diff options
186 files changed, 3226 insertions, 716 deletions
@@ -447,6 +447,8 @@ Luca Ceresoli <luca.ceresoli@bootlin.com> <luca@lucaceresoli.net> Luca Weiss <luca@lucaweiss.eu> <luca@z3ntu.xyz> Lukasz Luba <lukasz.luba@arm.com> <l.luba@partner.samsung.com> Luo Jie <quic_luoj@quicinc.com> <luoj@codeaurora.org> +Lance Yang <lance.yang@linux.dev> <ioworker0@gmail.com> +Lance Yang <lance.yang@linux.dev> <mingzhe.yang@ly.com> Maciej W. Rozycki <macro@mips.com> <macro@imgtec.com> Maciej W. Rozycki <macro@orcam.me.uk> <macro@linux-mips.org> Maharaja Kennadyrajan <quic_mkenna@quicinc.com> <mkenna@codeaurora.org> @@ -483,6 +485,7 @@ Matthias Fuchs <socketcan@esd.eu> <matthias.fuchs@esd.eu> Matthieu Baerts <matttbe@kernel.org> <matthieu.baerts@tessares.net> Matthieu CASTET <castet.matthieu@free.fr> Matti Vaittinen <mazziesaccount@gmail.com> <matti.vaittinen@fi.rohmeurope.com> +Mattijs Korpershoek <mkorpershoek@kernel.org> <mkorpershoek@baylibre.com> Matt Ranostay <matt@ranostay.sg> <matt.ranostay@konsulko.com> Matt Ranostay <matt@ranostay.sg> <matt@ranostay.consulting> Matt Ranostay <matt@ranostay.sg> Matthew Ranostay <mranostay@embeddedalley.com> @@ -749,6 +752,7 @@ Tvrtko Ursulin <tursulin@ursulin.net> <tvrtko@ursulin.net> Tycho Andersen <tycho@tycho.pizza> <tycho@tycho.ws> Tzung-Bi Shih <tzungbi@kernel.org> <tzungbi@google.com> Uwe Kleine-König <ukleinek@informatik.uni-freiburg.de> +Uwe Kleine-König <u.kleine-koenig@baylibre.com> <ukleinek@baylibre.com> Uwe Kleine-König <u.kleine-koenig@pengutronix.de> Uwe Kleine-König <ukleinek@strlen.de> Uwe Kleine-König <ukl@pengutronix.de> diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu index 206079d3bd5b..6a1acabb29d8 100644 --- a/Documentation/ABI/testing/sysfs-devices-system-cpu +++ b/Documentation/ABI/testing/sysfs-devices-system-cpu @@ -511,6 +511,7 @@ Description: information about CPUs heterogeneity. What: /sys/devices/system/cpu/vulnerabilities /sys/devices/system/cpu/vulnerabilities/gather_data_sampling + /sys/devices/system/cpu/vulnerabilities/indirect_target_selection /sys/devices/system/cpu/vulnerabilities/itlb_multihit /sys/devices/system/cpu/vulnerabilities/l1tf /sys/devices/system/cpu/vulnerabilities/mds diff --git a/Documentation/admin-guide/hw-vuln/index.rst b/Documentation/admin-guide/hw-vuln/index.rst index 451874b8135d..ce296b8430fc 100644 --- a/Documentation/admin-guide/hw-vuln/index.rst +++ b/Documentation/admin-guide/hw-vuln/index.rst @@ -23,3 +23,4 @@ are configurable at compile, boot or run time. gather_data_sampling reg-file-data-sampling rsb + indirect-target-selection diff --git a/Documentation/admin-guide/hw-vuln/indirect-target-selection.rst b/Documentation/admin-guide/hw-vuln/indirect-target-selection.rst new file mode 100644 index 000000000000..d9ca64108d23 --- /dev/null +++ b/Documentation/admin-guide/hw-vuln/indirect-target-selection.rst @@ -0,0 +1,168 @@ +.. SPDX-License-Identifier: GPL-2.0 + +Indirect Target Selection (ITS) +=============================== + +ITS is a vulnerability in some Intel CPUs that support Enhanced IBRS and were +released before Alder Lake. ITS may allow an attacker to control the prediction +of indirect branches and RETs located in the lower half of a cacheline. + +ITS is assigned CVE-2024-28956 with a CVSS score of 4.7 (Medium). + +Scope of Impact +--------------- +- **eIBRS Guest/Host Isolation**: Indirect branches in KVM/kernel may still be + predicted with unintended target corresponding to a branch in the guest. + +- **Intra-Mode BTI**: In-kernel training such as through cBPF or other native + gadgets. + +- **Indirect Branch Prediction Barrier (IBPB)**: After an IBPB, indirect + branches may still be predicted with targets corresponding to direct branches + executed prior to the IBPB. This is fixed by the IPU 2025.1 microcode, which + should be available via distro updates. Alternatively microcode can be + obtained from Intel's github repository [#f1]_. + +Affected CPUs +------------- +Below is the list of ITS affected CPUs [#f2]_ [#f3]_: + + ======================== ============ ==================== =============== + Common name Family_Model eIBRS Intra-mode BTI + Guest/Host Isolation + ======================== ============ ==================== =============== + SKYLAKE_X (step >= 6) 06_55H Affected Affected + ICELAKE_X 06_6AH Not affected Affected + ICELAKE_D 06_6CH Not affected Affected + ICELAKE_L 06_7EH Not affected Affected + TIGERLAKE_L 06_8CH Not affected Affected + TIGERLAKE 06_8DH Not affected Affected + KABYLAKE_L (step >= 12) 06_8EH Affected Affected + KABYLAKE (step >= 13) 06_9EH Affected Affected + COMETLAKE 06_A5H Affected Affected + COMETLAKE_L 06_A6H Affected Affected + ROCKETLAKE 06_A7H Not affected Affected + ======================== ============ ==================== =============== + +- All affected CPUs enumerate Enhanced IBRS feature. +- IBPB isolation is affected on all ITS affected CPUs, and need a microcode + update for mitigation. +- None of the affected CPUs enumerate BHI_CTRL which was introduced in Golden + Cove (Alder Lake and Sapphire Rapids). This can help guests to determine the + host's affected status. +- Intel Atom CPUs are not affected by ITS. + +Mitigation +---------- +As only the indirect branches and RETs that have their last byte of instruction +in the lower half of the cacheline are vulnerable to ITS, the basic idea behind +the mitigation is to not allow indirect branches in the lower half. + +This is achieved by relying on existing retpoline support in the kernel, and in +compilers. ITS-vulnerable retpoline sites are runtime patched to point to newly +added ITS-safe thunks. These safe thunks consists of indirect branch in the +second half of the cacheline. Not all retpoline sites are patched to thunks, if +a retpoline site is evaluated to be ITS-safe, it is replaced with an inline +indirect branch. + +Dynamic thunks +~~~~~~~~~~~~~~ +From a dynamically allocated pool of safe-thunks, each vulnerable site is +replaced with a new thunk, such that they get a unique address. This could +improve the branch prediction accuracy. Also, it is a defense-in-depth measure +against aliasing. + +Note, for simplicity, indirect branches in eBPF programs are always replaced +with a jump to a static thunk in __x86_indirect_its_thunk_array. If required, +in future this can be changed to use dynamic thunks. + +All vulnerable RETs are replaced with a static thunk, they do not use dynamic +thunks. This is because RETs get their prediction from RSB mostly that does not +depend on source address. RETs that underflow RSB may benefit from dynamic +thunks. But, RETs significantly outnumber indirect branches, and any benefit +from a unique source address could be outweighed by the increased icache +footprint and iTLB pressure. + +Retpoline +~~~~~~~~~ +Retpoline sequence also mitigates ITS-unsafe indirect branches. For this +reason, when retpoline is enabled, ITS mitigation only relocates the RETs to +safe thunks. Unless user requested the RSB-stuffing mitigation. + +RSB Stuffing +~~~~~~~~~~~~ +RSB-stuffing via Call Depth Tracking is a mitigation for Retbleed RSB-underflow +attacks. And it also mitigates RETs that are vulnerable to ITS. + +Mitigation in guests +^^^^^^^^^^^^^^^^^^^^ +All guests deploy ITS mitigation by default, irrespective of eIBRS enumeration +and Family/Model of the guest. This is because eIBRS feature could be hidden +from a guest. One exception to this is when a guest enumerates BHI_DIS_S, which +indicates that the guest is running on an unaffected host. + +To prevent guests from unnecessarily deploying the mitigation on unaffected +platforms, Intel has defined ITS_NO bit(62) in MSR IA32_ARCH_CAPABILITIES. When +a guest sees this bit set, it should not enumerate the ITS bug. Note, this bit +is not set by any hardware, but is **intended for VMMs to synthesize** it for +guests as per the host's affected status. + +Mitigation options +^^^^^^^^^^^^^^^^^^ +The ITS mitigation can be controlled using the "indirect_target_selection" +kernel parameter. The available options are: + + ======== =================================================================== + on (default) Deploy the "Aligned branch/return thunks" mitigation. + If spectre_v2 mitigation enables retpoline, aligned-thunks are only + deployed for the affected RET instructions. Retpoline mitigates + indirect branches. + + off Disable ITS mitigation. + + vmexit Equivalent to "=on" if the CPU is affected by guest/host isolation + part of ITS. Otherwise, mitigation is not deployed. This option is + useful when host userspace is not in the threat model, and only + attacks from guest to host are considered. + + stuff Deploy RSB-fill mitigation when retpoline is also deployed. + Otherwise, deploy the default mitigation. When retpoline mitigation + is enabled, RSB-stuffing via Call-Depth-Tracking also mitigates + ITS. + + force Force the ITS bug and deploy the default mitigation. + ======== =================================================================== + +Sysfs reporting +--------------- + +The sysfs file showing ITS mitigation status is: + + /sys/devices/system/cpu/vulnerabilities/indirect_target_selection + +Note, microcode mitigation status is not reported in this file. + +The possible values in this file are: + +.. list-table:: + + * - Not affected + - The processor is not vulnerable. + * - Vulnerable + - System is vulnerable and no mitigation has been applied. + * - Vulnerable, KVM: Not affected + - System is vulnerable to intra-mode BTI, but not affected by eIBRS + guest/host isolation. + * - Mitigation: Aligned branch/return thunks + - The mitigation is enabled, affected indirect branches and RETs are + relocated to safe thunks. + * - Mitigation: Retpolines, Stuffing RSB + - The mitigation is enabled using retpoline and RSB stuffing. + +References +---------- +.. [#f1] Microcode repository - https://github.com/intel/Intel-Linux-Processor-Microcode-Data-Files + +.. [#f2] Affected Processors list - https://www.intel.com/content/www/us/en/developer/topic-technology/software-security-guidance/processors-affected-consolidated-product-cpu-model.html + +.. [#f3] Affected Processors list (machine readable) - https://github.com/intel/Intel-affected-processor-list diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index d9fd26b95b34..8f75ec177399 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -2202,6 +2202,23 @@ different crypto accelerators. This option can be used to achieve best performance for particular HW. + indirect_target_selection= [X86,Intel] Mitigation control for Indirect + Target Selection(ITS) bug in Intel CPUs. Updated + microcode is also required for a fix in IBPB. + + on: Enable mitigation (default). + off: Disable mitigation. + force: Force the ITS bug and deploy default + mitigation. + vmexit: Only deploy mitigation if CPU is affected by + guest/host isolation part of ITS. + stuff: Deploy RSB-fill mitigation when retpoline is + also deployed. Otherwise, deploy the default + mitigation. + + For details see: + Documentation/admin-guide/hw-vuln/indirect-target-selection.rst + init= [KNL] Format: <full_path> Run specified binary instead of /sbin/init as init @@ -3693,6 +3710,7 @@ expose users to several CPU vulnerabilities. Equivalent to: if nokaslr then kpti=0 [ARM64] gather_data_sampling=off [X86] + indirect_target_selection=off [X86] kvm.nx_huge_pages=off [X86] l1tf=off [X86] mds=off [X86] diff --git a/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml b/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml index 517a4ac1bea3..e365413732e7 100644 --- a/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml +++ b/Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml @@ -7,7 +7,7 @@ $schema: http://devicetree.org/meta-schemas/core.yaml# title: Mediatek's Keypad Controller maintainers: - - Mattijs Korpershoek <mkorpershoek@baylibre.com> + - Mattijs Korpershoek <mkorpershoek@kernel.org> allOf: - $ref: /schemas/input/matrix-keymap.yaml# diff --git a/MAINTAINERS b/MAINTAINERS index 183083ead1da..f21f1dabb5fe 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11237,7 +11237,6 @@ S: Maintained F: drivers/i2c/busses/i2c-cht-wc.c I2C/SMBUS ISMT DRIVER -M: Seth Heasley <seth.heasley@intel.com> M: Neil Horman <nhorman@tuxdriver.com> L: linux-i2c@vger.kernel.org F: Documentation/i2c/busses/i2c-ismt.rst @@ -15073,7 +15072,7 @@ F: Documentation/devicetree/bindings/media/mediatek-jpeg-*.yaml F: drivers/media/platform/mediatek/jpeg/ MEDIATEK KEYPAD DRIVER -M: Mattijs Korpershoek <mkorpershoek@baylibre.com> +M: Mattijs Korpershoek <mkorpershoek@kernel.org> S: Supported F: Documentation/devicetree/bindings/input/mediatek,mt6779-keypad.yaml F: drivers/input/keyboard/mt6779-keypad.c @@ -15496,24 +15495,45 @@ F: Documentation/mm/ F: include/linux/gfp.h F: include/linux/gfp_types.h F: include/linux/memfd.h -F: include/linux/memory.h F: include/linux/memory_hotplug.h F: include/linux/memory-tiers.h F: include/linux/mempolicy.h F: include/linux/mempool.h F: include/linux/memremap.h -F: include/linux/mm.h -F: include/linux/mm_*.h F: include/linux/mmzone.h F: include/linux/mmu_notifier.h F: include/linux/pagewalk.h -F: include/linux/rmap.h F: include/trace/events/ksm.h F: mm/ F: tools/mm/ F: tools/testing/selftests/mm/ N: include/linux/page[-_]* +MEMORY MANAGEMENT - CORE +M: Andrew Morton <akpm@linux-foundation.org> +M: David Hildenbrand <david@redhat.com> +R: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> +R: Liam R. Howlett <Liam.Howlett@oracle.com> +R: Vlastimil Babka <vbabka@suse.cz> +R: Mike Rapoport <rppt@kernel.org> +R: Suren Baghdasaryan <surenb@google.com> +R: Michal Hocko <mhocko@suse.com> +L: linux-mm@kvack.org +S: Maintained +W: http://www.linux-mm.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm +F: include/linux/memory.h +F: include/linux/mm.h +F: include/linux/mm_*.h +F: include/linux/mmdebug.h +F: include/linux/pagewalk.h +F: mm/Kconfig +F: mm/debug.c +F: mm/init-mm.c +F: mm/memory.c +F: mm/pagewalk.c +F: mm/util.c + MEMORY MANAGEMENT - EXECMEM M: Andrew Morton <akpm@linux-foundation.org> M: Mike Rapoport <rppt@kernel.org> @@ -15547,6 +15567,19 @@ F: mm/page_alloc.c F: include/linux/gfp.h F: include/linux/compaction.h +MEMORY MANAGEMENT - RMAP (REVERSE MAPPING) +M: Andrew Morton <akpm@linux-foundation.org> +M: David Hildenbrand <david@redhat.com> +M: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> +R: Rik van Riel <riel@surriel.com> +R: Liam R. Howlett <Liam.Howlett@oracle.com> +R: Vlastimil Babka <vbabka@suse.cz> +R: Harry Yoo <harry.yoo@oracle.com> +L: linux-mm@kvack.org +S: Maintained +F: include/linux/rmap.h +F: mm/rmap.c + MEMORY MANAGEMENT - SECRETMEM M: Andrew Morton <akpm@linux-foundation.org> M: Mike Rapoport <rppt@kernel.org> @@ -15555,6 +15588,30 @@ S: Maintained F: include/linux/secretmem.h F: mm/secretmem.c +MEMORY MANAGEMENT - THP (TRANSPARENT HUGE PAGE) +M: Andrew Morton <akpm@linux-foundation.org> +M: David Hildenbrand <david@redhat.com> +R: Zi Yan <ziy@nvidia.com> +R: Baolin Wang <baolin.wang@linux.alibaba.com> +R: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> +R: Liam R. Howlett <Liam.Howlett@oracle.com> +R: Nico Pache <npache@redhat.com> +R: Ryan Roberts <ryan.roberts@arm.com> +R: Dev Jain <dev.jain@arm.com> +L: linux-mm@kvack.org +S: Maintained +W: http://www.linux-mm.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm +F: Documentation/admin-guide/mm/transhuge.rst +F: include/linux/huge_mm.h +F: include/linux/khugepaged.h +F: include/trace/events/huge_memory.h +F: mm/huge_memory.c +F: mm/khugepaged.c +F: tools/testing/selftests/mm/khugepaged.c +F: tools/testing/selftests/mm/split_huge_page_test.c +F: tools/testing/selftests/mm/transhuge-stress.c + MEMORY MANAGEMENT - USERFAULTFD M: Andrew Morton <akpm@linux-foundation.org> R: Peter Xu <peterx@redhat.com> @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 15 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc6 NAME = Baby Opossum Posse # *DOCUMENTATION* diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index d1cc0571798b..dffff6763812 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -81,6 +81,7 @@ #define ARM_CPU_PART_CORTEX_A78AE 0xD42 #define ARM_CPU_PART_CORTEX_X1 0xD44 #define ARM_CPU_PART_CORTEX_A510 0xD46 +#define ARM_CPU_PART_CORTEX_X1C 0xD4C #define ARM_CPU_PART_CORTEX_A520 0xD80 #define ARM_CPU_PART_CORTEX_A710 0xD47 #define ARM_CPU_PART_CORTEX_A715 0xD4D @@ -168,6 +169,7 @@ #define MIDR_CORTEX_A78AE MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE) #define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1) #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510) +#define MIDR_CORTEX_X1C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1C) #define MIDR_CORTEX_A520 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A520) #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710) #define MIDR_CORTEX_A715 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A715) diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h index ebceaae3c749..d40e427ddad9 100644 --- a/arch/arm64/include/asm/el2_setup.h +++ b/arch/arm64/include/asm/el2_setup.h @@ -52,7 +52,7 @@ mrs x0, id_aa64mmfr1_el1 ubfx x0, x0, #ID_AA64MMFR1_EL1_HCX_SHIFT, #4 cbz x0, .Lskip_hcrx_\@ - mov_q x0, HCRX_HOST_FLAGS + mov_q x0, (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En | HCRX_EL2_EnFPM) /* Enable GCS if supported */ mrs_s x1, SYS_ID_AA64PFR1_EL1 diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 39577f1d079a..18c7811774d3 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -706,6 +706,7 @@ u32 aarch64_insn_gen_cas(enum aarch64_insn_register result, } #endif u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type); +u32 aarch64_insn_gen_dsb(enum aarch64_insn_mb_type type); u32 aarch64_insn_gen_mrs(enum aarch64_insn_register result, enum aarch64_insn_system_register sysreg); diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 974d72b5905b..e9c8a581e16f 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -100,9 +100,8 @@ HCR_FMO | HCR_IMO | HCR_PTW | HCR_TID3 | HCR_TID1) #define HCR_HOST_NVHE_FLAGS (HCR_RW | HCR_API | HCR_APK | HCR_ATA) #define HCR_HOST_NVHE_PROTECTED_FLAGS (HCR_HOST_NVHE_FLAGS | HCR_TSC) -#define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H) +#define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H | HCR_AMO | HCR_IMO | HCR_FMO) -#define HCRX_HOST_FLAGS (HCRX_EL2_MSCEn | HCRX_EL2_TCR2En | HCRX_EL2_EnFPM) #define MPAMHCR_HOST_FLAGS 0 /* TCR_EL2 Registers bits */ diff --git a/arch/arm64/include/asm/spectre.h b/arch/arm64/include/asm/spectre.h index f1524cdeacf1..8fef12626090 100644 --- a/arch/arm64/include/asm/spectre.h +++ b/arch/arm64/include/asm/spectre.h @@ -97,6 +97,9 @@ enum mitigation_state arm64_get_meltdown_state(void); enum mitigation_state arm64_get_spectre_bhb_state(void); bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry, int scope); +extern bool __nospectre_bhb; +u8 get_spectre_bhb_loop_value(void); +bool is_spectre_bhb_fw_mitigated(void); void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *__unused); bool try_emulate_el1_ssbs(struct pt_regs *regs, u32 instr); diff --git a/arch/arm64/include/asm/vdso/gettimeofday.h b/arch/arm64/include/asm/vdso/gettimeofday.h index 92a2b59a9f3d..3322c7047d84 100644 --- a/arch/arm64/include/asm/vdso/gettimeofday.h +++ b/arch/arm64/include/asm/vdso/gettimeofday.h @@ -99,6 +99,19 @@ static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, return res; } +#if IS_ENABLED(CONFIG_CC_IS_GCC) && IS_ENABLED(CONFIG_PAGE_SIZE_64KB) +static __always_inline const struct vdso_time_data *__arch_get_vdso_u_time_data(void) +{ + const struct vdso_time_data *ret = &vdso_u_time_data; + + /* Work around invalid absolute relocations */ + OPTIMIZER_HIDE_VAR(ret); + + return ret; +} +#define __arch_get_vdso_u_time_data __arch_get_vdso_u_time_data +#endif /* IS_ENABLED(CONFIG_CC_IS_GCC) && IS_ENABLED(CONFIG_PAGE_SIZE_64KB) */ + #endif /* !__ASSEMBLY__ */ #endif /* __ASM_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index b607f6dfc5e6..edf1783ffc81 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -891,6 +891,7 @@ static u8 spectre_bhb_loop_affected(void) MIDR_ALL_VERSIONS(MIDR_CORTEX_A78AE), MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C), MIDR_ALL_VERSIONS(MIDR_CORTEX_X1), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X1C), MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), MIDR_ALL_VERSIONS(MIDR_CORTEX_X2), MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), @@ -999,6 +1000,11 @@ bool is_spectre_bhb_affected(const struct arm64_cpu_capabilities *entry, return true; } +u8 get_spectre_bhb_loop_value(void) +{ + return max_bhb_k; +} + static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot) { const char *v = arm64_get_bp_hardening_vector(slot); @@ -1016,7 +1022,7 @@ static void this_cpu_set_vectors(enum arm64_bp_harden_el1_vectors slot) isb(); } -static bool __read_mostly __nospectre_bhb; +bool __read_mostly __nospectre_bhb; static int __init parse_spectre_bhb_param(char *str) { __nospectre_bhb = true; @@ -1094,6 +1100,11 @@ void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry) update_mitigation_state(&spectre_bhb_state, state); } +bool is_spectre_bhb_fw_mitigated(void) +{ + return test_bit(BHB_FW, &system_bhb_mitigations); +} + /* Patched to NOP when enabled */ void noinstr spectre_bhb_patch_loop_mitigation_enable(struct alt_instr *alt, __le32 *origptr, diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index b741ea6aefa5..96f625dc7256 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -235,6 +235,8 @@ static inline void __deactivate_traps_mpam(void) static inline void __activate_traps_common(struct kvm_vcpu *vcpu) { + struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt); + /* Trap on AArch32 cp15 c15 (impdef sysregs) accesses (EL1 or EL0) */ write_sysreg(1 << 15, hstr_el2); @@ -245,11 +247,8 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu) * EL1 instead of being trapped to EL2. */ if (system_supports_pmuv3()) { - struct kvm_cpu_context *hctxt; - write_sysreg(0, pmselr_el0); - hctxt = host_data_ptr(host_ctxt); ctxt_sys_reg(hctxt, PMUSERENR_EL0) = read_sysreg(pmuserenr_el0); write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0); vcpu_set_flag(vcpu, PMUSERENR_ON_CPU); @@ -269,6 +268,7 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu) hcrx &= ~clr; } + ctxt_sys_reg(hctxt, HCRX_EL2) = read_sysreg_s(SYS_HCRX_EL2); write_sysreg_s(hcrx, SYS_HCRX_EL2); } @@ -278,19 +278,18 @@ static inline void __activate_traps_common(struct kvm_vcpu *vcpu) static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu) { + struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt); + write_sysreg(*host_data_ptr(host_debug_state.mdcr_el2), mdcr_el2); write_sysreg(0, hstr_el2); if (system_supports_pmuv3()) { - struct kvm_cpu_context *hctxt; - - hctxt = host_data_ptr(host_ctxt); write_sysreg(ctxt_sys_reg(hctxt, PMUSERENR_EL0), pmuserenr_el0); vcpu_clear_flag(vcpu, PMUSERENR_ON_CPU); } if (cpus_have_final_cap(ARM64_HAS_HCX)) - write_sysreg_s(HCRX_HOST_FLAGS, SYS_HCRX_EL2); + write_sysreg_s(ctxt_sys_reg(hctxt, HCRX_EL2), SYS_HCRX_EL2); __deactivate_traps_hfgxtr(vcpu); __deactivate_traps_mpam(); diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 2a5284f749b4..e80f3ebd3e2a 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -503,7 +503,7 @@ int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id) { int ret; - if (!addr_is_memory(addr)) + if (!range_is_memory(addr, addr + size)) return -EPERM; ret = host_stage2_try(kvm_pgtable_stage2_set_owner, &host_mmu.pgt, diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c index ed363aa3027e..50aa8dbcae75 100644 --- a/arch/arm64/kvm/hyp/vgic-v3-sr.c +++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c @@ -429,23 +429,27 @@ u64 __vgic_v3_get_gic_config(void) /* * To check whether we have a MMIO-based (GICv2 compatible) * CPU interface, we need to disable the system register - * view. To do that safely, we have to prevent any interrupt - * from firing (which would be deadly). + * view. * - * Note that this only makes sense on VHE, as interrupts are - * already masked for nVHE as part of the exception entry to - * EL2. - */ - if (has_vhe()) - flags = local_daif_save(); - - /* * Table 11-2 "Permitted ICC_SRE_ELx.SRE settings" indicates * that to be able to set ICC_SRE_EL1.SRE to 0, all the * interrupt overrides must be set. You've got to love this. + * + * As we always run VHE with HCR_xMO set, no extra xMO + * manipulation is required in that case. + * + * To safely disable SRE, we have to prevent any interrupt + * from firing (which would be deadly). This only makes sense + * on VHE, as interrupts are already masked for nVHE as part + * of the exception entry to EL2. */ - sysreg_clear_set(hcr_el2, 0, HCR_AMO | HCR_FMO | HCR_IMO); - isb(); + if (has_vhe()) { + flags = local_daif_save(); + } else { + sysreg_clear_set(hcr_el2, 0, HCR_AMO | HCR_FMO | HCR_IMO); + isb(); + } + write_gicreg(0, ICC_SRE_EL1); isb(); @@ -453,11 +457,13 @@ u64 __vgic_v3_get_gic_config(void) write_gicreg(sre, ICC_SRE_EL1); isb(); - sysreg_clear_set(hcr_el2, HCR_AMO | HCR_FMO | HCR_IMO, 0); - isb(); - if (has_vhe()) + if (has_vhe()) { local_daif_restore(flags); + } else { + sysreg_clear_set(hcr_el2, HCR_AMO | HCR_FMO | HCR_IMO, 0); + isb(); + } val = (val & ICC_SRE_EL1_SRE) ? 0 : (1ULL << 63); val |= read_gicreg(ICH_VTR_EL2); diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 754f2fe0cc67..eeda92330ade 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1501,6 +1501,11 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, return -EFAULT; } + if (!is_protected_kvm_enabled()) + memcache = &vcpu->arch.mmu_page_cache; + else + memcache = &vcpu->arch.pkvm_memcache; + /* * Permission faults just need to update the existing leaf entry, * and so normally don't require allocations from the memcache. The @@ -1510,13 +1515,11 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa, if (!fault_is_perm || (logging_active && write_fault)) { int min_pages = kvm_mmu_cache_min_pages(vcpu->arch.hw_mmu); - if (!is_protected_kvm_enabled()) { - memcache = &vcpu->arch.mmu_page_cache; + if (!is_protected_kvm_enabled()) ret = kvm_mmu_topup_memory_cache(memcache, min_pages); - } else { - memcache = &vcpu->arch.pkvm_memcache; + else ret = topup_hyp_memcache(memcache, min_pages); - } + if (ret) return ret; } diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 005ad28f7306..5dde9285afc8 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1945,6 +1945,12 @@ static int set_id_aa64pfr0_el1(struct kvm_vcpu *vcpu, if ((hw_val & mpam_mask) == (user_val & mpam_mask)) user_val &= ~ID_AA64PFR0_EL1_MPAM_MASK; + /* Fail the guest's request to disable the AA64 ISA at EL{0,1,2} */ + if (!FIELD_GET(ID_AA64PFR0_EL1_EL0, user_val) || + !FIELD_GET(ID_AA64PFR0_EL1_EL1, user_val) || + (vcpu_has_nv(vcpu) && !FIELD_GET(ID_AA64PFR0_EL1_EL2, user_val))) + return -EINVAL; + return set_id_reg(vcpu, rd, user_val); } diff --git a/arch/arm64/lib/insn.c b/arch/arm64/lib/insn.c index 9bef696e2230..4e298baddc2e 100644 --- a/arch/arm64/lib/insn.c +++ b/arch/arm64/lib/insn.c @@ -5,6 +5,7 @@ * * Copyright (C) 2014-2016 Zi Shen Lim <zlim.lnx@gmail.com> */ +#include <linux/bitfield.h> #include <linux/bitops.h> #include <linux/bug.h> #include <linux/printk.h> @@ -1500,43 +1501,41 @@ u32 aarch64_insn_gen_extr(enum aarch64_insn_variant variant, return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RM, insn, Rm); } -u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type) +static u32 __get_barrier_crm_val(enum aarch64_insn_mb_type type) { - u32 opt; - u32 insn; - switch (type) { case AARCH64_INSN_MB_SY: - opt = 0xf; - break; + return 0xf; case AARCH64_INSN_MB_ST: - opt = 0xe; - break; + return 0xe; case AARCH64_INSN_MB_LD: - opt = 0xd; - break; + return 0xd; case AARCH64_INSN_MB_ISH: - opt = 0xb; - break; + return 0xb; case AARCH64_INSN_MB_ISHST: - opt = 0xa; - break; + return 0xa; case AARCH64_INSN_MB_ISHLD: - opt = 0x9; - break; + return 0x9; case AARCH64_INSN_MB_NSH: - opt = 0x7; - break; + return 0x7; case AARCH64_INSN_MB_NSHST: - opt = 0x6; - break; + return 0x6; case AARCH64_INSN_MB_NSHLD: - opt = 0x5; - break; + return 0x5; default: - pr_err("%s: unknown dmb type %d\n", __func__, type); + pr_err("%s: unknown barrier type %d\n", __func__, type); return AARCH64_BREAK_FAULT; } +} + +u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type) +{ + u32 opt; + u32 insn; + + opt = __get_barrier_crm_val(type); + if (opt == AARCH64_BREAK_FAULT) + return AARCH64_BREAK_FAULT; insn = aarch64_insn_get_dmb_value(); insn &= ~GENMASK(11, 8); @@ -1545,6 +1544,21 @@ u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type) return insn; } +u32 aarch64_insn_gen_dsb(enum aarch64_insn_mb_type type) +{ + u32 opt, insn; + + opt = __get_barrier_crm_val(type); + if (opt == AARCH64_BREAK_FAULT) + return AARCH64_BREAK_FAULT; + + insn = aarch64_insn_get_dsb_base_value(); + insn &= ~GENMASK(11, 8); + insn |= (opt << 8); + + return insn; +} + u32 aarch64_insn_gen_mrs(enum aarch64_insn_register result, enum aarch64_insn_system_register sysreg) { diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 70d7c89d3ac9..634d78422adb 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -7,6 +7,7 @@ #define pr_fmt(fmt) "bpf_jit: " fmt +#include <linux/arm-smccc.h> #include <linux/bitfield.h> #include <linux/bpf.h> #include <linux/filter.h> @@ -17,6 +18,7 @@ #include <asm/asm-extable.h> #include <asm/byteorder.h> #include <asm/cacheflush.h> +#include <asm/cpufeature.h> #include <asm/debug-monitors.h> #include <asm/insn.h> #include <asm/text-patching.h> @@ -939,7 +941,51 @@ static void build_plt(struct jit_ctx *ctx) plt->target = (u64)&dummy_tramp; } -static void build_epilogue(struct jit_ctx *ctx) +/* Clobbers BPF registers 1-4, aka x0-x3 */ +static void __maybe_unused build_bhb_mitigation(struct jit_ctx *ctx) +{ + const u8 r1 = bpf2a64[BPF_REG_1]; /* aka x0 */ + u8 k = get_spectre_bhb_loop_value(); + + if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY) || + cpu_mitigations_off() || __nospectre_bhb || + arm64_get_spectre_v2_state() == SPECTRE_VULNERABLE) + return; + + if (capable(CAP_SYS_ADMIN)) + return; + + if (supports_clearbhb(SCOPE_SYSTEM)) { + emit(aarch64_insn_gen_hint(AARCH64_INSN_HINT_CLEARBHB), ctx); + return; + } + + if (k) { + emit_a64_mov_i64(r1, k, ctx); + emit(A64_B(1), ctx); + emit(A64_SUBS_I(true, r1, r1, 1), ctx); + emit(A64_B_(A64_COND_NE, -2), ctx); + emit(aarch64_insn_gen_dsb(AARCH64_INSN_MB_ISH), ctx); + emit(aarch64_insn_get_isb_value(), ctx); + } + + if (is_spectre_bhb_fw_mitigated()) { + emit(A64_ORR_I(false, r1, AARCH64_INSN_REG_ZR, + ARM_SMCCC_ARCH_WORKAROUND_3), ctx); + switch (arm_smccc_1_1_get_conduit()) { + case SMCCC_CONDUIT_HVC: + emit(aarch64_insn_get_hvc_value(), ctx); + break; + case SMCCC_CONDUIT_SMC: + emit(aarch64_insn_get_smc_value(), ctx); + break; + default: + pr_err_once("Firmware mitigation enabled with unknown conduit\n"); + } + } +} + +static void build_epilogue(struct jit_ctx *ctx, bool was_classic) { const u8 r0 = bpf2a64[BPF_REG_0]; const u8 ptr = bpf2a64[TCCNT_PTR]; @@ -952,10 +998,13 @@ static void build_epilogue(struct jit_ctx *ctx) emit(A64_POP(A64_ZR, ptr, A64_SP), ctx); + if (was_classic) + build_bhb_mitigation(ctx); + /* Restore FP/LR registers */ emit(A64_POP(A64_FP, A64_LR, A64_SP), ctx); - /* Set return value */ + /* Move the return value from bpf:r0 (aka x7) to x0 */ emit(A64_MOV(1, A64_R(0), r0), ctx); /* Authenticate lr */ @@ -1898,7 +1947,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) } ctx.epilogue_offset = ctx.idx; - build_epilogue(&ctx); + build_epilogue(&ctx, was_classic); build_plt(&ctx); extable_align = __alignof__(struct exception_table_entry); @@ -1961,7 +2010,7 @@ skip_init_ctx: goto out_free_hdr; } - build_epilogue(&ctx); + build_epilogue(&ctx, was_classic); build_plt(&ctx); /* Extra pass to validate JITed code. */ diff --git a/arch/mips/include/asm/idle.h b/arch/mips/include/asm/idle.h index 0992cad9c632..c7d75807d13f 100644 --- a/arch/mips/include/asm/idle.h +++ b/arch/mips/include/asm/idle.h @@ -6,11 +6,10 @@ #include <linux/linkage.h> extern void (*cpu_wait)(void); -extern void r4k_wait(void); -extern asmlinkage void __r4k_wait(void); +extern asmlinkage void r4k_wait(void); extern void r4k_wait_irqoff(void); -static inline int using_rollback_handler(void) +static inline int using_skipover_handler(void) { return cpu_wait == r4k_wait; } diff --git a/arch/mips/include/asm/ptrace.h b/arch/mips/include/asm/ptrace.h index 85fa9962266a..ef72c46b5568 100644 --- a/arch/mips/include/asm/ptrace.h +++ b/arch/mips/include/asm/ptrace.h @@ -65,7 +65,8 @@ static inline void instruction_pointer_set(struct pt_regs *regs, /* Query offset/name of register from its name/offset */ extern int regs_query_register_offset(const char *name); -#define MAX_REG_OFFSET (offsetof(struct pt_regs, __last)) +#define MAX_REG_OFFSET \ + (offsetof(struct pt_regs, __last) - sizeof(unsigned long)) /** * regs_get_register() - get register value from its offset diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S index a572ce36a24f..08c0a01d9a29 100644 --- a/arch/mips/kernel/genex.S +++ b/arch/mips/kernel/genex.S @@ -104,48 +104,59 @@ handle_vcei: __FINIT - .align 5 /* 32 byte rollback region */ -LEAF(__r4k_wait) - .set push - .set noreorder - /* start of rollback region */ - LONG_L t0, TI_FLAGS($28) - nop - andi t0, _TIF_NEED_RESCHED - bnez t0, 1f - nop - nop - nop -#ifdef CONFIG_CPU_MICROMIPS - nop - nop - nop - nop -#endif + .section .cpuidle.text,"ax" + /* Align to 32 bytes for the maximum idle interrupt region size. */ + .align 5 +LEAF(r4k_wait) + /* Keep the ISA bit clear for calculations on local labels here. */ +0: .fill 0 + /* Start of idle interrupt region. */ + local_irq_enable + /* + * If an interrupt lands here, before going idle on the next + * instruction, we must *NOT* go idle since the interrupt could + * have set TIF_NEED_RESCHED or caused a timer to need resched. + * Fall through -- see skipover_handler below -- and have the + * idle loop take care of things. + */ +1: .fill 0 + /* The R2 EI/EHB sequence takes 8 bytes, otherwise pad up. */ + .if 1b - 0b > 32 + .error "overlong idle interrupt region" + .elseif 1b - 0b > 8 + .align 4 + .endif +2: .fill 0 + .equ r4k_wait_idle_size, 2b - 0b + /* End of idle interrupt region; size has to be a power of 2. */ .set MIPS_ISA_ARCH_LEVEL_RAW +r4k_wait_insn: wait - /* end of rollback region (the region size must be power of two) */ -1: +r4k_wait_exit: + .set mips0 + local_irq_disable jr ra - nop - .set pop - END(__r4k_wait) + END(r4k_wait) + .previous - .macro BUILD_ROLLBACK_PROLOGUE handler - FEXPORT(rollback_\handler) + .macro BUILD_SKIPOVER_PROLOGUE handler + FEXPORT(skipover_\handler) .set push .set noat MFC0 k0, CP0_EPC - PTR_LA k1, __r4k_wait - ori k0, 0x1f /* 32 byte rollback region */ - xori k0, 0x1f + /* Subtract/add 2 to let the ISA bit propagate through the mask. */ + PTR_LA k1, r4k_wait_insn - 2 + ori k0, r4k_wait_idle_size - 2 + .set noreorder bne k0, k1, \handler + PTR_ADDIU k0, r4k_wait_exit - r4k_wait_insn + 2 + .set reorder MTC0 k0, CP0_EPC .set pop .endm .align 5 -BUILD_ROLLBACK_PROLOGUE handle_int +BUILD_SKIPOVER_PROLOGUE handle_int NESTED(handle_int, PT_SIZE, sp) .cfi_signal_frame #ifdef CONFIG_TRACE_IRQFLAGS @@ -265,7 +276,7 @@ NESTED(except_vec_ejtag_debug, 0, sp) * This prototype is copied to ebase + n*IntCtl.VS and patched * to invoke the handler */ -BUILD_ROLLBACK_PROLOGUE except_vec_vi +BUILD_SKIPOVER_PROLOGUE except_vec_vi NESTED(except_vec_vi, 0, sp) SAVE_SOME docfi=1 SAVE_AT docfi=1 diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c index 5abc8b7340f8..80e8a04a642e 100644 --- a/arch/mips/kernel/idle.c +++ b/arch/mips/kernel/idle.c @@ -35,13 +35,6 @@ static void __cpuidle r3081_wait(void) write_c0_conf(cfg | R30XX_CONF_HALT); } -void __cpuidle r4k_wait(void) -{ - raw_local_irq_enable(); - __r4k_wait(); - raw_local_irq_disable(); -} - /* * This variant is preferable as it allows testing need_resched and going to * sleep depending on the outcome atomically. Unfortunately the "It is diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index e85bd087467e..cc26d56f3ab6 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -332,6 +332,8 @@ static void __init cps_prepare_cpus(unsigned int max_cpus) mips_cps_cluster_bootcfg = kcalloc(nclusters, sizeof(*mips_cps_cluster_bootcfg), GFP_KERNEL); + if (!mips_cps_cluster_bootcfg) + goto err_out; if (nclusters > 1) mips_cm_update_property(); @@ -348,6 +350,8 @@ static void __init cps_prepare_cpus(unsigned int max_cpus) mips_cps_cluster_bootcfg[cl].core_power = kcalloc(BITS_TO_LONGS(ncores), sizeof(unsigned long), GFP_KERNEL); + if (!mips_cps_cluster_bootcfg[cl].core_power) + goto err_out; /* Allocate VPE boot configuration structs */ for (c = 0; c < ncores; c++) { diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 39e248d0ed59..8ec1e185b35c 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -77,7 +77,7 @@ #include "access-helper.h" extern void check_wait(void); -extern asmlinkage void rollback_handle_int(void); +extern asmlinkage void skipover_handle_int(void); extern asmlinkage void handle_int(void); extern asmlinkage void handle_adel(void); extern asmlinkage void handle_ades(void); @@ -2066,7 +2066,7 @@ void *set_vi_handler(int n, vi_handler_t addr) { extern const u8 except_vec_vi[]; extern const u8 except_vec_vi_ori[], except_vec_vi_end[]; - extern const u8 rollback_except_vec_vi[]; + extern const u8 skipover_except_vec_vi[]; unsigned long handler; unsigned long old_handler = vi_handlers[n]; int srssets = current_cpu_data.srsets; @@ -2095,7 +2095,7 @@ void *set_vi_handler(int n, vi_handler_t addr) change_c0_srsmap(0xf << n*4, 0 << n*4); } - vec_start = using_rollback_handler() ? rollback_except_vec_vi : + vec_start = using_skipover_handler() ? skipover_except_vec_vi : except_vec_vi; #if defined(CONFIG_CPU_MICROMIPS) || defined(CONFIG_CPU_BIG_ENDIAN) ori_offset = except_vec_vi_ori - vec_start + 2; @@ -2426,8 +2426,8 @@ void __init trap_init(void) if (board_be_init) board_be_init(); - set_except_vector(EXCCODE_INT, using_rollback_handler() ? - rollback_handle_int : handle_int); + set_except_vector(EXCCODE_INT, using_skipover_handler() ? + skipover_handle_int : handle_int); set_except_vector(EXCCODE_MOD, handle_tlbm); set_except_vector(EXCCODE_TLBL, handle_tlbl); set_except_vector(EXCCODE_TLBS, handle_tlbs); diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 60d684c76c58..02635bac91f1 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -77,6 +77,8 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu) memcpy(cntx, reset_cntx, sizeof(*cntx)); spin_unlock(&vcpu->arch.reset_cntx_lock); + memset(&vcpu->arch.smstateen_csr, 0, sizeof(vcpu->arch.smstateen_csr)); + kvm_riscv_vcpu_fp_reset(vcpu); kvm_riscv_vcpu_vector_reset(vcpu); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 5873c9e39919..e21cca404943 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2711,6 +2711,18 @@ config MITIGATION_SSB of speculative execution in a similar way to the Meltdown and Spectre security vulnerabilities. +config MITIGATION_ITS + bool "Enable Indirect Target Selection mitigation" + depends on CPU_SUP_INTEL && X86_64 + depends on MITIGATION_RETPOLINE && MITIGATION_RETHUNK + select EXECMEM + default y + help + Enable Indirect Target Selection (ITS) mitigation. ITS is a bug in + BPU on some Intel CPUs that may allow Spectre V2 style attacks. If + disabled, mitigation cannot be enabled via cmdline. + See <file:Documentation/admin-guide/hw-vuln/indirect-target-selection.rst> + endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index f40bdf97d390..ed04a968cc7d 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1525,7 +1525,9 @@ SYM_CODE_END(rewind_stack_and_make_dead) * ORC to unwind properly. * * The alignment is for performance and not for safety, and may be safely - * refactored in the future if needed. + * refactored in the future if needed. The .skips are for safety, to ensure + * that all RETs are in the second half of a cacheline to mitigate Indirect + * Target Selection, rather than taking the slowpath via its_return_thunk. */ SYM_FUNC_START(clear_bhb_loop) ANNOTATE_NOENDBR @@ -1536,10 +1538,22 @@ SYM_FUNC_START(clear_bhb_loop) call 1f jmp 5f .align 64, 0xcc + /* + * Shift instructions so that the RET is in the upper half of the + * cacheline and don't take the slowpath to its_return_thunk. + */ + .skip 32 - (.Lret1 - 1f), 0xcc ANNOTATE_INTRA_FUNCTION_CALL 1: call 2f - RET +.Lret1: RET .align 64, 0xcc + /* + * As above shift instructions for RET at .Lret2 as well. + * + * This should be ideally be: .skip 32 - (.Lret2 - 2f), 0xcc + * but some Clang versions (e.g. 18) don't like this. + */ + .skip 32 - 18, 0xcc 2: movl $5, %eax 3: jmp 4f nop @@ -1547,7 +1561,7 @@ SYM_FUNC_START(clear_bhb_loop) jnz 3b sub $1, %ecx jnz 1b - RET +.Lret2: RET 5: lfence pop %rbp RET diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 4a37a8bd87fd..f2294784babc 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -6,6 +6,7 @@ #include <linux/stringify.h> #include <linux/objtool.h> #include <asm/asm.h> +#include <asm/bug.h> #define ALT_FLAGS_SHIFT 16 @@ -124,6 +125,37 @@ static __always_inline int x86_call_depth_emit_accounting(u8 **pprog, } #endif +#ifdef CONFIG_MITIGATION_ITS +extern void its_init_mod(struct module *mod); +extern void its_fini_mod(struct module *mod); +extern void its_free_mod(struct module *mod); +extern u8 *its_static_thunk(int reg); +#else /* CONFIG_MITIGATION_ITS */ +static inline void its_init_mod(struct module *mod) { } +static inline void its_fini_mod(struct module *mod) { } +static inline void its_free_mod(struct module *mod) { } +static inline u8 *its_static_thunk(int reg) +{ + WARN_ONCE(1, "ITS not compiled in"); + + return NULL; +} +#endif + +#if defined(CONFIG_MITIGATION_RETHUNK) && defined(CONFIG_OBJTOOL) +extern bool cpu_wants_rethunk(void); +extern bool cpu_wants_rethunk_at(void *addr); +#else +static __always_inline bool cpu_wants_rethunk(void) +{ + return false; +} +static __always_inline bool cpu_wants_rethunk_at(void *addr) +{ + return false; +} +#endif + #ifdef CONFIG_SMP extern void alternatives_smp_module_add(struct module *mod, char *name, void *locks, void *locks_end, diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 6c2c152d8a67..39e61212ac9a 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -481,6 +481,7 @@ #define X86_FEATURE_AMD_HETEROGENEOUS_CORES (21*32 + 6) /* Heterogeneous Core Topology */ #define X86_FEATURE_AMD_WORKLOAD_CLASS (21*32 + 7) /* Workload Classification */ #define X86_FEATURE_PREFER_YMM (21*32 + 8) /* Avoid ZMM registers due to downclocking */ +#define X86_FEATURE_INDIRECT_THUNK_ITS (21*32 + 9) /* Use thunk for indirect branches in lower half of cacheline */ /* * BUG word(s) @@ -533,4 +534,6 @@ #define X86_BUG_BHI X86_BUG(1*32 + 3) /* "bhi" CPU is affected by Branch History Injection */ #define X86_BUG_IBPB_NO_RET X86_BUG(1*32 + 4) /* "ibpb_no_ret" IBPB omits return target predictions */ #define X86_BUG_SPECTRE_V2_USER X86_BUG(1*32 + 5) /* "spectre_v2_user" CPU is affected by Spectre variant 2 attack between user processes */ +#define X86_BUG_ITS X86_BUG(1*32 + 6) /* "its" CPU is affected by Indirect Target Selection */ +#define X86_BUG_ITS_NATIVE_ONLY X86_BUG(1*32 + 7) /* "its_native_only" CPU is affected by ITS, VMX is not affected */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 695e569159c1..be7cddc414e4 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -17,10 +17,12 @@ struct ucode_cpu_info { void load_ucode_bsp(void); void load_ucode_ap(void); void microcode_bsp_resume(void); +bool __init microcode_loader_disabled(void); #else static inline void load_ucode_bsp(void) { } static inline void load_ucode_ap(void) { } static inline void microcode_bsp_resume(void) { } +static inline bool __init microcode_loader_disabled(void) { return false; } #endif extern unsigned long initrd_start_early; diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index e6134ef2263d..e7d2f460fcc6 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -211,6 +211,14 @@ * VERW clears CPU Register * File. */ +#define ARCH_CAP_ITS_NO BIT_ULL(62) /* + * Not susceptible to + * Indirect Target Selection. + * This bit is not set by + * HW, but is synthesized by + * VMMs for guests to know + * their affected status. + */ #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 5c43f145454d..7d04ade33541 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -336,10 +336,14 @@ #else /* __ASSEMBLER__ */ +#define ITS_THUNK_SIZE 64 + typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; +typedef u8 its_thunk_t[ITS_THUNK_SIZE]; extern retpoline_thunk_t __x86_indirect_thunk_array[]; extern retpoline_thunk_t __x86_indirect_call_thunk_array[]; extern retpoline_thunk_t __x86_indirect_jump_thunk_array[]; +extern its_thunk_t __x86_indirect_its_thunk_array[]; #ifdef CONFIG_MITIGATION_RETHUNK extern void __x86_return_thunk(void); @@ -363,6 +367,12 @@ static inline void srso_return_thunk(void) {} static inline void srso_alias_return_thunk(void) {} #endif +#ifdef CONFIG_MITIGATION_ITS +extern void its_return_thunk(void); +#else +static inline void its_return_thunk(void) {} +#endif + extern void retbleed_return_thunk(void); extern void srso_return_thunk(void); extern void srso_alias_return_thunk(void); diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index bf82c6f7d690..48fd04e90114 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -18,6 +18,7 @@ #include <linux/mmu_context.h> #include <linux/bsearch.h> #include <linux/sync_core.h> +#include <linux/execmem.h> #include <asm/text-patching.h> #include <asm/alternative.h> #include <asm/sections.h> @@ -31,6 +32,8 @@ #include <asm/paravirt.h> #include <asm/asm-prototypes.h> #include <asm/cfi.h> +#include <asm/ibt.h> +#include <asm/set_memory.h> int __read_mostly alternatives_patched; @@ -124,6 +127,165 @@ const unsigned char * const x86_nops[ASM_NOP_MAX+1] = #endif }; +#ifdef CONFIG_FINEIBT +static bool cfi_paranoid __ro_after_init; +#endif + +#ifdef CONFIG_MITIGATION_ITS + +static struct module *its_mod; +static void *its_page; +static unsigned int its_offset; + +/* Initialize a thunk with the "jmp *reg; int3" instructions. */ +static void *its_init_thunk(void *thunk, int reg) +{ + u8 *bytes = thunk; + int offset = 0; + int i = 0; + +#ifdef CONFIG_FINEIBT + if (cfi_paranoid) { + /* + * When ITS uses indirect branch thunk the fineibt_paranoid + * caller sequence doesn't fit in the caller site. So put the + * remaining part of the sequence (<ea> + JNE) into the ITS + * thunk. + */ + bytes[i++] = 0xea; /* invalid instruction */ + bytes[i++] = 0x75; /* JNE */ + bytes[i++] = 0xfd; + + offset = 1; + } +#endif + + if (reg >= 8) { + bytes[i++] = 0x41; /* REX.B prefix */ + reg -= 8; + } + bytes[i++] = 0xff; + bytes[i++] = 0xe0 + reg; /* jmp *reg */ + bytes[i++] = 0xcc; + + return thunk + offset; +} + +void its_init_mod(struct module *mod) +{ + if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) + return; + + mutex_lock(&text_mutex); + its_mod = mod; + its_page = NULL; +} + +void its_fini_mod(struct module *mod) +{ + if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) + return; + + WARN_ON_ONCE(its_mod != mod); + + its_mod = NULL; + its_page = NULL; + mutex_unlock(&text_mutex); + + for (int i = 0; i < mod->its_num_pages; i++) { + void *page = mod->its_page_array[i]; + execmem_restore_rox(page, PAGE_SIZE); + } +} + +void its_free_mod(struct module *mod) +{ + if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) + return; + + for (int i = 0; i < mod->its_num_pages; i++) { + void *page = mod->its_page_array[i]; + execmem_free(page); + } + kfree(mod->its_page_array); +} + +static void *its_alloc(void) +{ + void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE); + + if (!page) + return NULL; + + if (its_mod) { + void *tmp = krealloc(its_mod->its_page_array, + (its_mod->its_num_pages+1) * sizeof(void *), + GFP_KERNEL); + if (!tmp) + return NULL; + + its_mod->its_page_array = tmp; + its_mod->its_page_array[its_mod->its_num_pages++] = page; + + execmem_make_temp_rw(page, PAGE_SIZE); + } + + return no_free_ptr(page); +} + +static void *its_allocate_thunk(int reg) +{ + int size = 3 + (reg / 8); + void *thunk; + +#ifdef CONFIG_FINEIBT + /* + * The ITS thunk contains an indirect jump and an int3 instruction so + * its size is 3 or 4 bytes depending on the register used. If CFI + * paranoid is used then 3 extra bytes are added in the ITS thunk to + * complete the fineibt_paranoid caller sequence. + */ + if (cfi_paranoid) + size += 3; +#endif + + if (!its_page || (its_offset + size - 1) >= PAGE_SIZE) { + its_page = its_alloc(); + if (!its_page) { + pr_err("ITS page allocation failed\n"); + return NULL; + } + memset(its_page, INT3_INSN_OPCODE, PAGE_SIZE); + its_offset = 32; + } + + /* + * If the indirect branch instruction will be in the lower half + * of a cacheline, then update the offset to reach the upper half. + */ + if ((its_offset + size - 1) % 64 < 32) + its_offset = ((its_offset - 1) | 0x3F) + 33; + + thunk = its_page + its_offset; + its_offset += size; + + return its_init_thunk(thunk, reg); +} + +u8 *its_static_thunk(int reg) +{ + u8 *thunk = __x86_indirect_its_thunk_array[reg]; + +#ifdef CONFIG_FINEIBT + /* Paranoid thunk starts 2 bytes before */ + if (cfi_paranoid) + return thunk - 2; +#endif + return thunk; +} + +#endif + /* * Nomenclature for variable names to simplify and clarify this code and ease * any potential staring at it: @@ -581,7 +743,8 @@ static int emit_indirect(int op, int reg, u8 *bytes) return i; } -static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 *bytes) +static int __emit_trampoline(void *addr, struct insn *insn, u8 *bytes, + void *call_dest, void *jmp_dest) { u8 op = insn->opcode.bytes[0]; int i = 0; @@ -602,7 +765,7 @@ static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 switch (op) { case CALL_INSN_OPCODE: __text_gen_insn(bytes+i, op, addr+i, - __x86_indirect_call_thunk_array[reg], + call_dest, CALL_INSN_SIZE); i += CALL_INSN_SIZE; break; @@ -610,7 +773,7 @@ static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 case JMP32_INSN_OPCODE: clang_jcc: __text_gen_insn(bytes+i, op, addr+i, - __x86_indirect_jump_thunk_array[reg], + jmp_dest, JMP32_INSN_SIZE); i += JMP32_INSN_SIZE; break; @@ -625,6 +788,48 @@ clang_jcc: return i; } +static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 *bytes) +{ + return __emit_trampoline(addr, insn, bytes, + __x86_indirect_call_thunk_array[reg], + __x86_indirect_jump_thunk_array[reg]); +} + +#ifdef CONFIG_MITIGATION_ITS +static int emit_its_trampoline(void *addr, struct insn *insn, int reg, u8 *bytes) +{ + u8 *thunk = __x86_indirect_its_thunk_array[reg]; + u8 *tmp = its_allocate_thunk(reg); + + if (tmp) + thunk = tmp; + + return __emit_trampoline(addr, insn, bytes, thunk, thunk); +} + +/* Check if an indirect branch is at ITS-unsafe address */ +static bool cpu_wants_indirect_its_thunk_at(unsigned long addr, int reg) +{ + if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) + return false; + + /* Indirect branch opcode is 2 or 3 bytes depending on reg */ + addr += 1 + reg / 8; + + /* Lower-half of the cacheline? */ + return !(addr & 0x20); +} +#else /* CONFIG_MITIGATION_ITS */ + +#ifdef CONFIG_FINEIBT +static bool cpu_wants_indirect_its_thunk_at(unsigned long addr, int reg) +{ + return false; +} +#endif + +#endif /* CONFIG_MITIGATION_ITS */ + /* * Rewrite the compiler generated retpoline thunk calls. * @@ -699,6 +904,15 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) bytes[i++] = 0xe8; /* LFENCE */ } +#ifdef CONFIG_MITIGATION_ITS + /* + * Check if the address of last byte of emitted-indirect is in + * lower-half of the cacheline. Such branches need ITS mitigation. + */ + if (cpu_wants_indirect_its_thunk_at((unsigned long)addr + i, reg)) + return emit_its_trampoline(addr, insn, reg, bytes); +#endif + ret = emit_indirect(op, reg, bytes + i); if (ret < 0) return ret; @@ -732,6 +946,7 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) int len, ret; u8 bytes[16]; u8 op1, op2; + u8 *dest; ret = insn_decode_kernel(&insn, addr); if (WARN_ON_ONCE(ret < 0)) @@ -748,6 +963,12 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) case CALL_INSN_OPCODE: case JMP32_INSN_OPCODE: + /* Check for cfi_paranoid + ITS */ + dest = addr + insn.length + insn.immediate.value; + if (dest[-1] == 0xea && (dest[0] & 0xf0) == 0x70) { + WARN_ON_ONCE(cfi_mode != CFI_FINEIBT); + continue; + } break; case 0x0f: /* escape */ @@ -775,6 +996,21 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) #ifdef CONFIG_MITIGATION_RETHUNK +bool cpu_wants_rethunk(void) +{ + return cpu_feature_enabled(X86_FEATURE_RETHUNK); +} + +bool cpu_wants_rethunk_at(void *addr) +{ + if (!cpu_feature_enabled(X86_FEATURE_RETHUNK)) + return false; + if (x86_return_thunk != its_return_thunk) + return true; + + return !((unsigned long)addr & 0x20); +} + /* * Rewrite the compiler generated return thunk tail-calls. * @@ -791,7 +1027,7 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes) int i = 0; /* Patch the custom return thunks... */ - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) { + if (cpu_wants_rethunk_at(addr)) { i = JMP32_INSN_SIZE; __text_gen_insn(bytes, JMP32_INSN_OPCODE, addr, x86_return_thunk, i); } else { @@ -808,7 +1044,7 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end) { s32 *s; - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + if (cpu_wants_rethunk()) static_call_force_reinit(); for (s = start; s < end; s++) { @@ -1022,8 +1258,6 @@ int cfi_get_func_arity(void *func) static bool cfi_rand __ro_after_init = true; static u32 cfi_seed __ro_after_init; -static bool cfi_paranoid __ro_after_init = false; - /* * Re-hash the CFI hash with a boot-time seed while making sure the result is * not a valid ENDBR instruction. @@ -1436,6 +1670,19 @@ static int cfi_rand_callers(s32 *start, s32 *end) return 0; } +static int emit_paranoid_trampoline(void *addr, struct insn *insn, int reg, u8 *bytes) +{ + u8 *thunk = (void *)__x86_indirect_its_thunk_array[reg] - 2; + +#ifdef CONFIG_MITIGATION_ITS + u8 *tmp = its_allocate_thunk(reg); + if (tmp) + thunk = tmp; +#endif + + return __emit_trampoline(addr, insn, bytes, thunk, thunk); +} + static int cfi_rewrite_callers(s32 *start, s32 *end) { s32 *s; @@ -1477,9 +1724,14 @@ static int cfi_rewrite_callers(s32 *start, s32 *end) memcpy(bytes, fineibt_paranoid_start, fineibt_paranoid_size); memcpy(bytes + fineibt_caller_hash, &hash, 4); - ret = emit_indirect(op, 11, bytes + fineibt_paranoid_ind); - if (WARN_ON_ONCE(ret != 3)) - continue; + if (cpu_wants_indirect_its_thunk_at((unsigned long)addr + fineibt_paranoid_ind, 11)) { + emit_paranoid_trampoline(addr + fineibt_caller_size, + &insn, 11, bytes + fineibt_caller_size); + } else { + ret = emit_indirect(op, 11, bytes + fineibt_paranoid_ind); + if (WARN_ON_ONCE(ret != 3)) + continue; + } text_poke_early(addr, bytes, fineibt_paranoid_size); } @@ -1706,29 +1958,66 @@ Efault: return false; } +static bool is_paranoid_thunk(unsigned long addr) +{ + u32 thunk; + + __get_kernel_nofault(&thunk, (u32 *)addr, u32, Efault); + return (thunk & 0x00FFFFFF) == 0xfd75ea; + +Efault: + return false; +} + /* * regs->ip points to a LOCK Jcc.d8 instruction from the fineibt_paranoid_start[] - * sequence. + * sequence, or to an invalid instruction (0xea) + Jcc.d8 for cfi_paranoid + ITS + * thunk. */ static bool decode_fineibt_paranoid(struct pt_regs *regs, unsigned long *target, u32 *type) { unsigned long addr = regs->ip - fineibt_paranoid_ud; - u32 hash; - if (!cfi_paranoid || !is_cfi_trap(addr + fineibt_caller_size - LEN_UD2)) + if (!cfi_paranoid) return false; - __get_kernel_nofault(&hash, addr + fineibt_caller_hash, u32, Efault); - *target = regs->r11 + fineibt_preamble_size; - *type = regs->r10; + if (is_cfi_trap(addr + fineibt_caller_size - LEN_UD2)) { + *target = regs->r11 + fineibt_preamble_size; + *type = regs->r10; + + /* + * Since the trapping instruction is the exact, but LOCK prefixed, + * Jcc.d8 that got us here, the normal fixup will work. + */ + return true; + } /* - * Since the trapping instruction is the exact, but LOCK prefixed, - * Jcc.d8 that got us here, the normal fixup will work. + * The cfi_paranoid + ITS thunk combination results in: + * + * 0: 41 ba 78 56 34 12 mov $0x12345678, %r10d + * 6: 45 3b 53 f7 cmp -0x9(%r11), %r10d + * a: 4d 8d 5b f0 lea -0x10(%r11), %r11 + * e: 2e e8 XX XX XX XX cs call __x86_indirect_paranoid_thunk_r11 + * + * Where the paranoid_thunk looks like: + * + * 1d: <ea> (bad) + * __x86_indirect_paranoid_thunk_r11: + * 1e: 75 fd jne 1d + * __x86_indirect_its_thunk_r11: + * 20: 41 ff eb jmp *%r11 + * 23: cc int3 + * */ - return true; + if (is_paranoid_thunk(regs->ip)) { + *target = regs->r11 + fineibt_preamble_size; + *type = regs->r10; + + regs->ip = *target; + return true; + } -Efault: return false; } @@ -2031,6 +2320,8 @@ static noinline void __init alt_reloc_selftest(void) void __init alternative_instructions(void) { + u64 ibt; + int3_selftest(); /* @@ -2057,6 +2348,9 @@ void __init alternative_instructions(void) */ paravirt_set_cap(); + /* Keep CET-IBT disabled until caller/callee are patched */ + ibt = ibt_save(/*disable*/ true); + __apply_fineibt(__retpoline_sites, __retpoline_sites_end, __cfi_sites, __cfi_sites_end, true); @@ -2080,6 +2374,8 @@ void __init alternative_instructions(void) */ apply_seal_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end); + ibt_restore(ibt); + #ifdef CONFIG_SMP /* Patch to UP if other cpus not imminent. */ if (!noreplace_smp && (num_present_cpus() == 1 || setup_max_cpus <= 1)) { diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 362602b705cc..8596ce85026c 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -49,6 +49,7 @@ static void __init srbds_select_mitigation(void); static void __init l1d_flush_select_mitigation(void); static void __init srso_select_mitigation(void); static void __init gds_select_mitigation(void); +static void __init its_select_mitigation(void); /* The base value of the SPEC_CTRL MSR without task-specific bits set */ u64 x86_spec_ctrl_base; @@ -66,6 +67,14 @@ static DEFINE_MUTEX(spec_ctrl_mutex); void (*x86_return_thunk)(void) __ro_after_init = __x86_return_thunk; +static void __init set_return_thunk(void *thunk) +{ + if (x86_return_thunk != __x86_return_thunk) + pr_warn("x86/bugs: return thunk changed\n"); + + x86_return_thunk = thunk; +} + /* Update SPEC_CTRL MSR and its cached copy unconditionally */ static void update_spec_ctrl(u64 val) { @@ -178,6 +187,7 @@ void __init cpu_select_mitigations(void) */ srso_select_mitigation(); gds_select_mitigation(); + its_select_mitigation(); } /* @@ -1118,7 +1128,7 @@ do_cmd_auto: setup_force_cpu_cap(X86_FEATURE_RETHUNK); setup_force_cpu_cap(X86_FEATURE_UNRET); - x86_return_thunk = retbleed_return_thunk; + set_return_thunk(retbleed_return_thunk); if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) @@ -1153,7 +1163,7 @@ do_cmd_auto: setup_force_cpu_cap(X86_FEATURE_RETHUNK); setup_force_cpu_cap(X86_FEATURE_CALL_DEPTH); - x86_return_thunk = call_depth_return_thunk; + set_return_thunk(call_depth_return_thunk); break; default: @@ -1188,6 +1198,145 @@ do_cmd_auto: } #undef pr_fmt +#define pr_fmt(fmt) "ITS: " fmt + +enum its_mitigation_cmd { + ITS_CMD_OFF, + ITS_CMD_ON, + ITS_CMD_VMEXIT, + ITS_CMD_RSB_STUFF, +}; + +enum its_mitigation { + ITS_MITIGATION_OFF, + ITS_MITIGATION_VMEXIT_ONLY, + ITS_MITIGATION_ALIGNED_THUNKS, + ITS_MITIGATION_RETPOLINE_STUFF, +}; + +static const char * const its_strings[] = { + [ITS_MITIGATION_OFF] = "Vulnerable", + [ITS_MITIGATION_VMEXIT_ONLY] = "Mitigation: Vulnerable, KVM: Not affected", + [ITS_MITIGATION_ALIGNED_THUNKS] = "Mitigation: Aligned branch/return thunks", + [ITS_MITIGATION_RETPOLINE_STUFF] = "Mitigation: Retpolines, Stuffing RSB", +}; + +static enum its_mitigation its_mitigation __ro_after_init = ITS_MITIGATION_ALIGNED_THUNKS; + +static enum its_mitigation_cmd its_cmd __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_ITS) ? ITS_CMD_ON : ITS_CMD_OFF; + +static int __init its_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!IS_ENABLED(CONFIG_MITIGATION_ITS)) { + pr_err("Mitigation disabled at compile time, ignoring option (%s)", str); + return 0; + } + + if (!strcmp(str, "off")) { + its_cmd = ITS_CMD_OFF; + } else if (!strcmp(str, "on")) { + its_cmd = ITS_CMD_ON; + } else if (!strcmp(str, "force")) { + its_cmd = ITS_CMD_ON; + setup_force_cpu_bug(X86_BUG_ITS); + } else if (!strcmp(str, "vmexit")) { + its_cmd = ITS_CMD_VMEXIT; + } else if (!strcmp(str, "stuff")) { + its_cmd = ITS_CMD_RSB_STUFF; + } else { + pr_err("Ignoring unknown indirect_target_selection option (%s).", str); + } + + return 0; +} +early_param("indirect_target_selection", its_parse_cmdline); + +static void __init its_select_mitigation(void) +{ + enum its_mitigation_cmd cmd = its_cmd; + + if (!boot_cpu_has_bug(X86_BUG_ITS) || cpu_mitigations_off()) { + its_mitigation = ITS_MITIGATION_OFF; + return; + } + + /* Retpoline+CDT mitigates ITS, bail out */ + if (boot_cpu_has(X86_FEATURE_RETPOLINE) && + boot_cpu_has(X86_FEATURE_CALL_DEPTH)) { + its_mitigation = ITS_MITIGATION_RETPOLINE_STUFF; + goto out; + } + + /* Exit early to avoid irrelevant warnings */ + if (cmd == ITS_CMD_OFF) { + its_mitigation = ITS_MITIGATION_OFF; + goto out; + } + if (spectre_v2_enabled == SPECTRE_V2_NONE) { + pr_err("WARNING: Spectre-v2 mitigation is off, disabling ITS\n"); + its_mitigation = ITS_MITIGATION_OFF; + goto out; + } + if (!IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) || + !IS_ENABLED(CONFIG_MITIGATION_RETHUNK)) { + pr_err("WARNING: ITS mitigation depends on retpoline and rethunk support\n"); + its_mitigation = ITS_MITIGATION_OFF; + goto out; + } + if (IS_ENABLED(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B)) { + pr_err("WARNING: ITS mitigation is not compatible with CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B\n"); + its_mitigation = ITS_MITIGATION_OFF; + goto out; + } + if (boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE)) { + pr_err("WARNING: ITS mitigation is not compatible with lfence mitigation\n"); + its_mitigation = ITS_MITIGATION_OFF; + goto out; + } + + if (cmd == ITS_CMD_RSB_STUFF && + (!boot_cpu_has(X86_FEATURE_RETPOLINE) || !IS_ENABLED(CONFIG_MITIGATION_CALL_DEPTH_TRACKING))) { + pr_err("RSB stuff mitigation not supported, using default\n"); + cmd = ITS_CMD_ON; + } + + switch (cmd) { + case ITS_CMD_OFF: + its_mitigation = ITS_MITIGATION_OFF; + break; + case ITS_CMD_VMEXIT: + if (boot_cpu_has_bug(X86_BUG_ITS_NATIVE_ONLY)) { + its_mitigation = ITS_MITIGATION_VMEXIT_ONLY; + goto out; + } + fallthrough; + case ITS_CMD_ON: + its_mitigation = ITS_MITIGATION_ALIGNED_THUNKS; + if (!boot_cpu_has(X86_FEATURE_RETPOLINE)) + setup_force_cpu_cap(X86_FEATURE_INDIRECT_THUNK_ITS); + setup_force_cpu_cap(X86_FEATURE_RETHUNK); + set_return_thunk(its_return_thunk); + break; + case ITS_CMD_RSB_STUFF: + its_mitigation = ITS_MITIGATION_RETPOLINE_STUFF; + setup_force_cpu_cap(X86_FEATURE_RETHUNK); + setup_force_cpu_cap(X86_FEATURE_CALL_DEPTH); + set_return_thunk(call_depth_return_thunk); + if (retbleed_mitigation == RETBLEED_MITIGATION_NONE) { + retbleed_mitigation = RETBLEED_MITIGATION_STUFF; + pr_info("Retbleed mitigation updated to stuffing\n"); + } + break; + } +out: + pr_info("%s\n", its_strings[its_mitigation]); +} + +#undef pr_fmt #define pr_fmt(fmt) "Spectre V2 : " fmt static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init = @@ -1697,11 +1846,11 @@ static void __init bhi_select_mitigation(void) return; } - /* Mitigate in hardware if supported */ - if (spec_ctrl_bhi_dis()) + if (!IS_ENABLED(CONFIG_X86_64)) return; - if (!IS_ENABLED(CONFIG_X86_64)) + /* Mitigate in hardware if supported */ + if (spec_ctrl_bhi_dis()) return; if (bhi_mitigation == BHI_MITIGATION_VMEXIT_ONLY) { @@ -2607,10 +2756,10 @@ static void __init srso_select_mitigation(void) if (boot_cpu_data.x86 == 0x19) { setup_force_cpu_cap(X86_FEATURE_SRSO_ALIAS); - x86_return_thunk = srso_alias_return_thunk; + set_return_thunk(srso_alias_return_thunk); } else { setup_force_cpu_cap(X86_FEATURE_SRSO); - x86_return_thunk = srso_return_thunk; + set_return_thunk(srso_return_thunk); } if (has_microcode) srso_mitigation = SRSO_MITIGATION_SAFE_RET; @@ -2800,6 +2949,11 @@ static ssize_t rfds_show_state(char *buf) return sysfs_emit(buf, "%s\n", rfds_strings[rfds_mitigation]); } +static ssize_t its_show_state(char *buf) +{ + return sysfs_emit(buf, "%s\n", its_strings[its_mitigation]); +} + static char *stibp_state(void) { if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && @@ -2982,6 +3136,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_RFDS: return rfds_show_state(buf); + case X86_BUG_ITS: + return its_show_state(buf); + default: break; } @@ -3061,6 +3218,11 @@ ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attrib { return cpu_show_common(dev, attr, buf, X86_BUG_RFDS); } + +ssize_t cpu_show_indirect_target_selection(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_ITS); +} #endif void __warn_thunk(void) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 12126adbc3a9..0ff057ff11ce 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1227,6 +1227,10 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define GDS BIT(6) /* CPU is affected by Register File Data Sampling */ #define RFDS BIT(7) +/* CPU is affected by Indirect Target Selection */ +#define ITS BIT(8) +/* CPU is affected by Indirect Target Selection, but guest-host isolation is not affected */ +#define ITS_NATIVE_ONLY BIT(9) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE, X86_STEP_MAX, SRBDS), @@ -1238,22 +1242,25 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPS(INTEL_BROADWELL_G, X86_STEP_MAX, SRBDS), VULNBL_INTEL_STEPS(INTEL_BROADWELL_X, X86_STEP_MAX, MMIO), VULNBL_INTEL_STEPS(INTEL_BROADWELL, X86_STEP_MAX, SRBDS), - VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, X86_STEP_MAX, MMIO | RETBLEED | GDS), + VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, 0x5, MMIO | RETBLEED | GDS), + VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, X86_STEP_MAX, MMIO | RETBLEED | GDS | ITS), VULNBL_INTEL_STEPS(INTEL_SKYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS), VULNBL_INTEL_STEPS(INTEL_SKYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPS(INTEL_KABYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, 0xb, MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | ITS), + VULNBL_INTEL_STEPS(INTEL_KABYLAKE, 0xc, MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPS(INTEL_KABYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | ITS), VULNBL_INTEL_STEPS(INTEL_CANNONLAKE_L, X86_STEP_MAX, RETBLEED), - VULNBL_INTEL_STEPS(INTEL_ICELAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS), - VULNBL_INTEL_STEPS(INTEL_ICELAKE_D, X86_STEP_MAX, MMIO | GDS), - VULNBL_INTEL_STEPS(INTEL_ICELAKE_X, X86_STEP_MAX, MMIO | GDS), - VULNBL_INTEL_STEPS(INTEL_COMETLAKE, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS), - VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, 0x0, MMIO | RETBLEED), - VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS), - VULNBL_INTEL_STEPS(INTEL_TIGERLAKE_L, X86_STEP_MAX, GDS), - VULNBL_INTEL_STEPS(INTEL_TIGERLAKE, X86_STEP_MAX, GDS), + VULNBL_INTEL_STEPS(INTEL_ICELAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS | ITS_NATIVE_ONLY), + VULNBL_INTEL_STEPS(INTEL_ICELAKE_D, X86_STEP_MAX, MMIO | GDS | ITS | ITS_NATIVE_ONLY), + VULNBL_INTEL_STEPS(INTEL_ICELAKE_X, X86_STEP_MAX, MMIO | GDS | ITS | ITS_NATIVE_ONLY), + VULNBL_INTEL_STEPS(INTEL_COMETLAKE, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS), + VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, 0x0, MMIO | RETBLEED | ITS), + VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS), + VULNBL_INTEL_STEPS(INTEL_TIGERLAKE_L, X86_STEP_MAX, GDS | ITS | ITS_NATIVE_ONLY), + VULNBL_INTEL_STEPS(INTEL_TIGERLAKE, X86_STEP_MAX, GDS | ITS | ITS_NATIVE_ONLY), VULNBL_INTEL_STEPS(INTEL_LAKEFIELD, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED), - VULNBL_INTEL_STEPS(INTEL_ROCKETLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS), + VULNBL_INTEL_STEPS(INTEL_ROCKETLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | ITS | ITS_NATIVE_ONLY), VULNBL_INTEL_TYPE(INTEL_ALDERLAKE, ATOM, RFDS), VULNBL_INTEL_STEPS(INTEL_ALDERLAKE_L, X86_STEP_MAX, RFDS), VULNBL_INTEL_TYPE(INTEL_RAPTORLAKE, ATOM, RFDS), @@ -1318,6 +1325,32 @@ static bool __init vulnerable_to_rfds(u64 x86_arch_cap_msr) return cpu_matches(cpu_vuln_blacklist, RFDS); } +static bool __init vulnerable_to_its(u64 x86_arch_cap_msr) +{ + /* The "immunity" bit trumps everything else: */ + if (x86_arch_cap_msr & ARCH_CAP_ITS_NO) + return false; + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return false; + + /* None of the affected CPUs have BHI_CTRL */ + if (boot_cpu_has(X86_FEATURE_BHI_CTRL)) + return false; + + /* + * If a VMM did not expose ITS_NO, assume that a guest could + * be running on a vulnerable hardware or may migrate to such + * hardware. + */ + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return true; + + if (cpu_matches(cpu_vuln_blacklist, ITS)) + return true; + + return false; +} + static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { u64 x86_arch_cap_msr = x86_read_arch_cap_msr(); @@ -1439,9 +1472,12 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) if (vulnerable_to_rfds(x86_arch_cap_msr)) setup_force_cpu_bug(X86_BUG_RFDS); - /* When virtualized, eIBRS could be hidden, assume vulnerable */ - if (!