[PATCH v2 1/6] x86/mm/pat: Change PAT to support non-default PAT MSR

[Toshi Kani]

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 <toshi.kani@xxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxx>
Cc: Luis R. Rodriguez <mcgrof@xxxxxxxx>
Cc: Juergen Gross <jgross@xxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
---
 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