Skip to contentSkip to conversation

MDS basics 0

PATCH Superseded Thomas Gleixner 8 participants 44 messages Feb 27, 2019 – Mar 2, 2019

Subsystems (8)

v5 of 6 Superseded Latest is v6 →

lore
Share & tools
lore
#0 lore raw

v5 cover MDS basics 0

Changes since V4:

- Fix SSB whitelist. Needs to go upstream independently.

- Consolidate whitelists before adding another one.

- Use an inline helper for the exit to user mitigation.

- Add VMX/VMENTER mitigation when CPU is not affected by L1TF.

- Remove 'auto' command line option.

- Rework the mitigation documentation so the handling of special exceptions is clear.

- Adjust the virt mitigation admin documentation.

- Fix typos and address review comments

Available from git:

cvs.ou.linutronix.de:linux/speck/linux WIP.mds

Delta patch and delta diffstat below.

Thanks,

Thomas

8<--------------------

 Documentation/admin-guide/hw-vuln/mds.rst       |   56 +++++++++---
 Documentation/admin-guide/kernel-parameters.txt |   11 --
 Documentation/x86/mds.rst                       |   90 ++++++++++----------
 arch/x86/entry/common.c                         |    7 -
 arch/x86/include/asm/nospec-branch.h            |   11 ++
 arch/x86/include/asm/processor.h                |    1 
 arch/x86/kernel/cpu/bugs.c                      |   25 +----
 arch/x86/kernel/cpu/common.c                    |  108 ++++++++++--------------
 arch/x86/kernel/nmi.c                           |    4 
 arch/x86/kernel/traps.c                         |    4 
 arch/x86/kvm/vmx/vmx.c                          |    2 
 11 files changed, 163 insertions(+), 156 deletions(-)
Documentation/admin-guide/hw-vuln/mds.rst +42 -14
index 151eb40ddadb..73cdc390aece 100644
@@ -50,7 +50,7 @@ may be able to forward this speculative data to a disclosure gadget which
 allows in turn to infer the value via a cache side channel attack.
 
 Because the buffers are potentially shared between Hyper-Threads cross
-Hyper-Thread attacks may be possible.
+Hyper-Thread attacks are possible.
 
 Deeper technical information is available in the MDS specific x86
 architecture section: :ref:`Documentation/x86/mds.rst <mds>`.
@@ -161,14 +161,43 @@ CPU buffer clearing
 Virtualization mitigation
 ^^^^^^^^^^^^^^^^^^^^^^^^^
 
-  If the CPU is also affected by L1TF and the L1D flush mitigation is enabled
-  and up to date microcode is available, the L1D flush mitigation is
-  automatically protecting the guest transition. For details on L1TF and
-  virtualization see:
-  :ref:`Documentation/admin-guide/hw-vuln//l1tf.rst <mitigation_control_kvm>`.
+  The protection for host to guest transition depends on the L1TF
+  vulnerability of the CPU:
 
-  If the L1D flush mitigation is disabled or the microcode is not available
-  the guest transition is unprotected.
+  - CPU is affected by L1TF:
+
+    If the L1D flush mitigation is enabled and up to date microcode is
+    available, the L1D flush mitigation is automatically protecting the
+    guest transition. If the L1D flush mitigation is disabled the MDS
+    mitigation is disabled as well.
+
+    For details on L1TF and virtualization see:
+    :ref:`Documentation/admin-guide/hw-vuln//l1tf.rst <mitigation_control_kvm>`.
+
+  - CPU is not affected by L1TF:
+
+    CPU buffers are flushed before entering the guest when the host MDS
+    protection is enabled.
+
+  The resulting MDS protection matrix for the host to guest transition:
+
+  ============ ===== ============= ============ =================
+   L1TF         MDS   VMX-L1FLUSH   Host MDS     State
+
+   Don't care   No    Don't care    N/A          Not affected
+
+   Yes          Yes   Disabled      Don't care   Vulnerable
+
+   Yes          Yes   Enabled       Don't care   Mitigated
+
+   No           Yes   N/A           Off          Vulnerable
+
+   No           Yes   N/A           Full         Mitigated
+  ============ ===== ============= ============ =================
+
+  This only covers the host to guest transition, i.e. prevents leakage from
+  host to guest, but does not protect the guest internally. Guest need to
+  have their own protections.
 
 .. _xeon_phi:
 
@@ -203,13 +232,10 @@ The kernel command line allows to control the MDS mitigations at boot
 time with the option "mds=". The valid arguments for this option are:
 
   ============  =============================================================
-  auto		Kernel selects the appropriate mitigation mode when the CPU
-		is affected. Defaults to full.
-
-  full		Provides all available mitigations for the MDS vulnerability
-		vulnerability, unconditional CPU buffer clearing on exit to
+  full		If the CPU is vulnerable, enable all available mitigations
+		for the MDS vulnerability, CPU buffer clearing on exit to
 		userspace and when entering a VM. Idle transitions are
-		protect as well.
+		protected as well if SMT is enabled.
 
 		It does not automatically disable SMT.
 
@@ -217,6 +243,8 @@ time with the option "mds=". The valid arguments for this option are:
 
   ============  =============================================================
 
+Not specifying this option is equivalent to "mds=full".
+
 
 Mitigation selection guide
 --------------------------
Documentation/admin-guide/kernel-parameters.txt +3 -8
index 46410fe1ce88..dddb024eb523 100644
@@ -2369,19 +2369,14 @@
 			attack, to access data to which the attacker does
 			not have direct access.
 
-			This parameter controls the MDS mitigation. The the
+			This parameter controls the MDS mitigation. The
 			options are:
 
-			full    - Unconditionally enable MDS mitigation
+			full    - Enable MDS mitigation on vulnerable CPUs
 			off     - Unconditionally disable MDS mitigation
-			auto    - Kernel detects whether the CPU model is
-				  vulnerable to MDS and picks the most
-				  appropriate mitigation. If the CPU is not
-				  vulnerable, "off" is selected. If the CPU
-				  is vulnerable "full" is selected.
 
 			Not specifying this option is equivalent to
-			mds=auto.
+			mds=full.
 
 	mem=nn[KMG]	[KNL,BOOT] Force usage of a specific amount of memory
 			Amount of memory to be used when the kernel is not able
Documentation/x86/mds.rst +49 -41

148 lines not on this page · raw message

arch/x86/entry/common.c +0 -7
index 63da15ced746..19f650d729f5 100644
@@ -181,13 +181,6 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
 	}
 }
 
-static inline void mds_user_clear_cpu_buffers(void)
-{
-	if (!static_branch_likely(&mds_user_clear))
-		return;
-	mds_clear_cpu_buffers();
-}
-
 /* Called with IRQs disabled. */
 __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
 {
arch/x86/include/asm/nospec-branch.h +11 -0
index 3e27ccd6d5c5..4e970390110f 100644
@@ -346,6 +346,17 @@ static inline void mds_clear_cpu_buffers(void)
 	asm volatile("verw %[ds]" : : [ds] "m" (ds) : "cc");
 }
 
+/**
+ * mds_user_clear_cpu_buffers - Mitigation for MDS vulnerability
+ *
+ * Clear CPU buffers if the corresponding static key is enabled
+ */
+static inline void mds_user_clear_cpu_buffers(void)
+{
+	if (static_branch_likely(&mds_user_clear))
+		mds_clear_cpu_buffers();
+}
+
 /**
  * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability
  *
arch/x86/include/asm/processor.h +0 -1
index c3f5e10891a2..aca1ef8cc79f 100644
@@ -994,7 +994,6 @@ extern enum l1tf_mitigations l1tf_mitigation;
 
 enum mds_mitigations {
 	MDS_MITIGATION_OFF,
-	MDS_MITIGATION_AUTO,
 	MDS_MITIGATION_FULL,
 	MDS_MITIGATION_VMWERV,
 };
arch/x86/kernel/cpu/bugs.c +7 -18
index 83b19bb54093..aea871e69d64 100644
@@ -66,6 +66,7 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
 /* Control MDS CPU buffer clear before returning to user space */
 DEFINE_STATIC_KEY_FALSE(mds_user_clear);
+EXPORT_SYMBOL_GPL(mds_user_clear);
 /* Control MDS CPU buffer clear before idling (halt, mwait) */
 DEFINE_STATIC_KEY_FALSE(mds_idle_clear);
 EXPORT_SYMBOL_GPL(mds_idle_clear);
@@ -73,6 +74,7 @@ EXPORT_SYMBOL_GPL(mds_idle_clear);
 void __init check_bugs(void)
 {
 	identify_boot_cpu();
+
 	/*
 	 * identify_boot_cpu() initialized SMT support information, let the
 	 * core code know.
@@ -218,7 +220,7 @@ static void x86_amd_ssb_disable(void)
 #define pr_fmt(fmt)	"MDS: " fmt
 
 /* Default mitigation for L1TF-affected CPUs */
-static enum mds_mitigations mds_mitigation __ro_after_init = MDS_MITIGATION_AUTO;
+static enum mds_mitigations mds_mitigation __ro_after_init = MDS_MITIGATION_FULL;
 
 static const char * const mds_strings[] = {
 	[MDS_MITIGATION_OFF]	= "Vulnerable",
@@ -233,18 +235,10 @@ static void mds_select_mitigation(void)
 		return;
 	}
 
-	switch (mds_mitigation) {
-	case MDS_MITIGATION_OFF:
-		break;
-	case MDS_MITIGATION_AUTO:
-	case MDS_MITIGATION_FULL:
-	case MDS_MITIGATION_VMWERV:
-		if (boot_cpu_has(X86_FEATURE_MD_CLEAR))
-			mds_mitigation = MDS_MITIGATION_FULL;
-		else
+	if (mds_mitigation == MDS_MITIGATION_FULL) {
+		if (!boot_cpu_has(X86_FEATURE_MD_CLEAR))
 			mds_mitigation = MDS_MITIGATION_VMWERV;
 		static_branch_enable(&mds_user_clear);
-		break;
 	}
 	pr_info("%s\n", mds_strings[mds_mitigation]);
 }
@@ -259,8 +253,6 @@ static int __init mds_cmdline(char *str)
 
 	if (!strcmp(str, "off"))
 		mds_mitigation = MDS_MITIGATION_OFF;
-	else if (!strcmp(str, "auto"))
-		mds_mitigation = MDS_MITIGATION_AUTO;
 	else if (!strcmp(str, "full"))
 		mds_mitigation = MDS_MITIGATION_FULL;
 
@@ -702,15 +694,12 @@ void arch_smt_update(void)
 		break;
 	}
 
-	switch (mds_mitigation) {
-	case MDS_MITIGATION_OFF:
-		break;
+	switch(mds_mitigation) {
 	case MDS_MITIGATION_FULL:
 	case MDS_MITIGATION_VMWERV:
 		update_mds_branch_idle();
 		break;
-	/* Keep GCC happy */
-	case MDS_MITIGATION_AUTO:
+	case MDS_MITIGATION_OFF:
 		break;
 	}
 
arch/x86/kernel/cpu/common.c +47 -61

143 lines not on this page · raw message

arch/x86/kernel/nmi.c +1 -3
index 02f7f96dde73..086cf1d1d71d 100644
@@ -535,10 +535,8 @@ do_nmi(struct pt_regs *regs, long error_code)
 	if (this_cpu_dec_return(nmi_state))
 		goto nmi_restart;
 
-	if (!static_branch_likely(&mds_user_clear))
-		return;
 	if (user_mode(regs))
-		mds_clear_cpu_buffers();
+		mds_user_clear_cpu_buffers();
 }
 NOKPROBE_SYMBOL(do_nmi);
 
arch/x86/kernel/traps.c +1 -3
index d2779f4730f5..5942060dba9a 100644
@@ -372,9 +372,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 		 * user space exit, so a CPU buffer clear is required when
 		 * MDS mitigation is enabled.
 		 */
-		if (static_branch_unlikely(&mds_user_clear))
-			mds_clear_cpu_buffers();
-
+		mds_user_clear_cpu_buffers();
 		return;
 	}
 #endif
arch/x86/kvm/vmx/vmx.c +2 -0
index 30a6bcd735ec..b33da789eb67 100644
@@ -6371,6 +6371,8 @@ static void __vmx_vcpu_run(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx)
 
 	if (static_branch_unlikely(&vmx_l1d_should_flush))
 		vmx_l1d_flush(vcpu);
+	else if (static_branch_unlikely(&mds_user_clear))
+		mds_clear_cpu_buffers();
 
 	asm(
 		/* Store host registers */
#1 lore raw

PATCH v5 1/14 MDS basics 1

Subject: [patch V5 01/14] x86/speculation: Add INTEL_FAM6_ATOM_AIRMONT_MID to SSB whitelist
From: Thomas Gleixner <[email protected]>

AIRMONT is not affected by SSB, but AIRMONT_MID is according to the white list. This does not make sense as the SILVERMONT/AIRMONT vulnerabilities are identical otherwise. Also the Intel website which lists the affected CPUs does not have AIRMONT_MID on the list.

Add it to the whitelist.

