diff options
| author | Jakub Kicinski <kuba@kernel.org> | 2023-11-23 12:19:49 -0800 |
|---|---|---|
| committer | Jakub Kicinski <kuba@kernel.org> | 2023-11-23 12:20:58 -0800 |
| commit | 45c226dde742a92e22dcd65b96bf7e02620a9c19 (patch) | |
| tree | abaedb7f2ddf75914659c7b9a48af34ca89a9208 | |
| parent | c5b9f4792ea6b9abfcfb9486ba256f55e296aaa7 (diff) | |
| parent | d3fa86b1a7b4cdc4367acacea16b72e0a200b3d7 (diff) | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Cross-merge networking fixes after downstream PR.
Conflicts:
drivers/net/ethernet/intel/ice/ice_main.c
c9663f79cd82 ("ice: adjust switchdev rebuild path")
7758017911a4 ("ice: restore timestamp configuration after device reset")
https://lore.kernel.org/all/20231121211259.3348630-1-anthony.l.nguyen@intel.com/
Adjacent changes:
kernel/bpf/verifier.c
bb124da69c47 ("bpf: keep track of max number of bpf_loop callback iterations")
5f99f312bd3b ("bpf: add register bounds sanity checks and sanitization")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
231 files changed, 4253 insertions, 3236 deletions
diff --git a/Documentation/arch/loongarch/introduction.rst b/Documentation/arch/loongarch/introduction.rst index 8c568cfc2107..5e6db78abeaf 100644 --- a/Documentation/arch/loongarch/introduction.rst +++ b/Documentation/arch/loongarch/introduction.rst @@ -375,9 +375,9 @@ Developer web site of Loongson and LoongArch (Software and Documentation): Documentation of LoongArch ISA: - https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-Vol1-v1.02-CN.pdf (in Chinese) + https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-Vol1-v1.10-CN.pdf (in Chinese) - https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-Vol1-v1.02-EN.pdf (in English) + https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-Vol1-v1.10-EN.pdf (in English) Documentation of LoongArch ELF psABI: diff --git a/Documentation/arch/x86/boot.rst b/Documentation/arch/x86/boot.rst index f5d2f2414de8..22cc7a040dae 100644 --- a/Documentation/arch/x86/boot.rst +++ b/Documentation/arch/x86/boot.rst @@ -77,7 +77,7 @@ Protocol 2.14 BURNT BY INCORRECT COMMIT Protocol 2.15 (Kernel 5.5) Added the kernel_info and kernel_info.setup_type_max. ============= ============================================================ -.. note:: + .. note:: The protocol version number should be changed only if the setup header is changed. There is no need to update the version number if boot_params or kernel_info are changed. Additionally, it is recommended to use diff --git a/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml b/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml index 462ead5a1cec..2cf3d016db42 100644 --- a/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml +++ b/Documentation/devicetree/bindings/ufs/qcom,ufs.yaml @@ -36,6 +36,7 @@ properties: - qcom,sm8350-ufshc - qcom,sm8450-ufshc - qcom,sm8550-ufshc + - qcom,sm8650-ufshc - const: qcom,ufshc - const: jedec,ufs-2.0 @@ -122,6 +123,7 @@ allOf: - qcom,sm8350-ufshc - qcom,sm8450-ufshc - qcom,sm8550-ufshc + - qcom,sm8650-ufshc then: properties: clocks: diff --git a/Documentation/filesystems/erofs.rst b/Documentation/filesystems/erofs.rst index 57c6ae23b3fc..cc4626d6ee4f 100644 --- a/Documentation/filesystems/erofs.rst +++ b/Documentation/filesystems/erofs.rst @@ -91,6 +91,10 @@ compatibility checking tool (fsck.erofs), and a debugging tool (dump.erofs): - git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs-utils.git +For more information, please also refer to the documentation site: + +- https://erofs.docs.kernel.org + Bugs and patches are welcome, please kindly help us and send to the following linux-erofs mailing list: diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst index 7feacc20835e..84ee60fceef2 100644 --- a/Documentation/process/maintainer-netdev.rst +++ b/Documentation/process/maintainer-netdev.rst @@ -193,9 +193,23 @@ Review timelines Generally speaking, the patches get triaged quickly (in less than 48h). But be patient, if your patch is active in patchwork (i.e. it's listed on the project's patch list) the chances it was missed are close to zero. -Asking the maintainer for status updates on your -patch is a good way to ensure your patch is ignored or pushed to the -bottom of the priority list. + +The high volume of development on netdev makes reviewers move on +from discussions relatively quickly. New comments and replies +are very unlikely to arrive after a week of silence. If a patch +is no longer active in patchwork and the thread went idle for more +than a week - clarify the next steps and/or post the next version. + +For RFC postings specifically, if nobody responded in a week - reviewers +either missed the posting or have no strong opinions. If the code is ready, +repost as a PATCH. + +Emails saying just "ping" or "bump" are considered rude. If you can't figure +out the status of the patch from patchwork or where the discussion has +landed - describe your best guess and ask if it's correct. For example:: + + I don't understand what the next steps are. Person X seems to be unhappy + with A, should I do B and repost the patches? .. _Changes requested: diff --git a/Documentation/translations/zh_CN/arch/loongarch/introduction.rst b/Documentation/translations/zh_CN/arch/loongarch/introduction.rst index 59d6bf33050c..bf463c5a4c51 100644 --- a/Documentation/translations/zh_CN/arch/loongarch/introduction.rst +++ b/Documentation/translations/zh_CN/arch/loongarch/introduction.rst @@ -338,9 +338,9 @@ Loongson与LoongArch的开发者网站（软件与文档资源）： LoongArch指令集架构的文档： - https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-Vol1-v1.02-CN.pdf （中文版） + https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-Vol1-v1.10-CN.pdf （中文版） - https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-Vol1-v1.02-EN.pdf （英文版） + https://github.com/loongson/LoongArch-Documentation/releases/latest/download/LoongArch-Vol1-v1.10-EN.pdf （英文版） LoongArch的ELF psABI文档： diff --git a/MAINTAINERS b/MAINTAINERS index 482d428472e7..509281e9e169 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7855,6 +7855,7 @@ R: Yue Hu <huyue2@coolpad.com> R: Jeffle Xu <jefflexu@linux.alibaba.com> L: linux-erofs@lists.ozlabs.org S: Maintained +W: https://erofs.docs.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/xiang/erofs.git F: Documentation/ABI/testing/sysfs-fs-erofs F: Documentation/filesystems/erofs.rst @@ -11024,7 +11025,6 @@ F: drivers/net/wireless/intel/iwlwifi/ INTEL WMI SLIM BOOTLOADER (SBL) FIRMWARE UPDATE DRIVER M: Jithu Joseph <jithu.joseph@intel.com> -R: Maurice Ma <maurice.ma@intel.com> S: Maintained W: https://slimbootloader.github.io/security/firmware-update.html F: drivers/platform/x86/intel/wmi/sbl-fw-update.c @@ -13778,7 +13778,6 @@ F: drivers/net/ethernet/mellanox/mlxfw/ MELLANOX HARDWARE PLATFORM SUPPORT M: Hans de Goede <hdegoede@redhat.com> M: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com> -M: Mark Gross <markgross@kernel.org> M: Vadim Pasternak <vadimp@nvidia.com> L: platform-driver-x86@vger.kernel.org S: Supported @@ -14387,7 +14386,6 @@ F: drivers/platform/surface/surface_gpe.c MICROSOFT SURFACE HARDWARE PLATFORM SUPPORT M: Hans de Goede <hdegoede@redhat.com> M: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com> -M: Mark Gross <markgross@kernel.org> M: Maximilian Luz <luzmaximilian@gmail.com> L: platform-driver-x86@vger.kernel.org S: Maintained @@ -14994,6 +14992,7 @@ M: Jakub Kicinski <kuba@kernel.org> M: Paolo Abeni <pabeni@redhat.com> L: netdev@vger.kernel.org S: Maintained +P: Documentation/process/maintainer-netdev.rst Q: https://patchwork.kernel.org/project/netdevbpf/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git @@ -15045,6 +15044,7 @@ M: Jakub Kicinski <kuba@kernel.org> M: Paolo Abeni <pabeni@redhat.com> L: netdev@vger.kernel.org S: Maintained +P: Documentation/process/maintainer-netdev.rst Q: https://patchwork.kernel.org/project/netdevbpf/list/ B: mailto:netdev@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git @@ -15055,6 +15055,7 @@ F: Documentation/networking/ F: Documentation/process/maintainer-netdev.rst F: Documentation/userspace-api/netlink/ F: include/linux/in.h +F: include/linux/indirect_call_wrapper.h F: include/linux/net.h F: include/linux/netdevice.h F: include/net/ @@ -23664,7 +23665,6 @@ F: drivers/platform/x86/x86-android-tablets/ X86 PLATFORM DRIVERS M: Hans de Goede <hdegoede@redhat.com> M: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com> -M: Mark Gross <markgross@kernel.org> L: platform-driver-x86@vger.kernel.org S: Maintained Q: https://patchwork.kernel.org/project/platform-driver-x86/list/ @@ -23702,6 +23702,20 @@ F: arch/x86/kernel/dumpstack.c F: arch/x86/kernel/stacktrace.c F: arch/x86/kernel/unwind_*.c +X86 TRUST DOMAIN EXTENSIONS (TDX) +M: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> +R: Dave Hansen <dave.hansen@linux.intel.com> +L: x86@kernel.org +L: linux-coco@lists.linux.dev +S: Supported +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/tdx +F: arch/x86/boot/compressed/tdx* +F: arch/x86/coco/tdx/ +F: arch/x86/include/asm/shared/tdx.h +F: arch/x86/include/asm/tdx.h +F: arch/x86/virt/vmx/tdx/ +F: drivers/virt/coco/tdx-guest + X86 VDSO M: Andy Lutomirski <luto@kernel.org> L: linux-kernel@vger.kernel.org @@ -23882,8 +23896,7 @@ T: git git://git.kernel.org/pub/scm/fs/xfs/xfs-linux.git P: Documentation/filesystems/xfs-maintainer-entry-profile.rst F: Documentation/ABI/testing/sysfs-fs-xfs F: Documentation/admin-guide/xfs.rst -F: Documentation/filesystems/xfs-delayed-logging-design.rst -F: Documentation/filesystems/xfs-self-describing-metadata.rst +F: Documentation/filesystems/xfs-* F: fs/xfs/ F: include/uapi/linux/dqblk_xfs.h F: include/uapi/linux/fsmap.h @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 7 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile index 9eeb0c05f3f4..204b94b2e6aa 100644 --- a/arch/loongarch/Makefile +++ b/arch/loongarch/Makefile @@ -68,6 +68,7 @@ LDFLAGS_vmlinux += -static -n -nostdlib ifdef CONFIG_AS_HAS_EXPLICIT_RELOCS cflags-y += $(call cc-option,-mexplicit-relocs) KBUILD_CFLAGS_KERNEL += $(call cc-option,-mdirect-extern-access) +KBUILD_CFLAGS_KERNEL += $(call cc-option,-fdirect-access-external-data) KBUILD_AFLAGS_MODULE += $(call cc-option,-fno-direct-access-external-data) KBUILD_CFLAGS_MODULE += $(call cc-option,-fno-direct-access-external-data) KBUILD_AFLAGS_MODULE += $(call cc-option,-mno-relax) $(call cc-option,-Wa$(comma)-mno-relax) @@ -142,6 +143,8 @@ vdso-install-y += arch/loongarch/vdso/vdso.so.dbg all: $(notdir $(KBUILD_IMAGE)) +vmlinuz.efi: vmlinux.efi + vmlinux.elf vmlinux.efi vmlinuz.efi: vmlinux $(Q)$(MAKE) $(build)=$(boot) $(bootvars-y) $(boot)/$@ diff --git a/arch/loongarch/include/asm/asmmacro.h b/arch/loongarch/include/asm/asmmacro.h index c9544f358c33..655db7d7a427 100644 --- a/arch/loongarch/include/asm/asmmacro.h +++ b/arch/loongarch/include/asm/asmmacro.h @@ -609,8 +609,7 @@ lu32i.d \reg, 0 lu52i.d \reg, \reg, 0 .pushsection ".la_abs", "aw", %progbits - 768: - .dword 768b-766b + .dword 766b .dword \sym .popsection #endif diff --git a/arch/loongarch/include/asm/percpu.h b/arch/loongarch/include/asm/percpu.h index ed5da02b1cf6..9b36ac003f89 100644 --- a/arch/loongarch/include/asm/percpu.h +++ b/arch/loongarch/include/asm/percpu.h @@ -40,13 +40,13 @@ static __always_inline unsigned long __percpu_##op(void *ptr, \ switch (size) { \ case 4: \ __asm__ __volatile__( \ - "am"#asm_op".w" " %[ret], %[val], %[ptr] \n" \ + "am"#asm_op".w" " %[ret], %[val], %[ptr] \n" \ : [ret] "=&r" (ret), [ptr] "+ZB"(*(u32 *)ptr) \ : [val] "r" (val)); \ break; \ case 8: \ __asm__ __volatile__( \ - "am"#asm_op".d" " %[ret], %[val], %[ptr] \n" \ + "am"#asm_op".d" " %[ret], %[val], %[ptr] \n" \ : [ret] "=&r" (ret), [ptr] "+ZB"(*(u64 *)ptr) \ : [val] "r" (val)); \ break; \ @@ -63,7 +63,7 @@ PERCPU_OP(and, and, &) PERCPU_OP(or, or, |) #undef PERCPU_OP -static __always_inline unsigned long __percpu_read(void *ptr, int size) +static __always_inline unsigned long __percpu_read(void __percpu *ptr, int size) { unsigned long ret; @@ -100,7 +100,7 @@ static __always_inline unsigned long __percpu_read(void *ptr, int size) return ret; } -static __always_inline void __percpu_write(void *ptr, unsigned long val, int size) +static __always_inline void __percpu_write(void __percpu *ptr, unsigned long val, int size) { switch (size) { case 1: @@ -132,8 +132,7 @@ static __always_inline void __percpu_write(void *ptr, unsigned long val, int siz } } -static __always_inline unsigned long __percpu_xchg(void *ptr, unsigned long val, - int size) +static __always_inline unsigned long __percpu_xchg(void *ptr, unsigned long val, int size) { switch (size) { case 1: diff --git a/arch/loongarch/include/asm/setup.h b/arch/loongarch/include/asm/setup.h index a0bc159ce8bd..ee52fb1e9963 100644 --- a/arch/loongarch/include/asm/setup.h +++ b/arch/loongarch/include/asm/setup.h @@ -25,7 +25,7 @@ extern void set_merr_handler(unsigned long offset, void *addr, unsigned long len #ifdef CONFIG_RELOCATABLE struct rela_la_abs { - long offset; + long pc; long symvalue; }; diff --git a/arch/loongarch/kernel/relocate.c b/arch/loongarch/kernel/relocate.c index 6c3eff9af9fb..1acfa704c8d0 100644 --- a/arch/loongarch/kernel/relocate.c +++ b/arch/loongarch/kernel/relocate.c @@ -52,7 +52,7 @@ static inline void __init relocate_absolute(long random_offset) for (p = begin; (void *)p < end; p++) { long v = p->symvalue; uint32_t lu12iw, ori, lu32id, lu52id; - union loongarch_instruction *insn = (void *)p - p->offset; + union loongarch_instruction *insn = (void *)p->pc; lu12iw = (v >> 12) & 0xfffff; ori = v & 0xfff; @@ -102,6 +102,14 @@ static inline __init unsigned long get_random_boot(void) return hash; } +static int __init nokaslr(char *p) +{ + pr_info("KASLR is disabled.\n"); + + return 0; /* Print a notice and silence the boot warning */ +} +early_param("nokaslr", nokaslr); + static inline __init bool kaslr_disabled(void) { char *str; diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c index 3064af94db9c..e7015f7b70e3 100644 --- a/arch/loongarch/kernel/time.c +++ b/arch/loongarch/kernel/time.c @@ -58,14 +58,16 @@ static int constant_set_state_oneshot(struct clock_event_device *evt) return 0; } -static int constant_set_state_oneshot_stopped(struct clock_event_device *evt) +static int constant_set_state_periodic(struct clock_event_device *evt) { + unsigned long period; unsigned long timer_config; raw_spin_lock(&state_lock); - timer_config = csr_read64(LOONGARCH_CSR_TCFG); - timer_config &= ~CSR_TCFG_EN; + period = const_clock_freq / HZ; + timer_config = period & CSR_TCFG_VAL; + timer_config |= (CSR_TCFG_PERIOD | CSR_TCFG_EN); csr_write64(timer_config, LOONGARCH_CSR_TCFG); raw_spin_unlock(&state_lock); @@ -73,16 +75,14 @@ static int constant_set_state_oneshot_stopped(struct clock_event_device *evt) return 0; } -static int constant_set_state_periodic(struct clock_event_device *evt) +static int constant_set_state_shutdown(struct clock_event_device *evt) { - unsigned long period; unsigned long timer_config; raw_spin_lock(&state_lock); - period = const_clock_freq / HZ; - timer_config = period & CSR_TCFG_VAL; - timer_config |= (CSR_TCFG_PERIOD | CSR_TCFG_EN); + timer_config = csr_read64(LOONGARCH_CSR_TCFG); + timer_config &= ~CSR_TCFG_EN; csr_write64(timer_config, LOONGARCH_CSR_TCFG); raw_spin_unlock(&state_lock); @@ -90,11 +90,6 @@ static int constant_set_state_periodic(struct clock_event_device *evt) return 0; } -static int constant_set_state_shutdown(struct clock_event_device *evt) -{ - return 0; -} - static int constant_timer_next_event(unsigned long delta, struct clock_event_device *evt) { unsigned long timer_config; @@ -161,7 +156,7 @@ int constant_clockevent_init(void) cd->rating = 320; cd->cpumask = cpumask_of(cpu); cd->set_state_oneshot = constant_set_state_oneshot; - cd->set_state_oneshot_stopped = constant_set_state_oneshot_stopped; + cd->set_state_oneshot_stopped = constant_set_state_shutdown; cd->set_state_periodic = constant_set_state_periodic; cd->set_state_shutdown = constant_set_state_shutdown; cd->set_next_event = constant_timer_next_event; diff --git a/arch/loongarch/mm/pgtable.c b/arch/loongarch/mm/pgtable.c index 71d0539e2d0b..2aae72e63871 100644 --- a/arch/loongarch/mm/pgtable.c +++ b/arch/loongarch/mm/pgtable.c @@ -13,13 +13,13 @@ struct page *dmw_virt_to_page(unsigned long kaddr) { return pfn_to_page(virt_to_pfn(kaddr)); } -EXPORT_SYMBOL_GPL(dmw_virt_to_page); +EXPORT_SYMBOL(dmw_virt_to_page); struct page *tlb_virt_to_page(unsigned long kaddr) { return pfn_to_page(pte_pfn(*virt_to_kpte(kaddr))); } -EXPORT_SYMBOL_GPL(tlb_virt_to_page); +EXPORT_SYMBOL(tlb_virt_to_page); pgd_t *pgd_alloc(struct mm_struct *mm) { diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index fd69dfa0cdab..a7c9c0e69e5a 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -140,11 +140,11 @@ config ARCH_MMAP_RND_COMPAT_BITS_MIN default 8 config ARCH_MMAP_RND_BITS_MAX - default 24 if 64BIT - default 17 + default 18 if 64BIT + default 13 config ARCH_MMAP_RND_COMPAT_BITS_MAX - default 17 + default 13 # unless you want to implement ACPI on PA-RISC ... ;-) config PM diff --git a/arch/parisc/include/asm/elf.h b/arch/parisc/include/asm/elf.h index 140eaa97bf21..2d73d3c3cd37 100644 --- a/arch/parisc/include/asm/elf.h +++ b/arch/parisc/include/asm/elf.h @@ -349,15 +349,7 @@ struct pt_regs; /* forward declaration... */ #define ELF_HWCAP 0 -/* Masks for stack and mmap randomization */ -#define BRK_RND_MASK (is_32bit_task() ? 