(x86_arch_cap_msr & ARCH_CAP_BHI_NO) && - !cpu_matches(cpu_vuln_whitelist, NO_BHI) && + /* + * Intel parts with eIBRS are vulnerable to BHI attacks. Parts with + * BHI_NO still need to use the BHI mitigation to prevent Intra-mode + * attacks. When virtualized, eIBRS could be hidden, assume vulnerable. + */ + if (!cpu_matches(cpu_vuln_whitelist, NO_BHI) && (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED) || boot_cpu_has(X86_FEATURE_HYPERVISOR))) setup_force_cpu_bug(X86_BUG_BHI); @@ -1449,6 +1485,12 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_AMD_IBPB) && !cpu_has(c, X86_FEATURE_AMD_IBPB_RET)) setup_force_cpu_bug(X86_BUG_IBPB_NO_RET); + if (vulnerable_to_its(x86_arch_cap_msr)) { + setup_force_cpu_bug(X86_BUG_ITS); + if (cpu_matches(cpu_vuln_blacklist, ITS_NATIVE_ONLY)) + setup_force_cpu_bug(X86_BUG_ITS_NATIVE_ONLY); + } + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 4a10d35e70aa..96cb992d50ef 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -1098,15 +1098,17 @@ static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t siz static int __init save_microcode_in_initrd(void) { - unsigned int cpuid_1_eax = native_cpuid_eax(1); struct cpuinfo_x86 *c = &boot_cpu_data; struct cont_desc desc = { 0 }; + unsigned int cpuid_1_eax; enum ucode_state ret; struct cpio_data cp; - if (dis_ucode_ldr || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) + if (microcode_loader_disabled() || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) return 0; + cpuid_1_eax = native_cpuid_eax(1); + if (!find_blobs_in_containers(&cp)) return -EINVAL; diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index b3658d11e7b6..079f046ee26d 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -41,8 +41,8 @@ #include "internal.h" -static struct microcode_ops *microcode_ops; -bool dis_ucode_ldr = true; +static struct microcode_ops *microcode_ops; +static bool dis_ucode_ldr = false; bool force_minrev = IS_ENABLED(CONFIG_MICROCODE_LATE_FORCE_MINREV); module_param(force_minrev, bool, S_IRUSR | S_IWUSR); @@ -84,6 +84,9 @@ static bool amd_check_current_patch_level(void) u32 lvl, dummy, i; u32 *levels; + if (x86_cpuid_vendor() != X86_VENDOR_AMD) + return false; + native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy); levels = final_levels; @@ -95,27 +98,29 @@ static bool amd_check_current_patch_level(void) return false; } -static bool __init check_loader_disabled_bsp(void) +bool __init microcode_loader_disabled(void) { - static const char *__dis_opt_str = "dis_ucode_ldr"; - const char *cmdline = boot_command_line; - const char *option = __dis_opt_str; + if (dis_ucode_ldr) + return true; /* - * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not - * completely accurate as xen pv guests don't see that CPUID bit set but - * that's good enough as they don't land on the BSP path anyway. + * Disable when: + * + * 1) The CPU does not support CPUID. + * + * 2) Bit 31 in CPUID[1]:ECX is clear + * The bit is reserved for hypervisor use. This is still not + * completely accurate as XEN PV guests don't see that CPUID bit + * set, but that's good enough as they don't land on the BSP + * path anyway. + * + * 3) Certain AMD patch levels are not allowed to be + * overwritten. */ - if (native_cpuid_ecx(1) & BIT(31)) - return true; - - if (x86_cpuid_vendor() == X86_VENDOR_AMD) { - if (amd_check_current_patch_level()) - return true; - } - - if (cmdline_find_option_bool(cmdline, option) <= 0) - dis_ucode_ldr = false; + if (!have_cpuid_p() || + native_cpuid_ecx(1) & BIT(31) || + amd_check_current_patch_level()) + dis_ucode_ldr = true; return dis_ucode_ldr; } @@ -125,7 +130,10 @@ void __init load_ucode_bsp(void) unsigned int cpuid_1_eax; bool intel = true; - if (!have_cpuid_p()) + if (cmdline_find_option_bool(boot_command_line, "dis_ucode_ldr") > 0) + dis_ucode_ldr = true; + + if (microcode_loader_disabled()) return; cpuid_1_eax = native_cpuid_eax(1); @@ -146,9 +154,6 @@ void __init load_ucode_bsp(void) return; } - if (check_loader_disabled_bsp()) - return; - if (intel) load_ucode_intel_bsp(&early_data); else @@ -159,6 +164,11 @@ void load_ucode_ap(void) { unsigned int cpuid_1_eax; + /* + * Can't use microcode_loader_disabled() here - .init section + * hell. It doesn't have to either - the BSP variant must've + * parsed cmdline already anyway. + */ if (dis_ucode_ldr) return; @@ -810,7 +820,7 @@ static int __init microcode_init(void) struct cpuinfo_x86 *c = &boot_cpu_data; int error; - if (dis_ucode_ldr) + if (microcode_loader_disabled()) return -EINVAL; if (c->x86_vendor == X86_VENDOR_INTEL) diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 819199bc0119..2a397da43923 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -389,7 +389,7 @@ static int __init save_builtin_microcode(void) if (xchg(&ucode_patch_va, NULL) != UCODE_BSP_LOADED) return 0; - if (dis_ucode_ldr || boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + if (microcode_loader_disabled() || boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return 0; uci.mc = get_microcode_blob(&uci, true); diff --git a/arch/x86/kernel/cpu/microcode/internal.h b/arch/x86/kernel/cpu/microcode/internal.h index 5df621752fef..50a9702ae4e2 100644 --- a/arch/x86/kernel/cpu/microcode/internal.h +++ b/arch/x86/kernel/cpu/microcode/internal.h @@ -94,7 +94,6 @@ static inline unsigned int x86_cpuid_family(void) return x86_family(eax); } -extern bool dis_ucode_ldr; extern bool force_minrev; #ifdef CONFIG_CPU_SUP_AMD diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index cace6e8d7cc7..5eb1514af559 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -354,7 +354,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) goto fail; ip = trampoline + size; - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + if (cpu_wants_rethunk_at(ip)) __text_gen_insn(ip, JMP32_INSN_OPCODE, ip, x86_return_thunk, JMP32_INSN_SIZE); else memcpy(ip, retq, sizeof(retq)); diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index de001b2146ab..375f2d7f1762 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -145,10 +145,6 @@ void __init __no_stack_protector mk_early_pgtbl_32(void) *ptr = (unsigned long)ptep + PAGE_OFFSET; #ifdef CONFIG_MICROCODE_INITRD32 - /* Running on a hypervisor? */ - if (native_cpuid_ecx(1) & BIT(31)) - return; - params = (struct boot_params *)__pa_nodebug(&boot_params); if (!params->hdr.ramdisk_size || !params->hdr.ramdisk_image) return; diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index a7998f351701..ff07558b7ebc 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -266,6 +266,8 @@ int module_finalize(const Elf_Ehdr *hdr, ibt_endbr = s; } + its_init_mod(me); + if (retpolines || cfi) { void *rseg = NULL, *cseg = NULL; unsigned int rsize = 0, csize = 0; @@ -286,6 +288,9 @@ int module_finalize(const Elf_Ehdr *hdr, void *rseg = (void *)retpolines->sh_addr; apply_retpolines(rseg, rseg + retpolines->sh_size); } + + its_fini_mod(me); + if (returns) { void *rseg = (void *)returns->sh_addr; apply_returns(rseg, rseg + returns->sh_size); @@ -326,4 +331,5 @@ int module_finalize(const Elf_Ehdr *hdr, void module_arch_cleanup(struct module *mod) { alternatives_smp_module_del(mod); + its_free_mod(mod); } diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index a59c72e77645..c3d7ff44b29a 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -81,7 +81,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, break; case RET: - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + if (cpu_wants_rethunk_at(insn)) code = text_gen_insn(JMP32_INSN_OPCODE, insn, x86_return_thunk); else code = &retinsn; @@ -90,7 +90,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, case JCC: if (!func) { func = __static_call_return; - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + if (cpu_wants_rethunk()) func = x86_return_thunk; } diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index ccdc45e5b759..cda5f8362e9d 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -466,10 +466,18 @@ SECTIONS } /* - * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility: + * COMPILE_TEST kernels can be large - CONFIG_KASAN, for example, can cause + * this. Let's assume that nobody will be running a COMPILE_TEST kernel and + * let's assert that fuller build coverage is more valuable than being able to + * run a COMPILE_TEST kernel. + */ +#ifndef CONFIG_COMPILE_TEST +/* + * The ASSERT() sync to . is intentional, for binutils 2.14 compatibility: */ . = ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE), "kernel image bigger than KERNEL_IMAGE_SIZE"); +#endif /* needed for Clang - see arch/x86/entry/entry.S */ PROVIDE(__ref_stack_chk_guard = __stack_chk_guard); @@ -497,6 +505,16 @@ PROVIDE(__ref_stack_chk_guard = __stack_chk_guard); "SRSO function pair won't alias"); #endif +#if defined(CONFIG_MITIGATION_ITS) && !defined(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B) +. = ASSERT(__x86_indirect_its_thunk_rax & 0x20, "__x86_indirect_thunk_rax not in second half of cacheline"); +. = ASSERT(((__x86_indirect_its_thunk_rcx - __x86_indirect_its_thunk_rax) % 64) == 0, "Indirect thunks are not cacheline apart"); +. = ASSERT(__x86_indirect_its_thunk_array == __x86_indirect_its_thunk_rax, "Gap in ITS thunk array"); +#endif + +#if defined(CONFIG_MITIGATION_ITS) && !defined(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B) +. = ASSERT(its_return_thunk & 0x20, "its_return_thunk not in second half of cacheline"); +#endif + #endif /* CONFIG_X86_64 */ /* diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 050a0e229a4d..f2b36d32ef40 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -104,6 +104,9 @@ void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu) { + if (kvm_check_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu)) + kvm_mmu_free_obsolete_roots(vcpu); + /* * Checking root.hpa is sufficient even when KVM has mirror root. * We can have either: diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 63bb77ee1bb1..8d1b632e33d2 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5974,6 +5974,7 @@ void kvm_mmu_free_obsolete_roots(struct kvm_vcpu *vcpu) __kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.root_mmu); __kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.guest_mmu); } +EXPORT_SYMBOL_GPL(kvm_mmu_free_obsolete_roots); static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa, int *bytes) @@ -7669,9 +7670,30 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm) } #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn, + int level) +{ + return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG; +} + +static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn, + int level) +{ + lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG; +} + +static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn, + int level) +{ + lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG; +} + bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, struct kvm_gfn_range *range) { + struct kvm_memory_slot *slot = range->slot; + int level; + /* * Zap SPTEs even if the slot can't be mapped PRIVATE. KVM x86 only * supports KVM_MEMORY_ATTRIBUTE_PRIVATE, and so it *seems* like KVM @@ -7686,6 +7708,38 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm))) return false; + if (WARN_ON_ONCE(range->end <= range->start)) + return false; + + /* + * If the head and tail pages of the range currently allow a hugepage, + * i.e. reside fully in the slot and don't have mixed attributes, then + * add each corresponding hugepage range to the ongoing invalidation, + * e.g. to prevent KVM from creating a hugepage in response to a fault + * for a gfn whose attributes aren't changing. Note, only the range + * of gfns whose attributes are being modified needs to be explicitly + * unmapped, as that will unmap any existing hugepages. + */ + for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) { + gfn_t start = gfn_round_for_level(range->start, level); + gfn_t end = gfn_round_for_level(range->end - 1, level); + gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level); + + if ((start != range->start || start + nr_pages > range->end) && + start >= slot->base_gfn && + start + nr_pages <= slot->base_gfn + slot->npages && + !hugepage_test_mixed(slot, start, level)) + kvm_mmu_invalidate_range_add(kvm, start, start + nr_pages); + + if (end == start) + continue; + + if ((end + nr_pages) > range->end && + (end + nr_pages) <= (slot->base_gfn + slot->npages) && + !hugepage_test_mixed(slot, end, level)) + kvm_mmu_invalidate_range_add(kvm, end, end + nr_pages); + } + /* Unmap the old attribute page. */ if (range->arg.attributes & KVM_MEMORY_ATTRIBUTE_PRIVATE) range->attr_filter = KVM_FILTER_SHARED; @@ -7695,23 +7749,7 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, return kvm_unmap_gfn_range(kvm, range); } -static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn, - int level) -{ - return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG; -} - -static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn, - int level) -{ - lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG; -} -static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn, - int level) -{ - lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG; -} static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, int level, unsigned long attrs) diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c index 699e551ec93b..9864c057187d 100644 --- a/arch/x86/kvm/smm.c +++ b/arch/x86/kvm/smm.c @@ -131,6 +131,7 @@ void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm) kvm_mmu_reset_context(vcpu); } +EXPORT_SYMBOL_GPL(kvm_smm_changed); void process_smi(struct kvm_vcpu *vcpu) { diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 0bc708ee2788..a7a7dc507336 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -3173,9 +3173,14 @@ skip_vmsa_free: kvfree(svm->sev_es.ghcb_sa); } +static u64 kvm_ghcb_get_sw_exit_code(struct vmcb_control_area *control) +{ + return (((u64)control->exit_code_hi) << 32) | control->exit_code; +} + static void dump_ghcb(struct vcpu_svm *svm) { - struct ghcb *ghcb = svm->sev_es.ghcb; + struct vmcb_control_area *control = &svm->vmcb->control; unsigned int nbits; /* Re-use the dump_invalid_vmcb module parameter */ @@ -3184,18 +3189,24 @@ static void dump_ghcb(struct vcpu_svm *svm) return; } - nbits = sizeof(ghcb->save.valid_bitmap) * 8; + nbits = sizeof(svm->sev_es.valid_bitmap) * 8; - pr_err("GHCB (GPA=%016llx):\n", svm->vmcb->control.ghcb_gpa); + /* + * Print KVM's snapshot of the GHCB values that were (unsuccessfully) + * used to handle the exit. If the guest has since modified the GHCB + * itself, dumping the raw GHCB won't help debug why KVM was unable to + * handle the VMGEXIT that KVM observed. + */ + pr_err("GHCB (GPA=%016llx) snapshot:\n", svm->vmcb->control.ghcb_gpa); pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_code", - ghcb->save.sw_exit_code, ghcb_sw_exit_code_is_valid(ghcb)); + kvm_ghcb_get_sw_exit_code(control), kvm_ghcb_sw_exit_code_is_valid(svm)); pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_1", - ghcb->save.sw_exit_info_1, ghcb_sw_exit_info_1_is_valid(ghcb)); + control->exit_info_1, kvm_ghcb_sw_exit_info_1_is_valid(svm)); pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_2", - ghcb->save.sw_exit_info_2, ghcb_sw_exit_info_2_is_valid(ghcb)); + control->exit_info_2, kvm_ghcb_sw_exit_info_2_is_valid(svm)); pr_err("%-20s%016llx is_valid: %u\n", "sw_scratch", - ghcb->save.sw_scratch, ghcb_sw_scratch_is_valid(ghcb)); - pr_err("%-20s%*pb\n", "valid_bitmap", nbits, ghcb->save.valid_bitmap); + svm->sev_es.sw_scratch, kvm_ghcb_sw_scratch_is_valid(svm)); + pr_err("%-20s%*pb\n", "valid_bitmap", nbits, svm->sev_es.valid_bitmap); } static void sev_es_sync_to_ghcb(struct vcpu_svm *svm) @@ -3266,11 +3277,6 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); } -static u64 kvm_ghcb_get_sw_exit_code(struct vmcb_control_area *control) -{ - return (((u64)control->exit_code_hi) << 32) | control->exit_code; -} - static int sev_es_validate_vmgexit(struct vcpu_svm *svm) { struct vmcb_control_area *control = &svm->vmcb->control; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index d5d0c5c3300b..a89c271a1951 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -607,9 +607,6 @@ static void svm_disable_virtualization_cpu(void) kvm_cpu_svm_disable(); amd_pmu_disable_virt(); - - if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE)) - msr_clear_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT); } static int svm_enable_virtualization_cpu(void) @@ -687,9 +684,6 @@ static int svm_enable_virtualization_cpu(void) rdmsr(MSR_TSC_AUX, sev_es_host_save_area(sd)->tsc_aux, msr_hi); } - if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE)) - msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT); - return 0; } @@ -1518,6 +1512,63 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu) __free_pages(virt_to_page(svm->msrpm), get_order(MSRPM_SIZE)); } +#ifdef CONFIG_CPU_MITIGATIONS +static DEFINE_SPINLOCK(srso_lock); +static atomic_t srso_nr_vms; + +static void svm_srso_clear_bp_spec_reduce(void *ign) +{ + struct svm_cpu_data *sd = this_cpu_ptr(&svm_data); + + if (!sd->bp_spec_reduce_set) + return; + + msr_clear_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT); + sd->bp_spec_reduce_set = false; +} + +static void svm_srso_vm_destroy(void) +{ + if (!cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE)) + return; + + if (atomic_dec_return(&srso_nr_vms)) + return; + + guard(spinlock)(&srso_lock); + + /* + * Verify a new VM didn't come along, acquire the lock, and increment + * the count before this task acquired the lock. + */ + if (atomic_read(&srso_nr_vms)) + return; + + on_each_cpu(svm_srso_clear_bp_spec_reduce, NULL, 1); +} + +static void svm_srso_vm_init(void) +{ + if (!cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE)) + return; + + /* + * Acquire the lock on 0 => 1 transitions to ensure a potential 1 => 0 + * transition, i.e. destroying the last VM, is fully complete, e.g. so + * that a delayed IPI doesn't clear BP_SPEC_REDUCE after a vCPU runs. + */ + if (atomic_inc_not_zero(&srso_nr_vms)) + return; + + guard(spinlock)(&srso_lock); + + atomic_inc(&srso_nr_vms); +} +#else +static void svm_srso_vm_init(void) { } +static void svm_srso_vm_destroy(void) { } +#endif + static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1550,6 +1601,11 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) (!boot_cpu_has(X86_FEATURE_V_TSC_AUX) || !sev_es_guest(vcpu->kvm))) kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull); + if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE) && + !sd->bp_spec_reduce_set) { + sd->bp_spec_reduce_set = true; + msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT); + } svm->guest_state_loaded = true; } @@ -2231,6 +2287,10 @@ static int shutdown_interception(struct kvm_vcpu *vcpu) */ if (!sev_es_guest(vcpu->kvm)) { clear_page(svm->vmcb); +#ifdef CONFIG_KVM_SMM + if (is_smm(vcpu)) + kvm_smm_changed(vcpu, false); +#endif kvm_vcpu_reset(vcpu, true); } @@ -5036,6 +5096,8 @@ static void svm_vm_destroy(struct kvm *kvm) { avic_vm_destroy(kvm); sev_vm_destroy(kvm); + + svm_srso_vm_destroy(); } static int svm_vm_init(struct kvm *kvm) @@ -5061,6 +5123,7 @@ static int svm_vm_init(struct kvm *kvm) return ret; } + svm_srso_vm_init(); return 0; } diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index d4490eaed55d..f16b068c4228 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -335,6 +335,8 @@ struct svm_cpu_data { u32 next_asid; u32 min_asid; + bool bp_spec_reduce_set; + struct vmcb *save_area; unsigned long save_area_pa; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index df5b99ea1f18..be7bb6d20129 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1584,7 +1584,7 @@ EXPORT_SYMBOL_GPL(kvm_emulate_rdpmc); ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \ ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \ ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \ - ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO) + ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO | ARCH_CAP_ITS_NO) static u64 kvm_get_arch_capabilities(void) { @@ -1618,6 +1618,8 @@ static u64 kvm_get_arch_capabilities(void) data |= ARCH_CAP_MDS_NO; if (!boot_cpu_has_bug(X86_BUG_RFDS)) data |= ARCH_CAP_RFDS_NO; + if (!boot_cpu_has_bug(X86_BUG_ITS)) + data |= ARCH_CAP_ITS_NO; if (!boot_cpu_has(X86_FEATURE_RTM)) { /* @@ -4597,7 +4599,7 @@ static bool kvm_is_vm_type_supported(unsigned long type) return type < 32 && (kvm_caps.supported_vm_types & BIT(type)); } -static inline u32 kvm_sync_valid_fields(struct kvm *kvm) +static inline u64 kvm_sync_valid_fields(struct kvm *kvm) { return kvm && kvm->arch.has_protected_state ? 0 : KVM_SYNC_X86_VALID_FIELDS; } @@ -11493,7 +11495,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { struct kvm_queued_exception *ex = &vcpu->arch.exception; struct kvm_run *kvm_run = vcpu->run; - u32 sync_valid_fields; + u64 sync_valid_fields; int r; r = kvm_mmu_post_init_vm(vcpu->kvm); diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index a26c43abd47d..39374949daa2 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -367,6 +367,54 @@ SYM_FUNC_END(call_depth_return_thunk) #endif /* CONFIG_MITIGATION_CALL_DEPTH_TRACKING */ +#ifdef CONFIG_MITIGATION_ITS + +.macro ITS_THUNK reg + +/* + * If CFI paranoid is used then the ITS thunk starts with opcodes (0xea; jne 1b) + * that complete the fineibt_paranoid caller sequence. + */ +1: .byte 0xea +SYM_INNER_LABEL(__x86_indirect_paranoid_thunk_\reg, SYM_L_GLOBAL) + UNWIND_HINT_UNDEFINED + ANNOTATE_NOENDBR + jne 1b +SYM_INNER_LABEL(__x86_indirect_its_thunk_\reg, SYM_L_GLOBAL) + UNWIND_HINT_UNDEFINED + ANNOTATE_NOENDBR + ANNOTATE_RETPOLINE_SAFE + jmp *%\reg + int3 + .align 32, 0xcc /* fill to the end of the line */ + .skip 32 - (__x86_indirect_its_thunk_\reg - 1b), 0xcc /* skip to the next upper half */ +.endm + +/* ITS mitigation requires thunks be aligned to upper half of cacheline */ +.align 64, 0xcc +.skip 29, 0xcc + +#define GEN(reg) ITS_THUNK reg +#include <asm/GEN-for-each-reg.h> +#undef GEN + + .align 64, 0xcc +SYM_FUNC_ALIAS(__x86_indirect_its_thunk_array, __x86_indirect_its_thunk_rax) +SYM_CODE_END(__x86_indirect_its_thunk_array) + +.align 64, 0xcc +.skip 32, 0xcc +SYM_CODE_START(its_return_thunk) + UNWIND_HINT_FUNC + ANNOTATE_NOENDBR + ANNOTATE_UNRET_SAFE + ret + int3 +SYM_CODE_END(its_return_thunk) +EXPORT_SYMBOL(its_return_thunk) + +#endif /* CONFIG_MITIGATION_ITS */ + /* * This function name is magical and is used by -mfunction-return=thunk-extern * for the compiler to generate JMPs to it. diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index ad662cc4605c..7fa3965dcef1 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -30,6 +30,7 @@ #include <linux/initrd.h> #include <linux/cpumask.h> #include <linux/gfp.h> +#include <linux/execmem.h> #include <asm/asm.h> #include <asm/bios_ebda.h> @@ -755,6 +756,8 @@ void mark_rodata_ro(void) pr_info("Write protecting kernel text and read-only data: %luk\n", size >> 10); + execmem_cache_make_ro(); + kernel_set_to_readonly = 1; #ifdef CONFIG_CPA_DEBUG diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 7c4f6f591f2b..949a447f75ec 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -34,6 +34,7 @@ #include <linux/gfp.h> #include <linux/kcore.h> #include <linux/bootmem_info.h> +#include <linux/execmem.h> #include <asm/processor.h> #include <asm/bios_ebda.h> @@ -1391,6 +1392,8 @@ void mark_rodata_ro(void) (end - start) >> 10); set_memory_ro(start, (end - start) >> PAGE_SHIFT); + execmem_cache_make_ro(); + kernel_set_to_readonly = 1; /* diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 9e5fe2ba858f..ea4dd5b393aa 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -41,6 +41,8 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len) #define EMIT2(b1, b2) EMIT((b1) + ((b2) << 8), 2) #define EMIT3(b1, b2, b3) EMIT((b1) + ((b2) << 8) + ((b3) << 16), 3) #define EMIT4(b1, b2, b3, b4) EMIT((b1) + ((b2) << 8) + ((b3) << 16) + ((b4) << 24), 4) +#define EMIT5(b1, b2, b3, b4, b5) \ + do { EMIT1(b1); EMIT4(b2, b3, b4, b5); } while (0) #define EMIT1_off32(b1, off) \ do { EMIT1(b1); EMIT(off, 4); } while (0) @@ -661,7 +663,10 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) { u8 *prog = *pprog; - if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) { + if (cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) { + OPTIMIZER_HIDE_VAR(reg); + emit_jump(&prog, its_static_thunk(reg), ip); + } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) { EMIT_LFENCE(); EMIT2(0xFF, 0xE0 + reg); } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) { @@ -683,7 +688,7 @@ static void emit_return(u8 **pprog, u8 *ip) { u8 *prog = *pprog; - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) { + if (cpu_wants_rethunk()) { emit_jump(&prog, x86_return_thunk, ip); } else { EMIT1(0xC3); /* ret */ @@ -1502,6 +1507,48 @@ static void emit_priv_frame_ptr(u8 **pprog, void __percpu *priv_frame_ptr) #define PRIV_STACK_GUARD_SZ 8 #define PRIV_STACK_GUARD_VAL 0xEB9F12345678eb9fULL +static int emit_spectre_bhb_barrier(u8 **pprog, u8 *ip, + struct bpf_prog *bpf_prog) +{ + u8 *prog = *pprog; + u8 *func; + + if (cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_LOOP)) { + /* The clearing sequence clobbers eax and ecx. */ + EMIT1(0x50); /* push rax */ + EMIT1(0x51); /* push rcx */ + ip += 2; + + func = (u8 *)clear_bhb_loop; + ip += x86_call_depth_emit_accounting(&prog, func, ip); + + if (emit_call(&prog, func, ip)) + return -EINVAL; + EMIT1(0x59); /* pop rcx */ + EMIT1(0x58); /* pop rax */ + } + /* Insert IBHF instruction */ + if ((cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_LOOP) && + cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) || + cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_HW)) { + /* + * Add an Indirect Branch History Fence (IBHF). IBHF acts as a + * fence preventing branch history from before the fence from + * affecting indirect branches after the fence. This is + * specifically used in cBPF jitted code to prevent Intra-mode + * BHI attacks. The IBHF instruction is designed to be a NOP on + * hardware that doesn't need or support it. The REP and REX.W + * prefixes are required by the microcode, and they also ensure + * that the NOP is unlikely to be used in existing code. + * + * IBHF is not a valid instruction in 32-bit mode. + */ + EMIT5(0xF3, 0x48, 0x0F, 0x1E, 0xF8); /* ibhf */ + } + *pprog = prog; + return 0; +} + static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image, int oldproglen, struct jit_context *ctx, bool jmp_padding) { @@ -2544,6 +2591,13 @@ emit_jmp: seen_exit = true; /* Update cleanup_addr */ ctx->cleanup_addr = proglen; + if (bpf_prog_was_classic(bpf_prog) && + !capable(CAP_SYS_ADMIN)) { + u8 *ip = image + addrs[i - 1]; + + if (emit_spectre_bhb_barrier(&prog, ip, bpf_prog)) + return -EINVAL; + } if (bpf_prog->aux->exception_boundary) { pop_callee_regs(&prog, all_callee_regs_used); pop_r12(&prog); diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index a7e511849875..50651435577c 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -600,6 +600,7 @@ CPU_SHOW_VULN_FALLBACK(spec_rstack_overflow); CPU_SHOW_VULN_FALLBACK(gds); CPU_SHOW_VULN_FALLBACK(reg_file_data_sampling); CPU_SHOW_VULN_FALLBACK(ghostwrite); +CPU_SHOW_VULN_FALLBACK(indirect_target_selection); static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL); static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL); @@ -616,6 +617,7 @@ static DEVICE_ATTR(spec_rstack_overflow, 0444, cpu_show_spec_rstack_overflow, NU static DEVICE_ATTR(gather_data_sampling, 0444, cpu_show_gds, NULL); static DEVICE_ATTR(reg_file_data_sampling, 0444, cpu_show_reg_file_data_sampling, NULL); static DEVICE_ATTR(ghostwrite, 0444, cpu_show_ghostwrite, NULL); +static DEVICE_ATTR(indirect_target_selection, 0444, cpu_show_indirect_target_selection, NULL); static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_meltdown.attr, @@ -633,6 +635,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = { &dev_attr_gather_data_sampling.attr, &dev_attr_reg_file_data_sampling.attr, &dev_attr_ghostwrite.attr, + &dev_attr_indirect_target_selection.attr, NULL }; diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 1813cfd0c4bd..cfccf3ff36e7 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -1440,7 +1440,7 @@ static void platform_shutdown(struct device *_dev) static int platform_dma_configure(struct device *dev) { - struct platform_driver *drv = to_platform_driver(dev->driver); + struct device_driver *drv = READ_ONCE(dev->driver); struct fwnode_handle *fwnode = dev_fwnode(dev); enum dev_dma_attr attr; int ret = 0; @@ -1451,8 +1451,8 @@ static int platform_dma_configure(struct device *dev) attr = acpi_get_dma_attr(to_acpi_device_node(fwnode)); ret = acpi_dma_configure(dev, attr); } - /* @drv may not be valid when we're called from the IOMMU layer */ - if (ret || !dev->driver || drv->driver_managed_dma) + /* @dev->driver may not be valid when we're called from the IOMMU layer */ + if (ret || !drv || to_platform_driver(drv)->driver_managed_dma) return ret; ret = iommu_device_use_default_domain(dev); diff --git a/drivers/clocksource/i8253.c b/drivers/clocksource/i8253.c index 39f7c2d736d1..b603c25f3dfa 100644 --- a/drivers/clocksource/i8253.c +++ b/drivers/clocksource/i8253.c @@ -103,7 +103,7 @@ int __init clocksource_i8253_init(void) #ifdef CONFIG_CLKEVT_I8253 void clockevent_i8253_disable(void) { - raw_spin_lock(&i8253_lock); + guard(raw_spinlock_irqsave)(&i8253_lock); /* * Writing the MODE register should stop the counter, according to @@ -132,8 +132,6 @@ void clockevent_i8253_disable(void) outb_p(0, PIT_CH0); outb_p(0x30, PIT_MODE); - - raw_spin_unlock(&i8253_lock); } static int pit_shutdown(struct clock_event_device *evt) diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index 29780f3a7478..0b450e53161e 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -477,4 +477,10 @@ static inline int hv_debug_add_dev_dir(struct hv_device *dev) #endif /* CONFIG_HYPERV_TESTING */ +/* Create and remove sysfs entry for memory mapped ring buffers for a channel */ +int hv_create_ring_sysfs(struct vmbus_channel *channel, + int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel, + struct vm_area_struct *vma)); +int hv_remove_ring_sysfs(struct vmbus_channel *channel); + #endif /* _HYPERV_VMBUS_H */ diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 8d3cff42bdbb..e3d51a316316 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -1802,6 +1802,26 @@ static ssize_t subchannel_id_show(struct vmbus_channel *channel, } static VMBUS_CHAN_ATTR_RO(subchannel_id); +static int hv_mmap_ring_buffer_wrapper(struct file *filp, struct kobject *kobj, + const struct bin_attribute *attr, + struct vm_area_struct *vma) +{ + struct vmbus_channel *channel = container_of(kobj, struct vmbus_channel, kobj); + + /* + * hv_(create|remove)_ring_sysfs implementation ensures that mmap_ring_buffer + * is not NULL. + */ + return channel->mmap_ring_buffer(channel, vma); +} + +static struct bin_attribute chan_attr_ring_buffer = { + .attr = { + .name = "ring", + .mode = 0600, + }, + .mmap = hv_mmap_ring_buffer_wrapper, +}; static struct attribute *vmbus_chan_attrs[] = { &chan_attr_out_mask.attr, &chan_attr_in_mask.attr, @@ -1821,6 +1841,11 @@ static struct attribute *vmbus_chan_attrs[] = { NULL }; +static struct bin_attribute *vmbus_chan_bin_attrs[] = { + &chan_attr_ring_buffer, + NULL +}; + /* * Channel-level attribute_group callback function. Returns the permission for * each attribute, and returns 0 if an attribute is not visible. @@ -1841,9 +1866,34 @@ static umode_t vmbus_chan_attr_is_visible(struct kobject *kobj, return attr->mode; } +static umode_t vmbus_chan_bin_attr_is_visible(struct kobject *kobj, + const struct bin_attribute *attr, int idx) +{ + const struct vmbus_channel *channel = + container_of(kobj, struct vmbus_channel, kobj); + + /* Hide ring attribute if channel's ring_sysfs_visible is set to false */ + if (attr == &chan_attr_ring_buffer && !channel->ring_sysfs_visible) + return 0; + + return attr->attr.mode; +} + +static size_t vmbus_chan_bin_size(struct kobject *kobj, + const struct bin_attribute *bin_attr, int a) +{ + const struct vmbus_channel *channel = + container_of(kobj, struct vmbus_channel, kobj); + + return channel->ringbuffer_pagecount << PAGE_SHIFT; +} + static const struct attribute_group vmbus_chan_group = { .attrs = vmbus_chan_attrs, - .is_visible = vmbus_chan_attr_is_visible + .bin_attrs = vmbus_chan_bin_attrs, + .is_visible = vmbus_chan_attr_is_visible, + .is_bin_visible = vmbus_chan_bin_attr_is_visible, + .bin_size = vmbus_chan_bin_size, }; static const struct kobj_type vmbus_chan_ktype = { @@ -1851,6 +1901,63 @@ static const struct kobj_type vmbus_chan_ktype = { .release = vmbus_chan_release, }; +/** + * hv_create_ring_sysfs() - create "ring" sysfs entry corresponding to ring buffers for a channel. + * @channel: Pointer to vmbus_channel structure + * @hv_mmap_ring_buffer: function pointer for initializing the function to be called on mmap of + * channel's "ring" sysfs node, which is for the ring buffer of that channel. + * Function pointer is of below type: + * int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel, + * struct vm_area_struct *vma)) + * This has a pointer to the channel and a pointer to vm_area_struct, + * used for mmap, as arguments. + * + * Sysfs node for ring buffer of a channel is created along with other fields, however its + * visibility is disabled by default. Sysfs creation needs to be controlled when the use-case + * is running. + * For example, HV_NIC device is used either by uio_hv_generic or hv_netvsc at any given point of + * time, and "ring" sysfs is needed only when uio_hv_generic is bound to that device. To avoid + * exposing the ring buffer by default, this function is reponsible to enable visibility of + * ring for userspace to use. + * Note: Race conditions can happen with userspace and it is not encouraged to create new + * use-cases for this. This was added to maintain backward compatibility, while solving + * one of the race conditions in uio_hv_generic while creating sysfs. + * + * Returns 0 on success or error code on failure. + */ +int hv_create_ring_sysfs(struct vmbus_channel *channel, + int (*hv_mmap_ring_buffer)(struct vmbus_channel *channel, + struct vm_area_struct *vma)) +{ + struct kobject *kobj = &channel->kobj; + + channel->mmap_ring_buffer = hv_mmap_ring_buffer; + channel->ring_sysfs_visible = true; + + return sysfs_update_group(kobj, &vmbus_chan_group); +} +EXPORT_SYMBOL_GPL(hv_create_ring_sysfs); + +/** + * hv_remove_ring_sysfs() - remove ring sysfs entry corresponding to ring buffers for a channel. + * @channel: Pointer to vmbus_channel structure + * + * Hide "ring" sysfs for a channel by changing its is_visible attribute and updating sysfs group. + * + * Returns 0 on success or error code on failure. + */ +int hv_remove_ring_sysfs(struct vmbus_channel *channel) +{ + struct kobject *kobj = &channel->kobj; + int ret; + + channel->ring_sysfs_visible = false; + ret = sysfs_update_group(kobj, &vmbus_chan_group); + channel->mmap_ring_buffer = NULL; + return ret; +} +EXPORT_SYMBOL_GPL(hv_remove_ring_sysfs); + /* * vmbus_add_channel_kobj - setup a sub-directory under device/channels */ diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c index 16afb9ca19bb..876791d20ed5 100644 --- a/drivers/i2c/busses/i2c-omap.c +++ b/drivers/i2c/busses/i2c-omap.c @@ -1454,7 +1454,7 @@ omap_i2c_probe(struct platform_device *pdev) (1000 * omap->speed / 8); } - if (of_property_read_bool(node, "mux-states")) { + if (of_property_present(node, "mux-states")) { struct mux_state *mux_state; mux_state = devm_mux_state_get(&pdev->dev, NULL); diff --git a/drivers/iio/accel/adis16201.c b/drivers/iio/accel/adis16201.c index 8601b9a8b8e7..5127e58eebc7 100644 --- a/drivers/iio/accel/adis16201.c +++ b/drivers/iio/accel/adis16201.c @@ -211,9 +211,9 @@ static const struct iio_chan_spec adis16201_channels[] = { BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 14), ADIS_AUX_ADC_CHAN(ADIS16201_AUX_ADC_REG, ADIS16201_SCAN_AUX_ADC, 0, 12), ADIS_INCLI_CHAN(X, ADIS16201_XINCL_OUT_REG, ADIS16201_SCAN_INCLI_X, - BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 14), + BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 12), ADIS_INCLI_CHAN(Y, ADIS16201_YINCL_OUT_REG, ADIS16201_SCAN_INCLI_Y, - BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 14), + BIT(IIO_CHAN_INFO_CALIBBIAS), 0, 12), IIO_CHAN_SOFT_TIMESTAMP(7) }; diff --git a/drivers/iio/accel/adxl355_core.c b/drivers/iio/accel/adxl355_core.c index e8cd21fa77a6..cbac622ef821 100644 --- a/drivers/iio/accel/adxl355_core.c +++ b/drivers/iio/accel/adxl355_core.c @@ -231,7 +231,7 @@ struct adxl355_data { u8 transf_buf[3]; struct { u8 buf[14]; - s64 ts; + aligned_s64 ts; } buffer; } __aligned(IIO_DMA_MINALIGN); }; diff --git a/drivers/iio/accel/adxl367.c b/drivers/iio/accel/adxl367.c index add4053e7a02..0c04b2bb7efb 100644 --- a/drivers/iio/accel/adxl367.c +++ b/drivers/iio/accel/adxl367.c @@ -601,18 +601,14 @@ static int _adxl367_set_odr(struct adxl367_state *st, enum adxl367_odr odr) if (ret) return ret; + st->odr = odr; + /* Activity timers depend on ODR */ ret = _adxl367_set_act_time_ms(st, st->act_time_ms); if (ret) return ret; - ret = _adxl367_set_inact_time_ms(st, st->inact_time_ms); - if (ret) - return ret; - - st->odr = odr; - - return 0; + return _adxl367_set_inact_time_ms(st, st->inact_time_ms); } static int adxl367_set_odr(struct iio_dev *indio_dev, enum adxl367_odr odr) diff --git a/drivers/iio/accel/fxls8962af-core.c b/drivers/iio/accel/fxls8962af-core.c index 48e4282964a0..bf1d3923a181 100644 --- a/drivers/iio/accel/fxls8962af-core.c +++ b/drivers/iio/accel/fxls8962af-core.c @@ -1226,8 +1226,11 @@ int fxls8962af_core_probe(struct device *dev, struct regmap *regmap, int irq) if (ret) return ret; - if (device_property_read_bool(dev, "wakeup-source")) - device_init_wakeup(dev, true); + if (device_property_read_bool(dev, "wakeup-source")) { + ret = devm_device_init_wakeup(dev); + if (ret) + return dev_err_probe(dev, ret, "Failed to init wakeup\n"); + } return devm_iio_device_register(dev, indio_dev); } diff --git a/drivers/iio/adc/ad7266.c b/drivers/iio/adc/ad7266.c index 18559757f908..7fef2727f89e 100644 --- a/drivers/iio/adc/ad7266.c +++ b/drivers/iio/adc/ad7266.c @@ -45,7 +45,7 @@ struct ad7266_state { */ struct { __be16 sample[2]; - s64 timestamp; + aligned_s64 timestamp; } data __aligned(IIO_DMA_MINALIGN); }; diff --git a/drivers/iio/adc/ad7380.c b/drivers/iio/adc/ad7380.c index 4fcb49fdf566..aef85093eb16 100644 --- a/drivers/iio/adc/ad7380.c +++ b/drivers/iio/adc/ad7380.c @@ -1211,6 +1211,9 @@ static int ad7380_offload_buffer_predisable(struct iio_dev *indio_dev) struct ad7380_state *st = iio_priv(indio_dev); int ret; + spi_offload_trigger_disable(st->offload, st->offload_trigger); + spi_unoptimize_message(&st->offload_msg); + if (st->seq) { ret = regmap_update_bits(st->regmap, AD7380_REG_ADDR_CONFIG1, @@ -1222,10 +1225,6 @@ static int ad7380_offload_buffer_predisable(struct iio_dev *indio_dev) st->seq = false; } - spi_offload_trigger_disable(st->offload, st->offload_trigger); - - spi_unoptimize_message(&st->offload_msg); - return 0; } @@ -1611,11 +1610,25 @@ static int ad7380_write_event_config(struct iio_dev *indio_dev, return ret; } -static int ad7380_get_alert_th(struct ad7380_state *st, +static int ad7380_get_alert_th(struct iio_dev *indio_dev, + const struct iio_chan_spec *chan, enum iio_event_direction dir, int *val) { - int ret, tmp; + struct ad7380_state *st = iio_priv(indio_dev); + const struct iio_scan_type *scan_type; + int ret, tmp, shift; + + scan_type = iio_get_current_scan_type(indio_dev, chan); + if (IS_ERR(scan_type)) + return PTR_ERR(scan_type); + + /* + * The register value is 12-bits and is compared to the most significant + * bits of raw value, therefore a shift is required to convert this to + * the same scale as the raw value. + */ + shift = scan_type->realbits - 12; switch (dir) { case IIO_EV_DIR_RISING: @@ -1625,7 +1638,7 @@ static int ad7380_get_alert_th(struct ad7380_state *st, if (ret) return ret; - *val = FIELD_GET(AD7380_ALERT_HIGH_TH, tmp); + *val = FIELD_GET(AD7380_ALERT_HIGH_TH, tmp) << shift; return IIO_VAL_INT; case IIO_EV_DIR_FALLING: ret = regmap_read(st->regmap, @@ -1634,7 +1647,7 @@ static int ad7380_get_alert_th(struct ad7380_state *st, if (ret) return ret; - *val = FIELD_GET(AD7380_ALERT_LOW_TH, tmp); + *val = FIELD_GET(AD7380_ALERT_LOW_TH, tmp) << shift; return IIO_VAL_INT; default: return -EINVAL; @@ -1648,7 +1661,6 @@ static int ad7380_read_event_value(struct iio_dev *indio_dev, enum iio_event_info info, int *val, int *val2) { - struct ad7380_state *st = iio_priv(indio_dev); int ret; switch (info) { @@ -1656,7 +1668,7 @@ static int ad7380_read_event_value(struct iio_dev *indio_dev, if (!iio_device_claim_direct(indio_dev)) return -EBUSY; - ret = ad7380_get_alert_th(st, dir, val); + ret = ad7380_get_alert_th(indio_dev, chan, dir, val); iio_device_release_direct(indio_dev); return ret; diff --git a/drivers/iio/adc/ad7606.c b/drivers/iio/adc/ad7606.c index 1a314fddd7eb..703556eb7257 100644 --- a/drivers/iio/adc/ad7606.c +++ b/drivers/iio/adc/ad7606.c @@ -1236,9 +1236,11 @@ static int ad7616_sw_mode_setup(struct iio_dev *indio_dev) st->write_scale = ad7616_write_scale_sw; st->write_os = &ad7616_write_os_sw; - ret = st->bops->sw_mode_config(indio_dev); - if (ret) - return ret; + if (st->bops->sw_mode_config) { + ret = st->bops->sw_mode_config(indio_dev); + if (ret) + return ret; + } /* Activate Burst mode and SEQEN MODE */ return ad7606_write_mask(st, AD7616_CONFIGURATION_REGISTER, @@ -1268,6 +1270,9 @@ static int ad7606b_sw_mode_setup(struct iio_dev *indio_dev) st->write_scale = ad7606_write_scale_sw; st->write_os = &ad7606_write_os_sw; + if (!st->bops->sw_mode_config) + return 0; + return st->bops->sw_mode_config(indio_dev); } diff --git a/drivers/iio/adc/ad7606_spi.c b/drivers/iio/adc/ad7606_spi.c index 885bf0b68e77..179115e90988 100644 --- a/drivers/iio/adc/ad7606_spi.c +++ b/drivers/iio/adc/ad7606_spi.c @@ -131,7 +131,7 @@ static int ad7606_spi_reg_read(struct ad7606_state *st, unsigned int addr) { .tx_buf = &st->d16[0], .len = 2, - .cs_change = 0, + .cs_change = 1, }, { .rx_buf = &st->d16[1], .len = 2, diff --git a/drivers/iio/adc/ad7768-1.c b/drivers/iio/adc/ad7768-1.c index 5a863005aca6..5e0be36af0c5 100644 --- a/drivers/iio/adc/ad7768-1.c +++ b/drivers/iio/adc/ad7768-1.c @@ -168,7 +168,7 @@ struct ad7768_state { union { struct { __be32 chan; - s64 timestamp; + aligned_s64 timestamp; } scan; __be32 d32; u8 d8[2]; diff --git a/drivers/iio/adc/dln2-adc.c b/drivers/iio/adc/dln2-adc.c index a1e48a756a7b..359e26e3f5bc 100644 --- a/drivers/iio/adc/dln2-adc.c +++ b/drivers/iio/adc/dln2-adc.c @@ -466,7 +466,7 @@ static irqreturn_t dln2_adc_trigger_h(int irq, void *p) struct iio_dev *indio_dev = pf->indio_dev; struct { __le16 values[DLN2_ADC_MAX_CHANNELS]; - int64_t timestamp_space; + aligned_s64 timestamp_space; } data; struct dln2_adc_get_all_vals dev_data; struct dln2_adc *dln2 = iio_priv(indio_dev); diff --git a/drivers/iio/adc/qcom-spmi-iadc.c b/drivers/iio/adc/qcom-spmi-iadc.c index 7fb8b2499a1d..b64a8a407168 100644 --- a/drivers/iio/adc/qcom-spmi-iadc.c +++ b/drivers/iio/adc/qcom-spmi-iadc.c @@ -543,7 +543,9 @@ static int iadc_probe(struct platform_device *pdev) else return ret; } else { - device_init_wakeup(iadc->dev, 1); + ret = devm_device_init_wakeup(iadc->dev); + if (ret) + return dev_err_probe(iadc->dev, ret, "Failed to init wakeup\n"); } ret = iadc_update_offset(iadc); diff --git a/drivers/iio/adc/rockchip_saradc.c b/drivers/iio/adc/rockchip_saradc.c index 9a099df79518..5e28bd28b81a 100644 --- a/drivers/iio/adc/rockchip_saradc.c +++ b/drivers/iio/adc/rockchip_saradc.c @@ -520,15 +520,6 @@ static int rockchip_saradc_probe(struct platform_device *pdev) if (info->reset) rockchip_saradc_reset_controller(info->reset); - /* - * Use a default value for the converter clock. - * This may become user-configurable in the future. - */ - ret = clk_set_rate(info->clk, info->data->clk_rate); - if (ret < 0) - return dev_err_probe(&pdev->dev, ret, - "failed to set adc clk rate\n"); - ret = regulator_enable(info->vref); if (ret < 0) return dev_err_probe(&pdev->dev, ret, @@ -555,6 +546,14 @@ static int rockchip_saradc_probe(struct platform_device *pdev) if (IS_ERR(info->clk)) return dev_err_probe(&pdev->dev, PTR_ERR(info->clk), "failed to get adc clock\n"); + /* + * Use a default value for the converter clock. + * This may become user-configurable in the future. + */ + ret = clk_set_rate(info->clk, info->data->clk_rate); + if (ret < 0) + return dev_err_probe(&pdev->dev, ret, + "failed to set adc clk rate\n"); platform_set_drvdata(pdev, indio_dev); diff --git a/drivers/iio/chemical/pms7003.c b/drivers/iio/chemical/pms7003.c index d0bd94912e0a..e05ce1f12065 100644 --- a/drivers/iio/chemical/pms7003.c +++ b/drivers/iio/chemical/pms7003.c @@ -5,7 +5,6 @@ * Copyright (c) Tomasz Duszynski <tduszyns@gmail.com> */ -#include <linux/unaligned.h> #include <linux/completion.h> #include <linux/device.h> #include <linux/errno.h> @@ -19,6 +18,8 @@ #include <linux/module.h> #include <linux/mutex.h> #include <linux/serdev.h> +#include <linux/types.h> +#include <linux/unaligned.h> #define PMS7003_DRIVER_NAME "pms7003" @@ -76,7 +77,7 @@ struct pms7003_state { /* Used to construct scan to push to the IIO buffer */ struct { u16 data[3]; /* PM1, PM2P5, PM10 */ - s64 ts; + aligned_s64 ts; } scan; }; diff --git a/drivers/iio/chemical/sps30.c b/drivers/iio/chemical/sps30.c index 6f4f2ba2c09d..a7888146188d 100644 --- a/drivers/iio/chemical/sps30.c +++ b/drivers/iio/chemical/sps30.c @@ -108,7 +108,7 @@ static irqreturn_t sps30_trigger_handler(int irq, void *p) int ret; struct { s32 data[4]; /* PM1, PM2P5, PM4, PM10 */ - s64 ts; + aligned_s64 ts; } scan; mutex_lock(&state->lock); diff --git a/drivers/iio/common/hid-sensors/hid-sensor-attributes.c b/drivers/iio/common/hid-sensors/hid-sensor-attributes.c index ad1882f608c0..2055a03cbeb1 100644 --- a/drivers/iio/common/hid-sensors/hid-sensor-attributes.c +++ b/drivers/iio/common/hid-sensors/hid-sensor-attributes.c @@ -66,6 +66,10 @@ static struct { {HID_USAGE_SENSOR_HUMIDITY, 0, 1000, 0}, {HID_USAGE_SENSOR_HINGE, 0, 0, 17453293}, {HID_USAGE_SENSOR_HINGE, HID_USAGE_SENSOR_UNITS_DEGREES, 0, 17453293}, + + {HID_USAGE_SENSOR_HUMAN_PRESENCE, 0, 1, 0}, + {HID_USAGE_SENSOR_HUMAN_PROXIMITY, 0, 1, 0}, + {HID_USAGE_SENSOR_HUMAN_ATTENTION, 0, 1, 0}, }; static void simple_div(int dividend, int divisor, int *whole, diff --git a/drivers/iio/imu/adis16550.c b/drivers/iio/imu/adis16550.c index b14ea8937c7f..28f0dbd0226c 100644 --- a/drivers/iio/imu/adis16550.c +++ b/drivers/iio/imu/adis16550.c @@ -836,7 +836,7 @@ static irqreturn_t adis16550_trigger_handler(int irq, void *p) u16 dummy; bool valid; struct iio_poll_func *pf = p; - __be32 data[ADIS16550_MAX_SCAN_DATA]; + __be32 data[ADIS16550_MAX_SCAN_DATA] __aligned(8); struct iio_dev *indio_dev = pf->indio_dev; struct adis16550 *st = iio_priv(indio_dev); struct adis *adis = iio_device_get_drvdata(indio_dev); diff --git a/drivers/iio/imu/bmi270/bmi270_core.c b/drivers/iio/imu/bmi270/bmi270_core.c index a86be5af5ccb..2e4469f30d53 100644 --- a/drivers/iio/imu/bmi270/bmi270_core.c +++ b/drivers/iio/imu/bmi270/bmi270_core.c @@ -918,8 +918,7 @@ static int bmi270_configure_imu(struct bmi270_data *data) FIELD_PREP(BMI270_ACC_CONF_ODR_MSK, BMI270_ACC_CONF_ODR_100HZ) | FIELD_PREP(BMI270_ACC_CONF_BWP_MSK, - BMI270_ACC_CONF_BWP_NORMAL_MODE) | - BMI270_PWR_CONF_ADV_PWR_SAVE_MSK); + BMI270_ACC_CONF_BWP_NORMAL_MODE)); if (ret) return dev_err_probe(dev, ret, "Failed to configure accelerometer"); @@ -927,8 +926,7 @@ static int bmi270_configure_imu(struct bmi270_data *data) FIELD_PREP(BMI270_GYR_CONF_ODR_MSK, BMI270_GYR_CONF_ODR_200HZ) | FIELD_PREP(BMI270_GYR_CONF_BWP_MSK, - BMI270_GYR_CONF_BWP_NORMAL_MODE) | - BMI270_PWR_CONF_ADV_PWR_SAVE_MSK); + BMI270_GYR_CONF_BWP_NORMAL_MODE)); if (ret) return dev_err_probe(dev, ret, "Failed to configure gyroscope"); diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c index 3d3b27f28c9d..273196e647a2 100644 --- a/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c +++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_ring.c @@ -50,7 +50,7 @@ irqreturn_t inv_mpu6050_read_fifo(int irq, void *p) u16 fifo_count; u32 fifo_period; s64 timestamp; - u8 data[INV_MPU6050_OUTPUT_DATA_SIZE]; + u8 data[INV_MPU6050_OUTPUT_DATA_SIZE] __aligned(8); size_t i, nb; mutex_lock(&st->lock); diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c index 0a7cd8c1aa33..8a9d2593576a 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_buffer.c @@ -392,6 +392,9 @@ int st_lsm6dsx_read_fifo(struct st_lsm6dsx_hw *hw) if (fifo_status & cpu_to_le16(ST_LSM6DSX_FIFO_EMPTY_MASK)) return 0; + if (!pattern_len) + pattern_len = ST_LSM6DSX_SAMPLE_SIZE; + fifo_len = (le16_to_cpu(fifo_status) & fifo_diff_mask) * ST_LSM6DSX_CHAN_SIZE; fifo_len = (fifo_len / pattern_len) * pattern_len; @@ -623,6 +626,9 @@ int st_lsm6dsx_read_tagged_fifo(struct st_lsm6dsx_hw *hw) if (!fifo_len) return 0; + if (!pattern_len) + pattern_len = ST_LSM6DSX_TAGGED_SAMPLE_SIZE; + for (read_len = 0; read_len < fifo_len; read_len += pattern_len) { err = st_lsm6dsx_read_block(hw, ST_LSM6DSX_REG_FIFO_OUT_TAG_ADDR, diff --git a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c index 4fdcc2acc94e..96c6106b95ee 100644 --- a/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c +++ b/drivers/iio/imu/st_lsm6dsx/st_lsm6dsx_core.c @@ -2719,8 +2719,11 @@ int st_lsm6dsx_probe(struct device *dev, int irq, int hw_id, } if (device_property_read_bool(dev, "wakeup-source") || - (pdata && pdata->wakeup_source)) - device_init_wakeup(dev, true); + (pdata && pdata->wakeup_source)) { + err = devm_device_init_wakeup(dev); + if (err) + return dev_err_probe(dev, err, "Failed to init wakeup\n"); + } return 0; } diff --git a/drivers/iio/light/hid-sensor-prox.c b/drivers/iio/light/hid-sensor-prox.c index 76b76d12b388..4c65b32d34ce 100644 --- a/drivers/iio/light/hid-sensor-prox.c +++ b/drivers/iio/light/hid-sensor-prox.c @@ -34,9 +34,9 @@ struct prox_state { struct iio_chan_spec channels[MAX_CHANNELS]; u32 channel2usage[MAX_CHANNELS]; u32 human_presence[MAX_CHANNELS]; - int scale_pre_decml; - int scale_post_decml; - int scale_precision; + int scale_pre_decml[MAX_CHANNELS]; + int scale_post_decml[MAX_CHANNELS]; + int scale_precision[MAX_CHANNELS]; unsigned long scan_mask[2]; /* One entry plus one terminator. */ int num_channels; }; @@ -116,13 +116,15 @@ static int prox_read_raw(struct iio_dev *indio_dev, ret_type = IIO_VAL_INT; break; case IIO_CHAN_INFO_SCALE: - *val = prox_state->scale_pre_decml; - *val2 = prox_state->scale_post_decml; - ret_type = prox_state->scale_precision; + if (chan->scan_index >= prox_state->num_channels) + return -EINVAL; + + *val = prox_state->scale_pre_decml[chan->scan_index]; + *val2 = prox_state->scale_post_decml[chan->scan_index]; + ret_type = prox_state->scale_precision[chan->scan_index]; break; case IIO_CHAN_INFO_OFFSET: - *val = hid_sensor_convert_exponent( - prox_state->prox_attr[chan->scan_index].unit_expo); + *val = 0; ret_type = IIO_VAL_INT; break; case IIO_CHAN_INFO_SAMP_FREQ: @@ -249,6 +251,10 @@ static int prox_parse_report(struct platform_device *pdev, st->prox_attr[index].size); dev_dbg(&pdev->dev, "prox %x:%x\n", st->prox_attr[index].index, st->prox_attr[index].report_id); + st->scale_precision[index] = + hid_sensor_format_scale(usage_id, &st->prox_attr[index], + &st->scale_pre_decml[index], + &st->scale_post_decml[index]); index++; } diff --git a/drivers/iio/light/opt3001.c b/drivers/iio/light/opt3001.c index 65b295877b41..393a3d2fbe1d 100644 --- a/drivers/iio/light/opt3001.c +++ b/drivers/iio/light/opt3001.c @@ -788,8 +788,9 @@ static irqreturn_t opt3001_irq(int irq, void *_iio) int ret; bool wake_result_ready_queue = false; enum iio_chan_type chan_type = opt->chip_info->chan_type; + bool ok_to_ignore_lock = opt->ok_to_ignore_lock; - if (!opt->ok_to_ignore_lock) + if (!ok_to_ignore_lock) mutex_lock(&opt->lock); ret = i2c_smbus_read_word_swapped(opt->client, OPT3001_CONFIGURATION); @@ -826,7 +827,7 @@ static irqreturn_t opt3001_irq(int irq, void *_iio) } out: - if (!opt->ok_to_ignore_lock) + if (!ok_to_ignore_lock) mutex_unlock(&opt->lock); if (wake_result_ready_queue) diff --git a/drivers/iio/pressure/mprls0025pa.h b/drivers/iio/pressure/mprls0025pa.h index 9d5c30afa9d6..d62a018eaff3 100644 --- a/drivers/iio/pressure/mprls0025pa.h +++ b/drivers/iio/pressure/mprls0025pa.h @@ -34,16 +34,6 @@ struct iio_dev; struct mpr_data; struct mpr_ops; -/** - * struct mpr_chan - * @pres: pressure value - * @ts: timestamp - */ -struct mpr_chan { - s32 pres; - s64 ts; -}; - enum mpr_func_id { MPR_FUNCTION_A, MPR_FUNCTION_B, @@ -69,6 +59,8 @@ enum mpr_func_id { * reading in a loop until data is ready * @completion: handshake from irq to read * @chan: channel values for buffered mode + * @chan.pres: pressure value + * @chan.ts: timestamp * @buffer: raw conversion data */ struct mpr_data { @@ -87,7 +79,10 @@ struct mpr_data { struct gpio_desc *gpiod_reset; int irq; struct completion completion; - struct mpr_chan chan; + struct { + s32 pres; + aligned_s64 ts; + } chan; u8 buffer[MPR_MEASUREMENT_RD_SIZE] __aligned(IIO_DMA_MINALIGN); }; diff --git a/drivers/iio/temperature/maxim_thermocouple.c b/drivers/iio/temperature/maxim_thermocouple.c index c28a7a6dea5f..555a61e2f3fd 100644 --- a/drivers/iio/temperature/maxim_thermocouple.c +++ b/drivers/iio/temperature/maxim_thermocouple.c @@ -121,9 +121,9 @@ static const struct maxim_thermocouple_chip maxim_thermocouple_chips[] = { struct maxim_thermocouple_data { struct spi_device *spi; const struct maxim_thermocouple_chip *chip; + char tc_type; u8 buffer[16] __aligned(IIO_DMA_MINALIGN); - char tc_type; }; static int maxim_thermocouple_read(struct maxim_thermocouple_data *data, diff --git a/drivers/input/joystick/magellan.c b/drivers/input/joystick/magellan.c index d73389af4dd5..7622638e5bb8 100644 --- a/drivers/input/joystick/magellan.c +++ b/drivers/input/joystick/magellan.c @@ -48,7 +48,7 @@ struct magellan { static int magellan_crunch_nibbles(unsigned char *data, int count) { - static unsigned char nibbles[16] __nonstring = "0AB3D56GH9:K<MN?"; + static const unsigned char nibbles[16] __nonstring = "0AB3D56GH9:K<MN?"; do { if (data[count] == nibbles[data[count] & 0xf]) diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index c33e6f33265b..57a5ff3d1992 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -77,12 +77,13 @@ * xbox d-pads should map to buttons, as is required for DDR pads * but we map them to axes when possible to simplify things */ -#define MAP_DPAD_TO_BUTTONS (1 << 0) -#define MAP_TRIGGERS_TO_BUTTONS (1 << 1) -#define MAP_STICKS_TO_NULL (1 << 2) -#define MAP_SELECT_BUTTON (1 << 3) -#define MAP_PADDLES (1 << 4) -#define MAP_PROFILE_BUTTON (1 << 5) +#define MAP_DPAD_TO_BUTTONS BIT(0) +#define MAP_TRIGGERS_TO_BUTTONS BIT(1) +#define MAP_STICKS_TO_NULL BIT(2) +#define MAP_SHARE_BUTTON BIT(3) +#define MAP_PADDLES BIT(4) +#define MAP_PROFILE_BUTTON BIT(5) +#define MAP_SHARE_OFFSET BIT(6) #define DANCEPAD_MAP_CONFIG (MAP_DPAD_TO_BUTTONS | \ MAP_TRIGGERS_TO_BUTTONS | MAP_STICKS_TO_NULL) @@ -135,14 +136,14 @@ static const struct xpad_device { { 0x03f0, 0x048D, "HyperX Clutch", 0, XTYPE_XBOX360 }, /* wireless */ { 0x03f0, 0x0495, "HyperX Clutch Gladiate", 0, XTYPE_XBOXONE }, { 0x03f0, 0x07A0, "HyperX Clutch Gladiate RGB", 0, XTYPE_XBOXONE }, - { 0x03f0, 0x08B6, "HyperX Clutch Gladiate", 0, XTYPE_XBOXONE }, /* v2 */ + { 0x03f0, 0x08B6, "HyperX Clutch Gladiate", MAP_SHARE_BUTTON, XTYPE_XBOXONE }, /* v2 */ { 0x03f0, 0x09B4, "HyperX Clutch Tanto", 0, XTYPE_XBOXONE }, { 0x044f, 0x0f00, "Thrustmaster Wheel", 0, XTYPE_XBOX }, { 0x044f, 0x0f03, "Thrustmaster Wheel", 0, XTYPE_XBOX }, { 0x044f, 0x0f07, "Thrustmaster, Inc. Controller", 0, XTYPE_XBOX }, - { 0x044f, 0xd01e, "ThrustMaster, Inc. ESWAP X 2 ELDEN RING EDITION", 0, XTYPE_XBOXONE }, { 0x044f, 0x0f10, "Thrustmaster Modena GT Wheel", 0, XTYPE_XBOX }, { 0x044f, 0xb326, "Thrustmaster Gamepad GP XID", 0, XTYPE_XBOX360 }, + { 0x044f, 0xd01e, "ThrustMaster, Inc. ESWAP X 2 ELDEN RING EDITION", 0, XTYPE_XBOXONE }, { 0x045e, 0x0202, "Microsoft X-Box pad v1 (US)", 0, XTYPE_XBOX }, { 0x045e, 0x0285, "Microsoft X-Box pad (Japan)", 0, XTYPE_XBOX }, { 0x045e, 0x0287, "Microsoft Xbox Controller S", 0, XTYPE_XBOX }, @@ -159,7 +160,7 @@ static const struct xpad_device { { 0x045e, 0x0719, "Xbox 360 Wireless Receiver", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360W }, { 0x045e, 0x0b00, "Microsoft X-Box One Elite 2 pad", MAP_PADDLES, XTYPE_XBOXONE }, { 0x045e, 0x0b0a, "Microsoft X-Box Adaptive Controller", MAP_PROFILE_BUTTON, XTYPE_XBOXONE }, - { 0x045e, 0x0b12, "Microsoft Xbox Series S|X Controller", MAP_SELECT_BUTTON, XTYPE_XBOXONE }, + { 0x045e, 0x0b12, "Microsoft Xbox Series S|X Controller", MAP_SHARE_BUTTON | MAP_SHARE_OFFSET, XTYPE_XBOXONE }, { 0x046d, 0xc21d, "Logitech Gamepad F310", 0, XTYPE_XBOX360 }, { 0x046d, 0xc21e, "Logitech Gamepad F510", 0, XTYPE_XBOX360 }, { 0x046d, 0xc21f, "Logitech Gamepad F710", 0, XTYPE_XBOX360 }, @@ -205,13 +206,13 @@ static const struct xpad_device { { 0x0738, 0x9871, "Mad Catz Portable Drum", 0, XTYPE_XBOX360 }, { 0x0738, 0xb726, "Mad Catz Xbox controller - MW2", 0, XTYPE_XBOX360 }, { 0x0738, 0xb738, "Mad Catz MVC2TE Stick 2", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 }, - { 0x0738, 0xbeef, "Mad Catz JOYTECH NEO SE Advanced GamePad", XTYPE_XBOX360 }, + { 0x0738, 0xbeef, "Mad Catz JOYTECH NEO SE Advanced GamePad", 0, XTYPE_XBOX360 }, { 0x0738, 0xcb02, "Saitek Cyborg Rumble Pad - PC/Xbox 360", 0, XTYPE_XBOX360 }, { 0x0738, 0xcb03, "Saitek P3200 Rumble Pad - PC/Xbox 360", 0, XTYPE_XBOX360 }, { 0x0738, 0xcb29, "Saitek Aviator Stick AV8R02", 0, XTYPE_XBOX360 }, { 0x0738, 0xf738, "Super SFIV FightStick TE S", 0, XTYPE_XBOX360 }, { 0x07ff, 0xffff, "Mad Catz GamePad", 0, XTYPE_XBOX360 }, - { 0x0b05, 0x1a38, "ASUS ROG RAIKIRI", 0, XTYPE_XBOXONE }, + { 0x0b05, 0x1a38, "ASUS ROG RAIKIRI", MAP_SHARE_BUTTON, XTYPE_XBOXONE }, { 0x0b05, 0x1abb, "ASUS ROG RAIKIRI PRO", 0, XTYPE_XBOXONE }, { 0x0c12, 0x0005, "Intec wireless", 0, XTYPE_XBOX }, { 0x0c12, 0x8801, "Nyko Xbox Controller", 0, XTYPE_XBOX }, @@ -240,7 +241,7 @@ static const struct xpad_device { { 0x0e6f, 0x0146, "Rock Candy Wired Controller for Xbox One", 0, XTYPE_XBOXONE }, { 0x0e6f, 0x0147, "PDP Marvel Xbox One Controller", 0, XTYPE_XBOXONE }, { 0x0e6f, 0x015c, "PDP Xbox One Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOXONE }, - { 0x0e6f, 0x015d, "PDP Mirror's Edge Official Wired Controller for Xbox One", XTYPE_XBOXONE }, + { 0x0e6f, 0x015d, "PDP Mirror's Edge Official Wired Controller for Xbox One", 0, XTYPE_XBOXONE }, { 0x0e6f, 0x0161, "PDP Xbox One Controller", 0, XTYPE_XBOXONE }, { 0x0e6f, 0x0162, "PDP Xbox One Controller", 0, XTYPE_XBOXONE }, { 0x0e6f, 0x0163, "PDP Xbox One Controller", 0, XTYPE_XBOXONE }, @@ -281,6 +282,7 @@ static const struct xpad_device { { 0x0f0d, 0x00dc, "HORIPAD FPS for Nintendo Switch", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 }, { 0x0f0d, 0x0151, "Hori Racing Wheel Overdrive for Xbox Series X", 0, XTYPE_XBOXONE }, { 0x0f0d, 0x0152, "Hori Racing Wheel Overdrive for Xbox Series X", 0, XTYPE_XBOXONE }, + { 0x0f0d, 0x01b2, "HORI Taiko No Tatsujin Drum Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE }, { 0x0f30, 0x010b, "Philips Recoil", 0, XTYPE_XBOX }, { 0x0f30, 0x0202, "Joytech Advanced Controller", 0, XTYPE_XBOX }, { 0x0f30, 0x8888, "BigBen XBMiniPad Controller", 0, XTYPE_XBOX }, @@ -353,6 +355,8 @@ static const struct xpad_device { { 0x20d6, 0x2001, "BDA Xbox Series X Wired Controller", 0, XTYPE_XBOXONE }, { 0x20d6, 0x2009, "PowerA Enhanced Wired Controller for Xbox Series X|S", 0, XTYPE_XBOXONE }, { 0x20d6, 0x281f, "PowerA Wired Controller For Xbox 360", 0, XTYPE_XBOX360 }, + { 0x20d6, 0x400b, "PowerA FUSION Pro 4 Wired Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE }, + { 0x20d6, 0x890b, "PowerA MOGA XP-Ultra Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE }, { 0x2345, 0xe00b, "Machenike G5 Pro Controller", 0, XTYPE_XBOX360 }, { 0x24c6, 0x5000, "Razer Atrox Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 }, { 0x24c6, 0x5300, "PowerA MINI PROEX Controller", 0, XTYPE_XBOX360 }, @@ -384,13 +388,16 @@ static const struct xpad_device { { 0x294b, 0x3404, "Snakebyte GAMEPAD RGB X", 0, XTYPE_XBOXONE }, { 0x2993, 0x2001, "TECNO Pocket Go", 0, XTYPE_XBOX360 }, { 0x2dc8, 0x2000, "8BitDo Pro 2 Wired Controller fox Xbox", 0, XTYPE_XBOXONE }, + { 0x2dc8, 0x200f, "8BitDo Ultimate 3-mode Controller for Xbox", MAP_SHARE_BUTTON, XTYPE_XBOXONE }, { 0x2dc8, 0x3106, "8BitDo Ultimate Wireless / Pro 2 Wired Controller", 0, XTYPE_XBOX360 }, { 0x2dc8, 0x3109, "8BitDo Ultimate Wireless Bluetooth", 0, XTYPE_XBOX360 }, { 0x2dc8, 0x310a, "8BitDo Ultimate 2C Wireless Controller", 0, XTYPE_XBOX360 }, + { 0x2dc8, 0x310b, "8BitDo Ultimate 2 Wireless Controller", 0, XTYPE_XBOX360 }, { 0x2dc8, 0x6001, "8BitDo SN30 Pro", 0, XTYPE_XBOX360 }, + { 0x2e24, 0x0423, "Hyperkin DuchesS Xbox One pad", MAP_SHARE_BUTTON, XTYPE_XBOXONE }, { 0x2e24, 0x0652, "Hyperkin Duke X-Box One pad", 0, XTYPE_XBOXONE }, { 0x2e24, 0x1688, "Hyperkin X91 X-Box One pad", 0, XTYPE_XBOXONE }, - { 0x2e95, 0x0504, "SCUF Gaming Controller", MAP_SELECT_BUTTON, XTYPE_XBOXONE }, + { 0x2e95, 0x0504, "SCUF Gaming Controller", MAP_SHARE_BUTTON, XTYPE_XBOXONE }, { 0x31e3, 0x1100, "Wooting One", 0, XTYPE_XBOX360 }, { 0x31e3, 0x1200, "Wooting Two", 0, XTYPE_XBOX360 }, { 0x31e3, 0x1210, "Wooting Lekker", 0, XTYPE_XBOX360 }, @@ -714,8 +721,10 @@ static const struct xboxone_init_packet xboxone_init_packets[] = { XBOXONE_INIT_PKT(0x045e, 0x0b00, xboxone_s_init), XBOXONE_INIT_PKT(0x045e, 0x0b00, extra_input_packet_init), XBOXONE_INIT_PKT(0x0e6f, 0x0000, xboxone_pdp_led_on), + XBOXONE_INIT_PKT(0x0f0d, 0x01b2, xboxone_pdp_led_on), XBOXONE_INIT_PKT(0x20d6, 0xa01a, xboxone_pdp_led_on), XBOXONE_INIT_PKT(0x0e6f, 0x0000, xboxone_pdp_auth), + XBOXONE_INIT_PKT(0x0f0d, 0x01b2, xboxone_pdp_auth), XBOXONE_INIT_PKT(0x20d6, 0xa01a, xboxone_pdp_auth), XBOXONE_INIT_PKT(0x24c6, 0x541a, xboxone_rumblebegin_init), XBOXONE_INIT_PKT(0x24c6, 0x542a, xboxone_rumblebegin_init), @@ -1027,7 +1036,7 @@ static void xpad360w_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned cha * The report format was gleaned from * https://github.com/kylelemons/xbox/blob/master/xbox.go */ -static void xpadone_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned char *data) +static void xpadone_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned char *data, u32 len) { struct input_dev *dev = xpad->dev; bool do_sync = false; @@ -1068,8 +1077,12 @@ static void xpadone_process_packet(struct usb_xpad *xpad, u16 cmd, unsigned char /* menu/view buttons */ input_report_key(dev, BTN_START, data[4] & BIT(2)); input_report_key(dev, BTN_SELECT, data[4] & BIT(3)); - if (xpad->mapping & MAP_SELECT_BUTTON) - input_report_key(dev, KEY_RECORD, data[22] & BIT(0)); + if (xpad->mapping & MAP_SHARE_BUTTON) { + if (xpad->mapping & MAP_SHARE_OFFSET) + input_report_key(dev, KEY_RECORD, data[len - 26] & BIT(0)); + else + input_report_key(dev, KEY_RECORD, data[len - 18] & BIT(0)); + } /* buttons A,B,X,Y */ input_report_key(dev, BTN_A, data[4] & BIT(4)); @@ -1217,7 +1230,7 @@ static void xpad_irq_in(struct urb *urb) xpad360w_process_packet(xpad, 0, xpad->idata); break; case XTYPE_XBOXONE: - xpadone_process_packet(xpad, 0, xpad->idata); + xpadone_process_packet(xpad, 0, xpad->idata, urb->actual_length); break; default: xpad_process_packet(xpad, 0, xpad->idata); @@ -1944,7 +1957,7 @@ static int xpad_init_input(struct usb_xpad *xpad) xpad->xtype == XTYPE_XBOXONE) { for (i = 0; xpad360_btn[i] >= 0; i++) input_set_capability(input_dev, EV_KEY, xpad360_btn[i]); - if (xpad->mapping & MAP_SELECT_BUTTON) + if (xpad->mapping & MAP_SHARE_BUTTON) input_set_capability(input_dev, EV_KEY, KEY_RECORD); } else { for (i = 0; xpad_btn[i] >= 0; i++) diff --git a/drivers/input/keyboard/mtk-pmic-keys.c b/drivers/input/keyboard/mtk-pmic-keys.c index 5ad6be914160..061d48350df6 100644 --- a/drivers/input/keyboard/mtk-pmic-keys.c +++ b/drivers/input/keyboard/mtk-pmic-keys.c @@ -147,8 +147,8 @@ static void mtk_pmic_keys_lp_reset_setup(struct mtk_pmic_keys *keys, u32 value, mask; int error; - kregs_home = keys->keys[MTK_PMIC_HOMEKEY_INDEX].regs; - kregs_pwr = keys->keys[MTK_PMIC_PWRKEY_INDEX].regs; + kregs_home = ®s->keys_regs[MTK_PMIC_HOMEKEY_INDEX]; + kregs_pwr = ®s->keys_regs[MTK_PMIC_PWRKEY_INDEX]; error = of_property_read_u32(keys->dev->of_node, "power-off-time-sec", &long_press_debounce); diff --git a/drivers/input/misc/hisi_powerkey.c b/drivers/input/misc/hisi_powerkey.c index d3c293a95d32..d315017324d9 100644 --- a/drivers/input/misc/hisi_powerkey.c +++ b/drivers/input/misc/hisi_powerkey.c @@ -30,7 +30,7 @@ static irqreturn_t hi65xx_power_press_isr(int irq, void *q) { struct input_dev *input = q; - pm_wakeup_event(input->dev.parent, MAX_HELD_TIME); + pm_wakeup_dev_event(input->dev.parent, MAX_HELD_TIME, true); input_report_key(input, KEY_POWER, 1); input_sync(input); diff --git a/drivers/input/misc/sparcspkr.c b/drivers/input/misc/sparcspkr.c index 8d7303fc13bc..1cfadd73829f 100644 --- a/drivers/input/misc/sparcspkr.c +++ b/drivers/input/misc/sparcspkr.c @@ -74,9 +74,14 @@ static int bbc_spkr_event(struct input_dev *dev, unsigned int type, unsigned int return -1; switch (code) { - case SND_BELL: if (value) value = 1000; - case SND_TONE: break; - default: return -1; + case SND_BELL: + if (value) + value = 1000; + break; + case SND_TONE: + break; + default: + return -1; } if (value > 20 && value < 32767) @@ -109,9 +114,14 @@ static int grover_spkr_event(struct input_dev *dev, unsigned int type, unsigned return -1; switch (code) { - case SND_BELL: if (value) value = 1000; - case SND_TONE: break; - default: return -1; + case SND_BELL: + if (value) + value = 1000; + break; + case SND_TONE: + break; + default: + return -1; } if (value > 20 && value < 32767) diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index 309c360aab55..c5c88a75a019 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -164,6 +164,7 @@ static const char * const topbuttonpad_pnp_ids[] = { #ifdef CONFIG_MOUSE_PS2_SYNAPTICS_SMBUS static const char * const smbus_pnp_ids[] = { /* all of the topbuttonpad_pnp_ids are valid, we just add some extras */ + "DLL060d", /* Dell Precision M3800 */ "LEN0048", /* X1 Carbon 3 */ "LEN0046", /* X250 */ "LEN0049", /* Yoga 11e */ @@ -190,11 +191,15 @@ static const char * const smbus_pnp_ids[] = { "LEN2054", /* E480 */ "LEN2055", /* E580 */ "LEN2068", /* T14 Gen 1 */ + "SYN1221", /* TUXEDO InfinityBook Pro 14 v5 */ + "SYN3003", /* HP EliteBook 850 G1 */ "SYN3015", /* HP EliteBook 840 G2 */ "SYN3052", /* HP EliteBook 840 G4 */ "SYN3221", /* HP 15-ay000 */ "SYN323d", /* HP Spectre X360 13-w013dx */ "SYN3257", /* HP Envy 13-ad105ng */ + "TOS01f6", /* Dynabook Portege X30L-G */ + "TOS0213", /* Dynabook Portege X30-D */ NULL }; #endif diff --git a/drivers/input/touchscreen/cyttsp5.c b/drivers/input/touchscreen/cyttsp5.c index eafe5a9b8964..071b7c9bf566 100644 --- a/drivers/input/touchscreen/cyttsp5.c +++ b/drivers/input/touchscreen/cyttsp5.c @@ -580,7 +580,7 @@ static int cyttsp5_power_control(struct cyttsp5 *ts, bool on) int rc; SET_CMD_REPORT_TYPE(cmd[0], 0); - SET_CMD_REPORT_ID(cmd[0], HID_POWER_SLEEP); + SET_CMD_REPORT_ID(cmd[0], state); SET_CMD_OPCODE(cmd[1], HID_CMD_SET_POWER); rc = cyttsp5_write(ts, HID_COMMAND_REG, cmd, sizeof(cmd)); @@ -870,13 +870,16 @@ static int cyttsp5_probe(struct device *dev, struct regmap *regmap, int irq, ts->input->phys = ts->phys; input_set_drvdata(ts->input, ts); - /* Reset the gpio to be in a reset state */ + /* Assert gpio to be in a reset state */ ts->reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH); if (IS_ERR(ts->reset_gpio)) { error = PTR_ERR(ts->reset_gpio); dev_err(dev, "Failed to request reset gpio, error %d\n", error); return error; } + + fsleep(10); /* Ensure long-enough reset pulse (minimum 10us). */ + gpiod_set_value_cansleep(ts->reset_gpio, 0); /* Need a delay to have device up */ diff --git a/drivers/input/touchscreen/stmpe-ts.c b/drivers/input/touchscreen/stmpe-ts.c index a94a1997f96b..af0fb38bcfdc 100644 --- a/drivers/input/touchscreen/stmpe-ts.c +++ b/drivers/input/touchscreen/stmpe-ts.c @@ -366,12 +366,7 @@ static struct platform_driver stmpe_ts_driver = { }; module_platform_driver(stmpe_ts_driver); -static const struct of_device_id stmpe_ts_ids[] = { - { .compatible = "st,stmpe-ts", }, - { }, -}; -MODULE_DEVICE_TABLE(of, stmpe_ts_ids); - +MODULE_ALIAS("platform:stmpe-ts"); MODULE_AUTHOR("Luotao Fu <l.fu@pengutronix.de>"); MODULE_DESCRIPTION("STMPEXXX touchscreen driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/platform/x86/amd/hsmp/acpi.c b/drivers/platform/x86/amd/hsmp/acpi.c index c1eccb3c80c5..eaae044e4f82 100644 --- a/drivers/platform/x86/amd/hsmp/acpi.c +++ b/drivers/platform/x86/amd/hsmp/acpi.c @@ -27,9 +27,8 @@ #include "hsmp.h" -#define DRIVER_NAME "amd_hsmp" +#define DRIVER_NAME "hsmp_acpi" #define DRIVER_VERSION "2.3" -#define ACPI_HSMP_DEVICE_HID "AMDI0097" /* These are the strings specified in ACPI table */ #define MSG_IDOFF_STR "MsgIdOffset" diff --git a/drivers/platform/x86/amd/hsmp/hsmp.h b/drivers/platform/x86/amd/hsmp/hsmp.h index af8b21f821d6..d58d4f0c20d5 100644 --- a/drivers/platform/x86/amd/hsmp/hsmp.h +++ b/drivers/platform/x86/amd/hsmp/hsmp.h @@ -23,6 +23,7 @@ #define HSMP_CDEV_NAME "hsmp_cdev" #define HSMP_DEVNODE_NAME "hsmp" +#define ACPI_HSMP_DEVICE_HID "AMDI0097" struct hsmp_mbaddr_info { u32 base_addr; diff --git a/drivers/platform/x86/amd/hsmp/plat.c b/drivers/platform/x86/amd/hsmp/plat.c index b9782a078dbd..81931e808bbc 100644 --- a/drivers/platform/x86/amd/hsmp/plat.c +++ b/drivers/platform/x86/amd/hsmp/plat.c @@ -11,6 +11,7 @@ #include <asm/amd_hsmp.h> +#include <linux/acpi.h> #include <linux/build_bug.h> #include <linux/device.h> #include <linux/module.h> @@ -266,7 +267,7 @@ static bool legacy_hsmp_support(void) } case 0x1A: switch (boot_cpu_data.x86_model) { - case 0x00 ... 