Merge tag 'x86_cpu_for_v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 cpu updates from Borislav Petkov:

 - Split MTRR and PAT init code to accomodate at least Xen PV and TDX
   guests which do not get MTRRs exposed but only PAT. (TDX guests do
   not support the cache disabling dance when setting up MTRRs so they
   fall under the same category)

   This is a cleanup work to remove all the ugly workarounds for such
   guests and init things separately (Juergen Gross)

 - Add two new Intel CPUs to the list of CPUs with "normal" Energy
   Performance Bias, leading to power savings

 - Do not do bus master arbitration in C3 (ARB_DISABLE) on modern
   Centaur CPUs

* tag 'x86_cpu_for_v6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (26 commits)
  x86/mtrr: Make message for disabled MTRRs more descriptive
  x86/pat: Handle TDX guest PAT initialization
  x86/cpuid: Carve out all CPUID functionality
  x86/cpu: Switch to cpu_feature_enabled() for X86_FEATURE_XENPV
  x86/cpu: Remove X86_FEATURE_XENPV usage in setup_cpu_entry_area()
  x86/cpu: Drop 32-bit Xen PV guest code in update_task_stack()
  x86/cpu: Remove unneeded 64-bit dependency in arch_enter_from_user_mode()
  x86/cpufeatures: Add X86_FEATURE_XENPV to disabled-features.h
  x86/acpi/cstate: Optimize ARB_DISABLE on Centaur CPUs
  x86/mtrr: Simplify mtrr_ops initialization
  x86/cacheinfo: Switch cache_ap_init() to hotplug callback
  x86: Decouple PAT and MTRR handling
  x86/mtrr: Add a stop_machine() handler calling only cache_cpu_init()
  x86/mtrr: Let cache_aps_delayed_init replace mtrr_aps_delayed_init
  x86/mtrr: Get rid of __mtrr_enabled bool
  x86/mtrr: Simplify mtrr_bp_init()
  x86/mtrr: Remove set_all callback from struct mtrr_ops
  x86/mtrr: Disentangle MTRR init from PAT init
  x86/mtrr: Move cache control code to cacheinfo.c
  x86/mtrr: Split MTRR-specific handling from cache dis/enabling
  ...

1 files changed, 10 insertions, 97 deletions

diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 558108296f3c..ee09d359e08f 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -10,6 +10,7 @@
 #include <linux/mm.h>
 
 #include <asm/processor-flags.h>
+#include <asm/cacheinfo.h>
 #include <asm/cpufeature.h>
 #include <asm/tlbflush.h>
 #include <asm/mtrr.h>
@@ -396,9 +397,6 @@ print_fixed(unsigned base, unsigned step, const mtrr_type *types)
 	}
 }
 
-static void prepare_set(void);
-static void post_set(void);
-
 static void __init print_mtrr_state(void)
 {
 	unsigned int i;
@@ -444,20 +442,6 @@ static void __init print_mtrr_state(void)
 		pr_debug("TOM2: %016llx aka %lldM\n", mtrr_tom2, mtrr_tom2>>20);
 }
 
-/* PAT setup for BP. We need to go through sync steps here */
-void __init mtrr_bp_pat_init(void)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	prepare_set();
-
-	pat_init();
-
-	post_set();
-	local_irq_restore(flags);
-}
-
 /* Grab all of the MTRR state for this CPU into *state */
 bool __init get_mtrr_state(void)
 {
@@ -684,7 +668,10 @@ static u32 deftype_lo, deftype_hi;
 /**
  * set_mtrr_state - Set the MTRR state for this CPU.
  *
- * NOTE: The CPU must already be in a safe state for MTRR changes.
+ * NOTE: The CPU must already be in a safe state for MTRR changes, including
+ *       measures that only a single CPU can be active in set_mtrr_state() in
+ *       order to not be subject to races for usage of deftype_lo. This is
+ *       accomplished by taking cache_disable_lock.
  * RETURNS: 0 if no changes made, else a mask indicating what was changed.
  */
 static unsigned long set_mtrr_state(void)
@@ -715,106 +702,34 @@ static unsigned long set_mtrr_state(void)
 	return change_mask;
 }
 