0x07ffUL : 0x3ffffUL) -#define MMAP_RND_MASK (is_32bit_task() ? 0x1fffUL : 0x3ffffUL) -#define STACK_RND_MASK MMAP_RND_MASK - -struct mm_struct; -extern unsigned long arch_randomize_brk(struct mm_struct *); -#define arch_randomize_brk arch_randomize_brk - +#define STACK_RND_MASK 0x7ff /* 8MB of VA */ #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1 struct linux_binprm; diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h index c05d121cf5d0..982aca20f56f 100644 --- a/arch/parisc/include/asm/processor.h +++ b/arch/parisc/include/asm/processor.h @@ -47,6 +47,8 @@ #ifndef __ASSEMBLY__ +struct rlimit; +unsigned long mmap_upper_limit(struct rlimit *rlim_stack); unsigned long calc_max_stack_size(unsigned long stack_max); /* diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c index 29e2750f86a4..e95a977ba5f3 100644 --- a/arch/parisc/kernel/processor.c +++ b/arch/parisc/kernel/processor.c @@ -383,7 +383,7 @@ show_cpuinfo (struct seq_file *m, void *v) char cpu_name[60], *p; /* strip PA path from CPU name to not confuse lscpu */ - strlcpy(cpu_name, per_cpu(cpu_data, 0).dev->name, sizeof(cpu_name)); + strscpy(cpu_name, per_cpu(cpu_data, 0).dev->name, sizeof(cpu_name)); p = strrchr(cpu_name, '['); if (p) *(--p) = 0; diff --git a/arch/parisc/kernel/sys_parisc.c b/arch/parisc/kernel/sys_parisc.c index ab896eff7a1d..98af719d5f85 100644 --- a/arch/parisc/kernel/sys_parisc.c +++ b/arch/parisc/kernel/sys_parisc.c @@ -77,7 +77,7 @@ unsigned long calc_max_stack_size(unsigned long stack_max) * indicating that "current" should be used instead of a passed-in * value from the exec bprm as done with arch_pick_mmap_layout(). */ -static unsigned long mmap_upper_limit(struct rlimit *rlim_stack) +unsigned long mmap_upper_limit(struct rlimit *rlim_stack) { unsigned long stack_base; diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 21556ad87f4b..8f3a4d16bb79 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -15,6 +15,7 @@ #include <linux/io.h> #include <asm/apic.h> #include <asm/desc.h> +#include <asm/e820/api.h> #include <asm/sev.h> #include <asm/ibt.h> #include <asm/hypervisor.h> @@ -286,15 +287,31 @@ static int hv_cpu_die(unsigned int cpu) static int __init hv_pci_init(void) { - int gen2vm = efi_enabled(EFI_BOOT); + bool gen2vm = efi_enabled(EFI_BOOT); /* - * For Generation-2 VM, we exit from pci_arch_init() by returning 0. - * The purpose is to suppress the harmless warning: + * A Generation-2 VM doesn't support legacy PCI/PCIe, so both + * raw_pci_ops and raw_pci_ext_ops are NULL, and pci_subsys_init() -> + * pcibios_init() doesn't call pcibios_resource_survey() -> + * e820__reserve_resources_late(); as a result, any emulated persistent + * memory of E820_TYPE_PRAM (12) via the kernel parameter + * memmap=nn[KMG]!ss is not added into iomem_resource and hence can't be + * detected by register_e820_pmem(). Fix this by directly calling + * e820__reserve_resources_late() here: e820__reserve_resources_late() + * depends on e820__reserve_resources(), which has been called earlier + * from setup_arch(). Note: e820__reserve_resources_late() also adds + * any memory of E820_TYPE_PMEM (7) into iomem_resource, and + * acpi_nfit_register_region() -> acpi_nfit_insert_resource() -> + * region_intersects() returns REGION_INTERSECTS, so the memory of + * E820_TYPE_PMEM won't get added twice. + * + * We return 0 here so that pci_arch_init() won't print the warning: * "PCI: Fatal: No config space access function found" */ - if (gen2vm) + if (gen2vm) { + e820__reserve_resources_late(); return 0; + } /* For Generation-1 VM, we'll proceed in pci_arch_init(). */ return 1; diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index d0918a75cb00..1a0dd80d81ac 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -63,6 +63,7 @@ int acpi_fix_pin2_polarity __initdata; #ifdef CONFIG_X86_LOCAL_APIC static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; +static bool has_lapic_cpus __initdata; static bool acpi_support_online_capable; #endif @@ -233,6 +234,14 @@ acpi_parse_x2apic(union acpi_subtable_headers *header, const unsigned long end) return 0; /* + * According to https://uefi.org/specs/ACPI/6.5/05_ACPI_Software_Programming_Model.html#processor-local-x2apic-structure + * when MADT provides both valid LAPIC and x2APIC entries, the APIC ID + * in x2APIC must be equal or greater than 0xff. + */ + if (has_lapic_cpus && apic_id < 0xff) + return 0; + + /* * We need to register disabled CPU as well to permit * counting disabled CPUs. This allows us to size * cpus_possible_map more accurately, to permit @@ -1114,10 +1123,7 @@ static int __init early_acpi_parse_madt_lapic_addr_ovr(void) static int __init acpi_parse_madt_lapic_entries(void) { - int count; - int x2count = 0; - int ret; - struct acpi_subtable_proc madt_proc[2]; + int count, x2count = 0; if (!boot_cpu_has(X86_FEATURE_APIC)) return -ENODEV; @@ -1126,21 +1132,11 @@ static int __init acpi_parse_madt_lapic_entries(void) acpi_parse_sapic, MAX_LOCAL_APIC); if (!count) { - memset(madt_proc, 0, sizeof(madt_proc)); - madt_proc[0].id = ACPI_MADT_TYPE_LOCAL_APIC; - madt_proc[0].handler = acpi_parse_lapic; - madt_proc[1].id = ACPI_MADT_TYPE_LOCAL_X2APIC; - madt_proc[1].handler = acpi_parse_x2apic; - ret = acpi_table_parse_entries_array(ACPI_SIG_MADT, - sizeof(struct acpi_table_madt), - madt_proc, ARRAY_SIZE(madt_proc), MAX_LOCAL_APIC); - if (ret < 0) { - pr_err("Error parsing LAPIC/X2APIC entries\n"); - return ret; - } - - count = madt_proc[0].count; - x2count = madt_proc[1].count; + count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC, + acpi_parse_lapic, MAX_LOCAL_APIC); + has_lapic_cpus = count > 0; + x2count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC, + acpi_parse_x2apic, MAX_LOCAL_APIC); } if (!count && !x2count) { pr_err("No LAPIC entries present\n"); diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index e6bba12c759c..01fa06dd06b6 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -262,11 +262,14 @@ static uint32_t __init ms_hyperv_platform(void) static int hv_nmi_unknown(unsigned int val, struct pt_regs *regs) { static atomic_t nmi_cpu = ATOMIC_INIT(-1); + unsigned int old_cpu, this_cpu; if (!unknown_nmi_panic) return NMI_DONE; - if (atomic_cmpxchg(&nmi_cpu, -1, raw_smp_processor_id()) != -1) + old_cpu = -1; + this_cpu = raw_smp_processor_id(); + if (!atomic_try_cmpxchg(&nmi_cpu, &old_cpu, this_cpu)) return NMI_HANDLED; return NMI_DONE; diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c index cacf2ede6217..23d8aaf8d9fd 100644 --- a/arch/x86/kernel/signal_64.c +++ b/arch/x86/kernel/signal_64.c @@ -175,9 +175,6 @@ int x64_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) frame = get_sigframe(ksig, regs, sizeof(struct rt_sigframe), &fp); uc_flags = frame_uc_flags(regs); - if (setup_signal_shadow_stack(ksig)) - return -EFAULT; - if (!user_access_begin(frame, sizeof(*frame))) return -EFAULT; @@ -198,6 +195,9 @@ int x64_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) return -EFAULT; } + if (setup_signal_shadow_stack(ksig)) + return -EFAULT; + /* Set up registers for signal handler */ regs->di = ksig->sig; /* In case the signal handler was declared without prototypes */ diff --git a/block/blk-mq.c b/block/blk-mq.c index e2d11183f62e..900c1be1fee1 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2858,11 +2858,8 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q, }; struct request *rq; - if (unlikely(bio_queue_enter(bio))) - return NULL; - if (blk_mq_attempt_bio_merge(q, bio, nsegs)) - goto queue_exit; + return NULL; rq_qos_throttle(q, bio); @@ -2878,35 +2875,23 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q, rq_qos_cleanup(q, bio); if (bio->bi_opf & REQ_NOWAIT) bio_wouldblock_error(bio); -queue_exit: - blk_queue_exit(q); return NULL; } -static inline struct request *blk_mq_get_cached_request(struct request_queue *q, - struct blk_plug *plug, struct bio **bio, unsigned int nsegs) +/* return true if this @rq can be used for @bio */ +static bool blk_mq_can_use_cached_rq(struct request *rq, struct blk_plug *plug, + struct bio *bio) { - struct request *rq; - enum hctx_type type, hctx_type; + enum hctx_type type = blk_mq_get_hctx_type(bio->bi_opf); + enum hctx_type hctx_type = rq->mq_hctx->type; - if (!plug) - return NULL; - rq = rq_list_peek(&plug->cached_rq); - if (!rq || rq->q != q) - return NULL; + WARN_ON_ONCE(rq_list_peek(&plug->cached_rq) != rq); - if (blk_mq_attempt_bio_merge(q, *bio, nsegs)) { - *bio = NULL; - return NULL; - } - - type = blk_mq_get_hctx_type((*bio)->bi_opf); - hctx_type = rq->mq_hctx->type; if (type != hctx_type && !(type == HCTX_TYPE_READ && hctx_type == HCTX_TYPE_DEFAULT)) - return NULL; - if (op_is_flush(rq->cmd_flags) != op_is_flush((*bio)->bi_opf)) - return NULL; + return false; + if (op_is_flush(rq->cmd_flags) != op_is_flush(bio->bi_opf)) + return false; /* * If any qos ->throttle() end up blocking, we will have flushed the @@ -2914,12 +2899,12 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q, * before we throttle. */ plug->cached_rq = rq_list_next(rq); - rq_qos_throttle(q, *bio); + rq_qos_throttle(rq->q, bio); blk_mq_rq_time_init(rq, 0); - rq->cmd_flags = (*bio)->bi_opf; + rq->cmd_flags = bio->bi_opf; INIT_LIST_HEAD(&rq->queuelist); - return rq; + return true; } static void bio_set_ioprio(struct bio *bio) @@ -2949,7 +2934,7 @@ void blk_mq_submit_bio(struct bio *bio) struct blk_plug *plug = blk_mq_plug(bio); const int is_sync = op_is_sync(bio->bi_opf); struct blk_mq_hw_ctx *hctx; - struct request *rq; + struct request *rq = NULL; unsigned int nr_segs = 1; blk_status_t ret; @@ -2960,20 +2945,36 @@ void blk_mq_submit_bio(struct bio *bio) return; } - if (!bio_integrity_prep(bio)) - return; - bio_set_ioprio(bio); - rq = blk_mq_get_cached_request(q, plug, &bio, nr_segs); - if (!rq) { - if (!bio) + if (plug) { + rq = rq_list_peek(&plug->cached_rq); + if (rq && rq->q != q) + rq = NULL; + } + if (rq) { + if (!bio_integrity_prep(bio)) return; - rq = blk_mq_get_new_requests(q, plug, bio, nr_segs); - if (unlikely(!rq)) + if (blk_mq_attempt_bio_merge(q, bio, nr_segs)) return; + if (blk_mq_can_use_cached_rq(rq, plug, bio)) + goto done; + percpu_ref_get(&q->q_usage_counter); + } else { + if (unlikely(bio_queue_enter(bio))) + return; + if (!bio_integrity_prep(bio)) + goto fail; + } + + rq = blk_mq_get_new_requests(q, plug, bio, nr_segs); + if (unlikely(!rq)) { +fail: + blk_queue_exit(q); + return; } +done: trace_block_getrq(bio); rq_qos_track(q, rq, bio); diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c index 0ace218783c8..e9b16cbc26f4 100644 --- a/drivers/accel/ivpu/ivpu_pm.c +++ b/drivers/accel/ivpu/ivpu_pm.c @@ -250,9 +250,6 @@ int ivpu_rpm_get_if_active(struct ivpu_device *vdev) { int ret; - ivpu_dbg(vdev, RPM, "rpm_get_if_active count %d\n", - atomic_read(&vdev->drm.dev->power.usage_count)); - ret = pm_runtime_get_if_active(vdev->drm.dev, false); drm_WARN_ON(&vdev->drm, ret < 0); diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index a6dc3997bf5c..442a0ebeb953 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -1093,9 +1093,10 @@ int dpll_nl_pin_id_get_doit(struct sk_buff *skb, struct genl_info *info) return -ENOMEM; hdr = genlmsg_put_reply(msg, info, &dpll_nl_family, 0, DPLL_CMD_PIN_ID_GET); - if (!hdr) + if (!hdr) { + nlmsg_free(msg); return -EMSGSIZE; - + } pin = dpll_pin_find_from_nlattr(info); if (!IS_ERR(pin)) { ret = dpll_msg_add_pin_handle(msg, pin); @@ -1123,8 +1124,10 @@ int dpll_nl_pin_get_doit(struct sk_buff *skb, struct genl_info *info) return -ENOMEM; hdr = genlmsg_put_reply(msg, info, &dpll_nl_family, 0, DPLL_CMD_PIN_GET); - if (!hdr) + if (!hdr) { + nlmsg_free(msg); return -EMSGSIZE; + } ret = dpll_cmd_pin_get_one(msg, pin, info->extack); if (ret) { nlmsg_free(msg); @@ -1256,8 +1259,10 @@ int dpll_nl_device_id_get_doit(struct sk_buff *skb, struct genl_info *info) return -ENOMEM; hdr = genlmsg_put_reply(msg, info, &dpll_nl_family, 0, DPLL_CMD_DEVICE_ID_GET); - if (!hdr) + if (!hdr) { + nlmsg_free(msg); return -EMSGSIZE; + } dpll = dpll_device_find_from_nlattr(info); if (!IS_ERR(dpll)) { @@ -1284,8 +1289,10 @@ int dpll_nl_device_get_doit(struct sk_buff *skb, struct genl_info *info) return -ENOMEM; hdr = genlmsg_put_reply(msg, info, &dpll_nl_family, 0, DPLL_CMD_DEVICE_GET); - if (!hdr) + if (!hdr) { + nlmsg_free(msg); return -EMSGSIZE; + } ret = dpll_device_get_one(dpll, msg, info->extack); if (ret) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index afec09930efa..9d92ca157677 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -248,6 +248,7 @@ extern int amdgpu_umsch_mm; extern int amdgpu_seamless; extern int amdgpu_user_partt_mode; +extern int amdgpu_agp; #define AMDGPU_VM_MAX_NUM_CTX 4096 #define AMDGPU_SG_THRESHOLD (256*1024*1024) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index df3ecfa9e13f..e50be6500030 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -207,7 +207,7 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p, } for (i = 0; i < p->nchunks; i++) { - struct drm_amdgpu_cs_chunk __user **chunk_ptr = NULL; + struct drm_amdgpu_cs_chunk __user *chunk_ptr = NULL; struct drm_amdgpu_cs_chunk user_chunk; uint32_t __user *cdata; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 3095a3a864af..8f24cabe2155 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -207,6 +207,7 @@ int amdgpu_user_partt_mode = AMDGPU_AUTO_COMPUTE_PARTITION_MODE; int amdgpu_umsch_mm; int amdgpu_seamless = -1; /* auto */ uint amdgpu_debug_mask; +int amdgpu_agp = -1; /* auto */ static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work); @@ -961,6 +962,15 @@ module_param_named(seamless, amdgpu_seamless, int, 0444); MODULE_PARM_DESC(debug_mask, "debug options for amdgpu, disabled by default"); module_param_named(debug_mask, amdgpu_debug_mask, uint, 0444); +/** + * DOC: agp (int) + * Enable the AGP aperture. This provides an aperture in the GPU's internal + * address space for direct access to system memory. Note that these accesses + * are non-snooped, so they are only used for access to uncached memory. + */ +MODULE_PARM_DESC(agp, "AGP (-1 = auto (default), 0 = disable, 1 = enable)"); +module_param_named(agp, amdgpu_agp, int, 0444); + /* These devices are not supported by amdgpu. * They are supported by the mach64, r128, radeon drivers */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 32b701cc0376..a21045d018f2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -1473,6 +1473,11 @@ int psp_xgmi_get_topology_info(struct psp_context *psp, topology->nodes[i].num_links = (requires_reflection && topology->nodes[i].num_links) ? topology->nodes[i].num_links : node_num_links; } + /* popluate the connected port num info if supported and available */ + if (ta_port_num_support && topology->nodes[i].num_links) { + memcpy(topology->nodes[i].port_num, link_extend_info_output->nodes[i].port_num, + sizeof(struct xgmi_connected_port_num) * TA_XGMI__MAX_PORT_NUM); + } /* reflect the topology information for bi-directionality */ if (requires_reflection && topology->nodes[i].num_hops) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h index 5d36ad3f48c7..c4d9cbde55b9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h @@ -150,6 +150,7 @@ struct psp_xgmi_node_info { uint8_t is_sharing_enabled; enum ta_xgmi_assigned_sdma_engine sdma_engine; uint8_t num_links; + struct xgmi_connected_port_num port_num[TA_XGMI__MAX_PORT_NUM]; }; struct psp_xgmi_topology_info { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 84e5987b14e0..a3dc68e98910 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1188,7 +1188,7 @@ static int amdgpu_ras_query_error_status_helper(struct amdgpu_device *adev, } if (block_obj->hw_ops->query_ras_error_count) - block_obj->hw_ops->query_ras_error_count(adev, &err_data); + block_obj->hw_ops->query_ras_error_count(adev, err_data); if ((info->head.block == AMDGPU_RAS_BLOCK__SDMA) || (info->head.block == AMDGPU_RAS_BLOCK__GFX) || diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c index 65949cc7abb9..07d930339b07 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c @@ -398,6 +398,7 @@ int amdgpu_uvd_sw_fini(struct amdgpu_device *adev) * amdgpu_uvd_entity_init - init entity * * @adev: amdgpu_device pointer + * @ring: amdgpu_ring pointer to check * * Initialize the entity used for handle management in the kernel driver. */ diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c index 0954447f689d..59acf424a078 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c @@ -230,6 +230,7 @@ int amdgpu_vce_sw_fini(struct amdgpu_device *adev) * amdgpu_vce_entity_init - init entity * * @adev: amdgpu_device pointer + * @ring: amdgpu_ring pointer to check * * Initialize the entity used for handle management in the kernel driver. */ diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c index 0ec7b061d7c2..a5a05c16c10d 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c @@ -675,7 +675,7 @@ static void gmc_v10_0_vram_gtt_location(struct amdgpu_device *adev, amdgpu_gmc_set_agp_default(adev, mc); amdgpu_gmc_vram_location(adev, &adev->gmc, base); amdgpu_gmc_gart_location(adev, mc, AMDGPU_GART_PLACEMENT_BEST_FIT); - if (!amdgpu_sriov_vf(adev)) + if (!amdgpu_sriov_vf(adev) && (amdgpu_agp == 1)) amdgpu_gmc_agp_location(adev, mc); /* base offset of vram pages */ diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c