From: Thadeu Lima de Souza Cascardo cascardo@canonical.com

This reverts commit 749ec6b48a9a41f95154cd5aa61053aaeb7c7aff.

This is commit e9d7144597b10ff13ff2264c059f7d4a7fbc89ac upstream. A proper backport will be done. This will make it easier to check for parts affected by Retbleed, which require X86_MATCH_VENDOR_FAM_MODEL.

Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/cpu_device_id.h | 30 ------------------------------ arch/x86/kernel/cpu/match.c | 7 +------ include/linux/mod_devicetable.h | 6 ------ 3 files changed, 1 insertion(+), 42 deletions(-)

--- a/arch/x86/include/asm/cpu_device_id.h +++ b/arch/x86/include/asm/cpu_device_id.h @@ -9,36 +9,6 @@

#include <linux/mod_devicetable.h>

-#define X86_CENTAUR_FAM6_C7_D 0xd -#define X86_CENTAUR_FAM6_NANO 0xf - -#define X86_STEPPINGS(mins, maxs) GENMASK(maxs, mins) - -/** - * X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE - Base macro for CPU matching - * @_vendor: The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY - * The name is expanded to X86_VENDOR_@_vendor - * @_family: The family number or X86_FAMILY_ANY - * @_model: The model number, model constant or X86_MODEL_ANY - * @_steppings: Bitmask for steppings, stepping constant or X86_STEPPING_ANY - * @_feature: A X86_FEATURE bit or X86_FEATURE_ANY - * @_data: Driver specific data or NULL. The internal storage - * format is unsigned long. The supplied value, pointer - * etc. is casted to unsigned long internally. - * - * Backport version to keep the SRBDS pile consistant. No shorter variants - * required for this. - */ -#define X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(_vendor, _family, _model, \ - _steppings, _feature, _data) { \ - .vendor = X86_VENDOR_##_vendor, \ - .family = _family, \ - .model = _model, \ - .steppings = _steppings, \ - .feature = _feature, \ - .driver_data = (unsigned long) _data \ -} - /* * Match specific microcode revisions. * --- a/arch/x86/kernel/cpu/match.c +++ b/arch/x86/kernel/cpu/match.c @@ -34,18 +34,13 @@ const struct x86_cpu_id *x86_match_cpu(c const struct x86_cpu_id *m; struct cpuinfo_x86 *c = &boot_cpu_data;

- for (m = match; - m->vendor | m->family | m->model | m->steppings | m->feature; - m++) { + for (m = match; m->vendor | m->family | m->model | m->feature; m++) { if (m->vendor != X86_VENDOR_ANY && c->x86_vendor != m->vendor) continue; if (m->family != X86_FAMILY_ANY && c->x86 != m->family) continue; if (m->model != X86_MODEL_ANY && c->x86_model != m->model) continue; - if (m->steppings != X86_STEPPING_ANY && - !(BIT(c->x86_stepping) & m->steppings)) - continue; if (m->feature != X86_FEATURE_ANY && !cpu_has(c, m->feature)) continue; return m; --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -657,10 +657,6 @@ struct mips_cdmm_device_id { /* * MODULE_DEVICE_TABLE expects this struct to be called x86cpu_device_id. * Although gcc seems to ignore this error, clang fails without this define. - * - * Note: The ordering of the struct is different from upstream because the - * static initializers in kernels < 5.7 still use C89 style while upstream - * has been converted to proper C99 initializers. */ #define x86cpu_device_id x86_cpu_id struct x86_cpu_id { @@ -669,7 +665,6 @@ struct x86_cpu_id { __u16 model; __u16 feature; /* bit index */ kernel_ulong_t driver_data; - __u16 steppings; };

#define X86_FEATURE_MATCH(x) \ @@ -678,7 +673,6 @@ struct x86_cpu_id { #define X86_VENDOR_ANY 0xffff #define X86_FAMILY_ANY 0 #define X86_MODEL_ANY 0 -#define X86_STEPPING_ANY 0 #define X86_FEATURE_ANY 0 /* Same as FPU, you can't test for that */

/*

From: Thomas Gleixner tglx@linutronix.de

commit 20d437447c0089cda46c683db219d3b4e2cde40e upstream.

Finding all places which build x86_cpu_id match tables is tedious and the logic is hidden in lots of differently named macro wrappers.

Most of these initializer macros use plain C89 initializers which rely on the ordering of the struct members. So new members could only be added at the end of the struct, but that's ugly as hell and C99 initializers are really the right thing to use.

Provide a set of macros which:

- Have a proper naming scheme, starting with X86_MATCH_

- Use C99 initializers

The set of provided macros are all subsets of the base macro

X86_MATCH_VENDOR_FAM_MODEL_FEATURE()

which allows to supply all possible selection criteria:

vendor, family, model, feature

The other macros shorten this to avoid typing all arguments when they are not needed and would require one of the _ANY constants. They have been created due to the requirements of the existing usage sites.

Also add a few model constants for Centaur CPUs and QUARK.

Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Link: https://lkml.kernel.org/r/20200320131508.826011988@linutronix.de Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/cpu_device_id.h | 140 ++++++++++++++++++++++++++++++++--- arch/x86/include/asm/intel-family.h | 6 + arch/x86/kernel/cpu/match.c | 13 ++- 3 files changed, 146 insertions(+), 13 deletions(-)

--- a/arch/x86/include/asm/cpu_device_id.h +++ b/arch/x86/include/asm/cpu_device_id.h @@ -5,21 +5,143 @@ /* * Declare drivers belonging to specific x86 CPUs * Similar in spirit to pci_device_id and related PCI functions - */ -#include <linux/mod_devicetable.h> - -/* + * * The wildcard initializers are in mod_devicetable.h because * file2alias needs them. Sigh. */ +#include <linux/mod_devicetable.h> +/* Get the INTEL_FAM* model defines */ +#include <asm/intel-family.h> +/* And the X86_VENDOR_* ones */ +#include <asm/processor.h>

-#define X86_FEATURE_MATCH(x) { \ - .vendor = X86_VENDOR_ANY, \ - .family = X86_FAMILY_ANY, \ - .model = X86_MODEL_ANY, \ - .feature = x, \ +/* Centaur FAM6 models */ +#define X86_CENTAUR_FAM6_C7_A 0xa +#define X86_CENTAUR_FAM6_C7_D 0xd +#define X86_CENTAUR_FAM6_NANO 0xf + +/** + * X86_MATCH_VENDOR_FAM_MODEL_FEATURE - Base macro for CPU matching + * @_vendor: The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY + * The name is expanded to X86_VENDOR_@_vendor + * @_family: The family number or X86_FAMILY_ANY + * @_model: The model number, model constant or X86_MODEL_ANY + * @_feature: A X86_FEATURE bit or X86_FEATURE_ANY + * @_data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is casted to unsigned long internally. + * + * Use only if you need all selectors. Otherwise use one of the shorter + * macros of the X86_MATCH_* family. If there is no matching shorthand + * macro, consider to add one. If you really need to wrap one of the macros + * into another macro at the usage site for good reasons, then please + * start this local macro with X86_MATCH to allow easy grepping. + */ +#define X86_MATCH_VENDOR_FAM_MODEL_FEATURE(_vendor, _family, _model, \ + _feature, _data) { \ + .vendor = X86_VENDOR_##_vendor, \ + .family = _family, \ + .model = _model, \ + .feature = _feature, \ + .driver_data = (unsigned long) _data \ }

+/** + * X86_MATCH_VENDOR_FAM_FEATURE - Macro for matching vendor, family and CPU feature + * @vendor: The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY + * The name is expanded to X86_VENDOR_@vendor + * @family: The family number or X86_FAMILY_ANY + * @feature: A X86_FEATURE bit + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is casted to unsigned long internally. + * + * All other missing arguments of X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are + * set to wildcards. + */ +#define X86_MATCH_VENDOR_FAM_FEATURE(vendor, family, feature, data) \ + X86_MATCH_VENDOR_FAM_MODEL_FEATURE(vendor, family, \ + X86_MODEL_ANY, feature, data) + +/** + * X86_MATCH_VENDOR_FEATURE - Macro for matching vendor and CPU feature + * @vendor: The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY + * The name is expanded to X86_VENDOR_@vendor + * @feature: A X86_FEATURE bit + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is casted to unsigned long internally. + * + * All other missing arguments of X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are + * set to wildcards. + */ +#define X86_MATCH_VENDOR_FEATURE(vendor, feature, data) \ + X86_MATCH_VENDOR_FAM_FEATURE(vendor, X86_FAMILY_ANY, feature, data) + +/** + * X86_MATCH_FEATURE - Macro for matching a CPU feature + * @feature: A X86_FEATURE bit + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is casted to unsigned long internally. + * + * All other missing arguments of X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are + * set to wildcards. + */ +#define X86_MATCH_FEATURE(feature, data) \ + X86_MATCH_VENDOR_FEATURE(ANY, feature, data) + +/* Transitional to keep the existing code working */ +#define X86_FEATURE_MATCH(feature) X86_MATCH_FEATURE(feature, NULL) + +/** + * X86_MATCH_VENDOR_FAM_MODEL - Match vendor, family and model + * @vendor: The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY + * The name is expanded to X86_VENDOR_@vendor + * @family: The family number or X86_FAMILY_ANY + * @model: The model number, model constant or X86_MODEL_ANY + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is casted to unsigned long internally. + * + * All other missing arguments of X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are + * set to wildcards. + */ +#define X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, data) \ + X86_MATCH_VENDOR_FAM_MODEL_FEATURE(vendor, family, model, \ + X86_FEATURE_ANY, data) + +/** + * X86_MATCH_VENDOR_FAM - Match vendor and family + * @vendor: The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY + * The name is expanded to X86_VENDOR_@vendor + * @family: The family number or X86_FAMILY_ANY + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is casted to unsigned long internally. + * + * All other missing arguments to X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are + * set of wildcards. + */ +#define X86_MATCH_VENDOR_FAM(vendor, family, data) \ + X86_MATCH_VENDOR_FAM_MODEL(vendor, family, X86_MODEL_ANY, data) + +/** + * X86_MATCH_INTEL_FAM6_MODEL - Match vendor INTEL, family 6 and model + * @model: The model name without the INTEL_FAM6_ prefix or ANY + * The model name is expanded to INTEL_FAM6_@model internally + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is casted to unsigned long internally. + * + * The vendor is set to INTEL, the family to 6 and all other missing + * arguments of X86_MATCH_VENDOR_FAM_MODEL_FEATURE() are set to wildcards. + * + * See X86_MATCH_VENDOR_FAM_MODEL_FEATURE() for further information. + */ +#define X86_MATCH_INTEL_FAM6_MODEL(model, data) \ + X86_MATCH_VENDOR_FAM_MODEL(INTEL, 6, INTEL_FAM6_##model, data) + /* * Match specific microcode revisions. * --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -35,6 +35,9 @@ * The #define line may optionally include a comment including platform names. */

+/* Wildcard match for FAM6 so X86_MATCH_INTEL_FAM6_MODEL(ANY) works */ +#define INTEL_FAM6_ANY X86_MODEL_ANY + #define INTEL_FAM6_CORE_YONAH 0x0E

#define INTEL_FAM6_CORE2_MEROM 0x0F @@ -126,6 +129,9 @@ #define INTEL_FAM6_XEON_PHI_KNL 0x57 /* Knights Landing */ #define INTEL_FAM6_XEON_PHI_KNM 0x85 /* Knights Mill */

+/* Family 5 */ +#define INTEL_FAM5_QUARK_X1000 0x09 /* Quark X1000 SoC */ + /* Useful macros */ #define INTEL_CPU_FAM_ANY(_family, _model, _driver_data) \ { \ --- a/arch/x86/kernel/cpu/match.c +++ b/arch/x86/kernel/cpu/match.c @@ -16,12 +16,17 @@ * respective wildcard entries. * * A typical table entry would be to match a specific CPU - * { X86_VENDOR_INTEL, 6, 0x12 } - * or to match a specific CPU feature - * { X86_FEATURE_MATCH(X86_FEATURE_FOOBAR) } + * + * X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, INTEL_FAM6_BROADWELL, + * X86_FEATURE_ANY, NULL); * * Fields can be wildcarded with %X86_VENDOR_ANY, %X86_FAMILY_ANY, - * %X86_MODEL_ANY, %X86_FEATURE_ANY or 0 (except for vendor) + * %X86_MODEL_ANY, %X86_FEATURE_ANY (except for vendor) + * + * asm/cpu_device_id.h contains a set of useful macros which are shortcuts + * for various common selections. The above can be shortened to: + * + * X86_MATCH_INTEL_FAM6_MODEL(BROADWELL, NULL); * * Arrays used to match for this should also be declared using * MODULE_DEVICE_TABLE(x86cpu, ...)

From: Peter Zijlstra peterz@infradead.org

commit 742ab6df974ae8384a2dd213db1a3a06cf6d8936 upstream.