---
 arch/x86/kernel/cpu/common.c |    1 +
 1 file changed, 1 insertion(+)
arch/x86/kernel/cpu/common.c +1 -0
@@ -971,6 +971,7 @@ static const __initconst struct x86_cpu_
 static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = {
 	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT	},
 	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT		},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT_MID	},
 	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_X	},
 	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_MID	},
 	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_CORE_YONAH		},
#2 lore raw

Re: [patch V5 01/14] MDS basics 1

Quoted 9 lines · speck for Thomas Gleixner

Subject: [patch V5 01/14] x86/speculation: Add INTEL_FAM6_ATOM_AIRMONT_MID to SSB whitelist
From: Thomas Gleixner <[email protected]>

AIRMONT is not affected by SSB, but AIRMONT_MID is according to the white list. This does not make sense as the SILVERMONT/AIRMONT vulnerabilities are identical otherwise. Also the Intel website which lists the affected CPUs does not have AIRMONT_MID on the list.

Add it to the whitelist.

I'll drop that for now and wait for Intel to find the information ...

#3 lore raw

PATCH v5 2/14 MDS basics 2

In reply to Thomas Gleixner

Subject: [patch V5 02/14] x86/msr-index: Cleanup bit defines
From: Thomas Gleixner <[email protected]>

Greg pointed out that speculation related bit defines are using (1 << N) format instead of BIT(N). Aside of that (1 << N) is wrong as it should use 1UL at least.

Clean it up.

---
 arch/x86/include/asm/msr-index.h |   34 ++++++++++++++++++----------------
 1 file changed, 18 insertions(+), 16 deletions(-)
arch/x86/include/asm/msr-index.h +18 -16
@@ -2,6 +2,8 @@
 #ifndef _ASM_X86_MSR_INDEX_H
 #define _ASM_X86_MSR_INDEX_H
 
+#include <linux/bits.h>
+
 /*
  * CPU model specific register (MSR) numbers.
  *
@@ -40,14 +42,14 @@
 /* Intel MSRs. Some also available on other CPUs */
 
 #define MSR_IA32_SPEC_CTRL		0x00000048 /* Speculation Control */
-#define SPEC_CTRL_IBRS			(1 << 0)   /* Indirect Branch Restricted Speculation */
+#define SPEC_CTRL_IBRS			BIT(0)	   /* Indirect Branch Restricted Speculation */
 #define SPEC_CTRL_STIBP_SHIFT		1	   /* Single Thread Indirect Branch Predictor (STIBP) bit */
-#define SPEC_CTRL_STIBP			(1 << SPEC_CTRL_STIBP_SHIFT)	/* STIBP mask */
+#define SPEC_CTRL_STIBP			BIT(SPEC_CTRL_STIBP_SHIFT)	/* STIBP mask */
 #define SPEC_CTRL_SSBD_SHIFT		2	   /* Speculative Store Bypass Disable bit */
-#define SPEC_CTRL_SSBD			(1 << SPEC_CTRL_SSBD_SHIFT)	/* Speculative Store Bypass Disable */
+#define SPEC_CTRL_SSBD			BIT(SPEC_CTRL_SSBD_SHIFT)	/* Speculative Store Bypass Disable */
 
 #define MSR_IA32_PRED_CMD		0x00000049 /* Prediction Command */
-#define PRED_CMD_IBPB			(1 << 0)   /* Indirect Branch Prediction Barrier */
+#define PRED_CMD_IBPB			BIT(0)	   /* Indirect Branch Prediction Barrier */
 
 #define MSR_PPIN_CTL			0x0000004e
 #define MSR_PPIN			0x0000004f
@@ -69,20 +71,20 @@
 #define MSR_MTRRcap			0x000000fe
 
 #define MSR_IA32_ARCH_CAPABILITIES	0x0000010a
-#define ARCH_CAP_RDCL_NO		(1 << 0)   /* Not susceptible to Meltdown */
-#define ARCH_CAP_IBRS_ALL		(1 << 1)   /* Enhanced IBRS support */
-#define ARCH_CAP_SKIP_VMENTRY_L1DFLUSH	(1 << 3)   /* Skip L1D flush on vmentry */
-#define ARCH_CAP_SSB_NO			(1 << 4)   /*
-						    * Not susceptible to Speculative Store Bypass
-						    * attack, so no Speculative Store Bypass
-						    * control required.
-						    */
+#define ARCH_CAP_RDCL_NO		BIT(0)	/* Not susceptible to Meltdown */
+#define ARCH_CAP_IBRS_ALL		BIT(1)	/* Enhanced IBRS support */
+#define ARCH_CAP_SKIP_VMENTRY_L1DFLUSH	BIT(3)	/* Skip L1D flush on vmentry */
+#define ARCH_CAP_SSB_NO			BIT(4)	/*
+						 * Not susceptible to Speculative Store Bypass
+						 * attack, so no Speculative Store Bypass
+						 * control required.
+						 */
 
 #define MSR_IA32_FLUSH_CMD		0x0000010b
-#define L1D_FLUSH			(1 << 0)   /*
-						    * Writeback and invalidate the
-						    * L1 data cache.
-						    */
+#define L1D_FLUSH			BIT(0)	/*
+						 * Writeback and invalidate the
+						 * L1 data cache.
+						 */
 
 #define MSR_IA32_BBL_CR_CTL		0x00000119
 #define MSR_IA32_BBL_CR_CTL3		0x0000011e
#4 lore raw

[MODERATED] Re: [patch V5 02/14] MDS basics 2

arch/x86/include/asm/msr-index.h line 5

Quoted 7 lines · speck for Thomas Gleixner
arch/x86/include/asm/msr-index.h +1 -0
@@ -2,6 +2,8 @@
 #ifndef _ASM_X86_MSR_INDEX_H
 #define _ASM_X86_MSR_INDEX_H
 
+#include <linux/bits.h>

This breaks the build of some tools which rely on this file. The below fixes it:

tools/power/x86/turbostat/Makefile +1 -1
index 2ab25aa38263..ff058bfbca3e 100644
@@ -9,7 +9,7 @@ ifeq ("$(origin O)", "command line")
 endif
 
 turbostat : turbostat.c
-CFLAGS +=	-Wall
+CFLAGS +=	-Wall -I../../../include
 CFLAGS +=	-DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"'
 CFLAGS +=	-DINTEL_FAMILY_HEADER='"../../../../arch/x86/include/asm/intel-family.h"'
 
tools/power/x86/x86_energy_perf_policy/Makefile +1 -1
index f4534fb8b951..da781b430937 100644
@@ -9,7 +9,7 @@ ifeq ("$(origin O)", "command line")
 endif
 
 x86_energy_perf_policy : x86_energy_perf_policy.c
-CFLAGS +=	-Wall
+CFLAGS +=	-Wall -I../../../include
 CFLAGS +=	-DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"'
 
 %: %.c
#5 lore raw

Re: [patch V5 02/14] MDS basics 2

Quoted 11 lines · speck for Josh Poimboeuf

arch/x86/include/asm/msr-index.h line 5

Quoted 7 lines · speck for Thomas Gleixner
arch/x86/include/asm/msr-index.h +1 -0
@@ -2,6 +2,8 @@
 #ifndef _ASM_X86_MSR_INDEX_H
 #define _ASM_X86_MSR_INDEX_H
 
+#include <linux/bits.h>

This breaks the build of some tools which rely on this file. The below fixes it:

Thanks for spotting this. I'll fold it into that change.

Thanks,

tglx

#6 lore raw

[MODERATED] Re: [patch V5 02/14] MDS basics 2

Thomas,

Staring/drooling at the latest cpu_vuln_whitelist table in git, I think I spotted a few differences:

- INTEL_FAM6_ATOM_BONNELL_MID was removed (should be NO_SPECULATION).

- I think INTEL_FAM6_CORE_YONAH had NO_L1TF added.

If those were intentional (which I doubt) then they should go in separate commits.

Signature · 1 line
Josh
#7 lore raw

Re: [patch V5 02/14] MDS basics 2

Josh,

Quoted 9 lines · speck for Josh Poimboeuf

Staring/drooling at the latest cpu_vuln_whitelist table in git, I think I spotted a few differences:

- INTEL_FAM6_ATOM_BONNELL_MID was removed (should be NO_SPECULATION).

- I think INTEL_FAM6_CORE_YONAH had NO_L1TF added.

If those were intentional (which I doubt) then they should go in separate commits.

Definitely not. Thanks for spotting. I'll go over them with a fine comb once again.

Thanks,

tglx

#8 lore raw

PATCH v5 3/14 MDS basics 3

In reply to Thomas Gleixner

Subject: [patch V5 03/14] x86/speculation: Consolidate CPU whitelists
From: Thomas Gleixner <[email protected]>

The CPU vulnerability whitelists have some overlap and there are more whitelists coming along.

Use the driver_data field in the x86_cpu_id struct to denote the whitelisted vulnerabilities and combine all whitelists into one.

---
 arch/x86/kernel/cpu/common.c |   96 ++++++++++++++++++++-----------------------
 1 file changed, 45 insertions(+), 51 deletions(-)
arch/x86/kernel/cpu/common.c +45 -51
@@ -948,62 +948,57 @@ static void identify_cpu_without_cpuid(s
 #endif
 }
 
-static const __initconst struct x86_cpu_id cpu_no_speculation[] = {
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_SALTWELL,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_SALTWELL_TABLET,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_BONNELL_MID,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_SALTWELL_MID,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_BONNELL,	X86_FEATURE_ANY },
-	{ X86_VENDOR_CENTAUR,	5 },
-	{ X86_VENDOR_INTEL,	5 },
-	{ X86_VENDOR_NSC,	5 },
-	{ X86_VENDOR_ANY,	4 },
+#define NO_SPECULATION	BIT(0)
+#define NO_MELTDOWN	BIT(1)
+#define NO_SSB		BIT(2)
+#define NO_L1TF		BIT(3)
+
+static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
+	{ X86_VENDOR_ANY,	4, X86_MODEL_ANY,			X86_FEATURE_ANY, NO_SPECULATION },
+	{ X86_VENDOR_CENTAUR,	5, X86_MODEL_ANY,			X86_FEATURE_ANY, NO_SPECULATION },
+	{ X86_VENDOR_INTEL,	5, X86_MODEL_ANY,			X86_FEATURE_ANY, NO_SPECULATION },
+	{ X86_VENDOR_NSC,	5, X86_MODEL_ANY,			X86_FEATURE_ANY, NO_SPECULATION },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_SALTWELL,		X86_FEATURE_ANY, NO_SPECULATION },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_SALTWELL_TABLET,	X86_FEATURE_ANY, NO_SPECULATION },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_BONNELL_MID,		X86_FEATURE_ANY, NO_SPECULATION },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_SALTWELL_MID,	X86_FEATURE_ANY, NO_SPECULATION },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_BONNELL,		X86_FEATURE_ANY, NO_SPECULATION },
+
+	{ X86_VENDOR_AMD,	X86_FAMILY_ANY, X86_MODEL_ANY,		X86_FEATURE_ANY, NO_MELTDOWN | NO_L1TF },
+	{ X86_VENDOR_HYGON,	X86_FAMILY_ANY, X86_MODEL_ANY,		X86_FEATURE_ANY, NO_MELTDOWN | NO_L1TF },
+
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_SILVERMONT,		X86_FEATURE_ANY, NO_SSB | NO_L1TF },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_SILVERMONT_X,	X86_FEATURE_ANY, NO_SSB | NO_L1TF },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_SILVERMONT_MID,	X86_FEATURE_ANY, NO_SSB | NO_L1TF },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_AIRMONT,		X86_FEATURE_ANY, NO_SSB | NO_L1TF },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_AIRMONT_MID,		X86_FEATURE_ANY, NO_SSB | NO_L1TF },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_CORE_YONAH,		X86_FEATURE_ANY, NO_SSB | NO_L1TF },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_XEON_PHI_KNL,		X86_FEATURE_ANY, NO_SSB | NO_L1TF },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_XEON_PHI_KNM,		X86_FEATURE_ANY, NO_SSB | NO_L1TF },
+
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_GOLDMONT,		X86_FEATURE_ANY, NO_L1TF },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_GOLDMONT_X,		X86_FEATURE_ANY, NO_L1TF },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_GOLDMONT_PLUS,	X86_FEATURE_ANY, NO_L1TF },
+
+	{ X86_VENDOR_AMD,	0x0f, X86_MODEL_ANY,			X86_FEATURE_ANY, NO_SSB },
+	{ X86_VENDOR_AMD,	0x10, X86_MODEL_ANY,			X86_FEATURE_ANY, NO_SSB },
+	{ X86_VENDOR_AMD,	0x11, X86_MODEL_ANY,			X86_FEATURE_ANY, NO_SSB },
+	{ X86_VENDOR_AMD,	0x12, X86_MODEL_ANY,			X86_FEATURE_ANY, NO_SSB },
 	{}
 };
 
-static const __initconst struct x86_cpu_id cpu_no_meltdown[] = {
-	{ X86_VENDOR_AMD },
-	{ X86_VENDOR_HYGON },
-	{}
-};
-
-/* Only list CPUs which speculate but are non susceptible to SSB */
-static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = {
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT		},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT_MID	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_X	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_MID	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_CORE_YONAH		},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNL		},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNM		},
-	{ X86_VENDOR_AMD,	0x12,					},
-	{ X86_VENDOR_AMD,	0x11,					},
-	{ X86_VENDOR_AMD,	0x10,					},
-	{ X86_VENDOR_AMD,	0xf,					},
-	{}
-};
+static bool __init cpu_matches(unsigned long which)
+{
+	const struct x86_cpu_id *m = x86_match_cpu(cpu_vuln_whitelist);
 
-static const __initconst struct x86_cpu_id cpu_no_l1tf[] = {
-	/* in addition to cpu_no_speculation */
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_X	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT		},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_MID	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT_MID	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GOLDMONT	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GOLDMONT_X	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GOLDMONT_PLUS	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNL		},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNM		},
-	{}
-};
+	return m && !!(m->driver_data & which);
+}
 
 static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 {
 	u64 ia32_cap = 0;
 
-	if (x86_match_cpu(cpu_no_speculation))
+	if (cpu_matches(NO_SPECULATION))
 		return;
 
 	setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
@@ -1012,15 +1007,14 @@ static void __init cpu_set_bug_bits(stru
 	if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES))
 		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
 
-	if (!x86_match_cpu(cpu_no_spec_store_bypass) &&
-	   !(ia32_cap & ARCH_CAP_SSB_NO) &&
+	if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) &&
 	   !cpu_has(c, X86_FEATURE_AMD_SSB_NO))
 		setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
 
 	if (ia32_cap & ARCH_CAP_IBRS_ALL)
 		setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED);
 
-	if (x86_match_cpu(cpu_no_meltdown))
+	if (cpu_matches(NO_MELTDOWN))
 		return;
 
 	/* Rogue Data Cache Load? No! */
@@ -1029,7 +1023,7 @@ static void __init cpu_set_bug_bits(stru
 
 	setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
 
-	if (x86_match_cpu(cpu_no_l1tf))
+	if (cpu_matches(NO_L1TF))
 		return;
 
 	setup_force_cpu_bug(X86_BUG_L1TF);
maintainer Reviewed-by on v5 3/14
#9 lore raw

[MODERATED] Re: [patch V5 03/14] MDS basics 3

Quoted 11 lines · speck for Thomas Gleixner

Subject: [patch V5 03/14] x86/speculation: Consolidate CPU whitelists
From: Thomas Gleixner <[email protected]>

The CPU vulnerability whitelists have some overlap and there are more whitelists coming along.

