mirrors/armbian_build
1
0
Fork 0
mirror of https://github.com/armbian/build.git synced 2025-09-19 20:51:12 +02:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity
armbian_build/patch/kernel/archive/sun50iw9-btt-6.1/linux-6.1.43-44.patch

2842 lines
89 KiB
Diff
Raw Blame History

diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index f54867cadb0f6..13c01b641dc70 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -513,17 +513,18 @@ Description: information about CPUs heterogeneity.
cpu_capacity: capacity of cpuX.
What: /sys/devices/system/cpu/vulnerabilities
+ /sys/devices/system/cpu/vulnerabilities/gather_data_sampling
+ /sys/devices/system/cpu/vulnerabilities/itlb_multihit
+ /sys/devices/system/cpu/vulnerabilities/l1tf
+ /sys/devices/system/cpu/vulnerabilities/mds
/sys/devices/system/cpu/vulnerabilities/meltdown
+ /sys/devices/system/cpu/vulnerabilities/mmio_stale_data
+ /sys/devices/system/cpu/vulnerabilities/retbleed
+ /sys/devices/system/cpu/vulnerabilities/spec_store_bypass
/sys/devices/system/cpu/vulnerabilities/spectre_v1
/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
/sys/devices/system/cpu/vulnerabilities/srbds
/sys/devices/system/cpu/vulnerabilities/tsx_async_abort
- /sys/devices/system/cpu/vulnerabilities/itlb_multihit
- /sys/devices/system/cpu/vulnerabilities/mmio_stale_data
- /sys/devices/system/cpu/vulnerabilities/retbleed
Date: January 2018
Contact: Linux kernel mailing list <linux-kernel@vger.kernel.org>
Description: Information about CPU vulnerabilities
diff --git a/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst b/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst
new file mode 100644
index 0000000000000..264bfa937f7de
--- /dev/null
+++ b/Documentation/admin-guide/hw-vuln/gather_data_sampling.rst
@@ -0,0 +1,109 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+GDS - Gather Data Sampling
+==========================
+
+Gather Data Sampling is a hardware vulnerability which allows unprivileged
+speculative access to data which was previously stored in vector registers.
+
+Problem
+-------
+When a gather instruction performs loads from memory, different data elements
+are merged into the destination vector register. However, when a gather
+instruction that is transiently executed encounters a fault, stale data from
+architectural or internal vector registers may get transiently forwarded to the
+destination vector register instead. This will allow a malicious attacker to
+infer stale data using typical side channel techniques like cache timing
+attacks. GDS is a purely sampling-based attack.
+
+The attacker uses gather instructions to infer the stale vector register data.
+The victim does not need to do anything special other than use the vector
+registers. The victim does not need to use gather instructions to be
+vulnerable.
+
+Because the buffers are shared between Hyper-Threads cross Hyper-Thread attacks
+are possible.
+
+Attack scenarios
+----------------
+Without mitigation, GDS can infer stale data across virtually all
+permission boundaries:
+
+ Non-enclaves can infer SGX enclave data
+ Userspace can infer kernel data
+ Guests can infer data from hosts
+ Guest can infer guest from other guests
+ Users can infer data from other users
+
+Because of this, it is important to ensure that the mitigation stays enabled in
+lower-privilege contexts like guests and when running outside SGX enclaves.
+
+The hardware enforces the mitigation for SGX. Likewise, VMMs should ensure
+that guests are not allowed to disable the GDS mitigation. If a host erred and
+allowed this, a guest could theoretically disable GDS mitigation, mount an
+attack, and re-enable it.
+
+Mitigation mechanism
+--------------------
+This issue is mitigated in microcode. The microcode defines the following new
+bits:
+
+ ================================ === ============================
+ IA32_ARCH_CAPABILITIES[GDS_CTRL] R/O Enumerates GDS vulnerability
+ and mitigation support.
+ IA32_ARCH_CAPABILITIES[GDS_NO] R/O Processor is not vulnerable.
+ IA32_MCU_OPT_CTRL[GDS_MITG_DIS] R/W Disables the mitigation
+ 0 by default.
+ IA32_MCU_OPT_CTRL[GDS_MITG_LOCK] R/W Locks GDS_MITG_DIS=0. Writes
+ to GDS_MITG_DIS are ignored
+ Can't be cleared once set.
+ ================================ === ============================
+
+GDS can also be mitigated on systems that don't have updated microcode by
+disabling AVX. This can be done by setting gather_data_sampling="force" or
+"clearcpuid=avx" on the kernel command-line.
+
+If used, these options will disable AVX use by turning off XSAVE YMM support.
+However, the processor will still enumerate AVX support. Userspace that
+does not follow proper AVX enumeration to check both AVX *and* XSAVE YMM
+support will break.
+
+Mitigation control on the kernel command line
+---------------------------------------------
+The mitigation can be disabled by setting "gather_data_sampling=off" or
+"mitigations=off" on the kernel command line. Not specifying either will default
+to the mitigation being enabled. Specifying "gather_data_sampling=force" will
+use the microcode mitigation when available or disable AVX on affected systems
+where the microcode hasn't been updated to include the mitigation.
+
+GDS System Information
+------------------------
+The kernel provides vulnerability status information through sysfs. For
+GDS this can be accessed by the following sysfs file:
+
+/sys/devices/system/cpu/vulnerabilities/gather_data_sampling
+
+The possible values contained in this file are:
+
+ ============================== =============================================
+ Not affected Processor not vulnerable.
+ Vulnerable Processor vulnerable and mitigation disabled.
+ Vulnerable: No microcode Processor vulnerable and microcode is missing
+ mitigation.
+ Mitigation: AVX disabled,
+ no microcode Processor is vulnerable and microcode is missing
+ mitigation. AVX disabled as mitigation.
+ Mitigation: Microcode Processor is vulnerable and mitigation is in
+ effect.
+ Mitigation: Microcode (locked) Processor is vulnerable and mitigation is in
+ effect and cannot be disabled.
+ Unknown: Dependent on
+ hypervisor status Running on a virtual guest processor that is
+ affected but with no way to know if host
+ processor is mitigated or vulnerable.
+ ============================== =============================================
+
+GDS Default mitigation
+----------------------
+The updated microcode will enable the mitigation by default. The kernel's
+default action is to leave the mitigation enabled.
diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst
index e0614760a99e7..6828102baaa7a 100644
--- a/Documentation/admin-guide/hw-vuln/index.rst
+++ b/Documentation/admin-guide/hw-vuln/index.rst
@@ -19,3 +19,5 @@ are configurable at compile, boot or run time.
l1d_flush.rst
processor_mmio_stale_data.rst
cross-thread-rsb.rst
+ gather_data_sampling.rst
+ srso
diff --git a/Documentation/admin-guide/hw-vuln/srso.rst b/Documentation/admin-guide/hw-vuln/srso.rst
new file mode 100644
index 0000000000000..2f923c805802f
--- /dev/null
+++ b/Documentation/admin-guide/hw-vuln/srso.rst
@@ -0,0 +1,133 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Speculative Return Stack Overflow (SRSO)
+========================================
+
+This is a mitigation for the speculative return stack overflow (SRSO)
+vulnerability found on AMD processors. The mechanism is by now the well
+known scenario of poisoning CPU functional units - the Branch Target
+Buffer (BTB) and Return Address Predictor (RAP) in this case - and then
+tricking the elevated privilege domain (the kernel) into leaking
+sensitive data.
+
+AMD CPUs predict RET instructions using a Return Address Predictor (aka
+Return Address Stack/Return Stack Buffer). In some cases, a non-architectural
+CALL instruction (i.e., an instruction predicted to be a CALL but is
+not actually a CALL) can create an entry in the RAP which may be used
+to predict the target of a subsequent RET instruction.
+
+The specific circumstances that lead to this varies by microarchitecture
+but the concern is that an attacker can mis-train the CPU BTB to predict
+non-architectural CALL instructions in kernel space and use this to
+control the speculative target of a subsequent kernel RET, potentially
+leading to information disclosure via a speculative side-channel.
+
+The issue is tracked under CVE-2023-20569.
+
+Affected processors
+-------------------
+
+AMD Zen, generations 1-4. That is, all families 0x17 and 0x19. Older
+processors have not been investigated.
+
+System information and options
+------------------------------
+
+First of all, it is required that the latest microcode be loaded for
+mitigations to be effective.
+
+The sysfs file showing SRSO mitigation status is:
+
+ /sys/devices/system/cpu/vulnerabilities/spec_rstack_overflow
+
+The possible values in this file are:
+
+ - 'Not affected' The processor is not vulnerable
+
+ - 'Vulnerable: no microcode' The processor is vulnerable, no
+ microcode extending IBPB functionality
+ to address the vulnerability has been
+ applied.
+
+ - 'Mitigation: microcode' Extended IBPB functionality microcode
+ patch has been applied. It does not
+ address User->Kernel and Guest->Host
+ transitions protection but it does
+ address User->User and VM->VM attack
+ vectors.
+
+ (spec_rstack_overflow=microcode)
+
+ - 'Mitigation: safe RET' Software-only mitigation. It complements
+ the extended IBPB microcode patch
+ functionality by addressing User->Kernel
+ and Guest->Host transitions protection.
+
+ Selected by default or by
+ spec_rstack_overflow=safe-ret
+
+ - 'Mitigation: IBPB' Similar protection as "safe RET" above
+ but employs an IBPB barrier on privilege
+ domain crossings (User->Kernel,
+ Guest->Host).
+
+ (spec_rstack_overflow=ibpb)
+
+ - 'Mitigation: IBPB on VMEXIT' Mitigation addressing the cloud provider
+ scenario - the Guest->Host transitions
+ only.
+
+ (spec_rstack_overflow=ibpb-vmexit)
+
+In order to exploit vulnerability, an attacker needs to:
+
+ - gain local access on the machine
+
+ - break kASLR
+
+ - find gadgets in the running kernel in order to use them in the exploit
+
+ - potentially create and pin an additional workload on the sibling
+ thread, depending on the microarchitecture (not necessary on fam 0x19)
+
+ - run the exploit
+
+Considering the performance implications of each mitigation type, the
+default one is 'Mitigation: safe RET' which should take care of most
+attack vectors, including the local User->Kernel one.
+
+As always, the user is advised to keep her/his system up-to-date by
+applying software updates regularly.
+
+The default setting will be reevaluated when needed and especially when
+new attack vectors appear.
+
+As one can surmise, 'Mitigation: safe RET' does come at the cost of some
+performance depending on the workload. If one trusts her/his userspace
+and does not want to suffer the performance impact, one can always
+disable the mitigation with spec_rstack_overflow=off.
+
+Similarly, 'Mitigation: IBPB' is another full mitigation type employing
+an indrect branch prediction barrier after having applied the required
+microcode patch for one's system. This mitigation comes also at
+a performance cost.
+
+Mitigation: safe RET
+--------------------
+
+The mitigation works by ensuring all RET instructions speculate to
+a controlled location, similar to how speculation is controlled in the
+retpoline sequence. To accomplish this, the __x86_return_thunk forces
+the CPU to mispredict every function return using a 'safe return'
+sequence.
+
+To ensure the safety of this mitigation, the kernel must ensure that the
+safe return sequence is itself free from attacker interference. In Zen3
+and Zen4, this is accomplished by creating a BTB alias between the
+untraining function srso_untrain_ret_alias() and the safe return
+function srso_safe_ret_alias() which results in evicting a potentially
+poisoned BTB entry and using that safe one for all function returns.
+
+In older Zen1 and Zen2, this is accomplished using a reinterpretation
+technique similar to Retbleed one: srso_untrain_ret() and
+srso_safe_ret().
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 6b838869554b1..286be425f3bfa 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1593,6 +1593,26 @@
Format: off | on
default: on
+ gather_data_sampling=
+ [X86,INTEL] Control the Gather Data Sampling (GDS)
+ mitigation.
+
+ Gather Data Sampling is a hardware vulnerability which
+ allows unprivileged speculative access to data which was
+ previously stored in vector registers.
+
+ This issue is mitigated by default in updated microcode.
+ The mitigation may have a performance impact but can be
+ disabled. On systems without the microcode mitigation
+ disabling AVX serves as a mitigation.