The recent mmio_stale_data fixes broke the noinstr constraints:

vmlinux.o: warning: objtool: vmx_vcpu_enter_exit+0x15b: call to wrmsrl.constprop.0() leaves .noinstr.text section vmlinux.o: warning: objtool: vmx_vcpu_enter_exit+0x1bf: call to kvm_arch_has_assigned_device() leaves .noinstr.text section

make it all happy again.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/vmx/vmx.c | 6 +++--- arch/x86/kvm/x86.c | 4 ++-- include/linux/kvm_host.h | 2 +- 3 files changed, 6 insertions(+), 6 deletions(-)

--- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -359,9 +359,9 @@ static __always_inline void vmx_disable_ if (!vmx->disable_fb_clear) return;

- rdmsrl(MSR_IA32_MCU_OPT_CTRL, msr); + msr = __rdmsr(MSR_IA32_MCU_OPT_CTRL); msr |= FB_CLEAR_DIS; - wrmsrl(MSR_IA32_MCU_OPT_CTRL, msr); + native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, msr); /* Cache the MSR value to avoid reading it later */ vmx->msr_ia32_mcu_opt_ctrl = msr; } @@ -372,7 +372,7 @@ static __always_inline void vmx_enable_f return;

vmx->msr_ia32_mcu_opt_ctrl &= ~FB_CLEAR_DIS; - wrmsrl(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl); + native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl); }

static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx) --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -10329,9 +10329,9 @@ void kvm_arch_end_assignment(struct kvm } EXPORT_SYMBOL_GPL(kvm_arch_end_assignment);

-bool kvm_arch_has_assigned_device(struct kvm *kvm) +bool noinstr kvm_arch_has_assigned_device(struct kvm *kvm) { - return atomic_read(&kvm->arch.assigned_device_count); + return arch_atomic_read(&kvm->arch.assigned_device_count); } EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device);

--- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -955,7 +955,7 @@ static inline void kvm_arch_end_assignme { }

-static inline bool kvm_arch_has_assigned_device(struct kvm *kvm) +static __always_inline bool kvm_arch_has_assigned_device(struct kvm *kvm) { return false; }

From: Alexandre Chartre alexandre.chartre@oracle.com

commit 6b80b59b3555706508008f1f127b5412c89c7fd8 upstream.

Report that AMD x86 CPUs are vulnerable to the RETBleed (Arbitrary Speculative Code Execution with Return Instructions) attack.

[peterz: add hygon] [kim: invert parity; fam15h]

Co-developed-by: Kim Phillips kim.phillips@amd.com Signed-off-by: Kim Phillips kim.phillips@amd.com Signed-off-by: Alexandre Chartre alexandre.chartre@oracle.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Borislav Petkov bp@suse.de [cascardo: adjusted BUG numbers to match upstream] Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/cpufeatures.h | 3 ++- arch/x86/kernel/cpu/bugs.c | 13 +++++++++++++ arch/x86/kernel/cpu/common.c | 19 +++++++++++++++++++ drivers/base/cpu.c | 8 ++++++++ include/linux/cpu.h | 2 ++ 5 files changed, 44 insertions(+), 1 deletion(-)

--- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -408,6 +408,7 @@ #define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */ #define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */ #define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* CPU is affected by Processor MMIO Stale Data vulnerabilities */ -#define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* CPU is too old and its MMIO Stale Data status is unknown */ +#define X86_BUG_RETBLEED X86_BUG(26) /* CPU is affected by RETBleed */ +#define X86_BUG_MMIO_UNKNOWN X86_BUG(28) /* CPU is too old and its MMIO Stale Data status is unknown */

#endif /* _ASM_X86_CPUFEATURES_H */ --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1911,6 +1911,11 @@ static ssize_t srbds_show_state(char *bu return sprintf(buf, "%s\n", srbds_strings[srbds_mitigation]); }

+static ssize_t retbleed_show_state(char *buf) +{ + return sprintf(buf, "Vulnerable\n"); +} + static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { @@ -1957,6 +1962,9 @@ static ssize_t cpu_show_common(struct de case X86_BUG_MMIO_UNKNOWN: return mmio_stale_data_show_state(buf);

+ case X86_BUG_RETBLEED: + return retbleed_show_state(buf); + default: break; } @@ -2016,4 +2024,9 @@ ssize_t cpu_show_mmio_stale_data(struct else return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA); } + +ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_RETBLEED); +} #endif --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1099,16 +1099,27 @@ static const __initconst struct x86_cpu_ {} };

+#define VULNBL(vendor, family, model, blacklist) \ + X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, blacklist) + #define VULNBL_INTEL_STEPPINGS(model, steppings, issues) \ X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(INTEL, 6, \ INTEL_FAM6_##model, steppings, \ X86_FEATURE_ANY, issues)

+#define VULNBL_AMD(family, blacklist) \ + VULNBL(AMD, family, X86_MODEL_ANY, blacklist) + +#define VULNBL_HYGON(family, blacklist) \ + VULNBL(HYGON, family, X86_MODEL_ANY, blacklist) + #define SRBDS BIT(0) /* CPU is affected by X86_BUG_MMIO_STALE_DATA */ #define MMIO BIT(1) /* CPU is affected by Shared Buffers Data Sampling (SBDS), a variant of X86_BUG_MMIO_STALE_DATA */ #define MMIO_SBDS BIT(2) +/* CPU is affected by RETbleed, speculating where you would not expect it */ +#define RETBLEED BIT(3)

static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPPINGS(IVYBRIDGE, X86_STEPPING_ANY, SRBDS), @@ -1141,6 +1152,11 @@ static const struct x86_cpu_id cpu_vuln_ VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPINGS(0x1, 0x1), MMIO | MMIO_SBDS), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPINGS(0x0, 0x0), MMIO | MMIO_SBDS), + + VULNBL_AMD(0x15, RETBLEED), + VULNBL_AMD(0x16, RETBLEED), + VULNBL_AMD(0x17, RETBLEED), + VULNBL_HYGON(0x18, RETBLEED), {} };

@@ -1248,6 +1264,9 @@ static void __init cpu_set_bug_bits(stru setup_force_cpu_bug(X86_BUG_MMIO_UNKNOWN); }

+ if (cpu_matches(cpu_vuln_blacklist, RETBLEED)) + setup_force_cpu_bug(X86_BUG_RETBLEED); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return;

--- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -574,6 +574,12 @@ ssize_t __weak cpu_show_mmio_stale_data( return sysfs_emit(buf, "Not affected\n"); }

+ssize_t __weak cpu_show_retbleed(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); @@ -584,6 +590,7 @@ static DEVICE_ATTR(tsx_async_abort, 0444 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 struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -596,6 +603,7 @@ static struct attribute *cpu_root_vulner &dev_attr_itlb_multihit.attr, &dev_attr_srbds.attr, &dev_attr_mmio_stale_data.attr, + &dev_attr_retbleed.attr, NULL };

--- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -68,6 +68,8 @@ extern ssize_t cpu_show_srbds(struct dev extern ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_retbleed(struct device *dev, + struct device_attribute *attr, char *buf);

extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata,

From: Peter Zijlstra peterz@infradead.org

commit caa0ff24d5d0e02abce5e65c3d2b7f20a6617be5 upstream.

Due to TIF_SSBD and TIF_SPEC_IB the actual IA32_SPEC_CTRL value can differ from x86_spec_ctrl_base. As such, keep a per-CPU value reflecting the current task's MSR content.

[jpoimboe: rename]

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/nospec-branch.h | 1 + arch/x86/kernel/cpu/bugs.c | 28 +++++++++++++++++++++++----- arch/x86/kernel/process.c | 2 +- 3 files changed, 25 insertions(+), 6 deletions(-)

--- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -297,6 +297,7 @@ static inline void indirect_branch_predi

/* The Intel SPEC CTRL MSR base value cache */ extern u64 x86_spec_ctrl_base; +extern void write_spec_ctrl_current(u64 val);

/* * With retpoline, we must use IBRS to restrict branch prediction --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -47,12 +47,30 @@ static void __init taa_select_mitigation static void __init mmio_select_mitigation(void); static void __init srbds_select_mitigation(void);

-/* The base value of the SPEC_CTRL MSR that always has to be preserved. */ +/* The base value of the SPEC_CTRL MSR without task-specific bits set */ u64 x86_spec_ctrl_base; EXPORT_SYMBOL_GPL(x86_spec_ctrl_base); + +/* The current value of the SPEC_CTRL MSR with task-specific bits set */ +DEFINE_PER_CPU(u64, x86_spec_ctrl_current); +EXPORT_SYMBOL_GPL(x86_spec_ctrl_current); + static DEFINE_MUTEX(spec_ctrl_mutex);

/* + * Keep track of the SPEC_CTRL MSR value for the current task, which may differ + * from x86_spec_ctrl_base due to STIBP/SSB in __speculation_ctrl_update(). + */ +void write_spec_ctrl_current(u64 val) +{ + if (this_cpu_read(x86_spec_ctrl_current) == val) + return; + + this_cpu_write(x86_spec_ctrl_current, val); + wrmsrl(MSR_IA32_SPEC_CTRL, val); +} + +/* * The vendor and possibly platform specific bits which can be modified in * x86_spec_ctrl_base. */ @@ -1177,7 +1195,7 @@ static void __init spectre_v2_select_mit if (spectre_v2_in_eibrs_mode(mode)) { /* Force it so VMEXIT will restore correctly */ x86_spec_ctrl_base |= SPEC_CTRL_IBRS; - wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + write_spec_ctrl_current(x86_spec_ctrl_base); }

switch (mode) { @@ -1232,7 +1250,7 @@ static void __init spectre_v2_select_mit

static void update_stibp_msr(void * __unused) { - wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + write_spec_ctrl_current(x86_spec_ctrl_base); }

/* Update x86_spec_ctrl_base in case SMT state changed. */ @@ -1475,7 +1493,7 @@ static enum ssb_mitigation __init __ssb_ x86_amd_ssb_disable(); } else { x86_spec_ctrl_base |= SPEC_CTRL_SSBD; - wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + write_spec_ctrl_current(x86_spec_ctrl_base); } }

@@ -1692,7 +1710,7 @@ int arch_prctl_spec_ctrl_get(struct task void x86_spec_ctrl_setup_ap(void) { if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) - wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base); + write_spec_ctrl_current(x86_spec_ctrl_base);

if (ssb_mode == SPEC_STORE_BYPASS_DISABLE) x86_amd_ssb_disable(); --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -449,7 +449,7 @@ static __always_inline void __speculatio }

if (updmsr) - wrmsrl(MSR_IA32_SPEC_CTRL, msr); + write_spec_ctrl_current(msr); }

static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk)

From: Peter Zijlstra peterz@infradead.org

commit 2dbb887e875b1de3ca8f40ddf26bcfe55798c609 upstream.

Implement Kernel IBRS - currently the only known option to mitigate RSB underflow speculation issues on Skylake hardware.

Note: since IBRS_ENTER requires fuller context established than UNTRAIN_RET, it must be placed after it. However, since UNTRAIN_RET itself implies a RET, it must come after IBRS_ENTER. This means IBRS_ENTER needs to also move UNTRAIN_RET.

Note 2: KERNEL_IBRS is sub-optimal for XenPV.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Borislav Petkov bp@suse.de [cascardo: conflict at arch/x86/entry/entry_64.S, skip_r11rcx] [cascardo: conflict at arch/x86/entry/entry_64_compat.S] [cascardo: conflict fixups, no ANNOTATE_NOENDBR] [cascardo: entry fixups because of missing UNTRAIN_RET] [cascardo: conflicts on fsgsbase] Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/entry/calling.h | 58 +++++++++++++++++++++++++++++++++++++ arch/x86/entry/entry_64.S | 29 +++++++++++++++++- arch/x86/entry/entry_64_compat.S | 11 ++++++- arch/x86/include/asm/cpufeatures.h | 2 - 4 files changed, 97 insertions(+), 3 deletions(-)

--- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -6,6 +6,8 @@ #include <asm/percpu.h> #include <asm/asm-offsets.h> #include <asm/processor-flags.h> +#include <asm/msr.h> +#include <asm/nospec-branch.h>

/*

@@ -309,6 +311,62 @@ For 32-bit we have the following convent #endif

/* + * IBRS kernel mitigation for Spectre_v2. + * + * Assumes full context is established (PUSH_REGS, CR3 and GS) and it clobbers + * the regs it uses (AX, CX, DX). Must be called before the first RET + * instruction (NOTE! UNTRAIN_RET includes a RET instruction) + * + * The optional argument is used to save/restore the current value, + * which is used on the paranoid paths. + * + * Assumes x86_spec_ctrl_{base,current} to have SPEC_CTRL_IBRS set. + */ +.macro IBRS_ENTER save_reg + ALTERNATIVE "jmp .Lend_@", "", X86_FEATURE_KERNEL_IBRS + movl $MSR_IA32_SPEC_CTRL, %ecx + +.ifnb \save_reg + rdmsr + shl $32, %rdx + or %rdx, %rax + mov %rax, \save_reg + test $SPEC_CTRL_IBRS, %eax + jz .Ldo_wrmsr_@ + lfence + jmp .Lend_@ +.Ldo_wrmsr_@: +.endif + + movq PER_CPU_VAR(x86_spec_ctrl_current), %rdx + movl %edx, %eax + shr $32, %rdx + wrmsr +.Lend_@: +.endm + +/* + * Similar to IBRS_ENTER, requires KERNEL GS,CR3 and clobbers (AX, CX, DX) + * regs. Must be called after the last RET. + */ +.macro IBRS_EXIT save_reg + ALTERNATIVE "jmp .Lend_@", "", X86_FEATURE_KERNEL_IBRS + movl $MSR_IA32_SPEC_CTRL, %ecx + +.ifnb \save_reg + mov \save_reg, %rdx +.else + movq PER_CPU_VAR(x86_spec_ctrl_current), %rdx + andl $(~SPEC_CTRL_IBRS), %edx +.endif + + movl %edx, %eax + shr $32, %rdx + wrmsr +.Lend_@: +.endm + +/* * Mitigate Spectre v1 for conditional swapgs code paths. * * FENCE_SWAPGS_USER_ENTRY is used in the user entry swapgs code path, to --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -172,6 +172,10 @@ GLOBAL(entry_SYSCALL_64_after_hwframe) /* IRQs are off. */ movq %rax, %rdi movq %rsp, %rsi + + /* clobbers %rax, make sure it is after saving the syscall nr */ + IBRS_ENTER + call do_syscall_64 /* returns with IRQs disabled */