Use the driver_data field in the x86_cpu_id struct to denote the whitelisted vulnerabilities and combine all whitelists into one.

So much nicer and sane:

#10 lore raw

PATCH v5 4/14 MDS basics 4

In reply to Thomas Gleixner

Subject: [patch V5 04/14] x86/speculation/mds: Add basic bug infrastructure for MDS
From: Andi Kleen <[email protected]>

Microarchitectural Data Sampling (MDS), is a class of side channel attacks on internal buffers in Intel CPUs. The variants are:

- Microarchitectural Store Buffer Data Sampling (MSBDS) (CVE-2018-12126)
- Microarchitectural Fill Buffer Data Sampling (MFBDS) (CVE-2018-12130)
- Microarchitectural Load Port Data Sampling (MLPDS) (CVE-2018-12127)

MSBDS leaks Store Buffer Entries which can be speculatively forwarded to a dependent load (store-to-load forwarding) as an optimization. The forward can also happen to a faulting or assisting load operation for a different memory address, which can be exploited under certain conditions. Store buffers are partitioned between Hyper-Threads so cross thread forwarding is not possible. But if a thread enters or exits a sleep state the store buffer is repartitioned which can expose data from one thread to the other.

MFBDS leaks Fill Buffer Entries. Fill buffers are used internally to manage L1 miss situations and to hold data which is returned or sent in response to a memory or I/O operation. Fill buffers can forward data to a load operation and also write data to the cache. When the fill buffer is deallocated it can retain the stale data of the preceding operations which can then be forwarded to a faulting or assisting load operation, which can be exploited under certain conditions. Fill buffers are shared between Hyper-Threads so cross thread leakage is possible.

MLDPS leaks Load Port Data. Load ports are used to perform load operations from memory or I/O. The received data is then forwarded to the register file or a subsequent operation. In some implementations the Load Port can contain stale data from a previous operation which can be forwarded to faulting or assisting loads under certain conditions, which again can be exploited eventually. Load ports are shared between Hyper-Threads so cross thread leakage is possible.

All variants have the same mitigation for single CPU thread case (SMT off), so the kernel can treat them as one MDS issue.

Add the basic infrastructure to detect if the current CPU is affected by MDS.

[ tglx: Rewrote changelog ]

---
V5: Adopt to the consolidated quirk table
V3: Addressed Borislav's review comments

---
 arch/x86/include/asm/cpufeatures.h |    2 ++
 arch/x86/include/asm/msr-index.h   |    5 +++++
 arch/x86/kernel/cpu/common.c       |   10 +++++++---
 3 files changed, 14 insertions(+), 3 deletions(-)
arch/x86/include/asm/cpufeatures.h +2 -0
@@ -344,6 +344,7 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */
 #define X86_FEATURE_AVX512_4VNNIW	(18*32+ 2) /* AVX-512 Neural Network Instructions */
 #define X86_FEATURE_AVX512_4FMAPS	(18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
+#define X86_FEATURE_MD_CLEAR		(18*32+10) /* VERW clears CPU buffers */
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
@@ -381,5 +382,6 @@
 #define X86_BUG_SPECTRE_V2		X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
 #define X86_BUG_SPEC_STORE_BYPASS	X86_BUG(17) /* CPU is affected by speculative store bypass attack */
 #define X86_BUG_L1TF			X86_BUG(18) /* CPU is affected by L1 Terminal Fault */
+#define X86_BUG_MDS			X86_BUG(19) /* CPU is affected by Microarchitectural data sampling */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
arch/x86/include/asm/msr-index.h +5 -0
@@ -79,6 +79,11 @@
 						 * attack, so no Speculative Store Bypass
 						 * control required.
 						 */
+#define ARCH_CAP_MDS_NO			BIT(5)   /*
+						  * Not susceptible to
+						  * Microarchitectural Data
+						  * Sampling (MDS) vulnerabilities.
+						  */
 
 #define MSR_IA32_FLUSH_CMD		0x0000010b
 #define L1D_FLUSH			BIT(0)	/*
arch/x86/kernel/cpu/common.c +7 -3
@@ -952,6 +952,7 @@ static void identify_cpu_without_cpuid(s
 #define NO_MELTDOWN	BIT(1)
 #define NO_SSB		BIT(2)
 #define NO_L1TF		BIT(3)
+#define NO_MDS		BIT(4)
 
 static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 	{ X86_VENDOR_ANY,	4, X86_MODEL_ANY,			X86_FEATURE_ANY, NO_SPECULATION },
@@ -976,9 +977,9 @@ static const __initconst struct x86_cpu_
 	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_XEON_PHI_KNL,		X86_FEATURE_ANY, NO_SSB | NO_L1TF },
 	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_XEON_PHI_KNM,		X86_FEATURE_ANY, NO_SSB | NO_L1TF },
 
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_GOLDMONT,		X86_FEATURE_ANY, NO_L1TF },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_GOLDMONT_X,		X86_FEATURE_ANY, NO_L1TF },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_GOLDMONT_PLUS,	X86_FEATURE_ANY, NO_L1TF },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_GOLDMONT,		X86_FEATURE_ANY, NO_L1TF | NO_MDS },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_GOLDMONT_X,		X86_FEATURE_ANY, NO_L1TF | NO_MDS },
+	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_GOLDMONT_PLUS,	X86_FEATURE_ANY, NO_L1TF | NO_MDS },
 
 	{ X86_VENDOR_AMD,	0x0f, X86_MODEL_ANY,			X86_FEATURE_ANY, NO_SSB },
 	{ X86_VENDOR_AMD,	0x10, X86_MODEL_ANY,			X86_FEATURE_ANY, NO_SSB },
@@ -1014,6 +1015,9 @@ static void __init cpu_set_bug_bits(stru
 	if (ia32_cap & ARCH_CAP_IBRS_ALL)
 		setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED);
 
+	if (!cpu_matches(NO_MDS) && !(ia32_cap & ARCH_CAP_MDS_NO))
+		setup_force_cpu_bug(X86_BUG_MDS);
+
 	if (cpu_matches(NO_MELTDOWN))
 		return;
 
#11 lore raw

PATCH v5 5/14 MDS basics 5

In reply to Thomas Gleixner

From: Andi Kleen <[email protected]>
Subject: [patch V5 05/14] x86/kvm: Expose X86_FEATURE_MD_CLEAR to guests

X86_FEATURE_MD_CLEAR is a new CPUID bit which is set when microcode provides the mechanism to invoke a flush of various exploitable CPU buffers by invoking the VERW instruction.

Hand it through to guests so they can adjust their mitigations.

This also requires corresponding qemu changes, which are available separately.

[ tglx: Massaged changelog ]

---
 arch/x86/kvm/cpuid.c |    3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)
arch/x86/kvm/cpuid.c +2 -1
@@ -410,7 +410,8 @@ static inline int __do_cpuid_ent(struct
 	/* cpuid 7.0.edx*/
 	const u32 kvm_cpuid_7_0_edx_x86_features =
 		F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) |
-		F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP);
+		F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) |
+		F(MD_CLEAR);
 
 	/* all calls to cpuid_count() should be made on the same cpu */
 	get_cpu();
#12 lore raw

PATCH v5 6/14 MDS basics 6

In reply to Thomas Gleixner

Subject: [patch V5 06/14] x86/speculation/mds: Add mds_clear_cpu_buffers()
From: Thomas Gleixner <[email protected]>

The Microarchitectural Data Sampling (MDS) vulernabilities are mitigated by clearing the affected CPU buffers. The mechanism for clearing the buffers uses the unused and obsolete VERW instruction in combination with a microcode update which triggers a CPU buffer clear when VERW is executed.

Provide a inline function with the assembly magic. The argument of the VERW instruction must be a memory operand as documented:

"MD_CLEAR enumerates that the memory-operand variant of VERW (for
example, VERW m16) has been extended to also overwrite buffers affected by MDS. This buffer overwriting functionality is not guaranteed for the register operand variant of VERW."

Documentation also recommends to use a writable data segment selector:

"The buffer overwriting occurs regardless of the result of the VERW
permission check, as well as when the selector is null or causes a descriptor load segment violation. However, for lowest latency we recommend using a selector that indicates a valid writable data segment."

Add x86 specific documentation about MDS and the internal workings of the mitigation.

---
v4 --> V5: Fix typos and remove the conditional mode reference.

V3 --> V4: Document the segment selecor choice as well.

V2 --> V3: Add VERW documentation and fix typos/grammar..., dropped 'i(0)'
Add more details fo the documentation file

V1 --> V2: Add "cc" clobber and documentation

---
 Documentation/index.rst              |    1 
 Documentation/x86/conf.py            |   10 +++
 Documentation/x86/index.rst          |    8 ++
 Documentation/x86/mds.rst            |   99 +++++++++++++++++++++++++++++++++++
 arch/x86/include/asm/nospec-branch.h |   25 ++++++++
 5 files changed, 143 insertions(+)
Documentation/index.rst +1 -0
@@ -101,6 +101,7 @@ implementation.
    :maxdepth: 2
 
    sh/index
+   x86/index
 
 Filesystem Documentation
 ------------------------
Documentation/x86/conf.py new file +10 -0
@@ -0,0 +1,10 @@
+# -*- coding: utf-8; mode: python -*-
+
+project = "X86 architecture specific documentation"
+
+tags.add("subproject")
+
+latex_documents = [
+    ('index', 'x86.tex', project,
+     'The kernel development community', 'manual'),
+]
Documentation/x86/index.rst new file +8 -0
@@ -0,0 +1,8 @@
+==========================
+x86 architecture specifics
+==========================
+
+.. toctree::
+   :maxdepth: 1
+
+   mds
Documentation/x86/mds.rst new file +99 -0

99 lines not on this page · raw message

arch/x86/include/asm/nospec-branch.h +25 -0
@@ -318,6 +318,31 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_
 DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
 DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
+#include <asm/segment.h>
+
+/**
+ * mds_clear_cpu_buffers - Mitigation for MDS vulnerability
+ *
+ * This uses the otherwise unused and obsolete VERW instruction in
+ * combination with microcode which triggers a CPU buffer flush when the
+ * instruction is executed.
+ */
+static inline void mds_clear_cpu_buffers(void)
+{
+	static const u16 ds = __KERNEL_DS;
+
+	/*
+	 * Has to be the memory-operand variant because only that
+	 * guarantees the CPU buffer flush functionality according to
+	 * documentation. The register-operand variant does not.
+	 * Works with any segment selector, but a valid writable
+	 * data segment is the fastest variant.
+	 *
+	 * "cc" clobber is required because VERW modifies ZF.
+	 */
+	asm volatile("verw %[ds]" : : [ds] "m" (ds) : "cc");
+}
+
 #endif /* __ASSEMBLY__ */
 
 /*
#13 lore raw

PATCH v5 7/14 MDS basics 7

In reply to Thomas Gleixner

Subject: [patch V5 07/14] x86/speculation/mds: Clear CPU buffers on exit to user
From: Thomas Gleixner <[email protected]>

Add a static key which controls the invocation of the CPU buffer clear mechanism on exit to user space and add the call into prepare_exit_to_usermode() and do_nmi() right before actually returning.

Add documentation which kernel to user space transition this covers and explain why some corner cases are not mitigated.

---
V4 --> v5: Use an inline helper instead of open coding it.
Rework the documentation paragraph about exceptions.

V3 --> V4: Add #DS mitigation and document that the #MC corner case
is really not interesting.

V3: Add NMI conditional on user regs and update documentation accordingly.
Use the static branch scheme suggested by Peter. Fix typos ...