+
+ force: Disable AVX to mitigate systems without
+ microcode mitigation. No effect if the microcode
+ mitigation is present. Known to cause crashes in
+ userspace with buggy AVX enumeration.
+
+ off: Disable GDS mitigation.
+
gcov_persist= [GCOV] When non-zero (default), profiling data for
kernel modules is saved and remains accessible via
debugfs, even when the module is unloaded/reloaded.
@@ -3228,24 +3248,25 @@
Disable all optional CPU mitigations. This
improves system performance, but it may also
expose users to several CPU vulnerabilities.
- Equivalent to: nopti [X86,PPC]
- if nokaslr then kpti=0 [ARM64]
- nospectre_v1 [X86,PPC]
- nobp=0 [S390]
- nospectre_v2 [X86,PPC,S390,ARM64]
- spectre_v2_user=off [X86]
- spec_store_bypass_disable=off [X86,PPC]
- ssbd=force-off [ARM64]
- nospectre_bhb [ARM64]
+ Equivalent to: if nokaslr then kpti=0 [ARM64]
+ gather_data_sampling=off [X86]
+ kvm.nx_huge_pages=off [X86]
l1tf=off [X86]
mds=off [X86]
- tsx_async_abort=off [X86]
- kvm.nx_huge_pages=off [X86]
- srbds=off [X86,INTEL]
+ mmio_stale_data=off [X86]
no_entry_flush [PPC]
no_uaccess_flush [PPC]
- mmio_stale_data=off [X86]
+ nobp=0 [S390]
+ nopti [X86,PPC]
+ nospectre_bhb [ARM64]
+ nospectre_v1 [X86,PPC]
+ nospectre_v2 [X86,PPC,S390,ARM64]
retbleed=off [X86]
+ spec_store_bypass_disable=off [X86,PPC]
+ spectre_v2_user=off [X86]
+ srbds=off [X86,INTEL]
+ ssbd=force-off [ARM64]
+ tsx_async_abort=off [X86]
Exceptions:
This does not have any effect on
@@ -5764,6 +5785,17 @@
Not specifying this option is equivalent to
spectre_v2_user=auto.
+ spec_rstack_overflow=
+ [X86] Control RAS overflow mitigation on AMD Zen CPUs
+
+ off - Disable mitigation
+ microcode - Enable microcode mitigation only
+ safe-ret - Enable sw-only safe RET mitigation (default)
+ ibpb - Enable mitigation by issuing IBPB on
+ kernel entry
+ ibpb-vmexit - Issue IBPB only on VMEXIT
+ (cloud-specific mitigation)
+
spec_store_bypass_disable=
[HW] Control Speculative Store Bypass (SSB) Disable mitigation
(Speculative Store Bypass vulnerability)
diff --git a/Makefile b/Makefile
index 69cdd0d2946c3..612f3d83629b4 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
VERSION = 6
PATCHLEVEL = 1
-SUBLEVEL = 43
+SUBLEVEL = 44
EXTRAVERSION =
NAME = Curry Ramen
diff --git a/arch/Kconfig b/arch/Kconfig
index 81599f5c17b0f..b60d271bf76a9 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -285,6 +285,9 @@ config ARCH_HAS_DMA_SET_UNCACHED
config ARCH_HAS_DMA_CLEAR_UNCACHED
bool
+config ARCH_HAS_CPU_FINALIZE_INIT
+ bool
+
# Select if arch init_task must go in the __init_task_data section
config ARCH_TASK_STRUCT_ON_STACK
bool
diff --git a/arch/alpha/include/asm/bugs.h b/arch/alpha/include/asm/bugs.h
deleted file mode 100644
index 78030d1c7e7e0..0000000000000
--- a/arch/alpha/include/asm/bugs.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * include/asm-alpha/bugs.h
- *
- * Copyright (C) 1994 Linus Torvalds
- */
-
-/*
- * This is included by init/main.c to check for architecture-dependent bugs.
- *
- * Needs:
- * void check_bugs(void);
- */
-
-/*
- * I don't know of any alpha bugs yet.. Nice chip
- */
-
-static void check_bugs(void)
-{
-}
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 0202e48e7a207..6d5afe2e6ba33 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -5,6 +5,7 @@ config ARM
select ARCH_32BIT_OFF_T
select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE if HAVE_KRETPROBES && FRAME_POINTER && !ARM_UNWIND
select ARCH_HAS_BINFMT_FLAT
+ select ARCH_HAS_CPU_FINALIZE_INIT if MMU
select ARCH_HAS_CURRENT_STACK_POINTER
select ARCH_HAS_DEBUG_VIRTUAL if MMU
select ARCH_HAS_DMA_WRITE_COMBINE if !ARM_DMA_MEM_BUFFERABLE
diff --git a/arch/arm/include/asm/bugs.h b/arch/arm/include/asm/bugs.h
index 97a312ba08401..fe385551edeca 100644
--- a/arch/arm/include/asm/bugs.h
+++ b/arch/arm/include/asm/bugs.h
@@ -1,7 +1,5 @@
/* SPDX-License-Identifier: GPL-2.0-only */
/*
- * arch/arm/include/asm/bugs.h
- *
* Copyright (C) 1995-2003 Russell King
*/
#ifndef __ASM_BUGS_H
@@ -10,10 +8,8 @@
extern void check_writebuffer_bugs(void);
#ifdef CONFIG_MMU
-extern void check_bugs(void);
extern void check_other_bugs(void);
#else
-#define check_bugs() do { } while (0)
#define check_other_bugs() do { } while (0)
#endif
diff --git a/arch/arm/kernel/bugs.c b/arch/arm/kernel/bugs.c
index 14c8dbbb7d2df..087bce6ec8e9b 100644
--- a/arch/arm/kernel/bugs.c
+++ b/arch/arm/kernel/bugs.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/init.h>
+#include <linux/cpu.h>
#include <asm/bugs.h>
#include <asm/proc-fns.h>
@@ -11,7 +12,7 @@ void check_other_bugs(void)
#endif
}
-void __init check_bugs(void)
+void __init arch_cpu_finalize_init(void)
{
check_writebuffer_bugs();
check_other_bugs();
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index c6e06cdc738f0..283b751cbf6ab 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -9,6 +9,7 @@ menu "Processor type and features"
config IA64
bool
select ARCH_BINFMT_ELF_EXTRA_PHDRS
+ select ARCH_HAS_CPU_FINALIZE_INIT
select ARCH_HAS_DMA_MARK_CLEAN
select ARCH_HAS_STRNCPY_FROM_USER
select ARCH_HAS_STRNLEN_USER
diff --git a/arch/ia64/include/asm/bugs.h b/arch/ia64/include/asm/bugs.h
deleted file mode 100644
index 0d6b9bded56c6..0000000000000
--- a/arch/ia64/include/asm/bugs.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * This is included by init/main.c to check for architecture-dependent bugs.
- *
- * Needs:
- * void check_bugs(void);
- *
- * Based on <asm-alpha/bugs.h>.
- *
- * Modified 1998, 1999, 2003
- * David Mosberger-Tang <davidm@hpl.hp.com>, Hewlett-Packard Co.
- */
-#ifndef _ASM_IA64_BUGS_H
-#define _ASM_IA64_BUGS_H
-
-#include <asm/processor.h>
-
-extern void check_bugs (void);
-
-#endif /* _ASM_IA64_BUGS_H */
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index c057280442727..9009f1871e3b8 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -1067,8 +1067,7 @@ cpu_init (void)
}
}
-void __init
-check_bugs (void)
+void __init arch_cpu_finalize_init(void)
{
ia64_patch_mckinley_e9((unsigned long) __start___mckinley_e9_bundles,
(unsigned long) __end___mckinley_e9_bundles);
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index e737dc8cd660c..270742cc3ca49 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -10,6 +10,7 @@ config LOONGARCH
select ARCH_ENABLE_MEMORY_HOTPLUG
select ARCH_ENABLE_MEMORY_HOTREMOVE
select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
+ select ARCH_HAS_CPU_FINALIZE_INIT
select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
select ARCH_HAS_PTE_SPECIAL
select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index ae436def7ee98..29725b37b35ca 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -12,6 +12,7 @@
*/
#include <linux/init.h>
#include <linux/acpi.h>
+#include <linux/cpu.h>
#include <linux/dmi.h>
#include <linux/efi.h>
#include <linux/export.h>
@@ -80,6 +81,11 @@ const char *get_system_type(void)
return "generic-loongson-machine";
}
+void __init arch_cpu_finalize_init(void)
+{
+ alternative_instructions();
+}
+
static const char *dmi_string_parse(const struct dmi_header *dm, u8 s)
{
const u8 *bp = ((u8 *) dm) + dm->length;
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index 7bff881185070..1fe5b20187457 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -4,6 +4,7 @@ config M68K
default y
select ARCH_32BIT_OFF_T
select ARCH_HAS_BINFMT_FLAT
+ select ARCH_HAS_CPU_FINALIZE_INIT if MMU
select ARCH_HAS_CURRENT_STACK_POINTER
select ARCH_HAS_DMA_PREP_COHERENT if HAS_DMA && MMU && !COLDFIRE
select ARCH_HAS_SYNC_DMA_FOR_DEVICE if HAS_DMA
diff --git a/arch/m68k/include/asm/bugs.h b/arch/m68k/include/asm/bugs.h
deleted file mode 100644
index 745530651e0bf..0000000000000
--- a/arch/m68k/include/asm/bugs.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * include/asm-m68k/bugs.h
- *
- * Copyright (C) 1994 Linus Torvalds
- */
-
-/*
- * This is included by init/main.c to check for architecture-dependent bugs.
- *
- * Needs:
- * void check_bugs(void);
- */
-
-#ifdef CONFIG_MMU
-extern void check_bugs(void); /* in arch/m68k/kernel/setup.c */
-#else
-static void check_bugs(void)
-{
-}
-#endif
diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c
index fbff1cea62caa..6f1ae01f322cf 100644
--- a/arch/m68k/kernel/setup_mm.c
+++ b/arch/m68k/kernel/setup_mm.c
@@ -10,6 +10,7 @@
*/
#include <linux/kernel.h>
+#include <linux/cpu.h>
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/delay.h>
@@ -504,7 +505,7 @@ static int __init proc_hardware_init(void)
module_init(proc_hardware_init);
#endif
-void check_bugs(void)
+void __init arch_cpu_finalize_init(void)
{
#if defined(CONFIG_FPU) && !defined(CONFIG_M68KFPU_EMU)
if (m68k_fputype == 0) {
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 7b0856c76c9ad..cf1fbf4eaa8a0 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -4,6 +4,7 @@ config MIPS
default y
select ARCH_32BIT_OFF_T if !64BIT
select ARCH_BINFMT_ELF_STATE if MIPS_FP_SUPPORT
+ select ARCH_HAS_CPU_FINALIZE_INIT
select ARCH_HAS_CURRENT_STACK_POINTER if !CC_IS_CLANG || CLANG_VERSION >= 140000
select ARCH_HAS_DEBUG_VIRTUAL if !64BIT
select ARCH_HAS_FORTIFY_SOURCE
diff --git a/arch/mips/include/asm/bugs.h b/arch/mips/include/asm/bugs.h
index d72dc6e1cf3cd..8d4cf29861b87 100644
--- a/arch/mips/include/asm/bugs.h
+++ b/arch/mips/include/asm/bugs.h
@@ -1,17 +1,11 @@
/* SPDX-License-Identifier: GPL-2.0 */
/*
- * This is included by init/main.c to check for architecture-dependent bugs.