TRACE_IRQS_IRETQ /* we're about to change IF */ @@ -248,6 +252,7 @@ GLOBAL(entry_SYSCALL_64_after_hwframe) * perf profiles. Nothing jumps here. */ syscall_return_via_sysret: + IBRS_EXIT POP_REGS pop_rdi=0

/* @@ -621,6 +626,7 @@ GLOBAL(retint_user) TRACE_IRQS_IRETQ

GLOBAL(swapgs_restore_regs_and_return_to_usermode) + IBRS_EXIT #ifdef CONFIG_DEBUG_ENTRY /* Assert that pt_regs indicates user mode. */ testb $3, CS(%rsp) @@ -1247,7 +1253,13 @@ ENTRY(paranoid_entry) */ FENCE_SWAPGS_KERNEL_ENTRY

- ret + /* + * Once we have CR3 and %GS setup save and set SPEC_CTRL. Just like + * CR3 above, keep the old value in a callee saved register. + */ + IBRS_ENTER save_reg=%r15 + + RET END(paranoid_entry)

/* @@ -1275,12 +1287,20 @@ ENTRY(paranoid_exit) jmp .Lparanoid_exit_restore .Lparanoid_exit_no_swapgs: TRACE_IRQS_IRETQ_DEBUG + + /* + * Must restore IBRS state before both CR3 and %GS since we need access + * to the per-CPU x86_spec_ctrl_shadow variable. + */ + IBRS_EXIT save_reg=%r15 + /* Always restore stashed CR3 value (see paranoid_entry) */ RESTORE_CR3 scratch_reg=%rbx save_reg=%r14 .Lparanoid_exit_restore: jmp restore_regs_and_return_to_kernel END(paranoid_exit)

+ /* * Save all registers in pt_regs, and switch GS if needed. */ @@ -1300,6 +1320,7 @@ ENTRY(error_entry) FENCE_SWAPGS_USER_ENTRY /* We have user CR3. Change to kernel CR3. */ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax + IBRS_ENTER

.Lerror_entry_from_usermode_after_swapgs: /* Put us onto the real thread stack. */ @@ -1355,6 +1376,7 @@ ENTRY(error_entry) SWAPGS FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rax + IBRS_ENTER

/* * Pretend that the exception came from user mode: set up pt_regs @@ -1460,6 +1482,8 @@ ENTRY(nmi) PUSH_AND_CLEAR_REGS rdx=(%rdx) ENCODE_FRAME_POINTER

+ IBRS_ENTER + /* * At this point we no longer need to worry about stack damage * due to nesting -- we're on the normal thread stack and we're @@ -1683,6 +1707,9 @@ end_repeat_nmi: movq $-1, %rsi call do_nmi

+ /* Always restore stashed SPEC_CTRL value (see paranoid_entry) */ + IBRS_EXIT save_reg=%r15 + /* Always restore stashed CR3 value (see paranoid_entry) */ RESTORE_CR3 scratch_reg=%r15 save_reg=%r14

--- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -4,7 +4,6 @@ * * Copyright 2000-2002 Andi Kleen, SuSE Labs. */ -#include "calling.h" #include <asm/asm-offsets.h> #include <asm/current.h> #include <asm/errno.h> @@ -17,6 +16,8 @@ #include <linux/linkage.h> #include <linux/err.h>

+#include "calling.h" + .section .entry.text, "ax"

/* @@ -106,6 +107,8 @@ ENTRY(entry_SYSENTER_compat) xorl %r15d, %r15d /* nospec r15 */ cld

+ IBRS_ENTER + /* * SYSENTER doesn't filter flags, so we need to clear NT and AC * ourselves. To save a few cycles, we can check whether @@ -253,6 +256,8 @@ GLOBAL(entry_SYSCALL_compat_after_hwfram */ TRACE_IRQS_OFF

+ IBRS_ENTER + movq %rsp, %rdi call do_fast_syscall_32 /* XEN PV guests always use IRET path */ @@ -267,6 +272,9 @@ sysret32_from_system_call: */ STACKLEAK_ERASE TRACE_IRQS_ON /* User mode traces as IRQs on. */ + + IBRS_EXIT + movq RBX(%rsp), %rbx /* pt_regs->rbx */ movq RBP(%rsp), %rbp /* pt_regs->rbp */ movq EFLAGS(%rsp), %r11 /* pt_regs->flags (in r11) */ @@ -408,6 +416,7 @@ ENTRY(entry_INT80_compat) * gate turned them off. */ TRACE_IRQS_OFF + IBRS_ENTER

movq %rsp, %rdi call do_int80_syscall_32 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -203,7 +203,7 @@ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ -/* FREE! ( 7*32+12) */ +#define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* "" Set/clear IBRS on kernel entry/exit */ /* FREE! ( 7*32+13) */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */

From: Pawan Gupta pawan.kumar.gupta@linux.intel.com

commit 7c693f54c873691a4b7da05c7e0f74e67745d144 upstream.

Extend spectre_v2= boot option with Kernel IBRS.

[jpoimboe: no STIBP with IBRS]

Signed-off-by: Pawan Gupta pawan.kumar.gupta@linux.intel.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Documentation/admin-guide/kernel-parameters.txt | 1 arch/x86/include/asm/nospec-branch.h | 1 arch/x86/kernel/cpu/bugs.c | 66 ++++++++++++++++++------ 3 files changed, 54 insertions(+), 14 deletions(-)

--- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -4553,6 +4553,7 @@ eibrs - enhanced IBRS eibrs,retpoline - enhanced IBRS + Retpolines eibrs,lfence - enhanced IBRS + LFENCE + ibrs - use IBRS to protect kernel

Not specifying this option is equivalent to spectre_v2=auto. --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -234,6 +234,7 @@ enum spectre_v2_mitigation { SPECTRE_V2_EIBRS, SPECTRE_V2_EIBRS_RETPOLINE, SPECTRE_V2_EIBRS_LFENCE, + SPECTRE_V2_IBRS, };

/* The indirect branch speculation control variants */ --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -877,6 +877,7 @@ enum spectre_v2_mitigation_cmd { SPECTRE_V2_CMD_EIBRS, SPECTRE_V2_CMD_EIBRS_RETPOLINE, SPECTRE_V2_CMD_EIBRS_LFENCE, + SPECTRE_V2_CMD_IBRS, };

enum spectre_v2_user_cmd { @@ -949,11 +950,12 @@ spectre_v2_parse_user_cmdline(enum spect return SPECTRE_V2_USER_CMD_AUTO; }

-static inline bool spectre_v2_in_eibrs_mode(enum spectre_v2_mitigation mode) +static inline bool spectre_v2_in_ibrs_mode(enum spectre_v2_mitigation mode) { - return (mode == SPECTRE_V2_EIBRS || - mode == SPECTRE_V2_EIBRS_RETPOLINE || - mode == SPECTRE_V2_EIBRS_LFENCE); + return mode == SPECTRE_V2_IBRS || + mode == SPECTRE_V2_EIBRS || + mode == SPECTRE_V2_EIBRS_RETPOLINE || + mode == SPECTRE_V2_EIBRS_LFENCE; }

static void __init @@ -1018,12 +1020,12 @@ spectre_v2_user_select_mitigation(enum s }

/* - * If no STIBP, enhanced IBRS is enabled or SMT impossible, STIBP is not - * required. + * If no STIBP, IBRS or enhanced IBRS is enabled, or SMT impossible, + * STIBP is not required. */ if (!boot_cpu_has(X86_FEATURE_STIBP) || !smt_possible || - spectre_v2_in_eibrs_mode(spectre_v2_enabled)) + spectre_v2_in_ibrs_mode(spectre_v2_enabled)) return;

/* @@ -1048,6 +1050,7 @@ static const char * const spectre_v2_str [SPECTRE_V2_EIBRS] = "Mitigation: Enhanced IBRS", [SPECTRE_V2_EIBRS_LFENCE] = "Mitigation: Enhanced IBRS + LFENCE", [SPECTRE_V2_EIBRS_RETPOLINE] = "Mitigation: Enhanced IBRS + Retpolines", + [SPECTRE_V2_IBRS] = "Mitigation: IBRS", };

static const struct { @@ -1065,6 +1068,7 @@ static const struct { { "eibrs,lfence", SPECTRE_V2_CMD_EIBRS_LFENCE, false }, { "eibrs,retpoline", SPECTRE_V2_CMD_EIBRS_RETPOLINE, false }, { "auto", SPECTRE_V2_CMD_AUTO, false }, + { "ibrs", SPECTRE_V2_CMD_IBRS, false }, };

static void __init spec_v2_print_cond(const char *reason, bool secure) @@ -1127,6 +1131,24 @@ static enum spectre_v2_mitigation_cmd __ return SPECTRE_V2_CMD_AUTO; }

+ if (cmd == SPECTRE_V2_CMD_IBRS && boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) { + pr_err("%s selected but not Intel CPU. Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + + if (cmd == SPECTRE_V2_CMD_IBRS && !boot_cpu_has(X86_FEATURE_IBRS)) { + pr_err("%s selected but CPU doesn't have IBRS. Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + + if (cmd == SPECTRE_V2_CMD_IBRS && boot_cpu_has(X86_FEATURE_XENPV)) { + pr_err("%s selected but running as XenPV guest. Switching to AUTO select\n", + mitigation_options[i].option); + return SPECTRE_V2_CMD_AUTO; + } + spec_v2_print_cond(mitigation_options[i].option, mitigation_options[i].secure); return cmd; @@ -1166,6 +1188,14 @@ static void __init spectre_v2_select_mit break; }

+ if (boot_cpu_has_bug(X86_BUG_RETBLEED) && + retbleed_cmd != RETBLEED_CMD_OFF && + boot_cpu_has(X86_FEATURE_IBRS) && + boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) { + mode = SPECTRE_V2_IBRS; + break; + } + mode = spectre_v2_select_retpoline(); break;

@@ -1182,6 +1212,10 @@ static void __init spectre_v2_select_mit mode = spectre_v2_select_retpoline(); break;

+ case SPECTRE_V2_CMD_IBRS: + mode = SPECTRE_V2_IBRS; + break; + case SPECTRE_V2_CMD_EIBRS: mode = SPECTRE_V2_EIBRS; break; @@ -1198,7 +1232,7 @@ static void __init spectre_v2_select_mit if (mode == SPECTRE_V2_EIBRS && unprivileged_ebpf_enabled()) pr_err(SPECTRE_V2_EIBRS_EBPF_MSG);

- if (spectre_v2_in_eibrs_mode(mode)) { + if (spectre_v2_in_ibrs_mode(mode)) { /* Force it so VMEXIT will restore correctly */ x86_spec_ctrl_base |= SPEC_CTRL_IBRS; write_spec_ctrl_current(x86_spec_ctrl_base, true); @@ -1209,6 +1243,10 @@ static void __init spectre_v2_select_mit case SPECTRE_V2_EIBRS: break;

+ case SPECTRE_V2_IBRS: + setup_force_cpu_cap(X86_FEATURE_KERNEL_IBRS); + break; + case SPECTRE_V2_LFENCE: case SPECTRE_V2_EIBRS_LFENCE: setup_force_cpu_cap(X86_FEATURE_RETPOLINE_LFENCE); @@ -1235,17 +1273,17 @@ static void __init spectre_v2_select_mit pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n");

/* - * Retpoline means the kernel is safe because it has no indirect - * branches. Enhanced IBRS protects firmware too, so, enable restricted - * speculation around firmware calls only when Enhanced IBRS isn't - * supported. + * Retpoline protects the kernel, but doesn't protect firmware. IBRS + * and Enhanced IBRS protect firmware too, so enable IBRS around + * firmware calls only when IBRS / Enhanced IBRS aren't otherwise + * enabled. * * Use "mode" to check Enhanced IBRS instead of boot_cpu_has(), because * the user might select retpoline on the kernel command line and if * the CPU supports Enhanced IBRS, kernel might un-intentionally not * enable IBRS around firmware calls. */ - if (boot_cpu_has(X86_FEATURE_IBRS) && !spectre_v2_in_eibrs_mode(mode)) { + if (boot_cpu_has(X86_FEATURE_IBRS) && !spectre_v2_in_ibrs_mode(mode)) { setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW); pr_info("Enabling Restricted Speculation for firmware calls\n"); } @@ -1951,7 +1989,7 @@ static ssize_t mmio_stale_data_show_stat

static char *stibp_state(void) { - if (spectre_v2_in_eibrs_mode(spectre_v2_enabled)) + if (spectre_v2_in_ibrs_mode(spectre_v2_enabled)) return "";

switch (spectre_v2_user_stibp) {

From: Peter Zijlstra peterz@infradead.org

commit 6ad0ad2bf8a67e27d1f9d006a1dabb0e1c360cc3 upstream.