---
 Documentation/x86/mds.rst            |   52 +++++++++++++++++++++++++++++++++++
 arch/x86/entry/common.c              |    3 ++
 arch/x86/include/asm/nospec-branch.h |   13 ++++++++
 arch/x86/kernel/cpu/bugs.c           |    3 ++
 arch/x86/kernel/nmi.c                |    4 ++
 arch/x86/kernel/traps.c              |    7 ++++
 6 files changed, 82 insertions(+)
Documentation/x86/mds.rst +52 -0
@@ -97,3 +97,55 @@ According to current knowledge additiona
 itself are not required because the necessary gadgets to expose the leaked
 data cannot be controlled in a way which allows exploitation from malicious
 user space or VM guests.
+
+Mitigation points
+-----------------
+
+1. Return to user space
+^^^^^^^^^^^^^^^^^^^^^^^
+
+   When transitioning from kernel to user space the CPU buffers are flushed
+   on affected CPUs when the mitigation is not disabled on the kernel
+   command line. The migitation is enabled through the static key
+   mds_user_clear.
+
+   The mitigation is invoked in prepare_exit_to_usermode() which covers
+   most of the kernel to user space transitions. There are a few exceptions
+   which are not invoking prepare_exit_to_usermode() on return to user
+   space. These exceptions use the paranoid exit code.
+
+   - Non Maskable Interrupt (NMI):
+
+     Access to sensible data like keys, credentials in the NMI context is
+     mostly theoretical: The CPU can do prefetching or execute a
+     misspeculated code path and thereby fetching data which might end up
+     leaking through a buffer.
+
+     But for mounting other attacks the kernel stack address of the task is
+     already valuable information. So in full mitigation mode, the NMI is
+     mitigated on the return from do_nmi() to provide almost complete
+     coverage.
+
+   - Double fault (#DF):
+
+     A double fault is usually fatal, but the ESPFIX workaround, which can
+     be triggered from user space through modify_ldt(2) is a recoverable
+     double fault. #DF uses the paranoid exit path, so explicit mitigation
+     in the double fault handler is required.
+
+   - Machine Check Exception (#MC):
+
+     Another corner case is a #MC which hits between the CPU buffer clear
+     invocation and the actual return to user. As this still is in kernel
+     space it takes the paranoid exit path which does not clear the CPU
+     buffers. So the #MC handler repopulates the buffers to some
+     extent. Machine checks are not reliably controllable and the window is
+     extremly small so mitigation would just tick a checkbox that this
+     theoretical corner case is covered. To keep the amount of special
+     cases small, ignore #MC.
+
+   - Debug Exception (#DB):
+
+     This takes the paranoid exit path only when the INT1 breakpoint is in
+     kernel space. #DB on a user space address takes the regular exit path,
+     so no extra mitigation required.
arch/x86/entry/common.c +3 -0
@@ -31,6 +31,7 @@
 #include <asm/vdso.h>
 #include <linux/uaccess.h>
 #include <asm/cpufeature.h>
+#include <asm/nospec-branch.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
@@ -212,6 +213,8 @@ static void exit_to_usermode_loop(struct
 #endif
 
 	user_enter_irqoff();
+
+	mds_user_clear_cpu_buffers();
 }
 
 #define SYSCALL_EXIT_WORK_FLAGS				\
arch/x86/include/asm/nospec-branch.h +13 -0
@@ -318,6 +318,8 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_
 DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
 DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
+DECLARE_STATIC_KEY_FALSE(mds_user_clear);
+
 #include <asm/segment.h>
 
 /**
@@ -343,6 +345,17 @@ static inline void mds_clear_cpu_buffers
 	asm volatile("verw %[ds]" : : [ds] "m" (ds) : "cc");
 }
 
+/**
+ * mds_user_clear_cpu_buffers - Mitigation for MDS vulnerability
+ *
+ * Clear CPU buffers if the corresponding static key is enabled
+ */
+static inline void mds_user_clear_cpu_buffers(void)
+{
+	if (static_branch_likely(&mds_user_clear))
+		mds_clear_cpu_buffers();
+}
+
 #endif /* __ASSEMBLY__ */
 
 /*
arch/x86/kernel/cpu/bugs.c +3 -0
@@ -63,6 +63,9 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_i
 /* Control unconditional IBPB in switch_mm() */
 DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
+/* Control MDS CPU buffer clear before returning to user space */
+DEFINE_STATIC_KEY_FALSE(mds_user_clear);
+
 void __init check_bugs(void)
 {
 	identify_boot_cpu();
arch/x86/kernel/nmi.c +4 -0
@@ -34,6 +34,7 @@
 #include <asm/x86_init.h>
 #include <asm/reboot.h>
 #include <asm/cache.h>
+#include <asm/nospec-branch.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/nmi.h>
@@ -533,6 +534,9 @@ do_nmi(struct pt_regs *regs, long error_
 		write_cr2(this_cpu_read(nmi_cr2));
 	if (this_cpu_dec_return(nmi_state))
 		goto nmi_restart;
+
+	if (user_mode(regs))
+		mds_user_clear_cpu_buffers();
 }
 NOKPROBE_SYMBOL(do_nmi);
 
arch/x86/kernel/traps.c +7 -0
@@ -366,6 +366,13 @@ dotraplinkage void do_double_fault(struc
 		regs->ip = (unsigned long)general_protection;
 		regs->sp = (unsigned long)&gpregs->orig_ax;
 
+		/*
+		 * This situation can be triggered by userspace via
+		 * modify_ldt(2) and the return does not take the regular
+		 * user space exit, so a CPU buffer clear is required when
+		 * MDS mitigation is enabled.
+		 */
+		mds_user_clear_cpu_buffers();
 		return;
 	}
 #endif
maintainer Reviewed-by on v5 7/14
#14 lore raw

[MODERATED] Re: [patch V5 07/14] MDS basics 7

Quoted 11 lines · speck for Thomas Gleixner

Subject: [patch V5 07/14] x86/speculation/mds: Clear CPU buffers on exit to user
From: Thomas Gleixner <[email protected]>

Add a static key which controls the invocation of the CPU buffer clear mechanism on exit to user space and add the call into prepare_exit_to_usermode() and do_nmi() right before actually returning.

Add documentation which kernel to user space transition this covers and explain why some corner cases are not mitigated.

#15 lore raw

PATCH v5 8/14 MDS basics 8

In reply to Thomas Gleixner

CPUs which are affected by L1TF and MDS mitigate MDS with the L1D Flush on VMENTER when updated microcode is installed. CPUs which are not affected by L1TF but affected by MDS need explicit MDS mitigation.

For these cases, follow the host mitigation state and invoke the MDS mitigation before VMENTER.

---
 arch/x86/kernel/cpu/bugs.c |    1 +
 arch/x86/kvm/vmx/vmx.c     |    2 ++
 2 files changed, 3 insertions(+)
arch/x86/kernel/cpu/bugs.c +1 -0
@@ -65,6 +65,7 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_always
 
 /* Control MDS CPU buffer clear before returning to user space */
 DEFINE_STATIC_KEY_FALSE(mds_user_clear);
+EXPORT_SYMBOL_GPL(mds_user_clear);
 
 void __init check_bugs(void)
 {
arch/x86/kvm/vmx/vmx.c +2 -0
@@ -6371,6 +6371,8 @@ static void __vmx_vcpu_run(struct kvm_vc
 
 	if (static_branch_unlikely(&vmx_l1d_should_flush))
 		vmx_l1d_flush(vcpu);
+	else if (static_branch_unlikely(&mds_user_clear))
+		mds_clear_cpu_buffers();
 
 	asm(
 		/* Store host registers */
maintainer Reviewed-by on v5 8/14
#16 lore raw

[MODERATED] Re: [patch V5 08/14] MDS basics 8

Quoted 8 lines · speck for Thomas Gleixner

CPUs which are affected by L1TF and MDS mitigate MDS with the L1D Flush on VMENTER when updated microcode is installed. CPUs which are not affected by L1TF but affected by MDS need explicit MDS mitigation.

For these cases, follow the host mitigation state and invoke the MDS mitigation before VMENTER.

#17 lore raw

PATCH v5 9/14 MDS basics 9

In reply to Thomas Gleixner

Subject: [patch V5 09/14] x86/speculation/mds: Conditionally clear CPU buffers on idle entry
From: Thomas Gleixner <[email protected]>

Add a static key which controls the invocation of the CPU buffer clear mechanism on idle entry. This is independent of other MDS mitigations because the idle entry invocation to mitigate the potential leakage due to store buffer repartitioning is only necessary on SMT systems.

Add the actual invocations to the different halt/mwait variants which covers all usage sites. mwaitx is not patched as it's not available on Intel CPUs.

The buffer clear is only invoked before entering the C-State to prevent that stale data from the idling CPU is spilled to the Hyper-Thread sibling after the Store buffer got repartitioned and all entries are available to the non idle sibling.

When coming out of idle the store buffer is partitioned again so each sibling has half of it available. Now CPU which returned from idle could be speculatively exposed to contents of the sibling, but the buffers are flushed either on exit to user space or on VMENTER.

When later on conditional buffer clearing is implemented on top of this, then there is no action required either because before returning to user space the context switch will set the condition flag which causes a flush on the return to user path.

This intentionally does not handle the case in the acpi/processor_idle driver which uses the legacy IO port interface for C-State transitions for two reasons:

- The acpi/processor_idle driver was replaced by the intel_idle driver almost a decade ago. Anything Nehalem upwards supports it and defaults to that new driver.

- The legacy IO port interface is likely to be used on older and therefore unaffected CPUs or on systems which do not receive microcode updates anymore, so there is no point in adding that.

---
V4: Export mds_idle_clear
V3: Adjust document wording

---
 Documentation/x86/mds.rst            |   35 +++++++++++++++++++++++++++++++++++
 arch/x86/include/asm/irqflags.h      |    4 ++++
 arch/x86/include/asm/mwait.h         |    7 +++++++
 arch/x86/include/asm/nospec-branch.h |   12 ++++++++++++
 arch/x86/kernel/cpu/bugs.c           |    3 +++
 5 files changed, 61 insertions(+)
Documentation/x86/mds.rst +35 -0
@@ -149,3 +149,38 @@ Mitigation points
      This takes the paranoid exit path only when the INT1 breakpoint is in
      kernel space. #DB on a user space address takes the regular exit path,
      so no extra mitigation required.
+
+
+2. C-State transition
+^^^^^^^^^^^^^^^^^^^^^
+
+   When a CPU goes idle and enters a C-State the CPU buffers need to be
+   cleared on affected CPUs when SMT is active. This addresses the
+   repartitioning of the store buffer when one of the Hyper-Threads enters
+   a C-State.
+
+   When SMT is inactive, i.e. either the CPU does not support it or all
+   sibling threads are offline CPU buffer clearing is not required.
+
+   The invocation is controlled by the static key mds_idle_clear which is
+   switched depending on the chosen mitigation mode and the SMT state of
+   the system.
+
+   The buffer clear is only invoked before entering the C-State to prevent
+   that stale data from the idling CPU from spilling to the Hyper-Thread
+   sibling after the store buffer got repartitioned and all entries are
+   available to the non idle sibling.
+
+   When coming out of idle the store buffer is partitioned again so each
+   sibling has half of it available. The back from idle CPU could be then
+   speculatively exposed to contents of the sibling. The buffers are
+   flushed either on exit to user space or on VMENTER so malicious code
+   in user space or the guest cannot speculatively access them.
+
+   The mitigation is hooked into all variants of halt()/mwait(), but does
+   not cover the legacy ACPI IO-Port mechanism because the ACPI idle driver
+   has been superseded by the intel_idle driver around 2010 and is
+   preferred on all affected CPUs which are expected to gain the MD_CLEAR
+   functionality in microcode. Aside of that the IO-Port mechanism is a
+   legacy interface which is only used on older systems which are either
+   not affected or do not receive microcode updates anymore.
arch/x86/include/asm/irqflags.h +4 -0
@@ -6,6 +6,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/nospec-branch.h>
+
 /* Provide __cpuidle; we can't safely include <linux/cpu.h> */
 #define __cpuidle __attribute__((__section__(".cpuidle.text")))
 
@@ -54,11 +56,13 @@ static inline void native_irq_enable(voi
 
 static inline __cpuidle void native_safe_halt(void)
 {
+	mds_idle_clear_cpu_buffers();
 	asm volatile("sti; hlt": : :"memory");
 }
 
 static inline __cpuidle void native_halt(void)
 {
+	mds_idle_clear_cpu_buffers();
 	asm volatile("hlt": : :"memory");
 }
 
arch/x86/include/asm/mwait.h +7 -0
@@ -6,6 +6,7 @@
 #include <linux/sched/idle.h>
 
