this + * procedure for PAT. + */ +void pat_init(void) +{ + u64 pat; + struct cpuinfo_x86 *c = &boot_cpu_data; + + if (!pat_enabled()) { + pat_keep_handoff_state(); + return; + } - } else if ((c->x86_vendor == X86_VENDOR_INTEL) && - (((c->x86 == 0x6) && (c->x86_model <= 0xd)) || - ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) { + if ((c->x86_vendor == X86_VENDOR_INTEL) && + (((c->x86 == 0x6) && (c->x86_model <= 0xd)) || + ((c->x86 == 0xf) && (c->x86_model <= 0x6)))) { /* * PAT support with the lower four entries. Intel Pentium 2, * 3, M, and 4 are affected by PAT errata, which makes the