- *
* Copyright (C) 2007 Maciej W. Rozycki
- *
- * Needs:
- * void check_bugs(void);
*/
#ifndef _ASM_BUGS_H
#define _ASM_BUGS_H
#include <linux/bug.h>
-#include <linux/delay.h>
#include <linux/smp.h>
#include <asm/cpu.h>
@@ -30,17 +24,6 @@ static inline void check_bugs_early(void)
check_bugs64_early();
}
-static inline void check_bugs(void)
-{
- unsigned int cpu = smp_processor_id();
-
- cpu_data[cpu].udelay_val = loops_per_jiffy;
- check_bugs32();
-
- if (IS_ENABLED(CONFIG_CPU_R4X00_BUGS64))
- check_bugs64();
-}
-
static inline int r4k_daddiu_bug(void)
{
if (!IS_ENABLED(CONFIG_CPU_R4X00_BUGS64))
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 81dbb4ef52317..7c540572f1f72 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -11,6 +11,8 @@
* Copyright (C) 2000, 2001, 2002, 2007 Maciej W. Rozycki
*/
#include <linux/init.h>
+#include <linux/cpu.h>
+#include <linux/delay.h>
#include <linux/ioport.h>
#include <linux/export.h>
#include <linux/screen_info.h>
@@ -840,3 +842,14 @@ static int __init setnocoherentio(char *str)
}
early_param("nocoherentio", setnocoherentio);
#endif
+
+void __init arch_cpu_finalize_init(void)
+{
+ unsigned int cpu = smp_processor_id();
+
+ cpu_data[cpu].udelay_val = loops_per_jiffy;
+ check_bugs32();
+
+ if (IS_ENABLED(CONFIG_CPU_R4X00_BUGS64))
+ check_bugs64();
+}
diff --git a/arch/parisc/include/asm/bugs.h b/arch/parisc/include/asm/bugs.h
deleted file mode 100644
index 0a7f9db6bd1c7..0000000000000
--- a/arch/parisc/include/asm/bugs.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * include/asm-parisc/bugs.h
- *
- * Copyright (C) 1999 Mike Shaver
- */
-
-/*
- * This is included by init/main.c to check for architecture-dependent bugs.
- *
- * Needs:
- * void check_bugs(void);
- */
-
-#include <asm/processor.h>
-
-static inline void check_bugs(void)
-{
-// identify_cpu(&boot_cpu_data);
-}
diff --git a/arch/powerpc/include/asm/bugs.h b/arch/powerpc/include/asm/bugs.h
deleted file mode 100644
index 01b8f6ca4dbbc..0000000000000
--- a/arch/powerpc/include/asm/bugs.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-#ifndef _ASM_POWERPC_BUGS_H
-#define _ASM_POWERPC_BUGS_H
-
-/*
- */
-
-/*
- * This file is included by 'init/main.c' to check for
- * architecture-dependent bugs.
- */
-
-static inline void check_bugs(void) { }
-
-#endif /* _ASM_POWERPC_BUGS_H */
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 8e4d1f757bcc9..a0593f6ce0e0f 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -7,6 +7,7 @@ config SUPERH
select ARCH_HAVE_CUSTOM_GPIO_H
select ARCH_HAVE_NMI_SAFE_CMPXCHG if (GUSA_RB || CPU_SH4A)
select ARCH_HAS_BINFMT_FLAT if !MMU
+ select ARCH_HAS_CPU_FINALIZE_INIT
select ARCH_HAS_CURRENT_STACK_POINTER
select ARCH_HAS_GIGANTIC_PAGE
select ARCH_HAS_GCOV_PROFILE_ALL
diff --git a/arch/sh/include/asm/bugs.h b/arch/sh/include/asm/bugs.h
deleted file mode 100644
index fe52abb69cea3..0000000000000
--- a/arch/sh/include/asm/bugs.h
+++ /dev/null
@@ -1,74 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __ASM_SH_BUGS_H
-#define __ASM_SH_BUGS_H
-
-/*
- * This is included by init/main.c to check for architecture-dependent bugs.
- *
- * Needs:
- * void check_bugs(void);
- */
-
-/*
- * I don't know of any Super-H bugs yet.
- */
-
-#include <asm/processor.h>
-
-extern void select_idle_routine(void);
-
-static void __init check_bugs(void)
-{
- extern unsigned long loops_per_jiffy;
- char *p = &init_utsname()->machine[2]; /* "sh" */
-
- select_idle_routine();
-
- current_cpu_data.loops_per_jiffy = loops_per_jiffy;
-
- switch (current_cpu_data.family) {
- case CPU_FAMILY_SH2:
- *p++ = '2';
- break;
- case CPU_FAMILY_SH2A:
- *p++ = '2';
- *p++ = 'a';
- break;
- case CPU_FAMILY_SH3:
- *p++ = '3';
- break;
- case CPU_FAMILY_SH4:
- *p++ = '4';
- break;
- case CPU_FAMILY_SH4A:
- *p++ = '4';
- *p++ = 'a';
- break;
- case CPU_FAMILY_SH4AL_DSP:
- *p++ = '4';
- *p++ = 'a';
- *p++ = 'l';
- *p++ = '-';
- *p++ = 'd';
- *p++ = 's';
- *p++ = 'p';
- break;
- case CPU_FAMILY_UNKNOWN:
- /*
- * Specifically use CPU_FAMILY_UNKNOWN rather than
- * default:, so we're able to have the compiler whine
- * about unhandled enumerations.
- */
- break;
- }
-
- printk("CPU: %s\n", get_cpu_subtype(&current_cpu_data));
-
-#ifndef __LITTLE_ENDIAN__
- /* 'eb' means 'Endian Big' */
- *p++ = 'e';
- *p++ = 'b';
-#endif
- *p = '\0';
-}
-#endif /* __ASM_SH_BUGS_H */
diff --git a/arch/sh/include/asm/processor.h b/arch/sh/include/asm/processor.h
index 85a6c1c3c16e7..73fba7c922f92 100644
--- a/arch/sh/include/asm/processor.h
+++ b/arch/sh/include/asm/processor.h
@@ -166,6 +166,8 @@ extern unsigned int instruction_size(unsigned int insn);
#define instruction_size(insn) (2)
#endif
+void select_idle_routine(void);
+
#endif /* __ASSEMBLY__ */
#include <asm/processor_32.h>
diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c
index f59814983bd59..a80b2a5b25c7f 100644
--- a/arch/sh/kernel/idle.c
+++ b/arch/sh/kernel/idle.c
@@ -14,6 +14,7 @@
#include <linux/irqflags.h>
#include <linux/smp.h>
#include <linux/atomic.h>
+#include <asm/processor.h>
#include <asm/smp.h>
#include <asm/bl_bit.h>
diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c
index af977ec4ca5e5..cf7c0f72f2935 100644
--- a/arch/sh/kernel/setup.c
+++ b/arch/sh/kernel/setup.c
@@ -43,6 +43,7 @@
#include <asm/smp.h>
#include <asm/mmu_context.h>
#include <asm/mmzone.h>
+#include <asm/processor.h>
#include <asm/sparsemem.h>
#include <asm/platform_early.h>
@@ -354,3 +355,57 @@ int test_mode_pin(int pin)
{
return sh_mv.mv_mode_pins() & pin;
}
+
+void __init arch_cpu_finalize_init(void)
+{
+ char *p = &init_utsname()->machine[2]; /* "sh" */
+
+ select_idle_routine();
+
+ current_cpu_data.loops_per_jiffy = loops_per_jiffy;
+
+ switch (current_cpu_data.family) {
+ case CPU_FAMILY_SH2:
+ *p++ = '2';
+ break;
+ case CPU_FAMILY_SH2A:
+ *p++ = '2';
+ *p++ = 'a';
+ break;
+ case CPU_FAMILY_SH3:
+ *p++ = '3';
+ break;
+ case CPU_FAMILY_SH4:
+ *p++ = '4';
+ break;
+ case CPU_FAMILY_SH4A:
+ *p++ = '4';
+ *p++ = 'a';
+ break;
+ case CPU_FAMILY_SH4AL_DSP:
+ *p++ = '4';
+ *p++ = 'a';
+ *p++ = 'l';
+ *p++ = '-';
+ *p++ = 'd';
+ *p++ = 's';
+ *p++ = 'p';
+ break;
+ case CPU_FAMILY_UNKNOWN:
+ /*
+ * Specifically use CPU_FAMILY_UNKNOWN rather than
+ * default:, so we're able to have the compiler whine
+ * about unhandled enumerations.
+ */
+ break;
+ }
+
+ pr_info("CPU: %s\n", get_cpu_subtype(&current_cpu_data));
+
+#ifndef __LITTLE_ENDIAN__
+ /* 'eb' means 'Endian Big' */
+ *p++ = 'e';
+ *p++ = 'b';
+#endif
+ *p = '\0';
+}
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index dbb1760cbe8c9..b67d96e3392e5 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -51,6 +51,7 @@ config SPARC
config SPARC32
def_bool !64BIT
select ARCH_32BIT_OFF_T
+ select ARCH_HAS_CPU_FINALIZE_INIT if !SMP
select ARCH_HAS_SYNC_DMA_FOR_CPU
select CLZ_TAB
select DMA_DIRECT_REMAP
diff --git a/arch/sparc/include/asm/bugs.h b/arch/sparc/include/asm/bugs.h
deleted file mode 100644
index 02fa369b9c21f..0000000000000
--- a/arch/sparc/include/asm/bugs.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* include/asm/bugs.h: Sparc probes for various bugs.
- *
- * Copyright (C) 1996, 2007 David S. Miller (davem@davemloft.net)
- */
-
-#ifdef CONFIG_SPARC32
-#include <asm/cpudata.h>
-#endif
-
-extern unsigned long loops_per_jiffy;
-
-static void __init check_bugs(void)
-{
-#if defined(CONFIG_SPARC32) && !defined(CONFIG_SMP)
- cpu_data(0).udelay_val = loops_per_jiffy;
-#endif
-}
diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c
index c8e0dd99f3700..c9d1ba4f311b9 100644
--- a/arch/sparc/kernel/setup_32.c
+++ b/arch/sparc/kernel/setup_32.c
@@ -412,3 +412,10 @@ static int __init topology_init(void)
}
subsys_initcall(topology_init);
+
+#if defined(CONFIG_SPARC32) && !defined(CONFIG_SMP)
+void __init arch_cpu_finalize_init(void)
+{
+ cpu_data(0).udelay_val = loops_per_jiffy;
+}
+#endif
diff --git a/arch/um/Kconfig b/arch/um/Kconfig
index ad4ff3b0e91e5..82709bc36df7d 100644
--- a/arch/um/Kconfig
+++ b/arch/um/Kconfig
@@ -6,6 +6,7 @@ config UML
bool
default y
select ARCH_EPHEMERAL_INODES
+ select ARCH_HAS_CPU_FINALIZE_INIT
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
select ARCH_HAS_KCOV
diff --git a/arch/um/include/asm/bugs.h b/arch/um/include/asm/bugs.h
deleted file mode 100644
index 4473942a08397..0000000000000
--- a/arch/um/include/asm/bugs.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __UM_BUGS_H
-#define __UM_BUGS_H
-
-void check_bugs(void);
-
-#endif
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index 8adf8e89b2558..334c91191b316 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -3,6 +3,7 @@
* Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
*/
+#include <linux/cpu.h>
#include <linux/delay.h>
#include <linux/init.h>
#include <linux/mm.h>
@@ -426,7 +427,7 @@ void __init setup_arch(char **cmdline_p)
}
}
-void __init check_bugs(void)
+void __init arch_cpu_finalize_init(void)
{
arch_check_bugs();
os_check_bugs();
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index b3d5706579d43..4c9bfc4be58d4 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -69,6 +69,7 @@ config X86
select ARCH_ENABLE_THP_MIGRATION if X86_64 && TRANSPARENT_HUGEPAGE
select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
select ARCH_HAS_CACHE_LINE_SIZE
+ select ARCH_HAS_CPU_FINALIZE_INIT
select ARCH_HAS_CURRENT_STACK_POINTER
select ARCH_HAS_DEBUG_VIRTUAL
select ARCH_HAS_DEBUG_VM_PGTABLE if !X86_PAE
@@ -2511,6 +2512,13 @@ config CPU_IBRS_ENTRY
This mitigates both spectre_v2 and retbleed at great cost to
performance.
+config CPU_SRSO
+ bool "Mitigate speculative RAS overflow on AMD"
+ depends on CPU_SUP_AMD && X86_64 && RETHUNK
+ default y
+ help
+ Enable the SRSO mitigation needed on AMD Zen1-4 machines.
+
config SLS
bool "Mitigate Straight-Line-Speculation"
depends on CC_HAS_SLS && X86_64
@@ -2521,6 +2529,25 @@ config SLS
against straight line speculation. The kernel image might be slightly
larger.