-
-static unsigned long cr4;
-static DEFINE_RAW_SPINLOCK(set_atomicity_lock);
-
-/*
- * Since we are disabling the cache don't allow any interrupts,
- * they would run extremely slow and would only increase the pain.
- *
- * The caller must ensure that local interrupts are disabled and
- * are reenabled after post_set() has been called.
- */
-static void prepare_set(void) __acquires(set_atomicity_lock)
+void mtrr_disable(void)
 {
-	unsigned long cr0;
-
-	/*
-	 * Note that this is not ideal
-	 * since the cache is only flushed/disabled for this CPU while the
-	 * MTRRs are changed, but changing this requires more invasive
-	 * changes to the way the kernel boots
-	 */
-
-	raw_spin_lock(&set_atomicity_lock);
-
-	/* Enter the no-fill (CD=1, NW=0) cache mode and flush caches. */
-	cr0 = read_cr0() | X86_CR0_CD;
-	write_cr0(cr0);
-
-	/*
-	 * Cache flushing is the most time-consuming step when programming
-	 * the MTRRs. Fortunately, as per the Intel Software Development
-	 * Manual, we can skip it if the processor supports cache self-
-	 * snooping.
-	 */
-	if (!static_cpu_has(X86_FEATURE_SELFSNOOP))
-		wbinvd();
-
-	/* Save value of CR4 and clear Page Global Enable (bit 7) */
-	if (boot_cpu_has(X86_FEATURE_PGE)) {
-		cr4 = __read_cr4();
-		__write_cr4(cr4 & ~X86_CR4_PGE);
-	}
-
-	/* Flush all TLBs via a mov %cr3, %reg; mov %reg, %cr3 */
-	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
-	flush_tlb_local();
-
 	/* Save MTRR state */
 	rdmsr(MSR_MTRRdefType, deftype_lo, deftype_hi);
 
 	/* Disable MTRRs, and set the default type to uncached */
 	mtrr_wrmsr(MSR_MTRRdefType, deftype_lo & ~0xcff, deftype_hi);
-
-	/* Again, only flush caches if we have to. */
-	if (!static_cpu_has(X86_FEATURE_SELFSNOOP))
-		wbinvd();
 }
 
-static void post_set(void) __releases(set_atomicity_lock)
+void mtrr_enable(void)
 {
-	/* Flush TLBs (no need to flush caches - they are disabled) */
-	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
-	flush_tlb_local();
-
 	/* Intel (P6) standard MTRRs */
 	mtrr_wrmsr(MSR_MTRRdefType, deftype_lo, deftype_hi);
-
-	/* Enable caches */
-	write_cr0(read_cr0() & ~X86_CR0_CD);
-
-	/* Restore value of CR4 */
-	if (boot_cpu_has(X86_FEATURE_PGE))
-		__write_cr4(cr4);
-	raw_spin_unlock(&set_atomicity_lock);
 }
 
-static void generic_set_all(void)
+void mtrr_generic_set_state(void)
 {
 	unsigned long mask, count;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	prepare_set();
 
 	/* Actually set the state */
 	mask = set_mtrr_state();
 
-	/* also set PAT */
-	pat_init();
-
-	post_set();
-	local_irq_restore(flags);
-
 	/* Use the atomic bitops to update the global mask */
 	for (count = 0; count < sizeof(mask) * 8; ++count) {
 		if (mask & 0x01)
 			set_bit(count, &smp_changes_mask);
 		mask >>= 1;
 	}
-
 }
 
 /**
@@ -836,7 +751,7 @@ static void generic_set_mtrr(unsigned int reg, unsigned long base,
 	vr = &mtrr_state.var_ranges[reg];
 
 	local_irq_save(flags);
-	prepare_set();
+	cache_disable();
 
 	if (size == 0) {
 		/*
@@ -855,7 +770,7 @@ static void generic_set_mtrr(unsigned int reg, unsigned long base,
 		mtrr_wrmsr(MTRRphysMask_MSR(reg), vr->mask_lo, vr->mask_hi);
 	}
 
-	post_set();
+	cache_enable();
 	local_irq_restore(flags);
 }
 
@@ -914,8 +829,6 @@ int positive_have_wrcomb(void)
  * Generic structure...
  */
 const struct mtrr_ops generic_mtrr_ops = {
-	.use_intel_if		= 1,
-	.set_all		= generic_set_all,
 	.get			= generic_get_mtrr,
 	.get_free_region	= generic_get_free_region,
 	.set			= generic_set_mtrr,