[PATCH v5 04/15] x86/mtrr: support setting MTRR state for software defined MTRRs

[Juergen Gross]

When running virtualized, MTRR access can be reduced (e.g. in Xen PV
guests or when running as a SEV-SNP guest under Hyper-V). Typically
the hypervisor will reset the MTRR feature in CPUID data, resulting
in no MTRR memory type information being available for the kernel.

This has turned out to result in problems:

- Hyper-V SEV-SNP guests using uncached mappings where they shouldn't
- Xen PV dom0 mapping memory as WB which should be UC- instead

Solve those problems by supporting to set a static MTRR state,
overwriting the empty state used today. In case such a state has been
set, don't call get_mtrr_state() in mtrr_bp_init(). The set state
will only be used by mtrr_type_lookup(), as in all other cases
mtrr_enabled() is being checked, which will return false. Accept the
overwrite call only for selected cases when running as a guest.
Disable X86_FEATURE_MTRR in order to avoid any MTRR modifications by
just refusing them.

Signed-off-by: Juergen Gross <jgross@xxxxxxxx>
Tested-by: Michael Kelley <mikelley@xxxxxxxxxxxxx>
---
V2:
- new patch
V3:
- omit fixed MTRRs, as those are currently not needed
- disable X86_FEATURE_MTRR instead of testing it
- provide a stub for !CONFIG_MTRR (Michael Kelley)
- use cpu_feature_enabled() (Boris Petkov)
- add tests for mtrr_overwrite_state() being allowed (Boris Petkov)
V4:
- add test for hv_is_isolation_supported() (Michael Kelley)
V5:
- drop test for running as native (Boris Petkov)
- split large complex test into multiple simple ones (Boris Petkov)
- enhance test in mtrr_bp_init() (Boris Petkov)
---
 arch/x86/include/asm/mtrr.h        |  8 +++++
 arch/x86/kernel/cpu/mtrr/generic.c | 58 +++++++++++++++++++++++++++++-
 arch/x86/kernel/cpu/mtrr/mtrr.c    |  9 +++++
 arch/x86/kernel/setup.c            |  2 ++
 4 files changed, 76 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h
index 4e59f7854950..6decb18e22ed 100644
--- a/arch/x86/include/asm/mtrr.h
+++ b/arch/x86/include/asm/mtrr.h
@@ -49,6 +49,8 @@
  */
 # ifdef CONFIG_MTRR
 void mtrr_bp_init(void);
+void mtrr_overwrite_state(struct mtrr_var_range *var, unsigned int num_var,
+			  mtrr_type def_type);
 extern u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform);
 extern void mtrr_save_fixed_ranges(void *);
 extern void mtrr_save_state(void);
@@ -66,6 +68,12 @@ void mtrr_disable(void);
 void mtrr_enable(void);
 void mtrr_generic_set_state(void);
 #  else
+static inline void mtrr_overwrite_state(struct mtrr_var_range *var,
+					unsigned int num_var,
+					mtrr_type def_type)
+{
+}
+
 static inline u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform)
 {
 	/*
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 9a12da76635c..0794f3f1cc27 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -8,10 +8,12 @@
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/mm.h>
-
+#include <linux/cc_platform.h>
 #include <asm/processor-flags.h>
 #include <asm/cacheinfo.h>
 #include <asm/cpufeature.h>
+#include <asm/hypervisor.h>
+#include <asm/mshyperv.h>
 #include <asm/tlbflush.h>
 #include <asm/mtrr.h>
 #include <asm/msr.h>
@@ -241,6 +243,60 @@ static u8 mtrr_type_lookup_variable(u64 start, u64 end, u64 *partial_end,
 	return mtrr_state.def_type;
 }
 
+/**
+ * mtrr_overwrite_state - set static MTRR state
+ *
+ * Used to set MTRR state via different means (e.g. with data obtained from
+ * a hypervisor).
+ * Is allowed only for special cases when running virtualized. Must be called
+ * from the x86_init.hyper.init_platform() hook.
+ */
+void mtrr_overwrite_state(struct mtrr_var_range *var, unsigned int num_var,
+			  mtrr_type def_type)
+{
+	unsigned int i;
+
+	/* Only allowed to be called once before mtrr_bp_init(). */
+	if (WARN_ON(mtrr_state_set))
+		return;
+
+	/* Only allowed when running virtualized. */
+	if (!cpu_feature_enabled(X86_FEATURE_HYPERVISOR))
+		return;
+
+	/*
+	 * Only allowed for special virtualization cases:
+	 * - when running as SEV-SNP guest
+	 * - when running as Hyper-V isolated guest
+	 * - when running as Xen PV guest
+	 * - when running as TSX guest
+	 */
+	if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP) &&
+	    !hv_is_isolation_supported() &&
+	    !cpu_feature_enabled(X86_FEATURE_XENPV) &&
+	    !cpu_feature_enabled(X86_FEATURE_TDX_GUEST))
+		return;
+
+	/* Disable MTRR in order to disable MTRR modifications. */
+	setup_clear_cpu_cap(X86_FEATURE_MTRR);
+
+	if (var) {
+		if (num_var > MTRR_MAX_VAR_RANGES) {
+			pr_warn("Trying to overwrite MTRR state with %u variable entries\n",
+				num_var);
+			num_var = MTRR_MAX_VAR_RANGES;
+		}
+		for (i = 0; i < num_var; i++)
+			mtrr_state.var_ranges[i] = var[i];
+		num_var_ranges = num_var;
+	}
+
+	mtrr_state.def_type = def_type;
+	mtrr_state.enabled |= MTRR_STATE_MTRR_ENABLED;
+
+	mtrr_state_set = 1;
+}
+
 /**
  * mtrr_type_lookup - look up memory type in MTRR
  *
diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c
index 1beb38f7a7a3..1c19d67ddab3 100644
--- a/arch/x86/kernel/cpu/mtrr/mtrr.c
+++ b/arch/x86/kernel/cpu/mtrr/mtrr.c
@@ -666,6 +666,15 @@ void __init mtrr_bp_init(void)
 	const char *why = "(not available)";
 	unsigned int phys_addr;
 
+	if (!generic_mtrrs && mtrr_state.enabled) {
+		/* Software overwrite of MTRR state, only for generic case. */
+		mtrr_calc_physbits(true);
+		init_table();
+		pr_info("MTRRs set to read-only\n");
+
+		return;
+	}
+
 	phys_addr = mtrr_calc_physbits(generic_mtrrs);
 
 	if (generic_mtrrs) {
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 16babff771bd..0cccfeb67c3a 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1037,6 +1037,8 @@ void __init setup_arch(char **cmdline_p)
 	/*
 	 * VMware detection requires dmi to be available, so this
 	 * needs to be done after dmi_setup(), for the boot CPU.
+	 * For some guest types (Xen PV, SEV-SNP, TDX) it is required to be
+	 * called before cache_bp_init() for setting up MTRR state.
 	 */
 	init_hypervisor_platform();
 
-- 
2.35.3