 #include <asm/cpufeature.h>
+#include <asm/nospec-branch.h>
 
 #define MWAIT_SUBSTATE_MASK		0xf
 #define MWAIT_CSTATE_MASK		0xf
@@ -40,6 +41,8 @@ static inline void __monitorx(const void
 
 static inline void __mwait(unsigned long eax, unsigned long ecx)
 {
+	mds_idle_clear_cpu_buffers();
+
 	/* "mwait %eax, %ecx;" */
 	asm volatile(".byte 0x0f, 0x01, 0xc9;"
 		     :: "a" (eax), "c" (ecx));
@@ -74,6 +77,8 @@ static inline void __mwait(unsigned long
 static inline void __mwaitx(unsigned long eax, unsigned long ebx,
 			    unsigned long ecx)
 {
+	/* No MDS buffer clear as this is AMD/HYGON only */
+
 	/* "mwaitx %eax, %ebx, %ecx;" */
 	asm volatile(".byte 0x0f, 0x01, 0xfb;"
 		     :: "a" (eax), "b" (ebx), "c" (ecx));
@@ -81,6 +86,8 @@ static inline void __mwaitx(unsigned lon
 
 static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
 {
+	mds_idle_clear_cpu_buffers();
+
 	trace_hardirqs_on();
 	/* "mwait %eax, %ecx;" */
 	asm volatile("sti; .byte 0x0f, 0x01, 0xc9;"
arch/x86/include/asm/nospec-branch.h +12 -0
@@ -319,6 +319,7 @@ DECLARE_STATIC_KEY_FALSE(switch_mm_cond_
 DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
 DECLARE_STATIC_KEY_FALSE(mds_user_clear);
+DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
 
 #include <asm/segment.h>
 
@@ -356,6 +357,17 @@ static inline void mds_user_clear_cpu_bu
 		mds_clear_cpu_buffers();
 }
 
+/**
+ * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability
+ *
+ * Clear CPU buffers if the corresponding static key is enabled
+ */
+static inline void mds_idle_clear_cpu_buffers(void)
+{
+	if (static_branch_likely(&mds_idle_clear))
+		mds_clear_cpu_buffers();
+}
+
 #endif /* __ASSEMBLY__ */
 
 /*
arch/x86/kernel/cpu/bugs.c +3 -0
@@ -66,6 +66,9 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_always
 /* Control MDS CPU buffer clear before returning to user space */
 DEFINE_STATIC_KEY_FALSE(mds_user_clear);
 EXPORT_SYMBOL_GPL(mds_user_clear);
+/* Control MDS CPU buffer clear before idling (halt, mwait) */
+DEFINE_STATIC_KEY_FALSE(mds_idle_clear);
+EXPORT_SYMBOL_GPL(mds_idle_clear);
 
 void __init check_bugs(void)
 {
#18 lore raw

[MODERATED] Re: [patch V5 09/14] MDS basics 9

Quoted 8 lines · speck for Thomas Gleixner

Subject: [patch V5 09/14] x86/speculation/mds: Conditionally clear CPU buffers on idle entry
From: Thomas Gleixner <[email protected]>

Add a static key which controls the invocation of the CPU buffer clear mechanism on idle entry. This is independent of other MDS mitigations because the idle entry invocation to mitigate the potential leakage due to store buffer repartitioning is only necessary on SMT systems.

Quoted 8 lines

Add the actual invocations to the different halt/mwait variants which covers all usage sites. mwaitx is not patched as it's not available on Intel CPUs.

The buffer clear is only invoked before entering the C-State to prevent that stale data from the idling CPU is spilled to the Hyper-Thread sibling after the Store buffer got repartitioned and all entries are available to the non idle sibling.

Andrea brought up a good question privately -- this patch mitigates MSBDS for HT, but HT will still be susceptible to the other two MDS issues. So what's the point? It seems this patch only protects people who don't care about MDS in the first place.

Signature · 1 line
Josh
#19 lore raw

Re: [patch V5 09/14] MDS basics 9

Quoted 18 lines · speck for Josh Poimboeuf
Quoted 8 lines · speck for Thomas Gleixner

Subject: [patch V5 09/14] x86/speculation/mds: Conditionally clear CPU buffers on idle entry
From: Thomas Gleixner <[email protected]>

Add a static key which controls the invocation of the CPU buffer clear mechanism on idle entry. This is independent of other MDS mitigations because the idle entry invocation to mitigate the potential leakage due to store buffer repartitioning is only necessary on SMT systems.

Quoted 8 lines

Add the actual invocations to the different halt/mwait variants which covers all usage sites. mwaitx is not patched as it's not available on Intel CPUs.

The buffer clear is only invoked before entering the C-State to prevent that stale data from the idling CPU is spilled to the Hyper-Thread sibling after the Store buffer got repartitioned and all entries are available to the non idle sibling.

Quoted 4 lines

Andrea brought up a good question privately -- this patch mitigates MSBDS for HT, but HT will still be susceptible to the other two MDS issues. So what's the point? It seems this patch only protects people who don't care about MDS in the first place.

Indeed for most CPU models it's pointless.

The ones which are only affected by MSBDS are Atom Silvermont/Airmont which are all single threaded and the XEON PHIs.

For XEON PHI it actually makes sense because XEON PHI does not have L1TF either.

But yes, for everything else it's just window dressing.

Thanks,

tglx

#20 lore raw

[MODERATED] Re: [patch V5 09/14] MDS basics 9

Quoted 26 lines · speck for Thomas Gleixner
Quoted 18 lines · speck for Josh Poimboeuf
Quoted 8 lines · speck for Thomas Gleixner

Subject: [patch V5 09/14] x86/speculation/mds: Conditionally clear CPU buffers on idle entry
From: Thomas Gleixner <[email protected]>

Add a static key which controls the invocation of the CPU buffer clear mechanism on idle entry. This is independent of other MDS mitigations because the idle entry invocation to mitigate the potential leakage due to store buffer repartitioning is only necessary on SMT systems.

Quoted 8 lines

Add the actual invocations to the different halt/mwait variants which covers all usage sites. mwaitx is not patched as it's not available on Intel CPUs.

The buffer clear is only invoked before entering the C-State to prevent that stale data from the idling CPU is spilled to the Hyper-Thread sibling after the Store buffer got repartitioned and all entries are available to the non idle sibling.

Quoted 4 lines

Andrea brought up a good question privately -- this patch mitigates MSBDS for HT, but HT will still be susceptible to the other two MDS issues. So what's the point? It seems this patch only protects people who don't care about MDS in the first place.

Indeed for most CPU models it's pointless.

Quoted 7 lines

The ones which are only affected by MSBDS are Atom Silvermont/Airmont which are all single threaded and the XEON PHIs.

For XEON PHI it actually makes sense because XEON PHI does not have L1TF either.

But yes, for everything else it's just window dressing.

Makes sense. I didn't realize that some CPUs were affected by MSBDS and not other MDSes.

Can you add that justification to the documentation and/or patch description?

Signature · 1 line
Josh
#21 lore raw

[MODERATED] Re: [patch V5 09/14] MDS basics 9

Quoted 33 lines · Josh Poimboeuf
Quoted 32 lines · speck for Thomas Gleixner
Quoted 18 lines · speck for Josh Poimboeuf
Quoted 8 lines · speck for Thomas Gleixner

Subject: [patch V5 09/14] x86/speculation/mds: Conditionally clear CPU buffers on idle entry
From: Thomas Gleixner <[email protected]>

Add a static key which controls the invocation of the CPU buffer clear mechanism on idle entry. This is independent of other MDS mitigations because the idle entry invocation to mitigate the potential leakage due to store buffer repartitioning is only necessary on SMT systems.

Quoted 8 lines

Add the actual invocations to the different halt/mwait variants which covers all usage sites. mwaitx is not patched as it's not available on Intel CPUs.

The buffer clear is only invoked before entering the C-State to prevent that stale data from the idling CPU is spilled to the Hyper-Thread sibling after the Store buffer got repartitioned and all entries are available to the non idle sibling.

Quoted 4 lines

Andrea brought up a good question privately -- this patch mitigates MSBDS for HT, but HT will still be susceptible to the other two MDS issues. So what's the point? It seems this patch only protects people who don't care about MDS in the first place.

Indeed for most CPU models it's pointless.

The ones which are only affected by MSBDS are Atom Silvermont/Airmont which are all single threaded and the XEON PHIs.

For XEON PHI it actually makes sense because XEON PHI does not have L1TF either.

Quoted 7 lines
Quoted 1 line

But yes, for everything else it's just window dressing.

Makes sense. I didn't realize that some CPUs were affected by MSBDS and not other MDSes.

Can you add that justification to the documentation and/or patch description?

Or even better, can we only do the idle clearing on XEON PHI?

Also it sounds like the mds vulnerabilities file shouldn't ever show "SMT vulnerable" for XEON PHI.

Signature · 1 line
Josh
#22 lore raw

Re: [patch V5 09/14] MDS basics 9

Quoted 21 lines · speck for Josh Poimboeuf
Quoted 20 lines · Josh Poimboeuf
Quoted 8 lines · speck for Thomas Gleixner
Quoted 4 lines · speck for Josh Poimboeuf

Andrea brought up a good question privately -- this patch mitigates MSBDS for HT, but HT will still be susceptible to the other two MDS issues. So what's the point? It seems this patch only protects people who don't care about MDS in the first place.

Indeed for most CPU models it's pointless.

Quoted 7 lines

The ones which are only affected by MSBDS are Atom Silvermont/Airmont which are all single threaded and the XEON PHIs.

For XEON PHI it actually makes sense because XEON PHI does not have L1TF either.

But yes, for everything else it's just window dressing.

Makes sense. I didn't realize that some CPUs were affected by MSBDS and not other MDSes.

Quoted 7 lines
Quoted 2 lines

Can you add that justification to the documentation and/or patch description?

Or even better, can we only do the idle clearing on XEON PHI?

Also it sounds like the mds vulnerabilities file shouldn't ever show "SMT vulnerable" for XEON PHI.

Yeah.

So I was looking at that table again and found the following stepping related info:

06_8EH,06_9EH <=B Kaby/Coffe Lake Yes Yes Yes Yes
06_9E 0xC Coffee Lake No Yes Yes Yes
06_8E 0xB Whiskey Lake(ULT) No Yes Yes Yes

06_8E		0xC	Whiskey L (ULT refresh) No  No  No  No
06_9E		0xD	Whiskey Lake (Deskto)   No  No  No  No

06_55H 5 Cascade Lake No Yes Yes Yes

06_55H 6 Cascade Lake No No No No

Will these 'fixed' steppings have MDS_NO set?

Thanks,

tglx

#23 lore raw

[MODERATED] Re: [patch V5 09/14] MDS basics 9

Hello,

Quoted 25 lines · speck for Thomas Gleixner
Quoted 24 lines · speck for Josh Poimboeuf
Quoted 22 lines · Josh Poimboeuf
Quoted 8 lines · speck for Thomas Gleixner
Quoted 4 lines · speck for Josh Poimboeuf

Andrea brought up a good question privately -- this patch mitigates MSBDS for HT, but HT will still be susceptible to the other two MDS issues. So what's the point? It seems this patch only protects people who don't care about MDS in the first place.

Indeed for most CPU models it's pointless.

Quoted 7 lines

The ones which are only affected by MSBDS are Atom Silvermont/Airmont which are all single threaded and the XEON PHIs.

For XEON PHI it actually makes sense because XEON PHI does not have L1TF either.

But yes, for everything else it's just window dressing.

Makes sense. I didn't realize that some CPUs were affected by MSBDS and not other MDSes.

Can you add that justification to the documentation and/or patch description?

Quoted 6 lines
Quoted 4 lines

Or even better, can we only do the idle clearing on XEON PHI?

Also it sounds like the mds vulnerabilities file shouldn't ever show "SMT vulnerable" for XEON PHI.

Yeah.

So maybe this patch should be moved to the end of the series flagged as an incremental XEON PHI optimization by also adding the other XEON PHI specific change for the l1tf default mitigation and the respective alteration of the vulnerabilities mds/l1tf sysfs file outputs.

Is the verw measurable before mwait/hlt? I was just afraid this could hurt who needs to keep HT on for performance reasons and that won't be safe anyway if HT is kept on.

Unless we also alter the vulnerabilites file like Josh suggested, XEON PHI owners not reading the fineprint (assuming it's reachable for them) may decide then to disable HT for security reasons anyway and they won't even benefit from the XEON PHI mwait/hlt specific static key to keep HT enabled safely.

Quoted 12 lines

So I was looking at that table again and found the following stepping related info:

06_8EH,06_9EH <=B Kaby/Coffe Lake Yes Yes Yes Yes
06_9E 0xC Coffee Lake No Yes Yes Yes
06_8E 0xB Whiskey Lake(ULT) No Yes Yes Yes

06_8E		0xC	Whiskey L (ULT refresh) No  No  No  No
06_9E		0xD	Whiskey Lake (Deskto)   No  No  No  No
Quoted 5 lines

06_55H 5 Cascade Lake No Yes Yes Yes

06_55H 6 Cascade Lake No No No No

Will these 'fixed' steppings have MDS_NO set?

I couldn't understand the table, so I'm can't answer this one.

Thanks,
Andrea

#24 lore raw

Re: [patch V5 09/14] MDS basics 9

Quoted 15 lines · speck for Andrea Arcangeli
Quoted 4 lines · speck for Thomas Gleixner
Quoted 2 lines

Also it sounds like the mds vulnerabilities file shouldn't ever show "SMT vulnerable" for XEON PHI.

Yeah.

So maybe this patch should be moved to the end of the series flagged as an incremental XEON PHI optimization by also adding the other XEON PHI specific change for the l1tf default mitigation and the respective alteration of the vulnerabilities mds/l1tf sysfs file outputs.

Is the verw measurable before mwait/hlt? I was just afraid this could hurt who needs to keep HT on for performance reasons and that won't be safe anyway if HT is kept on.