index 6dce9b29f675..23d7b548d13f 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c @@ -640,8 +640,9 @@ static void gmc_v11_0_vram_gtt_location(struct amdgpu_device *adev, amdgpu_gmc_set_agp_default(adev, mc); amdgpu_gmc_vram_location(adev, &adev->gmc, base); amdgpu_gmc_gart_location(adev, mc, AMDGPU_GART_PLACEMENT_HIGH); - if (!amdgpu_sriov_vf(adev) || - (amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(11, 5, 0))) + if (!amdgpu_sriov_vf(adev) && + (amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(11, 5, 0)) && + (amdgpu_agp == 1)) amdgpu_gmc_agp_location(adev, mc); /* base offset of vram pages */ diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c index bde25eb4ed8e..2ac5820e9c92 100644 --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c @@ -1630,7 +1630,7 @@ static void gmc_v9_0_vram_gtt_location(struct amdgpu_device *adev, } else { amdgpu_gmc_vram_location(adev, mc, base); amdgpu_gmc_gart_location(adev, mc, AMDGPU_GART_PLACEMENT_BEST_FIT); - if (!amdgpu_sriov_vf(adev)) + if (!amdgpu_sriov_vf(adev) && (amdgpu_agp == 1)) amdgpu_gmc_agp_location(adev, mc); } /* base offset of vram pages */ @@ -2170,8 +2170,6 @@ static int gmc_v9_0_sw_fini(void *handle) if (amdgpu_ip_version(adev, GC_HWIP, 0) == IP_VERSION(9, 4, 3)) amdgpu_gmc_sysfs_fini(adev); - adev->gmc.num_mem_partitions = 0; - kfree(adev->gmc.mem_partitions); amdgpu_gmc_ras_fini(adev); amdgpu_gem_force_release(adev); @@ -2185,6 +2183,9 @@ static int gmc_v9_0_sw_fini(void *handle) amdgpu_bo_free_kernel(&adev->gmc.pdb0_bo, NULL, &adev->gmc.ptr_pdb0); amdgpu_bo_fini(adev); + adev->gmc.num_mem_partitions = 0; + kfree(adev->gmc.mem_partitions); + return 0; } diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c index ea142611be1c..9b0146732e13 100644 --- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c +++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c @@ -130,6 +130,9 @@ static void mmhub_v1_8_init_system_aperture_regs(struct amdgpu_device *adev) uint64_t value; int i; + if (amdgpu_sriov_vf(adev)) + return; + inst_mask = adev->aid_mask; for_each_inst(i, inst_mask) { /* Program the AGP BAR */ @@ -139,9 +142,6 @@ static void mmhub_v1_8_init_system_aperture_regs(struct amdgpu_device *adev) WREG32_SOC15(MMHUB, i, regMC_VM_AGP_TOP, adev->gmc.agp_end >> 24); - if (amdgpu_sriov_vf(adev)) - return; - /* Program the system aperture low logical page number. */ WREG32_SOC15(MMHUB, i, regMC_VM_SYSTEM_APERTURE_LOW_ADDR, min(adev->gmc.fb_start, adev->gmc.agp_start) >> 18); diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 6f99f6754c11..ee97814ebd99 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2079,7 +2079,7 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev) struct dmub_srv_create_params create_params; struct dmub_srv_region_params region_params; struct dmub_srv_region_info region_info; - struct dmub_srv_fb_params fb_params; + struct dmub_srv_memory_params memory_params; struct dmub_srv_fb_info *fb_info; struct dmub_srv *dmub_srv; const struct dmcub_firmware_header_v1_0 *hdr; @@ -2182,6 +2182,7 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev) adev->dm.dmub_fw->data + le32_to_cpu(hdr->header.ucode_array_offset_bytes) + PSP_HEADER_BYTES; + region_params.is_mailbox_in_inbox = false; status = dmub_srv_calc_region_info(dmub_srv, ®ion_params, ®ion_info); @@ -2205,10 +2206,10 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev) return r; /* Rebase the regions on the framebuffer address. */ - memset(&fb_params, 0, sizeof(fb_params)); - fb_params.cpu_addr = adev->dm.dmub_bo_cpu_addr; - fb_params.gpu_addr = adev->dm.dmub_bo_gpu_addr; - fb_params.region_info = ®ion_info; + memset(&memory_params, 0, sizeof(memory_params)); + memory_params.cpu_fb_addr = adev->dm.dmub_bo_cpu_addr; + memory_params.gpu_fb_addr = adev->dm.dmub_bo_gpu_addr; + memory_params.region_info = ®ion_info; adev->dm.dmub_fb_info = kzalloc(sizeof(*adev->dm.dmub_fb_info), GFP_KERNEL); @@ -2220,7 +2221,7 @@ static int dm_dmub_sw_init(struct amdgpu_device *adev) return -ENOMEM; } - status = dmub_srv_calc_fb_info(dmub_srv, &fb_params, fb_info); + status = dmub_srv_calc_mem_info(dmub_srv, &memory_params, fb_info); if (status != DMUB_STATUS_OK) { DRM_ERROR("Error calculating DMUB FB info: %d\n", status); return -EINVAL; @@ -7481,6 +7482,9 @@ static int amdgpu_dm_i2c_xfer(struct i2c_adapter *i2c_adap, int i; int result = -EIO; + if (!ddc_service->ddc_pin || !ddc_service->ddc_pin->hw_info.hw_supported) + return result; + cmd.payloads = kcalloc(num, sizeof(struct i2c_payload), GFP_KERNEL); if (!cmd.payloads) @@ -9603,14 +9607,14 @@ static bool should_reset_plane(struct drm_atomic_state *state, struct drm_plane *other; struct drm_plane_state *old_other_state, *new_other_state; struct drm_crtc_state *new_crtc_state; + struct amdgpu_device *adev = drm_to_adev(plane->dev); int i; /* - * TODO: Remove this hack once the checks below are sufficient - * enough to determine when we need to reset all the planes on - * the stream. + * TODO: Remove this hack for all asics once it proves that the + * fast updates works fine on DCN3.2+. */ - if (state->allow_modeset) + if (adev->ip_versions[DCE_HWIP][0] < IP_VERSION(3, 2, 0) && state->allow_modeset) return true; /* Exit early if we know that we're adding or removing the plane. */ diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c index ed784cf27d39..c7a29bb737e2 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c @@ -536,11 +536,8 @@ bool dm_helpers_dp_read_dpcd( struct amdgpu_dm_connector *aconnector = link->priv; - if (!aconnector) { - drm_dbg_dp(aconnector->base.dev, - "Failed to find connector for link!\n"); + if (!aconnector) return false; - } return drm_dp_dpcd_read(&aconnector->dm_dp_aux.aux, address, data, size) == size; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index d3b13d362eda..11da0eebee6c 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -1604,31 +1604,31 @@ enum dc_status dm_dp_mst_is_port_support_mode( unsigned int upper_link_bw_in_kbps = 0, down_link_bw_in_kbps = 0; unsigned int max_compressed_bw_in_kbps = 0; struct dc_dsc_bw_range bw_range = {0}; - struct drm_dp_mst_topology_mgr *mst_mgr; + uint16_t full_pbn = aconnector->mst_output_port->full_pbn; /* - * check if the mode could be supported if DSC pass-through is supported - * AND check if there enough bandwidth available to support the mode - * with DSC enabled. + * Consider the case with the depth of the mst topology tree is equal or less than 2 + * A. When dsc bitstream can be transmitted along the entire path + * 1. dsc is possible between source and branch/leaf device (common dsc params is possible), AND + * 2. dsc passthrough supported at MST branch, or + * 3. dsc decoding supported at leaf MST device + * Use maximum dsc compression as bw constraint + * B. When dsc bitstream cannot be transmitted along the entire path + * Use native bw as bw constraint */ if (is_dsc_common_config_possible(stream, &bw_range) && - aconnector->mst_output_port->passthrough_aux) { - mst_mgr = aconnector->mst_output_port->mgr; - mutex_lock(&mst_mgr->lock); - + (aconnector->mst_output_port->passthrough_aux || + aconnector->dsc_aux == &aconnector->mst_output_port->aux)) { cur_link_settings = stream->link->verified_link_cap; upper_link_bw_in_kbps = dc_link_bandwidth_kbps(aconnector->dc_link, - &cur_link_settings - ); - down_link_bw_in_kbps = kbps_from_pbn(aconnector->mst_output_port->full_pbn); + &cur_link_settings); + down_link_bw_in_kbps = kbps_from_pbn(full_pbn); /* pick the bottleneck */ end_to_end_bw_in_kbps = min(upper_link_bw_in_kbps, down_link_bw_in_kbps); - mutex_unlock(&mst_mgr->lock); - /* * use the maximum dsc compression bandwidth as the required * bandwidth for the mode @@ -1643,8 +1643,7 @@ enum dc_status dm_dp_mst_is_port_support_mode( /* check if mode could be supported within full_pbn */ bpp = convert_dc_color_depth_into_bpc(stream->timing.display_color_depth) * 3; pbn = drm_dp_calc_pbn_mode(stream->timing.pix_clk_100hz / 10, bpp, false); - - if (pbn > aconnector->mst_output_port->full_pbn) + if (pbn > full_pbn) return DC_FAIL_BANDWIDTH_VALIDATE; } diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c index 0fa4fcd00de2..507a7cf56711 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c @@ -820,22 +820,22 @@ static void dcn35_set_idle_state(struct clk_mgr *clk_mgr_base, bool allow_idle) if (dc->config.disable_ips == DMUB_IPS_ENABLE || dc->config.disable_ips == DMUB_IPS_DISABLE_DYNAMIC) { - val |= DMUB_IPS1_ALLOW_MASK; - val |= DMUB_IPS2_ALLOW_MASK; - } else if (dc->config.disable_ips == DMUB_IPS_DISABLE_IPS1) { val = val & ~DMUB_IPS1_ALLOW_MASK; val = val & ~DMUB_IPS2_ALLOW_MASK; - } else if (dc->config.disable_ips == DMUB_IPS_DISABLE_IPS2) { - val |= DMUB_IPS1_ALLOW_MASK; - val = val & ~DMUB_IPS2_ALLOW_MASK; - } else if (dc->config.disable_ips == DMUB_IPS_DISABLE_IPS2_Z10) { + } else if (dc->config.disable_ips == DMUB_IPS_DISABLE_IPS1) { val |= DMUB_IPS1_ALLOW_MASK; val |= DMUB_IPS2_ALLOW_MASK; + } else if (dc->config.disable_ips == DMUB_IPS_DISABLE_IPS2) { + val = val & ~DMUB_IPS1_ALLOW_MASK; + val |= DMUB_IPS2_ALLOW_MASK; + } else if (dc->config.disable_ips == DMUB_IPS_DISABLE_IPS2_Z10) { + val = val & ~DMUB_IPS1_ALLOW_MASK; + val = val & ~DMUB_IPS2_ALLOW_MASK; } if (!allow_idle) { - val = val & ~DMUB_IPS1_ALLOW_MASK; - val = val & ~DMUB_IPS2_ALLOW_MASK; + val |= DMUB_IPS1_ALLOW_MASK; + val |= DMUB_IPS2_ALLOW_MASK; } dcn35_smu_write_ips_scratch(clk_mgr, val); diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 7b9bf5cb4529..76b47f178127 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -3178,7 +3178,7 @@ static bool update_planes_and_stream_state(struct dc *dc, struct pipe_ctx *otg_master = resource_get_otg_master_for_stream(&context->res_ctx, context->streams[i]); - if (otg_master->stream->test_pattern.type != DP_TEST_PATTERN_VIDEO_MODE) + if (otg_master && otg_master->stream->test_pattern.type != DP_TEST_PATTERN_VIDEO_MODE) resource_build_test_pattern_params(&context->res_ctx, otg_master); } } @@ -4934,8 +4934,8 @@ bool dc_dmub_is_ips_idle_state(struct dc *dc) if (dc->hwss.get_idle_state) idle_state = dc->hwss.get_idle_state(dc); - if ((idle_state & DMUB_IPS1_ALLOW_MASK) || - (idle_state & DMUB_IPS2_ALLOW_MASK)) + if (!(idle_state & DMUB_IPS1_ALLOW_MASK) || + !(idle_state & DMUB_IPS2_ALLOW_MASK)) return true; return false; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 1d48278cba96..a1f1d1003992 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -5190,6 +5190,9 @@ bool dc_resource_acquire_secondary_pipe_for_mpc_odm_legacy( sec_next = sec_pipe->next_odm_pipe; sec_prev = sec_pipe->prev_odm_pipe; + if (pri_pipe == NULL) + return false; + *sec_pipe = *pri_pipe; sec_pipe->top_pipe = sec_top; diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c index e4c007203318..0e07699c1e83 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c +++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c @@ -1202,11 +1202,11 @@ void dc_dmub_srv_exit_low_power_state(const struct dc *dc) allow_state = dc->hwss.get_idle_state(dc); dc->hwss.set_idle_state(dc, false); - if (allow_state & DMUB_IPS2_ALLOW_MASK) { + if (!(allow_state & DMUB_IPS2_ALLOW_MASK)) { // Wait for evaluation time udelay(dc->debug.ips2_eval_delay_us); commit_state = dc->hwss.get_idle_state(dc); - if (commit_state & DMUB_IPS2_COMMIT_MASK) { + if (!(commit_state & DMUB_IPS2_COMMIT_MASK)) { // Tell PMFW to exit low power state dc->clk_mgr->funcs->exit_low_power_state(dc->clk_mgr); @@ -1216,7 +1216,7 @@ void dc_dmub_srv_exit_low_power_state(const struct dc *dc) for (i = 0; i < max_num_polls; ++i) { commit_state = dc->hwss.get_idle_state(dc); - if (!(commit_state & DMUB_IPS2_COMMIT_MASK)) + if (commit_state & DMUB_IPS2_COMMIT_MASK) break; udelay(1); @@ -1235,10 +1235,10 @@ void dc_dmub_srv_exit_low_power_state(const struct dc *dc) } dc_dmub_srv_notify_idle(dc, false); - if (allow_state & DMUB_IPS1_ALLOW_MASK) { + if (!(allow_state & DMUB_IPS1_ALLOW_MASK)) { for (i = 0; i < max_num_polls; ++i) { commit_state = dc->hwss.get_idle_state(dc); - if (!(commit_state & DMUB_IPS1_COMMIT_MASK)) + if (commit_state & DMUB_IPS1_COMMIT_MASK) break; udelay(1); diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h index cea666ea66c6..fcb825e4f1bb 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_types.h +++ b/drivers/gpu/drm/amd/display/dc/dc_types.h @@ -177,6 +177,7 @@ struct dc_panel_patch { unsigned int disable_fams; unsigned int skip_avmute; unsigned int mst_start_top_delay; + unsigned int remove_sink_ext_caps; }; struct dc_edid_caps { diff --git a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_stream_encoder.c index 001f9eb66920..62a8f0b56006 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_stream_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dio_stream_encoder.c @@ -261,12 +261,6 @@ static void enc35_stream_encoder_enable( /* invalid mode ! */ ASSERT_CRITICAL(false); } - - REG_UPDATE(DIG_FE_CLK_CNTL, DIG_FE_CLK_EN, 1); - REG_UPDATE(DIG_FE_EN_CNTL, DIG_FE_ENABLE, 1); - } else { - REG_UPDATE(DIG_FE_EN_CNTL, DIG_FE_ENABLE, 0); - REG_UPDATE(DIG_FE_CLK_CNTL, DIG_FE_CLK_EN, 0); } } @@ -436,6 +430,8 @@ static void enc35_disable_fifo(struct stream_encoder *enc) struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc); REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_ENABLE, 0); + REG_UPDATE(DIG_FE_EN_CNTL, DIG_FE_ENABLE, 0); + REG_UPDATE(DIG_FE_CLK_CNTL, DIG_FE_CLK_EN, 0); } static void enc35_enable_fifo(struct stream_encoder *enc) @@ -443,6 +439,8 @@ static void enc35_enable_fifo(struct stream_encoder *enc) struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc); REG_UPDATE(DIG_FIFO_CTRL0, DIG_FIFO_READ_START_LEVEL, 0x7); + REG_UPDATE(DIG_FE_CLK_CNTL, DIG_FE_CLK_EN, 1); + REG_UPDATE(DIG_FE_EN_CNTL, DIG_FE_ENABLE, 1); enc35_reset_fifo(enc, true); enc35_reset_fifo(enc, false); diff --git a/drivers/gpu/drm/amd/display/dc/link/link_detection.c b/drivers/gpu/drm/amd/display/dc/link/link_detection.c index d6f0f857c05a..f2fe523f914f 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_detection.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_detection.c @@ -1088,6 +1088,9 @@ static bool detect_link_and_local_sink(struct dc_link *link, if (sink->edid_caps.panel_patch.skip_scdc_overwrite) link->ctx->dc->debug.hdmi20_disable = true; + if (sink->edid_caps.panel_patch.remove_sink_ext_caps) + link->dpcd_sink_ext_caps.raw = 0; + if (dc_is_hdmi_signal(link->connector_signal)) read_scdc_caps(link->ddc, link->local_sink); diff --git a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h index 9665ada0f894..df63aa8f01e9 100644 --- a/drivers/gpu/drm/amd/display/dmub/dmub_srv.h +++ b/drivers/gpu/drm/amd/display/dmub/dmub_srv.h @@ -195,6 +195,7 @@ struct dmub_srv_region_params { uint32_t vbios_size; const uint8_t *fw_inst_const; const uint8_t *fw_bss_data; + bool is_mailbox_in_inbox; }; /** @@ -214,20 +215,25 @@ struct dmub_srv_region_params { */ struct dmub_srv_region_info { uint32_t fb_size; + uint32_t inbox_size; uint8_t num_regions; struct dmub_region regions[DMUB_WINDOW_TOTAL]; }; /** - * struct dmub_srv_fb_params - parameters used for driver fb setup + * struct dmub_srv_memory_params - parameters used for driver fb setup * @region_info: region info calculated by dmub service - * @cpu_addr: base cpu address for the framebuffer - * @gpu_addr: base gpu virtual address for the framebuffer + * @cpu_fb_addr: base cpu address for the framebuffer + * @cpu_inbox_addr: base cpu address for the gart + * @gpu_fb_addr: base gpu virtual address for the framebuffer + * @gpu_inbox_addr: base gpu virtual address for the gart */ -struct dmub_srv_fb_params { +struct dmub_srv_memory_params { const struct dmub_srv_region_info *region_info; - void *cpu_addr; - uint64_t gpu_addr; + void *cpu_fb_addr; + void *cpu_inbox_addr; + uint64_t gpu_fb_addr; + uint64_t gpu_inbox_addr; }; /** @@ -563,8 +569,8 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub, * DMUB_STATUS_OK - success * DMUB_STATUS_INVALID - unspecified error */ -enum dmub_status dmub_srv_calc_fb_info(struct dmub_srv *dmub, - const struct dmub_srv_fb_params *params, +enum dmub_status dmub_srv_calc_mem_info(struct dmub_srv *dmub, + const struct dmub_srv_memory_params *params, struct dmub_srv_fb_info *out); /** diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c index e43e8d4bfe37..22fc4ba96def 100644 --- a/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c +++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_srv.c @@ -434,7 +434,7 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub, uint32_t fw_state_size = DMUB_FW_STATE_SIZE; uint32_t trace_buffer_size = DMUB_TRACE_BUFFER_SIZE; uint32_t scratch_mem_size = DMUB_SCRATCH_MEM_SIZE; - + uint32_t previous_top = 0; if (!dmub->sw_init) return DMUB_STATUS_INVALID; @@ -459,8 +459,15 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub, bios->base = dmub_align(stack->top, 256); bios->top = bios->base + params->vbios_size; - mail->base = dmub_align(bios->top, 256); - mail->top = mail->base + DMUB_MAILBOX_SIZE; + if (params->is_mailbox_in_inbox) { + mail->base = 0; + mail->top = mail->base + DMUB_MAILBOX_SIZE; + previous_top = bios->top; + } else { + mail->base = dmub_align(bios->top, 256); + mail->top = mail->base + DMUB_MAILBOX_SIZE; + previous_top = mail->top; + } fw_info = dmub_get_fw_meta_info(params); @@ -479,7 +486,7 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub, dmub->fw_version = fw_info->fw_version; } - trace_buff->base = dmub_align(mail->top, 256); + trace_buff->base = dmub_align(previous_top, 256); trace_buff->top = trace_buff->base + dmub_align(trace_buffer_size, 64); fw_state->base = dmub_align(trace_buff->top, 256); @@ -490,11 +497,14 @@ dmub_srv_calc_region_info(struct dmub_srv *dmub, out->fb_size = dmub_align(scratch_mem->top, 4096); + if (params->is_mailbox_in_inbox) + out->inbox_size = dmub_align(mail->top, 4096); + return DMUB_STATUS_OK; } -enum dmub_status dmub_srv_calc_fb_info(struct dmub_srv *dmub, - const struct dmub_srv_fb_params *params, +enum dmub_status dmub_srv_calc_mem_info(struct dmub_srv *dmub, + const struct dmub_srv_memory_params *params, struct dmub_srv_fb_info *out) { uint8_t *cpu_base; @@ -509,8 +519,8 @@ enum dmub_status dmub_srv_calc_fb_info(struct dmub_srv *dmub, if (params->region_info->num_regions != DMUB_NUM_WINDOWS) return DMUB_STATUS_INVALID; - cpu_base = (uint8_t *)params->cpu_addr; - gpu_base = params->gpu_addr; + cpu_base = (uint8_t *)params->cpu_fb_addr; + gpu_base = params->gpu_fb_addr; for (i = 0; i < DMUB_NUM_WINDOWS; ++i) { const struct dmub_region *reg = @@ -518,6 +528,12 @@ enum dmub_status dmub_srv_calc_fb_info(struct dmub_srv *dmub, out->fb[i].cpu_addr = cpu_base + reg->base; out->fb[i].gpu_addr = gpu_base + reg->base; + + if (i == DMUB_WINDOW_4_MAILBOX && params->cpu_inbox_addr != 0) { + out->fb[i].cpu_addr = (uint8_t *)params->cpu_inbox_addr + reg->base; + out->fb[i].gpu_addr = params->gpu_inbox_addr + reg->base; + } + out->fb[i].size = reg->top - reg->base; } @@ -707,9 +723,16 @@ enum dmub_status dmub_srv_sync_inbox1(struct dmub_srv *dmub) return DMUB_STATUS_INVALID; if (dmub->hw_funcs.get_inbox1_rptr && dmub->hw_funcs.get_inbox1_wptr) { - dmub->inbox1_rb.rptr = dmub->hw_funcs.get_inbox1_rptr(dmub); - dmub->inbox1_rb.wrpt = dmub->hw_funcs.get_inbox1_wptr(dmub); - dmub->inbox1_last_wptr = dmub->inbox1_rb.wrpt; + uint32_t rptr = dmub->hw_funcs.get_inbox1_rptr(dmub); + uint32_t wptr = dmub->hw_funcs.get_inbox1_wptr(dmub); + + if (rptr > dmub->inbox1_rb.capacity || wptr > dmub->inbox1_rb.capacity) { + return DMUB_STATUS_HW_FAILURE; + } else { + dmub->inbox1_rb.rptr = rptr; + dmub->inbox1_rb.wrpt = wptr; + dmub->inbox1_last_wptr = dmub->inbox1_rb.wrpt; + } } return DMUB_STATUS_OK; @@ -743,6 +766,11 @@ enum dmub_status dmub_srv_cmd_queue(struct dmub_srv *dmub, if (!dmub->hw_init) return DMUB_STATUS_INVALID; + if (dmub->inbox1_rb.rptr > dmub->inbox1_rb.capacity || + dmub->inbox1_rb.wrpt > dmub->inbox1_rb.capacity) { + return DMUB_STATUS_HW_FAILURE; + } + if (dmub_rb_push_front(&dmub->inbox1_rb, cmd)) return DMUB_STATUS_OK; diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h index dab35d878a90..fef2d290f3f2 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/pmfw_if/smu_v13_0_6_pmfw.h @@ -123,7 +123,7 @@ typedef enum { VOLTAGE_GUARDBAND_COUNT } GFX_GUARDBAND_e; -#define SMU_METRICS_TABLE_VERSION 0x8 +#define SMU_METRICS_TABLE_VERSION 0x9 typedef struct __attribute__((packed, aligned(4))) { uint32_t AccumulationCounter; @@ -211,6 +211,14 @@ typedef struct __attribute__((packed, aligned(4))) { //XGMI Data tranfser size uint64_t XgmiReadDataSizeAcc[8];//in KByte uint64_t XgmiWriteDataSizeAcc[8];//in KByte + + //PCIE BW Data and error count + uint32_t PcieBandwidth[4]; + uint32_t PCIeL0ToRecoveryCountAcc; // The Pcie counter itself is accumulated + uint32_t PCIenReplayAAcc; // The Pcie counter itself is accumulated + uint32_t PCIenReplayARolloverCountAcc; // The Pcie counter itself is accumulated + uint32_t PCIeNAKSentCountAcc; // The Pcie counter itself is accumulated + uint32_t PCIeNAKReceivedCountAcc; // The Pcie counter itself is accumulated } MetricsTable_t; #define SMU_VF_METRICS_TABLE_VERSION 0x3 diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c index 891605d4975f..0e5a77c3c2e2 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c @@ -1454,7 +1454,7 @@ static int smu_v13_0_6_register_irq_handler(struct smu_context *smu) static int smu_v13_0_6_notify_unload(struct smu_context *smu) { - if (smu->smc_fw_version <= 0x553500) + if (amdgpu_in_reset(smu->adev)) return 0; dev_dbg(smu->adev->dev, "Notify PMFW about driver unload"); @@ -2095,6 +2095,14 @@ static ssize_t smu_v13_0_6_get_gpu_metrics(struct smu_context *smu, void **table smu_v13_0_6_get_current_pcie_link_speed(smu); gpu_metrics->pcie_bandwidth_acc = SMUQ10_ROUND(metrics->PcieBandwidthAcc[0]); + gpu_metrics->pcie_bandwidth_inst = + SMUQ10_ROUND(metrics->PcieBandwidth[0]); + gpu_metrics->pcie_l0_to_recov_count_acc = + metrics->PCIeL0ToRecoveryCountAcc; + gpu_metrics->pcie_replay_count_acc = + metrics->PCIenReplayAAcc; + gpu_metrics->pcie_replay_rover_count_acc = + metrics->PCIenReplayARolloverCountAcc; } gpu_metrics->system_clock_counter = ktime_get_boottime_ns(); diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index d5c15292ae93..3d92f66e550c 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -336,6 +336,12 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "IdeaPad Duet 3 10IGL5"), }, .driver_data = (void *)&lcd1200x1920_rightside_up, + }, { /* Lenovo Legion Go 8APU1 */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_EXACT_MATCH(DMI_PRODUCT_VERSION, "Legion Go 8APU1"), + }, + .driver_data = (void *)&lcd1600x2560_leftside_up, }, { /* Lenovo Yoga Book X90F / X90L */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Intel Corporation"), diff --git a/drivers/gpu/drm/nouveau/include/nvkm/core/event.h b/drivers/gpu/drm/nouveau/include/nvkm/core/event.h index 82b267c11147..460459af272d 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/core/event.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/core/event.h @@ -14,7 +14,7 @@ struct nvkm_event { int index_nr; spinlock_t refs_lock; - spinlock_t list_lock; + rwlock_t list_lock; int *refs; struct list_head ntfy; @@ -38,7 +38,7 @@ nvkm_event_init(const struct nvkm_event_func *func, struct nvkm_subdev *subdev, int types_nr, int index_nr, struct nvkm_event *event) { spin_lock_init(&event->refs_lock); - spin_lock_init(&event->list_lock); + rwlock_init(&event->list_lock); return __nvkm_event_init(func, subdev, types_nr, index_nr, event); } diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index d8c92521226d..f28f9a857458 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -726,6 +726,11 @@ nouveau_display_create(struct drm_device *dev) if (nouveau_modeset != 2) { ret = nvif_disp_ctor(&drm->client.device, "kmsDisp", 0, &disp->disp); + /* no display hw */ + if (ret == -ENODEV) { + ret = 0; + goto disp_create_err; + } if (!ret && (disp->disp.outp_mask || drm->vbios.dcb.entries)) { nouveau_display_create_properties(dev); diff --git a/drivers/gpu/drm/nouveau/nvkm/core/event.c b/drivers/gpu/drm/nouveau/nvkm/core/event.c index a6c877135598..61fed7792e41 100644 --- a/drivers/gpu/drm/nouveau/nvkm/core/event.c +++ b/drivers/gpu/drm/nouveau/nvkm/core/event.c @@ -81,17 +81,17 @@ nvkm_event_ntfy_state(struct nvkm_event_ntfy *ntfy) static void nvkm_event_ntfy_remove(struct nvkm_event_ntfy *ntfy) { - spin_lock_irq(&ntfy->event->list_lock); + write_lock_irq(&ntfy->event->list_lock); list_del_init(&ntfy->head); - spin_unlock_irq(&ntfy->event->list_lock); + write_unlock_irq(&ntfy->event->list_lock); } static void nvkm_event_ntfy_insert(struct nvkm_event_ntfy *ntfy) { - spin_lock_irq(&ntfy->event->list_lock); + write_lock_irq(&ntfy->event->list_lock); list_add_tail(&ntfy->head, &ntfy->event->ntfy); - spin_unlock_irq(&ntfy->event->list_lock); + write_unlock_irq(&ntfy->event->list_lock); } static void @@ -176,7 +176,7 @@ nvkm_event_ntfy(struct nvkm_event *event, int id, u32 bits) return; nvkm_trace(event->subdev, "event: ntfy %08x on %d\n", bits, id); - spin_lock_irqsave(&event->list_lock, flags); + read_lock_irqsave(&event->list_lock, flags); list_for_each_entry_safe(ntfy, ntmp, &event->ntfy, head) { if (ntfy->id == id && ntfy->bits & bits) { @@ -185,7 +185,7 @@ nvkm_event_ntfy(struct nvkm_event *event, int id, u32 bits) } } - spin_unlock_irqrestore(&event->list_lock, flags); + read_unlock_irqrestore(&event->list_lock, flags); } void diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c index e31f9641114b..dc44f5c7833f 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/r535.c @@ -689,8 +689,8 @@ r535_gsp_rpc_get(struct nvkm_gsp *gsp, u32 fn, u32 argc) struct nvfw_gsp_rpc *rpc; rpc = r535_gsp_cmdq_get(gsp, ALIGN(sizeof(*rpc) + argc, sizeof(u64))); - if (!rpc) - return NULL; + if (IS_ERR(rpc)) + return ERR_CAST(rpc); rpc->header_version = 0x03000000; rpc->signature = ('C' << 24) | ('P' << 16) | ('R' << 8) | 'V'; @@ -1159,7 +1159,7 @@ static void r535_gsp_acpi_mux_id(acpi_handle handle, u32 id, MUX_METHOD_DATA_ELEMENT *mode, MUX_METHOD_DATA_ELEMENT *part) { - acpi_handle iter = NULL, handle_mux; + acpi_handle iter = NULL, handle_mux = NULL; acpi_status status; unsigned long long value; diff --git a/drivers/i2c/busses/i2c-designware-common.c b/drivers/i2c/busses/i2c-designware-common.c index affcfb243f0f..35f762872b8a 100644 --- a/drivers/i2c/busses/i2c-designware-common.c +++ b/drivers/i2c/busses/i2c-designware-common.c @@ -63,7 +63,7 @@ static int dw_reg_read(void *context, unsigned int reg, unsigned int *val) { struct dw_i2c_dev *dev = context; - *val = readl_relaxed(dev->base + reg); + *val = readl(dev->base + reg); return 0; } @@ -72,7 +72,7 @@ static int dw_reg_write(void *context, unsigned int reg, unsigned int val) { struct dw_i2c_dev *dev = context; - writel_relaxed(val, dev->base + reg); + writel(val, dev->base + reg); return 0; } @@ -81,7 +81,7 @@ static int dw_reg_read_swab(void *context, unsigned int reg, unsigned int *val) { struct dw_i2c_dev *dev = context; - *val = swab32(readl_relaxed(dev->base + reg)); + *val = swab32(readl(dev->base + reg)); return 0; } @@ -90,7 +90,7 @@ static int dw_reg_write_swab(void *context, unsigned int reg, unsigned int val) { struct dw_i2c_dev *dev = context; - writel_relaxed(swab32(val), dev->base + reg); + writel(swab32(val), dev->base + reg); return 0; } @@ -99,8 +99,8 @@ static int dw_reg_read_word(void *context, unsigned int reg, unsigned int *val) { struct dw_i2c_dev *dev = context; - *val = readw_relaxed(dev->base + reg) | - (readw_relaxed(dev->base + reg + 2) << 16); + *val = readw(dev->base + reg) | + (readw(dev->base + reg + 2) << 16); return 0; } @@ -109,8 +109,8 @@ static int dw_reg_write_word(void *context, unsigned int reg, unsigned int val) { struct dw_i2c_dev *dev = context; - writew_relaxed(val, dev->base + reg); - writew_relaxed(val >> 16, dev->base + reg + 2); + writew(val, dev->base + reg); + writew(val >> 16, dev->base + reg + 2); return 0; } diff --git a/drivers/i2c/busses/i2c-ocores.c b/drivers/i2c/busses/i2c-ocores.c index 041a76f71a49..e106af83cef4 100644 --- a/drivers/i2c/busses/i2c-ocores.c +++ b/drivers/i2c/busses/i2c-ocores.c @@ -771,8 +771,8 @@ static int ocores_i2c_resume(struct device *dev) return ocores_init(dev, i2c); } -static DEFINE_SIMPLE_DEV_PM_OPS(ocores_i2c_pm, - ocores_i2c_suspend, ocores_i2c_resume); +static DEFINE_NOIRQ_DEV_PM_OPS(ocores_i2c_pm, + ocores_i2c_suspend, ocores_i2c_resume); static struct platform_driver ocores_i2c_driver = { .probe = ocores_i2c_probe, diff --git a/drivers/i2c/busses/i2c-pxa.c b/drivers/i2c/busses/i2c-pxa.c index 1d7648242749..76f79b68cef8 100644 --- a/drivers/i2c/busses/i2c-pxa.c +++ b/drivers/i2c/busses/i2c-pxa.c @@ -265,6 +265,9 @@ struct pxa_i2c { u32 hs_mask; struct i2c_bus_recovery_info recovery; + struct pinctrl *pinctrl; + struct pinctrl_state *pinctrl_default; + struct pinctrl_state *pinctrl_recovery; }; #define _IBMR(i2c) ((i2c)->reg_ibmr) @@ -1299,12 +1302,13 @@ static void i2c_pxa_prepare_recovery(struct i2c_adapter *adap) */ gpiod_set_value(i2c->recovery.scl_gpiod, ibmr & IBMR_SCLS); gpiod_set_value(i2c->recovery.sda_gpiod, ibmr & IBMR_SDAS); + + WARN_ON(pinctrl_select_state(i2c->pinctrl, i2c->pinctrl_recovery)); } static void i2c_pxa_unprepare_recovery(struct i2c_adapter *adap) { struct pxa_i2c *i2c = adap->algo_data; - struct i2c_bus_recovery_info *bri = adap->bus_recovery_info; u32 isr; /* @@ -1318,7 +1322,7 @@ static void i2c_pxa_unprepare_recovery(struct i2c_adapter *adap) i2c_pxa_do_reset(i2c); } - WARN_ON(pinctrl_select_state(bri->pinctrl, bri->pins_default)); + WARN_ON(pinctrl_select_state(i2c->pinctrl, i2c->pinctrl_default)); dev_dbg(&i2c->adap.dev, "recovery: IBMR 0x%08x ISR 0x%08x\n", readl(_IBMR(i2c)), readl(_ISR(i2c))); @@ -1340,20 +1344,76 @@ static int i2c_pxa_init_recovery(struct pxa_i2c *i2c) if (IS_ENABLED(CONFIG_I2C_PXA_SLAVE)) return 0; - bri->pinctrl = devm_pinctrl_get(dev); - if (PTR_ERR(bri->pinctrl) == -ENODEV) { - bri->pinctrl = NULL; + i2c->pinctrl = devm_pinctrl_get(dev); + if (PTR_ERR(i2c->pinctrl) == -ENODEV) + i2c->pinctrl = NULL; + if (IS_ERR(i2c->pinctrl)) + return PTR_ERR(i2c->pinctrl); + + if (!i2c->pinctrl) + return 0; + + i2c->pinctrl_default = pinctrl_lookup_state(i2c->pinctrl, + PINCTRL_STATE_DEFAULT); + i2c->pinctrl_recovery = pinctrl_lookup_state(i2c->pinctrl, "recovery"); + + if (IS_ERR(i2c->pinctrl_default) || IS_ERR(i2c->pinctrl_recovery)) { + dev_info(dev, "missing pinmux recovery information: %ld %ld\n", + PTR_ERR(i2c->pinctrl_default), + PTR_ERR(i2c->pinctrl_recovery)); + return 0; + } + + /* + * Claiming GPIOs can influence the pinmux state, and may glitch the + * I2C bus. Do this carefully. + */ + bri->scl_gpiod = devm_gpiod_get(dev, "scl", GPIOD_OUT_HIGH_OPEN_DRAIN); + if (bri->scl_gpiod == ERR_PTR(-EPROBE_DEFER)) + return -EPROBE_DEFER; + if (IS_ERR(bri->scl_gpiod)) { + dev_info(dev, "missing scl gpio recovery information: %pe\n", + bri->scl_gpiod); + return 0; + } + + /* + * We have SCL. Pull SCL low and wait a bit so that SDA glitches + * have no effect. + */ + gpiod_direction_output(bri->scl_gpiod, 0); + udelay(10); + bri->sda_gpiod = devm_gpiod_get(dev, "sda", GPIOD_OUT_HIGH_OPEN_DRAIN); + + /* Wait a bit in case of a SDA glitch, and then release SCL. */ + udelay(10); + gpiod_direction_output(bri->scl_gpiod, 1); + + if (bri->sda_gpiod == ERR_PTR(-EPROBE_DEFER)) + return -EPROBE_DEFER; + + if (IS_ERR(bri->sda_gpiod)) { + dev_info(dev, "missing sda gpio recovery information: %pe\n", + bri->sda_gpiod); return 0; } - if (IS_ERR(bri->pinctrl)) - return PTR_ERR(bri->pinctrl); bri->prepare_recovery = i2c_pxa_prepare_recovery; bri->unprepare_recovery = i2c_pxa_unprepare_recovery; + bri->recover_bus = i2c_generic_scl_recovery; i2c->adap.bus_recovery_info = bri; - return 0; + /* + * Claiming GPIOs can change the pinmux state, which confuses the + * pinctrl since pinctrl's idea of the current setting is unaffected + * by the pinmux change caused by claiming the GPIO. Work around that + * by switching pinctrl to the GPIO state here. We do it this way to + * avoid glitching the I2C bus. + */ + pinctrl_select_state(i2c->pinctrl, i2c->pinctrl_recovery); + + return pinctrl_select_state(i2c->pinctrl, i2c->pinctrl_default); } static int i2c_pxa_probe(struct platform_device *dev) diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index a8c89df1a997..9a7a74239eab 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -2379,12 +2379,12 @@ retry_baser: break; } + if (!shr) + gic_flush_dcache_to_poc(base, PAGE_ORDER_TO_SIZE(order)); + its_write_baser(its, baser, val); tmp = baser->val; - if (its->flags & ITS_FLAGS_FORCE_NON_SHAREABLE) - tmp &= ~GITS_BASER_SHAREABILITY_MASK; - if ((val ^ tmp) & GITS_BASER_SHAREABILITY_MASK) { /* * Shareability didn't stick. Just use @@ -2394,10 +2394,9 @@ retry_baser: * non-cacheable as well. */ shr = tmp & GITS_BASER_SHAREABILITY_MASK; - if (!shr) { + if (!shr) cache = GITS_BASER_nC; - gic_flush_dcache_to_poc(base, PAGE_ORDER_TO_SIZE(order)); - } + goto retry_baser; } @@ -2609,6 +2608,11 @@ static int its_alloc_tables(struct its_node *its) /* erratum 24313: ignore memory access type */ cache = GITS_BASER_nCnB; + if (its->flags & ITS_FLAGS_FORCE_NON_SHAREABLE) { + cache = GITS_BASER_nC; + shr = 0; + } + for (i = 0; i < GITS_BASER_NR_REGS; i++) { struct its_baser *baser = its->tables + i; u64 val = its_read_baser(its, baser); diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 62eb27639c9b..f03d7dba270c 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -254,7 +254,7 @@ enum evict_result { typedef enum evict_result (*le_predicate)(struct lru_entry *le, void *context); -static struct lru_entry *lru_evict(struct lru *lru, le_predicate pred, void *context) +static struct lru_entry *lru_evict(struct lru *lru, le_predicate pred, void *context, bool no_sleep) { unsigned long tested = 0; struct list_head *h = lru->cursor; @@ -295,7 +295,8 @@ static struct lru_entry *lru_evict(struct lru *lru, le_predicate pred, void *con h = h->next; - cond_resched(); + if (!no_sleep) + cond_resched(); } return NULL; @@ -382,7 +383,10 @@ struct dm_buffer { */ struct buffer_tree { - struct rw_semaphore lock; + union { + struct rw_semaphore lock; + rwlock_t spinlock; + } u; struct rb_root root; } ____cacheline_aligned_in_smp; @@ -393,9 +397,12 @@ struct dm_buffer_cache { * on the locks. */ unsigned int num_locks; + bool no_sleep; struct buffer_tree trees[]; }; +static DEFINE_STATIC_KEY_FALSE(no_sleep_enabled); + static inline unsigned int cache_index(sector_t block, unsigned int num_locks) { return dm_hash_locks_index(block, num_locks); @@ -403,22 +410,34 @@ static inline unsigned int cache_index(sector_t block, unsigned int num_locks) static inline