+config GDS_FORCE_MITIGATION
+ bool "Force GDS Mitigation"
+ depends on CPU_SUP_INTEL
+ default n
+ help
+ Gather Data Sampling (GDS) is a hardware vulnerability which allows
+ unprivileged speculative access to data which was previously stored in
+ vector registers.
+
+ This option is equivalent to setting gather_data_sampling=force on the
+ command line. The microcode mitigation is used if present, otherwise
+ AVX is disabled as a mitigation. On affected systems that are missing
+ the microcode any userspace code that unconditionally uses AVX will
+ break with this option set.
+
+ Setting this option on systems not vulnerable to GDS has no effect.
+
+ If in doubt, say N.
+
endif
config ARCH_HAS_ADD_PAGES
diff --git a/arch/x86/include/asm/bugs.h b/arch/x86/include/asm/bugs.h
index 92ae283899409..f25ca2d709d40 100644
--- a/arch/x86/include/asm/bugs.h
+++ b/arch/x86/include/asm/bugs.h
@@ -4,8 +4,6 @@
#include <asm/processor.h>
-extern void check_bugs(void);
-
#if defined(CONFIG_CPU_SUP_INTEL) && defined(CONFIG_X86_32)
int ppro_with_ram_bug(void);
#else
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 1a85e1fb09226..ce0c8f7d32186 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -32,6 +32,7 @@ enum cpuid_leafs
CPUID_8000_0007_EBX,
CPUID_7_EDX,
CPUID_8000_001F_EAX,
+ CPUID_8000_0021_EAX,
};
#define X86_CAP_FMT_NUM "%d:%d"
@@ -94,8 +95,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 17, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) || \
+ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 20, feature_bit) || \
REQUIRED_MASK_CHECK || \
- BUILD_BUG_ON_ZERO(NCAPINTS != 20))
+ BUILD_BUG_ON_ZERO(NCAPINTS != 21))
#define DISABLED_MASK_BIT_SET(feature_bit) \
( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \
@@ -118,8 +120,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 17, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \
CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) || \
+ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 20, feature_bit) || \
DISABLED_MASK_CHECK || \
- BUILD_BUG_ON_ZERO(NCAPINTS != 20))
+ BUILD_BUG_ON_ZERO(NCAPINTS != 21))
#define cpu_has(c, bit) \
(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 92729c38853d1..e721b8426c245 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -13,8 +13,8 @@
/*
* Defines x86 CPU feature bits
*/
-#define NCAPINTS 20 /* N 32-bit words worth of info */
-#define NBUGINTS 1 /* N 32-bit bug flags */
+#define NCAPINTS 21 /* N 32-bit words worth of info */
+#define NBUGINTS 2 /* N 32-bit bug flags */
/*
* Note: If the comment begins with a quoted string, that string is used
@@ -308,6 +308,10 @@
#define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */
+#define X86_FEATURE_SRSO (11*32+24) /* "" AMD BTB untrain RETs */
+#define X86_FEATURE_SRSO_ALIAS (11*32+25) /* "" AMD BTB untrain RETs through aliasing */
+#define X86_FEATURE_IBPB_ON_VMEXIT (11*32+26) /* "" Issue an IBPB only on VMEXIT */
+
/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */
#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */
@@ -423,6 +427,10 @@
#define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */
#define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */
+#define X86_FEATURE_SBPB (20*32+27) /* "" Selective Branch Prediction Barrier */
+#define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */
+#define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */
+
/*
* BUG word(s)
*/
@@ -464,5 +472,8 @@
#define X86_BUG_RETBLEED X86_BUG(27) /* CPU is affected by RETBleed */
#define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */
#define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */
+#define X86_BUG_GDS X86_BUG(30) /* CPU is affected by Gather Data Sampling */
+/* BUG word 2 */
+#define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 33d2cd04d2544..000037078db43 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -111,6 +111,7 @@
#define DISABLED_MASK17 0
#define DISABLED_MASK18 0
#define DISABLED_MASK19 0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20)
+#define DISABLED_MASK20 0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
#endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index 503a577814b2e..b475d9a582b88 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -109,7 +109,7 @@ extern void fpu_reset_from_exception_fixup(void);
/* Boot, hotplug and resume */
extern void fpu__init_cpu(void);
-extern void fpu__init_system(struct cpuinfo_x86 *c);
+extern void fpu__init_system(void);
extern void fpu__init_check_bugs(void);
extern void fpu__resume_cpu(void);
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index 72ca90552b6a4..8f513372cd8d4 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -17,6 +17,12 @@
#include <asm/bootparam.h>
+#ifdef CONFIG_X86_MEM_ENCRYPT
+void __init mem_encrypt_init(void);
+#else
+static inline void mem_encrypt_init(void) { }
+#endif
+
#ifdef CONFIG_AMD_MEM_ENCRYPT
extern u64 sme_me_mask;
@@ -86,9 +92,6 @@ static inline void mem_encrypt_free_decrypted_mem(void) { }
#endif /* CONFIG_AMD_MEM_ENCRYPT */
-/* Architecture __weak replacement functions */
-void __init mem_encrypt_init(void);
-
void add_encrypt_protection_map(void);
/*
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 846067e1ee8bb..52d8c67d93081 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -60,6 +60,7 @@
#define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */
#define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */
+#define PRED_CMD_SBPB BIT(7) /* Selective Branch Prediction Barrier */
#define MSR_PPIN_CTL 0x0000004e
#define MSR_PPIN 0x0000004f
@@ -158,6 +159,15 @@
* Not susceptible to Post-Barrier
* Return Stack Buffer Predictions.
*/
+#define ARCH_CAP_GDS_CTRL BIT(25) /*
+ * CPU is vulnerable to Gather
+ * Data Sampling (GDS) and
+ * has controls for mitigation.
+ */
+#define ARCH_CAP_GDS_NO BIT(26) /*
+ * CPU is not vulnerable to Gather
+ * Data Sampling (GDS).
+ */
#define ARCH_CAP_XAPIC_DISABLE BIT(21) /*
* IA32_XAPIC_DISABLE_STATUS MSR
@@ -181,6 +191,8 @@
#define RNGDS_MITG_DIS BIT(0) /* SRBDS support */
#define RTM_ALLOW BIT(1) /* TSX development mode */
#define FB_CLEAR_DIS BIT(3) /* CPU Fill buffer clear disable */
+#define GDS_MITG_DIS BIT(4) /* Disable GDS mitigation */
+#define GDS_MITG_LOCKED BIT(5) /* GDS mitigation locked */
#define MSR_IA32_SYSENTER_CS 0x00000174
#define MSR_IA32_SYSENTER_ESP 0x00000175
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index dfdb103ae4f6f..31fa631c8587c 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -112,7 +112,7 @@
* eventually turn into it's own annotation.
*/
.macro ANNOTATE_UNRET_END
-#ifdef CONFIG_DEBUG_ENTRY
+#if (defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO))
ANNOTATE_RETPOLINE_SAFE
nop
#endif
@@ -185,12 +185,18 @@
* where we have a stack but before any RET instruction.
*/
.macro UNTRAIN_RET
-#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY)
+#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \
+ defined(CONFIG_CPU_SRSO)
ANNOTATE_UNRET_END
ALTERNATIVE_2 "", \
CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET, \
"call entry_ibpb", X86_FEATURE_ENTRY_IBPB
#endif
+
+#ifdef CONFIG_CPU_SRSO
+ ALTERNATIVE_2 "", "call srso_untrain_ret", X86_FEATURE_SRSO, \
+ "call srso_untrain_ret_alias", X86_FEATURE_SRSO_ALIAS
+#endif
.endm
#else /* __ASSEMBLY__ */
@@ -206,6 +212,8 @@ extern retpoline_thunk_t __x86_indirect_thunk_array[];
extern void __x86_return_thunk(void);
extern void zen_untrain_ret(void);
+extern void srso_untrain_ret(void);
+extern void srso_untrain_ret_alias(void);
extern void entry_ibpb(void);
#ifdef CONFIG_RETPOLINE
@@ -311,11 +319,11 @@ void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature)
: "memory");
}
+extern u64 x86_pred_cmd;
+
static inline void indirect_branch_prediction_barrier(void)
{
- u64 val = PRED_CMD_IBPB;
-
- alternative_msr_write(MSR_IA32_PRED_CMD, val, X86_FEATURE_USE_IBPB);
+ alternative_msr_write(MSR_IA32_PRED_CMD, x86_pred_cmd, X86_FEATURE_USE_IBPB);
}
/* The Intel SPEC CTRL MSR base value cache */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index d8277eec1bcd6..c13e4ff8ec70c 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -800,9 +800,11 @@ extern u16 get_llc_id(unsigned int cpu);
#ifdef CONFIG_CPU_SUP_AMD
extern u32 amd_get_nodes_per_socket(void);
extern u32 amd_get_highest_perf(void);
+extern bool cpu_has_ibpb_brtype_microcode(void);
#else
static inline u32 amd_get_nodes_per_socket(void) { return 0; }
static inline u32 amd_get_highest_perf(void) { return 0; }
+static inline bool cpu_has_ibpb_brtype_microcode(void) { return false; }
#endif
#define for_each_possible_hypervisor_cpuid_base(function) \
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index aff774775c678..7ba1726b71c7b 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -98,6 +98,7 @@
#define REQUIRED_MASK17 0
#define REQUIRED_MASK18 0
#define REQUIRED_MASK19 0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 20)
+#define REQUIRED_MASK20 0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
#endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/arch/x86/include/asm/sigframe.h b/arch/x86/include/asm/sigframe.h
index 5b1ed650b1248..84eab27248754 100644
--- a/arch/x86/include/asm/sigframe.h
+++ b/arch/x86/include/asm/sigframe.h
@@ -85,6 +85,4 @@ struct rt_sigframe_x32 {
#endif /* CONFIG_X86_64 */
-void __init init_sigframe_size(void);
-
#endif /* _ASM_X86_SIGFRAME_H */
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 7f4eb8b027cc8..7f0cf4a959c02 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1245,6 +1245,25 @@ u32 amd_get_highest_perf(void)
}
EXPORT_SYMBOL_GPL(amd_get_highest_perf);
+bool cpu_has_ibpb_brtype_microcode(void)
+{
+ switch (boot_cpu_data.x86) {
+ /* Zen1/2 IBPB flushes branch type predictions too. */
+ case 0x17:
+ return boot_cpu_has(X86_FEATURE_AMD_IBPB);
+ case 0x19:
+ /* Poke the MSR bit on Zen3/4 to check its presence. */
+ if (!wrmsrl_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB)) {
+ setup_force_cpu_cap(X86_FEATURE_SBPB);
+ return true;
+ } else {
+ return false;
+ }
+ default:
+ return false;
+ }
+}
+
static void zenbleed_check_cpu(void *unused)
{
struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index f54992887491e..d98f33ea57e47 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -9,7 +9,6 @@
* - Andrew D. Balsa (code cleanup).
*/
#include <linux/init.h>
-#include <linux/utsname.h>
#include <linux/cpu.h>
#include <linux/module.h>
#include <linux/nospec.h>
@@ -27,8 +26,6 @@
#include <asm/msr.h>
#include <asm/vmx.h>
#include <asm/paravirt.h>
-#include <asm/alternative.h>
-#include <asm/set_memory.h>
#include <asm/intel-family.h>
#include <asm/e820/api.h>
#include <asm/hypervisor.h>
@@ -49,6 +46,8 @@ static void __init taa_select_mitigation(void);
static void __init mmio_select_mitigation(void);
static void __init srbds_select_mitigation(void);
static void __init l1d_flush_select_mitigation(void);
+static void __init gds_select_mitigation(void);
+static void __init srso_select_mitigation(void);
/* The base value of the SPEC_CTRL MSR without task-specific bits set */
u64 x86_spec_ctrl_base;
@@ -58,6 +57,9 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_base);
DEFINE_PER_CPU(u64, x86_spec_ctrl_current);
EXPORT_SYMBOL_GPL(x86_spec_ctrl_current);
+u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB;
+EXPORT_SYMBOL_GPL(x86_pred_cmd);
+
static DEFINE_MUTEX(spec_ctrl_mutex);
/* Update SPEC_CTRL MSR and its cached copy unconditionally */
@@ -124,21 +126,8 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);
DEFINE_STATIC_KEY_FALSE(mmio_stale_data_clear);
EXPORT_SYMBOL_GPL(mmio_stale_data_clear);
-void __init check_bugs(void)
+void __init cpu_select_mitigations(void)
{
- identify_boot_cpu();
-
- /*
- * identify_boot_cpu() initialized SMT support information, let the
- * core code know.