Quoted 5 lines

Unless we also alter the vulnerabilites file like Josh suggested, XEON PHI owners not reading the fineprint (assuming it's reachable for them) may decide then to disable HT for security reasons anyway and they won't even benefit from the XEON PHI mwait/hlt specific static key to keep HT enabled safely.

I already did those changes to the sysfs file and updated documentation accordingly. Will send an updated series soon.

Quoted 11 lines
Quoted 11 lines

So I was looking at that table again and found the following stepping related info:

06_8EH,06_9EH <=B Kaby/Coffe Lake Yes Yes Yes Yes
06_9E 0xC Coffee Lake No Yes Yes Yes
06_8E 0xB Whiskey Lake(ULT) No Yes Yes Yes

06_8E		0xC	Whiskey L (ULT refresh) No  No  No  No
06_9E		0xD	Whiskey Lake (Deskto)   No  No  No  No
Quoted 7 lines
Quoted 5 lines

06_55H 5 Cascade Lake No Yes Yes Yes

06_55H 6 Cascade Lake No No No No

Will these 'fixed' steppings have MDS_NO set?

I couldn't understand the table, so I'm can't answer this one.

Sorry I dropped the first line:

Family_model, Stepping, Codename, MFBDS, MSBDS, MLPDS Vector, MLPDS Split line.

So the thing is that newer steppings are fixed vs. all of the issues. I surely hope that these have MDS_NO set in MSR_IA32_ARCH_CAPABILITIES.

If that's not the case, then we'll end up with stepping specific quirks which would be an utter mess.

Can anyone @Intel please answer this question?

Thanks,

tglx

#25 lore raw

[MODERATED] Re: [SPAM] Re: [patch V5 09/14] MDS basics 9

Quoted 7 lines · speck for Thomas Gleixner

So the thing is that newer steppings are fixed vs. all of the issues. I surely hope that these have MDS_NO set in MSR_IA32_ARCH_CAPABILITIES.

If that's not the case, then we'll end up with stepping specific quirks which would be an utter mess.

Can anyone @Intel please answer this question?

MDS_NO will be set on all unaffected processor steppings. We should not have to do any stepping-specific tweaks in the kernel.

#26 lore raw

Re: [SPAM] Re: [patch V5 09/14] MDS basics 9

Quoted 11 lines · speck for Dave Hansen
Quoted 7 lines · speck for Thomas Gleixner

So the thing is that newer steppings are fixed vs. all of the issues. I surely hope that these have MDS_NO set in MSR_IA32_ARCH_CAPABILITIES.

If that's not the case, then we'll end up with stepping specific quirks which would be an utter mess.

Can anyone @Intel please answer this question?

MDS_NO will be set on all unaffected processor steppings. We should not have to do any stepping-specific tweaks in the kernel.

Thanks for that info! That spares me to supress a non CoC compliant tirade :)

#27 lore raw

PATCH v5 10/14 MDS basics 10

In reply to Thomas Gleixner

Subject: [patch V5 10/14] x86/speculation/mds: Add mitigation control for MDS
From: Thomas Gleixner <[email protected]>

Now that the mitigations are in place, add a command line parameter to control the mitigation, a mitigation selector function and a SMT update mechanism.

This is the minimal straight forward initial implementation which just provides an always on/off mode. The command line parameter is:

mds=[full|off]

This is consistent with the existing mitigations for other speculative hardware vulnerabilities.

The idle invocation is dynamically updated according to the SMT state of the system similar to the dynamic update of the STIBP mitigation.

---
V4 --> V5: Remove 'auto'

---
 Documentation/admin-guide/kernel-parameters.txt |   22 ++++++++
 arch/x86/include/asm/processor.h                |    5 ++
 arch/x86/kernel/cpu/bugs.c                      |   59 ++++++++++++++++++++++++
 3 files changed, 86 insertions(+)
Documentation/admin-guide/kernel-parameters.txt +22 -0
@@ -2356,6 +2356,28 @@
 			Format: <first>,<last>
 			Specifies range of consoles to be captured by the MDA.
 
+	mds=		[X86,INTEL]
+			Control mitigation for the Micro-architectural Data
+			Sampling (MDS) vulnerability.
+
+			Certain CPUs are vulnerable to an exploit against CPU
+			internal buffers which can forward information to a
+			disclosure gadget under certain conditions.
+
+			In vulnerable processors, the speculatively
+			forwarded data can be used in a cache side channel
+			attack, to access data to which the attacker does
+			not have direct access.
+
+			This parameter controls the MDS mitigation. The
+			options are:
+
+			full    - Enable MDS mitigation on vulnerable CPUs
+			off     - Unconditionally disable MDS mitigation
+
+			Not specifying this option is equivalent to
+			mds=full.
+
 	mem=nn[KMG]	[KNL,BOOT] Force usage of a specific amount of memory
 			Amount of memory to be used when the kernel is not able
 			to see the whole system memory or for test.
arch/x86/include/asm/processor.h +5 -0
@@ -992,4 +992,9 @@ enum l1tf_mitigations {
 
 extern enum l1tf_mitigations l1tf_mitigation;
 
+enum mds_mitigations {
+	MDS_MITIGATION_OFF,
+	MDS_MITIGATION_FULL,
+};
+
 #endif /* _ASM_X86_PROCESSOR_H */
arch/x86/kernel/cpu/bugs.c +59 -0

89 lines not on this page · raw message

#28 lore raw

PATCH v5 11/14 MDS basics 11

In reply to Thomas Gleixner

Subject: [patch V5 11/14] x86/speculation/mds: Add sysfs reporting for MDS
From: Thomas Gleixner <[email protected]>

Add the sysfs reporting file for MDS. It exposes the vulnerability and mitigation state similar to the existing files for the other speculative hardware vulnerabilities.

---
V3: Copy & Paste done right :(

---
 Documentation/ABI/testing/sysfs-devices-system-cpu |    1 +
 arch/x86/kernel/cpu/bugs.c                         |   20 ++++++++++++++++++++
 drivers/base/cpu.c                                 |    8 ++++++++
 include/linux/cpu.h                                |    2 ++
 4 files changed, 31 insertions(+)
Documentation/ABI/testing/sysfs-devices-system-cpu +1 -0
@@ -484,6 +484,7 @@ What:		/sys/devices/system/cpu/vulnerabi
 		/sys/devices/system/cpu/vulnerabilities/spectre_v2
 		/sys/devices/system/cpu/vulnerabilities/spec_store_bypass
 		/sys/devices/system/cpu/vulnerabilities/l1tf
+		/sys/devices/system/cpu/vulnerabilities/mds
 Date:		January 2018
 Contact:	Linux kernel mailing list <[email protected]>
 Description:	Information about CPU vulnerabilities
arch/x86/kernel/cpu/bugs.c +20 -0
@@ -1161,6 +1161,17 @@ static ssize_t l1tf_show_state(char *buf
 }
 #endif
 
+static ssize_t mds_show_state(char *buf)
+{
+	if (!hypervisor_is_type(X86_HYPER_NATIVE)) {
+		return sprintf(buf, "%s; SMT Host state unknown\n",
+			       mds_strings[mds_mitigation]);
+	}
+
+	return sprintf(buf, "%s; SMT %s\n", mds_strings[mds_mitigation],
+		       sched_smt_active() ? "vulnerable" : "disabled");
+}
+
 static char *stibp_state(void)
 {
 	if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
@@ -1227,6 +1238,10 @@ static ssize_t cpu_show_common(struct de
 		if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV))
 			return l1tf_show_state(buf);
 		break;
+
+	case X86_BUG_MDS:
+		return mds_show_state(buf);
+
 	default:
 		break;
 	}
@@ -1258,4 +1273,9 @@ ssize_t cpu_show_l1tf(struct device *dev
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_L1TF);
 }
+
+ssize_t cpu_show_mds(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_MDS);
+}
 #endif
drivers/base/cpu.c +8 -0
@@ -546,11 +546,18 @@ ssize_t __weak cpu_show_l1tf(struct devi
 	return sprintf(buf, "Not affected\n");
 }
 
+ssize_t __weak cpu_show_mds(struct device *dev,
+			    struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "Not affected\n");
+}
+
 static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
 static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
 static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL);
 static DEVICE_ATTR(spec_store_bypass, 0444, cpu_show_spec_store_bypass, NULL);
 static DEVICE_ATTR(l1tf, 0444, cpu_show_l1tf, NULL);
+static DEVICE_ATTR(mds, 0444, cpu_show_mds, NULL);
 
 static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_meltdown.attr,
@@ -558,6 +565,7 @@ static struct attribute *cpu_root_vulner
 	&dev_attr_spectre_v2.attr,
 	&dev_attr_spec_store_bypass.attr,
 	&dev_attr_l1tf.attr,
+	&dev_attr_mds.attr,
 	NULL
 };
 
include/linux/cpu.h +2 -0
@@ -57,6 +57,8 @@ extern ssize_t cpu_show_spec_store_bypas
 					  struct device_attribute *attr, char *buf);
 extern ssize_t cpu_show_l1tf(struct device *dev,
 			     struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_mds(struct device *dev,
+			    struct device_attribute *attr, char *buf);
 
 extern __printf(4, 5)
 struct device *cpu_device_create(struct device *parent, void *drvdata,
#29 lore raw

PATCH v5 12/14 MDS basics 12

In reply to Thomas Gleixner

Subject: [patch V5 12/14] x86/speculation/mds: Add mitigation mode VMWERV
From: Thomas Gleixner <[email protected]>

In virtualized environments it can happen that the host has the microcode update which utilizes the VERW instruction to clear CPU buffers, but the hypervisor is not yet updated to expose the X86_FEATURE_MD_CLEAR CPUID bit to guests.

Introduce an internal mitigation mode VWWERV which enables the invocation of the CPU buffer clearing even if X86_FEATURE_MD_CLEAR is not set. If the system has no updated microcode this results in a pointless execution of the VERW instruction wasting a few CPU cycles. If the microcode is updated, but not exposed to a guest then the CPU buffers will be cleared.

That said: Virtual Machines Will Eventually Receive Vaccine

---
V2 -> V3: Rename mode.

---
 Documentation/x86/mds.rst        |   27 +++++++++++++++++++++++++++
 arch/x86/include/asm/processor.h |    1 +
 arch/x86/kernel/cpu/bugs.c       |   18 ++++++++++++------
 3 files changed, 40 insertions(+), 6 deletions(-)
Documentation/x86/mds.rst +27 -0
@@ -93,11 +93,38 @@ enters a C-state.
 The mitigation is invoked on kernel/userspace, hypervisor/guest and C-state
 (idle) transitions.
 
+As a special quirk to address virtualization scenarios where the host has
+the microcode updated, but the hypervisor does not (yet) expose the
+MD_CLEAR CPUID bit to guests, the kernel issues the VERW instruction in the
+hope that it might actually clear the buffers. The state is reflected
+accordingly.
+
 According to current knowledge additional mitigations inside the kernel
 itself are not required because the necessary gadgets to expose the leaked
 data cannot be controlled in a way which allows exploitation from malicious
 user space or VM guests.
 
+Kernel internal mitigation modes
+--------------------------------
+
+ ======= ===========================================================
+ off     Mitigation is disabled. Either the CPU is not affected or
+         mds=off is supplied on the kernel command line
+
+ full    Mitigation is eanbled. CPU is affected and MD_CLEAR is
+         advertised in CPUID.
+
+ vmwerv	 Mitigation is enabled. CPU is affected and MD_CLEAR is not
+	 advertised in CPUID. That is mainly for virtualization
+	 scenarios where the host has the updated microcode but the
+	 hypervisor does not expose MD_CLEAR in CPUID. It's a best
+	 effort approach without guarantee.
+ ======= ===========================================================
+
+If the CPU is affected and mds=off is not supplied on the kernel command
+line then the kernel selects the appropriate mitigation mode depending on
+the availability of the MD_CLEAR CPUID bit.
+
 Mitigation points
 -----------------
 
arch/x86/include/asm/processor.h +1 -0
@@ -995,6 +995,7 @@ extern enum l1tf_mitigations l1tf_mitiga
 enum mds_mitigations {
 	MDS_MITIGATION_OFF,
 	MDS_MITIGATION_FULL,
+	MDS_MITIGATION_VMWERV,
 };
 
 #endif /* _ASM_X86_PROCESSOR_H */
arch/x86/kernel/cpu/bugs.c +12 -6
@@ -224,7 +224,8 @@ static enum mds_mitigations mds_mitigati
 
 static const char * const mds_strings[] = {
 	[MDS_MITIGATION_OFF]	= "Vulnerable",
-	[MDS_MITIGATION_FULL]	= "Mitigation: Clear CPU buffers"
+	[MDS_MITIGATION_FULL]	= "Mitigation: Clear CPU buffers",
+	[MDS_MITIGATION_VMWERV]	= "Vulnerable: Clear CPU buffers attempted, no microcode",
 };
 
 static void mds_select_mitigation(void)
@@ -235,10 +236,9 @@ static void mds_select_mitigation(void)
 	}
 
 	if (mds_mitigation == MDS_MITIGATION_FULL) {
-		if (boot_cpu_has(X86_FEATURE_MD_CLEAR))
-			static_branch_enable(&mds_user_clear);
-		else
-			mds_mitigation = MDS_MITIGATION_OFF;
+		if (!boot_cpu_has(X86_FEATURE_MD_CLEAR))
+			mds_mitigation = MDS_MITIGATION_VMWERV;
+		static_branch_enable(&mds_user_clear);
 	}
 	pr_info("%s\n", mds_strings[mds_mitigation]);
 }
@@ -694,8 +694,14 @@ void arch_smt_update(void)
 		break;
 	}
 
-	if (mds_mitigation == MDS_MITIGATION_FULL)
+	switch(mds_mitigation) {
+	case MDS_MITIGATION_FULL:
+	case MDS_MITIGATION_VMWERV:
 		update_mds_branch_idle();
+		break;
+	case MDS_MITIGATION_OFF:
+		break;
+	}
 
 	mutex_unlock(&spec_ctrl_mutex);
 }
#30 lore raw

[MODERATED] Re: [patch V5 12/14] MDS basics 12

Quoted 9 lines · speck for Thomas Gleixner

Subject: [patch V5 12/14] x86/speculation/mds: Add mitigation mode VMWERV
From: Thomas Gleixner <[email protected]>

In virtualized environments it can happen that the host has the microcode update which utilizes the VERW instruction to clear CPU buffers, but the hypervisor is not yet updated to expose the X86_FEATURE_MD_CLEAR CPUID bit to guests.