void cache_read_lock(struct dm_buffer_cache *bc, sector_t block) { - down_read(&bc->trees[cache_index(block, bc->num_locks)].lock); + if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep) + read_lock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock); + else + down_read(&bc->trees[cache_index(block, bc->num_locks)].u.lock); } static inline void cache_read_unlock(struct dm_buffer_cache *bc, sector_t block) { - up_read(&bc->trees[cache_index(block, bc->num_locks)].lock); + if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep) + read_unlock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock); + else + up_read(&bc->trees[cache_index(block, bc->num_locks)].u.lock); } static inline void cache_write_lock(struct dm_buffer_cache *bc, sector_t block) { - down_write(&bc->trees[cache_index(block, bc->num_locks)].lock); + if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep) + write_lock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock); + else + down_write(&bc->trees[cache_index(block, bc->num_locks)].u.lock); } static inline void cache_write_unlock(struct dm_buffer_cache *bc, sector_t block) { - up_write(&bc->trees[cache_index(block, bc->num_locks)].lock); + if (static_branch_unlikely(&no_sleep_enabled) && bc->no_sleep) + write_unlock_bh(&bc->trees[cache_index(block, bc->num_locks)].u.spinlock); + else + up_write(&bc->trees[cache_index(block, bc->num_locks)].u.lock); } /* @@ -442,18 +461,32 @@ static void lh_init(struct lock_history *lh, struct dm_buffer_cache *cache, bool static void __lh_lock(struct lock_history *lh, unsigned int index) { - if (lh->write) - down_write(&lh->cache->trees[index].lock); - else - down_read(&lh->cache->trees[index].lock); + if (lh->write) { + if (static_branch_unlikely(&no_sleep_enabled) && lh->cache->no_sleep) + write_lock_bh(&lh->cache->trees[index].u.spinlock); + else + down_write(&lh->cache->trees[index].u.lock); + } else { + if (static_branch_unlikely(&no_sleep_enabled) && lh->cache->no_sleep) + read_lock_bh(&lh->cache->trees[index].u.spinlock); + else + down_read(&lh->cache->trees[index].u.lock); + } } static void __lh_unlock(struct lock_history *lh, unsigned int index) { - if (lh->write) - up_write(&lh->cache->trees[index].lock); - else - up_read(&lh->cache->trees[index].lock); + if (lh->write) { + if (static_branch_unlikely(&no_sleep_enabled) && lh->cache->no_sleep) + write_unlock_bh(&lh->cache->trees[index].u.spinlock); + else + up_write(&lh->cache->trees[index].u.lock); + } else { + if (static_branch_unlikely(&no_sleep_enabled) && lh->cache->no_sleep) + read_unlock_bh(&lh->cache->trees[index].u.spinlock); + else + up_read(&lh->cache->trees[index].u.lock); + } } /* @@ -502,14 +535,18 @@ static struct dm_buffer *list_to_buffer(struct list_head *l) return le_to_buffer(le); } -static void cache_init(struct dm_buffer_cache *bc, unsigned int num_locks) +static void cache_init(struct dm_buffer_cache *bc, unsigned int num_locks, bool no_sleep) { unsigned int i; bc->num_locks = num_locks; + bc->no_sleep = no_sleep; for (i = 0; i < bc->num_locks; i++) { - init_rwsem(&bc->trees[i].lock); + if (no_sleep) + rwlock_init(&bc->trees[i].u.spinlock); + else + init_rwsem(&bc->trees[i].u.lock); bc->trees[i].root = RB_ROOT; } @@ -648,7 +685,7 @@ static struct dm_buffer *__cache_evict(struct dm_buffer_cache *bc, int list_mode struct lru_entry *le; struct dm_buffer *b; - le = lru_evict(&bc->lru[list_mode], __evict_pred, &w); + le = lru_evict(&bc->lru[list_mode], __evict_pred, &w, bc->no_sleep); if (!le) return NULL; @@ -702,7 +739,7 @@ static void __cache_mark_many(struct dm_buffer_cache *bc, int old_mode, int new_ struct evict_wrapper w = {.lh = lh, .pred = pred, .context = context}; while (true) { - le = lru_evict(&bc->lru[old_mode], __evict_pred, &w); + le = lru_evict(&bc->lru[old_mode], __evict_pred, &w, bc->no_sleep); if (!le) break; @@ -915,10 +952,11 @@ static void cache_remove_range(struct dm_buffer_cache *bc, { unsigned int i; + BUG_ON(bc->no_sleep); for (i = 0; i < bc->num_locks; i++) { - down_write(&bc->trees[i].lock); + down_write(&bc->trees[i].u.lock); __remove_range(bc, &bc->trees[i].root, begin, end, pred, release); - up_write(&bc->trees[i].lock); + up_write(&bc->trees[i].u.lock); } } @@ -979,8 +1017,6 @@ struct dm_bufio_client { struct dm_buffer_cache cache; /* must be last member */ }; -static DEFINE_STATIC_KEY_FALSE(no_sleep_enabled); - /*----------------------------------------------------------------*/ #define dm_bufio_in_request() (!!current->bio_list) @@ -1871,7 +1907,8 @@ static void *new_read(struct dm_bufio_client *c, sector_t block, if (need_submit) submit_io(b, REQ_OP_READ, read_endio); - wait_on_bit_io(&b->state, B_READING, TASK_UNINTERRUPTIBLE); + if (nf != NF_GET) /* we already tested this condition above */ + wait_on_bit_io(&b->state, B_READING, TASK_UNINTERRUPTIBLE); if (b->read_error) { int error = blk_status_to_errno(b->read_error); @@ -2421,7 +2458,7 @@ struct dm_bufio_client *dm_bufio_client_create(struct block_device *bdev, unsign r = -ENOMEM; goto bad_client; } - cache_init(&c->cache, num_locks); + cache_init(&c->cache, num_locks, (flags & DM_BUFIO_CLIENT_NO_SLEEP) != 0); c->bdev = bdev; c->block_size = block_size; diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 6de107aff331..2ae8560b6a14 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1673,7 +1673,7 @@ static struct bio *crypt_alloc_buffer(struct dm_crypt_io *io, unsigned int size) unsigned int nr_iovecs = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; gfp_t gfp_mask = GFP_NOWAIT | __GFP_HIGHMEM; unsigned int remaining_size; - unsigned int order = MAX_ORDER - 1; + unsigned int order = MAX_ORDER; retry: if (unlikely(gfp_mask & __GFP_DIRECT_RECLAIM)) diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c index efd510984e25..5eabdb06c649 100644 --- a/drivers/md/dm-delay.c +++ b/drivers/md/dm-delay.c @@ -33,7 +33,7 @@ struct delay_c { struct work_struct flush_expired_bios; struct list_head delayed_bios; struct task_struct *worker; - atomic_t may_delay; + bool may_delay; struct delay_class read; struct delay_class write; @@ -73,39 +73,6 @@ static inline bool delay_is_fast(struct delay_c *dc) return !!dc->worker; } -static void flush_delayed_bios_fast(struct delay_c *dc, bool flush_all) -{ - struct dm_delay_info *delayed, *next; - - mutex_lock(&delayed_bios_lock); - list_for_each_entry_safe(delayed, next, &dc->delayed_bios, list) { - if (flush_all || time_after_eq(jiffies, delayed->expires)) { - struct bio *bio = dm_bio_from_per_bio_data(delayed, - sizeof(struct dm_delay_info)); - list_del(&delayed->list); - dm_submit_bio_remap(bio, NULL); - delayed->class->ops--; - } - } - mutex_unlock(&delayed_bios_lock); -} - -static int flush_worker_fn(void *data) -{ - struct delay_c *dc = data; - - while (1) { - flush_delayed_bios_fast(dc, false); - if (unlikely(list_empty(&dc->delayed_bios))) { - set_current_state(TASK_INTERRUPTIBLE); - schedule(); - } else - cond_resched(); - } - - return 0; -} - static void flush_bios(struct bio *bio) { struct bio *n; @@ -118,36 +85,61 @@ static void flush_bios(struct bio *bio) } } -static struct bio *flush_delayed_bios(struct delay_c *dc, bool flush_all) +static void flush_delayed_bios(struct delay_c *dc, bool flush_all) { struct dm_delay_info *delayed, *next; + struct bio_list flush_bio_list; unsigned long next_expires = 0; - unsigned long start_timer = 0; - struct bio_list flush_bios = { }; + bool start_timer = false; + bio_list_init(&flush_bio_list); mutex_lock(&delayed_bios_lock); list_for_each_entry_safe(delayed, next, &dc->delayed_bios, list) { + cond_resched(); if (flush_all || time_after_eq(jiffies, delayed->expires)) { struct bio *bio = dm_bio_from_per_bio_data(delayed, sizeof(struct dm_delay_info)); list_del(&delayed->list); - bio_list_add(&flush_bios, bio); + bio_list_add(&flush_bio_list, bio); delayed->class->ops--; continue; } - if (!start_timer) { - start_timer = 1; - next_expires = delayed->expires; - } else - next_expires = min(next_expires, delayed->expires); + if (!delay_is_fast(dc)) { + if (!start_timer) { + start_timer = true; + next_expires = delayed->expires; + } else { + next_expires = min(next_expires, delayed->expires); + } + } } mutex_unlock(&delayed_bios_lock); if (start_timer) queue_timeout(dc, next_expires); - return bio_list_get(&flush_bios); + flush_bios(bio_list_get(&flush_bio_list)); +} + +static int flush_worker_fn(void *data) +{ + struct delay_c *dc = data; + + while (!kthread_should_stop()) { + flush_delayed_bios(dc, false); + mutex_lock(&delayed_bios_lock); + if (unlikely(list_empty(&dc->delayed_bios))) { + set_current_state(TASK_INTERRUPTIBLE); + mutex_unlock(&delayed_bios_lock); + schedule(); + } else { + mutex_unlock(&delayed_bios_lock); + cond_resched(); + } + } + + return 0; } static void flush_expired_bios(struct work_struct *work) @@ -155,10 +147,7 @@ static void flush_expired_bios(struct work_struct *work) struct delay_c *dc; dc = container_of(work, struct delay_c, flush_expired_bios); - if (delay_is_fast(dc)) - flush_delayed_bios_fast(dc, false); - else - flush_bios(flush_delayed_bios(dc, false)); + flush_delayed_bios(dc, false); } static void delay_dtr(struct dm_target *ti) @@ -177,8 +166,7 @@ static void delay_dtr(struct dm_target *ti) if (dc->worker) kthread_stop(dc->worker); - if (!delay_is_fast(dc)) - mutex_destroy(&dc->timer_lock); + mutex_destroy(&dc->timer_lock); kfree(dc); } @@ -236,7 +224,8 @@ static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv) ti->private = dc; INIT_LIST_HEAD(&dc->delayed_bios); - atomic_set(&dc->may_delay, 1); + mutex_init(&dc->timer_lock); + dc->may_delay = true; dc->argc = argc; ret = delay_class_ctr(ti, &dc->read, argv); @@ -282,12 +271,12 @@ out: "dm-delay-flush-worker"); if (IS_ERR(dc->worker)) { ret = PTR_ERR(dc->worker); + dc->worker = NULL; goto bad; } } else { timer_setup(&dc->delay_timer, handle_delayed_timer, 0); INIT_WORK(&dc->flush_expired_bios, flush_expired_bios); - mutex_init(&dc->timer_lock); dc->kdelayd_wq = alloc_workqueue("kdelayd", WQ_MEM_RECLAIM, 0); if (!dc->kdelayd_wq) { ret = -EINVAL; @@ -312,7 +301,7 @@ static int delay_bio(struct delay_c *dc, struct delay_class *c, struct bio *bio) struct dm_delay_info *delayed; unsigned long expires = 0; - if (!c->delay || !atomic_read(&dc->may_delay)) + if (!c->delay) return DM_MAPIO_REMAPPED; delayed = dm_per_bio_data(bio, sizeof(struct dm_delay_info)); @@ -321,6 +310,10 @@ static int delay_bio(struct delay_c *dc, struct delay_class *c, struct bio *bio) delayed->expires = expires = jiffies + msecs_to_jiffies(c->delay); mutex_lock(&delayed_bios_lock); + if (unlikely(!dc->may_delay)) { + mutex_unlock(&delayed_bios_lock); + return DM_MAPIO_REMAPPED; + } c->ops++; list_add_tail(&delayed->list, &dc->delayed_bios); mutex_unlock(&delayed_bios_lock); @@ -337,21 +330,20 @@ static void delay_presuspend(struct dm_target *ti) { struct delay_c *dc = ti->private; - atomic_set(&dc->may_delay, 0); + mutex_lock(&delayed_bios_lock); + dc->may_delay = false; + mutex_unlock(&delayed_bios_lock); - if (delay_is_fast(dc)) - flush_delayed_bios_fast(dc, true); - else { + if (!delay_is_fast(dc)) del_timer_sync(&dc->delay_timer); - flush_bios(flush_delayed_bios(dc, true)); - } + flush_delayed_bios(dc, true); } static void delay_resume(struct dm_target *ti) { struct delay_c *dc = ti->private; - atomic_set(&dc->may_delay, 1); + dc->may_delay = true; } static int delay_map(struct dm_target *ti, struct bio *bio) diff --git a/drivers/md/dm-verity-fec.c b/drivers/md/dm-verity-fec.c index 3ef9f018da60..2099c755119e 100644 --- a/drivers/md/dm-verity-fec.c +++ b/drivers/md/dm-verity-fec.c @@ -185,7 +185,7 @@ static int fec_is_erasure(struct dm_verity *v, struct dm_verity_io *io, { if (unlikely(verity_hash(v, verity_io_hash_req(v, io), data, 1 << v->data_dev_block_bits, - verity_io_real_digest(v, io)))) + verity_io_real_digest(v, io), true))) return 0; return memcmp(verity_io_real_digest(v, io), want_digest, @@ -386,7 +386,7 @@ static int fec_decode_rsb(struct dm_verity *v, struct dm_verity_io *io, /* Always re-validate the corrected block against the expected hash */ r = verity_hash(v, verity_io_hash_req(v, io), fio->output, 1 << v->data_dev_block_bits, - verity_io_real_digest(v, io)); + verity_io_real_digest(v, io), true); if (unlikely(r < 0)) return r; diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index 26adcfea0302..e115fcfe723c 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -135,20 +135,21 @@ static int verity_hash_update(struct dm_verity *v, struct ahash_request *req, * Wrapper for crypto_ahash_init, which handles verity salting. */ static int verity_hash_init(struct dm_verity *v, struct ahash_request *req, - struct crypto_wait *wait) + struct crypto_wait *wait, bool may_sleep) { int r; ahash_request_set_tfm(req, v->tfm); - ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP | - CRYPTO_TFM_REQ_MAY_BACKLOG, - crypto_req_done, (void *)wait); + ahash_request_set_callback(req, + may_sleep ? CRYPTO_TFM_REQ_MAY_SLEEP | CRYPTO_TFM_REQ_MAY_BACKLOG : 0, + crypto_req_done, (void *)wait); crypto_init_wait(wait); r = crypto_wait_req(crypto_ahash_init(req), wait); if (unlikely(r < 0)) { - DMERR("crypto_ahash_init failed: %d", r); + if (r != -ENOMEM) + DMERR("crypto_ahash_init failed: %d", r); return r; } @@ -179,12 +180,12 @@ out: } int verity_hash(struct dm_verity *v, struct ahash_request *req, - const u8 *data, size_t len, u8 *digest) + const u8 *data, size_t len, u8 *digest, bool may_sleep) { int r; struct crypto_wait wait; - r = verity_hash_init(v, req, &wait); + r = verity_hash_init(v, req, &wait, may_sleep); if (unlikely(r < 0)) goto out; @@ -322,7 +323,7 @@ static int verity_verify_level(struct dm_verity *v, struct dm_verity_io *io, r = verity_hash(v, verity_io_hash_req(v, io), data, 1 << v->hash_dev_block_bits, - verity_io_real_digest(v, io)); + verity_io_real_digest(v, io), !io->in_tasklet); if (unlikely(r < 0)) goto release_ret_r; @@ -556,7 +557,7 @@ static int verity_verify_io(struct dm_verity_io *io) continue; } - r = verity_hash_init(v, req, &wait); + r = verity_hash_init(v, req, &wait, !io->in_tasklet); if (unlikely(r < 0)) return r; @@ -652,7 +653,7 @@ static void verity_tasklet(unsigned long data) io->in_tasklet = true; err = verity_verify_io(io); - if (err == -EAGAIN) { + if (err == -EAGAIN || err == -ENOMEM) { /* fallback to retrying with work-queue */ INIT_WORK(&io->work, verity_work); queue_work(io->v->verify_wq, &io->work); @@ -1033,7 +1034,7 @@ static int verity_alloc_zero_digest(struct dm_verity *v) goto out; r = verity_hash(v, req, zero_data, 1 << v->data_dev_block_bits, - v->zero_digest); + v->zero_digest, true); out: kfree(req); diff --git a/drivers/md/dm-verity.h b/drivers/md/dm-verity.h index 2f555b420367..f96f4e281ee4 100644 --- a/drivers/md/dm-verity.h +++ b/drivers/md/dm-verity.h @@ -128,7 +128,7 @@ extern int verity_for_bv_block(struct dm_verity *v, struct dm_verity_io *io, u8 *data, size_t len)); extern int verity_hash(struct dm_verity *v, struct ahash_request *req, - const u8 *data, size_t len, u8 *digest); + const u8 *data, size_t len, u8 *digest, bool may_sleep); extern int verity_hash_for_block(struct dm_verity *v, struct dm_verity_io *io, sector_t block, u8 *digest, bool *is_zero); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 614c0278419b..6b73648b3779 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -682,10 +682,24 @@ static void xgbe_service(struct work_struct *work) static void xgbe_service_timer(struct timer_list *t) { struct xgbe_prv_data *pdata = from_timer(pdata, t, service_timer); + struct xgbe_channel *channel; + unsigned int i; queue_work(pdata->dev_workqueue, &pdata->service_work); mod_timer(&pdata->service_timer, jiffies + HZ); + + if (!pdata->tx_usecs) + return; + + for (i = 0; i < pdata->channel_count; i++) { + channel = pdata->channel[i]; + if (!channel->tx_ring || channel->tx_timer_active) + break; + channel->tx_timer_active = 1; + mod_timer(&channel->tx_timer, + jiffies + usecs_to_jiffies(pdata->tx_usecs)); + } } static void xgbe_init_timers(struct xgbe_prv_data *pdata) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c index 6e83ff59172a..32fab5e77246 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c @@ -314,10 +314,15 @@ static int xgbe_get_link_ksettings(struct net_device *netdev, cmd->base.phy_address = pdata->phy.address; - cmd->base.autoneg = pdata->phy.autoneg; - cmd->base.speed = pdata->phy.speed; - cmd->base.duplex = pdata->phy.duplex; + if (netif_carrier_ok(netdev)) { + cmd->base.speed = pdata->phy.speed; + cmd->base.duplex = pdata->phy.duplex; + } else { + cmd->base.speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; + } + cmd->base.autoneg = pdata->phy.autoneg; cmd->base.port = PORT_NONE; XGBE_LM_COPY(cmd, supported, lks, supported); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c index 32d2c6fac652..4a2dc705b528 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-mdio.c @@ -1193,7 +1193,19 @@ static int xgbe_phy_config_fixed(struct xgbe_prv_data *pdata) if (pdata->phy.duplex != DUPLEX_FULL) return -EINVAL; - xgbe_set_mode(pdata, mode); + /* Force the mode change for SFI in Fixed PHY config. + * Fixed PHY configs needs PLL to be enabled while doing mode set. + * When the SFP module isn't connected during boot, driver assumes + * AN is ON and attempts autonegotiation. However, if the connected + * SFP comes up in Fixed PHY config, the link will not come