- */
- cpu_smt_check_topology();
-
- if (!IS_ENABLED(CONFIG_SMP)) {
- pr_info("CPU: ");
- print_cpu_info(&boot_cpu_data);
- }
-
/*
* Read the SPEC_CTRL MSR to account for reserved bits which may
* have unknown values. AMD64_LS_CFG MSR is cached in the early AMD
@@ -175,39 +164,8 @@ void __init check_bugs(void)
md_clear_select_mitigation();
srbds_select_mitigation();
l1d_flush_select_mitigation();
-
- arch_smt_update();
-
-#ifdef CONFIG_X86_32
- /*
- * Check whether we are able to run this kernel safely on SMP.
- *
- * - i386 is no longer supported.
- * - In order to run on anything without a TSC, we need to be
- * compiled for a i486.
- */
- if (boot_cpu_data.x86 < 4)
- panic("Kernel requires i486+ for 'invlpg' and other features");
-
- init_utsname()->machine[1] =
- '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
- alternative_instructions();
-
- fpu__init_check_bugs();
-#else /* CONFIG_X86_64 */
- alternative_instructions();
-
- /*
- * Make sure the first 2MB area is not mapped by huge pages
- * There are typically fixed size MTRRs in there and overlapping
- * MTRRs into large pages causes slow downs.
- *
- * Right now we don't do that with gbpages because there seems
- * very little benefit for that case.
- */
- if (!direct_gbpages)
- set_memory_4k((unsigned long)__va(0), 1);
-#endif
+ gds_select_mitigation();
+ srso_select_mitigation();
}
/*
@@ -693,6 +651,149 @@ static int __init l1d_flush_parse_cmdline(char *str)
}
early_param("l1d_flush", l1d_flush_parse_cmdline);
+#undef pr_fmt
+#define pr_fmt(fmt) "GDS: " fmt
+
+enum gds_mitigations {
+ GDS_MITIGATION_OFF,
+ GDS_MITIGATION_UCODE_NEEDED,
+ GDS_MITIGATION_FORCE,
+ GDS_MITIGATION_FULL,
+ GDS_MITIGATION_FULL_LOCKED,
+ GDS_MITIGATION_HYPERVISOR,
+};
+
+#if IS_ENABLED(CONFIG_GDS_FORCE_MITIGATION)
+static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FORCE;
+#else
+static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FULL;
+#endif
+
+static const char * const gds_strings[] = {
+ [GDS_MITIGATION_OFF] = "Vulnerable",
+ [GDS_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode",
+ [GDS_MITIGATION_FORCE] = "Mitigation: AVX disabled, no microcode",
+ [GDS_MITIGATION_FULL] = "Mitigation: Microcode",
+ [GDS_MITIGATION_FULL_LOCKED] = "Mitigation: Microcode (locked)",
+ [GDS_MITIGATION_HYPERVISOR] = "Unknown: Dependent on hypervisor status",
+};
+
+bool gds_ucode_mitigated(void)
+{
+ return (gds_mitigation == GDS_MITIGATION_FULL ||
+ gds_mitigation == GDS_MITIGATION_FULL_LOCKED);
+}
+EXPORT_SYMBOL_GPL(gds_ucode_mitigated);
+
+void update_gds_msr(void)
+{
+ u64 mcu_ctrl_after;
+ u64 mcu_ctrl;
+
+ switch (gds_mitigation) {
+ case GDS_MITIGATION_OFF:
+ rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+ mcu_ctrl |= GDS_MITG_DIS;
+ break;
+ case GDS_MITIGATION_FULL_LOCKED:
+ /*
+ * The LOCKED state comes from the boot CPU. APs might not have
+ * the same state. Make sure the mitigation is enabled on all
+ * CPUs.
+ */
+ case GDS_MITIGATION_FULL:
+ rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+ mcu_ctrl &= ~GDS_MITG_DIS;
+ break;
+ case GDS_MITIGATION_FORCE:
+ case GDS_MITIGATION_UCODE_NEEDED:
+ case GDS_MITIGATION_HYPERVISOR:
+ return;
+ };
+
+ wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+
+ /*
+ * Check to make sure that the WRMSR value was not ignored. Writes to
+ * GDS_MITG_DIS will be ignored if this processor is locked but the boot
+ * processor was not.
+ */
+ rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl_after);
+ WARN_ON_ONCE(mcu_ctrl != mcu_ctrl_after);
+}
+
+static void __init gds_select_mitigation(void)
+{
+ u64 mcu_ctrl;
+
+ if (!boot_cpu_has_bug(X86_BUG_GDS))
+ return;
+
+ if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
+ gds_mitigation = GDS_MITIGATION_HYPERVISOR;
+ goto out;
+ }
+
+ if (cpu_mitigations_off())
+ gds_mitigation = GDS_MITIGATION_OFF;
+ /* Will verify below that mitigation _can_ be disabled */
+
+ /* No microcode */
+ if (!(x86_read_arch_cap_msr() & ARCH_CAP_GDS_CTRL)) {
+ if (gds_mitigation == GDS_MITIGATION_FORCE) {
+ /*
+ * This only needs to be done on the boot CPU so do it
+ * here rather than in update_gds_msr()
+ */
+ setup_clear_cpu_cap(X86_FEATURE_AVX);
+ pr_warn("Microcode update needed! Disabling AVX as mitigation.\n");
+ } else {
+ gds_mitigation = GDS_MITIGATION_UCODE_NEEDED;
+ }
+ goto out;
+ }
+
+ /* Microcode has mitigation, use it */
+ if (gds_mitigation == GDS_MITIGATION_FORCE)
+ gds_mitigation = GDS_MITIGATION_FULL;
+
+ rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+ if (mcu_ctrl & GDS_MITG_LOCKED) {
+ if (gds_mitigation == GDS_MITIGATION_OFF)
+ pr_warn("Mitigation locked. Disable failed.\n");
+
+ /*
+ * The mitigation is selected from the boot CPU. All other CPUs
+ * _should_ have the same state. If the boot CPU isn't locked
+ * but others are then update_gds_msr() will WARN() of the state
+ * mismatch. If the boot CPU is locked update_gds_msr() will
+ * ensure the other CPUs have the mitigation enabled.
+ */
+ gds_mitigation = GDS_MITIGATION_FULL_LOCKED;
+ }
+
+ update_gds_msr();
+out:
+ pr_info("%s\n", gds_strings[gds_mitigation]);
+}
+
+static int __init gds_parse_cmdline(char *str)
+{
+ if (!str)
+ return -EINVAL;
+
+ if (!boot_cpu_has_bug(X86_BUG_GDS))
+ return 0;
+
+ if (!strcmp(str, "off"))
+ gds_mitigation = GDS_MITIGATION_OFF;
+ else if (!strcmp(str, "force"))
+ gds_mitigation = GDS_MITIGATION_FORCE;
+
+ return 0;
+}
+early_param("gather_data_sampling", gds_parse_cmdline);
+
#undef pr_fmt
#define pr_fmt(fmt) "Spectre V1 : " fmt
@@ -2207,6 +2308,165 @@ static int __init l1tf_cmdline(char *str)
}
early_param("l1tf", l1tf_cmdline);
+#undef pr_fmt
+#define pr_fmt(fmt) "Speculative Return Stack Overflow: " fmt
+
+enum srso_mitigation {
+ SRSO_MITIGATION_NONE,
+ SRSO_MITIGATION_MICROCODE,
+ SRSO_MITIGATION_SAFE_RET,
+ SRSO_MITIGATION_IBPB,
+ SRSO_MITIGATION_IBPB_ON_VMEXIT,
+};
+
+enum srso_mitigation_cmd {
+ SRSO_CMD_OFF,
+ SRSO_CMD_MICROCODE,
+ SRSO_CMD_SAFE_RET,
+ SRSO_CMD_IBPB,
+ SRSO_CMD_IBPB_ON_VMEXIT,
+};
+
+static const char * const srso_strings[] = {
+ [SRSO_MITIGATION_NONE] = "Vulnerable",
+ [SRSO_MITIGATION_MICROCODE] = "Mitigation: microcode",
+ [SRSO_MITIGATION_SAFE_RET] = "Mitigation: safe RET",
+ [SRSO_MITIGATION_IBPB] = "Mitigation: IBPB",
+ [SRSO_MITIGATION_IBPB_ON_VMEXIT] = "Mitigation: IBPB on VMEXIT only"
+};
+
+static enum srso_mitigation srso_mitigation __ro_after_init = SRSO_MITIGATION_NONE;
+static enum srso_mitigation_cmd srso_cmd __ro_after_init = SRSO_CMD_SAFE_RET;
+
+static int __init srso_parse_cmdline(char *str)
+{
+ if (!str)
+ return -EINVAL;
+
+ if (!strcmp(str, "off"))
+ srso_cmd = SRSO_CMD_OFF;
+ else if (!strcmp(str, "microcode"))
+ srso_cmd = SRSO_CMD_MICROCODE;
+ else if (!strcmp(str, "safe-ret"))
+ srso_cmd = SRSO_CMD_SAFE_RET;
+ else if (!strcmp(str, "ibpb"))
+ srso_cmd = SRSO_CMD_IBPB;
+ else if (!strcmp(str, "ibpb-vmexit"))
+ srso_cmd = SRSO_CMD_IBPB_ON_VMEXIT;
+ else
+ pr_err("Ignoring unknown SRSO option (%s).", str);
+
+ return 0;
+}
+early_param("spec_rstack_overflow", srso_parse_cmdline);
+
+#define SRSO_NOTICE "WARNING: See https://kernel.org/doc/html/latest/admin-guide/hw-vuln/srso.html for mitigation options."
+
+static void __init srso_select_mitigation(void)
+{
+ bool has_microcode;
+
+ if (!boot_cpu_has_bug(X86_BUG_SRSO) || cpu_mitigations_off())
+ goto pred_cmd;
+
+ /*
+ * The first check is for the kernel running as a guest in order
+ * for guests to verify whether IBPB is a viable mitigation.
+ */
+ has_microcode = boot_cpu_has(X86_FEATURE_IBPB_BRTYPE) || cpu_has_ibpb_brtype_microcode();
+ if (!has_microcode) {
+ pr_warn("IBPB-extending microcode not applied!\n");
+ pr_warn(SRSO_NOTICE);
+ } else {
+ /*
+ * Enable the synthetic (even if in a real CPUID leaf)
+ * flags for guests.
+ */
+ setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE);
+
+ /*
+ * Zen1/2 with SMT off aren't vulnerable after the right
+ * IBPB microcode has been applied.
+ */
+ if ((boot_cpu_data.x86 < 0x19) &&
+ (!cpu_smt_possible() || (cpu_smt_control == CPU_SMT_DISABLED)))
+ setup_force_cpu_cap(X86_FEATURE_SRSO_NO);
+ }
+
+ if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB) {
+ if (has_microcode) {
+ pr_err("Retbleed IBPB mitigation enabled, using same for SRSO\n");
+ srso_mitigation = SRSO_MITIGATION_IBPB;
+ goto pred_cmd;
+ }
+ }
+
+ switch (srso_cmd) {
+ case SRSO_CMD_OFF:
+ return;
+
+ case SRSO_CMD_MICROCODE:
+ if (has_microcode) {
+ srso_mitigation = SRSO_MITIGATION_MICROCODE;
+ pr_warn(SRSO_NOTICE);
+ }
+ break;
+
+ case SRSO_CMD_SAFE_RET:
+ if (IS_ENABLED(CONFIG_CPU_SRSO)) {
+ /*
+ * Enable the return thunk for generated code
+ * like ftrace, static_call, etc.