Skylake suffers from RSB underflow speculation issues; report this vulnerability and it's mitigation (spectre_v2=ibrs).

[jpoimboe: cleanups, eibrs]

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/msr-index.h | 1 + arch/x86/kernel/cpu/bugs.c | 36 +++++++++++++++++++++++++++++++----- arch/x86/kernel/cpu/common.c | 24 ++++++++++++------------ 3 files changed, 44 insertions(+), 17 deletions(-)

--- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -82,6 +82,7 @@ #define MSR_IA32_ARCH_CAPABILITIES 0x0000010a #define ARCH_CAP_RDCL_NO BIT(0) /* Not susceptible to Meltdown */ #define ARCH_CAP_IBRS_ALL BIT(1) /* Enhanced IBRS support */ +#define ARCH_CAP_RSBA BIT(2) /* RET may use alternative branch predictors */ #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 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -743,11 +743,16 @@ static int __init nospectre_v1_cmdline(c } early_param("nospectre_v1", nospectre_v1_cmdline);

+static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = + SPECTRE_V2_NONE; + #undef pr_fmt #define pr_fmt(fmt) "RETBleed: " fmt

enum retbleed_mitigation { RETBLEED_MITIGATION_NONE, + RETBLEED_MITIGATION_IBRS, + RETBLEED_MITIGATION_EIBRS, };

enum retbleed_mitigation_cmd { @@ -757,6 +762,8 @@ enum retbleed_mitigation_cmd {

const char * const retbleed_strings[] = { [RETBLEED_MITIGATION_NONE] = "Vulnerable", + [RETBLEED_MITIGATION_IBRS] = "Mitigation: IBRS", + [RETBLEED_MITIGATION_EIBRS] = "Mitigation: Enhanced IBRS", };

static enum retbleed_mitigation retbleed_mitigation __ro_after_init = @@ -782,6 +789,7 @@ early_param("retbleed", retbleed_parse_c

#define RETBLEED_UNTRAIN_MSG "WARNING: BTB untrained return thunk mitigation is only effective on AMD/Hygon!\n" #define RETBLEED_COMPILER_MSG "WARNING: kernel not compiled with RETPOLINE or -mfunction-return capable compiler!\n" +#define RETBLEED_INTEL_MSG "WARNING: Spectre v2 mitigation leaves CPU vulnerable to RETBleed attacks, data leaks possible!\n"

static void __init retbleed_select_mitigation(void) { @@ -794,8 +802,10 @@ static void __init retbleed_select_mitig

case RETBLEED_CMD_AUTO: default: - if (!boot_cpu_has_bug(X86_BUG_RETBLEED)) - break; + /* + * The Intel mitigation (IBRS) was already selected in + * spectre_v2_select_mitigation(). + */

break; } @@ -805,15 +815,31 @@ static void __init retbleed_select_mitig break; }

+ /* + * Let IBRS trump all on Intel without affecting the effects of the + * retbleed= cmdline option. + */ + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) { + switch (spectre_v2_enabled) { + case SPECTRE_V2_IBRS: + retbleed_mitigation = RETBLEED_MITIGATION_IBRS; + break; + case SPECTRE_V2_EIBRS: + case SPECTRE_V2_EIBRS_RETPOLINE: + case SPECTRE_V2_EIBRS_LFENCE: + retbleed_mitigation = RETBLEED_MITIGATION_EIBRS; + break; + default: + pr_err(RETBLEED_INTEL_MSG); + } + } + pr_info("%s\n", retbleed_strings[retbleed_mitigation]); }

#undef pr_fmt #define pr_fmt(fmt) "Spectre V2 : " fmt

-static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = - SPECTRE_V2_NONE; - static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init = SPECTRE_V2_USER_NONE; static enum spectre_v2_user_mitigation spectre_v2_user_ibpb __ro_after_init = --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1131,24 +1131,24 @@ static const struct x86_cpu_id cpu_vuln_ VULNBL_INTEL_STEPPINGS(BROADWELL_G, X86_STEPPING_ANY, SRBDS), VULNBL_INTEL_STEPPINGS(BROADWELL_X, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(BROADWELL, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPINGS(0x3, 0x3), SRBDS | MMIO), + VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPINGS(0x3, 0x3), SRBDS | MMIO | RETBLEED), VULNBL_INTEL_STEPPINGS(SKYLAKE_L, X86_STEPPING_ANY, SRBDS), VULNBL_INTEL_STEPPINGS(SKYLAKE_X, BIT(3) | BIT(4) | BIT(6) | - BIT(7) | BIT(0xB), MMIO), - VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPINGS(0x3, 0x3), SRBDS | MMIO), + BIT(7) | BIT(0xB), MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPINGS(0x3, 0x3), SRBDS | MMIO | RETBLEED), VULNBL_INTEL_STEPPINGS(SKYLAKE, X86_STEPPING_ANY, SRBDS), - VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPINGS(0x9, 0xC), SRBDS | MMIO), + VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPINGS(0x9, 0xC), SRBDS | MMIO | RETBLEED), VULNBL_INTEL_STEPPINGS(KABYLAKE_L, X86_STEPPINGS(0x0, 0x8), SRBDS), - VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPINGS(0x9, 0xD), SRBDS | MMIO), + VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPINGS(0x9, 0xD), SRBDS | MMIO | RETBLEED), VULNBL_INTEL_STEPPINGS(KABYLAKE, X86_STEPPINGS(0x0, 0x8), SRBDS), - VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPINGS(0x5, 0x5), MMIO | MMIO_SBDS), + VULNBL_INTEL_STEPPINGS(ICELAKE_L, X86_STEPPINGS(0x5, 0x5), MMIO | MMIO_SBDS | RETBLEED), VULNBL_INTEL_STEPPINGS(ICELAKE_D, X86_STEPPINGS(0x1, 0x1), MMIO), VULNBL_INTEL_STEPPINGS(ICELAKE_X, X86_STEPPINGS(0x4, 0x6), MMIO), - VULNBL_INTEL_STEPPINGS(COMETLAKE, BIT(2) | BIT(3) | BIT(5), MMIO | MMIO_SBDS), - VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x1, 0x1), MMIO | MMIO_SBDS), - VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO), - VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPINGS(0x1, 0x1), MMIO | MMIO_SBDS), - VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPINGS(0x1, 0x1), MMIO), + VULNBL_INTEL_STEPPINGS(COMETLAKE, BIT(2) | BIT(3) | BIT(5), MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x1, 0x1), MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(COMETLAKE_L, X86_STEPPINGS(0x0, 0x0), MMIO | RETBLEED), + VULNBL_INTEL_STEPPINGS(LAKEFIELD, X86_STEPPINGS(0x1, 0x1), MMIO | MMIO_SBDS | RETBLEED), + VULNBL_INTEL_STEPPINGS(ROCKETLAKE, X86_STEPPINGS(0x1, 0x1), MMIO | RETBLEED), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT, X86_STEPPINGS(0x1, 0x1), MMIO | MMIO_SBDS), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D, X86_STEPPING_ANY, MMIO), VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L, X86_STEPPINGS(0x0, 0x0), MMIO | MMIO_SBDS), @@ -1264,7 +1264,7 @@ static void __init cpu_set_bug_bits(stru setup_force_cpu_bug(X86_BUG_MMIO_UNKNOWN); }

- if (cpu_matches(cpu_vuln_blacklist, RETBLEED)) + if ((cpu_matches(cpu_vuln_blacklist, RETBLEED) || (ia32_cap & ARCH_CAP_RSBA))) setup_force_cpu_bug(X86_BUG_RETBLEED);

if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))

From: Peter Zijlstra peterz@infradead.org

commit 089dd8e53126ebaf506e2dc0bf89d652c36bfc12 upstream.

Change FILL_RETURN_BUFFER so that objtool groks it and can generate correct ORC unwind information.

- Since ORC is alternative invariant; that is, all alternatives should have the same ORC entries, the __FILL_RETURN_BUFFER body can not be part of an alternative.

Therefore, move it out of the alternative and keep the alternative as a sort of jump_label around it.

- Use the ANNOTATE_INTRA_FUNCTION_CALL annotation to white-list these 'funny' call instructions to nowhere.

- Use UNWIND_HINT_EMPTY to 'fill' the speculation traps, otherwise objtool will consider them unreachable.

- Move the RSP adjustment into the loop, such that the loop has a deterministic stack layout.

Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Reviewed-by: Alexandre Chartre alexandre.chartre@oracle.com Acked-by: Josh Poimboeuf jpoimboe@redhat.com Link: https://lkml.kernel.org/r/20200428191700.032079304@infradead.org [cascardo: fixup because of backport of ba6e31af2be96c4d0536f2152ed6f7b6c11bca47 ("x86/speculation: Add LFENCE to RSB fill sequence")] [cascardo: no intra-function call validation support] [cascardo: avoid UNWIND_HINT_EMPTY because of svm] Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/nospec-branch.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)

--- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -4,11 +4,13 @@ #define _ASM_X86_NOSPEC_BRANCH_H_

#include <linux/static_key.h> +#include <linux/frame.h>

#include <asm/alternative.h> #include <asm/alternative-asm.h> #include <asm/cpufeatures.h> #include <asm/msr-index.h> +#include <asm/unwind_hints.h>

/* * This should be used immediately before a retpoline alternative. It tells @@ -60,9 +62,9 @@ lfence; \ jmp 775b; \ 774: \ + add $(BITS_PER_LONG/8) * 2, sp; \ dec reg; \ jnz 771b; \ - add $(BITS_PER_LONG/8) * nr, sp; \ /* barrier for jnz misprediction */ \ lfence; #else @@ -154,10 +156,8 @@ */ .macro FILL_RETURN_BUFFER reg:req nr:req ftr:req #ifdef CONFIG_RETPOLINE - ANNOTATE_NOSPEC_ALTERNATIVE - ALTERNATIVE "jmp .Lskip_rsb_@", \ - __stringify(__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)) \ - \ftr + ALTERNATIVE "jmp .Lskip_rsb_@", "", \ftr + __FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP) .Lskip_rsb_@: #endif .endm

From: Josh Poimboeuf jpoimboe@kernel.org

commit e6aa13622ea8283cc699cac5d018cc40a2ba2010 upstream.

The firmware entry code may accidentally clear STIBP or SSBD. Fix that.

Signed-off-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/nospec-branch.h | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-)

--- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -307,18 +307,16 @@ extern u64 spec_ctrl_current(void); */ #define firmware_restrict_branch_speculation_start() \ do { \ - u64 val = x86_spec_ctrl_base | SPEC_CTRL_IBRS; \ - \ preempt_disable(); \ - alternative_msr_write(MSR_IA32_SPEC_CTRL, val, \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, \ + spec_ctrl_current() | SPEC_CTRL_IBRS, \ X86_FEATURE_USE_IBRS_FW); \ } while (0)

#define firmware_restrict_branch_speculation_end() \ do { \ - u64 val = x86_spec_ctrl_base; \ - \ - alternative_msr_write(MSR_IA32_SPEC_CTRL, val, \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, \ + spec_ctrl_current(), \ X86_FEATURE_USE_IBRS_FW); \ preempt_enable(); \ } while (0)

From: Josh Poimboeuf jpoimboe@kernel.org

commit bbb69e8bee1bd882784947095ffb2bfe0f7c9470 upstream.

There's no need to recalculate the host value for every entry/exit. Just use the cached value in spec_ctrl_current().

Signed-off-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kernel/cpu/bugs.c | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-)

--- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -198,7 +198,7 @@ void __init check_bugs(void) void x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest) { - u64 msrval, guestval, hostval = x86_spec_ctrl_base; + u64 msrval, guestval, hostval = spec_ctrl_current(); struct thread_info *ti = current_thread_info();

/* Is MSR_SPEC_CTRL implemented ? */ @@ -211,15 +211,6 @@ x86_virt_spec_ctrl(u64 guest_spec_ctrl, guestval = hostval & ~x86_spec_ctrl_mask; guestval |= guest_spec_ctrl & x86_spec_ctrl_mask;

- /* SSBD controlled in MSR_SPEC_CTRL */ - if (static_cpu_has(X86_FEATURE_SPEC_CTRL_SSBD) || - static_cpu_has(X86_FEATURE_AMD_SSBD)) - hostval |= ssbd_tif_to_spec_ctrl(ti->flags); - - /* Conditional STIBP enabled? */ - if (static_branch_unlikely(&switch_to_cond_stibp)) - hostval |= stibp_tif_to_spec_ctrl(ti->flags); - if (hostval != guestval) { msrval = setguest ? guestval : hostval; wrmsrl(MSR_IA32_SPEC_CTRL, msrval); @@ -1274,7 +1265,6 @@ static void __init spectre_v2_select_mit pr_err(SPECTRE_V2_EIBRS_EBPF_MSG);

if (spectre_v2_in_ibrs_mode(mode)) { - /* Force it so VMEXIT will restore correctly */ x86_spec_ctrl_base |= SPEC_CTRL_IBRS; write_spec_ctrl_current(x86_spec_ctrl_base, true); }

From: Uros Bizjak ubizjak@gmail.com

commit 6c44221b05236cc65d76cb5dc2463f738edff39d upstream.