up as + * PLL isn't enabled while the initial mode set command is issued. + * So, force the mode change for SFI in Fixed PHY configuration to + * fix link issues. + */ + if (mode == XGBE_MODE_SFI) + xgbe_change_mode(pdata, mode); + else + xgbe_set_mode(pdata, mode); return 0; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index af47ba51e28a..37cca484abb8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -3844,7 +3844,7 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg) struct i40e_pf *pf = vf->pf; struct i40e_vsi *vsi = NULL; int aq_ret = 0; - int i, ret; + int i; if (!i40e_sync_vf_state(vf, I40E_VF_STATE_ACTIVE)) { aq_ret = -EINVAL; @@ -3868,8 +3868,10 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg) } cfilter = kzalloc(sizeof(*cfilter), GFP_KERNEL); - if (!cfilter) - return -ENOMEM; + if (!cfilter) { + aq_ret = -ENOMEM; + goto err_out; + } /* parse destination mac address */ for (i = 0; i < ETH_ALEN; i++) @@ -3917,13 +3919,13 @@ static int i40e_vc_add_cloud_filter(struct i40e_vf *vf, u8 *msg) /* Adding cloud filter programmed as TC filter */ if (tcf.dst_port) - ret = i40e_add_del_cloud_filter_big_buf(vsi, cfilter, true); + aq_ret = i40e_add_del_cloud_filter_big_buf(vsi, cfilter, true); else - ret = i40e_add_del_cloud_filter(vsi, cfilter, true); - if (ret) { + aq_ret = i40e_add_del_cloud_filter(vsi, cfilter, true); + if (aq_ret) { dev_err(&pf->pdev->dev, "VF %d: Failed to add cloud filter, err %pe aq_err %s\n", - vf->vf_id, ERR_PTR(ret), + vf->vf_id, ERR_PTR(aq_ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); goto err_free; } diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 10822011de22..43ba3e55b8c1 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -7403,15 +7403,6 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) goto err_vsi_rebuild; } - /* configure PTP timestamping after VSI rebuild */ - if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags)) { - if (pf->ptp.tx_interrupt_mode == ICE_PTP_TX_INTERRUPT_SELF) - ice_ptp_cfg_timestamp(pf, false); - else if (pf->ptp.tx_interrupt_mode == ICE_PTP_TX_INTERRUPT_ALL) - /* for E82x PHC owner always need to have interrupts */ - ice_ptp_cfg_timestamp(pf, true); - } - err = ice_eswitch_rebuild(pf); if (err) { dev_err(dev, "Switchdev rebuild failed: %d\n", err); @@ -7463,6 +7454,9 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) ice_plug_aux_dev(pf); if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG)) ice_lag_rebuild(pf); + + /* Restore timestamp mode settings after VSI rebuild */ + ice_ptp_restore_timestamp_mode(pf); return; err_vsi_rebuild: diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index 1eddcbe89b0c..71f405f8a6fe 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -256,48 +256,42 @@ ice_verify_pin_e810t(struct ptp_clock_info *info, unsigned int pin, } /** - * ice_ptp_configure_tx_tstamp - Enable or disable Tx timestamp interrupt - * @pf: The PF pointer to search in - * @on: bool value for whether timestamp interrupt is enabled or disabled + * ice_ptp_cfg_tx_interrupt - Configure Tx timestamp interrupt for the device + * @pf: Board private structure + * + * Program the device to respond appropriately to the Tx timestamp interrupt + * cause. */ -static void ice_ptp_configure_tx_tstamp(struct ice_pf *pf, bool on) +static void ice_ptp_cfg_tx_interrupt(struct ice_pf *pf) { + struct ice_hw *hw = &pf->hw; + bool enable; u32 val; + switch (pf->ptp.tx_interrupt_mode) { + case ICE_PTP_TX_INTERRUPT_ALL: + /* React to interrupts across all quads. */ + wr32(hw, PFINT_TSYN_MSK + (0x4 * hw->pf_id), (u32)0x1f); + enable = true; + break; + case ICE_PTP_TX_INTERRUPT_NONE: + /* Do not react to interrupts on any quad. */ + wr32(hw, PFINT_TSYN_MSK + (0x4 * hw->pf_id), (u32)0x0); + enable = false; + break; + case ICE_PTP_TX_INTERRUPT_SELF: + default: + enable = pf->ptp.tstamp_config.tx_type == HWTSTAMP_TX_ON; + break; + } + /* Configure the Tx timestamp interrupt */ - val = rd32(&pf->hw, PFINT_OICR_ENA); - if (on) + val = rd32(hw, PFINT_OICR_ENA); + if (enable) val |= PFINT_OICR_TSYN_TX_M; else val &= ~PFINT_OICR_TSYN_TX_M; - wr32(&pf->hw, PFINT_OICR_ENA, val); -} - -/** - * ice_set_tx_tstamp - Enable or disable Tx timestamping - * @pf: The PF pointer to search in - * @on: bool value for whether timestamps are enabled or disabled - */ -static void ice_set_tx_tstamp(struct ice_pf *pf, bool on) -{ - struct ice_vsi *vsi; - u16 i; - - vsi = ice_get_main_vsi(pf); - if (!vsi) - return; - - /* Set the timestamp enable flag for all the Tx rings */ - ice_for_each_txq(vsi, i) { - if (!vsi->tx_rings[i]) - continue; - vsi->tx_rings[i]->ptp_tx = on; - } - - if (pf->ptp.tx_interrupt_mode == ICE_PTP_TX_INTERRUPT_SELF) - ice_ptp_configure_tx_tstamp(pf, on); - - pf->ptp.tstamp_config.tx_type = on ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; + wr32(hw, PFINT_OICR_ENA, val); } /** @@ -311,7 +305,7 @@ static void ice_set_rx_tstamp(struct ice_pf *pf, bool on) u16 i; vsi = ice_get_main_vsi(pf); - if (!vsi) + if (!vsi || !vsi->rx_rings) return; /* Set the timestamp flag for all the Rx rings */ @@ -320,23 +314,50 @@ static void ice_set_rx_tstamp(struct ice_pf *pf, bool on) continue; vsi->rx_rings[i]->ptp_rx = on; } +} + +/** + * ice_ptp_disable_timestamp_mode - Disable current timestamp mode + * @pf: Board private structure + * + * Called during preparation for reset to temporarily disable timestamping on + * the device. Called during remove to disable timestamping while cleaning up + * driver resources. + */ +static void ice_ptp_disable_timestamp_mode(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + u32 val; + + val = rd32(hw, PFINT_OICR_ENA); + val &= ~PFINT_OICR_TSYN_TX_M; + wr32(hw, PFINT_OICR_ENA, val); - pf->ptp.tstamp_config.rx_filter = on ? HWTSTAMP_FILTER_ALL : - HWTSTAMP_FILTER_NONE; + ice_set_rx_tstamp(pf, false); } /** - * ice_ptp_cfg_timestamp - Configure timestamp for init/deinit + * ice_ptp_restore_timestamp_mode - Restore timestamp configuration * @pf: Board private structure - * @ena: bool value to enable or disable time stamp * - * This function will configure timestamping during PTP initialization - * and deinitialization + * Called at the end of rebuild to restore timestamp configuration after + * a device reset. */ -void ice_ptp_cfg_timestamp(struct ice_pf *pf, bool ena) +void ice_ptp_restore_timestamp_mode(struct ice_pf *pf) { - ice_set_tx_tstamp(pf, ena); - ice_set_rx_tstamp(pf, ena); + struct ice_hw *hw = &pf->hw; + bool enable_rx; + + ice_ptp_cfg_tx_interrupt(pf); + + enable_rx = pf->ptp.tstamp_config.rx_filter == HWTSTAMP_FILTER_ALL; + ice_set_rx_tstamp(pf, enable_rx); + + /* Trigger an immediate software interrupt to ensure that timestamps + * which occurred during reset are handled now. + */ + wr32(hw, PFINT_OICR, PFINT_OICR_TSYN_TX_M); + ice_flush(hw); } /** @@ -2037,10 +2058,10 @@ ice_ptp_set_timestamp_mode(struct ice_pf *pf, struct hwtstamp_config *config) { switch (config->tx_type) { case HWTSTAMP_TX_OFF: - ice_set_tx_tstamp(pf, false); + pf->ptp.tstamp_config.tx_type = HWTSTAMP_TX_OFF; break; case HWTSTAMP_TX_ON: - ice_set_tx_tstamp(pf, true); + pf->ptp.tstamp_config.tx_type = HWTSTAMP_TX_ON; break; default: return -ERANGE; @@ -2048,7 +2069,7 @@ ice_ptp_set_timestamp_mode(struct ice_pf *pf, struct hwtstamp_config *config) switch (config->rx_filter) { case HWTSTAMP_FILTER_NONE: - ice_set_rx_tstamp(pf, false); + pf->ptp.tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; break; case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: @@ -2064,12 +2085,15 @@ ice_ptp_set_timestamp_mode(struct ice_pf *pf, struct hwtstamp_config *config) case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: case HWTSTAMP_FILTER_NTP_ALL: case HWTSTAMP_FILTER_ALL: - ice_set_rx_tstamp(pf, true); + pf->ptp.tstamp_config.rx_filter = HWTSTAMP_FILTER_ALL; break; default: return -ERANGE; } + /* Immediately update the device timestamping mode */ + ice_ptp_restore_timestamp_mode(pf); + return 0; } @@ -2737,7 +2761,7 @@ void ice_ptp_prepare_for_reset(struct ice_pf *pf) clear_bit(ICE_FLAG_PTP, pf->flags); /* Disable timestamping for both Tx and Rx */ - ice_ptp_cfg_timestamp(pf, false); + ice_ptp_disable_timestamp_mode(pf); kthread_cancel_delayed_work_sync(&ptp->work); @@ -2803,15 +2827,7 @@ static int ice_ptp_init_owner(struct ice_pf *pf) /* Release the global hardware lock */ ice_ptp_unlock(hw); - if (pf->ptp.tx_interrupt_mode == ICE_PTP_TX_INTERRUPT_ALL) { - /* The clock owner for this device type handles the timestamp - * interrupt for all ports. - */ - ice_ptp_configure_tx_tstamp(pf, true); - - /* React on all quads interrupts for E82x */ - wr32(hw, PFINT_TSYN_MSK + (0x4 * hw->pf_id), (u32)0x1f); - + if (!ice_is_e810(hw)) { /* Enable quad interrupts */ err = ice_ptp_tx_ena_intr(pf, true, itr); if (err) @@ -2881,13 +2897,6 @@ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port) case ICE_PHY_E810: return ice_ptp_init_tx_e810(pf, &ptp_port->tx); case ICE_PHY_E822: - /* Non-owner PFs don't react to any interrupts on E82x, - * neither on own quad nor on others - */ - if (!ice_ptp_pf_handles_tx_interrupt(pf)) { - ice_ptp_configure_tx_tstamp(pf, false); - wr32(hw, PFINT_TSYN_MSK + (0x4 * hw->pf_id), (u32)0x0); - } kthread_init_delayed_work(&ptp_port->ov_work, ice_ptp_wait_for_offsets); @@ -3032,6 +3041,9 @@ void ice_ptp_init(struct ice_pf *pf) /* Start the PHY timestamping block */ ice_ptp_reset_phy_timestamping(pf); + /* Configure initial Tx interrupt settings */ + ice_ptp_cfg_tx_interrupt(pf); + set_bit(ICE_FLAG_PTP, pf->flags); err = ice_ptp_init_work(pf, ptp); if (err) @@ -3067,7 +3079,7 @@ void ice_ptp_release(struct ice_pf *pf) return; /* Disable timestamping for both Tx and Rx */ - ice_ptp_cfg_timestamp(pf, false); + ice_ptp_disable_timestamp_mode(pf); ice_ptp_remove_auxbus_device(pf); diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h index 8f6f94392756..06a330867fc9 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp.h @@ -292,7 +292,7 @@ int ice_ptp_clock_index(struct ice_pf *pf); struct ice_pf; int ice_ptp_set_ts_config(struct ice_pf *pf, struct ifreq *ifr); int ice_ptp_get_ts_config(struct ice_pf *pf, struct ifreq *ifr); -void ice_ptp_cfg_timestamp(struct ice_pf *pf, bool ena); +void ice_ptp_restore_timestamp_mode(struct ice_pf *pf); void ice_ptp_extts_event(struct ice_pf *pf); s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb); @@ -317,8 +317,7 @@ static inline int ice_ptp_get_ts_config(struct ice_pf *pf, struct ifreq *ifr) return -EOPNOTSUPP; } -static inline void ice_ptp_cfg_timestamp(struct ice_pf *pf, bool ena) { } - +static inline void ice_ptp_restore_timestamp_mode(struct ice_pf *pf) { } static inline void ice_ptp_extts_event(struct ice_pf *pf) { } static inline s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb) diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 52d0a126eb61..9e97ea863068 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -2306,9 +2306,6 @@ ice_tstamp(struct ice_tx_ring *tx_ring, struct sk_buff *skb, if (likely(!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))) return; - if (!tx_ring->ptp_tx) - return; - /* Tx timestamps cannot be sampled when doing TSO */ if (first->tx_flags & ICE_TX_FLAGS_TSO) return; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index 166413fc33f4..daf7b9dbb143 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -380,7 +380,6 @@ struct ice_tx_ring { #define ICE_TX_FLAGS_RING_VLAN_L2TAG2 BIT(2) u8 flags; u8 dcb_tc; /* Traffic class of ring */ - u8 ptp_tx; } ____cacheline_internodealigned_in_smp; static inline bool ice_ring_uses_build_skb(struct ice_rx_ring *ring) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c index 4762dbea64a1..97a71e9b8563 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c @@ -1088,6 +1088,7 @@ int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc) struct ethhdr *eth_hdr; bool new = false; int err = 0; + u64 vf_num; u32 ring; if (!flow_cfg->max_flows) { @@ -1100,7 +1101,21 @@ int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc) if (!(pfvf->flags & OTX2_FLAG_NTUPLE_SUPPORT)) return -ENOMEM; - if (ring >= pfvf->hw.rx_queues && fsp->ring_cookie != RX_CLS_FLOW_DISC) + /* Number of queues on a VF can be greater or less than + * the PF's queue. Hence no need to check for the + * queue count. Hence no need to check queue count if PF + * is installing for its VF. Below is the expected vf_num value + * based on the ethtool commands. + * + * e.g. + * 1. ethtool -U <netdev> ... action -1 ==> vf_num:255 + * 2. ethtool -U <netdev> ... action <queue_num> ==> vf_num:0 + * 3. ethtool -U <netdev> ... vf <vf_idx> queue <queue_num> ==> + * vf_num:vf_idx+1 + */ + vf_num = ethtool_get_flow_spec_ring_vf(fsp->ring_cookie); + if (!is_otx2_vf(pfvf->pcifunc) && !vf_num && + ring >= pfvf->hw.rx_queues && fsp->ring_cookie != RX_CLS_FLOW_DISC) return -EINVAL; if (fsp->location >= otx2_get_maxflows(flow_cfg)) @@ -1182,6 +1197,9 @@ int otx2_add_flow(struct otx2_nic *pfvf, struct ethtool_rxnfc *nfc) flow_cfg->nr_flows++; } + if (flow->is_vf) + netdev_info(pfvf->netdev, + "Make sure that VF's queue number is within its queue limit\n"); return 0; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 91b99fd70361..ba95ac913274 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1934,6 +1934,8 @@ int otx2_stop(struct net_device *netdev) /* Clear RSS enable flag */ rss = &pf->hw.rss_info; rss->enable = false; + if (!netif_is_rxfh_configured(netdev)) + kfree(rss->rss_ctx[DEFAULT_RSS_CONTEXT_GROUP]); /* Cleanup Queue IRQ */ vec = pci_irq_vector(pf->pdev, diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index a8b623145efc..dbc5c9d354c6 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -2599,9 +2599,7 @@ static void rtl_set_rx_mode(struct net_device *dev) rx_mode &= ~AcceptMulticast; } else if (netdev_mc_count(dev) > MC_FILTER_LIMIT || dev->flags & IFF_ALLMULTI || - tp->mac_version == RTL_GIGA_MAC_VER_35 || - tp->mac_version == RTL_GIGA_MAC_VER_46 || - tp->mac_version == RTL_GIGA_MAC_VER_48) { + tp->mac_version == RTL_GIGA_MAC_VER_35) { /* accept all multicasts */ } else if (netdev_mc_empty(dev)) { rx_mode &= ~AcceptMulticast; diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index a2b9e289aa36..85dcda51df05 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -280,7 +280,7 @@ config DWMAC_INTEL config DWMAC_LOONGSON tristate "Loongson PCI DWMAC support" default MACH_LOONGSON64 - depends on STMMAC_ETH && PCI + depends on (MACH_LOONGSON64 || COMPILE_TEST) && STMMAC_ETH && PCI depends on COMMON_CLK help This selects the LOONGSON PCI bus support for the stmmac driver, diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c index a3c5de9d547a..533e912af089 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c @@ -1769,10 +1769,12 @@ int wx_sw_init(struct wx *wx) wx->subsystem_device_id = pdev->subsystem_device; } else { err = wx_flash_read_dword(wx, 0xfffdc, &ssid); - if (!err) - wx->subsystem_device_id = swab16((u16)ssid); + if (err < 0) { + wx_err(wx, "read of internal subsystem device id failed\n"); + return err; + } - return err; + wx->subsystem_device_id = swab16((u16)ssid); } wx->mac_table = kcalloc(wx->mac.num_rar_entries, diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c index 3d43f808c86b..8db804543e66 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c @@ -121,10 +121,8 @@ static int ngbe_sw_init(struct wx *wx) /* PCI config space info */ err = wx_sw_init(wx); - if (err < 0) { - wx_err(wx, "read of internal subsystem device id failed\n"); + if (err < 0) return err; - } /* mac type, phy type , oem type */ ngbe_init_type_code(wx); diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c index 70f0b5c01dac..526250102db2 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c @@ -364,10 +364,8 @@ static int txgbe_sw_init(struct wx *wx) /* PCI config space info */ err = wx_sw_init(wx); - if (err < 0) { - wx_err(wx, "read of internal subsystem device id failed\n"); + if (err < 0) return err; - } txgbe_init_type_code(wx); diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c index 7d8e22929385..aaf780fd4f5e 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c +++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c @@ -966,7 +966,7 @@ axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev) if (lp->features & XAE_FEATURE_FULL_TX_CSUM) { /* Tx Full Checksum Offload Enabled */ cur_p->app0 |= 2; - } else if (lp->features & XAE_FEATURE_PARTIAL_RX_CSUM) { + } else if (lp->features & XAE_FEATURE_PARTIAL_TX_CSUM) { csum_start_off = skb_transport_offset(skb); csum_index_off = csum_start_off + skb->csum_offset; /* Tx Partial Checksum Offload Enabled */ diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 3ba3c8fb28a5..706ea5263e87 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -2206,9 +2206,6 @@ static int netvsc_vf_join(struct net_device *vf_netdev, goto upper_link_failed; } - /* set slave flag before open to prevent IPv6 addrconf */ - vf_netdev->flags |= IFF_SLAVE; - schedule_delayed_work(&ndev_ctx->vf_takeover, VF_TAKEOVER_INT); call_netdevice_notifiers(NETDEV_JOIN, vf_netdev); @@ -2315,16 +2312,18 @@ static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev) } - /* Fallback path to check synthetic vf with - * help of mac addr + /* Fallback path to check synthetic vf with help of mac addr. + * Because this function can be called before vf_netdev is + * initialized (NETDEV_POST_INIT) when its perm_addr has not