+ */
+ setup_force_cpu_cap(X86_FEATURE_RETHUNK);
+
+ if (boot_cpu_data.x86 == 0x19)
+ setup_force_cpu_cap(X86_FEATURE_SRSO_ALIAS);
+ else
+ setup_force_cpu_cap(X86_FEATURE_SRSO);
+ srso_mitigation = SRSO_MITIGATION_SAFE_RET;
+ } else {
+ pr_err("WARNING: kernel not compiled with CPU_SRSO.\n");
+ goto pred_cmd;
+ }
+ break;
+
+ case SRSO_CMD_IBPB:
+ if (IS_ENABLED(CONFIG_CPU_IBPB_ENTRY)) {
+ if (has_microcode) {
+ setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB);
+ srso_mitigation = SRSO_MITIGATION_IBPB;
+ }
+ } else {
+ pr_err("WARNING: kernel not compiled with CPU_IBPB_ENTRY.\n");
+ goto pred_cmd;
+ }
+ break;
+
+ case SRSO_CMD_IBPB_ON_VMEXIT:
+ if (IS_ENABLED(CONFIG_CPU_SRSO)) {
+ if (!boot_cpu_has(X86_FEATURE_ENTRY_IBPB) && has_microcode) {
+ setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT);
+ srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT;
+ }
+ } else {
+ pr_err("WARNING: kernel not compiled with CPU_SRSO.\n");
+ goto pred_cmd;
+ }
+ break;
+
+ default:
+ break;
+ }
+
+ pr_info("%s%s\n", srso_strings[srso_mitigation], (has_microcode ? "" : ", no microcode"));
+
+pred_cmd:
+ if ((boot_cpu_has(X86_FEATURE_SRSO_NO) || srso_cmd == SRSO_CMD_OFF) &&
+ boot_cpu_has(X86_FEATURE_SBPB))
+ x86_pred_cmd = PRED_CMD_SBPB;
+}
+
#undef pr_fmt
#define pr_fmt(fmt) fmt
@@ -2405,6 +2665,18 @@ static ssize_t retbleed_show_state(char *buf)
return sprintf(buf, "%s\n", retbleed_strings[retbleed_mitigation]);
}
+static ssize_t gds_show_state(char *buf)
+{
+ return sysfs_emit(buf, "%s\n", gds_strings[gds_mitigation]);
+}
+
+static ssize_t srso_show_state(char *buf)
+{
+ return sysfs_emit(buf, "%s%s\n",
+ srso_strings[srso_mitigation],
+ (cpu_has_ibpb_brtype_microcode() ? "" : ", no microcode"));
+}
+
static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
char *buf, unsigned int bug)
{
@@ -2454,6 +2726,12 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
case X86_BUG_RETBLEED:
return retbleed_show_state(buf);
+ case X86_BUG_GDS:
+ return gds_show_state(buf);
+
+ case X86_BUG_SRSO:
+ return srso_show_state(buf);
+
default:
break;
}
@@ -2518,4 +2796,14 @@ ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, cha
{
return cpu_show_common(dev, attr, buf, X86_BUG_RETBLEED);
}
+
+ssize_t cpu_show_gds(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ return cpu_show_common(dev, attr, buf, X86_BUG_GDS);
+}
+
+ssize_t cpu_show_spec_rstack_overflow(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ return cpu_show_common(dev, attr, buf, X86_BUG_SRSO);
+}
#endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index d298d70f74ce6..d38ae25e7c01f 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -18,11 +18,15 @@
#include <linux/init.h>
#include <linux/kprobes.h>
#include <linux/kgdb.h>
+#include <linux/mem_encrypt.h>
#include <linux/smp.h>
+#include <linux/cpu.h>
#include <linux/io.h>
#include <linux/syscore_ops.h>
#include <linux/pgtable.h>
+#include <linux/utsname.h>
+#include <asm/alternative.h>
#include <asm/cmdline.h>
#include <asm/stackprotector.h>
#include <asm/perf_event.h>
@@ -58,7 +62,7 @@
#include <asm/intel-family.h>
#include <asm/cpu_device_id.h>
#include <asm/uv/uv.h>
-#include <asm/sigframe.h>
+#include <asm/set_memory.h>
#include <asm/traps.h>
#include <asm/sev.h>
@@ -1072,6 +1076,9 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
if (c->extended_cpuid_level >= 0x8000001f)
c->x86_capability[CPUID_8000_001F_EAX] = cpuid_eax(0x8000001f);
+ if (c->extended_cpuid_level >= 0x80000021)
+ c->x86_capability[CPUID_8000_0021_EAX] = cpuid_eax(0x80000021);
+
init_scattered_cpuid_features(c);
init_speculation_control(c);
@@ -1237,6 +1244,10 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
#define RETBLEED BIT(3)
/* CPU is affected by SMT (cross-thread) return predictions */
#define SMT_RSB BIT(4)
+/* CPU is affected by SRSO */
+#define SRSO BIT(5)
+/* CPU is affected by GDS */
+#define GDS BIT(6)
static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS),
@@ -1249,27 +1260,30 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
VULNBL_INTEL_STEPPINGS(BROADWELL_X, X86_STEPPING_ANY, MMIO),
VULNBL_INTEL_STEPPINGS(BROADWELL, X86_STEPPING_ANY, SRBDS),
VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED),
- VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED),
+ VULNBL_INTEL_STEPPINGS(SKYLAKE_X, X86_STEPPING_ANY, MMIO | RETBLEED | GDS),
VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED),
- VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED),
- VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED),
+ VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED | GDS),
+ VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPING_ANY, SRBDS | MMIO | RETBLEED | GDS),
VULNBL_INTEL_STEPPINGS(CANNONLAKE_L, X86_STEPPING_ANY, RETBLEED),
- VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED),
- VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPING_ANY, MMIO),
- VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPING_ANY, MMIO),
- VULNBL_INTEL_STEPPINGS(COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED),
+ VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS),
+ VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPING_ANY, MMIO | GDS),
+ VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPING_ANY, MMIO | GDS),
+ VULNBL_INTEL_STEPPINGS(COMETLAKE, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS),
VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO | RETBLEED),
- VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED),
+ VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED | GDS),
+ VULNBL_INTEL_STEPPINGS(TIGERLAKE_L, X86_STEPPING_ANY, GDS),
+ VULNBL_INTEL_STEPPINGS(TIGERLAKE, X86_STEPPING_ANY, GDS),
VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPING_ANY, MMIO | MMIO_SBDS | RETBLEED),
- VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED),
+ VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPING_ANY, MMIO | RETBLEED | GDS),
VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPING_ANY, MMIO | MMIO_SBDS),
VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO),
VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPING_ANY, MMIO | MMIO_SBDS),
VULNBL_AMD(0x15, RETBLEED),
VULNBL_AMD(0x16, RETBLEED),
- VULNBL_AMD(0x17, RETBLEED | SMT_RSB),
+ VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO),
VULNBL_HYGON(0x18, RETBLEED | SMT_RSB),
+ VULNBL_AMD(0x19, SRSO),
{}
};
@@ -1390,6 +1404,21 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
if (cpu_matches(cpu_vuln_blacklist, SMT_RSB))
setup_force_cpu_bug(X86_BUG_SMT_RSB);
+ /*
+ * Check if CPU is vulnerable to GDS. If running in a virtual machine on
+ * an affected processor, the VMM may have disabled the use of GATHER by
+ * disabling AVX2. The only way to do this in HW is to clear XCR0[2],
+ * which means that AVX will be disabled.
+ */
+ if (cpu_matches(cpu_vuln_blacklist, GDS) && !(ia32_cap & ARCH_CAP_GDS_NO) &&
+ boot_cpu_has(X86_FEATURE_AVX))
+ setup_force_cpu_bug(X86_BUG_GDS);
+
+ if (!cpu_has(c, X86_FEATURE_SRSO_NO)) {
+ if (cpu_matches(cpu_vuln_blacklist, SRSO))
+ setup_force_cpu_bug(X86_BUG_SRSO);
+ }
+
if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
return;
@@ -1571,10 +1600,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
sld_setup(c);
- fpu__init_system(c);
-
- init_sigframe_size();
-
#ifdef CONFIG_X86_32
/*
* Regardless of whether PCID is enumerated, the SDM says
@@ -1957,6 +1982,8 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c)
validate_apic_and_package_id(c);
x86_spec_ctrl_setup_ap();
update_srbds_msr();
+ if (boot_cpu_has_bug(X86_BUG_GDS))
+ update_gds_msr();
tsx_ap_init();
}
@@ -2290,8 +2317,6 @@ void cpu_init(void)
doublefault_init_cpu_tss();
- fpu__init_cpu();
-
if (is_uv_system())
uv_cpu_init();
@@ -2307,6 +2332,7 @@ void cpu_init_secondary(void)
*/
cpu_init_exception_handling();
cpu_init();
+ fpu__init_cpu();
}
#endif
@@ -2369,3 +2395,69 @@ void arch_smt_update(void)
/* Check whether IPI broadcasting can be enabled */
apic_smt_update();
}
+
+void __init arch_cpu_finalize_init(void)
+{
+ identify_boot_cpu();
+
+ /*
+ * identify_boot_cpu() initialized SMT support information, let the
+ * core code know.
+ */
+ cpu_smt_check_topology();
+
+ if (!IS_ENABLED(CONFIG_SMP)) {
+ pr_info("CPU: ");
+ print_cpu_info(&boot_cpu_data);
+ }
+
+ cpu_select_mitigations();
+
+ arch_smt_update();
+
+ if (IS_ENABLED(CONFIG_X86_32)) {
+ /*
+ * Check whether this is a real i386 which is not longer
+ * supported and fixup the utsname.
+ */
+ if (boot_cpu_data.x86 < 4)
+ panic("Kernel requires i486+ for 'invlpg' and other features");
+
+ init_utsname()->machine[1] =
+ '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
+ }
+
+ /*
+ * Must be before alternatives because it might set or clear
+ * feature bits.
+ */
+ fpu__init_system();
+ fpu__init_cpu();
+
+ alternative_instructions();
+
+ if (IS_ENABLED(CONFIG_X86_64)) {
+ /*
+ * Make sure the first 2MB area is not mapped by huge pages
+ * There are typically fixed size MTRRs in there and overlapping
+ * MTRRs into large pages causes slow downs.
+ *
+ * Right now we don't do that with gbpages because there seems
+ * very little benefit for that case.
+ */
+ if (!direct_gbpages)
+ set_memory_4k((unsigned long)__va(0), 1);
+ } else {
+ fpu__init_check_bugs();
+ }
+
+ /*
+ * This needs to be called before any devices perform DMA
+ * operations that might use the SWIOTLB bounce buffers. It will
+ * mark the bounce buffers as decrypted so that their usage will
+ * not cause "plain-text" data to be decrypted when accessed. It
+ * must be called after late_time_init() so that Hyper-V x86/x64
+ * hypercalls work when the SWIOTLB bounce buffers are decrypted.