Saves one byte in __vmx_vcpu_run for the same functionality.

Cc: Paolo Bonzini pbonzini@redhat.com Cc: Sean Christopherson sean.j.christopherson@intel.com Signed-off-by: Uros Bizjak ubizjak@gmail.com Message-Id: 20201029140457.126965-1-ubizjak@gmail.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/vmx/vmenter.S | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -135,7 +135,7 @@ ENTRY(__vmx_vcpu_run) mov (%_ASM_SP), %_ASM_AX

/* Check if vmlaunch or vmresume is needed */ - cmpb $0, %bl + testb %bl, %bl

/* Load guest registers. Don't clobber flags. */ mov VCPU_RBX(%_ASM_AX), %_ASM_BX

From: Josh Poimboeuf jpoimboe@kernel.org

commit 8bd200d23ec42d66ccd517a72dd0b9cc6132d2fd upstream.

Move the vmx_vm{enter,exit}() functionality into __vmx_vcpu_run(). This will make it easier to do the spec_ctrl handling before the first RET.

Signed-off-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de [cascardo: remove ENDBR] Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Ben Hutchings ben@decadent.org.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org [cascardo: no unwinding save/restore] Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kvm/vmx/vmenter.S | 114 ++++++++++++++------------------------------- 1 file changed, 37 insertions(+), 77 deletions(-)

--- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -30,72 +30,6 @@ .text

/** - * vmx_vmenter - VM-Enter the current loaded VMCS - * - * %RFLAGS.ZF: !VMCS.LAUNCHED, i.e. controls VMLAUNCH vs. VMRESUME - * - * Returns: - * %RFLAGS.CF is set on VM-Fail Invalid - * %RFLAGS.ZF is set on VM-Fail Valid - * %RFLAGS.{CF,ZF} are cleared on VM-Success, i.e. VM-Exit - * - * Note that VMRESUME/VMLAUNCH fall-through and return directly if - * they VM-Fail, whereas a successful VM-Enter + VM-Exit will jump - * to vmx_vmexit. - */ -ENTRY(vmx_vmenter) - /* EFLAGS.ZF is set if VMCS.LAUNCHED == 0 */ - je 2f - -1: vmresume - ret - -2: vmlaunch - ret - -3: cmpb $0, kvm_rebooting - je 4f - ret -4: ud2 - - .pushsection .fixup, "ax" -5: jmp 3b - .popsection - - _ASM_EXTABLE(1b, 5b) - _ASM_EXTABLE(2b, 5b) - -ENDPROC(vmx_vmenter) - -/** - * vmx_vmexit - Handle a VMX VM-Exit - * - * Returns: - * %RFLAGS.{CF,ZF} are cleared on VM-Success, i.e. VM-Exit - * - * This is vmx_vmenter's partner in crime. On a VM-Exit, control will jump - * here after hardware loads the host's state, i.e. this is the destination - * referred to by VMCS.HOST_RIP. - */ -ENTRY(vmx_vmexit) -#ifdef CONFIG_RETPOLINE - ALTERNATIVE "jmp .Lvmexit_skip_rsb", "", X86_FEATURE_RETPOLINE - /* Preserve guest's RAX, it's used to stuff the RSB. */ - push %_ASM_AX - - /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ - FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE - - /* Clear RFLAGS.CF and RFLAGS.ZF to preserve VM-Exit, i.e. !VM-Fail. */ - or $1, %_ASM_AX - - pop %_ASM_AX -.Lvmexit_skip_rsb: -#endif - ret -ENDPROC(vmx_vmexit) - -/** * __vmx_vcpu_run - Run a vCPU via a transition to VMX guest mode * @vmx: struct vcpu_vmx * (forwarded to vmx_update_host_rsp) * @regs: unsigned long * (to guest registers) @@ -127,8 +61,7 @@ ENTRY(__vmx_vcpu_run) /* Copy @launched to BL, _ASM_ARG3 is volatile. */ mov %_ASM_ARG3B, %bl

- /* Adjust RSP to account for the CALL to vmx_vmenter(). */ - lea -WORD_SIZE(%_ASM_SP), %_ASM_ARG2 + lea (%_ASM_SP), %_ASM_ARG2 call vmx_update_host_rsp

/* Load @regs to RAX. */ @@ -157,11 +90,25 @@ ENTRY(__vmx_vcpu_run) /* Load guest RAX. This kills the @regs pointer! */ mov VCPU_RAX(%_ASM_AX), %_ASM_AX

- /* Enter guest mode */ - call vmx_vmenter + /* Check EFLAGS.ZF from 'testb' above */ + je .Lvmlaunch

- /* Jump on VM-Fail. */ - jbe 2f +/* + * If VMRESUME/VMLAUNCH and corresponding vmexit succeed, execution resumes at + * the 'vmx_vmexit' label below. + */ +.Lvmresume: + vmresume + jmp .Lvmfail + +.Lvmlaunch: + vmlaunch + jmp .Lvmfail + + _ASM_EXTABLE(.Lvmresume, .Lfixup) + _ASM_EXTABLE(.Lvmlaunch, .Lfixup) + +SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL)

/* Temporarily save guest's RAX. */ push %_ASM_AX @@ -188,9 +135,13 @@ ENTRY(__vmx_vcpu_run) mov %r15, VCPU_R15(%_ASM_AX) #endif

+ /* IMPORTANT: RSB must be stuffed before the first return. */ + FILL_RETURN_BUFFER %_ASM_BX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE + /* Clear RAX to indicate VM-Exit (as opposed to VM-Fail). */ xor %eax, %eax

+.Lclear_regs: /* * Clear all general purpose registers except RSP and RAX to prevent * speculative use of the guest's values, even those that are reloaded @@ -200,7 +151,7 @@ ENTRY(__vmx_vcpu_run) * free. RSP and RAX are exempt as RSP is restored by hardware during * VM-Exit and RAX is explicitly loaded with 0 or 1 to return VM-Fail. */ -1: xor %ebx, %ebx + xor %ebx, %ebx xor %ecx, %ecx xor %edx, %edx xor %esi, %esi @@ -219,8 +170,8 @@ ENTRY(__vmx_vcpu_run)

/* "POP" @regs. */ add $WORD_SIZE, %_ASM_SP - pop %_ASM_BX

+ pop %_ASM_BX #ifdef CONFIG_X86_64 pop %r12 pop %r13 @@ -233,11 +184,20 @@ ENTRY(__vmx_vcpu_run) pop %_ASM_BP ret

- /* VM-Fail. Out-of-line to avoid a taken Jcc after VM-Exit. */ -2: mov $1, %eax - jmp 1b +.Lfixup: + cmpb $0, kvm_rebooting + jne .Lvmfail + ud2 +.Lvmfail: + /* VM-Fail: set return value to 1 */ + mov $1, %eax + jmp .Lclear_regs + ENDPROC(__vmx_vcpu_run)

+ +.section .text, "ax" + /** * vmread_error_trampoline - Trampoline from inline asm to vmread_error() * @field: VMCS field encoding that failed

From: Josh Poimboeuf jpoimboe@kernel.org

commit fc02735b14fff8c6678b521d324ade27b1a3d4cf upstream.

On eIBRS systems, the returns in the vmexit return path from __vmx_vcpu_run() to vmx_vcpu_run() are exposed to RSB poisoning attacks.

Fix that by moving the post-vmexit spec_ctrl handling to immediately after the vmexit.

Signed-off-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/nospec-branch.h | 1 arch/x86/kernel/cpu/bugs.c | 4 ++ arch/x86/kvm/vmx/run_flags.h | 1 arch/x86/kvm/vmx/vmenter.S | 49 +++++++++++++++++++++++++++-------- arch/x86/kvm/vmx/vmx.c | 48 ++++++++++++++++++++-------------- arch/x86/kvm/vmx/vmx.h | 1 6 files changed, 73 insertions(+), 31 deletions(-)

--- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -296,6 +296,7 @@ static inline void indirect_branch_predi

/* The Intel SPEC CTRL MSR base value cache */ extern u64 x86_spec_ctrl_base; +extern u64 x86_spec_ctrl_current; extern void write_spec_ctrl_current(u64 val, bool force); extern u64 spec_ctrl_current(void);

--- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -185,6 +185,10 @@ void __init check_bugs(void) #endif }

+/* + * NOTE: For VMX, this function is not called in the vmexit path. + * It uses vmx_spec_ctrl_restore_host() instead. + */ void x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest) { --- a/arch/x86/kvm/vmx/run_flags.h +++ b/arch/x86/kvm/vmx/run_flags.h @@ -3,5 +3,6 @@ #define __KVM_X86_VMX_RUN_FLAGS_H

#define VMX_RUN_VMRESUME (1 << 0) +#define VMX_RUN_SAVE_SPEC_CTRL (1 << 1)

#endif /* __KVM_X86_VMX_RUN_FLAGS_H */ --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -32,9 +32,10 @@

/** * __vmx_vcpu_run - Run a vCPU via a transition to VMX guest mode - * @vmx: struct vcpu_vmx * (forwarded to vmx_update_host_rsp) + * @vmx: struct vcpu_vmx * * @regs: unsigned long * (to guest registers) - * @flags: VMX_RUN_VMRESUME: use VMRESUME instead of VMLAUNCH + * @flags: VMX_RUN_VMRESUME: use VMRESUME instead of VMLAUNCH + * VMX_RUN_SAVE_SPEC_CTRL: save guest SPEC_CTRL into vmx->spec_ctrl * * Returns: * 0 on VM-Exit, 1 on VM-Fail @@ -53,6 +54,12 @@ ENTRY(__vmx_vcpu_run) #endif push %_ASM_BX

+ /* Save @vmx for SPEC_CTRL handling */ + push %_ASM_ARG1 + + /* Save @flags for SPEC_CTRL handling */ + push %_ASM_ARG3 + /* * Save @regs, _ASM_ARG2 may be modified by vmx_update_host_rsp() and * @regs is needed after VM-Exit to save the guest's register values. @@ -136,23 +143,21 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL mov %r15, VCPU_R15(%_ASM_AX) #endif

- /* IMPORTANT: RSB must be stuffed before the first return. */ - FILL_RETURN_BUFFER %_ASM_BX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE - - /* Clear RAX to indicate VM-Exit (as opposed to VM-Fail). */ - xor %eax, %eax + /* Clear return value to indicate VM-Exit (as opposed to VM-Fail). */ + xor %ebx, %ebx

.Lclear_regs: /* - * Clear all general purpose registers except RSP and RAX to prevent + * Clear all general purpose registers except RSP and RBX to prevent * speculative use of the guest's values, even those that are reloaded * via the stack. In theory, an L1 cache miss when restoring registers * could lead to speculative execution with the guest's values. * Zeroing XORs are dirt cheap, i.e. the extra paranoia is essentially * free. RSP and RAX are exempt as RSP is restored by hardware during - * VM-Exit and RAX is explicitly loaded with 0 or 1 to return VM-Fail. + * VM-Exit and RBX is explicitly loaded with 0 or 1 to hold the return + * value. */ - xor %ebx, %ebx + xor %eax, %eax xor %ecx, %ecx xor %edx, %edx xor %esi, %esi @@ -172,6 +177,28 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL /* "POP" @regs. */ add $WORD_SIZE, %_ASM_SP

+ /* + * IMPORTANT: RSB filling and SPEC_CTRL handling must be done before + * the first unbalanced RET after vmexit! + * + * For retpoline, RSB filling is needed to prevent poisoned RSB entries + * and (in some cases) RSB underflow. + * + * eIBRS has its own protection against poisoned RSB, so it doesn't + * need the RSB filling sequence. But it does need to be enabled + * before the first unbalanced RET. + */ + + FILL_RETURN_BUFFER %_ASM_CX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE + + pop %_ASM_ARG2 /* @flags */ + pop %_ASM_ARG1 /* @vmx */ + + call vmx_spec_ctrl_restore_host + + /* Put return value in AX */ + mov %_ASM_BX, %_ASM_AX + pop %_ASM_BX #ifdef CONFIG_X86_64 pop %r12 @@ -191,7 +218,7 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL ud2 .Lvmfail: /* VM-Fail: set return value to 1 */ - mov $1, %eax + mov $1, %_ASM_BX jmp .Lclear_regs

ENDPROC(__vmx_vcpu_run) --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -870,6 +870,14 @@ unsigned int __vmx_vcpu_run_flags(struct if (vmx->loaded_vmcs->launched) flags |= VMX_RUN_VMRESUME;

+ /* + * If writes to the SPEC_CTRL MSR aren't intercepted, the guest is free + * to change it directly without causing a vmexit. In that case read + * it after vmexit and store it in vmx->spec_ctrl. + */ + if (unlikely(!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL))) + flags |= VMX_RUN_SAVE_SPEC_CTRL; + return flags; }