0x1F: + case 0x00 ... 0x0F: return true; default: return false; @@ -288,6 +289,9 @@ static int __init hsmp_plt_init(void) return ret; } + if (acpi_dev_present(ACPI_HSMP_DEVICE_HID, NULL, -1)) + return -ENODEV; + hsmp_pdev = get_hsmp_pdev(); if (!hsmp_pdev) return -ENOMEM; diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c index b4f49720c87f..2e3f6fc67c56 100644 --- a/drivers/platform/x86/amd/pmc/pmc-quirks.c +++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c @@ -217,6 +217,13 @@ static const struct dmi_system_id fwbug_list[] = { DMI_MATCH(DMI_BIOS_VERSION, "03.05"), } }, + { + .ident = "MECHREVO Wujie 14X (GX4HRXL)", + .driver_data = &quirk_spurious_8042, + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "WUJIE14-GX4HRXL"), + } + }, {} }; diff --git a/drivers/platform/x86/amd/pmf/tee-if.c b/drivers/platform/x86/amd/pmf/tee-if.c index 14b99d8b63d2..d3bd12ad036a 100644 --- a/drivers/platform/x86/amd/pmf/tee-if.c +++ b/drivers/platform/x86/amd/pmf/tee-if.c @@ -334,6 +334,11 @@ static int amd_pmf_start_policy_engine(struct amd_pmf_dev *dev) return 0; } +static inline bool amd_pmf_pb_valid(struct amd_pmf_dev *dev) +{ + return memchr_inv(dev->policy_buf, 0xff, dev->policy_sz); +} + #ifdef CONFIG_AMD_PMF_DEBUG static void amd_pmf_hex_dump_pb(struct amd_pmf_dev *dev) { @@ -361,12 +366,22 @@ static ssize_t amd_pmf_get_pb_data(struct file *filp, const char __user *buf, dev->policy_buf = new_policy_buf; dev->policy_sz = length; + if (!amd_pmf_pb_valid(dev)) { + ret = -EINVAL; + goto cleanup; + } + amd_pmf_hex_dump_pb(dev); ret = amd_pmf_start_policy_engine(dev); if (ret < 0) - return ret; + goto cleanup; return length; + +cleanup: + kfree(dev->policy_buf); + dev->policy_buf = NULL; + return ret; } static const struct file_operations pb_fops = { @@ -528,6 +543,12 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev) memcpy_fromio(dev->policy_buf, dev->policy_base, dev->policy_sz); + if (!amd_pmf_pb_valid(dev)) { + dev_info(dev->dev, "No Smart PC policy present\n"); + ret = -EINVAL; + goto err_free_policy; + } + amd_pmf_hex_dump_pb(dev); dev->prev_data = kzalloc(sizeof(*dev->prev_data), GFP_KERNEL); diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 0c697b46f436..47cc766624d7 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -4779,7 +4779,8 @@ static int asus_wmi_add(struct platform_device *pdev) goto fail_leds; asus_wmi_get_devstate(asus, ASUS_WMI_DEVID_WLAN, &result); - if (result & (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT)) + if ((result & (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT)) == + (ASUS_WMI_DSTS_PRESENCE_BIT | ASUS_WMI_DSTS_USER_BIT)) asus->driver->wlan_ctrl_by_user = 1; if (!(asus->driver->wlan_ctrl_by_user && ashs_present())) { diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index 5790095c175e..92b21e49faf6 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -11478,6 +11478,8 @@ static int __must_check __init get_thinkpad_model_data( tp->vendor = PCI_VENDOR_ID_IBM; else if (dmi_name_in_vendors("LENOVO")) tp->vendor = PCI_VENDOR_ID_LENOVO; + else if (dmi_name_in_vendors("NEC")) + tp->vendor = PCI_VENDOR_ID_LENOVO; else return 0; diff --git a/drivers/staging/axis-fifo/axis-fifo.c b/drivers/staging/axis-fifo/axis-fifo.c index 7540c20090c7..351f983ef914 100644 --- a/drivers/staging/axis-fifo/axis-fifo.c +++ b/drivers/staging/axis-fifo/axis-fifo.c @@ -393,16 +393,14 @@ static ssize_t axis_fifo_read(struct file *f, char __user *buf, bytes_available = ioread32(fifo->base_addr + XLLF_RLR_OFFSET); if (!bytes_available) { - dev_err(fifo->dt_device, "received a packet of length 0 - fifo core will be reset\n"); - reset_ip_core(fifo); + dev_err(fifo->dt_device, "received a packet of length 0\n"); ret = -EIO; goto end_unlock; } if (bytes_available > len) { - dev_err(fifo->dt_device, "user read buffer too small (available bytes=%zu user buffer bytes=%zu) - fifo core will be reset\n", + dev_err(fifo->dt_device, "user read buffer too small (available bytes=%zu user buffer bytes=%zu)\n", bytes_available, len); - reset_ip_core(fifo); ret = -EINVAL; goto end_unlock; } @@ -411,8 +409,7 @@ static ssize_t axis_fifo_read(struct file *f, char __user *buf, /* this probably can't happen unless IP * registers were previously mishandled */ - dev_err(fifo->dt_device, "received a packet that isn't word-aligned - fifo core will be reset\n"); - reset_ip_core(fifo); + dev_err(fifo->dt_device, "received a packet that isn't word-aligned\n"); ret = -EIO; goto end_unlock; } @@ -433,7 +430,6 @@ static ssize_t axis_fifo_read(struct file *f, char __user *buf, if (copy_to_user(buf + copied * sizeof(u32), tmp_buf, copy * sizeof(u32))) { - reset_ip_core(fifo); ret = -EFAULT; goto end_unlock; } @@ -542,7 +538,6 @@ static ssize_t axis_fifo_write(struct file *f, const char __user *buf, if (copy_from_user(tmp_buf, buf + copied * sizeof(u32), copy * sizeof(u32))) { - reset_ip_core(fifo); ret = -EFAULT; goto end_unlock; } @@ -775,9 +770,6 @@ static int axis_fifo_parse_dt(struct axis_fifo *fifo) goto end; } - /* IP sets TDFV to fifo depth - 4 so we will do the same */ - fifo->tx_fifo_depth -= 4; - ret = get_dts_property(fifo, "xlnx,use-rx-data", &fifo->has_rx_fifo); if (ret) { dev_err(fifo->dt_device, "missing xlnx,use-rx-data property\n"); diff --git a/drivers/staging/iio/adc/ad7816.c b/drivers/staging/iio/adc/ad7816.c index 6c14d7bcdd67..081b17f49863 100644 --- a/drivers/staging/iio/adc/ad7816.c +++ b/drivers/staging/iio/adc/ad7816.c @@ -136,7 +136,7 @@ static ssize_t ad7816_store_mode(struct device *dev, struct iio_dev *indio_dev = dev_to_iio_dev(dev); struct ad7816_chip_info *chip = iio_priv(indio_dev); - if (strcmp(buf, "full")) { + if (strcmp(buf, "full") == 0) { gpiod_set_value(chip->rdwr_pin, 1); chip->mode = AD7816_FULL; } else { diff --git a/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c b/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c index b839b50ac26a..fa7ea4ca4c36 100644 --- a/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c +++ b/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c @@ -1900,6 +1900,7 @@ static int bcm2835_mmal_probe(struct vchiq_device *device) __func__, ret); goto free_dev; } + dev->v4l2_dev.dev = &device->dev; /* setup v4l controls */ ret = bcm2835_mmal_init_controls(dev, &dev->ctrl_handler); diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c index 1b19b5647495..69c1df0f4ca5 100644 --- a/drivers/uio/uio_hv_generic.c +++ b/drivers/uio/uio_hv_generic.c @@ -131,15 +131,12 @@ static void hv_uio_rescind(struct vmbus_channel *channel) vmbus_device_unregister(channel->device_obj); } -/* Sysfs API to allow mmap of the ring buffers +/* Function used for mmap of ring buffer sysfs interface. * The ring buffer is allocated as contiguous memory by vmbus_open */ -static int hv_uio_ring_mmap(struct file *filp, struct kobject *kobj, - const struct bin_attribute *attr, - struct vm_area_struct *vma) +static int +hv_uio_ring_mmap(struct vmbus_channel *channel, struct vm_area_struct *vma) { - struct vmbus_channel *channel - = container_of(kobj, struct vmbus_channel, kobj); void *ring_buffer = page_address(channel->ringbuffer_page); if (channel->state != CHANNEL_OPENED_STATE) @@ -149,15 +146,6 @@ static int hv_uio_ring_mmap(struct file *filp, struct kobject *kobj, channel->ringbuffer_pagecount << PAGE_SHIFT); } -static const struct bin_attribute ring_buffer_bin_attr = { - .attr = { - .name = "ring", - .mode = 0600, - }, - .size = 2 * SZ_2M, - .mmap = hv_uio_ring_mmap, -}; - /* Callback from VMBUS subsystem when new channel created. */ static void hv_uio_new_channel(struct vmbus_channel *new_sc) @@ -178,8 +166,7 @@ hv_uio_new_channel(struct vmbus_channel *new_sc) /* Disable interrupts on sub channel */ new_sc->inbound.ring_buffer->interrupt_mask = 1; set_channel_read_mode(new_sc, HV_CALL_ISR); - - ret = sysfs_create_bin_file(&new_sc->kobj, &ring_buffer_bin_attr); + ret = hv_create_ring_sysfs(new_sc, hv_uio_ring_mmap); if (ret) { dev_err(device, "sysfs create ring bin file failed; %d\n", ret); vmbus_close(new_sc); @@ -350,10 +337,18 @@ hv_uio_probe(struct hv_device *dev, goto fail_close; } - ret = sysfs_create_bin_file(&channel->kobj, &ring_buffer_bin_attr); - if (ret) - dev_notice(&dev->device, - "sysfs create ring bin file failed; %d\n", ret); + /* + * This internally calls sysfs_update_group, which returns a non-zero value if it executes + * before sysfs_create_group. This is expected as the 'ring' will be created later in + * vmbus_device_register() -> vmbus_add_channel_kobj(). Thus, no need to check the return + * value and print warning. + * + * Creating/exposing sysfs in driver probe is not encouraged as it can lead to race + * conditions with userspace. For backward compatibility, "ring" sysfs could not be removed + * or decoupled from uio_hv_generic probe. Userspace programs can make use of inotify + * APIs to make sure that ring is created. + */ + hv_create_ring_sysfs(channel, hv_uio_ring_mmap); hv_set_drvdata(dev, pdata); @@ -375,7 +370,7 @@ hv_uio_remove(struct hv_device *dev) if (!pdata) return; - sysfs_remove_bin_file(&dev->channel->kobj, &ring_buffer_bin_attr); + hv_remove_ring_sysfs(dev->channel); uio_unregister_device(&pdata->info); hv_uio_cleanup(dev, pdata); diff --git a/drivers/usb/cdns3/cdnsp-gadget.c b/drivers/usb/cdns3/cdnsp-gadget.c index 87f310841735..4824a10df07e 100644 --- a/drivers/usb/cdns3/cdnsp-gadget.c +++ b/drivers/usb/cdns3/cdnsp-gadget.c @@ -139,6 +139,26 @@ static void cdnsp_clear_port_change_bit(struct cdnsp_device *pdev, (portsc & PORT_CHANGE_BITS), port_regs); } +static void cdnsp_set_apb_timeout_value(struct cdnsp_device *pdev) +{ + struct cdns *cdns = dev_get_drvdata(pdev->dev); + __le32 __iomem *reg; + void __iomem *base; + u32 offset = 0; + u32 val; + + if (!cdns->override_apb_timeout) + return; + + base = &pdev->cap_regs->hc_capbase; + offset = cdnsp_find_next_ext_cap(base, offset, D_XEC_PRE_REGS_CAP); + reg = base + offset + REG_CHICKEN_BITS_3_OFFSET; + + val = le32_to_cpu(readl(reg)); + val = CHICKEN_APB_TIMEOUT_SET(val, cdns->override_apb_timeout); + writel(cpu_to_le32(val), reg); +} + static void cdnsp_set_chicken_bits_2(struct cdnsp_device *pdev, u32 bit) { __le32 __iomem *reg; @@ -1773,6 +1793,8 @@ static void cdnsp_get_rev_cap(struct cdnsp_device *pdev) reg += cdnsp_find_next_ext_cap(reg, 0, RTL_REV_CAP); pdev->rev_cap = reg; + pdev->rtl_revision = readl(&pdev->rev_cap->rtl_revision); + dev_info(pdev->dev, "Rev: %08x/%08x, eps: %08x, buff: %08x/%08x\n", readl(&pdev->rev_cap->ctrl_revision), readl(&pdev->rev_cap->rtl_revision), @@ -1798,6 +1820,15 @@ static int cdnsp_gen_setup(struct cdnsp_device *pdev) pdev->hci_version = HC_VERSION(pdev->hcc_params); pdev->hcc_params = readl(&pdev->cap_regs->hcc_params); + /* + * Override the APB timeout value to give the controller more time for + * enabling UTMI clock and synchronizing APB and UTMI clock domains. + * This fix is platform specific and is required to fixes issue with + * reading incorrect value from PORTSC register after resuming + * from L1 state. + */ + cdnsp_set_apb_timeout_value(pdev); + cdnsp_get_rev_cap(pdev); /* Make sure the Device Controller is halted. */ diff --git a/drivers/usb/cdns3/cdnsp-gadget.h b/drivers/usb/cdns3/cdnsp-gadget.h index 84887dfea763..12534be52f39 100644 --- a/drivers/usb/cdns3/cdnsp-gadget.h +++ b/drivers/usb/cdns3/cdnsp-gadget.h @@ -520,6 +520,9 @@ struct cdnsp_rev_cap { #define REG_CHICKEN_BITS_2_OFFSET 0x48 #define CHICKEN_XDMA_2_TP_CACHE_DIS BIT(28) +#define REG_CHICKEN_BITS_3_OFFSET 0x4C +#define CHICKEN_APB_TIMEOUT_SET(p, val) (((p) & ~GENMASK(21, 0)) | (val)) + /* XBUF Extended Capability ID. */ #define XBUF_CAP_ID 0xCB #define XBUF_RX_TAG_MASK_0_OFFSET 0x1C @@ -1357,6 +1360,7 @@ struct cdnsp_port { * @rev_cap: Controller Capabilities Registers. * @hcs_params1: Cached register copies of read-only HCSPARAMS1 * @hcc_params: Cached register copies of read-only HCCPARAMS1 + * @rtl_revision: Cached controller rtl revision. * @setup: Temporary buffer for setup packet. * @ep0_preq: Internal allocated request used during enumeration. * @ep0_stage: ep0 stage during enumeration process. @@ -1411,6 +1415,8 @@ struct cdnsp_device { __u32 hcs_params1; __u32 hcs_params3; __u32 hcc_params; + #define RTL_REVISION_NEW_LPM 0x2700 + __u32 rtl_revision; /* Lock used in interrupt thread context. */ spinlock_t lock; struct usb_ctrlrequest setup; diff --git a/drivers/usb/cdns3/cdnsp-pci.c b/drivers/usb/cdns3/cdnsp-pci.c index a51144504ff3..8c361b8394e9 100644 --- a/drivers/usb/cdns3/cdnsp-pci.c +++ b/drivers/usb/cdns3/cdnsp-pci.c @@ -28,6 +28,8 @@ #define PCI_DRIVER_NAME "cdns-pci-usbssp" #define PLAT_DRIVER_NAME "cdns-usbssp" +#define CHICKEN_APB_TIMEOUT_VALUE 0x1C20 + static struct pci_dev *cdnsp_get_second_fun(struct pci_dev *pdev) { /* @@ -139,6 +141,14 @@ static int cdnsp_pci_probe(struct pci_dev *pdev, cdnsp->otg_irq = pdev->irq; } + /* + * Cadence PCI based platform require some longer timeout for APB + * to fixes domain clock synchronization issue after resuming + * controller from L1 state. + */ + cdnsp->override_apb_timeout = CHICKEN_APB_TIMEOUT_VALUE; + pci_set_drvdata(pdev, cdnsp); + if (pci_is_enabled(func)) { cdnsp->dev = dev; cdnsp->gadget_init = cdnsp_gadget_init; @@ -148,8 +158,6 @@ static int cdnsp_pci_probe(struct pci_dev *pdev, goto free_cdnsp; } - pci_set_drvdata(pdev, cdnsp); - device_wakeup_enable(&pdev->dev); if (pci_dev_run_wake(pdev)) pm_runtime_put_noidle(&pdev->dev); diff --git a/drivers/usb/cdns3/cdnsp-ring.c b/drivers/usb/cdns3/cdnsp-ring.c index 46852529499d..fd06cb85c4ea 100644 --- a/drivers/usb/cdns3/cdnsp-ring.c +++ b/drivers/usb/cdns3/cdnsp-ring.c @@ -308,7 +308,8 @@ static bool cdnsp_ring_ep_doorbell(struct cdnsp_device *pdev, writel(db_value, reg_addr); - cdnsp_force_l0_go(pdev); + if (pdev->rtl_revision < RTL_REVISION_NEW_LPM) + cdnsp_force_l0_go(pdev); /* Doorbell was set. */ return true; diff --git a/drivers/usb/cdns3/core.h b/drivers/usb/cdns3/core.h index 921cccf1ca9d..801be9e61340 100644 --- a/drivers/usb/cdns3/core.h +++ b/drivers/usb/cdns3/core.h @@ -79,6 +79,8 @@ struct cdns3_platform_data { * @pdata: platform data from glue layer * @lock: spinlock structure * @xhci_plat_data: xhci private data structure pointer + * @override_apb_timeout: hold value of APB timeout. For value 0 the default + * value in CHICKEN_BITS_3 will be preserved. * @gadget_init: pointer to gadget initialization function */ struct cdns { @@ -117,6 +119,7 @@ struct cdns { struct cdns3_platform_data *pdata; spinlock_t lock; struct xhci_plat_priv *xhci_plat_data; + u32 override_apb_timeout; int (*gadget_init)(struct cdns *cdns); }; diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c index 34e46ef308ab..740d2d2b19fb 100644 --- a/drivers/usb/class/usbtmc.c +++ b/drivers/usb/class/usbtmc.c @@ -482,6 +482,7 @@ static int usbtmc_get_stb(struct usbtmc_file_data *file_data, __u8 *stb) u8 *buffer; u8 tag; int rv; + long wait_rv; dev_dbg(dev, "Enter ioctl_read_stb iin_ep_present: %d\n", data->iin_ep_present); @@ -511,16 +512,17 @@ static int usbtmc_get_stb(struct usbtmc_file_data *file_data, __u8 *stb) } if (data->iin_ep_present) { - rv = wait_event_interruptible_timeout( + wait_rv = wait_event_interruptible_timeout( data->waitq, atomic_read(&data->iin_data_valid) != 0, file_data->timeout); - if (rv < 0) { - dev_dbg(dev, "wait interrupted %d\n", rv); + if (wait_rv < 0) { + dev_dbg(dev, "wait interrupted %ld\n", wait_rv); + rv = wait_rv; goto exit; } - if (rv == 0) { + if (wait_rv == 0) { dev_dbg(dev, "wait timed out\n"); rv = -ETIMEDOUT; goto exit; @@ -539,6 +541,8 @@ static int usbtmc_get_stb(struct usbtmc_file_data *file_data, __u8 *stb) dev_dbg(dev, "stb:0x%02x received %d\n", (unsigned int)*stb, rv); + rv = 0; + exit: /* bump interrupt bTag */ data->iin_bTag += 1; @@ -602,9 +606,9 @@ static int usbtmc488_ioctl_wait_srq(struct usbtmc_file_data *file_data, { struct usbtmc_device_data *data = file_data->data; struct device *dev = &data->intf->dev; - int rv; u32 timeout; unsigned long expire; + long wait_rv; if (!data->iin_ep_present) { dev_dbg(dev, "no interrupt endpoint present\n"); @@ -618,25 +622,24 @@ static int usbtmc488_ioctl_wait_srq(struct usbtmc_file_data *file_data, mutex_unlock(&data->io_mutex); - rv = wait_event_interruptible_timeout( - data->waitq, - atomic_read(&file_data->srq_asserted) != 0 || - atomic_read(&file_data->closing), - expire); + wait_rv = wait_event_interruptible_timeout( + data->waitq, + atomic_read(&file_data->srq_asserted) != 0 || + atomic_read(&file_data->closing), + expire); mutex_lock(&data->io_mutex); /* Note! disconnect or close could be called in the meantime */ if (atomic_read(&file_data->closing) || data->zombie) - rv = -ENODEV; + return -ENODEV; - if (rv < 0) { - /* dev can be invalid now! */ - pr_debug("%s - wait interrupted %d\n", __func__, rv); - return rv; + if (wait_rv < 0) { + dev_dbg(dev, "%s - wait interrupted %ld\n", __func__, wait_rv); + return wait_rv; } - if (rv == 0) { + if (wait_rv == 0) { dev_dbg(dev, "%s - wait timed out\n", __func__); return -ETIMEDOUT; } @@ -830,6 +833,7 @@ static ssize_t usbtmc_generic_read(struct usbtmc_file_data *file_data, unsigned long expire; int bufcount = 1; int again = 0; + long wait_rv; /* mutex already locked */ @@ -942,19 +946,24 @@ static ssize_t usbtmc_generic_read(struct usbtmc_file_data *file_data, if (!(flags & USBTMC_FLAG_ASYNC)) { dev_dbg(dev, "%s: before wait time %lu\n", __func__, expire); - retval = wait_event_interruptible_timeout( + wait_rv = wait_event_interruptible_timeout( file_data->wait_bulk_in, usbtmc_do_transfer(file_data), expire); - dev_dbg(dev, "%s: wait returned %d\n", - __func__, retval); + dev_dbg(dev, "%s: wait returned %ld\n", + __func__, wait_rv); + + if (wait_rv < 0) { + retval = wait_rv; + goto error; + } - if (retval <= 0) { - if (retval == 0) - retval = -ETIMEDOUT; + if (wait_rv == 0) { + retval = -ETIMEDOUT; goto error; } + } urb = usb_get_from_anchor(&file_data->in_anchor); @@ -1380,7 +1389,10 @@ static ssize_t usbtmc_read(struct file *filp, char __user *buf, if (!buffer) return -ENOMEM; - mutex_lock(&data->io_mutex); + retval = mutex_lock_interruptible(&data->io_mutex); + if (retval < 0) + goto exit_nolock; + if (data->zombie) { retval = -ENODEV; goto exit; @@ -1503,6 +1515,7 @@ static ssize_t usbtmc_read(struct file *filp, char __user *buf, exit: mutex_unlock(&data->io_mutex); +exit_nolock: kfree(buffer); return retval; } diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h index aaa39e663f60..27eae4cf223d 100644 --- a/drivers/usb/dwc3/core.h +++ b/drivers/usb/dwc3/core.h @@ -1164,6 +1164,9 @@ struct dwc3_scratchpad_array { * @gsbuscfg0_reqinfo: store GSBUSCFG0.DATRDREQINFO, DESRDREQINFO, * DATWRREQINFO, and DESWRREQINFO value passed from * glue driver. + * @wakeup_pending_funcs: Indicates whether any interface has requested for + * function wakeup in bitmap format where bit position + * represents interface_id. */ struct dwc3 { struct work_struct drd_work; @@ -1394,6 +1397,7 @@ struct dwc3 { int num_ep_resized; struct dentry *debug_root; u32 gsbuscfg0_reqinfo; + u32 wakeup_pending_funcs; }; #define INCRX_BURST_MODE 0 diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index 8c30d86cc4e3..321361288935 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -276,8 +276,6 @@ int dwc3_send_gadget_generic_command(struct dwc3 *dwc, unsigned int cmd, return ret; } -static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async); - /** * dwc3_send_gadget_ep_cmd - issue an endpoint command * @dep: the endpoint to which the command is going to be issued @@ -2359,10 +2357,8 @@ static int dwc3_gadget_get_frame(struct usb_gadget *g) return __dwc3_gadget_get_frame(dwc); } -static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async) +static int __dwc3_gadget_wakeup(struct dwc3 *dwc) { - int retries; - int ret; u32 reg; @@ -2390,8 +2386,7 @@ static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async) return -EINVAL; } - if (async) - dwc3_gadget_enable_linksts_evts(dwc, true); + dwc3_gadget_enable_linksts_evts(dwc, true); ret = dwc3_gadget_set_link_state(dwc, DWC3_LINK_STATE_RECOV); if (ret < 0) { @@ -2410,27 +2405,8 @@ static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async) /* * Since link status change events are enabled we will receive - * an U0 event when wakeup is successful. So bail out. + * an U0 event when wakeup is successful. */ - if (async) - return 0; - - /* poll until Link State changes to ON */ - retries = 20000; - - while (retries--) { - reg = dwc3_readl(dwc->regs, DWC3_DSTS); - - /* in HS, means ON */ - if (DWC3_DSTS_USBLNKST(reg) == DWC3_LINK_STATE_U0) - break; - } - - if (DWC3_DSTS_USBLNKST(reg) != DWC3_LINK_STATE_U0) { - dev_err(dwc->dev, "failed to send remote wakeup\n"); - return -EINVAL; - } - return 0; } @@ -2451,7 +2427,7 @@ static int dwc3_gadget_wakeup(struct usb_gadget *g) spin_unlock_irqrestore(&dwc->lock, flags); return -EINVAL; } - ret = __dwc3_gadget_wakeup(dwc, true); + ret = __dwc3_gadget_wakeup(dwc); spin_unlock_irqrestore(&dwc->lock, flags); @@ -2479,14 +2455,10 @@ static int dwc3_gadget_func_wakeup(struct usb_gadget *g, int intf_id) */ link_state = dwc3_gadget_get_link_state(dwc); if (link_state == DWC3_LINK_STATE_U3) { - ret = __dwc3_gadget_wakeup(dwc, false); - if (ret) { - spin_unlock_irqrestore(&dwc->lock, flags); - return -EINVAL; - } - dwc3_resume_gadget(dwc); - dwc->suspended = false; - dwc->link_state = DWC3_LINK_STATE_U0; + dwc->wakeup_pending_funcs |= BIT(intf_id); + ret = __dwc3_gadget_wakeup(dwc); + spin_unlock_irqrestore(&dwc->lock, flags); + return ret; } ret = dwc3_send_gadget_generic_command(dwc, DWC3_DGCMD_DEV_NOTIFICATION, @@ -4353,6 +4325,8 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc, { enum dwc3_link_state next = evtinfo & DWC3_LINK_STATE_MASK; unsigned int pwropt; + int ret; + int intf_id; /* * WORKAROUND: DWC3 < 2.50a have an issue when configured without @@ -4428,7 +4402,7 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc, switch (next) { case DWC3_LINK_STATE_U0: - if (dwc->gadget->wakeup_armed) { + if (dwc->gadget->wakeup_armed || dwc->wakeup_pending_funcs) { dwc3_gadget_enable_linksts_evts(dwc, false); dwc3_resume_gadget(dwc); dwc->suspended = false; @@ -4451,6 +4425,18 @@ static void dwc3_gadget_linksts_change_interrupt(struct dwc3 *dwc, } dwc->link_state = next; + + /* Proceed with func wakeup if any interfaces that has requested */ + while (dwc->wakeup_pending_funcs && (next == DWC3_LINK_STATE_U0)) { + intf_id = ffs(dwc->wakeup_pending_funcs) - 1; + ret = dwc3_send_gadget_generic_command(dwc, DWC3_DGCMD_DEV_NOTIFICATION, + DWC3_DGCMDPAR_DN_FUNC_WAKE | + DWC3_DGCMDPAR_INTF_SEL(intf_id)); + if (ret) + dev_err(dwc->dev, "Failed to send DN wake for intf %d\n", intf_id); + + dwc->wakeup_pending_funcs &= ~BIT(intf_id); + } } static void dwc3_gadget_suspend_interrupt(struct dwc3 *dwc, diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c index 869ad99afb48..8dbc132a505e 100644 --- a/drivers/usb/gadget/composite.c +++ b/drivers/usb/gadget/composite.c @@ -2011,15 +2011,13 @@ composite_setup(struct usb_gadget *gadget, const struct usb_ctrlrequest *ctrl) if (f->get_status) { status = f->get_status(f); + if (status < 0) break; - } else { - /* Set D0 and D1 bits based on func wakeup capability */ - if (f->config->bmAttributes & USB_CONFIG_ATT_WAKEUP) { - status |= USB_INTRF_STAT_FUNC_RW_CAP; - if (f->func_wakeup_armed) - status |= USB_INTRF_STAT_FUNC_RW; - } + + /* if D5 is not set, then device is not wakeup capable */ + if (!(f->config->bmAttributes & USB_CONFIG_ATT_WAKEUP)) + status &= ~(USB_INTRF_STAT_FUNC_RW_CAP | USB_INTRF_STAT_FUNC_RW); } put_unaligned_le16(status & 0x0000ffff, req->buf); diff --git a/drivers/usb/gadget/function/f_ecm.c b/drivers/usb/gadget/function/f_ecm.c index 80841de845b0..027226325039 100644 --- a/drivers/usb/gadget/function/f_ecm.c +++ b/drivers/usb/gadget/function/f_ecm.c @@ -892,6 +892,12 @@ static void ecm_resume(struct usb_function *f) gether_resume(&ecm->port); } +static int ecm_get_status(struct usb_function *f) +{ + return (f->func_wakeup_armed ? USB_INTRF_STAT_FUNC_RW : 0) | + USB_INTRF_STAT_FUNC_RW_CAP; +} + static void ecm_free(struct usb_function *f) { struct f_ecm *ecm; @@ -960,6 +966,7 @@ static struct usb_function *ecm_alloc(struct usb_function_instance *fi) ecm->port.func.disable = ecm_disable; ecm->port.func.free_func = ecm_free; ecm->port.func.suspend = ecm_suspend; + ecm->port.func.get_status = ecm_get_status; ecm->port.func.resume = ecm_resume; return &ecm->port.func; diff --git a/drivers/usb/gadget/udc/tegra-xudc.c b/drivers/usb/gadget/udc/tegra-xudc.c index c7fdbc55fb0b..2957316fd3d0 100644 --- a/drivers/usb/gadget/udc/tegra-xudc.c +++ b/drivers/usb/gadget/udc/tegra-xudc.c @@ -1749,6 +1749,10 @@ static int __tegra_xudc_ep_disable(struct tegra_xudc_ep *ep) val = xudc_readl(xudc, CTRL); val &= ~CTRL_RUN; xudc_writel(xudc, val, CTRL); + + val = xudc_readl(xudc, ST); + if (val & ST_RC) + xudc_writel(xudc, ST_RC, ST); } dev_info(xudc->dev, "ep %u disabled\n", ep->index); diff --git a/drivers/usb/host/uhci-platform.c b/drivers/usb/host/uhci-platform.c index a7c934404ebc..62318291f566 100644 --- a/drivers/usb/host/uhci-platform.c +++ b/drivers/usb/host/uhci-platform.c @@ -121,7 +121,7 @@ static int uhci_hcd_platform_probe(struct platform_device *pdev) } /* Get and enable clock if any specified */ - uhci->clk = devm_clk_get(&pdev->dev, NULL); + uhci->clk = devm_clk_get_optional(&pdev->dev, NULL); if (IS_ERR(uhci->clk)) { ret = PTR_ERR(uhci->clk); goto err_rmr; diff --git a/drivers/usb/host/xhci-dbgcap.c b/drivers/usb/host/xhci-dbgcap.c index fd7895b24367..0d4ce5734165 100644 --- a/drivers/usb/host/xhci-dbgcap.c +++ b/drivers/usb/host/xhci-dbgcap.c @@ -823,6 +823,7 @@ static enum evtreturn xhci_dbc_do_handle_events(struct xhci_dbc *dbc) { dma_addr_t deq; union xhci_trb *evt; + enum evtreturn ret = EVT_DONE; u32 ctrl, portsc; bool update_erdp = false; @@ -909,6 +910,7 @@ static enum evtreturn xhci_dbc_do_handle_events(struct xhci_dbc *dbc) break; case TRB_TYPE(TRB_TRANSFER): dbc_handle_xfer_event(dbc, evt); + ret = EVT_XFER_DONE; break; default: break; @@ -927,7 +929,7 @@ static enum evtreturn xhci_dbc_do_handle_events(struct xhci_dbc *dbc) lo_hi_writeq(deq, &dbc->regs->erdp); } - return EVT_DONE; + return ret; } static void xhci_dbc_handle_events(struct work_struct *work) @@ -936,6 +938,7 @@ static void xhci_dbc_handle_events(struct work_struct *work) struct xhci_dbc *dbc; unsigned long flags; unsigned int poll_interval; + unsigned long busypoll_timelimit; dbc = container_of(to_delayed_work(work), struct xhci_dbc, event_work); poll_interval = dbc->poll_interval; @@ -954,11 +957,21 @@ static void xhci_dbc_handle_events(struct work_struct *work) dbc->driver->disconnect(dbc); break; case EVT_DONE: - /* set fast poll rate if there are pending data transfers */ + /* + * Set fast poll rate if there are pending out transfers, or + * a transfer was recently processed + */ + busypoll_timelimit = dbc->xfer_timestamp + + msecs_to_jiffies(DBC_XFER_INACTIVITY_TIMEOUT); + if (!list_empty(&dbc->eps[BULK_OUT].list_pending) || - !list_empty(&dbc->eps[BULK_IN].list_pending)) + time_is_after_jiffies(busypoll_timelimit)) poll_interval = 0; break; + case EVT_XFER_DONE: + dbc->xfer_timestamp = jiffies; + poll_interval = 0; + break; default: dev_info(dbc->dev, "stop handling dbc events\n"); return; diff --git a/drivers/usb/host/xhci-dbgcap.h b/drivers/usb/host/xhci-dbgcap.h index 9dc8f4d8077c..47ac72c2286d 100644 --- a/drivers/usb/host/xhci-dbgcap.h +++ b/drivers/usb/host/xhci-dbgcap.h @@ -96,6 +96,7 @@ struct dbc_ep { #define DBC_WRITE_BUF_SIZE 8192 #define DBC_POLL_INTERVAL_DEFAULT 64 /* milliseconds */ #define DBC_POLL_INTERVAL_MAX 5000 /* milliseconds */ +#define DBC_XFER_INACTIVITY_TIMEOUT 10 /* milliseconds */ /* * Private structure for DbC hardware state: */ @@ -142,6 +143,7 @@ struct xhci_dbc { enum dbc_state state; struct delayed_work event_work; unsigned int poll_interval; /* ms */ + unsigned long xfer_timestamp; unsigned resume_required:1; struct dbc_ep eps[2]; @@ -187,6 +189,7 @@ struct dbc_request { enum evtreturn { EVT_ERR = -1, EVT_DONE, + EVT_XFER_DONE, EVT_GSER, EVT_DISC, }; diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index b906bc2eea5f..423bf3649570 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -699,7 +699,7 @@ static int xhci_move_dequeue_past_td(struct xhci_hcd *xhci, int new_cycle; dma_addr_t addr; u64 hw_dequeue; - bool cycle_found = false; + bool hw_dequeue_found = false; bool td_last_trb_found = false; u32 trb_sct = 0; int ret; @@ -715,25 +715,24 @@ static int xhci_move_dequeue_past_td(struct xhci_hcd *xhci, hw_dequeue = xhci_get_hw_deq(xhci, dev, ep_index, stream_id); new_seg = ep_ring->deq_seg; new_deq = ep_ring->dequeue; - new_cycle = hw_dequeue & 0x1; + new_cycle = le32_to_cpu(td->end_trb->generic.field[3]) & TRB_CYCLE; /* - * We want to find the pointer, segment and cycle state of the new trb - * (the one after current TD's end_trb). We know the cycle state at - * hw_dequeue, so walk the ring until both hw_dequeue and end_trb are - * found. + * Walk the ring until both the next TRB and hw_dequeue are found (don't + * move hw_dequeue back if it went forward due to a HW bug). Cycle state + * is loaded from a known good TRB, track later toggles to maintain it. */ do { - if (!cycle_found && xhci_trb_virt_to_dma(new_seg, new_deq) + if (!hw_dequeue_found && xhci_trb_virt_to_dma(new_seg, new_deq) == (dma_addr_t)(hw_dequeue & ~0xf)) { - cycle_found = true; + hw_dequeue_found = true; if (td_last_trb_found) break; } if (new_deq == td->end_trb) td_last_trb_found = true; - if (cycle_found && trb_is_link(new_deq) && + if (td_last_trb_found && trb_is_link(new_deq) && link_trb_toggles_cycle(new_deq)) new_cycle ^= 0x1; @@ -745,7 +744,7 @@ static int xhci_move_dequeue_past_td(struct xhci_hcd *xhci, return -EINVAL; } - } while (!cycle_found || !td_last_trb_found); + } while (!hw_dequeue_found || !td_last_trb_found); /* Don't update the ring cycle state for the producer (us). */ addr = xhci_trb_virt_to_dma(new_seg, new_deq); diff --git a/drivers/usb/host/xhci-tegra.c b/drivers/usb/host/xhci-tegra.c index b5c362c2051d..0c7af44d4dae 100644 --- a/drivers/usb/host/xhci-tegra.c +++ b/drivers/usb/host/xhci-tegra.c @@ -1364,6 +1364,7 @@ static void tegra_xhci_id_work(struct work_struct *work) tegra->otg_usb3_port = tegra_xusb_padctl_get_usb3_companion(tegra->padctl, tegra->otg_usb2_port); + pm_runtime_get_sync(tegra->dev); if (tegra->host_mode) { /* switch to host mode */ if (tegra->otg_usb3_port >= 0) { @@ -1393,6 +1394,7 @@ static void tegra_xhci_id_work(struct work_struct *work) } tegra_xhci_set_port_power(tegra, true, true); + pm_runtime_mark_last_busy(tegra->dev); } else { if (tegra->otg_usb3_port >= 0) @@ -1400,6 +1402,7 @@ static void tegra_xhci_id_work(struct work_struct *work) tegra_xhci_set_port_power(tegra, true, false); } + pm_runtime_put_autosuspend(tegra->dev); } #if IS_ENABLED(CONFIG_PM) || IS_ENABLED(CONFIG_PM_SLEEP) diff --git a/drivers/usb/misc/onboard_usb_dev.c b/drivers/usb/misc/onboard_usb_dev.c index 75ac3c6aa92d..f5372dfa241a 100644 --- a/drivers/usb/misc/onboard_usb_dev.c +++ b/drivers/usb/misc/onboard_usb_dev.c @@ -569,8 +569,14 @@ static void onboard_dev_usbdev_disconnect(struct usb_device *udev) } static const struct usb_device_id onboard_dev_id_table[] = { - { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6504) }, /* CYUSB33{0,1,2}x/CYUSB230x 3.0 HUB */ - { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6506) }, /* CYUSB33{0,1,2}x/CYUSB230x 2.0 HUB */ + { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6500) }, /* CYUSB330x 3.0 HUB */ + { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6502) }, /* CYUSB330x 2.0 HUB */ + { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6503) }, /* CYUSB33{0,1}x 2.0 HUB, Vendor Mode */ + { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6504) }, /* CYUSB331x 3.0 HUB */ + { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6506) }, /* CYUSB331x 2.0 HUB */ + { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6507) }, /* CYUSB332x 2.0 HUB, Vendor Mode */ + { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6508) }, /* CYUSB332x 3.0 HUB */ + { USB_DEVICE(VENDOR_ID_CYPRESS, 0x650a) }, /* CYUSB332x 2.0 HUB */ { USB_DEVICE(VENDOR_ID_CYPRESS, 0x6570) }, /* CY7C6563x 2.0 HUB */ { USB_DEVICE(VENDOR_ID_GENESYS, 0x0608) }, /* Genesys Logic GL850G USB 2.0 HUB */ { USB_DEVICE(VENDOR_ID_GENESYS, 0x0610) }, /* Genesys Logic GL852G USB 2.0 HUB */ diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c index a99db4e025cd..8adf6f954633 100644 --- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -5965,7 +5965,7 @@ static void _tcpm_cc_change(struct tcpm_port *port, enum typec_cc_status cc1, case SNK_TRY_WAIT_DEBOUNCE: if (!tcpm_port_is_sink(port)) { port->max_wait = 0; - tcpm_set_state(port, SRC_TRYWAIT, 0); + tcpm_set_state(port, SRC_TRYWAIT, PD_T_PD_DEBOUNCE); } break; case SRC_TRY_WAIT: diff --git a/drivers/usb/typec/ucsi/displayport.c b/drivers/usb/typec/ucsi/displayport.c index 420af5139c70..8aae80b457d7 100644 --- a/drivers/usb/typec/ucsi/displayport.c +++ b/drivers/usb/typec/ucsi/displayport.c @@ -54,7 +54,8 @@ static int ucsi_displayport_enter(struct typec_altmode *alt, u32 *vdo) u8 cur = 0; int ret; - mutex_lock(&dp->con->lock); + if (!ucsi_con_mutex_lock(dp->con)) + return -ENOTCONN; if (!dp->override && dp->initialized) { const struct typec_altmode *p = typec_altmode_get_partner(alt); @@ -100,7 +101,7 @@ static int ucsi_displayport_enter(struct typec_altmode *alt, u32 *vdo) schedule_work(&dp->work); ret = 0; err_unlock: - mutex_unlock(&dp->con->lock); + ucsi_con_mutex_unlock(dp->con); return ret; } @@ -112,7 +113,8 @@ static int ucsi_displayport_exit(struct typec_altmode *alt) u64 command; int ret = 0; - mutex_lock(&dp->con->lock); + if (!ucsi_con_mutex_lock(dp->con)) + return -ENOTCONN; if (!dp->override) { const struct typec_altmode *p = typec_altmode_get_partner(alt); @@ -144,7 +146,7 @@ static int ucsi_displayport_exit(struct typec_altmode *alt) schedule_work(&dp->work); out_unlock: - mutex_unlock(&dp->con->lock); + ucsi_con_mutex_unlock(dp->con); return ret; } @@ -202,20 +204,21 @@ static int ucsi_displayport_vdm(struct typec_altmode *alt, int cmd = PD_VDO_CMD(header); int svdm_version; - mutex_lock(&dp->con->lock); + if (!ucsi_con_mutex_lock(dp->con)) + return -ENOTCONN; if (!dp->override && dp->initialized) { const struct typec_altmode *p = typec_altmode_get_partner(alt); dev_warn(&p->dev, "firmware doesn't support alternate mode overriding\n"); - mutex_unlock(&dp->con->lock); + ucsi_con_mutex_unlock(dp->con); return -EOPNOTSUPP; } svdm_version = typec_altmode_get_svdm_version(alt); if (svdm_version < 0) { - mutex_unlock(&dp->con->lock); + ucsi_con_mutex_unlock(dp->con); return svdm_version; } @@ -259,7 +262,7 @@ static int ucsi_displayport_vdm(struct typec_altmode *alt, break; } - mutex_unlock(&dp->con->lock); + ucsi_con_mutex_unlock(dp->con); return 0; } @@ -296,6 +299,8 @@ void ucsi_displayport_remove_partner(struct typec_altmode *alt) if (!dp) return; + cancel_work_sync(&dp->work); + dp->data.conf = 0; dp->data.status = 0; dp->initialized = false; diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index e8c7e9dc4930..01ce858a1a2b 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -1923,6 +1923,40 @@ void ucsi_set_drvdata(struct ucsi *ucsi, void *data) EXPORT_SYMBOL_GPL(ucsi_set_drvdata); /** + * ucsi_con_mutex_lock - Acquire the connector mutex + * @con: The connector interface to lock + * + * Returns true on success, false if the connector is disconnected + */ +bool ucsi_con_mutex_lock(struct ucsi_connector *con) +{ + bool mutex_locked = false; + bool connected = true; + + while (connected && !mutex_locked) { + mutex_locked = mutex_trylock(&con->lock) != 0; + connected = UCSI_CONSTAT(con, CONNECTED); + if (connected && !mutex_locked) + msleep(20); + } + + connected = connected && con->partner; + if (!connected && mutex_locked) + mutex_unlock(&con->lock); + + return connected; +} + +/** + * ucsi_con_mutex_unlock - Release the connector mutex + * @con: The connector interface to unlock + */ +void ucsi_con_mutex_unlock(struct ucsi_connector *con) +{ + mutex_unlock(&con->lock); +} + +/** * ucsi_create - Allocate UCSI instance * @dev: Device interface to the PPM (Platform Policy Manager) * @ops: I/O routines diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h index 3a2c1762bec1..9c5278a0c5d4 100644 --- a/drivers/usb/typec/ucsi/ucsi.h +++ b/drivers/usb/typec/ucsi/ucsi.h @@ -94,6 +94,8 @@ int ucsi_register(struct ucsi *ucsi); void ucsi_unregister(struct ucsi *ucsi); void *ucsi_get_drvdata(struct ucsi *ucsi); void ucsi_set_drvdata(struct ucsi *ucsi, void *data); +bool ucsi_con_mutex_lock(struct ucsi_connector *con); +void ucsi_con_mutex_unlock(struct ucsi_connector *con); void ucsi_connector_change(struct ucsi *ucsi, u8 num); diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 1f65795cf5d7..ef56a2500ed6 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -217,6 +217,7 @@ static dma_addr_t xen_swiotlb_map_page(struct device *dev, struct page *page, * buffering it. */ if (dma_capable(dev, dev_addr, size, true) && + !dma_kmalloc_needs_bounce(dev, size, dir) && !range_straddles_page_boundary(phys, size) && !xen_arch_need_swiotlb(dev, phys, dev_addr) && !is_swiotlb_force_bounce(dev)) diff --git a/drivers/xen/xenbus/xenbus.h b/drivers/xen/xenbus/xenbus.h index 13821e7e825e..9ac0427724a3 100644 --- a/drivers/xen/xenbus/xenbus.h +++ b/drivers/xen/xenbus/xenbus.h @@ -77,6 +77,7 @@ enum xb_req_state { struct xb_req_data { struct list_head list; wait_queue_head_t wq; + struct kref kref; struct xsd_sockmsg msg; uint32_t caller_req_id; enum xsd_sockmsg_type type; @@ -103,6 +104,7 @@ int xb_init_comms(void); void xb_deinit_comms(void); int xs_watch_msg(struct xs_watch_event *event); void xs_request_exit(struct xb_req_data *req); +void xs_free_req(struct kref *kref); int xenbus_match(struct device *_dev, const struct device_driver *_drv); int xenbus_dev_probe(struct device *_dev); diff --git a/drivers/xen/xenbus/xenbus_comms.c b/drivers/xen/xenbus/xenbus_comms.c index e5fda0256feb..82df2da1b880 100644 --- a/drivers/xen/xenbus/xenbus_comms.c +++ b/drivers/xen/xenbus/xenbus_comms.c @@ -309,8 +309,8 @@ static int process_msg(void) virt_wmb(); req->state = xb_req_state_got_reply; req->cb(req); - } else - kfree(req); + } + kref_put(&req->kref, xs_free_req); } mutex_unlock(&xs_response_mutex); @@ -386,14 +386,13 @@ static int process_writes(void) state.req->msg.type = XS_ERROR; state.req->err = err; list_del(&state.req->list); - if (state.req->state == xb_req_state_aborted) - kfree(state.req); - else { + if (state.req->state != xb_req_state_aborted) { /* write err, then update state */ virt_wmb(); state.req->state = xb_req_state_got_reply; wake_up(&state.req->wq); } + kref_put(&state.req->kref, xs_free_req); mutex_unlock(&xb_write_mutex); diff --git a/drivers/xen/xenbus/xenbus_dev_frontend.c b/drivers/xen/xenbus/xenbus_dev_frontend.c index 46f8916597e5..f5c21ba64df5 100644 --- a/drivers/xen/xenbus/xenbus_dev_frontend.c +++ b/drivers/xen/xenbus/xenbus_dev_frontend.c @@ -406,7 +406,7 @@ void xenbus_dev_queue_reply(struct xb_req_data *req) mutex_unlock(&u->reply_mutex); kfree(req->body); - kfree(req); + kref_put(&req->kref, xs_free_req); kref_put(&u->kref, xenbus_file_free); diff --git a/drivers/xen/xenbus/xenbus_probe.c b/drivers/xen/xenbus/xenbus_probe.c index 6d32ffb01136..86fe6e779056 100644 --- a/drivers/xen/xenbus/xenbus_probe.c +++ b/drivers/xen/xenbus/xenbus_probe.c @@ -966,9 +966,15 @@ static int __init xenbus_init(void) if (xen_pv_domain()) xen_store_domain_type = XS_PV; if (xen_hvm_domain()) + { xen_store_domain_type = XS_HVM; - if (xen_hvm_domain() && xen_initial_domain()) - xen_store_domain_type = XS_LOCAL; + err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v); + if (err) + goto out_error; + xen_store_evtchn = (int)v; + if (!v && xen_initial_domain()) + xen_store_domain_type = XS_LOCAL; + } if (xen_pv_domain() && !xen_start_info->store_evtchn) xen_store_domain_type = XS_LOCAL; if (xen_pv_domain() && xen_start_info->store_evtchn) @@ -987,10 +993,6 @@ static int __init xenbus_init(void) xen_store_interface = gfn_to_virt(xen_store_gfn); break; case XS_HVM: - err = hvm_get_parameter(HVM_PARAM_STORE_EVTCHN, &v); - if (err) - goto out_error; - xen_store_evtchn = (int)v; err = hvm_get_parameter(HVM_PARAM_STORE_PFN, &v); if (err) goto out_error; diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index d32c726f7a12..dcf9182c8451 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -112,6 +112,12 @@ static void xs_suspend_exit(void) wake_up_all(&xs_state_enter_wq); } +void xs_free_req(struct kref *kref) +{ + struct xb_req_data *req = container_of(kref, struct xb_req_data, kref); + kfree(req); +} + static uint32_t xs_request_enter(struct xb_req_data *req) { uint32_t rq_id; @@ -237,6 +243,12 @@ static void xs_send(struct xb_req_data *req, struct xsd_sockmsg *msg) req->caller_req_id = req->msg.req_id; req->msg.req_id = xs_request_enter(req); + /* + * Take 2nd ref. One for this thread, and the second for the + * xenbus_thread. + */ + kref_get(&req->kref); + mutex_lock(&xb_write_mutex); list_add_tail(&req->list, &xb_write_list); notify = list_is_singular(&xb_write_list); @@ -261,8 +273,8 @@ static void *xs_wait_for_reply(struct xb_req_data *req, struct xsd_sockmsg *msg) if (req->state == xb_req_state_queued || req->state == xb_req_state_wait_reply) req->state = xb_req_state_aborted; - else - kfree(req); + + kref_put(&req->kref, xs_free_req); mutex_unlock(&xb_write_mutex); return ret; @@ -291,6 +303,7 @@ int xenbus_dev_request_and_reply(struct xsd_sockmsg *msg, void *par) req->cb = xenbus_dev_queue_reply; req->par = par; req->user_req = true; + kref_init(&req->kref); xs_send(req, msg); @@ -319,6 +332,7 @@ static void *xs_talkv(struct xenbus_transaction t, req->num_vecs = num_vecs; req->cb = xs_wake_up; req->user_req = false; + kref_init(&req->kref); msg.req_id = 0; msg.tx_id = t.id; diff --git a/fs/buffer.c b/fs/buffer.c index 7be23ff20b27..7ba1807145aa 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1220,10 +1220,8 @@ void mark_buffer_write_io_error(struct buffer_head *bh) /* FIXME: do we need to set this in both places? */ if (bh->b_folio && bh->b_folio->mapping) mapping_set_error(bh->b_folio->mapping, -EIO); - if (bh->b_assoc_map) { + if (bh->b_assoc_map) mapping_set_error(bh->b_assoc_map, -EIO); - errseq_set(&bh->b_assoc_map->host->i_sb->s_wb_err, -EIO); - } } EXPORT_SYMBOL(mark_buffer_write_io_error); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 4bc264b854c4..d4dbffdedd08 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -2111,9 +2111,10 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, write_unlock_irq(&ep->lock); - if (!eavail && ep_schedule_timeout(to)) - timed_out = !schedule_hrtimeout_range(to, slack, - HRTIMER_MODE_ABS); + if (!eavail) + timed_out = !ep_schedule_timeout(to) || + !schedule_hrtimeout_range(to, slack, + HRTIMER_MODE_ABS); __set_current_state(TASK_RUNNING); /* diff --git a/fs/namespace.c b/fs/namespace.c index 98a5cd756e9a..1b466c54a357 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -787,15 +787,11 @@ int __legitimize_mnt(struct vfsmount *bastard, unsigned seq) return 0; mnt = real_mount(bastard); mnt_add_count(mnt, 1); - smp_mb(); // see mntput_no_expire() + smp_mb(); // see mntput_no_expire() and do_umount() if (likely(!read_seqretry(&mount_lock, seq))) return 0; - if (bastard->mnt_flags & MNT_SYNC_UMOUNT) { - mnt_add_count(mnt, -1); - return 1; - } lock_mount_hash(); - if (unlikely(bastard->mnt_flags & MNT_DOOMED)) { + if (unlikely(bastard->mnt_flags & (MNT_SYNC_UMOUNT | MNT_DOOMED))) { mnt_add_count(mnt, -1); unlock_mount_hash(); return 1; @@ -2048,6 +2044,7 @@ static int do_umount(struct mount *mnt, int flags) umount_tree(mnt, UMOUNT_PROPAGATE); retval = 0; } else { + smp_mb(); // paired with __legitimize_mnt() shrink_submounts(mnt); retval = -EBUSY; if (!propagate_mount_busy(mnt, 2)) { @@ -3560,7 +3557,8 @@ static int can_move_mount_beneath(const struct path *from, * @mnt_from itself. This defeats the whole purpose of mounting * @mnt_from beneath @mnt_to. */ - if (propagation_would_overmount(parent_mnt_to, mnt_from, mp)) + if (check_mnt(mnt_from) && + propagation_would_overmount(parent_mnt_to, mnt_from, mp)) return -EINVAL; return 0; @@ -3718,15 +3716,14 @@ static int do_move_mount(struct path *old_path, if (err) goto out; - if (is_anon_ns(ns)) - ns->mntns_flags &= ~MNTNS_PROPAGATING; - /* if the mount is moved, it should no longer be expire * automatically */ list_del_init(&old->mnt_expire); if (attached) put_mountpoint(old_mp); out: + if (is_anon_ns(ns)) + ns->mntns_flags &= ~MNTNS_PROPAGATING; unlock_mount(mp); if (!err) { if (attached) { diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index cb01ea81724d..d0bcf744c553 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -705,8 +705,6 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb) int blocksize; int err; - down_write(&nilfs->ns_sem); - blocksize = sb_min_blocksize(sb, NILFS_MIN_BLOCK_SIZE); if (!blocksize) { nilfs_err(sb, "unable to set blocksize"); @@ -779,7 +777,6 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb) set_nilfs_init(nilfs); err = 0; out: - up_write(&nilfs->ns_sem); return err; failed_sbh: diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c index b8ac85b548c7..821cb7874685 100644 --- a/fs/ocfs2/alloc.c +++ b/fs/ocfs2/alloc.c @@ -6918,6 +6918,7 @@ static int ocfs2_grab_folios(struct inode *inode, loff_t start, loff_t end, if (IS_ERR(folios[numfolios])) { ret = PTR_ERR(folios[numfolios]); mlog_errno(ret); + folios[numfolios] = NULL; goto out; } diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c index c7a9729dc9d0..e5f58ff2175f 100644 --- a/fs/ocfs2/journal.c +++ b/fs/ocfs2/journal.c @@ -174,7 +174,7 @@ int ocfs2_recovery_init(struct ocfs2_super *osb) struct ocfs2_recovery_map *rm; mutex_init(&osb->recovery_lock); - osb->disable_recovery = 0; + osb->recovery_state = OCFS2_REC_ENABLED; osb->recovery_thread_task = NULL; init_waitqueue_head(&osb->recovery_event); @@ -190,31 +190,53 @@ int ocfs2_recovery_init(struct ocfs2_super *osb) return 0; } -/* we can't grab the goofy sem lock from inside wait_event, so we use - * memory barriers to make sure that we'll see the null task before - * being woken up */ static int ocfs2_recovery_thread_running(struct ocfs2_super *osb) { - mb(); return osb->recovery_thread_task != NULL; } -void ocfs2_recovery_exit(struct ocfs2_super *osb) +static void ocfs2_recovery_disable(struct ocfs2_super *osb, + enum ocfs2_recovery_state state) { - struct ocfs2_recovery_map *rm; - - /* disable any new recovery threads and wait for any currently - * running ones to exit. Do this before setting the vol_state. */ mutex_lock(&osb->recovery_lock); - osb->disable_recovery = 1; + /* + * If recovery thread is not running, we can directly transition to + * final state. + */ + if (!ocfs2_recovery_thread_running(osb)) { + osb->recovery_state = state + 1; + goto out_lock; + } + osb->recovery_state = state; + /* Wait for recovery thread to acknowledge state transition */ + wait_event_cmd(osb->recovery_event, + !ocfs2_recovery_thread_running(osb) || + osb->recovery_state >= state + 1, + mutex_unlock(&osb->recovery_lock), + mutex_lock(&osb->recovery_lock)); +out_lock: mutex_unlock(&osb->recovery_lock); - wait_event(osb->recovery_event, !ocfs2_recovery_thread_running(osb)); - /* At this point, we know that no more recovery threads can be - * launched, so wait for any recovery completion work to - * complete. */ + /* + * At this point we know that no more recovery work can be queued so + * wait for any recovery completion work to complete. + */ if (osb->ocfs2_wq) flush_workqueue(osb->ocfs2_wq); +} + +void ocfs2_recovery_disable_quota(struct ocfs2_super *osb) +{ + ocfs2_recovery_disable(osb, OCFS2_REC_QUOTA_WANT_DISABLE); +} + +void ocfs2_recovery_exit(struct ocfs2_super *osb) +{ + struct ocfs2_recovery_map *rm; + + /* disable any new recovery threads and wait for any currently + * running ones to exit. Do this before setting the vol_state. */ + ocfs2_recovery_disable(osb, OCFS2_REC_WANT_DISABLE); /* * Now that recovery is shut down, and the osb is about to be @@ -1472,6 +1494,18 @@ static int __ocfs2_recovery_thread(void *arg) } } restart: + if (quota_enabled) { + mutex_lock(&osb->recovery_lock); + /* Confirm that recovery thread will no longer recover quotas */ + if (osb->recovery_state == OCFS2_REC_QUOTA_WANT_DISABLE) { + osb->recovery_state = OCFS2_REC_QUOTA_DISABLED; + wake_up(&osb->recovery_event); + } + if (osb->recovery_state >= OCFS2_REC_QUOTA_DISABLED) + quota_enabled = 0; + mutex_unlock(&osb->recovery_lock); + } + status = ocfs2_super_lock(osb, 1); if (status < 0) { mlog_errno(status); @@ -1569,27 +1603,29 @@ bail: ocfs2_free_replay_slots(osb); osb->recovery_thread_task = NULL; - mb(); /* sync with ocfs2_recovery_thread_running */ + if (osb->recovery_state == OCFS2_REC_WANT_DISABLE) + osb->recovery_state = OCFS2_REC_DISABLED; wake_up(&osb->recovery_event); mutex_unlock(&osb->recovery_lock); - if (quota_enabled) - kfree(rm_quota); + kfree(rm_quota); return status; } void ocfs2_recovery_thread(struct ocfs2_super *osb, int node_num) { + int was_set = -1; + mutex_lock(&osb->recovery_lock); + if (osb->recovery_state < OCFS2_REC_WANT_DISABLE) + was_set = ocfs2_recovery_map_set(osb, node_num); trace_ocfs2_recovery_thread(node_num, osb->node_num, - osb->disable_recovery, osb->recovery_thread_task, - osb->disable_recovery ? - -1 : ocfs2_recovery_map_set(osb, node_num)); + osb->recovery_state, osb->recovery_thread_task, was_set); - if (osb->disable_recovery) + if (osb->recovery_state >= OCFS2_REC_WANT_DISABLE) goto out; if (osb->recovery_thread_task) diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h index e3c3a35dc5e0..6397170f302f 100644 --- a/fs/ocfs2/journal.h +++ b/fs/ocfs2/journal.h @@ -148,6 +148,7 @@ void ocfs2_wait_for_recovery(struct ocfs2_super *osb); int ocfs2_recovery_init(struct ocfs2_super *osb); void ocfs2_recovery_exit(struct ocfs2_super *osb); +void ocfs2_recovery_disable_quota(struct ocfs2_super *osb); int ocfs2_compute_replay_slots(struct ocfs2_super *osb); void ocfs2_free_replay_slots(struct ocfs2_super *osb); diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h index 51c52768132d..6aaa94c554c1 100644 --- a/fs/ocfs2/ocfs2.h +++ b/fs/ocfs2/ocfs2.h @@ -308,6 +308,21 @@ enum ocfs2_journal_trigger_type { void ocfs2_initialize_journal_triggers(struct super_block *sb, struct ocfs2_triggers triggers[]); +enum ocfs2_recovery_state { + OCFS2_REC_ENABLED = 0, + OCFS2_REC_QUOTA_WANT_DISABLE, + /* + * Must be OCFS2_REC_QUOTA_WANT_DISABLE + 1 for + * ocfs2_recovery_disable_quota() to work. + */ + OCFS2_REC_QUOTA_DISABLED, + OCFS2_REC_WANT_DISABLE, + /* + * Must be OCFS2_REC_WANT_DISABLE + 1 for ocfs2_recovery_exit() to work + */ + OCFS2_REC_DISABLED, +}; + struct ocfs2_journal; struct ocfs2_slot_info; struct ocfs2_recovery_map; @@ -370,7 +385,7 @@ struct ocfs2_super struct ocfs2_recovery_map *recovery_map; struct ocfs2_replay_map *replay_map; struct task_struct *recovery_thread_task; - int disable_recovery; + enum ocfs2_recovery_state recovery_state; wait_queue_head_t checkpoint_event; struct ocfs2_journal *journal; unsigned long osb_commit_interval; diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c index 2956d888c131..e272429da3db 100644 --- a/fs/ocfs2/quota_local.c +++ b/fs/ocfs2/quota_local.c @@ -453,8 +453,7 @@ out: /* Sync changes in local quota file into global quota file and * reinitialize local quota file. - * The function expects local quota file to be already locked and - * s_umount locked in shared mode. */ + * The function expects local quota file to be already locked. */ static int ocfs2_recover_local_quota_file(struct inode *lqinode, int type, struct ocfs2_quota_recovery *rec) @@ -588,7 +587,6 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb, { unsigned int ino[OCFS2_MAXQUOTAS] = { LOCAL_USER_QUOTA_SYSTEM_INODE, LOCAL_GROUP_QUOTA_SYSTEM_INODE }; - struct super_block *sb = osb->sb; struct ocfs2_local_disk_dqinfo *ldinfo; struct buffer_head *bh; handle_t *handle; @@ -600,7 +598,6 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb, printk(KERN_NOTICE "ocfs2: Finishing quota recovery on device (%s) for " "slot %u\n", osb->dev_str, slot_num); - down_read(&sb->s_umount); for (type = 0; type < OCFS2_MAXQUOTAS; type++) { if (list_empty(&(rec->r_list[type]))) continue; @@ -677,7 +674,6 @@ out_put: break; } out: - up_read(&sb->s_umount); kfree(rec); return status; } @@ -843,8 +839,7 @@ static int ocfs2_local_free_info(struct super_block *sb, int type) ocfs2_release_local_quota_bitmaps(&oinfo->dqi_chunk); /* - * s_umount held in exclusive mode protects us against racing with - * recovery thread... + * ocfs2_dismount_volume() has already aborted quota recovery... */ if (oinfo->dqi_rec) { ocfs2_free_quota_recovery(oinfo->dqi_rec); diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index f7b483f0de2a..6ac4dcd54588 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -698,10 +698,12 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb, bg_bh = ocfs2_block_group_alloc_contig(osb, handle, alloc_inode, ac, cl); - if (PTR_ERR(bg_bh) == -ENOSPC) + if (PTR_ERR(bg_bh) == -ENOSPC) { + ac->ac_which = OCFS2_AC_USE_MAIN_DISCONTIG; bg_bh = ocfs2_block_group_alloc_discontig(handle, alloc_inode, ac, cl); + } if (IS_ERR(bg_bh)) { status = PTR_ERR(bg_bh); bg_bh = NULL; @@ -1794,6 +1796,7 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac, { int status; u16 chain; + u32 contig_bits; u64 next_group; struct inode *alloc_inode = ac->ac_inode; struct buffer_head *group_bh = NULL; @@ -1819,10 +1822,21 @@ static int ocfs2_search_chain(struct ocfs2_alloc_context *ac, status = -ENOSPC; /* for now, the chain search is a bit simplistic. We just use * the 1st group with any empty bits. */ - while ((status = ac->ac_group_search(alloc_inode, group_bh, - bits_wanted, min_bits, - ac->ac_max_block, - res)) == -ENOSPC) { + while (1) { + if (ac->ac_which == OCFS2_AC_USE_MAIN_DISCONTIG) { + contig_bits = le16_to_cpu(bg->bg_contig_free_bits); + if (!contig_bits) + contig_bits = ocfs2_find_max_contig_free_bits(bg->bg_bitmap, + le16_to_cpu(bg->bg_bits), 0); + if (bits_wanted > contig_bits && contig_bits >= min_bits) + bits_wanted = contig_bits; + } + + status = ac->ac_group_search(alloc_inode, group_bh, + bits_wanted, min_bits, + ac->ac_max_block, res); + if (status != -ENOSPC) + break; if (!bg->bg_next_group) break; @@ -1982,6 +1996,7 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac, victim = ocfs2_find_victim_chain(cl); ac->ac_chain = victim; +search: status = ocfs2_search_chain(ac, handle, bits_wanted, min_bits, res, &bits_left); if (!status) { @@ -2022,6 +2037,16 @@ static int ocfs2_claim_suballoc_bits(struct ocfs2_alloc_context *ac, } } + /* Chains can't supply the bits_wanted contiguous space. + * We should switch to using every single bit when allocating + * from the global bitmap. */ + if (i == le16_to_cpu(cl->cl_next_free_rec) && + status == -ENOSPC && ac->ac_which == OCFS2_AC_USE_MAIN) { + ac->ac_which = OCFS2_AC_USE_MAIN_DISCONTIG; + ac->ac_chain = victim; + goto search; + } + set_hint: if (status != -ENOSPC) { /* If the next search of this group is not likely to @@ -2365,7 +2390,8 @@ int __ocfs2_claim_clusters(handle_t *handle, BUG_ON(ac->ac_bits_given >= ac->ac_bits_wanted); BUG_ON(ac->ac_which != OCFS2_AC_USE_LOCAL - && ac->ac_which != OCFS2_AC_USE_MAIN); + && ac->ac_which != OCFS2_AC_USE_MAIN + && ac->ac_which != OCFS2_AC_USE_MAIN_DISCONTIG); if (ac->ac_which == OCFS2_AC_USE_LOCAL) { WARN_ON(min_clusters > 1); diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h index b481b834857d..bcf2ed4a8631 100644 --- a/fs/ocfs2/suballoc.h +++ b/fs/ocfs2/suballoc.h @@ -29,6 +29,7 @@ struct ocfs2_alloc_context { #define OCFS2_AC_USE_MAIN 2 #define OCFS2_AC_USE_INODE 3 #define OCFS2_AC_USE_META 4 +#define OCFS2_AC_USE_MAIN_DISCONTIG 5 u32 ac_which; /* these are used by the chain search */ diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c index 8bb5022f3082..3d2533950bae 100644 --- a/fs/ocfs2/super.c +++ b/fs/ocfs2/super.c @@ -1812,6 +1812,9 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err) /* Orphan scan should be stopped as early as possible */ ocfs2_orphan_scan_stop(osb); + /* Stop quota recovery so that we can disable quotas */ + ocfs2_recovery_disable_quota(osb); + ocfs2_disable_quotas(osb); /* All dquots should be freed by now */ diff --git a/fs/pnode.c b/fs/pnode.c index 7a062a5de10e..fb77427df39e 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -150,7 +150,7 @@ static struct mount *propagation_next(struct mount *m, struct mount *origin) { /* are there any slaves of this mount? */ - if (!IS_MNT_PROPAGATED(m) && !list_empty(&m->mnt_slave_list)) + if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list)) return first_slave(m); while (1) { @@ -174,7 +174,7 @@ static struct mount *skip_propagation_subtree(struct mount *m, * Advance m such that propagation_next will not return * the slaves of m. */ - if (!IS_MNT_PROPAGATED(m) && !list_empty(&m->mnt_slave_list)) + if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list)) m = last_slave(m); return m; @@ -185,7 +185,7 @@ static struct mount *next_group(struct mount *m, struct mount *origin) while (1) { while (1) { struct mount *next; - if (!IS_MNT_PROPAGATED(m) && !list_empty(&m->mnt_slave_list)) + if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list)) return first_slave(m); next = next_peer(m); if (m->mnt_group_id == origin->mnt_group_id) { @@ -226,11 +226,15 @@ static int propagate_one(struct mount *m, struct mountpoint *dest_mp) struct mount *child; int type; /* skip ones added by this propagate_mnt() */ - if (IS_MNT_PROPAGATED(m)) + if (IS_MNT_NEW(m)) return 0; - /* skip if mountpoint isn't covered by it */ + /* skip if mountpoint isn't visible in m */ if (!is_subdir(dest_mp->m_dentry, m->mnt.mnt_root)) return 0; + /* skip if m is in the anon_ns we are emptying */ + if (m->mnt_ns->mntns_flags & MNTNS_PROPAGATING) + return 0; + if (peers(m, last_dest)) { type = CL_MAKE_SHARED; } else { @@ -380,9 +384,6 @@ bool propagation_would_overmount(const struct mount *from, if (!IS_MNT_SHARED(from)) return false; - if (IS_MNT_PROPAGATED(to)) - return false; - if (to->mnt.mnt_root != mp->m_dentry) return false; diff --git a/fs/pnode.h b/fs/pnode.h index ddafe0d087ca..34b6247af01d 100644 --- a/fs/pnode.h +++ b/fs/pnode.h @@ -12,7 +12,7 @@ #define IS_MNT_SHARED(m) ((m)->mnt.mnt_flags & MNT_SHARED) #define IS_MNT_SLAVE(m) ((m)->mnt_master) -#define IS_MNT_PROPAGATED(m) (!(m)->mnt_ns || ((m)->mnt_ns->mntns_flags & MNTNS_PROPAGATING)) +#define IS_MNT_NEW(m) (!(m)->mnt_ns) #define CLEAR_MNT_SHARED(m) ((m)->mnt.mnt_flags &= ~MNT_SHARED) #define IS_MNT_UNBINDABLE(m) ((m)->mnt.mnt_flags & MNT_UNBINDABLE) #define IS_MNT_MARKED(m) ((m)->mnt.mnt_flags & MNT_MARKED) diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index fe738623cf1b..240d82c6f908 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -29,7 +29,6 @@ static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids, { struct cached_fid *cfid; - spin_lock(&cfids->cfid_list_lock); list_for_each_entry(cfid, &cfids->entries, entry) { if (!strcmp(cfid->path, path)) { /* @@ -38,25 +37,20 @@ static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids, * being deleted due to a lease break. */ if (!cfid->time || !cfid->has_lease) { - spin_unlock(&cfids->cfid_list_lock); return NULL; } kref_get(&cfid->refcount); - spin_unlock(&cfids->cfid_list_lock); return cfid; } } if (lookup_only) { - spin_unlock(&cfids->cfid_list_lock); return NULL; } if (cfids->num_entries >= max_cached_dirs) { - spin_unlock(&cfids->cfid_list_lock); return NULL; } cfid = init_cached_dir(path); if (cfid == NULL) { - spin_unlock(&cfids->cfid_list_lock); return NULL; } cfid->cfids = cfids; @@ -74,7 +68,6 @@ static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids, */ cfid->has_lease = true; - spin_unlock(&cfids->cfid_list_lock); return cfid; } @@ -187,8 +180,10 @@ replay_again: if (!utf16_path) return -ENOMEM; + spin_lock(&cfids->cfid_list_lock); cfid = find_or_create_cached_dir(cfids, path, lookup_only, tcon->max_cached_dirs); if (cfid == NULL) { + spin_unlock(&cfids->cfid_list_lock); kfree(utf16_path); return -ENOENT; } @@ -197,7 +192,6 @@ replay_again: * Otherwise, it is either a new entry or laundromat worker removed it * from @cfids->entries. Caller will put last reference if the latter. */ - spin_lock(&cfids->cfid_list_lock); if (cfid->has_lease && cfid->time) { spin_unlock(&cfids->cfid_list_lock); *ret_cfid = cfid; diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index 57d9bfbadd97..2a3e46b8e15a 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -666,6 +666,8 @@ finished: /* smb2_parse_contexts() fills idata->fi.IndexNumber */ rc = smb2_parse_contexts(server, &rsp_iov[0], &oparms->fid->epoch, oparms->fid->lease_key, &oplock, &idata->fi, NULL); + if (rc) + cifs_dbg(VFS, "rc: %d parsing context of compound op\n", rc); } for (i = 0; i < num_cmds; i++) { diff --git a/fs/udf/truncate.c b/fs/udf/truncate.c index 4f33a4a48886..b4071c9cf8c9 100644 --- a/fs/udf/truncate.c +++ b/fs/udf/truncate.c @@ -115,7 +115,7 @@ void udf_truncate_tail_extent(struct inode *inode) } /* This inode entry is in-memory only and thus we don't have to mark * the inode dirty */ - if (ret == 0) + if (ret >= 0) iinfo->i_lenExtents = inode->i_size; brelse(epos.bh); } diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index d80f94346199..22f4bf956ba1 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1585,8 +1585,11 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx, user_uffdio_copy = (struct uffdio_copy __user *) arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_copy->copy))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_copy, user_uffdio_copy, @@ -1641,8 +1644,11 @@ static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx, user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage, @@ -1744,8 +1750,11 @@ static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg) user_uffdio_continue = (struct uffdio_continue __user *)arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_continue->mapped))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_continue, user_uffdio_continue, @@ -1801,8 +1810,11 @@ static inline int userfaultfd_poison(struct userfaultfd_ctx *ctx, unsigned long user_uffdio_poison = (struct uffdio_poison __user *)arg; ret = -EAGAIN; - if (atomic_read(&ctx->mmap_changing)) + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_poison->updated))) + return -EFAULT; goto out; + } ret = -EFAULT; if (copy_from_user(&uffdio_poison, user_uffdio_poison, @@ -1870,8 +1882,12 @@ static int userfaultfd_move(struct userfaultfd_ctx *ctx, user_uffdio_move = (struct uffdio_move __user *) arg; - if (atomic_read(&ctx->mmap_changing)) - return -EAGAIN; + ret = -EAGAIN; + if (unlikely(atomic_read(&ctx->mmap_changing))) { + if (unlikely(put_user(ret, &user_uffdio_move->move))) + return -EFAULT; + goto out; + } if (copy_from_user(&uffdio_move, user_uffdio_move, /* don't copy "move" last field */ diff --git a/fs/xattr.c b/fs/xattr.c index fabb2a04501e..8ec5b0204bfd 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -1428,6 +1428,15 @@ static bool xattr_is_trusted(const char *name) return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN); } +static bool xattr_is_maclabel(const char *name) +{ + const char *suffix = name + XATTR_SECURITY_PREFIX_LEN; + + return !strncmp(name, XATTR_SECURITY_PREFIX, + XATTR_SECURITY_PREFIX_LEN) && + security_ismaclabel(suffix); +} + /** * simple_xattr_list - list all xattr objects * @inode: inode from which to get the xattrs @@ -1460,6 +1469,17 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, if (err) return err; + err = security_inode_listsecurity(inode, buffer, remaining_size); + if (err < 0) + return err; + + if (buffer) { + if (remaining_size < err) + return -ERANGE; + buffer += err; + } + remaining_size -= err; + read_lock(&xattrs->lock); for (rbp = rb_first(&xattrs->rb_root); rbp; rbp = rb_next(rbp)) { xattr = rb_entry(rbp, struct simple_xattr, rb_node); @@ -1468,6 +1488,10 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, if (!trusted && xattr_is_trusted(xattr->name)) continue; + /* skip MAC labels; these are provided by LSM above */ + if (xattr_is_maclabel(xattr->name)) + continue; + err = xattr_list_one(&buffer, &remaining_size, xattr->name); if (err) break; diff --git a/include/linux/cpu.h b/include/linux/cpu.h index e3049543008b..3aa955102b34 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -78,6 +78,8 @@ extern ssize_t cpu_show_gds(struct device *dev, extern ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attribute *attr, char *buf); extern ssize_t cpu_show_ghostwrite(struct device *dev, struct device_attribute *attr, char *buf); +extern ssize_t cpu_show_indirect_target_selection(struct device *dev, + struct device_attribute *attr, char *buf); extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, diff --git a/include/linux/execmem.h b/include/linux/execmem.h index 65655a5d1be2..ca42d5e46ccc 100644 --- a/include/linux/execmem.h +++ b/include/linux/execmem.h @@ -4,6 +4,7 @@ #include <linux/types.h> #include <linux/moduleloader.h> +#include <linux/cleanup.h> #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ !defined(CONFIG_KASAN_VMALLOC) @@ -53,7 +54,7 @@ enum execmem_range_flags { EXECMEM_ROX_CACHE = (1 << 1), }; -#ifdef CONFIG_ARCH_HAS_EXECMEM_ROX +#if defined(CONFIG_ARCH_HAS_EXECMEM_ROX) && defined(CONFIG_EXECMEM) /** * execmem_fill_trapping_insns - set memory to contain instructions that * will trap @@ -93,9 +94,15 @@ int execmem_make_temp_rw(void *ptr, size_t size); * Return: 0 on success or negative error code on failure. */ int execmem_restore_rox(void *ptr, size_t size); + +/* + * Called from mark_readonly(), where the system transitions to ROX. + */ +void execmem_cache_make_ro(void); #else static inline int execmem_make_temp_rw(void *ptr, size_t size) { return 0; } static inline int execmem_restore_rox(void *ptr, size_t size) { return 0; } +static inline void execmem_cache_make_ro(void) { } #endif /** @@ -170,6 +177,8 @@ void *execmem_alloc(enum execmem_type type, size_t size); */ void execmem_free(void *ptr); +DEFINE_FREE(execmem, void *, if (_T) execmem_free(_T)); + #ifdef CONFIG_MMU /** * execmem_vmap - create virtual mapping for EXECMEM_MODULE_DATA memory diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index 675959fb97ba..d6ffe01962c2 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1002,6 +1002,12 @@ struct vmbus_channel { /* The max size of a packet on this channel */ u32 max_pkt_size; + + /* function to mmap ring buffer memory to the channel's sysfs ring attribute */ + int (*mmap_ring_buffer)(struct vmbus_channel *channel, struct vm_area_struct *vma); + + /* boolean to control visibility of sysfs for ring buffer */ + bool ring_sysfs_visible; }; #define lock_requestor(channel, flags) \ diff --git a/include/linux/module.h b/include/linux/module.h index b3329110d668..8050f77c3b64 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -586,6 +586,11 @@ struct module { atomic_t refcnt; #endif +#ifdef CONFIG_MITIGATION_ITS + int its_num_pages; + void **its_page_array; +#endif + #ifdef CONFIG_CONSTRUCTORS /* Constructor functions. */ ctor_fn_t *ctors; diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h index e39d4d563b19..785048a3b3e6 100644 --- a/include/linux/timekeeper_internal.h +++ b/include/linux/timekeeper_internal.h @@ -51,7 +51,7 @@ struct tk_read_base { * @offs_real: Offset clock monotonic -> clock realtime * @offs_boot: Offset clock monotonic -> clock boottime * @offs_tai: Offset clock monotonic -> clock tai - * @tai_offset: The current UTC to TAI offset in seconds + * @coarse_nsec: The nanoseconds part for coarse time getters * @tkr_raw: The readout base structure for CLOCK_MONOTONIC_RAW * @raw_sec: CLOCK_MONOTONIC_RAW time in seconds * @clock_was_set_seq: The sequence number of clock was set events @@ -76,6 +76,7 @@ struct tk_read_base { * ntp shifted nano seconds. * @ntp_err_mult: Multiplication factor for scaled math conversion * @skip_second_overflow: Flag used to avoid updating NTP twice with same second + * @tai_offset: The current UTC to TAI offset in seconds * * Note: For timespec(64) based interfaces wall_to_monotonic is what * we need to add to xtime (or xtime corrected for sub jiffy times) @@ -100,7 +101,7 @@ struct tk_read_base { * which results in the following cacheline layout: * * 0: seqcount, tkr_mono - * 1: xtime_sec ... tai_offset + * 1: xtime_sec ... coarse_nsec * 2: tkr_raw, raw_sec * 3,4: Internal variables * @@ -121,7 +122,7 @@ struct timekeeper { ktime_t offs_real; ktime_t offs_boot; ktime_t offs_tai; - s32 tai_offset; + u32 coarse_nsec; /* Cacheline 2: */ struct tk_read_base tkr_raw; @@ -144,6 +145,7 @@ struct timekeeper { u32 ntp_error_shift; u32 ntp_err_mult; u32 skip_second_overflow; + s32 tai_offset; }; #ifdef CONFIG_GENERIC_TIME_VSYSCALL diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 31e9ffd936e3..5ca8d4dd149d 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -61,6 +61,7 @@ struct vm_struct { unsigned int nr_pages; phys_addr_t phys_addr; const void *caller; + unsigned long requested_size; }; struct vmap_area { diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 306b60430091..24b70ea3e6ce 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1116,9 +1116,11 @@ void cpuset_update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus) if (top_cs) { /* - * Percpu kthreads in top_cpuset are ignored + * PF_NO_SETAFFINITY tasks are ignored. + * All per cpu kthreads should have PF_NO_SETAFFINITY + * flag set, see kthread_set_per_cpu(). */ - if (kthread_is_per_cpu(task)) + if (task->flags & PF_NO_SETAFFINITY) continue; cpumask_andnot(new_cpus, possible_mask, subpartitions_cpus); } else { diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index fdbf249d1c68..f5133249fd4d 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -1118,8 +1118,38 @@ static void scx_kf_disallow(u32 mask) current->scx.kf_mask &= ~mask; } -#define SCX_CALL_OP(mask, op, args...) \ +/* + * Track the rq currently locked. + * + * This allows kfuncs to safely operate on rq from any scx ops callback, + * knowing which rq is already locked. + */ +static DEFINE_PER_CPU(struct rq *, locked_rq); + +static inline void update_locked_rq(struct rq *rq) +{ + /* + * Check whether @rq is actually locked. This can help expose bugs + * or incorrect assumptions about the context in which a kfunc or + * callback is executed. + */ + if (rq) + lockdep_assert_rq_held(rq); + __this_cpu_write(locked_rq, rq); +} + +/* + * Return the rq currently locked from an scx callback, or NULL if no rq is + * locked. + */ +static inline struct rq *scx_locked_rq(void) +{ + return __this_cpu_read(locked_rq); +} + +#define SCX_CALL_OP(mask, op, rq, args...) \ do { \ + update_locked_rq(rq); \ if (mask) { \ scx_kf_allow(mask); \ scx_ops.op(args); \ @@ -1127,11 +1157,14 @@ do { \ } else { \ scx_ops.op(args); \ } \ + update_locked_rq(NULL); \ } while (0) -#define SCX_CALL_OP_RET(mask, op, args...) \ +#define SCX_CALL_OP_RET(mask, op, rq, args...) \ ({ \ __typeof__(scx_ops.op(args)) __ret; \ + \ + update_locked_rq(rq); \ if (mask) { \ scx_kf_allow(mask); \ __ret = scx_ops.op(args); \ @@ -1139,6 +1172,7 @@ do { \ } else { \ __ret = scx_ops.op(args); \ } \ + update_locked_rq(NULL); \ __ret; \ }) @@ -1153,31 +1187,31 @@ do { \ * scx_kf_allowed_on_arg_tasks() to test whether the invocation is allowed on * the specific task. */ -#define SCX_CALL_OP_TASK(mask, op, task, args...) \ +#define SCX_CALL_OP_TASK(mask, op, rq, task, args...) \ do { \ BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL); \ current->scx.kf_tasks[0] = task; \ - SCX_CALL_OP(mask, op, task, ##args); \ + SCX_CALL_OP(mask, op, rq, task, ##args); \ current->scx.kf_tasks[0] = NULL; \ } while (0) -#define SCX_CALL_OP_TASK_RET(mask, op, task, args...) \ +#define SCX_CALL_OP_TASK_RET(mask, op, rq, task, args...) \ ({ \ __typeof__(scx_ops.op(task, ##args)) __ret; \ BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL); \ current->scx.kf_tasks[0] = task; \ - __ret = SCX_CALL_OP_RET(mask, op, task, ##args); \ + __ret = SCX_CALL_OP_RET(mask, op, rq, task, ##args); \ current->scx.kf_tasks[0] = NULL; \ __ret; \ }) -#define SCX_CALL_OP_2TASKS_RET(mask, op, task0, task1, args...) \ +#define SCX_CALL_OP_2TASKS_RET(mask, op, rq, task0, task1, args...) \ ({ \ __typeof__(scx_ops.op(task0, task1, ##args)) __ret; \ BUILD_BUG_ON((mask) & ~__SCX_KF_TERMINAL); \ current->scx.kf_tasks[0] = task0; \ current->scx.kf_tasks[1] = task1; \ - __ret = SCX_CALL_OP_RET(mask, op, task0, task1, ##args); \ + __ret = SCX_CALL_OP_RET(mask, op, rq, task0, task1, ##args); \ current->scx.kf_tasks[0] = NULL; \ current->scx.kf_tasks[1] = NULL; \ __ret; \ @@ -2172,7 +2206,7 @@ static void do_enqueue_task(struct rq *rq, struct task_struct *p, u64 enq_flags, WARN_ON_ONCE(*ddsp_taskp); *ddsp_taskp = p; - SCX_CALL_OP_TASK(SCX_KF_ENQUEUE, enqueue, p, enq_flags); + SCX_CALL_OP_TASK(SCX_KF_ENQUEUE, enqueue, rq, p, enq_flags); *ddsp_taskp = NULL; if (p->scx.ddsp_dsq_id != SCX_DSQ_INVALID) @@ -2269,7 +2303,7 @@ static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int enq_flags add_nr_running(rq, 1); if (SCX_HAS_OP(runnable) && !task_on_rq_migrating(p)) - SCX_CALL_OP_TASK(SCX_KF_REST, runnable, p, enq_flags); + SCX_CALL_OP_TASK(SCX_KF_REST, runnable, rq, p, enq_flags); if (enq_flags & SCX_ENQ_WAKEUP) touch_core_sched(rq, p); @@ -2283,7 +2317,7 @@ out: __scx_add_event(SCX_EV_SELECT_CPU_FALLBACK, 1); } -static void ops_dequeue(struct task_struct *p, u64 deq_flags) +static void ops_dequeue(struct rq *rq, struct task_struct *p, u64 deq_flags) { unsigned long opss; @@ -2304,7 +2338,7 @@ static void ops_dequeue(struct task_struct *p, u64 deq_flags) BUG(); case SCX_OPSS_QUEUED: if (SCX_HAS_OP(dequeue)) - SCX_CALL_OP_TASK(SCX_KF_REST, dequeue, p, deq_flags); + SCX_CALL_OP_TASK(SCX_KF_REST, dequeue, rq, p, deq_flags); if (atomic_long_try_cmpxchg(&p->scx.ops_state, &opss, SCX_OPSS_NONE)) @@ -2337,7 +2371,7 @@ static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int deq_flags return true; } - ops_dequeue(p, deq_flags); + ops_dequeue(rq, p, deq_flags); /* * A currently running task which is going off @rq first gets dequeued @@ -2353,11 +2387,11 @@ static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int deq_flags */ if (SCX_HAS_OP(stopping) && task_current(rq, p)) { update_curr_scx(rq); - SCX_CALL_OP_TASK(SCX_KF_REST, stopping, p, false); + SCX_CALL_OP_TASK(SCX_KF_REST, stopping, rq, p, false); } if (SCX_HAS_OP(quiescent) && !task_on_rq_migrating(p)) - SCX_CALL_OP_TASK(SCX_KF_REST, quiescent, p, deq_flags); + SCX_CALL_OP_TASK(SCX_KF_REST, quiescent, rq, p, deq_flags); if (deq_flags & SCX_DEQ_SLEEP) p->scx.flags |= SCX_TASK_DEQD_FOR_SLEEP; @@ -2377,7 +2411,7 @@ static void yield_task_scx(struct rq *rq) struct task_struct *p = rq->curr; if (SCX_HAS_OP(yield)) - SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, p, NULL); + SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, rq, p, NULL); else p->scx.slice = 0; } @@ -2387,7 +2421,7 @@ static bool yield_to_task_scx(struct rq *rq, struct task_struct *to) struct task_struct *from = rq->curr; if (SCX_HAS_OP(yield)) - return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, from, to); + return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, yield, rq, from, to); else return false; } @@ -2945,7 +2979,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev) * emitted in switch_class(). */ if (SCX_HAS_OP(cpu_acquire)) - SCX_CALL_OP(SCX_KF_REST, cpu_acquire, cpu_of(rq), NULL); + SCX_CALL_OP(SCX_KF_REST, cpu_acquire, rq, cpu_of(rq), NULL); rq->scx.cpu_released = false; } @@ -2990,7 +3024,7 @@ static int balance_one(struct rq *rq, struct task_struct *prev) do { dspc->nr_tasks = 0; - SCX_CALL_OP(SCX_KF_DISPATCH, dispatch, cpu_of(rq), + SCX_CALL_OP(SCX_KF_DISPATCH, dispatch, rq, cpu_of(rq), prev_on_scx ? prev : NULL); flush_dispatch_buf(rq); @@ -3104,7 +3138,7 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first) * Core-sched might decide to execute @p before it is * dispatched. Call ops_dequeue() to notify the BPF scheduler. */ - ops_dequeue(p, SCX_DEQ_CORE_SCHED_EXEC); + ops_dequeue(rq, p, SCX_DEQ_CORE_SCHED_EXEC); dispatch_dequeue(rq, p); } @@ -3112,7 +3146,7 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first) /* see dequeue_task_scx() on why we skip when !QUEUED */ if (SCX_HAS_OP(running) && (p->scx.flags & SCX_TASK_QUEUED)) - SCX_CALL_OP_TASK(SCX_KF_REST, running, p); + SCX_CALL_OP_TASK(SCX_KF_REST, running, rq, p); clr_task_runnable(p, true); @@ -3193,8 +3227,7 @@ static void switch_class(struct rq *rq, struct task_struct *next) .task = next, }; - SCX_CALL_OP(SCX_KF_CPU_RELEASE, - cpu_release, cpu_of(rq), &args); + SCX_CALL_OP(SCX_KF_CPU_RELEASE, cpu_release, rq, cpu_of(rq), &args); } rq->scx.cpu_released = true; } @@ -3207,7 +3240,7 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p, /* see dequeue_task_scx() on why we skip when !QUEUED */ if (SCX_HAS_OP(stopping) && (p->scx.flags & SCX_TASK_QUEUED)) - SCX_CALL_OP_TASK(SCX_KF_REST, stopping, p, true); + SCX_CALL_OP_TASK(SCX_KF_REST, stopping, rq, p, true); if (p->scx.flags & SCX_TASK_QUEUED) { set_task_runnable(rq, p); @@ -3348,7 +3381,7 @@ bool scx_prio_less(const struct task_struct *a, const struct task_struct *b, * verifier. */ if (SCX_HAS_OP(core_sched_before) && !scx_rq_bypassing(task_rq(a))) - return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, core_sched_before, + return SCX_CALL_OP_2TASKS_RET(SCX_KF_REST, core_sched_before, NULL, (struct task_struct *)a, (struct task_struct *)b); else @@ -3385,7 +3418,7 @@ static int select_task_rq_scx(struct task_struct *p, int prev_cpu, int wake_flag *ddsp_taskp = p; cpu = SCX_CALL_OP_TASK_RET(SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU, - select_cpu, p, prev_cpu, wake_flags); + select_cpu, NULL, p, prev_cpu, wake_flags); p->scx.selected_cpu = cpu; *ddsp_taskp = NULL; if (ops_cpu_valid(cpu, "from ops.select_cpu()")) @@ -3430,8 +3463,8 @@ static void set_cpus_allowed_scx(struct task_struct *p, * designation pointless. Cast it away when calling the operation. */ if (SCX_HAS_OP(set_cpumask)) - SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, p, - (struct cpumask *)p->cpus_ptr); + SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, NULL, + p, (struct cpumask *)p->cpus_ptr); } static void handle_hotplug(struct rq *rq, bool online) @@ -3444,9 +3477,9 @@ static void handle_hotplug(struct rq *rq, bool online) scx_idle_update_selcpu_topology(&scx_ops); if (online && SCX_HAS_OP(cpu_online)) - SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_online, cpu); + SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_online, NULL, cpu); else if (!online && SCX_HAS_OP(cpu_offline)) - SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_offline, cpu); + SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_offline, NULL, cpu); else scx_ops_exit(SCX_ECODE_ACT_RESTART | SCX_ECODE_RSN_HOTPLUG, "cpu %d going %s, exiting scheduler", cpu, @@ -3550,7 +3583,7 @@ static void task_tick_scx(struct rq *rq, struct task_struct *curr, int queued) curr->scx.slice = 0; touch_core_sched(rq, curr); } else if (SCX_HAS_OP(tick)) { - SCX_CALL_OP_TASK(SCX_KF_REST, tick, curr); + SCX_CALL_OP_TASK(SCX_KF_REST, tick, rq, curr); } if (!curr->scx.slice) @@ -3627,7 +3660,7 @@ static int scx_ops_init_task(struct task_struct *p, struct task_group *tg, bool .fork = fork, }; - ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init_task, p, &args); + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init_task, NULL, p, &args); if (unlikely(ret)) { ret = ops_sanitize_err("init_task", ret); return ret; @@ -3668,9 +3701,10 @@ static int scx_ops_init_task(struct task_struct *p, struct task_group *tg, bool static void scx_ops_enable_task(struct task_struct *p) { + struct rq *rq = task_rq(p); u32 weight; - lockdep_assert_rq_held(task_rq(p)); + lockdep_assert_rq_held(rq); /* * Set the weight before calling ops.enable() so that the scheduler @@ -3684,20 +3718,22 @@ static void scx_ops_enable_task(struct task_struct *p) p->scx.weight = sched_weight_to_cgroup(weight); if (SCX_HAS_OP(enable)) - SCX_CALL_OP_TASK(SCX_KF_REST, enable, p); + SCX_CALL_OP_TASK(SCX_KF_REST, enable, rq, p); scx_set_task_state(p, SCX_TASK_ENABLED); if (SCX_HAS_OP(set_weight)) - SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, p, p->scx.weight); + SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, rq, p, p->scx.weight); } static void scx_ops_disable_task(struct task_struct *p) { - lockdep_assert_rq_held(task_rq(p)); + struct rq *rq = task_rq(p); + + lockdep_assert_rq_held(rq); WARN_ON_ONCE(scx_get_task_state(p) != SCX_TASK_ENABLED); if (SCX_HAS_OP(disable)) - SCX_CALL_OP_TASK(SCX_KF_REST, disable, p); + SCX_CALL_OP_TASK(SCX_KF_REST, disable, rq, p); scx_set_task_state(p, SCX_TASK_READY); } @@ -3726,7 +3762,7 @@ static void scx_ops_exit_task(struct task_struct *p) } if (SCX_HAS_OP(exit_task)) - SCX_CALL_OP_TASK(SCX_KF_REST, exit_task, p, &args); + SCX_CALL_OP_TASK(SCX_KF_REST, exit_task, task_rq(p), p, &args); scx_set_task_state(p, SCX_TASK_NONE); } @@ -3835,7 +3871,7 @@ static void reweight_task_scx(struct rq *rq, struct task_struct *p, p->scx.weight = sched_weight_to_cgroup(scale_load_down(lw->weight)); if (SCX_HAS_OP(set_weight)) - SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, p, p->scx.weight); + SCX_CALL_OP_TASK(SCX_KF_REST, set_weight, rq, p, p->scx.weight); } static void prio_changed_scx(struct rq *rq, struct task_struct *p, int oldprio) @@ -3851,8 +3887,8 @@ static void switching_to_scx(struct rq *rq, struct task_struct *p) * different scheduler class. Keep the BPF scheduler up-to-date. */ if (SCX_HAS_OP(set_cpumask)) - SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, p, - (struct cpumask *)p->cpus_ptr); + SCX_CALL_OP_TASK(SCX_KF_REST, set_cpumask, rq, + p, (struct cpumask *)p->cpus_ptr); } static void switched_from_scx(struct rq *rq, struct task_struct *p) @@ -3913,7 +3949,7 @@ int scx_tg_online(struct task_group *tg) struct scx_cgroup_init_args args = { .weight = tg->scx_weight }; - ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init, + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init, NULL, tg->css.cgroup, &args); if (ret) ret = ops_sanitize_err("cgroup_init", ret); @@ -3935,7 +3971,7 @@ void scx_tg_offline(struct task_group *tg) percpu_down_read(&scx_cgroup_rwsem); if (SCX_HAS_OP(cgroup_exit) && (tg->scx_flags & SCX_TG_INITED)) - SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, tg->css.cgroup); + SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, NULL, tg->css.cgroup); tg->scx_flags &= ~(SCX_TG_ONLINE | SCX_TG_INITED); percpu_up_read(&scx_cgroup_rwsem); @@ -3968,7 +4004,7 @@ int scx_cgroup_can_attach(struct cgroup_taskset *tset) continue; if (SCX_HAS_OP(cgroup_prep_move)) { - ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_prep_move, + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_prep_move, NULL, p, from, css->cgroup); if (ret) goto err; @@ -3982,8 +4018,8 @@ int scx_cgroup_can_attach(struct cgroup_taskset *tset) err: cgroup_taskset_for_each(p, css, tset) { if (SCX_HAS_OP(cgroup_cancel_move) && p->scx.cgrp_moving_from) - SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, p, - p->scx.cgrp_moving_from, css->cgroup); + SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, NULL, + p, p->scx.cgrp_moving_from, css->cgroup); p->scx.cgrp_moving_from = NULL; } @@ -4001,8 +4037,8 @@ void scx_cgroup_move_task(struct task_struct *p) * cgrp_moving_from set. */ if (SCX_HAS_OP(cgroup_move) && !WARN_ON_ONCE(!p->scx.cgrp_moving_from)) - SCX_CALL_OP_TASK(SCX_KF_UNLOCKED, cgroup_move, p, - p->scx.cgrp_moving_from, tg_cgrp(task_group(p))); + SCX_CALL_OP_TASK(SCX_KF_UNLOCKED, cgroup_move, NULL, + p, p->scx.cgrp_moving_from, tg_cgrp(task_group(p))); p->scx.cgrp_moving_from = NULL; } @@ -4021,8 +4057,8 @@ void scx_cgroup_cancel_attach(struct cgroup_taskset *tset) cgroup_taskset_for_each(p, css, tset) { if (SCX_HAS_OP(cgroup_cancel_move) && p->scx.cgrp_moving_from) - SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, p, - p->scx.cgrp_moving_from, css->cgroup); + SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_cancel_move, NULL, + p, p->scx.cgrp_moving_from, css->cgroup); p->scx.cgrp_moving_from = NULL; } out_unlock: @@ -4035,7 +4071,7 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight) if (scx_cgroup_enabled && tg->scx_weight != weight) { if (SCX_HAS_OP(cgroup_set_weight)) - SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_set_weight, + SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_set_weight, NULL, tg_cgrp(tg), weight); tg->scx_weight = weight; } @@ -4224,7 +4260,7 @@ static void scx_cgroup_exit(void) continue; rcu_read_unlock(); - SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, css->cgroup); + SCX_CALL_OP(SCX_KF_UNLOCKED, cgroup_exit, NULL, css->cgroup); rcu_read_lock(); css_put(css); @@ -4261,7 +4297,7 @@ static int scx_cgroup_init(void) continue; rcu_read_unlock(); - ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init, + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, cgroup_init, NULL, css->cgroup, &args); if (ret) { css_put(css); @@ -4758,7 +4794,7 @@ static void scx_ops_disable_workfn(struct kthread_work *work) } if (scx_ops.exit) - SCX_CALL_OP(SCX_KF_UNLOCKED, exit, ei); + SCX_CALL_OP(SCX_KF_UNLOCKED, exit, NULL, ei); cancel_delayed_work_sync(&scx_watchdog_work); @@ -4965,7 +5001,7 @@ static void scx_dump_task(struct seq_buf *s, struct scx_dump_ctx *dctx, if (SCX_HAS_OP(dump_task)) { ops_dump_init(s, " "); - SCX_CALL_OP(SCX_KF_REST, dump_task, dctx, p); + SCX_CALL_OP(SCX_KF_REST, dump_task, NULL, dctx, p); ops_dump_exit(); } @@ -5012,7 +5048,7 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len) if (SCX_HAS_OP(dump)) { ops_dump_init(&s, ""); - SCX_CALL_OP(SCX_KF_UNLOCKED, dump, &dctx); + SCX_CALL_OP(SCX_KF_UNLOCKED, dump, NULL, &dctx); ops_dump_exit(); } @@ -5069,7 +5105,7 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len) used = seq_buf_used(&ns); if (SCX_HAS_OP(dump_cpu)) { ops_dump_init(&ns, " "); - SCX_CALL_OP(SCX_KF_REST, dump_cpu, &dctx, cpu, idle); + SCX_CALL_OP(SCX_KF_REST, dump_cpu, NULL, &dctx, cpu, idle); ops_dump_exit(); } @@ -5328,7 +5364,7 @@ static int scx_ops_enable(struct sched_ext_ops *ops, struct bpf_link *link) scx_idle_enable(ops); if (scx_ops.init) { - ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init); + ret = SCX_CALL_OP_RET(SCX_KF_UNLOCKED, init, NULL); if (ret) { ret = ops_sanitize_err("init", ret); cpus_read_unlock(); @@ -6791,6 +6827,12 @@ __bpf_kfunc int bpf_iter_scx_dsq_new(struct bpf_iter_scx_dsq *it, u64 dsq_id, BUILD_BUG_ON(__alignof__(struct bpf_iter_scx_dsq_kern) != __alignof__(struct bpf_iter_scx_dsq)); + /* + * next() and destroy() will be called regardless of the return value. + * Always clear $kit->dsq. + */ + kit->dsq = NULL; + if (flags & ~__SCX_DSQ_ITER_USER_FLAGS) return -EINVAL; @@ -7077,13 +7119,32 @@ __bpf_kfunc void scx_bpf_cpuperf_set(s32 cpu, u32 perf) } if (ops_cpu_valid(cpu, NULL)) { - struct rq *rq = cpu_rq(cpu); + struct rq *rq = cpu_rq(cpu), *locked_rq = scx_locked_rq(); + struct rq_flags rf; + + /* + * When called with an rq lock held, restrict the operation + * to the corresponding CPU to prevent ABBA deadlocks. + */ + if (locked_rq && rq != locked_rq) { + scx_ops_error("Invalid target CPU %d", cpu); + return; + } + + /* + * If no rq lock is held, allow to operate on any CPU by + * acquiring the corresponding rq lock. + */ + if (!locked_rq) { + rq_lock_irqsave(rq, &rf); + update_rq_clock(rq); + } rq->scx.cpuperf_target = perf; + cpufreq_update_util(rq, 0); - rcu_read_lock_sched_notrace(); - cpufreq_update_util(cpu_rq(cpu), 0); - rcu_read_unlock_sched_notrace(); + if (!locked_rq) + rq_unlock_irqrestore(rq, &rf); } } @@ -7314,12 +7375,6 @@ BTF_ID_FLAGS(func, scx_bpf_nr_cpu_ids) BTF_ID_FLAGS(func, scx_bpf_get_possible_cpumask, KF_ACQUIRE) BTF_ID_FLAGS(func, scx_bpf_get_online_cpumask, KF_ACQUIRE) BTF_ID_FLAGS(func, scx_bpf_put_cpumask, KF_RELEASE) -BTF_ID_FLAGS(func, scx_bpf_get_idle_cpumask, KF_ACQUIRE) -BTF_ID_FLAGS(func, scx_bpf_get_idle_smtmask, KF_ACQUIRE) -BTF_ID_FLAGS(func, scx_bpf_put_idle_cpumask, KF_RELEASE) -BTF_ID_FLAGS(func, scx_bpf_test_and_clear_cpu_idle) -BTF_ID_FLAGS(func, scx_bpf_pick_idle_cpu, KF_RCU) -BTF_ID_FLAGS(func, scx_bpf_pick_any_cpu, KF_RCU) BTF_ID_FLAGS(func, scx_bpf_task_running, KF_RCU) BTF_ID_FLAGS(func, scx_bpf_task_cpu, KF_RCU) BTF_ID_FLAGS(func, scx_bpf_cpu_rq) diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c index cb343ca889e0..e67a19a071c1 100644 --- a/kernel/sched/ext_idle.c +++ b/kernel/sched/ext_idle.c @@ -674,7 +674,7 @@ void __scx_update_idle(struct rq *rq, bool idle, bool do_notify) * managed by put_prev_task_idle()/set_next_task_idle(). */ if (SCX_HAS_OP(update_idle) && do_notify && !scx_rq_bypassing(rq)) - SCX_CALL_OP(SCX_KF_REST, update_idle, cpu_of(rq), idle); + SCX_CALL_OP(SCX_KF_REST, update_idle, rq, cpu_of(rq), idle); /* * Update the idle masks: diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 1e67d076f195..a009c91f7b05 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -164,10 +164,34 @@ static inline struct timespec64 tk_xtime(const struct timekeeper *tk) return ts; } +static inline struct timespec64 tk_xtime_coarse(const struct timekeeper *tk) +{ + struct timespec64 ts; + + ts.tv_sec = tk->xtime_sec; + ts.tv_nsec = tk->coarse_nsec; + return ts; +} + +/* + * Update the nanoseconds part for the coarse time keepers. They can't rely + * on xtime_nsec because xtime_nsec could be adjusted by a small negative + * amount when the multiplication factor of the clock is adjusted, which + * could cause the coarse clocks to go slightly backwards. See + * timekeeping_apply_adjustment(). Thus we keep a separate copy for the coarse + * clockids which only is updated when the clock has been set or we have + * accumulated time. + */ +static inline void tk_update_coarse_nsecs(struct timekeeper *tk) +{ + tk->coarse_nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; +} + static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec = ts->tv_sec; tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift; + tk_update_coarse_nsecs(tk); } static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts) @@ -175,6 +199,7 @@ static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts) tk->xtime_sec += ts->tv_sec; tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift; tk_normalize_xtime(tk); + tk_update_coarse_nsecs(tk); } static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm) @@ -708,6 +733,7 @@ static void timekeeping_forward_now(struct timekeeper *tk) tk_normalize_xtime(tk); delta -= incr; } + tk_update_coarse_nsecs(tk); } /** @@ -804,8 +830,8 @@ EXPORT_SYMBOL_GPL(ktime_get_with_offset); ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs) { struct timekeeper *tk = &tk_core.timekeeper; - unsigned int seq; ktime_t base, *offset = offsets[offs]; + unsigned int seq; u64 nsecs; WARN_ON(timekeeping_suspended); @@ -813,7 +839,7 @@ ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs) do { seq = read_seqcount_begin(&tk_core.seq); base = ktime_add(tk->tkr_mono.base, *offset); - nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; + nsecs = tk->coarse_nsec; } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -2161,7 +2187,7 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode) struct timekeeper *real_tk = &tk_core.timekeeper; unsigned int clock_set = 0; int shift = 0, maxshift; - u64 offset; + u64 offset, orig_offset; guard(raw_spinlock_irqsave)(&tk_core.lock); @@ -2172,7 +2198,7 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode) offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), tk->tkr_mono.cycle_last, tk->tkr_mono.mask, tk->tkr_mono.clock->max_raw_delta); - + orig_offset = offset; /* Check if there's really nothing to do */ if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK) return false; @@ -2205,6 +2231,14 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode) */ clock_set |= accumulate_nsecs_to_secs(tk); + /* + * To avoid inconsistencies caused adjtimex TK_ADV_FREQ calls + * making small negative adjustments to the base xtime_nsec + * value, only update the coarse clocks if we accumulated time + */ + if (orig_offset != offset) + tk_update_coarse_nsecs(tk); + timekeeping_update_from_shadow(&tk_core, clock_set); return !!clock_set; @@ -2248,7 +2282,7 @@ void ktime_get_coarse_real_ts64(struct timespec64 *ts) do { seq = read_seqcount_begin(&tk_core.seq); - *ts = tk_xtime(tk); + *ts = tk_xtime_coarse(tk); } while (read_seqcount_retry(&tk_core.seq, seq)); } EXPORT_SYMBOL(ktime_get_coarse_real_ts64); @@ -2271,7 +2305,7 @@ void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts) do { seq = read_seqcount_begin(&tk_core.seq); - *ts = tk_xtime(tk); + *ts = tk_xtime_coarse(tk); offset = tk_core.timekeeper.offs_real; } while (read_seqcount_retry(&tk_core.seq, seq)); @@ -2350,12 +2384,12 @@ void ktime_get_coarse_ts64(struct timespec64 *ts) do { seq = read_seqcount_begin(&tk_core.seq); - now = tk_xtime(tk); + now = tk_xtime_coarse(tk); mono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); set_normalized_timespec64(ts, now.tv_sec + mono.tv_sec, - now.tv_nsec + mono.tv_nsec); + now.tv_nsec + mono.tv_nsec); } EXPORT_SYMBOL(ktime_get_coarse_ts64); diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c index 01c2ab1e8971..32ef27c71b57 100644 --- a/kernel/time/vsyscall.c +++ b/kernel/time/vsyscall.c @@ -98,12 +98,12 @@ void update_vsyscall(struct timekeeper *tk) /* CLOCK_REALTIME_COARSE */ vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_REALTIME_COARSE]; vdso_ts->sec = tk->xtime_sec; - vdso_ts->nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; + vdso_ts->nsec = tk->coarse_nsec; /* CLOCK_MONOTONIC_COARSE */ vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC_COARSE]; vdso_ts->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; - nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; + nsec = tk->coarse_nsec; nsec = nsec + tk->wall_to_monotonic.tv_nsec; vdso_ts->sec += __iter_div_u64_rem(nsec, NSEC_PER_SEC, &vdso_ts->nsec); diff --git a/mm/execmem.c b/mm/execmem.c index e6c4f5076ca8..6f7a2653b280 100644 --- a/mm/execmem.c +++ b/mm/execmem.c @@ -254,6 +254,34 @@ out_unlock: return ptr; } +static bool execmem_cache_rox = false; + +void execmem_cache_make_ro(void) +{ + struct maple_tree *free_areas = &execmem_cache.free_areas; + struct maple_tree *busy_areas = &execmem_cache.busy_areas; + MA_STATE(mas_free, free_areas, 0, ULONG_MAX); + MA_STATE(mas_busy, busy_areas, 0, ULONG_MAX); + struct mutex *mutex = &execmem_cache.mutex; + void *area; + + execmem_cache_rox = true; + + mutex_lock(mutex); + + mas_for_each(&mas_free, area, ULONG_MAX) { + unsigned long pages = mas_range_len(&mas_free) >> PAGE_SHIFT; + set_memory_ro(mas_free.index, pages); + } + + mas_for_each(&mas_busy, area, ULONG_MAX) { + unsigned long pages = mas_range_len(&mas_busy) >> PAGE_SHIFT; + set_memory_ro(mas_busy.index, pages); + } + + mutex_unlock(mutex); +} + static int execmem_cache_populate(struct execmem_range *range, size_t size) { unsigned long vm_flags = VM_ALLOW_HUGE_VMAP; @@ -274,9 +302,15 @@ static int execmem_cache_populate(struct execmem_range *range, size_t size) /* fill memory with instructions that will trap */ execmem_fill_trapping_insns(p, alloc_size, /* writable = */ true); - err = set_memory_rox((unsigned long)p, vm->nr_pages); - if (err) - goto err_free_mem; + if (execmem_cache_rox) { + err = set_memory_rox((unsigned long)p, vm->nr_pages); + if (err) + goto err_free_mem; + } else { + err = set_memory_x((unsigned long)p, vm->nr_pages); + if (err) + goto err_free_mem; + } err = execmem_cache_add(p, alloc_size); if (err) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2a47682d1ab7..47d76d03ce30 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -3075,6 +3075,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, bool freeze, struct folio *folio) { + bool pmd_migration = is_pmd_migration_entry(*pmd); + VM_WARN_ON_ONCE(folio && !folio_test_pmd_mappable(folio)); VM_WARN_ON_ONCE(!IS_ALIGNED(address, HPAGE_PMD_SIZE)); VM_WARN_ON_ONCE(folio && !folio_test_locked(folio)); @@ -3085,9 +3087,12 @@ void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address, * require a folio to check the PMD against. Otherwise, there * is a risk of replacing the wrong folio. */ - if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) || - is_pmd_migration_entry(*pmd)) { - if (folio && folio != pmd_folio(*pmd)) + if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) || pmd_migration) { + /* + * Do not apply pmd_folio() to a migration entry; and folio lock + * guarantees that it must be of the wrong folio anyway. + */ + if (folio && (pmd_migration || folio != pmd_folio(*pmd))) return; __split_huge_pmd_locked(vma, pmd, address, freeze); } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index e3e6ac991b9c..6ea1be71aa42 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4034,10 +4034,13 @@ static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst, list_for_each_entry_safe(folio, next, src_list, lru) { int i; + bool cma; if (folio_test_hugetlb_vmemmap_optimized(folio)) continue; + cma = folio_test_hugetlb_cma(folio); + list_del(&folio->lru); split_page_owner(&folio->page, huge_page_order(src), huge_page_order(dst)); @@ -4053,6 +4056,9 @@ static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst, new_folio->mapping = NULL; init_new_hugetlb_folio(dst, new_folio); + /* Copy the CMA flag so that it is freed correctly */ + if (cma) + folio_set_hugetlb_cma(new_folio); list_add(&new_folio->lru, &dst_list); } } diff --git a/mm/internal.h b/mm/internal.h index e9695baa5922..25a29872c634 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -248,11 +248,9 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags, bool *any_writable, bool *any_young, bool *any_dirty) { - unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio); - const pte_t *end_ptep = start_ptep + max_nr; pte_t expected_pte, *ptep; bool writable, young, dirty; - int nr; + int nr, cur_nr; if (any_writable) *any_writable = false; @@ -265,11 +263,15 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio); VM_WARN_ON_FOLIO(page_folio(pfn_to_page(pte_pfn(pte))) != folio, folio); + /* Limit