+ */
+ mem_encrypt_init();
+}
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 7c9b5893c30ab..d9aeb335002dd 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -79,9 +79,11 @@ extern void detect_ht(struct cpuinfo_x86 *c);
extern void check_null_seg_clears_base(struct cpuinfo_x86 *c);
unsigned int aperfmperf_get_khz(int cpu);
+void cpu_select_mitigations(void);
extern void x86_spec_ctrl_setup_ap(void);
extern void update_srbds_msr(void);
+extern void update_gds_msr(void);
extern u64 x86_read_arch_cap_msr(void);
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 851eb13edc014..998a08f17e331 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -53,7 +53,7 @@ void fpu__init_cpu(void)
fpu__init_cpu_xstate();
}
-static bool fpu__probe_without_cpuid(void)
+static bool __init fpu__probe_without_cpuid(void)
{
unsigned long cr0;
u16 fsw, fcw;
@@ -71,7 +71,7 @@ static bool fpu__probe_without_cpuid(void)
return fsw == 0 && (fcw & 0x103f) == 0x003f;
}
-static void fpu__init_system_early_generic(struct cpuinfo_x86 *c)
+static void __init fpu__init_system_early_generic(void)
{
if (!boot_cpu_has(X86_FEATURE_CPUID) &&
!test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) {
@@ -211,10 +211,10 @@ static void __init fpu__init_system_xstate_size_legacy(void)
* Called on the boot CPU once per system bootup, to set up the initial
* FPU state that is later cloned into all processes:
*/
-void __init fpu__init_system(struct cpuinfo_x86 *c)
+void __init fpu__init_system(void)
{
fpstate_reset(&current->thread.fpu);
- fpu__init_system_early_generic(c);
+ fpu__init_system_early_generic();
/*
* The FPU has to be operational for some of the
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 82c562e2cc982..55ed638cb3fdc 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -724,7 +724,7 @@ badframe:
static unsigned long __ro_after_init max_frame_size;
static unsigned int __ro_after_init fpu_default_state_size;
-void __init init_sigframe_size(void)
+static int __init init_sigframe_size(void)
{
fpu_default_state_size = fpu__get_fpstate_size();
@@ -736,7 +736,9 @@ void __init init_sigframe_size(void)
max_frame_size = round_up(max_frame_size, FRAME_ALIGNMENT);
pr_info("max sigframe size: %lu\n", max_frame_size);
+ return 0;
}
+early_initcall(init_sigframe_size);
unsigned long get_sigframe_size(void)
{
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 15f29053cec46..fd03f5a1f0ef0 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -133,7 +133,20 @@ SECTIONS
LOCK_TEXT
KPROBES_TEXT
ALIGN_ENTRY_TEXT_BEGIN
+#ifdef CONFIG_CPU_SRSO
+ *(.text.__x86.rethunk_untrain)
+#endif
+
ENTRY_TEXT
+
+#ifdef CONFIG_CPU_SRSO
+ /*
+ * See the comment above srso_untrain_ret_alias()'s
+ * definition.
+ */
+ . = srso_untrain_ret_alias | (1 << 2) | (1 << 8) | (1 << 14) | (1 << 20);
+ *(.text.__x86.rethunk_safe)
+#endif
ALIGN_ENTRY_TEXT_END
SOFTIRQENTRY_TEXT
STATIC_CALL_TEXT
@@ -141,13 +154,15 @@ SECTIONS
#ifdef CONFIG_RETPOLINE
__indirect_thunk_start = .;
- *(.text.__x86.*)
+ *(.text.__x86.indirect_thunk)
+ *(.text.__x86.return_thunk)
__indirect_thunk_end = .;
#endif
} :text =0xcccc
/* End of text section, which should occupy whole number of pages */
_etext = .;
+
. = ALIGN(PAGE_SIZE);
X86_ALIGN_RODATA_BEGIN
@@ -492,6 +507,21 @@ INIT_PER_CPU(irq_stack_backing_store);
"fixed_percpu_data is not at start of per-cpu area");
#endif
+ #ifdef CONFIG_RETHUNK
+. = ASSERT((__ret & 0x3f) == 0, "__ret not cacheline-aligned");
+. = ASSERT((srso_safe_ret & 0x3f) == 0, "srso_safe_ret not cacheline-aligned");
+#endif
+
+#ifdef CONFIG_CPU_SRSO
+/*
+ * GNU ld cannot do XOR so do: (A | B) - (A & B) in order to compute the XOR
+ * of the two function addresses:
+ */
+. = ASSERT(((srso_untrain_ret_alias | srso_safe_ret_alias) -
+ (srso_untrain_ret_alias & srso_safe_ret_alias)) == ((1 << 2) | (1 << 8) | (1 << 14) | (1 << 20)),
+ "SRSO function pair won't alias");
+#endif
+
#endif /* CONFIG_X86_64 */
#ifdef CONFIG_KEXEC_CORE
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 6047dbe048803..7b4224f5ee2de 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -736,6 +736,9 @@ void kvm_set_cpu_caps(void)
F(PMM) | F(PMM_EN)
);
+ if (cpu_feature_enabled(X86_FEATURE_SRSO_NO))
+ kvm_cpu_cap_set(X86_FEATURE_SRSO_NO);
+
/*
* Hide RDTSCP and RDPID if either feature is reported as supported but
* probing MSR_TSC_AUX failed. This is purely a sanity check and
diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h
index a19d473d01847..7eeade35a425b 100644
--- a/arch/x86/kvm/reverse_cpuid.h
+++ b/arch/x86/kvm/reverse_cpuid.h
@@ -48,6 +48,7 @@ static const struct cpuid_reg reverse_cpuid[] = {
[CPUID_7_1_EAX] = { 7, 1, CPUID_EAX},
[CPUID_12_EAX] = {0x00000012, 0, CPUID_EAX},
[CPUID_8000_001F_EAX] = {0x8000001f, 0, CPUID_EAX},
+ [CPUID_8000_0021_EAX] = {0x80000021, 0, CPUID_EAX},
};
/*
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 0a212fe2cd398..fdb6007f2eb86 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1485,7 +1485,9 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
if (sd->current_vmcb != svm->vmcb) {
sd->current_vmcb = svm->vmcb;
- indirect_branch_prediction_barrier();
+
+ if (!cpu_feature_enabled(X86_FEATURE_IBPB_ON_VMEXIT))
+ indirect_branch_prediction_barrier();
}
if (kvm_vcpu_apicv_active(vcpu))
avic_vcpu_load(vcpu, cpu);
diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S
index 34367dc203f21..5be9a63f09fff 100644
--- a/arch/x86/kvm/svm/vmenter.S
+++ b/arch/x86/kvm/svm/vmenter.S
@@ -223,6 +223,9 @@ SYM_FUNC_START(__svm_vcpu_run)
*/
UNTRAIN_RET
+ /* SRSO */
+ ALTERNATIVE "", "call entry_ibpb", X86_FEATURE_IBPB_ON_VMEXIT
+
/*
* Clear all general purpose registers except RSP and RAX to prevent
* speculative use of the guest's values, even those that are reloaded
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 32f589b96d997..f4b12c3c30a01 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -311,6 +311,8 @@ u64 __read_mostly host_xcr0;
static struct kmem_cache *x86_emulator_cache;
+extern bool gds_ucode_mitigated(void);
+
/*
* When called, it means the previous get/set msr reached an invalid msr.
* Return true if we want to ignore/silent this failed msr access.
@@ -1613,7 +1615,7 @@ static unsigned int num_msr_based_features;
ARCH_CAP_SKIP_VMENTRY_L1DFLUSH | ARCH_CAP_SSB_NO | ARCH_CAP_MDS_NO | \
ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \
ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \
- ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO)
+ ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO)
static u64 kvm_get_arch_capabilities(void)
{
@@ -1670,6 +1672,9 @@ static u64 kvm_get_arch_capabilities(void)
*/
}
+ if (!boot_cpu_has_bug(X86_BUG_GDS) || gds_ucode_mitigated())
+ data |= ARCH_CAP_GDS_NO;
+
return data;
}
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 841955dc2573d..30e76fab678a5 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -9,6 +9,7 @@
#include <asm/nospec-branch.h>
#include <asm/unwind_hints.h>
#include <asm/frame.h>
+#include <asm/nops.h>
.section .text.__x86.indirect_thunk
@@ -74,6 +75,46 @@ SYM_CODE_END(__x86_indirect_thunk_array)
*/
#ifdef CONFIG_RETHUNK
+/*
+ * srso_untrain_ret_alias() and srso_safe_ret_alias() are placed at
+ * special addresses:
+ *
+ * - srso_untrain_ret_alias() is 2M aligned
+ * - srso_safe_ret_alias() is also in the same 2M page but bits 2, 8, 14
+ * and 20 in its virtual address are set (while those bits in the
+ * srso_untrain_ret_alias() function are cleared).
+ *
+ * This guarantees that those two addresses will alias in the branch
+ * target buffer of Zen3/4 generations, leading to any potential
+ * poisoned entries at that BTB slot to get evicted.
+ *
+ * As a result, srso_safe_ret_alias() becomes a safe return.
+ */
+#ifdef CONFIG_CPU_SRSO
+ .section .text.__x86.rethunk_untrain
+
+SYM_START(srso_untrain_ret_alias, SYM_L_GLOBAL, SYM_A_NONE)
+ ANNOTATE_NOENDBR
+ ASM_NOP2
+ lfence
+ jmp __x86_return_thunk
+SYM_FUNC_END(srso_untrain_ret_alias)
+__EXPORT_THUNK(srso_untrain_ret_alias)
+
+ .section .text.__x86.rethunk_safe
+#endif
+
+/* Needs a definition for the __x86_return_thunk alternative below. */
+SYM_START(srso_safe_ret_alias, SYM_L_GLOBAL, SYM_A_NONE)
+#ifdef CONFIG_CPU_SRSO
+ add $8, %_ASM_SP
+ UNWIND_HINT_FUNC
+#endif
+ ANNOTATE_UNRET_SAFE
+ ret
+ int3
+SYM_FUNC_END(srso_safe_ret_alias)
+
.section .text.__x86.return_thunk
/*
@@ -86,7 +127,7 @@ SYM_CODE_END(__x86_indirect_thunk_array)
* from re-poisioning the BTB prediction.
*/
.align 64
- .skip 63, 0xcc
+ .skip 64 - (__ret - zen_untrain_ret), 0xcc
SYM_START(zen_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
ANNOTATE_NOENDBR
/*
@@ -118,10 +159,10 @@ SYM_START(zen_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
* evicted, __x86_return_thunk will suffer Straight Line Speculation
* which will be contained safely by the INT3.
*/
-SYM_INNER_LABEL(__x86_return_thunk, SYM_L_GLOBAL)
+SYM_INNER_LABEL(__ret, SYM_L_GLOBAL)
ret
int3
-SYM_CODE_END(__x86_return_thunk)
+SYM_CODE_END(__ret)
/*
* Ensure the TEST decoding / BTB invalidation is complete.
@@ -132,11 +173,45 @@ SYM_CODE_END(__x86_return_thunk)
* Jump back and execute the RET in the middle of the TEST instruction.
* INT3 is for SLS protection.
*/
- jmp __x86_return_thunk
+ jmp __ret
int3
SYM_FUNC_END(zen_untrain_ret)
__EXPORT_THUNK(zen_untrain_ret)
+/*
+ * SRSO untraining sequence for Zen1/2, similar to zen_untrain_ret()
+ * above. On kernel entry, srso_untrain_ret() is executed which is a
+ *
+ * movabs $0xccccccc308c48348,%rax
+ *
+ * and when the return thunk executes the inner label srso_safe_ret()
+ * later, it is a stack manipulation and a RET which is mispredicted and
+ * thus a "safe" one to use.
+ */
+ .align 64
+ .skip 64 - (srso_safe_ret - srso_untrain_ret), 0xcc
+SYM_START(srso_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
+ ANNOTATE_NOENDBR
+ .byte 0x48, 0xb8
+
+SYM_INNER_LABEL(srso_safe_ret, SYM_L_GLOBAL)
+ add $8, %_ASM_SP
+ ret
+ int3
+ int3
+ int3
+ lfence
+ call srso_safe_ret
+ int3
+SYM_CODE_END(srso_safe_ret)
+SYM_FUNC_END(srso_untrain_ret)
+__EXPORT_THUNK(srso_untrain_ret)
+
+SYM_FUNC_START(__x86_return_thunk)
+ ALTERNATIVE_2 "jmp __ret", "call srso_safe_ret", X86_FEATURE_SRSO, \
+ "call srso_safe_ret_alias", X86_FEATURE_SRSO_ALIAS
+ int3
+SYM_CODE_END(__x86_return_thunk)
EXPORT_SYMBOL(__x86_return_thunk)
#endif /* CONFIG_RETHUNK */
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 0d5ccea2538fc..913287b9340c9 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -27,6 +27,7 @@
#include <asm/pti.h>
#include <asm/text-patching.h>
#include <asm/memtype.h>
+#include <asm/paravirt.h>
/*
* We need to define the tracepoints somewhere, and tlb.c
@@ -826,9 +827,12 @@ void __init poking_init(void)
spinlock_t *ptl;
pte_t *ptep;
- poking_mm = copy_init_mm();
+ poking_mm = mm_alloc();
BUG_ON(!poking_mm);
+ /* Xen PV guests need the PGD to be pinned. */
+ paravirt_arch_dup_mmap(NULL, poking_mm);
+
/*
* Randomize the poking address, but make sure that the following page
* will be mapped at the same PMD. We need 2 pages, so find space for 3,
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 6175f2c5c8224..e97bab7b00100 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -63,6 +63,7 @@ static void cpu_bringup(void)
cr4_init();
cpu_init();
+ fpu__init_cpu();
touch_softlockup_watchdog();
/* PVH runs in ring 0 and allows us to do native syscalls. Yay! */
diff --git a/arch/xtensa/include/asm/bugs.h b/arch/xtensa/include/asm/bugs.h
deleted file mode 100644
index 69b29d1982494..0000000000000
--- a/arch/xtensa/include/asm/bugs.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/*
- * include/asm-xtensa/bugs.h
- *
- * This is included by init/main.c to check for architecture-dependent bugs.