@@ -6550,6 +6558,26 @@ void vmx_update_host_rsp(struct vcpu_vmx } }

+void noinstr vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx, + unsigned int flags) +{ + u64 hostval = this_cpu_read(x86_spec_ctrl_current); + + if (!cpu_feature_enabled(X86_FEATURE_MSR_SPEC_CTRL)) + return; + + if (flags & VMX_RUN_SAVE_SPEC_CTRL) + vmx->spec_ctrl = __rdmsr(MSR_IA32_SPEC_CTRL); + + /* + * If the guest/host SPEC_CTRL values differ, restore the host value. + */ + if (vmx->spec_ctrl != hostval) + native_wrmsrl(MSR_IA32_SPEC_CTRL, hostval); + + barrier_nospec(); +} + static void vmx_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -6643,26 +6671,6 @@ static void vmx_vcpu_run(struct kvm_vcpu

vmx_enable_fb_clear(vmx);

- /* - * We do not use IBRS in the kernel. If this vCPU has used the - * SPEC_CTRL MSR it may have left it on; save the value and - * turn it off. This is much more efficient than blindly adding - * it to the atomic save/restore list. Especially as the former - * (Saving guest MSRs on vmexit) doesn't even exist in KVM. - * - * For non-nested case: - * If the L01 MSR bitmap does not intercept the MSR, then we need to - * save it. - * - * For nested case: - * If the L02 MSR bitmap does not intercept the MSR, then we need to - * save it. - */ - if (unlikely(!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL))) - vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); - - x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0); - /* All fields are clean at this point */ if (static_branch_unlikely(&enable_evmcs)) current_evmcs->hv_clean_fields |= --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -337,6 +337,7 @@ void vmx_set_virtual_apic_mode(struct kv struct shared_msr_entry *find_msr_entry(struct vcpu_vmx *vmx, u32 msr); void pt_update_intercept_for_msr(struct vcpu_vmx *vmx); void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp); +void vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx, unsigned int flags); unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx); bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, unsigned int flags);

From: Josh Poimboeuf jpoimboe@kernel.org

commit 9756bba28470722dacb79ffce554336dd1f6a6cd upstream.

Prevent RSB underflow/poisoning attacks with RSB. While at it, add a bunch of comments to attempt to document the current state of tribal knowledge about RSB attacks and what exactly is being mitigated.

Signed-off-by: Josh Poimboeuf jpoimboe@kernel.org Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/cpufeatures.h | 2 - arch/x86/kernel/cpu/bugs.c | 63 ++++++++++++++++++++++++++++++++++--- arch/x86/kvm/vmx/vmenter.S | 6 +-- 3 files changed, 62 insertions(+), 9 deletions(-)

--- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -204,7 +204,7 @@ #define X86_FEATURE_SME ( 7*32+10) /* AMD Secure Memory Encryption */ #define X86_FEATURE_PTI ( 7*32+11) /* Kernel Page Table Isolation enabled */ #define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* "" Set/clear IBRS on kernel entry/exit */ -/* FREE! ( 7*32+13) */ +#define X86_FEATURE_RSB_VMEXIT ( 7*32+13) /* "" Fill RSB on VM-Exit */ #define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* Intel Processor Inventory Number */ #define X86_FEATURE_CDP_L2 ( 7*32+15) /* Code and Data Prioritization L2 */ #define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* "" MSR SPEC_CTRL is implemented */ --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1278,17 +1278,70 @@ static void __init spectre_v2_select_mit pr_info("%s\n", spectre_v2_strings[mode]);

/* - * If spectre v2 protection has been enabled, unconditionally fill - * RSB during a context switch; this protects against two independent - * issues: + * If Spectre v2 protection has been enabled, fill the RSB during a + * context switch. In general there are two types of RSB attacks + * across context switches, for which the CALLs/RETs may be unbalanced. * - * - RSB underflow (and switch to BTB) on Skylake+ - * - SpectreRSB variant of spectre v2 on X86_BUG_SPECTRE_V2 CPUs + * 1) RSB underflow + * + * Some Intel parts have "bottomless RSB". When the RSB is empty, + * speculated return targets may come from the branch predictor, + * which could have a user-poisoned BTB or BHB entry. + * + * AMD has it even worse: *all* returns are speculated from the BTB, + * regardless of the state of the RSB. + * + * When IBRS or eIBRS is enabled, the "user -> kernel" attack + * scenario is mitigated by the IBRS branch prediction isolation + * properties, so the RSB buffer filling wouldn't be necessary to + * protect against this type of attack. + * + * The "user -> user" attack scenario is mitigated by RSB filling. + * + * 2) Poisoned RSB entry + * + * If the 'next' in-kernel return stack is shorter than 'prev', + * 'next' could be tricked into speculating with a user-poisoned RSB + * entry. + * + * The "user -> kernel" attack scenario is mitigated by SMEP and + * eIBRS. + * + * The "user -> user" scenario, also known as SpectreBHB, requires + * RSB clearing. + * + * So to mitigate all cases, unconditionally fill RSB on context + * switches. + * + * FIXME: Is this pointless for retbleed-affected AMD? */ setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n");

/* + * Similar to context switches, there are two types of RSB attacks + * after vmexit: + * + * 1) RSB underflow + * + * 2) Poisoned RSB entry + * + * When retpoline is enabled, both are mitigated by filling/clearing + * the RSB. + * + * When IBRS is enabled, while #1 would be mitigated by the IBRS branch + * prediction isolation protections, RSB still needs to be cleared + * because of #2. Note that SMEP provides no protection here, unlike + * user-space-poisoned RSB entries. + * + * eIBRS, on the other hand, has RSB-poisoning protections, so it + * doesn't need RSB clearing after vmexit. + */ + if (boot_cpu_has(X86_FEATURE_RETPOLINE) || + boot_cpu_has(X86_FEATURE_KERNEL_IBRS)) + setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT); + + /* * Retpoline protects the kernel, but doesn't protect firmware. IBRS * and Enhanced IBRS protect firmware too, so enable IBRS around * firmware calls only when IBRS / Enhanced IBRS aren't otherwise --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -181,15 +181,15 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL * IMPORTANT: RSB filling and SPEC_CTRL handling must be done before * the first unbalanced RET after vmexit! * - * For retpoline, RSB filling is needed to prevent poisoned RSB entries - * and (in some cases) RSB underflow. + * For retpoline or IBRS, RSB filling is needed to prevent poisoned RSB + * entries and (in some cases) RSB underflow. * * eIBRS has its own protection against poisoned RSB, so it doesn't * need the RSB filling sequence. But it does need to be enabled * before the first unbalanced RET. */

- FILL_RETURN_BUFFER %_ASM_CX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE + FILL_RETURN_BUFFER %_ASM_CX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT

pop %_ASM_ARG2 /* @flags */ pop %_ASM_ARG1 /* @vmx */

From: Andrew Cooper andrew.cooper3@citrix.com

commit 26aae8ccbc1972233afd08fb3f368947c0314265 upstream.

BTC_NO indicates that hardware is not susceptible to Branch Type Confusion.

Zen3 CPUs don't suffer BTC.

Hypervisors are expected to synthesise BTC_NO when it is appropriate given the migration pool, to prevent kernels using heuristics.

[ bp: Massage. ]

Signed-off-by: Andrew Cooper andrew.cooper3@citrix.com Signed-off-by: Borislav Petkov bp@suse.de Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/kernel/cpu/amd.c | 21 +++++++++++++++------ arch/x86/kernel/cpu/common.c | 6 ++++-- 3 files changed, 20 insertions(+), 8 deletions(-)

--- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -304,6 +304,7 @@ #define X86_FEATURE_AMD_SSBD (13*32+24) /* "" Speculative Store Bypass Disable */ #define X86_FEATURE_VIRT_SSBD (13*32+25) /* Virtualized Speculative Store Bypass Disable */ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ +#define X86_FEATURE_BTC_NO (13*32+29) /* "" Not vulnerable to Branch Type Confusion */

/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ #define X86_FEATURE_DTHERM (14*32+ 0) /* Digital Thermal Sensor */ --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -894,12 +894,21 @@ static void init_amd_zn(struct cpuinfo_x node_reclaim_distance = 32; #endif

- /* - * Fix erratum 1076: CPB feature bit not being set in CPUID. - * Always set it, except when running under a hypervisor. - */ - if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && !cpu_has(c, X86_FEATURE_CPB)) - set_cpu_cap(c, X86_FEATURE_CPB); + /* Fix up CPUID bits, but only if not virtualised. */ + if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) { + + /* Erratum 1076: CPB feature bit not being set in CPUID. */ + if (!cpu_has(c, X86_FEATURE_CPB)) + set_cpu_cap(c, X86_FEATURE_CPB); + + /* + * Zen3 (Fam19 model < 0x10) parts are not susceptible to + * Branch Type Confusion, but predate the allocation of the + * BTC_NO bit. + */ + if (c->x86 == 0x19 && !cpu_has(c, X86_FEATURE_BTC_NO)) + set_cpu_cap(c, X86_FEATURE_BTC_NO); + } }

static void init_amd(struct cpuinfo_x86 *c) --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1259,8 +1259,10 @@ static void __init cpu_set_bug_bits(stru setup_force_cpu_bug(X86_BUG_MMIO_UNKNOWN); }

- if ((cpu_matches(cpu_vuln_blacklist, RETBLEED) || (ia32_cap & ARCH_CAP_RSBA))) - setup_force_cpu_bug(X86_BUG_RETBLEED); + if (!cpu_has(c, X86_FEATURE_BTC_NO)) { + if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (ia32_cap & ARCH_CAP_RSBA)) + setup_force_cpu_bug(X86_BUG_RETBLEED); + }

if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return;

From: Pawan Gupta pawan.kumar.gupta@linux.intel.com

commit 4ad3278df6fe2b0852b00d5757fc2ccd8e92c26e upstream.

Some Intel processors may use alternate predictors for RETs on RSB-underflow. This condition may be vulnerable to Branch History Injection (BHI) and intramode-BTI.

Kernel earlier added spectre_v2 mitigation modes (eIBRS+Retpolines, eIBRS+LFENCE, Retpolines) which protect indirect CALLs and JMPs against such attacks. However, on RSB-underflow, RET target prediction may fallback to alternate predictors. As a result, RET's predicted target may get influenced by branch history.

A new MSR_IA32_SPEC_CTRL bit (RRSBA_DIS_S) controls this fallback behavior when in kernel mode. When set, RETs will not take predictions from alternate predictors, hence mitigating RETs as well. Support for this is enumerated by CPUID.7.2.EDX[RRSBA_CTRL] (bit2).

For spectre v2 mitigation, when a user selects a mitigation that protects indirect CALLs and JMPs against BHI and intramode-BTI, set RRSBA_DIS_S also to protect RETs for RSB-underflow case.

Signed-off-by: Pawan Gupta pawan.kumar.gupta@linux.intel.com Signed-off-by: Borislav Petkov bp@suse.de [cascardo: no tools/arch/x86/include/asm/msr-index.h] Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/include/asm/msr-index.h | 9 +++++++++ arch/x86/kernel/cpu/bugs.c | 26 ++++++++++++++++++++++++++ arch/x86/kernel/cpu/scattered.c | 1 + 4 files changed, 37 insertions(+)

--- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -286,6 +286,7 @@ #define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* LLC Local MBM monitoring */ #define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* "" LFENCE in user entry SWAPGS path */ #define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* "" LFENCE in kernel entry SWAPGS path */ +#define X86_FEATURE_RRSBA_CTRL (11*32+11) /* "" RET prediction control */ #define X86_FEATURE_RETPOLINE (11*32+12) /* "" Generic Retpoline mitigation for Spectre variant 2 */ #define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* "" Use LFENCE for Spectre variant 2 */

--- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -47,6 +47,8 @@ #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 BIT(SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */ +#define SPEC_CTRL_RRSBA_DIS_S_SHIFT 6 /* Disable RRSBA behavior */ +#define SPEC_CTRL_RRSBA_DIS_S BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT)

#define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ @@ -130,6 +132,13 @@ * bit available to control VERW * behavior. */ +#define ARCH_CAP_RRSBA BIT(19) /* + * Indicates RET may use predictors + * other than the RSB. With eIBRS + * enabled predictions in kernel mode + * are restricted to targets in + * kernel. + */

#define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1181,6 +1181,22 @@ static enum spectre_v2_mitigation __init return SPECTRE_V2_RETPOLINE; }

+/* Disable in-kernel use of non-RSB RET predictors */ +static void __init spec_ctrl_disable_kernel_rrsba(void) +{ + u64 ia32_cap; + + if (!boot_cpu_has(X86_FEATURE_RRSBA_CTRL)) + return; + + ia32_cap = x86_read_arch_cap_msr(); + + if (ia32_cap & ARCH_CAP_RRSBA) { + x86_spec_ctrl_base |= SPEC_CTRL_RRSBA_DIS_S; + write_spec_ctrl_current(x86_spec_ctrl_base, true); + } +} + static void __init spectre_v2_select_mitigation(void) { enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); @@ -1274,6 +1290,16 @@ static void __init spectre_v2_select_mit break; }

+ /* + * Disable alternate RSB predictions in kernel when indirect CALLs and + * JMPs gets protection against BHI and Intramode-BTI, but RET + * prediction from a non-RSB predictor is still a risk. + */ + if (mode == SPECTRE_V2_EIBRS_LFENCE || + mode == SPECTRE_V2_EIBRS_RETPOLINE || + mode == SPECTRE_V2_RETPOLINE) + spec_ctrl_disable_kernel_rrsba(); + spectre_v2_enabled = mode; pr_info("%s\n", spectre_v2_strings[mode]);

--- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -26,6 +26,7 @@ struct cpuid_bit { static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 }, + { X86_FEATURE_RRSBA_CTRL, CPUID_EDX, 2, 0x00000007, 2 }, { X86_FEATURE_CQM_LLC, CPUID_EDX, 1, 0x0000000f, 0 }, { X86_FEATURE_CQM_OCCUP_LLC, CPUID_EDX, 0, 0x0000000f, 1 }, { X86_FEATURE_CQM_MBM_TOTAL, CPUID_EDX, 1, 0x0000000f, 1 },

From: Pawan Gupta pawan.kumar.gupta@linux.intel.com

commit eb23b5ef9131e6d65011de349a4d25ef1b3d4314 upstream.