been copied + * from dev_addr, also try to match to its dev_addr. + * Note: On Hyper-V and Azure, it's not possible to set a MAC address + * on a VF that matches to the MAC of a unrelated NETVSC device. */ list_for_each_entry(ndev_ctx, &netvsc_dev_list, list) { ndev = hv_get_drvdata(ndev_ctx->device_ctx); - if (ether_addr_equal(vf_netdev->perm_addr, ndev->perm_addr)) { - netdev_notice(vf_netdev, - "falling back to mac addr based matching\n"); + if (ether_addr_equal(vf_netdev->perm_addr, ndev->perm_addr) || + ether_addr_equal(vf_netdev->dev_addr, ndev->perm_addr)) return ndev; - } } netdev_notice(vf_netdev, @@ -2332,6 +2331,19 @@ static struct net_device *get_netvsc_byslot(const struct net_device *vf_netdev) return NULL; } +static int netvsc_prepare_bonding(struct net_device *vf_netdev) +{ + struct net_device *ndev; + + ndev = get_netvsc_byslot(vf_netdev); + if (!ndev) + return NOTIFY_DONE; + + /* set slave flag before open to prevent IPv6 addrconf */ + vf_netdev->flags |= IFF_SLAVE; + return NOTIFY_DONE; +} + static int netvsc_register_vf(struct net_device *vf_netdev) { struct net_device_context *net_device_ctx; @@ -2531,15 +2543,6 @@ static int netvsc_probe(struct hv_device *dev, goto devinfo_failed; } - nvdev = rndis_filter_device_add(dev, device_info); - if (IS_ERR(nvdev)) { - ret = PTR_ERR(nvdev); - netdev_err(net, "unable to add netvsc device (ret %d)\n", ret); - goto rndis_failed; - } - - eth_hw_addr_set(net, device_info->mac_adr); - /* We must get rtnl lock before scheduling nvdev->subchan_work, * otherwise netvsc_subchan_work() can get rtnl lock first and wait * all subchannels to show up, but that may not happen because @@ -2547,9 +2550,23 @@ static int netvsc_probe(struct hv_device *dev, * -> ... -> device_add() -> ... -> __device_attach() can't get * the device lock, so all the subchannels can't be processed -- * finally netvsc_subchan_work() hangs forever. + * + * The rtnl lock also needs to be held before rndis_filter_device_add() + * which advertises nvsp_2_vsc_capability / sriov bit, and triggers + * VF NIC offering and registering. If VF NIC finished register_netdev() + * earlier it may cause name based config failure. */ rtnl_lock(); + nvdev = rndis_filter_device_add(dev, device_info); + if (IS_ERR(nvdev)) { + ret = PTR_ERR(nvdev); + netdev_err(net, "unable to add netvsc device (ret %d)\n", ret); + goto rndis_failed; + } + + eth_hw_addr_set(net, device_info->mac_adr); + if (nvdev->num_chn > 1) schedule_work(&nvdev->subchan_work); @@ -2586,9 +2603,9 @@ static int netvsc_probe(struct hv_device *dev, return 0; register_failed: - rtnl_unlock(); rndis_filter_device_remove(dev, nvdev); rndis_failed: + rtnl_unlock(); netvsc_devinfo_put(device_info); devinfo_failed: free_percpu(net_device_ctx->vf_stats); @@ -2753,6 +2770,8 @@ static int netvsc_netdev_event(struct notifier_block *this, return NOTIFY_DONE; switch (event) { + case NETDEV_POST_INIT: + return netvsc_prepare_bonding(event_dev); case NETDEV_REGISTER: return netvsc_register_vf(event_dev); case NETDEV_UNREGISTER: @@ -2788,12 +2807,17 @@ static int __init netvsc_drv_init(void) } netvsc_ring_bytes = ring_size * PAGE_SIZE; + register_netdevice_notifier(&netvsc_netdev_notifier); + ret = vmbus_driver_register(&netvsc_drv); if (ret) - return ret; + goto err_vmbus_reg; - register_netdevice_notifier(&netvsc_netdev_notifier); return 0; + +err_vmbus_reg: + unregister_netdevice_notifier(&netvsc_netdev_notifier); + return ret; } MODULE_LICENSE("GPL"); diff --git a/drivers/net/ipa/reg/gsi_reg-v5.0.c b/drivers/net/ipa/reg/gsi_reg-v5.0.c index d7b81a36d673..145eb0bd096d 100644 --- a/drivers/net/ipa/reg/gsi_reg-v5.0.c +++ b/drivers/net/ipa/reg/gsi_reg-v5.0.c @@ -78,7 +78,7 @@ REG_STRIDE_FIELDS(EV_CH_E_CNTXT_0, ev_ch_e_cntxt_0, 0x0001c000 + 0x12000 * GSI_EE_AP, 0x80); static const u32 reg_ev_ch_e_cntxt_1_fmask[] = { - [R_LENGTH] = GENMASK(19, 0), + [R_LENGTH] = GENMASK(23, 0), }; REG_STRIDE_FIELDS(EV_CH_E_CNTXT_1, ev_ch_e_cntxt_1, diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index 5a0f86f38f09..97bd6705c241 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -7,6 +7,7 @@ #include <linux/filter.h> #include <linux/netfilter_netdev.h> #include <linux/bpf_mprog.h> +#include <linux/indirect_call_wrapper.h> #include <net/netkit.h> #include <net/dst.h> @@ -68,6 +69,7 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev) netdev_tx_t ret_dev = NET_XMIT_SUCCESS; const struct bpf_mprog_entry *entry; struct net_device *peer; + int len = skb->len; rcu_read_lock(); peer = rcu_dereference(nk->peer); @@ -85,15 +87,22 @@ static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev) case NETKIT_PASS: skb->protocol = eth_type_trans(skb, skb->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); - __netif_rx(skb); + if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) { + dev_sw_netstats_tx_add(dev, 1, len); + dev_sw_netstats_rx_add(peer, len); + } else { + goto drop_stats; + } break; case NETKIT_REDIRECT: + dev_sw_netstats_tx_add(dev, 1, len); skb_do_redirect(skb); break; case NETKIT_DROP: default: drop: kfree_skb(skb); +drop_stats: dev_core_stats_tx_dropped_inc(dev); ret_dev = NET_XMIT_DROP; break; @@ -169,11 +178,18 @@ out: rcu_read_unlock(); } -static struct net_device *netkit_peer_dev(struct net_device *dev) +INDIRECT_CALLABLE_SCOPE struct net_device *netkit_peer_dev(struct net_device *dev) { return rcu_dereference(netkit_priv(dev)->peer); } +static void netkit_get_stats(struct net_device *dev, + struct rtnl_link_stats64 *stats) +{ + dev_fetch_sw_netstats(stats, dev->tstats); + stats->tx_dropped = DEV_STATS_READ(dev, tx_dropped); +} + static void netkit_uninit(struct net_device *dev); static const struct net_device_ops netkit_netdev_ops = { @@ -184,6 +200,7 @@ static const struct net_device_ops netkit_netdev_ops = { .ndo_set_rx_headroom = netkit_set_headroom, .ndo_get_iflink = netkit_get_iflink, .ndo_get_peer_dev = netkit_peer_dev, + .ndo_get_stats64 = netkit_get_stats, .ndo_uninit = netkit_uninit, .ndo_features_check = passthru_features_check, }; @@ -218,6 +235,7 @@ static void netkit_setup(struct net_device *dev) ether_setup(dev); dev->max_mtu = ETH_MAX_MTU; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; dev->flags |= IFF_NOARP; dev->priv_flags &= ~IFF_TX_SKB_SHARING; diff --git a/drivers/net/usb/aqc111.c b/drivers/net/usb/aqc111.c index a017e9de2119..7b8afa589a53 100644 --- a/drivers/net/usb/aqc111.c +++ b/drivers/net/usb/aqc111.c @@ -1079,17 +1079,17 @@ static int aqc111_rx_fixup(struct usbnet *dev, struct sk_buff *skb) u16 pkt_count = 0; u64 desc_hdr = 0; u16 vlan_tag = 0; - u32 skb_len = 0; + u32 skb_len; if (!skb) goto err; - if (skb->len == 0) + skb_len = skb->len; + if (skb_len < sizeof(desc_hdr)) goto err; - skb_len = skb->len; /* RX Descriptor Header */ - skb_trim(skb, skb->len - sizeof(desc_hdr)); + skb_trim(skb, skb_len - sizeof(desc_hdr)); desc_hdr = le64_to_cpup((u64 *)skb_tail_pointer(skb)); /* Check these packets */ diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index fb0903ad6de3..8d835fbc4316 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -1581,11 +1581,11 @@ static int ax88179_reset(struct usbnet *dev) *tmp16 = AX_PHYPWR_RSTCTL_IPRL; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_PHYPWR_RSTCTL, 2, 2, tmp16); - msleep(200); + msleep(500); *tmp = AX_CLK_SELECT_ACS | AX_CLK_SELECT_BCS; ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_CLK_SELECT, 1, 1, tmp); - msleep(100); + msleep(200); /* Ethernet PHY Auto Detach*/ ax88179_auto_detach(dev); diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 344af3c5c836..e2e181378f41 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1289,6 +1289,7 @@ static const struct usb_device_id products[] = { {QMI_FIXED_INTF(0x19d2, 0x0168, 4)}, {QMI_FIXED_INTF(0x19d2, 0x0176, 3)}, {QMI_FIXED_INTF(0x19d2, 0x0178, 3)}, + {QMI_FIXED_INTF(0x19d2, 0x0189, 4)}, /* ZTE MF290 */ {QMI_FIXED_INTF(0x19d2, 0x0191, 4)}, /* ZTE EuFi890 */ {QMI_FIXED_INTF(0x19d2, 0x0199, 1)}, /* ZTE MF820S */ {QMI_FIXED_INTF(0x19d2, 0x0200, 1)}, diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 9980517ed8b0..57efb3454c57 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -236,8 +236,8 @@ static void veth_get_ethtool_stats(struct net_device *dev, data[tx_idx + j] += *(u64 *)(base + offset); } } while (u64_stats_fetch_retry(&rq_stats->syncp, start)); - pp_idx = tx_idx + VETH_TQ_STATS_LEN; } + pp_idx = idx + dev->real_num_tx_queues * VETH_TQ_STATS_LEN; page_pool_stats: veth_get_page_pool_stats(dev, &data[pp_idx]); @@ -373,7 +373,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) skb_tx_timestamp(skb); if (likely(veth_forward_skb(rcv, skb, rq, use_napi) == NET_RX_SUCCESS)) { if (!use_napi) - dev_lstats_add(dev, length); + dev_sw_netstats_tx_add(dev, 1, length); else __veth_xdp_flush(rq); } else { @@ -387,14 +387,6 @@ drop: return ret; } -static u64 veth_stats_tx(struct net_device *dev, u64 *packets, u64 *bytes) -{ - struct veth_priv *priv = netdev_priv(dev); - - dev_lstats_read(dev, packets, bytes); - return atomic64_read(&priv->dropped); -} - static void veth_stats_rx(struct veth_stats *result, struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); @@ -432,24 +424,24 @@ static void veth_get_stats64(struct net_device *dev, struct veth_priv *priv = netdev_priv(dev); struct net_device *peer; struct veth_stats rx; - u64 packets, bytes; - tot->tx_dropped = veth_stats_tx(dev, &packets, &bytes); - tot->tx_bytes = bytes; - tot->tx_packets = packets; + tot->tx_dropped = atomic64_read(&priv->dropped); + dev_fetch_sw_netstats(tot, dev->tstats); veth_stats_rx(&rx, dev); tot->tx_dropped += rx.xdp_tx_err; tot->rx_dropped = rx.rx_drops + rx.peer_tq_xdp_xmit_err; - tot->rx_bytes = rx.xdp_bytes; - tot->rx_packets = rx.xdp_packets; + tot->rx_bytes += rx.xdp_bytes; + tot->rx_packets += rx.xdp_packets; rcu_read_lock(); peer = rcu_dereference(priv->peer); if (peer) { - veth_stats_tx(peer, &packets, &bytes); - tot->rx_bytes += bytes; - tot->rx_packets += packets; + struct rtnl_link_stats64 tot_peer = {}; + + dev_fetch_sw_netstats(&tot_peer, peer->tstats); + tot->rx_bytes += tot_peer.tx_bytes; + tot->rx_packets += tot_peer.tx_packets; veth_stats_rx(&rx, peer); tot->tx_dropped += rx.peer_tq_xdp_xmit_err; @@ -1506,25 +1498,12 @@ static void veth_free_queues(struct net_device *dev) static int veth_dev_init(struct net_device *dev) { - int err; - - dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats); - if (!dev->lstats) - return -ENOMEM; - - err = veth_alloc_queues(dev); - if (err) { - free_percpu(dev->lstats); - return err; - } - - return 0; + return veth_alloc_queues(dev); } static void veth_dev_free(struct net_device *dev) { veth_free_queues(dev); - free_percpu(dev->lstats); } #ifdef CONFIG_NET_POLL_CONTROLLER @@ -1796,6 +1775,7 @@ static void veth_setup(struct net_device *dev) NETIF_F_HW_VLAN_STAG_RX); dev->needs_free_netdev = true; dev->priv_destructor = veth_dev_free; + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; dev->max_mtu = ETH_MAX_MTU; dev->hw_features = VETH_FEATURES; diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index db766941b78f..bb95ce43cd97 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -121,22 +121,12 @@ struct net_vrf { int ifindex; }; -struct pcpu_dstats { - u64 tx_pkts; - u64 tx_bytes; - u64 tx_drps; - u64 rx_pkts; - u64 rx_bytes; - u64 rx_drps; - struct u64_stats_sync syncp; -}; - static void vrf_rx_stats(struct net_device *dev, int len) { struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); u64_stats_update_begin(&dstats->syncp); - dstats->rx_pkts++; + dstats->rx_packets++; dstats->rx_bytes += len; u64_stats_update_end(&dstats->syncp); } @@ -161,10 +151,10 @@ static void vrf_get_stats64(struct net_device *dev, do { start = u64_stats_fetch_begin(&dstats->syncp); tbytes = dstats->tx_bytes; - tpkts = dstats->tx_pkts; - tdrops = dstats->tx_drps; + tpkts = dstats->tx_packets; + tdrops = dstats->tx_drops; rbytes = dstats->rx_bytes; - rpkts = dstats->rx_pkts; + rpkts = dstats->rx_packets; } while (u64_stats_fetch_retry(&dstats->syncp, start)); stats->tx_bytes += tbytes; stats->tx_packets += tpkts; @@ -421,7 +411,7 @@ static int vrf_local_xmit(struct sk_buff *skb, struct net_device *dev, if (likely(__netif_rx(skb) == NET_RX_SUCCESS)) vrf_rx_stats(dev, len); else - this_cpu_inc(dev->dstats->rx_drps); + this_cpu_inc(dev->dstats->rx_drops); return NETDEV_TX_OK; } @@ -616,11 +606,11 @@ static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev) struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats); u64_stats_update_begin(&dstats->syncp); - dstats->tx_pkts++; + dstats->tx_packets++; dstats->tx_bytes += len; u64_stats_update_end(&dstats->syncp); } else { - this_cpu_inc(dev->dstats->tx_drps); + this_cpu_inc(dev->dstats->tx_drops); } return ret; @@ -1174,22 +1164,15 @@ static void vrf_dev_uninit(struct net_device *dev) vrf_rtable_release(dev, vrf); vrf_rt6_release(dev, vrf); - - free_percpu(dev->dstats); - dev->dstats = NULL; } static int vrf_dev_init(struct net_device *dev) { struct net_vrf *vrf = netdev_priv(dev); - dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats); - if (!dev->dstats) - goto out_nomem; - /* create the default dst which points back to us */ if (vrf_rtable_create(dev) != 0) - goto out_stats; + goto out_nomem; if (vrf_rt6_create(dev) != 0) goto out_rth; @@ -1203,9 +1186,6 @@ static int vrf_dev_init(struct net_device *dev) out_rth: vrf_rtable_release(dev, vrf); -out_stats: - free_percpu(dev->dstats); - dev->dstats = NULL; out_nomem: return -ENOMEM; } @@ -1704,6 +1684,8 @@ static void vrf_setup(struct net_device *dev) dev->min_mtu = IPV6_MIN_MTU; dev->max_mtu = IP6_MAX_MTU; dev->mtu = dev->max_mtu; + + dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS; } static int vrf_validate(struct nlattr *tb[], struct nlattr *data[], diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c index 258dcc103921..deb9636b0ecf 100644 --- a/drivers/net/wireguard/device.c +++ b/drivers/net/wireguard/device.c @@ -210,7 +210,7 @@ static netdev_tx_t wg_xmit(struct sk_buff *skb, struct net_device *dev) */ while (skb_queue_len(&peer->staged_packet_queue) > MAX_STAGED_PACKETS) { dev_kfree_skb(__skb_dequeue(&peer->staged_packet_queue)); - ++dev->stats.tx_dropped; + DEV_STATS_INC(dev, tx_dropped); } skb_queue_splice_tail(&packets, &peer->staged_packet_queue); spin_unlock_bh(&peer->staged_packet_queue.lock); @@ -228,7 +228,7 @@ err_icmp: else if (skb->protocol == htons(ETH_P_IPV6)) icmpv6_ndo_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0); err: - ++dev->stats.tx_errors; + DEV_STATS_INC(dev, tx_errors); kfree_skb(skb); return ret; } diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c index 0b3f0c843550..a176653c8861 100644 --- a/drivers/net/wireguard/receive.c +++ b/drivers/net/wireguard/receive.c @@ -416,20 +416,20 @@ dishonest_packet_peer: net_dbg_skb_ratelimited("%s: Packet has unallowed src IP (%pISc) from peer %llu (%pISpfsc)\n", dev->name, skb, peer->internal_id, &peer->endpoint.addr); - ++dev->stats.rx_errors; - ++dev->stats.rx_frame_errors; + DEV_STATS_INC(dev, rx_errors); + DEV_STATS_INC(dev, rx_frame_errors); goto packet_processed; dishonest_packet_type: net_dbg_ratelimited("%s: Packet is neither ipv4 nor ipv6 from peer %llu (%pISpfsc)\n", dev->name, peer->internal_id, &peer->endpoint.addr); - ++dev->stats.rx_errors; - ++dev->stats.rx_frame_errors; + DEV_STATS_INC(dev, rx_errors); + DEV_STATS_INC(dev, rx_frame_errors); goto packet_processed; dishonest_packet_size: net_dbg_ratelimited("%s: Packet has incorrect size from peer %llu (%pISpfsc)\n", dev->name, peer->internal_id, &peer->endpoint.addr); - ++dev->stats.rx_errors; - ++dev->stats.rx_length_errors; + DEV_STATS_INC(dev, rx_errors); + DEV_STATS_INC(dev, rx_length_errors); goto packet_processed; packet_processed: dev_kfree_skb(skb); diff --git a/drivers/net/wireguard/send.c b/drivers/net/wireguard/send.c index 95c853b59e1d..0d48e0f4a1ba 100644 --- a/drivers/net/wireguard/send.c +++ b/drivers/net/wireguard/send.c @@ -333,7 +333,8 @@ err: void wg_packet_purge_staged_packets(struct wg_peer *peer) { spin_lock_bh(&peer->staged_packet_queue.lock); - peer->device->dev->stats.tx_dropped += peer->staged_packet_queue.qlen; + DEV_STATS_ADD(peer->device->dev, tx_dropped, + peer->staged_packet_queue.qlen); __skb_queue_purge(&peer->staged_packet_queue); spin_unlock_bh(&peer->staged_packet_queue.lock); } diff --git a/drivers/nfc/virtual_ncidev.c b/drivers/nfc/virtual_ncidev.c index b027be0b0b6f..590b038e449e 100644 --- a/drivers/nfc/virtual_ncidev.c +++ b/drivers/nfc/virtual_ncidev.c @@ -26,10 +26,14 @@ struct virtual_nci_dev { struct mutex mtx; struct sk_buff *send_buff; struct wait_queue_head wq; + bool running; }; static int virtual_nci_open(struct nci_dev *ndev) { + struct virtual_nci_dev *vdev = nci_get_drvdata(ndev); + + vdev->running = true; return 0; } @@ -40,6 +44,7 @@ static int virtual_nci_close(struct nci_dev *ndev) mutex_lock(&vdev->mtx); kfree_skb(vdev->send_buff); vdev->send_buff = NULL; + vdev->running = false; mutex_unlock(&vdev->mtx); return 0; @@ -50,7 +55,7 @@ static int virtual_nci_send(struct nci_dev *ndev, struct sk_buff *skb) struct virtual_nci_dev *vdev = nci_get_drvdata(ndev); mutex_lock(&vdev->mtx); - if (vdev->send_buff) { + if (vdev->send_buff || !vdev->running) { mutex_unlock(&vdev->mtx); kfree_skb(skb); return -1; diff --git a/drivers/parisc/power.c b/drivers/parisc/power.c index 539d8920c202..bb0d92461b08 100644 --- a/drivers/parisc/power.c +++ b/drivers/parisc/power.c @@ -176,7 +176,7 @@ static struct notifier_block parisc_panic_block = { static int qemu_power_off(struct sys_off_data *data) { /* this turns the system off via SeaBIOS */ - *(int *)data->cb_data = 0; + gsc_writel(0, (unsigned long) data->cb_data); pdc_soft_power_button(1); return NOTIFY_DONE; } diff --git a/drivers/platform/x86/amd/pmc/pmc.c b/drivers/platform/x86/amd/pmc/pmc.c index cd6ac04c1468..c3104714b480 100644 --- a/drivers/platform/x86/amd/pmc/pmc.c +++ b/drivers/platform/x86/amd/pmc/pmc.c @@ -964,33 +964,6 @@ static const struct pci_device_id pmc_pci_ids[] = { { } }; -static int amd_pmc_get_dram_size(struct amd_pmc_dev *dev) -{ - int ret; - - switch (dev->cpu_id) { - case AMD_CPU_ID_YC: - if (!