- *
- * Xtensa processors don't have any bugs. :)
- *
- * This file is subject to the terms and conditions of the GNU General
- * Public License. See the file "COPYING" in the main directory of
- * this archive for more details.
- */
-
-#ifndef _XTENSA_BUGS_H
-#define _XTENSA_BUGS_H
-
-static void check_bugs(void) { }
-
-#endif /* _XTENSA_BUGS_H */
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 7af8e33735a36..dab70a65377c8 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -577,6 +577,18 @@ ssize_t __weak cpu_show_retbleed(struct device *dev,
return sysfs_emit(buf, "Not affected\n");
}
+ssize_t __weak cpu_show_gds(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ return sysfs_emit(buf, "Not affected\n");
+}
+
+ssize_t __weak cpu_show_spec_rstack_overflow(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ return sysfs_emit(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);
@@ -588,6 +600,8 @@ static DEVICE_ATTR(itlb_multihit, 0444, cpu_show_itlb_multihit, NULL);
static DEVICE_ATTR(srbds, 0444, cpu_show_srbds, NULL);
static DEVICE_ATTR(mmio_stale_data, 0444, cpu_show_mmio_stale_data, NULL);
static DEVICE_ATTR(retbleed, 0444, cpu_show_retbleed, NULL);
+static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL);
+static DEVICE_ATTR(spec_rstack_overflow, 0444, cpu_show_spec_rstack_overflow, NULL);
static struct attribute *cpu_root_vulnerabilities_attrs[] = {
&dev_attr_meltdown.attr,
@@ -601,6 +615,8 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = {
&dev_attr_srbds.attr,
&dev_attr_mmio_stale_data.attr,
&dev_attr_retbleed.attr,
+ &dev_attr_gather_data_sampling.attr,
+ &dev_attr_spec_rstack_overflow.attr,
NULL
};
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index c35c085dbc877..c3a8d78a41a7b 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -396,7 +396,7 @@ static void xenvif_get_requests(struct xenvif_queue *queue,
struct gnttab_map_grant_ref *gop = queue->tx_map_ops + *map_ops;
struct xen_netif_tx_request *txp = first;
- nr_slots = shinfo->nr_frags + 1;
+ nr_slots = shinfo->nr_frags + frag_overflow + 1;
copy_count(skb) = 0;
XENVIF_TX_CB(skb)->split_mask = 0;
@@ -462,8 +462,8 @@ static void xenvif_get_requests(struct xenvif_queue *queue,
}
}
- for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots;
- shinfo->nr_frags++, gop++) {
+ for (shinfo->nr_frags = 0; nr_slots > 0 && shinfo->nr_frags < MAX_SKB_FRAGS;
+ shinfo->nr_frags++, gop++, nr_slots--) {
index = pending_index(queue->pending_cons++);
pending_idx = queue->pending_ring[index];
xenvif_tx_create_map_op(queue, pending_idx, txp,
@@ -476,12 +476,12 @@ static void xenvif_get_requests(struct xenvif_queue *queue,
txp++;
}
- if (frag_overflow) {
+ if (nr_slots > 0) {
shinfo = skb_shinfo(nskb);
frags = shinfo->frags;
- for (shinfo->nr_frags = 0; shinfo->nr_frags < frag_overflow;
+ for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots;
shinfo->nr_frags++, txp++, gop++) {
index = pending_index(queue->pending_cons++);
pending_idx = queue->pending_ring[index];
@@ -492,6 +492,11 @@ static void xenvif_get_requests(struct xenvif_queue *queue,
}
skb_shinfo(skb)->frag_list = nskb;
+ } else if (nskb) {
+ /* A frag_list skb was allocated but it is no longer needed
+ * because enough slots were converted to copy ops above.
+ */
+ kfree_skb(nskb);
}
(*copy_ops) = cop - queue->tx_copy_ops;
diff --git a/include/asm-generic/bugs.h b/include/asm-generic/bugs.h
deleted file mode 100644
index 69021830f078d..0000000000000
--- a/include/asm-generic/bugs.h
+++ /dev/null
@@ -1,11 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __ASM_GENERIC_BUGS_H
-#define __ASM_GENERIC_BUGS_H
-/*
- * This file is included by 'init/main.c' to check for
- * architecture-dependent bugs.
- */
-
-static inline void check_bugs(void) { }
-
-#endif /* __ASM_GENERIC_BUGS_H */
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 314802f98b9da..f98cfe9f188f5 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -70,6 +70,8 @@ extern ssize_t cpu_show_mmio_stale_data(struct device *dev,
char *buf);
extern ssize_t cpu_show_retbleed(struct device *dev,
struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_spec_rstack_overflow(struct device *dev,
+ struct device_attribute *attr, char *buf);
extern __printf(4, 5)
struct device *cpu_device_create(struct device *parent, void *drvdata,
@@ -187,6 +189,12 @@ void arch_cpu_idle_enter(void);
void arch_cpu_idle_exit(void);
void arch_cpu_idle_dead(void);
+#ifdef CONFIG_ARCH_HAS_CPU_FINALIZE_INIT
+void arch_cpu_finalize_init(void);
+#else
+static inline void arch_cpu_finalize_init(void) { }
+#endif
+
int cpu_report_state(int cpu);
int cpu_check_up_prepare(int cpu);
void cpu_set_state_online(int cpu);
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index d6c48163c6def..357e0068497c1 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -65,6 +65,7 @@ extern void sched_dead(struct task_struct *p);
void __noreturn do_task_dead(void);
void __noreturn make_task_dead(int signr);
+extern void mm_cache_init(void);
extern void proc_caches_init(void);
extern void fork_init(void);
@@ -90,7 +91,6 @@ extern void exit_itimers(struct task_struct *);
extern pid_t kernel_clone(struct kernel_clone_args *kargs);
struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node);
struct task_struct *fork_idle(int);
-struct mm_struct *copy_init_mm(void);
extern pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
extern pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags);
extern long kernel_wait4(pid_t, int __user *, int, struct rusage *);
diff --git a/init/main.c b/init/main.c
index aa21add5f7c54..fe378351e8a95 100644
--- a/init/main.c
+++ b/init/main.c
@@ -96,7 +96,6 @@
#include <linux/cache.h>
#include <linux/rodata_test.h>
#include <linux/jump_label.h>
-#include <linux/mem_encrypt.h>
#include <linux/kcsan.h>
#include <linux/init_syscalls.h>
#include <linux/stackdepot.h>
@@ -104,7 +103,6 @@
#include <net/net_namespace.h>
#include <asm/io.h>
-#include <asm/bugs.h>
#include <asm/setup.h>
#include <asm/sections.h>
#include <asm/cacheflush.h>
@@ -781,8 +779,6 @@ void __init __weak thread_stack_cache_init(void)
}
#endif
-void __init __weak mem_encrypt_init(void) { }
-
void __init __weak poking_init(void) { }
void __init __weak pgtable_cache_init(void) { }
@@ -860,6 +856,7 @@ static void __init mm_init(void)
/* Should be run after espfix64 is set up. */
pti_init();
kmsan_init_runtime();
+ mm_cache_init();
}
#ifdef CONFIG_RANDOMIZE_KSTACK_OFFSET
@@ -995,7 +992,7 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void)
sort_main_extable();
trap_init();
mm_init();
-
+ poking_init();
ftrace_init();
/* trace_printk can be enabled here */
@@ -1084,14 +1081,6 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void)
*/
locking_selftest();
- /*
- * This needs to be called before any devices perform DMA
- * operations that might use the SWIOTLB bounce buffers. It will
- * mark the bounce buffers as decrypted so that their usage will
- * not cause "plain-text" data to be decrypted when accessed.
- */
- mem_encrypt_init();
-
#ifdef CONFIG_BLK_DEV_INITRD
if (initrd_start && !initrd_below_start_ok &&
page_to_pfn(virt_to_page((void *)initrd_start)) < min_low_pfn) {
@@ -1108,6 +1097,9 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void)
late_time_init();
sched_clock_init();
calibrate_delay();
+
+ arch_cpu_finalize_init();
+
pid_idr_init();
anon_vma_init();
#ifdef CONFIG_X86
@@ -1134,9 +1126,6 @@ asmlinkage __visible void __init __no_sanitize_address start_kernel(void)
taskstats_init_early();
delayacct_init();
- poking_init();
- check_bugs();
-
acpi_subsystem_init();
arch_post_acpi_subsys_init();
kcsan_init();
diff --git a/kernel/fork.c b/kernel/fork.c
index 6bb91fbbf73cc..41950ff90aa34 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2600,11 +2600,6 @@ struct task_struct * __init fork_idle(int cpu)
return task;
}
-struct mm_struct *copy_init_mm(void)
-{
- return dup_mm(NULL, &init_mm);
-}
-
/*
* This is like kernel_clone(), but shaved down and tailored to just
* creating io_uring workers. It returns a created task, or an error pointer.
@@ -3023,10 +3018,27 @@ static void sighand_ctor(void *data)
init_waitqueue_head(&sighand->signalfd_wqh);
}
-void __init proc_caches_init(void)
+void __init mm_cache_init(void)
{
unsigned int mm_size;
+ /*
+ * The mm_cpumask is located at the end of mm_struct, and is
+ * dynamically sized based on the maximum CPU number this system
+ * can have, taking hotplug into account (nr_cpu_ids).
+ */
+ mm_size = sizeof(struct mm_struct) + cpumask_size();
+
+ mm_cachep = kmem_cache_create_usercopy("mm_struct",
+ mm_size, ARCH_MIN_MMSTRUCT_ALIGN,
+ SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
+ offsetof(struct mm_struct, saved_auxv),
+ sizeof_field(struct mm_struct, saved_auxv),
+ NULL);
+}
+
+void __init proc_caches_init(void)
+{
sighand_cachep = kmem_cache_create("sighand_cache",
sizeof(struct sighand_struct), 0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU|
@@ -3044,19 +3056,6 @@ void __init proc_caches_init(void)
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
NULL);
- /*
- * The mm_cpumask is located at the end of mm_struct, and is
- * dynamically sized based on the maximum CPU number this system
- * can have, taking hotplug into account (nr_cpu_ids).
- */
- mm_size = sizeof(struct mm_struct) + cpumask_size();
-
- mm_cachep = kmem_cache_create_usercopy("mm_struct",
- mm_size, ARCH_MIN_MMSTRUCT_ALIGN,
- SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
- offsetof(struct mm_struct, saved_auxv),
- sizeof_field(struct mm_struct, saved_auxv),
- NULL);
vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC|SLAB_ACCOUNT);
mmap_init();
nsproxy_cache_init();
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index b71f4f2ecdd57..9ecc62861194e 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -14,7 +14,7 @@
* Defines x86 CPU feature bits
*/
#define NCAPINTS 20 /* N 32-bit words worth of info */
-#define NBUGINTS 1 /* N 32-bit bug flags */
+#define NBUGINTS 2 /* N 32-bit bug flags */
/*
* Note: If the comment begins with a quoted string, that string is used
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 1c253b4b7ce00..a60c5efe34b36 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -796,5 +796,8 @@ bool arch_is_retpoline(struct symbol *sym)
bool arch_is_rethunk(struct symbol *sym)
{
- return !strcmp(sym->name, "__x86_return_thunk");
+ return !strcmp(sym->name, "__x86_return_thunk") ||
+ !strcmp(sym->name, "srso_untrain_ret") ||
+ !strcmp(sym->name, "srso_safe_ret") ||
+ !strcmp(sym->name, "__ret");
}
Reference in New Issue View Git Blame Copy Permalink