IBRS mitigation for spectre_v2 forces write to MSR_IA32_SPEC_CTRL at every kernel entry/exit. On Enhanced IBRS parts setting MSR_IA32_SPEC_CTRL[IBRS] only once at boot is sufficient. MSR writes at every kernel entry/exit incur unnecessary performance loss.

When Enhanced IBRS feature is present, print a warning about this unnecessary performance loss.

Signed-off-by: Pawan Gupta pawan.kumar.gupta@linux.intel.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Reviewed-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/2a5eaf54583c2bfe0edc4fea64006656256cca17.165781485... Signed-off-by: Thadeu Lima de Souza Cascardo cascardo@canonical.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/x86/kernel/cpu/bugs.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -851,6 +851,7 @@ static inline const char *spectre_v2_mod #define SPECTRE_V2_LFENCE_MSG "WARNING: LFENCE mitigation is not recommended for this CPU, data leaks possible!\n" #define SPECTRE_V2_EIBRS_EBPF_MSG "WARNING: Unprivileged eBPF is enabled with eIBRS on, data leaks possible via Spectre v2 BHB attacks!\n" #define SPECTRE_V2_EIBRS_LFENCE_EBPF_SMT_MSG "WARNING: Unprivileged eBPF is enabled with eIBRS+LFENCE mitigation and SMT, data leaks possible via Spectre v2 BHB attacks!\n" +#define SPECTRE_V2_IBRS_PERF_MSG "WARNING: IBRS mitigation selected on Enhanced IBRS CPU, this may cause unnecessary performance loss\n"

#ifdef CONFIG_BPF_SYSCALL void unpriv_ebpf_notify(int new_state) @@ -1277,6 +1278,8 @@ static void __init spectre_v2_select_mit

case SPECTRE_V2_IBRS: setup_force_cpu_cap(X86_FEATURE_KERNEL_IBRS); + if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) + pr_warn(SPECTRE_V2_IBRS_PERF_MSG); break;

case SPECTRE_V2_LFENCE:

From: Christoph Hellwig hch@lst.de

commit 780d29057781d986cd87dbbe232cd02876ad430f upstream.

XFS_ATTR_INCOMPLETE is a flag in the on-disk attribute format, and thus in a different namespace as the ATTR_* flags in xfs_da_args.flags. Switch to using a XFS_DA_OP_INCOMPLETE flag in op_flags instead. Without this users might be able to inject this flag into operations using the attr by handle ioctl.

Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: Darrick J. Wong darrick.wong@oracle.com Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Acked-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Chandan Babu R chandan.babu@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/xfs/libxfs/xfs_attr.c | 2 +- fs/xfs/libxfs/xfs_attr_leaf.c | 4 ++-- fs/xfs/libxfs/xfs_da_btree.h | 4 +++- fs/xfs/libxfs/xfs_da_format.h | 2 -- 4 files changed, 6 insertions(+), 6 deletions(-)

--- a/fs/xfs/libxfs/xfs_attr.c +++ b/fs/xfs/libxfs/xfs_attr.c @@ -1007,7 +1007,7 @@ restart: * The INCOMPLETE flag means that we will find the "old" * attr, not the "new" one. */ - args->flags |= XFS_ATTR_INCOMPLETE; + args->op_flags |= XFS_DA_OP_INCOMPLETE; state = xfs_da_state_alloc(); state->args = args; state->mp = mp; --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -2345,8 +2345,8 @@ xfs_attr3_leaf_lookup_int( * If we are looking for INCOMPLETE entries, show only those. * If we are looking for complete entries, show only those. */ - if ((args->flags & XFS_ATTR_INCOMPLETE) != - (entry->flags & XFS_ATTR_INCOMPLETE)) { + if (!!(args->op_flags & XFS_DA_OP_INCOMPLETE) != + !!(entry->flags & XFS_ATTR_INCOMPLETE)) { continue; } if (entry->flags & XFS_ATTR_LOCAL) { --- a/fs/xfs/libxfs/xfs_da_btree.h +++ b/fs/xfs/libxfs/xfs_da_btree.h @@ -82,6 +82,7 @@ typedef struct xfs_da_args { #define XFS_DA_OP_OKNOENT 0x0008 /* lookup/add op, ENOENT ok, else die */ #define XFS_DA_OP_CILOOKUP 0x0010 /* lookup to return CI name if found */ #define XFS_DA_OP_ALLOCVAL 0x0020 /* lookup to alloc buffer if found */ +#define XFS_DA_OP_INCOMPLETE 0x0040 /* lookup INCOMPLETE attr keys */

#define XFS_DA_OP_FLAGS \ { XFS_DA_OP_JUSTCHECK, "JUSTCHECK" }, \ @@ -89,7 +90,8 @@ typedef struct xfs_da_args { { XFS_DA_OP_ADDNAME, "ADDNAME" }, \ { XFS_DA_OP_OKNOENT, "OKNOENT" }, \ { XFS_DA_OP_CILOOKUP, "CILOOKUP" }, \ - { XFS_DA_OP_ALLOCVAL, "ALLOCVAL" } + { XFS_DA_OP_ALLOCVAL, "ALLOCVAL" }, \ + { XFS_DA_OP_INCOMPLETE, "INCOMPLETE" }

/* * Storage for holding state during Btree searches and split/join ops. --- a/fs/xfs/libxfs/xfs_da_format.h +++ b/fs/xfs/libxfs/xfs_da_format.h @@ -740,8 +740,6 @@ struct xfs_attr3_icleaf_hdr {

/* * Flags used in the leaf_entry[i].flags field. - * NOTE: the INCOMPLETE bit must not collide with the flags bits specified - * on the system call, they are "or"ed together for various operations. */ #define XFS_ATTR_LOCAL_BIT 0 /* attr is stored locally */ #define XFS_ATTR_ROOT_BIT 1 /* limit access to trusted attrs */

From: "Darrick J. Wong" darrick.wong@oracle.com

commit 4bbb04abb4ee2e1f7d65e52557ba1c4038ea43ed upstream.

xfs_itruncate_extents_flags() is supposed to unmap every block in a file from EOF onwards. Oddly, it uses s_maxbytes as the upper limit to the bunmapi range, even though s_maxbytes reflects the highest offset the pagecache can support, not the highest offset that XFS supports.

The result of this confusion is that if you create a 20T file on a 64-bit machine, mount the filesystem on a 32-bit machine, and remove the file, we leak everything above 16T. Fix this by capping the bunmapi request at the maximum possible block offset, not s_maxbytes.

Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Reviewed-by: Christoph Hellwig hch@lst.de Acked-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Chandan Babu R chandan.babu@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/xfs/xfs_inode.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-)

--- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1513,7 +1513,6 @@ xfs_itruncate_extents_flags( struct xfs_mount *mp = ip->i_mount; struct xfs_trans *tp = *tpp; xfs_fileoff_t first_unmap_block; - xfs_fileoff_t last_block; xfs_filblks_t unmap_len; int error = 0; int done = 0; @@ -1536,21 +1535,22 @@ xfs_itruncate_extents_flags( * the end of the file (in a crash where the space is allocated * but the inode size is not yet updated), simply remove any * blocks which show up between the new EOF and the maximum - * possible file size. If the first block to be removed is - * beyond the maximum file size (ie it is the same as last_block), - * then there is nothing to do. + * possible file size. + * + * We have to free all the blocks to the bmbt maximum offset, even if + * the page cache can't scale that far. */ first_unmap_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)new_size); - last_block = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes); - if (first_unmap_block == last_block) + if (first_unmap_block >= XFS_MAX_FILEOFF) { + WARN_ON_ONCE(first_unmap_block > XFS_MAX_FILEOFF); return 0; + }

- ASSERT(first_unmap_block < last_block); - unmap_len = last_block - first_unmap_block + 1; - while (!done) { + unmap_len = XFS_MAX_FILEOFF - first_unmap_block + 1; + while (unmap_len > 0) { ASSERT(tp->t_firstblock == NULLFSBLOCK); - error = xfs_bunmapi(tp, ip, first_unmap_block, unmap_len, flags, - XFS_ITRUNC_MAX_EXTENTS, &done); + error = __xfs_bunmapi(tp, ip, first_unmap_block, &unmap_len, + flags, XFS_ITRUNC_MAX_EXTENTS); if (error) goto out;

@@ -1570,7 +1570,7 @@ xfs_itruncate_extents_flags( if (whichfork == XFS_DATA_FORK) { /* Remove all pending CoW reservations. */ error = xfs_reflink_cancel_cow_blocks(ip, &tp, - first_unmap_block, last_block, true); + first_unmap_block, XFS_MAX_FILEOFF, true); if (error) goto out;

From: Christoph Hellwig hch@lst.de

commit 7b53b868a1812a9a6ab5e69249394bd37f29ce2c upstream.

Direct I/O reads can also be used with RWF_NOWAIT & co. Fix the inode locking in xfs_file_dio_aio_read to take IOCB_NOWAIT into account.

Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: Carlos Maiolino cmaiolino@redhat.com Reviewed-by: Darrick J. Wong darrick.wong@oracle.com Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Acked-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Chandan Babu R chandan.babu@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/xfs/xfs_file.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

--- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -187,7 +187,12 @@ xfs_file_dio_aio_read(

file_accessed(iocb->ki_filp);

- xfs_ilock(ip, XFS_IOLOCK_SHARED); + if (iocb->ki_flags & IOCB_NOWAIT) { + if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) + return -EAGAIN; + } else { + xfs_ilock(ip, XFS_IOLOCK_SHARED); + } ret = iomap_dio_rw(iocb, to, &xfs_iomap_ops, NULL); xfs_iunlock(ip, XFS_IOLOCK_SHARED);

From: "Darrick J. Wong" darrick.wong@oracle.com

commit e8db2aafcedb7d88320ab83f1000f1606b26d4d7 upstream.

[Replaced XFS_IS_CORRUPT() calls with ASSERT() for 5.4.y backport]

While running generic/103, I observed what looks like memory corruption and (with slub debugging turned on) a slub redzone warning on i386 when inactivating an inode with a 64k remote attr value.

On a v5 filesystem, maximally sized remote attr values require one block more than 64k worth of space to hold both the remote attribute value header (64 bytes). On a 4k block filesystem this results in a 68k buffer; on a 64k block filesystem, this would be a 128k buffer. Note that even though we'll never use more than 65,600 bytes of this buffer, XFS_MAX_BLOCKSIZE is 64k.

This is a problem because the definition of struct xfs_buf_log_format allows for XFS_MAX_BLOCKSIZE worth of dirty bitmap (64k). On i386 when we invalidate a remote attribute, xfs_trans_binval zeroes all 68k worth of the dirty map, writing right off the end of the log item and corrupting memory. We've gotten away with this on x86_64 for years because the compiler inserts a u32 padding on the end of struct xfs_buf_log_format.

Fortunately for us, remote attribute values are written to disk with xfs_bwrite(), which is to say that they are not logged. Fix the problem by removing all places where we could end up creating a buffer log item for a remote attribute value and leave a note explaining why. Next, replace the open-coded buffer invalidation with a call to the helper we created in the previous patch that does better checking for bad metadata before marking the buffer stale.

Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Reviewed-by: Christoph Hellwig hch@lst.de Acked-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Chandan Babu R chandan.babu@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/xfs/libxfs/xfs_attr_remote.c | 37 ++++++++++++++++++++++++++----- fs/xfs/xfs_attr_inactive.c | 47 +++++++++++----------------------------- 2 files changed, 44 insertions(+), 40 deletions(-)

--- a/fs/xfs/libxfs/xfs_attr_remote.c +++ b/fs/xfs/libxfs/xfs_attr_remote.c @@ -25,6 +25,23 @@ #define ATTR_RMTVALUE_MAPSIZE 1 /* # of map entries at once */

/* + * Remote Attribute Values + * ======================= + * + * Remote extended attribute values are conceptually simple -- they're written + * to data blocks mapped by an inode's attribute fork, and they have an upper + * size limit of 64k. Setting a value does not involve the XFS log. + * + * However, on a v5 filesystem, maximally sized remote attr values require one + * block more than 64k worth of space to hold both the remote attribute value + * header (64 bytes). On a 4k block filesystem this results in a 68k buffer; + * on a 64k block filesystem, this would be a 128k buffer. Note that the log + * format can only handle a dirty buffer of XFS_MAX_BLOCKSIZE length (64k). + * Therefore, we /must/ ensure that remote attribute value buffers never touch + * the logging system and therefore never have a log item. + */ + +/* * Each contiguous block has a header, so it is not just a simple attribute * length to FSB conversion. */ @@ -400,17 +417,25 @@ xfs_attr_rmtval_get( (map[i].br_startblock != HOLESTARTBLOCK)); dblkno = XFS_FSB_TO_DADDR(mp, map[i].br_startblock); dblkcnt = XFS_FSB_TO_BB(mp, map[i].br_blockcount); - error = xfs_trans_read_buf(mp, args->trans, - mp->m_ddev_targp, - dblkno, dblkcnt, 0, &bp, - &xfs_attr3_rmt_buf_ops); - if (error) + bp = xfs_buf_read(mp->m_ddev_targp, dblkno, dblkcnt, 0, + &xfs_attr3_rmt_buf_ops); + if (!bp) + return -ENOMEM; + error = bp->b_error; + if (error) { + xfs_buf_ioerror_alert(bp, __func__); + xfs_buf_relse(bp); + + /* bad CRC means corrupted metadata */ + if (error == -EFSBADCRC) + error = -EFSCORRUPTED; return error; + }

error = xfs_attr_rmtval_copyout(mp, bp, args->dp->i_ino, &offset, &valuelen, &dst); - xfs_trans_brelse(args->trans, bp); + xfs_buf_relse(bp); if (error) return error;

--- a/fs/xfs/xfs_attr_inactive.c +++ b/fs/xfs/xfs_attr_inactive.c @@ -25,22 +25,20 @@ #include "xfs_error.h"

/* - * Look at all the extents for this logical region, - * invalidate any buffers that are incore/in transactions. + * Invalidate any incore buffers associated with this remote attribute value + * extent. We never log remote attribute value buffers, which means that they + * won't be attached to a transaction and are therefore safe to mark stale. + * The actual bunmapi will be taken care of later. */ STATIC int -xfs_attr3_leaf_freextent( - struct xfs_trans **trans, +xfs_attr3_rmt_stale( struct xfs_inode *dp, xfs_dablk_t blkno, int blkcnt) { struct xfs_bmbt_irec map; - struct xfs_buf *bp; xfs_dablk_t tblkno; - xfs_daddr_t dblkno; int tblkcnt; - int dblkcnt; int nmap; int error;

@@ -57,35 +55,18 @@ xfs_attr3_leaf_freextent( nmap = 1; error = xfs_bmapi_read(dp, (xfs_fileoff_t)tblkno, tblkcnt, &map, &nmap, XFS_BMAPI_ATTRFORK); - if (error) { + if (error) return error; - } ASSERT(nmap == 1); - ASSERT(map.br_startblock != DELAYSTARTBLOCK);

/* - * If it's a hole, these are already unmapped - * so there's nothing to invalidate. + * Mark any incore buffers for the remote value as stale. We + * never log remote attr value buffers, so the buffer should be + * easy to kill. */ - if (map.br_startblock != HOLESTARTBLOCK) { - - dblkno = XFS_FSB_TO_DADDR(dp->i_mount, - map.br_startblock); - dblkcnt = XFS_FSB_TO_BB(dp->i_mount, - map.br_blockcount); - bp = xfs_trans_get_buf(*trans, - dp->i_mount->m_ddev_targp, - dblkno, dblkcnt, 0); - if (!bp) - return -ENOMEM; - xfs_trans_binval(*trans, bp); - /* - * Roll to next transaction. - */ - error = xfs_trans_roll_inode(trans, dp); - if (error) - return error; - } + error = xfs_attr_rmtval_stale(dp, &map, 0); + if (error) + return error;

tblkno += map.br_blockcount; tblkcnt -= map.br_blockcount; @@ -174,9 +155,7 @@ xfs_attr3_leaf_inactive( */ error = 0; for (lp = list, i = 0; i < count; i++, lp++) { - tmp = xfs_attr3_leaf_freextent(trans, dp, - lp->valueblk, lp->valuelen); - + tmp = xfs_attr3_rmt_stale(dp, lp->valueblk, lp->valuelen); if (error == 0) error = tmp; /* save only the 1st errno */ }

From: "Darrick J. Wong" darrick.wong@oracle.com

commit 0bb9d159bd018b271e783d3b2d3bc82fa0727321 upstream.

Now that we know we don't have to take a transaction to stale the incore buffers for a remote value, get rid of the unnecessary memory allocation in the leaf walker and call the rmt_stale function directly. Flatten the loop while we're at it.

Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Reviewed-by: Christoph Hellwig hch@lst.de Acked-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Chandan Babu R chandan.babu@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/xfs/libxfs/xfs_attr_leaf.h | 9 --- fs/xfs/xfs_attr_inactive.c | 103 ++++++++++++------------------------------ 2 files changed, 30 insertions(+), 82 deletions(-)

--- a/fs/xfs/libxfs/xfs_attr_leaf.h +++ b/fs/xfs/libxfs/xfs_attr_leaf.h @@ -39,15 +39,6 @@ struct xfs_attr3_icleaf_hdr { } freemap[XFS_ATTR_LEAF_MAPSIZE]; };

-/* - * Used to keep a list of "remote value" extents when unlinking an inode. - */ -typedef struct xfs_attr_inactive_list { - xfs_dablk_t valueblk; /* block number of value bytes */ - int valuelen; /* number of bytes in value */ -} xfs_attr_inactive_list_t; - - /*======================================================================== * Function prototypes for the kernel. *========================================================================*/ --- a/fs/xfs/xfs_attr_inactive.c +++ b/fs/xfs/xfs_attr_inactive.c @@ -37,8 +37,6 @@ xfs_attr3_rmt_stale( int blkcnt) { struct xfs_bmbt_irec map; - xfs_dablk_t tblkno; - int tblkcnt; int nmap; int error;

@@ -46,14 +44,12 @@ xfs_attr3_rmt_stale( * Roll through the "value", invalidating the attribute value's * blocks. */ - tblkno = blkno; - tblkcnt = blkcnt; - while (tblkcnt > 0) { + while (blkcnt > 0) { /* * Try to remember where we decided to put the value. */ nmap = 1; - error = xfs_bmapi_read(dp, (xfs_fileoff_t)tblkno, tblkcnt, + error = xfs_bmapi_read(dp, (xfs_fileoff_t)blkno, blkcnt, &map, &nmap, XFS_BMAPI_ATTRFORK); if (error) return error; @@ -68,8 +64,8 @@ xfs_attr3_rmt_stale( if (error) return error;

- tblkno += map.br_blockcount; - tblkcnt -= map.br_blockcount; + blkno += map.br_blockcount; + blkcnt -= map.br_blockcount; }

return 0; @@ -83,84 +79,45 @@ xfs_attr3_rmt_stale( */ STATIC int xfs_attr3_leaf_inactive( - struct xfs_trans **trans, - struct xfs_inode *dp, - struct xfs_buf *bp) + struct xfs_trans **trans, + struct xfs_inode *dp, + struct xfs_buf *bp) { - struct xfs_attr_leafblock *leaf; - struct xfs_attr3_icleaf_hdr ichdr; - struct xfs_attr_leaf_entry *entry; + struct xfs_attr3_icleaf_hdr ichdr; + struct xfs_mount *mp = bp->b_mount; + struct xfs_attr_leafblock *leaf = bp->b_addr; + struct xfs_attr_leaf_entry *entry; struct xfs_attr_leaf_name_remote *name_rmt; - struct xfs_attr_inactive_list *list; - struct xfs_attr_inactive_list *lp; - int error; - int count; - int size; - int tmp; - int i; - struct xfs_mount *mp = bp->b_mount; + int error; + int i;

- leaf = bp->b_addr; xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, leaf);

/* - * Count the number of "remote" value extents. + * Find the remote value extents for this leaf and invalidate their + * incore buffers. */ - count = 0; entry = xfs_attr3_leaf_entryp(leaf); for (i = 0; i < ichdr.count; entry++, i++) { - if (be16_to_cpu(entry->nameidx) && - ((entry->flags & XFS_ATTR_LOCAL) == 0)) { - name_rmt = xfs_attr3_leaf_name_remote(leaf, i); - if (name_rmt->valueblk) - count++; - } - } + int blkcnt;

- /* - * If there are no "remote" values, we're done. - */ - if (count == 0) { - xfs_trans_brelse(*trans, bp); - return 0; - } + if (!entry->nameidx || (entry->flags & XFS_ATTR_LOCAL)) + continue;

- /* - * Allocate storage for a list of all the "remote" value extents. - */ - size = count * sizeof(xfs_attr_inactive_list_t); - list = kmem_alloc(size, 0); - - /* - * Identify each of the "remote" value extents. - */ - lp = list; - entry = xfs_attr3_leaf_entryp(leaf); - for (i = 0; i < ichdr.count; entry++, i++) { - if (be16_to_cpu(entry->nameidx) && - ((entry->flags & XFS_ATTR_LOCAL) == 0)) { - name_rmt = xfs_attr3_leaf_name_remote(leaf, i); - if (name_rmt->valueblk) { - lp->valueblk = be32_to_cpu(name_rmt->valueblk); - lp->valuelen = xfs_attr3_rmt_blocks(dp->i_mount, - be32_to_cpu(name_rmt->valuelen)); - lp++; - } - } - } - xfs_trans_brelse(*trans, bp); /* unlock for trans. in freextent() */ - - /* - * Invalidate each of the "remote" value extents. - */ - error = 0; - for (lp = list, i = 0; i < count; i++, lp++) { - tmp = xfs_attr3_rmt_stale(dp, lp->valueblk, lp->valuelen); - if (error == 0) - error = tmp; /* save only the 1st errno */ + name_rmt = xfs_attr3_leaf_name_remote(leaf, i); + if (!name_rmt->valueblk) + continue; + + blkcnt = xfs_attr3_rmt_blocks(dp->i_mount, + be32_to_cpu(name_rmt->valuelen)); + error = xfs_attr3_rmt_stale(dp, + be32_to_cpu(name_rmt->valueblk), blkcnt); + if (error) + goto err; }

- kmem_free(list); + xfs_trans_brelse(*trans, bp); +err: return error; }

From: YueHaibing yuehaibing@huawei.com

commit b3531f5fc16d4df2b12567bce48cd9f3ab5f9131 upstream.

fs/xfs/xfs_inode.c: In function 'xfs_itruncate_extents_flags': fs/xfs/xfs_inode.c:1523:8: warning: unused variable 'done' [-Wunused-variable]

commit 4bbb04abb4ee ("xfs: truncate should remove all blocks, not just to the end of the page cache") left behind this, so remove it.

Fixes: 4bbb04abb4ee ("xfs: truncate should remove all blocks, not just to the end of the page cache") Reported-by: Hulk Robot hulkci@huawei.com Reported-by: Stephen Rothwell sfr@canb.auug.org.au Signed-off-by: YueHaibing yuehaibing@huawei.com Reviewed-by: Darrick J. Wong darrick.wong@oracle.com Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Acked-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Chandan Babu R chandan.babu@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/xfs/xfs_inode.c | 1 - 1 file changed, 1 deletion(-)

--- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1515,7 +1515,6 @@ xfs_itruncate_extents_flags( xfs_fileoff_t first_unmap_block; xfs_filblks_t unmap_len; int error = 0; - int done = 0;

ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); ASSERT(!atomic_read(&VFS_I(ip)->i_count) ||

From: Sami Tolvanen samitolvanen@google.com

commit 2120635108b35ecad9c59c8b44f6cbdf4f98214e upstream.

We enable -Wcast-function-type globally in the kernel to warn about mismatching types in function pointer casts. Compilers currently warn only about ABI incompability with this flag, but Clang 16 will enable a stricter version of the check by default that checks for an exact type match. This will be very noisy in the kernel, so disable -Wcast-function-type-strict without W=1 until the new warnings have been addressed.

Cc: stable@vger.kernel.org Link: https://reviews.llvm.org/D134831 Link: https://github.com/ClangBuiltLinux/linux/issues/1724 Suggested-by: Nathan Chancellor nathan@kernel.org Signed-off-by: Sami Tolvanen samitolvanen@google.com Signed-off-by: Kees Cook keescook@chromium.org Link: https://lore.kernel.org/r/20220930203310.4010564-1-samitolvanen@google.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- scripts/Makefile.extrawarn | 1 + 1 file changed, 1 insertion(+)

--- a/scripts/Makefile.extrawarn +++ b/scripts/Makefile.extrawarn @@ -50,6 +50,7 @@ KBUILD_CFLAGS += -Wno-sign-compare KBUILD_CFLAGS += -Wno-format-zero-length KBUILD_CFLAGS += $(call cc-disable-warning, pointer-to-enum-cast) KBUILD_CFLAGS += $(call cc-disable-warning, unaligned-access) +KBUILD_CFLAGS += $(call cc-disable-warning, cast-function-type-strict) endif

endif