Introduce an internal mitigation mode VWWERV which enables the invocation

^VMWERV
--mark

#31 lore raw

PATCH v5 13/14 MDS basics 13

In reply to Thomas Gleixner

Subject: [patch V5 13/14] Documentation: Move L1TF to separate directory
From: Thomas Gleixner <[email protected]>

Move L!TF to a separate directory so the MDS stuff can be added at the side. Otherwise the all hardware vulnerabilites have their own top level entry. Should have done that right away.

---
 Documentation/admin-guide/hw-vuln/index.rst |   12 
 Documentation/admin-guide/hw-vuln/l1tf.rst  |  614 ++++++++++++++++++++++++++++
 Documentation/admin-guide/index.rst         |    6 
 Documentation/admin-guide/l1tf.rst          |  614 ----------------------------
 4 files changed, 628 insertions(+), 618 deletions(-)
Documentation/admin-guide/hw-vuln/index.rst new file +12 -0
@@ -0,0 +1,12 @@
+========================
+Hardware vulnerabilities
+========================
+
+This section describes CPU vulnerabilities and provides an overview of the
+possible mitigations along with guidance for selecting mitigations if they
+are configurable at compile, boot or run time.
+
+.. toctree::
+   :maxdepth: 1
+
+   l1tf
Documentation/admin-guide/hw-vuln/l1tf.rst new file +614 -0

614 lines not on this page · raw message

Documentation/admin-guide/index.rst +2 -4
@@ -17,14 +17,12 @@ etc.
    kernel-parameters
    devices
 
-This section describes CPU vulnerabilities and provides an overview of the
-possible mitigations along with guidance for selecting mitigations if they
-are configurable at compile, boot or run time.
+This section describes CPU vulnerabilities and their mitigations.
 
 .. toctree::
    :maxdepth: 1
 
-   l1tf
+   hw-vuln/index
 
 Here is a set of documents aimed at users who are trying to track down
 problems and bugs in particular.
Documentation/admin-guide/l1tf.rst deleted +0 -614

614 lines not on this page · raw message

#32 lore raw

[MODERATED] Re: [patch V5 13/14] MDS basics 13

Quoted 4 lines · speck for Thomas Gleixner

Subject: [patch V5 13/14] Documentation: Move L1TF to separate directory
From: Thomas Gleixner <[email protected]>

Move L!TF to a separate directory so the MDS stuff can be added at the

      ^L1TF

--mark

#33 lore raw

PATCH v5 14/14 MDS basics 14

In reply to Thomas Gleixner

Subject: [patch V5 14/14] Documentation: Add MDS vulnerability documentation
From: Thomas Gleixner <[email protected]>

Add the initial MDS vulnerability documentation.

---
V4 --> V5: Remove 'auto' option. Adjust virt mitigation info. V1 --> V4: Added the missing pieces

---
 Documentation/admin-guide/hw-vuln/index.rst |    1 
 Documentation/admin-guide/hw-vuln/l1tf.rst  |    1 
 Documentation/admin-guide/hw-vuln/mds.rst   |  286 ++++++++++++++++++++++++++++
 3 files changed, 288 insertions(+)
Documentation/admin-guide/hw-vuln/index.rst +1 -0
@@ -10,3 +10,4 @@ are configurable at compile, boot or run
    :maxdepth: 1
 
    l1tf
+   mds
Documentation/admin-guide/hw-vuln/l1tf.rst +1 -0
@@ -445,6 +445,7 @@ The default is 'cond'. If 'l1tf=full,for
 line, then 'always' is enforced and the kvm-intel.vmentry_l1d_flush
 module parameter is ignored and writes to the sysfs file are rejected.
 
+.. _mitigation_selection:
 
 Mitigation selection guide
 --------------------------
Documentation/admin-guide/hw-vuln/mds.rst new file +286 -0

286 lines not on this page · raw message

#34 lore raw

Re: [patch V5 14/14] MDS basics 14

Documentation/admin-guide/hw-vuln/mds.rst line 172

Quoted 12 lines · speck for Thomas Gleixner
Documentation/admin-guide/hw-vuln/mds.rst new file +12 -0
+Virtualization mitigation
+^^^^^^^^^^^^^^^^^^^^^^^^^
+
+  The protection for host to guest transition depends on the L1TF
+  vulnerability of the CPU:
+
+  - CPU is affected by L1TF:
+
+    If the L1D flush mitigation is enabled and up to date microcode is
+    available, the L1D flush mitigation is automatically protecting the
+    guest transition. If the L1D flush mitigation is disabled the MDS
+    mitigation is disabled as well.

Not true. Dammit. Write patch, write documentation, hate it, change patch, get dragged into a meeting, forget about documentation. I so hate my life.

Quoted 6 lines
Documentation/admin-guide/hw-vuln/mds.rst new file +6 -0
+    For details on L1TF and virtualization see:
+    :ref:`Documentation/admin-guide/hw-vuln//l1tf.rst <mitigation_control_kvm>`.
+
+  - CPU is not affected by L1TF:
+
+    CPU buffers are flushed before entering the guest when the host MDS

Documentation/admin-guide/hw-vuln/mds.rst line 189

Quoted 10 lines
Documentation/admin-guide/hw-vuln/mds.rst new file +10 -0
+    protection is enabled.
+
+  The resulting MDS protection matrix for the host to guest transition:
+
+  ============ ===== ============= ============ =================
+   L1TF         MDS   VMX-L1FLUSH   Host MDS     State
+
+   Don't care   No    Don't care    N/A          Not affected
+
+   Yes          Yes   Disabled      Don't care   Vulnerable

This has to be:

 +   Yes          Yes   Disabled      Off   Vulnerable
 +   Yes          Yes   Disabled      Full  Mitigated

Bah. I changed this because the L1TF mitigation is off when EPT is disabled, but in that case the MDS mitigation should not hang off the L1TF state.

Thanks,

tglx

#35 lore raw
In reply to Thomas Gleixner
Quoted 2 lines · speck for Thomas Gleixner

- Consolidate whitelists before adding another one.

So I know I suggested this, but the long lines end up bothering me.

arch/x86/kernel/cpu/common.c static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) · line 959

Quoted 3 lines
arch/x86/kernel/cpu/common.c +3 -0
+static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
+       { X86_VENDOR_ANY,       4, X86_MODEL_ANY,                       X86_FEATURE_ANY, NO_SPECULATION },
+       { X86_VENDOR_CENTAUR,   5, X86_MODEL_ANY,                       X86_FEATURE_ANY, NO_SPECULATION },

This just gets quite hard to read, and the patch to then add new spec flags becomes a mess too. In that sense the old model was simpler.

On the other hand I think the new consolidated list is better in the sense that it shows the commonalities much better, and you have everything in one place.

I wonder if we could make it a bit saner with some macro magic. Doing

  #define VULN_WHITELIST(vendor, number, model, whitelist) \
       { X86_VENDOR_##vendor, number, model, X86_FEATURE_ANY, whitelist)

and then the lines are at least a bit shorter:

VULN_WHITELIST(INTEL, 5, X86_MODEL_ANY, NO_SPECULATION),

(or do we actually need the feature mask? None of the existing cases seem to have it?)

I dunno. Maybe none of this matters.

Linus

#36 lore raw
Quoted 5 lines · speck for Linus Torvalds
Quoted 2 lines · speck for Thomas Gleixner

- Consolidate whitelists before adding another one.

Quoted 8 lines

So I know I suggested this, but the long lines end up bothering me.

arch/x86/kernel/cpu/common.c static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) · line 959

Quoted 3 lines
arch/x86/kernel/cpu/common.c +3 -0
+static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
+       { X86_VENDOR_ANY,       4, X86_MODEL_ANY,                       X86_FEATURE_ANY, NO_SPECULATION },
+       { X86_VENDOR_CENTAUR,   5, X86_MODEL_ANY,                       X86_FEATURE_ANY, NO_SPECULATION },

This just gets quite hard to read, and the patch to then add new spec flags becomes a mess too. In that sense the old model was simpler.

Yeah. I tried with line breaks, but that wasn't pretty either.

Quoted 9 lines

On the other hand I think the new consolidated list is better in the sense that it shows the commonalities much better, and you have everything in one place.

I wonder if we could make it a bit saner with some macro magic. Doing

  #define VULN_WHITELIST(vendor, number, model, whitelist) \
       { X86_VENDOR_##vendor, number, model, X86_FEATURE_ANY, whitelist)
Quoted 6 lines

and then the lines are at least a bit shorter:

VULN_WHITELIST(INTEL, 5, X86_MODEL_ANY, NO_SPECULATION),

(or do we actually need the feature mask? None of the existing cases seem to have it?)

No. I just had to add it to be able to use driver_data.

Quoted 1 line

I dunno. Maybe none of this matters.

Lemme have a try.

Thanks,

tglx

#37 lore raw
Quoted 5 lines · speck for Thomas Gleixner
Quoted 4 lines · speck for Linus Torvalds

and then the lines are at least a bit shorter:

VULN_WHITELIST(INTEL, 5, X86_MODEL_ANY, NO_SPECULATION),

Quoted 8 lines
Quoted 2 lines

(or do we actually need the feature mask? None of the existing cases seem to have it?)

No. I just had to add it to be able to use driver_data.

Quoted 1 line

I dunno. Maybe none of this matters.

Lemme have a try.

Something like this:

#define VULNWL(vendor, family, model, whitelist) \
{ X86_VENDOR_##vendor, number, model, X86_FEATURE_ANY, whitelist)

static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {

        VULNWL(ANY,     4, X86_MODEL_ANY,                     NO_SPECULATION },
        VULNWL(CENTAUR, 5, X86_MODEL_ANY,                     NO_SPECULATION },
        VULNWL(INTEL,   5, X86_MODEL_ANY,                     NO_SPECULATION },
        VULNWL(NSC,     5, X86_MODEL_ANY,                     NO_SPECULATION },
        VULNWL(INTEL,   6, INTEL_FAM6_ATOM_SALTWELL,          NO_SPECULATION },
        VULNWL(INTEL,   6, INTEL_FAM6_ATOM_SALTWELL_TABLET,   NO_SPECULATION },
        VULNWL(INTEL,   6, INTEL_FAM6_ATOM_SALTWELL_MID,      NO_SPECULATION },
        VULNWL(INTEL,   6, INTEL_FAM6_ATOM_BONELL,            NO_SPECULATION },
        VULNWL(INTEL,   6, INTEL_FAM6_ATOM_SILVERMONT,      NO_SSB | NO_L1TF },
        VULNWL(INTEL,   6, INTEL_FAM6_ATOM_SILVERMONT_,     NO_SSB | NO_L1TF },
        VULNWL(INTEL,   6, INTEL_FAM6_ATOM_SILVERMONT_MID,  NO_SSB | NO_L1TF },
        VULNWL(INTEL,   6, INTEL_FAM6_ATOM_AIRMONT,         NO_SSB | NO_L1TF },
        VULNWL(INTEL,   6, INTEL_FAM6_ATOM_AIRMONT_MID,     NO_SSB | NO_L1TF },
        VULNWL(INTEL,   6, INTEL_FAM6_CORE_YONAH,           NO_SSB | NO_L1TF },
        VULNWL(INTEL,   6, INTEL_FAM6_XEON_PHI_KNL,         NO_SSB | NO_L1TF },
        VULNWL(INTEL,   6, INTEL_FAM6_XEON_PHI_KNM,         NO_SSB | NO_L1TF },
        VULNWL(INTEL,   6, INTEL_FAM6_ATOM_GOLDMONT,                 NO_L1TF },
        VULNWL(INTEL,   6, INTEL_FAM6_ATOM_GOLDMONT_X,               NO_L1TF },
        VULNWL(INTEL,   6, INTEL_FAM6_ATOM_GOLDMONT_PLUS,            NO_L1TF },
        VULNWL(AMD,     0x0f, X86_MODEL_ANY,                NO_SSB           },
        VULNWL(AMD,     0x10, X86_MODEL_ANY,                NO_SSB           },
        VULNWL(AMD,     0x11, X86_MODEL_ANY,                NO_SSB           },
        VULNWL(AMD,     0x12, X86_MODEL_ANY,                NO_SSB           },
        /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
        VULNWL(AMD,     X86_FAMILY_ANY, X86_MODEL_ANY, NO_MELTDOWN | NO_L1TF },
        VULNWL(HYGON,   X86_FAMILY_ANY, X86_MODEL_ANY, NO_MELTDOWN | NO_L1TF },
        {}
};

Thanks,

tglx

#38 lore raw
Quoted 2 lines · speck for Thomas Gleixner

Something like this:

That looks better to me.