max_nr to the actual remaining PFNs in the folio we could batch. */ + max_nr = min_t(unsigned long, max_nr, + folio_pfn(folio) + folio_nr_pages(folio) - pte_pfn(pte)); + nr = pte_batch_hint(start_ptep, pte); expected_pte = __pte_batch_clear_ignored(pte_advance_pfn(pte, nr), flags); ptep = start_ptep + nr; - while (ptep < end_ptep) { + while (nr < max_nr) { pte = ptep_get(ptep); if (any_writable) writable = !!pte_write(pte); @@ -282,14 +284,6 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, if (!pte_same(pte, expected_pte)) break; - /* - * Stop immediately once we reached the end of the folio. In - * corner cases the next PFN might fall into a different - * folio. - */ - if (pte_pfn(pte) >= folio_end_pfn) - break; - if (any_writable) *any_writable |= writable; if (any_young) @@ -297,12 +291,13 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, if (any_dirty) *any_dirty |= dirty; - nr = pte_batch_hint(ptep, pte); - expected_pte = pte_advance_pfn(expected_pte, nr); - ptep += nr; + cur_nr = pte_batch_hint(ptep, pte); + expected_pte = pte_advance_pfn(expected_pte, cur_nr); + ptep += cur_nr; + nr += cur_nr; } - return min(ptep - start_ptep, max_nr); + return min(nr, max_nr); } /** diff --git a/mm/memblock.c b/mm/memblock.c index d3509414b8c3..0e9ebb8aa7fe 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -457,7 +457,14 @@ static int __init_memblock memblock_double_array(struct memblock_type *type, min(new_area_start, memblock.current_limit), new_alloc_size, PAGE_SIZE); - new_array = addr ? __va(addr) : NULL; + if (addr) { + /* The memory may not have been accepted, yet. */ + accept_memory(addr, new_alloc_size); + + new_array = __va(addr); + } else { + new_array = NULL; + } } if (!addr) { pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n", diff --git a/mm/mm_init.c b/mm/mm_init.c index 9659689b8ace..327764ca0ee4 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -1786,7 +1786,7 @@ static bool arch_has_descending_max_zone_pfns(void) return IS_ENABLED(CONFIG_ARC) && !IS_ENABLED(CONFIG_ARC_HAS_PAE40); } -static void set_high_memory(void) +static void __init set_high_memory(void) { phys_addr_t highmem = memblock_end_of_DRAM(); diff --git a/mm/swapfile.c b/mm/swapfile.c index 2eff8b51a945..412ccd6543b3 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1272,13 +1272,22 @@ int folio_alloc_swap(struct folio *folio, gfp_t gfp) VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(!folio_test_uptodate(folio), folio); - /* - * Should not even be attempting large allocations when huge - * page swap is disabled. Warn and fail the allocation. - */ - if (order && (!IS_ENABLED(CONFIG_THP_SWAP) || size > SWAPFILE_CLUSTER)) { - VM_WARN_ON_ONCE(1); - return -EINVAL; + if (order) { + /* + * Reject large allocation when THP_SWAP is disabled, + * the caller should split the folio and try again. + */ + if (!IS_ENABLED(CONFIG_THP_SWAP)) + return -EAGAIN; + + /* + * Allocation size should never exceed cluster size + * (HPAGE_PMD_SIZE). + */ + if (size > SWAPFILE_CLUSTER) { + VM_WARN_ON_ONCE(1); + return -EINVAL; + } } local_lock(&percpu_swap_cluster.lock); @@ -3323,6 +3332,15 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) } /* + * The swap subsystem needs a major overhaul to support this. + * It doesn't work yet so just disable it for now. + */ + if (mapping_min_folio_order(mapping) > 0) { + error = -EINVAL; + goto bad_swap_unlock_inode; + } + + /* * Read the swap header. */ if (!mapping->a_ops->read_folio) { diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 3ed720a787ec..2d7511654831 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1940,7 +1940,7 @@ static inline void setup_vmalloc_vm(struct vm_struct *vm, { vm->flags = flags; vm->addr = (void *)va->va_start; - vm->size = va_size(va); + vm->size = vm->requested_size = va_size(va); vm->caller = caller; va->vm = vm; } @@ -3133,6 +3133,7 @@ struct vm_struct *__get_vm_area_node(unsigned long size, area->flags = flags; area->caller = caller; + area->requested_size = requested_size; va = alloc_vmap_area(size, align, start, end, node, gfp_mask, 0, area); if (IS_ERR(va)) { @@ -4063,6 +4064,8 @@ EXPORT_SYMBOL(vzalloc_node_noprof); */ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags) { + struct vm_struct *vm = NULL; + size_t alloced_size = 0; size_t old_size = 0; void *n; @@ -4072,15 +4075,17 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags) } if (p) { - struct vm_struct *vm; - vm = find_vm_area(p); if (unlikely(!vm)) { WARN(1, "Trying to vrealloc() nonexistent vm area (%p)\n", p); return NULL; } - old_size = get_vm_area_size(vm); + alloced_size = get_vm_area_size(vm); + old_size = vm->requested_size; + if (WARN(alloced_size < old_size, + "vrealloc() has mismatched area vs requested sizes (%p)\n", p)) + return NULL; } /* @@ -4088,14 +4093,26 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags) * would be a good heuristic for when to shrink the vm_area? */ if (size <= old_size) { - /* Zero out spare memory. */ - if (want_init_on_alloc(flags)) + /* Zero out "freed" memory. */ + if (want_init_on_free()) memset((void *)p + size, 0, old_size - size); + vm->requested_size = size; kasan_poison_vmalloc(p + size, old_size - size); - kasan_unpoison_vmalloc(p, size, KASAN_VMALLOC_PROT_NORMAL); return (void *)p; } + /* + * We already have the bytes available in the allocation; use them. + */ + if (size <= alloced_size) { + kasan_unpoison_vmalloc(p + old_size, size - old_size, + KASAN_VMALLOC_PROT_NORMAL); + /* Zero out "alloced" memory. */ + if (want_init_on_alloc(flags)) + memset((void *)p + old_size, 0, size - old_size); + vm->requested_size = size; + } + /* TODO: Grow the vm_area, i.e. allocate and map additional pages. */ n = __vmalloc_noprof(size, flags); if (!n) diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c index 3ce7b54003c2..687c5eafb49a 100644 --- a/tools/objtool/arch/x86/decode.c +++ b/tools/objtool/arch/x86/decode.c @@ -189,6 +189,15 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec op2 = ins.opcode.bytes[1]; op3 = ins.opcode.bytes[2]; + /* + * XXX hack, decoder is buggered and thinks 0xea is 7 bytes long. + */ + if (op1 == 0xea) { + insn->len = 1; + insn->type = INSN_BUG; + return 0; + } + if (ins.rex_prefix.nbytes) { rex = ins.rex_prefix.bytes[0]; rex_w = X86_REX_W(rex) >> 3; diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index c77c8c8e3d9b..80fb84fa3cfc 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -121,6 +121,7 @@ TARGETS += user_events TARGETS += vDSO TARGETS += mm TARGETS += x86 +TARGETS += x86/bugs TARGETS += zram #Please keep the TARGETS list alphabetically sorted # Run "make quicktest=1 run_tests" or diff --git a/tools/testing/selftests/kvm/arm64/set_id_regs.c b/tools/testing/selftests/kvm/arm64/set_id_regs.c index 322b9d3b0125..57708de2075d 100644 --- a/tools/testing/selftests/kvm/arm64/set_id_regs.c +++ b/tools/testing/selftests/kvm/arm64/set_id_regs.c @@ -129,10 +129,10 @@ static const struct reg_ftr_bits ftr_id_aa64pfr0_el1[] = { REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, DIT, 0), REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, SEL2, 0), REG_FTR_BITS(FTR_EXACT, ID_AA64PFR0_EL1, GIC, 0), - REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL3, 0), - REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL2, 0), - REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL1, 0), - REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL0, 0), + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL3, 1), + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL2, 1), + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL1, 1), + REG_FTR_BITS(FTR_LOWER_SAFE, ID_AA64PFR0_EL1, EL0, 1), REG_FTR_END, }; diff --git a/tools/testing/selftests/mm/compaction_test.c b/tools/testing/selftests/mm/compaction_test.c index 2c3a0eb6b22d..9bc4591c7b16 100644 --- a/tools/testing/selftests/mm/compaction_test.c +++ b/tools/testing/selftests/mm/compaction_test.c @@ -90,6 +90,8 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size, int compaction_index = 0; char nr_hugepages[20] = {0}; char init_nr_hugepages[24] = {0}; + char target_nr_hugepages[24] = {0}; + int slen; snprintf(init_nr_hugepages, sizeof(init_nr_hugepages), "%lu", initial_nr_hugepages); @@ -106,11 +108,18 @@ int check_compaction(unsigned long mem_free, unsigned long hugepage_size, goto out; } - /* Request a large number of huge pages. The Kernel will allocate - as much as it can */ - if (write(fd, "100000", (6*sizeof(char))) != (6*sizeof(char))) { - ksft_print_msg("Failed to write 100000 to /proc/sys/vm/nr_hugepages: %s\n", - strerror(errno)); + /* + * Request huge pages for about half of the free memory. The Kernel + * will allocate as much as it can, and we expect it will get at least 1/3 + */ + nr_hugepages_ul = mem_free / hugepage_size / 2; + snprintf(target_nr_hugepages, sizeof(target_nr_hugepages), + "%lu", nr_hugepages_ul); + + slen = strlen(target_nr_hugepages); + if (write(fd, target_nr_hugepages, slen) != slen) { + ksft_print_msg("Failed to write %lu to /proc/sys/vm/nr_hugepages: %s\n", + nr_hugepages_ul, strerror(errno)); goto close_fd; } diff --git a/tools/testing/selftests/mm/guard-regions.c b/tools/testing/selftests/mm/guard-regions.c index b3d0e2771096..eba43ead13ae 100644 --- a/tools/testing/selftests/mm/guard-regions.c +++ b/tools/testing/selftests/mm/guard-regions.c @@ -271,12 +271,16 @@ FIXTURE_SETUP(guard_regions) self->page_size = (unsigned long)sysconf(_SC_PAGESIZE); setup_sighandler(); - if (variant->backing == ANON_BACKED) + switch (variant->backing) { + case ANON_BACKED: return; - - self->fd = open_file( - variant->backing == SHMEM_BACKED ? "/tmp/" : "", - self->path); + case LOCAL_FILE_BACKED: + self->fd = open_file("", self->path); + break; + case SHMEM_BACKED: + self->fd = memfd_create(self->path, 0); + break; + } /* We truncate file to at least 100 pages, tests can modify as needed. */ ASSERT_EQ(ftruncate(self->fd, 100 * self->page_size), 0); @@ -1696,7 +1700,7 @@ TEST_F(guard_regions, readonly_file) char *ptr; int i; - if (variant->backing == ANON_BACKED) + if (variant->backing != LOCAL_FILE_BACKED) SKIP(return, "Read-only test specific to file-backed"); /* Map shared so we can populate with pattern, populate it, unmap. */ diff --git a/tools/testing/selftests/mm/pkey-powerpc.h b/tools/testing/selftests/mm/pkey-powerpc.h index 1bad310d282a..17bf2d1b0192 100644 --- a/tools/testing/selftests/mm/pkey-powerpc.h +++ b/tools/testing/selftests/mm/pkey-powerpc.h @@ -3,6 +3,8 @@ #ifndef _PKEYS_POWERPC_H #define _PKEYS_POWERPC_H +#include <sys/stat.h> + #ifndef SYS_pkey_alloc # define SYS_pkey_alloc 384 # define SYS_pkey_free 385 @@ -102,8 +104,18 @@ static inline void expect_fault_on_read_execonly_key(void *p1, int pkey) return; } +#define REPEAT_8(s) s s s s s s s s +#define REPEAT_64(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) \ + REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) REPEAT_8(s) +#define REPEAT_512(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) \ + REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) REPEAT_64(s) +#define REPEAT_4096(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) \ + REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) REPEAT_512(s) +#define REPEAT_16384(s) REPEAT_4096(s) REPEAT_4096(s) \ + REPEAT_4096(s) REPEAT_4096(s) + /* 4-byte instructions * 16384 = 64K page */ -#define __page_o_noops() asm(".rept 16384 ; nop; .endr") +#define __page_o_noops() asm(REPEAT_16384("nop\n")) static inline void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey) { diff --git a/tools/testing/selftests/mm/pkey_util.c b/tools/testing/selftests/mm/pkey_util.c index ca4ad0d44ab2..255b332f7a08 100644 --- a/tools/testing/selftests/mm/pkey_util.c +++ b/tools/testing/selftests/mm/pkey_util.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only +#define __SANE_USERSPACE_TYPES__ #include <sys/syscall.h> #include <unistd.h> diff --git a/tools/testing/selftests/x86/bugs/Makefile b/tools/testing/selftests/x86/bugs/Makefile new file mode 100644 index 000000000000..8ff2d7226c7f --- /dev/null +++ b/tools/testing/selftests/x86/bugs/Makefile @@ -0,0 +1,3 @@ +TEST_PROGS := its_sysfs.py its_permutations.py its_indirect_alignment.py its_ret_alignment.py +TEST_FILES := common.py +include ../../lib.mk diff --git a/tools/testing/selftests/x86/bugs/common.py b/tools/testing/selftests/x86/bugs/common.py new file mode 100755 index 000000000000..2f9664a80617 --- /dev/null +++ b/tools/testing/selftests/x86/bugs/common.py @@ -0,0 +1,164 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2025 Intel Corporation +# +# This contains kselftest framework adapted common functions for testing +# mitigation for x86 bugs. + +import os, sys, re, shutil + +sys.path.insert(0, '../../kselftest') +import ksft + +def read_file(path): + if not os.path.exists(path): + return None + with open(path, 'r') as file: + return file.read().strip() + +def cpuinfo_has(arg): + cpuinfo = read_file('/proc/cpuinfo') + if arg in cpuinfo: + return True + return False + +def cmdline_has(arg): + cmdline = read_file('/proc/cmdline') + if arg in cmdline: + return True + return False + +def cmdline_has_either(args): + cmdline = read_file('/proc/cmdline') + for arg in args: + if arg in cmdline: + return True + return False + +def cmdline_has_none(args): + return not cmdline_has_either(args) + +def cmdline_has_all(args): + cmdline = read_file('/proc/cmdline') + for arg in args: + if arg not in cmdline: + return False + return True + +def get_sysfs(bug): + return read_file("/sys/devices/system/cpu/vulnerabilities/" + bug) + +def sysfs_has(bug, mitigation): + status = get_sysfs(bug) + if mitigation in status: + return True + return False + +def sysfs_has_either(bugs, mitigations): + for bug in bugs: + for mitigation in mitigations: + if sysfs_has(bug, mitigation): + return True + return False + +def sysfs_has_none(bugs, mitigations): + return not sysfs_has_either(bugs, mitigations) + +def sysfs_has_all(bugs, mitigations): + for bug in bugs: + for mitigation in mitigations: + if not sysfs_has(bug, mitigation): + return False + return True + +def bug_check_pass(bug, found): + ksft.print_msg(f"\nFound: {found}") + # ksft.print_msg(f"\ncmdline: {read_file('/proc/cmdline')}") + ksft.test_result_pass(f'{bug}: {found}') + +def bug_check_fail(bug, found, expected): + ksft.print_msg(f'\nFound:\t {found}') + ksft.print_msg(f'Expected:\t {expected}') + ksft.print_msg(f"\ncmdline: {read_file('/proc/cmdline')}") + ksft.test_result_fail(f'{bug}: {found}') + +def bug_status_unknown(bug, found): + ksft.print_msg(f'\nUnknown status: {found}') + ksft.print_msg(f"\ncmdline: {read_file('/proc/cmdline')}") + ksft.test_result_fail(f'{bug}: {found}') + +def basic_checks_sufficient(bug, mitigation): + if not mitigation: + bug_status_unknown(bug, "None") + return True + elif mitigation == "Not affected": + ksft.test_result_pass(bug) + return True + elif mitigation == "Vulnerable": + if cmdline_has_either([f'{bug}=off', 'mitigations=off']): + bug_check_pass(bug, mitigation) + return True + return False + +def get_section_info(vmlinux, section_name): + from elftools.elf.elffile import ELFFile + with open(vmlinux, 'rb') as f: + elffile = ELFFile(f) + section = elffile.get_section_by_name(section_name) + if section is None: + ksft.print_msg("Available sections in vmlinux:") + for sec in elffile.iter_sections(): + ksft.print_msg(sec.name) + raise ValueError(f"Section {section_name} not found in {vmlinux}") + return section['sh_addr'], section['sh_offset'], section['sh_size'] + +def get_patch_sites(vmlinux, offset, size): + import struct + output = [] + with open(vmlinux, 'rb') as f: + f.seek(offset) + i = 0 + while i < size: + data = f.read(4) # s32 + if not data: + break + sym_offset = struct.unpack('<i', data)[0] + i + i += 4 + output.append(sym_offset) + return output + +def get_instruction_from_vmlinux(elffile, section, virtual_address, target_address): + from capstone import Cs, CS_ARCH_X86, CS_MODE_64 + section_start = section['sh_addr'] + section_end = section_start + section['sh_size'] + + if not (section_start <= target_address < section_end): + return None + + offset = target_address - section_start + code = section.data()[offset:offset + 16] + + cap = init_capstone() + for instruction in cap.disasm(code, target_address): + if instruction.address == target_address: + return instruction + return None + +def init_capstone(): + from capstone import Cs, CS_ARCH_X86, CS_MODE_64, CS_OPT_SYNTAX_ATT + cap = Cs(CS_ARCH_X86, CS_MODE_64) + cap.syntax = CS_OPT_SYNTAX_ATT + return cap + +def get_runtime_kernel(): + import drgn + return drgn.program_from_kernel() + +def check_dependencies_or_skip(modules, script_name="unknown test"): + for mod in modules: + try: + __import__(mod) + except ImportError: + ksft.test_result_skip(f"Skipping {script_name}: missing module '{mod}'") + ksft.finished() diff --git a/tools/testing/selftests/x86/bugs/its_indirect_alignment.py b/tools/testing/selftests/x86/bugs/its_indirect_alignment.py new file mode 100755 index 000000000000..cdc33ae6a91c --- /dev/null +++ b/tools/testing/selftests/x86/bugs/its_indirect_alignment.py @@ -0,0 +1,150 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2025 Intel Corporation +# +# Test for indirect target selection (ITS) mitigation. +# +# Test if indirect CALL/JMP are correctly patched by evaluating +# the vmlinux .retpoline_sites in /proc/kcore. + +# Install dependencies +# add-apt-repository ppa:michel-slm/kernel-utils +# apt update +# apt install -y python3-drgn python3-pyelftools python3-capstone +# +# Best to copy the vmlinux at a standard location: +# mkdir -p /usr/lib/debug/lib/modules/$(uname -r) +# cp $VMLINUX /usr/lib/debug/lib/modules/$(uname -r)/vmlinux +# +# Usage: ./its_indirect_alignment.py [vmlinux] + +import os, sys, argparse +from pathlib import Path + +this_dir = os.path.dirname(os.path.realpath(__file__)) +sys.path.insert(0, this_dir + '/../../kselftest') +import ksft +import common as c + +bug = "indirect_target_selection" + +mitigation = c.get_sysfs(bug) +if not mitigation or "Aligned branch/return thunks" not in mitigation: + ksft.test_result_skip("Skipping its_indirect_alignment.py: Aligned branch/return thunks not enabled") + ksft.finished() + +if c.sysfs_has("spectre_v2", "Retpolines"): + ksft.test_result_skip("Skipping its_indirect_alignment.py: Retpolines deployed") + ksft.finished() + +c.check_dependencies_or_skip(['drgn', 'elftools', 'capstone'], script_name="its_indirect_alignment.py") + +from elftools.elf.elffile import ELFFile +from drgn.helpers.common.memory import identify_address + +cap = c.init_capstone() + +if len(os.sys.argv) > 1: + arg_vmlinux = os.sys.argv[1] + if not os.path.exists(arg_vmlinux): + ksft.test_result_fail(f"its_indirect_alignment.py: vmlinux not found at argument path: {arg_vmlinux}") + ksft.exit_fail() + os.makedirs(f"/usr/lib/debug/lib/modules/{os.uname().release}", exist_ok=True) + os.system(f'cp {arg_vmlinux} /usr/lib/debug/lib/modules/$(uname -r)/vmlinux') + +vmlinux = f"/usr/lib/debug/lib/modules/{os.uname().release}/vmlinux" +if not os.path.exists(vmlinux): + ksft.test_result_fail(f"its_indirect_alignment.py: vmlinux not found at {vmlinux}") + ksft.exit_fail() + +ksft.print_msg(f"Using vmlinux: {vmlinux}") + +retpolines_start_vmlinux, retpolines_sec_offset, size = c.get_section_info(vmlinux, '.retpoline_sites') +ksft.print_msg(f"vmlinux: Section .retpoline_sites (0x{retpolines_start_vmlinux:x}) found at 0x{retpolines_sec_offset:x} with size 0x{size:x}") + +sites_offset = c.get_patch_sites(vmlinux, retpolines_sec_offset, size) +total_retpoline_tests = len(sites_offset) +ksft.print_msg(f"Found {total_retpoline_tests} retpoline sites") + +prog = c.get_runtime_kernel() +retpolines_start_kcore = prog.symbol('__retpoline_sites').address +ksft.print_msg(f'kcore: __retpoline_sites: 0x{retpolines_start_kcore:x}') + +x86_indirect_its_thunk_r15 = prog.symbol('__x86_indirect_its_thunk_r15').address +ksft.print_msg(f'kcore: __x86_indirect_its_thunk_r15: 0x{x86_indirect_its_thunk_r15:x}') + +tests_passed = 0 +tests_failed = 0 +tests_unknown = 0 + +with open(vmlinux, 'rb') as f: + elffile = ELFFile(f) + text_section = elffile.get_section_by_name('.text') + + for i in range(0, len(sites_offset)): + site = retpolines_start_kcore + sites_offset[i] + vmlinux_site = retpolines_start_vmlinux + sites_offset[i] + passed = unknown = failed = False + try: + vmlinux_insn = c.get_instruction_from_vmlinux(elffile, text_section, text_section['sh_addr'], vmlinux_site) + kcore_insn = list(cap.disasm(prog.read(site, 16), site))[0] + operand = kcore_insn.op_str + insn_end = site + kcore_insn.size - 1 # TODO handle Jcc.32 __x86_indirect_thunk_\reg + safe_site = insn_end & 0x20 + site_status = "" if safe_site else "(unsafe)" + + ksft.print_msg(f"\nSite {i}: {identify_address(prog, site)} <0x{site:x}> {site_status}") + ksft.print_msg(f"\tvmlinux: 0x{vmlinux_insn.address:x}:\t{vmlinux_insn.mnemonic}\t{vmlinux_insn.op_str}") + ksft.print_msg(f"\tkcore: 0x{kcore_insn.address:x}:\t{kcore_insn.mnemonic}\t{kcore_insn.op_str}") + + if (site & 0x20) ^ (insn_end & 0x20): + ksft.print_msg(f"\tSite at safe/unsafe boundary: {str(kcore_insn.bytes)} {kcore_insn.mnemonic} {operand}") + if safe_site: + tests_passed += 1 + passed = True + ksft.print_msg(f"\tPASSED: At safe address") + continue + + if operand.startswith('0xffffffff'): + thunk = int(operand, 16) + if thunk > x86_indirect_its_thunk_r15: + insn_at_thunk = list(cap.disasm(prog.read(thunk, 16), thunk))[0] + operand += ' -> ' + insn_at_thunk.mnemonic + ' ' + insn_at_thunk.op_str + ' <dynamic-thunk?>' + if 'jmp' in insn_at_thunk.mnemonic and thunk & 0x20: + ksft.print_msg(f"\tPASSED: Found {operand} at safe address") + passed = True + if not passed: + if kcore_insn.operands[0].type == capstone.CS_OP_IMM: + operand += ' <' + prog.symbol(int(operand, 16)) + '>' + if '__x86_indirect_its_thunk_' in operand: + ksft.print_msg(f"\tPASSED: Found {operand}") + else: + ksft.print_msg(f"\tPASSED: Found direct branch: {kcore_insn}, ITS thunk not required.") + passed = True + else: + unknown = True + if passed: + tests_passed += 1 + elif unknown: + ksft.print_msg(f"UNKNOWN: unexpected operand: {kcore_insn}") + tests_unknown += 1 + else: + ksft.print_msg(f'\t************* FAILED *************') + ksft.print_msg(f"\tFound {kcore_insn.bytes} {kcore_insn.mnemonic} {operand}") + ksft.print_msg(f'\t**********************************') + tests_failed += 1 + except Exception as e: + ksft.print_msg(f"UNKNOWN: An unexpected error occurred: {e}") + tests_unknown += 1 + +ksft.print_msg(f"\n\nSummary:") +ksft.print_msg(f"PASS: \t{tests_passed} \t/ {total_retpoline_tests}") +ksft.print_msg(f"FAIL: \t{tests_failed} \t/ {total_retpoline_tests}") +ksft.print_msg(f"UNKNOWN: \t{tests_unknown} \t/ {total_retpoline_tests}") + +if tests_failed == 0: + ksft.test_result_pass("All ITS return thunk sites passed") +else: + ksft.test_result_fail(f"{tests_failed} ITS return thunk sites failed") +ksft.finished() diff --git a/tools/testing/selftests/x86/bugs/its_permutations.py b/tools/testing/selftests/x86/bugs/its_permutations.py new file mode 100755 index 000000000000..3204f4728c62 --- /dev/null +++ b/tools/testing/selftests/x86/bugs/its_permutations.py @@ -0,0 +1,109 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2025 Intel Corporation +# +# Test for indirect target selection (ITS) cmdline permutations with other bugs +# like spectre_v2 and retbleed. + +import os, sys, subprocess, itertools, re, shutil + +test_dir = os.path.dirname(os.path.realpath(__file__)) +sys.path.insert(0, test_dir + '/../../kselftest') +import ksft +import common as c + +bug = "indirect_target_selection" +mitigation = c.get_sysfs(bug) + +if not mitigation or "Not affected" in mitigation: + ksft.test_result_skip("Skipping its_permutations.py: not applicable") + ksft.finished() + +if shutil.which('vng') is None: + ksft.test_result_skip("Skipping its_permutations.py: virtme-ng ('vng') not found in PATH.") + ksft.finished() + +TEST = f"{test_dir}/its_sysfs.py" +default_kparam = ['clearcpuid=hypervisor', 'panic=5', 'panic_on_warn=1', 'oops=panic', 'nmi_watchdog=1', 'hung_task_panic=1'] + +DEBUG = " -v " + +# Install dependencies +# https://github.com/arighi/virtme-ng +# apt install virtme-ng +BOOT_CMD = f"vng --run {test_dir}/../../../../../arch/x86/boot/bzImage " +#BOOT_CMD += DEBUG + +bug = "indirect_target_selection" + +input_options = { + 'indirect_target_selection' : ['off', 'on', 'stuff', 'vmexit'], + 'retbleed' : ['off', 'stuff', 'auto'], + 'spectre_v2' : ['off', 'on', 'eibrs', 'retpoline', 'ibrs', 'eibrs,retpoline'], +} + +def pretty_print(output): + OKBLUE = '\033[94m' + OKGREEN = '\033[92m' + WARNING = '\033[93m' + FAIL = '\033[91m' + ENDC = '\033[0m' + BOLD = '\033[1m' + + # Define patterns and their corresponding colors + patterns = { + r"^ok \d+": OKGREEN, + r"^not ok \d+": FAIL, + r"^# Testing .*": OKBLUE, + r"^# Found: .*": WARNING, + r"^# Totals: .*": BOLD, + r"pass:([1-9]\d*)": OKGREEN, + r"fail:([1-9]\d*)": FAIL, + r"skip:([1-9]\d*)": WARNING, + } + + # Apply colors based on patterns + for pattern, color in patterns.items(): + output = re.sub(pattern, lambda match: f"{color}{match.group(0)}{ENDC}", output, flags=re.MULTILINE) + + print(output) + +combinations = list(itertools.product(*input_options.values())) +ksft.print_header() +ksft.set_plan(len(combinations)) + +logs = "" + +for combination in combinations: + append = "" + log = "" + for p in default_kparam: + append += f' --append={p}' + command = BOOT_CMD + append + test_params = "" + for i, key in enumerate(input_options.keys()): + param = f'{key}={combination[i]}' + test_params += f' {param}' + command += f" --append={param}" + command += f" -- {TEST}" + test_name = f"{bug} {test_params}" + pretty_print(f'# Testing {test_name}') + t = subprocess.Popen(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT) + t.wait() + output, _ = t.communicate() + if t.returncode == 0: + ksft.test_result_pass(test_name) + else: + ksft.test_result_fail(test_name) + output = output.decode() + log += f" {output}" + pretty_print(log) + logs += output + "\n" + +# Optionally use tappy to parse the output +# apt install python3-tappy +with open("logs.txt", "w") as f: + f.write(logs) + +ksft.finished() diff --git a/tools/testing/selftests/x86/bugs/its_ret_alignment.py b/tools/testing/selftests/x86/bugs/its_ret_alignment.py new file mode 100755 index 000000000000..f40078d9f6ff --- /dev/null +++ b/tools/testing/selftests/x86/bugs/its_ret_alignment.py @@ -0,0 +1,139 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2025 Intel Corporation +# +# Test for indirect target selection (ITS) mitigation. +# +# Tests if the RETs are correctly patched by evaluating the +# vmlinux .return_sites in /proc/kcore. +# +# Install dependencies +# add-apt-repository ppa:michel-slm/kernel-utils +# apt update +# apt install -y python3-drgn python3-pyelftools python3-capstone +# +# Run on target machine +# mkdir -p /usr/lib/debug/lib/modules/$(uname -r) +# cp $VMLINUX /usr/lib/debug/lib/modules/$(uname -r)/vmlinux +# +# Usage: ./its_ret_alignment.py + +import os, sys, argparse +from pathlib import Path + +this_dir = os.path.dirname(os.path.realpath(__file__)) +sys.path.insert(0, this_dir + '/../../kselftest') +import ksft +import common as c + +bug = "indirect_target_selection" +mitigation = c.get_sysfs(bug) +if not mitigation or "Aligned branch/return thunks" not in mitigation: + ksft.test_result_skip("Skipping its_ret_alignment.py: Aligned branch/return thunks not enabled") + ksft.finished() + +c.check_dependencies_or_skip(['drgn', 'elftools', 'capstone'], script_name="its_ret_alignment.py") + +from elftools.elf.elffile import ELFFile +from drgn.helpers.common.memory import identify_address + +cap = c.init_capstone() + +if len(os.sys.argv) > 1: + arg_vmlinux = os.sys.argv[1] + if not os.path.exists(arg_vmlinux): + ksft.test_result_fail(f"its_ret_alignment.py: vmlinux not found at user-supplied path: {arg_vmlinux}") + ksft.exit_fail() + os.makedirs(f"/usr/lib/debug/lib/modules/{os.uname().release}", exist_ok=True) + os.system(f'cp {arg_vmlinux} /usr/lib/debug/lib/modules/$(uname -r)/vmlinux') + +vmlinux = f"/usr/lib/debug/lib/modules/{os.uname().release}/vmlinux" +if not os.path.exists(vmlinux): + ksft.test_result_fail(f"its_ret_alignment.py: vmlinux not found at {vmlinux}") + ksft.exit_fail() + +ksft.print_msg(f"Using vmlinux: {vmlinux}") + +rethunks_start_vmlinux, rethunks_sec_offset, size = c.get_section_info(vmlinux, '.return_sites') +ksft.print_msg(f"vmlinux: Section .return_sites (0x{rethunks_start_vmlinux:x}) found at 0x{rethunks_sec_offset:x} with size 0x{size:x}") + +sites_offset = c.get_patch_sites(vmlinux, rethunks_sec_offset, size) +total_rethunk_tests = len(sites_offset) +ksft.print_msg(f"Found {total_rethunk_tests} rethunk sites") + +prog = c.get_runtime_kernel() +rethunks_start_kcore = prog.symbol('__return_sites').address +ksft.print_msg(f'kcore: __rethunk_sites: 0x{rethunks_start_kcore:x}') + +its_return_thunk = prog.symbol('its_return_thunk').address +ksft.print_msg(f'kcore: its_return_thunk: 0x{its_return_thunk:x}') + +tests_passed = 0 +tests_failed = 0 +tests_unknown = 0 +tests_skipped = 0 + +with open(vmlinux, 'rb') as f: + elffile = ELFFile(f) + text_section = elffile.get_section_by_name('.text') + + for i in range(len(sites_offset)): + site = rethunks_start_kcore + sites_offset[i] + vmlinux_site = rethunks_start_vmlinux + sites_offset[i] + try: + passed = unknown = failed = skipped = False + + symbol = identify_address(prog, site) + vmlinux_insn = c.get_instruction_from_vmlinux(elffile, text_section, text_section['sh_addr'], vmlinux_site) + kcore_insn = list(cap.disasm(prog.read(site, 16), site))[0] + + insn_end = site + kcore_insn.size - 1 + + safe_site = insn_end & 0x20 + site_status = "" if safe_site else "(unsafe)" + + ksft.print_msg(f"\nSite {i}: {symbol} <0x{site:x}> {site_status}") + ksft.print_msg(f"\tvmlinux: 0x{vmlinux_insn.address:x}:\t{vmlinux_insn.mnemonic}\t{vmlinux_insn.op_str}") + ksft.print_msg(f"\tkcore: 0x{kcore_insn.address:x}:\t{kcore_insn.mnemonic}\t{kcore_insn.op_str}") + + if safe_site: + tests_passed += 1 + passed = True + ksft.print_msg(f"\tPASSED: At safe address") + continue + + if "jmp" in kcore_insn.mnemonic: + passed = True + elif "ret" not in kcore_insn.mnemonic: + skipped = True + + if passed: + ksft.print_msg(f"\tPASSED: Found {kcore_insn.mnemonic} {kcore_insn.op_str}") + tests_passed += 1 + elif skipped: + ksft.print_msg(f"\tSKIPPED: Found '{kcore_insn.mnemonic}'") + tests_skipped += 1 + elif unknown: + ksft.print_msg(f"UNKNOWN: An unknown instruction: {kcore_insn}") + tests_unknown += 1 + else: + ksft.print_msg(f'\t************* FAILED *************') + ksft.print_msg(f"\tFound {kcore_insn.mnemonic} {kcore_insn.op_str}") + ksft.print_msg(f'\t**********************************') + tests_failed += 1 + except Exception as e: + ksft.print_msg(f"UNKNOWN: An unexpected error occurred: {e}") + tests_unknown += 1 + +ksft.print_msg(f"\n\nSummary:") +ksft.print_msg(f"PASSED: \t{tests_passed} \t/ {total_rethunk_tests}") +ksft.print_msg(f"FAILED: \t{tests_failed} \t/ {total_rethunk_tests}") +ksft.print_msg(f"SKIPPED: \t{tests_skipped} \t/ {total_rethunk_tests}") +ksft.print_msg(f"UNKNOWN: \t{tests_unknown} \t/ {total_rethunk_tests}") + +if tests_failed == 0: + ksft.test_result_pass("All ITS return thunk sites passed.") +else: + ksft.test_result_fail(f"{tests_failed} failed sites need ITS return thunks.") +ksft.finished() diff --git a/tools/testing/selftests/x86/bugs/its_sysfs.py b/tools/testing/selftests/x86/bugs/its_sysfs.py new file mode 100755 index 000000000000..7bca81f2f606 --- /dev/null +++ b/tools/testing/selftests/x86/bugs/its_sysfs.py @@ -0,0 +1,65 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (c) 2025 Intel Corporation +# +# Test for Indirect Target Selection(ITS) mitigation sysfs status. + +import sys, os, re +this_dir = os.path.dirname(os.path.realpath(__file__)) +sys.path.insert(0, this_dir + '/../../kselftest') +import ksft + +from common import * + +bug = "indirect_target_selection" +mitigation = get_sysfs(bug) + +ITS_MITIGATION_ALIGNED_THUNKS = "Mitigation: Aligned branch/return thunks" +ITS_MITIGATION_RETPOLINE_STUFF = "Mitigation: Retpolines, Stuffing RSB" +ITS_MITIGATION_VMEXIT_ONLY = "Mitigation: Vulnerable, KVM: Not affected" +ITS_MITIGATION_VULNERABLE = "Vulnerable" + +def check_mitigation(): + if mitigation == ITS_MITIGATION_ALIGNED_THUNKS: + if cmdline_has(f'{bug}=stuff') and sysfs_has("spectre_v2", "Retpolines"): + bug_check_fail(bug, ITS_MITIGATION_ALIGNED_THUNKS, ITS_MITIGATION_RETPOLINE_STUFF) + return + if cmdline_has(f'{bug}=vmexit') and cpuinfo_has('its_native_only'): + bug_check_fail(bug, ITS_MITIGATION_ALIGNED_THUNKS, ITS_MITIGATION_VMEXIT_ONLY) + return + bug_check_pass(bug, ITS_MITIGATION_ALIGNED_THUNKS) + return + + if mitigation == ITS_MITIGATION_RETPOLINE_STUFF: + if cmdline_has(f'{bug}=stuff') and sysfs_has("spectre_v2", "Retpolines"): + bug_check_pass(bug, ITS_MITIGATION_RETPOLINE_STUFF) + return + if sysfs_has('retbleed', 'Stuffing'): + bug_check_pass(bug, ITS_MITIGATION_RETPOLINE_STUFF) + return + bug_check_fail(bug, ITS_MITIGATION_RETPOLINE_STUFF, ITS_MITIGATION_ALIGNED_THUNKS) + + if mitigation == ITS_MITIGATION_VMEXIT_ONLY: + if cmdline_has(f'{bug}=vmexit') and cpuinfo_has('its_native_only'): + bug_check_pass(bug, ITS_MITIGATION_VMEXIT_ONLY) + return + bug_check_fail(bug, ITS_MITIGATION_VMEXIT_ONLY, ITS_MITIGATION_ALIGNED_THUNKS) + + if mitigation == ITS_MITIGATION_VULNERABLE: + if sysfs_has("spectre_v2", "Vulnerable"): + bug_check_pass(bug, ITS_MITIGATION_VULNERABLE) + else: + bug_check_fail(bug, "Mitigation", ITS_MITIGATION_VULNERABLE) + + bug_status_unknown(bug, mitigation) + return + +ksft.print_header() +ksft.set_plan(1) +ksft.print_msg(f'{bug}: {mitigation} ...') + +if not basic_checks_sufficient(bug, mitigation): + check_mitigation() + +ksft.finished() |