x86/mm/pat: Add support of non-default PAT MSR setting

In preparation for fixing a regression caused by:

  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 and PAT is disabled, it initializes the
PAT table with the BIOS default value. Xen, however, sets PAT MSR
with a non-default value to enable WC. This causes inconsistency
between the PAT table and PAT MSR when PAT is set to disable on Xen.

Change pat_init() to handle the PAT disable cases properly.  Add
init_cache_modes() 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.

Note, __init_cache_modes(), renamed from pat_init_cache_modes(),
will be changed to a static function in a later patch.

Signed-off-by: Toshi Kani <toshi.kani@hpe.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Borislav Petkov <bp@suse.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luis R. Rodriguez <mcgrof@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Toshi Kani <toshi.kani@hp.com>
Cc: elliott@hpe.com
Cc: konrad.wilk@oracle.com
Cc: paul.gortmaker@windriver.com
Cc: xen-devel@lists.xenproject.org
Link: http://lkml.kernel.org/r/1458769323-24491-2-git-send-email-toshi.kani@hpe.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

3 files changed, 55 insertions, 22 deletions

diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h
index ca6c228d5e62..97ea55bc2b54 100644
--- a/arch/x86/include/asm/pat.h
+++ b/arch/x86/include/asm/pat.h
@@ -6,7 +6,7 @@
 
 bool pat_enabled(void);
 extern void pat_init(void);
-void pat_init_cache_modes(u64);
+void __init_cache_modes(u64);
 
 extern int reserve_memtype(u64 start, u64 end,
                 enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm);
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index faec01e7a17d..b4663885308f 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -181,7 +181,7 @@ static enum page_cache_mode pat_get_cache_mode(unsigned pat_val, char *msg)
  * configuration.
  * Using lower indices is preferred, so we start with highest index.
  */
-void pat_init_cache_modes(u64 pat)
+void __init_cache_modes(u64 pat)
 {
         enum page_cache_mode cache;
         char pat_msg[33];
@@ -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);
+        __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 +231,32 @@ static void pat_ap_init(u64 pat)
         wrmsrl(MSR_IA32_CR_PAT, pat);
 }
 
-void pat_init(void)
+static void init_cache_modes(void)
 {
-        u64 pat;
-        struct cpuinfo_x86 *c = &boot_cpu_data;
+        u64 pat = 0;
+        static int init_cm_done;
 
-        if (!pat_enabled()) {
+        if (init_cm_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
+                 * MTRRs. 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 +273,36 @@ 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);
+        }
+
+        __init_cache_modes(pat);
+
+        init_cm_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 using 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()) {
+                init_cache_modes();
+                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
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 880862c7d9dd..c469a7c7c309 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1623,7 +1623,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
          * configuration.
          */
         rdmsrl(MSR_IA32_CR_PAT, pat);
-        pat_init_cache_modes(pat);
+        __init_cache_modes(pat);
 
         /* keep using Xen gdt for now; no urgent need to change it */