If I had my choice, I'd get rid of the "FAM6" thing entirely from the intel enumerations, but that's an independent thing

Although when I look at this, we actually already have a helper macro for the Intel case, and you could do

    INTEL_CPU_FAM6(ATOM_SALTWELL, NO_SPECULATION),
    INTEL_CPU_FAM6(ATOM_SALTWELL_TABLET,   NO_SPECULATION),
    ...

using the existing INTEL_CPU_FAM6() helper macro.

It's clearly not the first case people looked at those nasty model definitions and went "ugh. that's illegible".

Linus

#39 lore raw
Quoted 4 lines · speck for Linus Torvalds

That looks better to me.

If I had my choice, I'd get rid of the "FAM6" thing entirely from the intel enumerations, but that's an independent thing

Is on that ever growing todo list thingy already.

Quoted 11 lines

Although when I look at this, we actually already have a helper macro for the Intel case, and you could do

    INTEL_CPU_FAM6(ATOM_SALTWELL, NO_SPECULATION),
    INTEL_CPU_FAM6(ATOM_SALTWELL_TABLET,   NO_SPECULATION),
    ...

using the existing INTEL_CPU_FAM6() helper macro.

It's clearly not the first case people looked at those nasty model definitions and went "ugh. that's illegible".

Yes, but then I end up with two different macros in that table, which is not helping readability either.

Thanks,

tglx

#40 lore raw
In reply to Thomas Gleixner
Quoted 15 lines · speck for Thomas Gleixner

Changes since V4:

- Fix SSB whitelist. Needs to go upstream independently.

- Consolidate whitelists before adding another one.

- Use an inline helper for the exit to user mitigation.

- Add VMX/VMENTER mitigation when CPU is not affected by L1TF.

- Remove 'auto' command line option.

- Rework the mitigation documentation so the handling of special exceptions is clear.

Quoted 7 lines

- Adjust the virt mitigation admin documentation.

- Fix typos and address review comments

Available from git:

cvs.ou.linutronix.de:linux/speck/linux WIP.mds

Pushed out a new tree which contains the fixups for the consolidated table and the documentation for VMX.

Delta patch below.

Thanks,

tglx

8<---------------

Documentation/admin-guide/hw-vuln/mds.rst +6 -4
index 73cdc390aece..3fe53bd5b9cc 100644
@@ -169,7 +169,7 @@ Virtualization mitigation
     If the L1D flush mitigation is enabled and up to date microcode is
     available, the L1D flush mitigation is automatically protecting the
     guest transition. If the L1D flush mitigation is disabled the MDS
-    mitigation is disabled as well.
+    mitigation is invoked explicit when the host MDS mitigation is enabled.
 
     For details on L1TF and virtualization see:
     :ref:`Documentation/admin-guide/hw-vuln//l1tf.rst <mitigation_control_kvm>`.
@@ -177,7 +177,7 @@ Virtualization mitigation
   - CPU is not affected by L1TF:
 
     CPU buffers are flushed before entering the guest when the host MDS
-    protection is enabled.
+    mitigation is enabled.
 
   The resulting MDS protection matrix for the host to guest transition:
 
@@ -186,7 +186,9 @@ Virtualization mitigation
 
    Don't care   No    Don't care    N/A          Not affected
 
-   Yes          Yes   Disabled      Don't care   Vulnerable
+   Yes          Yes   Disabled      Off          Vulnerable
+
+   Yes          Yes   Disabled      Full         Mitigated
 
    Yes          Yes   Enabled       Don't care   Mitigated
 
@@ -196,7 +198,7 @@ Virtualization mitigation
   ============ ===== ============= ============ =================
 
   This only covers the host to guest transition, i.e. prevents leakage from
-  host to guest, but does not protect the guest internally. Guest need to
+  host to guest, but does not protect the guest internally. Guests need to
   have their own protections.
 
 .. _xeon_phi:
arch/x86/kernel/cpu/common.c +33 -30

70 lines not on this page · raw message

#41 lore raw
Quoted 21 lines · speck for Thomas Gleixner
Quoted 19 lines · speck for Thomas Gleixner

Changes since V4:

- Fix SSB whitelist. Needs to go upstream independently.

- Consolidate whitelists before adding another one.

- Use an inline helper for the exit to user mitigation.

- Add VMX/VMENTER mitigation when CPU is not affected by L1TF.

- Remove 'auto' command line option.

- Rework the mitigation documentation so the handling of special exceptions is clear.

- Adjust the virt mitigation admin documentation.

- Fix typos and address review comments

Quoted 8 lines
Quoted 3 lines

Available from git:

cvs.ou.linutronix.de:linux/speck/linux WIP.mds

Pushed out a new tree which contains the fixups for the consolidated table and the documentation for VMX.

Delta patch below.

Your last update had a bunch of issues: didn't compile, missing entries, typos, whitespace.

The below fixed it for me (on top of your bad patch):

arch/x86/kernel/cpu/common.c +30 -29
index 7b34ac46f4db..0558e9ee1fec 100644
@@ -955,39 +955,40 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 #define NO_MDS		BIT(4)
 
 #define VULNWL(vendor, family, model, whitelist)	\
-	{ X86_VENDOR_##vendor, number, model, X86_FEATURE_ANY, whitelist)
+	{ X86_VENDOR_##vendor, family, model, X86_FEATURE_ANY, whitelist }
 
 static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
-	VULNWL(ANY,	4, X86_MODEL_ANY,		      NO_SPECULATION },
-	VULNWL(CENTAUR,	5, X86_MODEL_ANY,		      NO_SPECULATION },
-	VULNWL(INTEL,	5, X86_MODEL_ANY,		      NO_SPECULATION },
-	VULNWL(NSC,	5, X86_MODEL_ANY,		      NO_SPECULATION },
-	VULNWL(INTEL,	6, INTEL_FAM6_ATOM_SALTWELL,	      NO_SPECULATION },
-	VULNWL(INTEL,	6, INTEL_FAM6_ATOM_SALTWELL_TABLET,   NO_SPECULATION },
-	VULNWL(INTEL,	6, INTEL_FAM6_ATOM_SALTWELL_MID,      NO_SPECULATION },
-	VULNWL(INTEL,	6, INTEL_FAM6_ATOM_BONELL,	      NO_SPECULATION },
-
-	VULNWL(INTEL,	6, INTEL_FAM6_ATOM_SILVERMONT,      NO_SSB | NO_L1TF },
-	VULNWL(INTEL,	6, INTEL_FAM6_ATOM_SILVERMONT_,     NO_SSB | NO_L1TF },
-	VULNWL(INTEL,	6, INTEL_FAM6_ATOM_SILVERMONT_MID,  NO_SSB | NO_L1TF },
-	VULNWL(INTEL,	6, INTEL_FAM6_ATOM_AIRMONT,	    NO_SSB | NO_L1TF },
-	VULNWL(INTEL,	6, INTEL_FAM6_ATOM_AIRMONT_MID,	    NO_SSB | NO_L1TF },
-	VULNWL(INTEL,	6, INTEL_FAM6_CORE_YONAH,	    NO_SSB | NO_L1TF },
-	VULNWL(INTEL,	6, INTEL_FAM6_XEON_PHI_KNL,	    NO_SSB | NO_L1TF },
-	VULNWL(INTEL,	6, INTEL_FAM6_XEON_PHI_KNM,	    NO_SSB | NO_L1TF },
-
-	VULNWL(INTEL,	6, INTEL_FAM6_ATOM_GOLDMONT,	    NO_MDS | NO_L1TF },
-	VULNWL(INTEL,	6, INTEL_FAM6_ATOM_GOLDMONT_X,	    NO_MDS | NO_L1TF },
-	VULNWL(INTEL,	6, INTEL_FAM6_ATOM_GOLDMONT_PLUS,   NO_MDS | NO_L1TF },
-
-	VULNWL(AMD,	0x0f, X86_MODEL_ANY,  NO_MELTDOWN | NO_SSB | NO_L1TF },
-	VULNWL(AMD,	0x10, X86_MODEL_ANY,  NO_MELTDOWN | NO_SSB | NO_L1TF },
-	VULNWL(AMD,	0x11, X86_MODEL_ANY,  NO_MELTDOWN | NO_SSB | NO_L1TF },
-	VULNWL(AMD,	0x12, X86_MODEL_ANY,  NO_MELTDOWN | NO_SSB | NO_L1TF },
+	VULNWL(ANY,	4, X86_MODEL_ANY,			NO_SPECULATION),
+	VULNWL(CENTAUR,	5, X86_MODEL_ANY,			NO_SPECULATION),
+	VULNWL(INTEL,	5, X86_MODEL_ANY,			NO_SPECULATION),
+	VULNWL(NSC,	5, X86_MODEL_ANY,			NO_SPECULATION),
+	VULNWL(INTEL,	6, INTEL_FAM6_ATOM_SALTWELL,		NO_SPECULATION),
+	VULNWL(INTEL,	6, INTEL_FAM6_ATOM_SALTWELL_TABLET,	NO_SPECULATION),
+	VULNWL(INTEL,	6, INTEL_FAM6_ATOM_SALTWELL_MID,	NO_SPECULATION),
+	VULNWL(INTEL,	6, INTEL_FAM6_ATOM_BONNELL,		NO_SPECULATION),
+	VULNWL(INTEL,	6, INTEL_FAM6_ATOM_BONNELL_MID,		NO_SPECULATION),
+
+	VULNWL(INTEL,	6, INTEL_FAM6_ATOM_SILVERMONT,		NO_SSB | NO_L1TF),
+	VULNWL(INTEL,	6, INTEL_FAM6_ATOM_SILVERMONT_X,	NO_SSB | NO_L1TF),
+	VULNWL(INTEL,	6, INTEL_FAM6_ATOM_SILVERMONT_MID,	NO_SSB | NO_L1TF),
+	VULNWL(INTEL,	6, INTEL_FAM6_ATOM_AIRMONT,		NO_SSB | NO_L1TF),
+	VULNWL(INTEL,	6, INTEL_FAM6_ATOM_AIRMONT_MID,		NO_SSB | NO_L1TF),
+	VULNWL(INTEL,	6, INTEL_FAM6_CORE_YONAH,		NO_SSB | NO_L1TF),
+	VULNWL(INTEL,	6, INTEL_FAM6_XEON_PHI_KNL,		NO_SSB | NO_L1TF),
+	VULNWL(INTEL,	6, INTEL_FAM6_XEON_PHI_KNM,		NO_SSB | NO_L1TF),
+
+	VULNWL(INTEL,	6, INTEL_FAM6_ATOM_GOLDMONT,		NO_MDS | NO_L1TF),
+	VULNWL(INTEL,	6, INTEL_FAM6_ATOM_GOLDMONT_X,		NO_MDS | NO_L1TF),
+	VULNWL(INTEL,	6, INTEL_FAM6_ATOM_GOLDMONT_PLUS,	NO_MDS | NO_L1TF),
+
+	VULNWL(AMD,	0x0f, X86_MODEL_ANY,			NO_MELTDOWN | NO_SSB | NO_L1TF),
+	VULNWL(AMD,	0x10, X86_MODEL_ANY,			NO_MELTDOWN | NO_SSB | NO_L1TF),
+	VULNWL(AMD,	0x11, X86_MODEL_ANY,			NO_MELTDOWN | NO_SSB | NO_L1TF),
+	VULNWL(AMD,	0x12, X86_MODEL_ANY,			NO_MELTDOWN | NO_SSB | NO_L1TF),
 
 	/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
-	VULNWL(AMD,	X86_FAMILY_ANY, X86_MODEL_ANY, NO_MELTDOWN | NO_L1TF },
-	VULNWL(HYGON,	X86_FAMILY_ANY, X86_MODEL_ANY, NO_MELTDOWN | NO_L1TF },
+	VULNWL(AMD,	X86_FAMILY_ANY, X86_MODEL_ANY,		NO_MELTDOWN | NO_L1TF),
+	VULNWL(HYGON,	X86_FAMILY_ANY, X86_MODEL_ANY,		NO_MELTDOWN | NO_L1TF),
 	{}
 };
 
#42 lore raw
In reply to Thomas Gleixner

I bet you sent all 14 patches....
I only got 0/14, 4/14, 6/14, 7/14, 9/14 and no others. :(

What was that git remote you keep some of your work in? I would like to pull there from there if I could. FWIW I attempted to send my ssh pub key a few days back. I'm not sure if you got it or not.

thanks,
--mark
ps I sometimes really dislike Intel IT...

Quoted 3 lines · speck for Thomas Gleixner

Changes since V4:

- Fix SSB whitelist. Needs to go upstream independently.

#43 lore raw

Mark,

Quoted 4 lines · speck for mark gross

I bet you sent all 14 patches....
I only got 0/14, 4/14, 6/14, 7/14, 9/14 and no others. :(

What was that git remote you keep some of your work in? I would like to pull

0/14 has the URL

Quoted 2 lines

there from there if I could. FWIW I attempted to send my ssh pub key a few days back. I'm not sure if you got it or not.

I added your key and replied

Quoted 1 line

ps I sometimes really dislike Intel IT...

Talk to Dave Hansen about it ....

Thanks,

tglx