(dev->major > 90 || (dev->major == 90 && dev->minor > 39))) { - ret = -EINVAL; - goto err_dram_size; - } - break; - default: - ret = -EINVAL; - goto err_dram_size; - } - - ret = amd_pmc_send_cmd(dev, S2D_DRAM_SIZE, &dev->dram_size, dev->s2d_msg_id, true); - if (ret || !dev->dram_size) - goto err_dram_size; - - return 0; - -err_dram_size: - dev_err(dev->dev, "DRAM size command not supported for this platform\n"); - return ret; -} - static int amd_pmc_s2d_init(struct amd_pmc_dev *dev) { u32 phys_addr_low, phys_addr_hi; @@ -1009,8 +982,8 @@ static int amd_pmc_s2d_init(struct amd_pmc_dev *dev) return -EIO; /* Get DRAM size */ - ret = amd_pmc_get_dram_size(dev); - if (ret) + ret = amd_pmc_send_cmd(dev, S2D_DRAM_SIZE, &dev->dram_size, dev->s2d_msg_id, true); + if (ret || !dev->dram_size) dev->dram_size = S2D_TELEMETRY_DRAMBYTES_MAX; /* Get STB DRAM address */ diff --git a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c index 5798b49ddaba..8c9f4f3227fc 100644 --- a/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c +++ b/drivers/platform/x86/hp/hp-bioscfg/bioscfg.c @@ -588,17 +588,14 @@ static void release_attributes_data(void) static int hp_add_other_attributes(int attr_type) { struct kobject *attr_name_kobj; - union acpi_object *obj = NULL; int ret; char *attr_name; - mutex_lock(&bioscfg_drv.mutex); - attr_name_kobj = kzalloc(sizeof(*attr_name_kobj), GFP_KERNEL); - if (!attr_name_kobj) { - ret = -ENOMEM; - goto err_other_attr_init; - } + if (!attr_name_kobj) + return -ENOMEM; + + mutex_lock(&bioscfg_drv.mutex); /* Check if attribute type is supported */ switch (attr_type) { @@ -615,14 +612,14 @@ static int hp_add_other_attributes(int attr_type) default: pr_err("Error: Unknown attr_type: %d\n", attr_type); ret = -EINVAL; - goto err_other_attr_init; + kfree(attr_name_kobj); + goto unlock_drv_mutex; } ret = kobject_init_and_add(attr_name_kobj, &attr_name_ktype, NULL, "%s", attr_name); if (ret) { pr_err("Error encountered [%d]\n", ret); - kobject_put(attr_name_kobj); goto err_other_attr_init; } @@ -630,27 +627,26 @@ static int hp_add_other_attributes(int attr_type) switch (attr_type) { case HPWMI_SECURE_PLATFORM_TYPE: ret = hp_populate_secure_platform_data(attr_name_kobj); - if (ret) - goto err_other_attr_init; break; case HPWMI_SURE_START_TYPE: ret = hp_populate_sure_start_data(attr_name_kobj); - if (ret) - goto err_other_attr_init; break; default: ret = -EINVAL; - goto err_other_attr_init; } + if (ret) + goto err_other_attr_init; + mutex_unlock(&bioscfg_drv.mutex); return 0; err_other_attr_init: + kobject_put(attr_name_kobj); +unlock_drv_mutex: mutex_unlock(&bioscfg_drv.mutex); - kfree(obj); return ret; } diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c index ac037540acfc..88eefccb6ed2 100644 --- a/drivers/platform/x86/ideapad-laptop.c +++ b/drivers/platform/x86/ideapad-laptop.c @@ -1425,18 +1425,17 @@ static int ideapad_kbd_bl_init(struct ideapad_private *priv) if (WARN_ON(priv->kbd_bl.initialized)) return -EEXIST; - brightness = ideapad_kbd_bl_brightness_get(priv); - if (brightness < 0) - return brightness; - - priv->kbd_bl.last_brightness = brightness; - if (ideapad_kbd_bl_check_tristate(priv->kbd_bl.type)) { priv->kbd_bl.led.max_brightness = 2; } else { priv->kbd_bl.led.max_brightness = 1; } + brightness = ideapad_kbd_bl_brightness_get(priv); + if (brightness < 0) + return brightness; + + priv->kbd_bl.last_brightness = brightness; priv->kbd_bl.led.name = "platform::" LED_FUNCTION_KBD_BACKLIGHT; priv->kbd_bl.led.brightness_get = ideapad_kbd_bl_led_cdev_brightness_get; priv->kbd_bl.led.brightness_set_blocking = ideapad_kbd_bl_led_cdev_brightness_set; diff --git a/drivers/platform/x86/intel/telemetry/core.c b/drivers/platform/x86/intel/telemetry/core.c index fdf55b5d6948..e4be40f73eeb 100644 --- a/drivers/platform/x86/intel/telemetry/core.c +++ b/drivers/platform/x86/intel/telemetry/core.c @@ -102,7 +102,7 @@ static const struct telemetry_core_ops telm_defpltops = { /** * telemetry_update_events() - Update telemetry Configuration * @pss_evtconfig: PSS related config. No change if num_evts = 0. - * @pss_evtconfig: IOSS related config. No change if num_evts = 0. + * @ioss_evtconfig: IOSS related config. No change if num_evts = 0. * * This API updates the IOSS & PSS Telemetry configuration. Old config * is overwritten. Call telemetry_reset_events when logging is over @@ -176,7 +176,7 @@ EXPORT_SYMBOL_GPL(telemetry_reset_events); /** * telemetry_get_eventconfig() - Returns the pss and ioss events enabled * @pss_evtconfig: Pointer to PSS related configuration. - * @pss_evtconfig: Pointer to IOSS related configuration. + * @ioss_evtconfig: Pointer to IOSS related configuration. * @pss_len: Number of u32 elements allocated for pss_evtconfig array * @ioss_len: Number of u32 elements allocated for ioss_evtconfig array * diff --git a/drivers/s390/net/Kconfig b/drivers/s390/net/Kconfig index 4902d45e929c..c61e6427384c 100644 --- a/drivers/s390/net/Kconfig +++ b/drivers/s390/net/Kconfig @@ -103,10 +103,11 @@ config CCWGROUP config ISM tristate "Support for ISM vPCI Adapter" depends on PCI + imply SMC default n help Select this option if you want to use the Internal Shared Memory - vPCI Adapter. + vPCI Adapter. The adapter can be used with the SMC network protocol. To compile as a module choose M. The module name is ism. If unsure, choose N. diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c index 6df7f377d2f9..81aabbfbbe2c 100644 --- a/drivers/s390/net/ism_drv.c +++ b/drivers/s390/net/ism_drv.c @@ -30,7 +30,6 @@ static const struct pci_device_id ism_device_table[] = { MODULE_DEVICE_TABLE(pci, ism_device_table); static debug_info_t *ism_debug_info; -static const struct smcd_ops ism_ops; #define NO_CLIENT 0xff /* must be >= MAX_CLIENTS */ static struct ism_client *clients[MAX_CLIENTS]; /* use an array rather than */ @@ -289,22 +288,6 @@ out: return ret; } -static int ism_query_rgid(struct ism_dev *ism, u64 rgid, u32 vid_valid, - u32 vid) -{ - union ism_query_rgid cmd; - - memset(&cmd, 0, sizeof(cmd)); - cmd.request.hdr.cmd = ISM_QUERY_RGID; - cmd.request.hdr.len = sizeof(cmd.request); - - cmd.request.rgid = rgid; - cmd.request.vlan_valid = vid_valid; - cmd.request.vlan_id = vid; - - return ism_cmd(ism, &cmd); -} - static void ism_free_dmb(struct ism_dev *ism, struct ism_dmb *dmb) { clear_bit(dmb->sba_idx, ism->sba_bitmap); @@ -429,23 +412,6 @@ static int ism_del_vlan_id(struct ism_dev *ism, u64 vlan_id) return ism_cmd(ism, &cmd); } -static int ism_signal_ieq(struct ism_dev *ism, u64 rgid, u32 trigger_irq, - u32 event_code, u64 info) -{ - union ism_sig_ieq cmd; - - memset(&cmd, 0, sizeof(cmd)); - cmd.request.hdr.cmd = ISM_SIGNAL_IEQ; - cmd.request.hdr.len = sizeof(cmd.request); - - cmd.request.rgid = rgid; - cmd.request.trigger_irq = trigger_irq; - cmd.request.event_code = event_code; - cmd.request.info = info; - - return ism_cmd(ism, &cmd); -} - static unsigned int max_bytes(unsigned int start, unsigned int len, unsigned int boundary) { @@ -503,14 +469,6 @@ u8 *ism_get_seid(void) } EXPORT_SYMBOL_GPL(ism_get_seid); -static u16 ism_get_chid(struct ism_dev *ism) -{ - if (!ism || !ism->pdev) - return 0; - - return to_zpci(ism->pdev)->pchid; -} - static void ism_handle_event(struct ism_dev *ism) { struct ism_event *entry; @@ -569,11 +527,6 @@ static irqreturn_t ism_handle_irq(int irq, void *data) return IRQ_HANDLED; } -static u64 ism_get_local_gid(struct ism_dev *ism) -{ - return ism->local_gid; -} - static int ism_dev_init(struct ism_dev *ism) { struct pci_dev *pdev = ism->pdev; @@ -774,6 +727,22 @@ module_exit(ism_exit); /*************************** SMC-D Implementation *****************************/ #if IS_ENABLED(CONFIG_SMC) +static int ism_query_rgid(struct ism_dev *ism, u64 rgid, u32 vid_valid, + u32 vid) +{ + union ism_query_rgid cmd; + + memset(&cmd, 0, sizeof(cmd)); + cmd.request.hdr.cmd = ISM_QUERY_RGID; + cmd.request.hdr.len = sizeof(cmd.request); + + cmd.request.rgid = rgid; + cmd.request.vlan_valid = vid_valid; + cmd.request.vlan_id = vid; + + return ism_cmd(ism, &cmd); +} + static int smcd_query_rgid(struct smcd_dev *smcd, u64 rgid, u32 vid_valid, u32 vid) { @@ -811,6 +780,23 @@ static int smcd_reset_vlan_required(struct smcd_dev *smcd) return ism_cmd_simple(smcd->priv, ISM_RESET_VLAN); } +static int ism_signal_ieq(struct ism_dev *ism, u64 rgid, u32 trigger_irq, + u32 event_code, u64 info) +{ + union ism_sig_ieq cmd; + + memset(&cmd, 0, sizeof(cmd)); + cmd.request.hdr.cmd = ISM_SIGNAL_IEQ; + cmd.request.hdr.len = sizeof(cmd.request); + + cmd.request.rgid = rgid; + cmd.request.trigger_irq = trigger_irq; + cmd.request.event_code = event_code; + cmd.request.info = info; + + return ism_cmd(ism, &cmd); +} + static int smcd_signal_ieq(struct smcd_dev *smcd, u64 rgid, u32 trigger_irq, u32 event_code, u64 info) { @@ -830,11 +816,24 @@ static int smcd_supports_v2(void) SYSTEM_EID.type[0] != '0'; } +static u64 ism_get_local_gid(struct ism_dev *ism) +{ + return ism->local_gid; +} + static u64 smcd_get_local_gid(struct smcd_dev *smcd) { return ism_get_local_gid(smcd->priv); } +static u16 ism_get_chid(struct ism_dev *ism) +{ + if (!ism || !ism->pdev) + return 0; + + return to_zpci(ism->pdev)->pchid; +} + static u16 smcd_get_chid(struct smcd_dev *smcd) { return ism_get_chid(smcd->priv); diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 32d1e73e46ee..03348f605c2e 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -1837,8 +1837,16 @@ static void qla2x00_abort_srb(struct qla_qpair *qp, srb_t *sp, const int res, } spin_lock_irqsave(qp->qp_lock_ptr, *flags); - if (ret_cmd && blk_mq_request_started(scsi_cmd_to_rq(cmd))) - sp->done(sp, res); + switch (sp->type) { + case SRB_SCSI_CMD: + if (ret_cmd && blk_mq_request_started(scsi_cmd_to_rq(cmd))) + sp->done(sp, res); + break; + default: + if (ret_cmd) + sp->done(sp, res); + break; + } } else { sp->done(sp, res); } diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 67922e2c4c19..6d8218a44122 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -1019,7 +1019,7 @@ static ssize_t sdebug_error_write(struct file *file, const char __user *ubuf, struct sdebug_err_inject *inject; struct scsi_device *sdev = (struct scsi_device *)file->f_inode->i_private; - buf = kmalloc(count, GFP_KERNEL); + buf = kzalloc(count + 1, GFP_KERNEL); if (!buf) return -ENOMEM; @@ -1132,7 +1132,6 @@ static const struct file_operations sdebug_target_reset_fail_fops = { static int sdebug_target_alloc(struct scsi_target *starget) { struct sdebug_target_info *targetip; - struct dentry *dentry; targetip = kzalloc(sizeof(struct sdebug_target_info), GFP_KERNEL); if (!targetip) @@ -1140,15 +1139,9 @@ static int sdebug_target_alloc(struct scsi_target *starget) targetip->debugfs_entry = debugfs_create_dir(dev_name(&starget->dev), sdebug_debugfs_root); - if (IS_ERR_OR_NULL(targetip->debugfs_entry)) - pr_info("%s: failed to create debugfs directory for target %s\n", - __func__, dev_name(&starget->dev)); debugfs_create_file("fail_reset", 0600, targetip->debugfs_entry, starget, &sdebug_target_reset_fail_fops); - if (IS_ERR_OR_NULL(dentry)) - pr_info("%s: failed to create fail_reset file for target %s\n", - __func__, dev_name(&starget->dev)); starget->hostdata = targetip; diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 530918cbfce2..fa00dd503cbf 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1643,24 +1643,21 @@ out: return disk_changed ? DISK_EVENT_MEDIA_CHANGE : 0; } -static int sd_sync_cache(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr) +static int sd_sync_cache(struct scsi_disk *sdkp) { int retries, res; struct scsi_device *sdp = sdkp->device; const int timeout = sdp->request_queue->rq_timeout * SD_FLUSH_TIMEOUT_MULTIPLIER; - struct scsi_sense_hdr my_sshdr; + struct scsi_sense_hdr sshdr; const struct scsi_exec_args exec_args = { .req_flags = BLK_MQ_REQ_PM, - /* caller might not be interested in sense, but we need it */ - .sshdr = sshdr ? : &my_sshdr, + .sshdr = &sshdr, }; if (!scsi_device_online(sdp)) return -ENODEV; - sshdr = exec_args.sshdr; - for (retries = 3; retries > 0; --retries) { unsigned char cmd[16] = { 0 }; @@ -1685,15 +1682,23 @@ static int sd_sync_cache(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr) return res; if (scsi_status_is_check_condition(res) && - scsi_sense_valid(sshdr)) { - sd_print_sense_hdr(sdkp, sshdr); + scsi_sense_valid(&sshdr)) { + sd_print_sense_hdr(sdkp, &sshdr); /* we need to evaluate the error return */ - if (sshdr->asc == 0x3a || /* medium not present */ - sshdr->asc == 0x20 || /* invalid command */ - (sshdr->asc == 0x74 && sshdr->ascq == 0x71)) /* drive is password locked */ + if (sshdr.asc == 0x3a || /* medium not present */ + sshdr.asc == 0x20 || /* invalid command */ + (sshdr.asc == 0x74 && sshdr.ascq == 0x71)) /* drive is password locked */ /* this is no error here */ return 0; + /* + * This drive doesn't support sync and there's not much + * we can do because this is called during shutdown + * or suspend so just return success so those operations + * can proceed. + */ + if (sshdr.sense_key == ILLEGAL_REQUEST) + return 0; } switch (host_byte(res)) { @@ -3853,7 +3858,7 @@ static void sd_shutdown(struct device *dev) if (sdkp->WCE && sdkp->media_present) { sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n"); - sd_sync_cache(sdkp, NULL); + sd_sync_cache(sdkp); } if ((system_state != SYSTEM_RESTART && @@ -3874,7 +3879,6 @@ static inline bool sd_do_start_stop(struct scsi_device *sdev, bool runtime) static int sd_suspend_common(struct device *dev, bool runtime) { struct scsi_disk *sdkp = dev_get_drvdata(dev); - struct scsi_sense_hdr sshdr; int ret = 0; if (!sdkp) /* E.g.: runtime suspend following sd_remove() */ @@ -3883,24 +3887,13 @@ static int sd_suspend_common(struct device *dev, bool runtime) if (sdkp->WCE && sdkp->media_present) { if (!sdkp->device->silence_suspend) sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n"); - ret = sd_sync_cache(sdkp, &sshdr); - - if (ret) { - /* ignore OFFLINE device */ - if (ret == -ENODEV) - return 0; - - if (!scsi_sense_valid(&sshdr) || - sshdr.sense_key != ILLEGAL_REQUEST) - return ret; + ret = sd_sync_cache(sdkp); + /* ignore OFFLINE device */ + if (ret == -ENODEV) + return 0; - /* - * sshdr.sense_key == ILLEGAL_REQUEST means this drive - * doesn't support sync. There's not much to do and - * suspend shouldn't fail. - */ - ret = 0; - } + if (ret) + return ret; } if (sd_do_start_stop(sdkp->device, runtime)) { diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c index 2ba8ec254dce..0787456c2b89 100644 --- a/drivers/ufs/core/ufs-mcq.c +++ b/drivers/ufs/core/ufs-mcq.c @@ -436,7 +436,7 @@ int ufshcd_mcq_init(struct ufs_hba *hba) for (i = 0; i < hba->nr_hw_queues; i++) { hwq = &hba->uhq[i]; - hwq->max_entries = hba->nutrs; + hwq->max_entries = hba->nutrs + 1; spin_lock_init(&hwq->sq_lock); spin_lock_init(&hwq->cq_lock); mutex_init(&hwq->sq_mutex); @@ -630,6 +630,7 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd) int tag = scsi_cmd_to_rq(cmd)->tag; struct ufshcd_lrb *lrbp = &hba->lrb[tag]; struct ufs_hw_queue *hwq; + unsigned long flags; int err = FAILED; if (!ufshcd_cmd_inflight(lrbp->cmd)) { @@ -670,8 +671,10 @@ int ufshcd_mcq_abort(struct scsi_cmnd *cmd) } err = SUCCESS; + spin_lock_irqsave(&hwq->cq_lock, flags); if (ufshcd_cmd_inflight(lrbp->cmd)) ufshcd_release_scsi_cmd(hba, lrbp); + spin_unlock_irqrestore(&hwq->cq_lock, flags); out: return err; diff --git a/fs/bcachefs/backpointers.c b/fs/bcachefs/backpointers.c index ef02c9bb0354..23c0834a97a4 100644 --- a/fs/bcachefs/backpointers.c +++ b/fs/bcachefs/backpointers.c @@ -313,17 +313,17 @@ struct btree *bch2_backpointer_get_node(struct btree_trans *trans, bp.level - 1, 0); b = bch2_btree_iter_peek_node(iter); - if (IS_ERR(b)) + if (IS_ERR_OR_NULL(b)) goto err; BUG_ON(b->c.level != bp.level - 1); - if (b && extent_matches_bp(c, bp.btree_id, bp.level, - bkey_i_to_s_c(&b->key), - bucket, bp)) + if (extent_matches_bp(c, bp.btree_id, bp.level, + bkey_i_to_s_c(&b->key), + bucket, bp)) return b; - if (b && btree_node_will_make_reachable(b)) { + if (btree_node_will_make_reachable(b)) { b = ERR_PTR(-BCH_ERR_backpointer_to_overwritten_btree_node); } else { backpointer_not_found(trans, bp_pos, bp, bkey_i_to_s_c(&b->key)); diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h index 9cb8684959ee..403aa3389fcc 100644 --- a/fs/bcachefs/bcachefs.h +++ b/fs/bcachefs/bcachefs.h @@ -617,7 +617,7 @@ struct journal_seq_blacklist_table { u64 start; u64 end; bool dirty; - } entries[0]; + } entries[]; }; struct journal_keys { diff --git a/fs/bcachefs/btree_iter.c b/fs/bcachefs/btree_iter.c index c2adf3fbb0b3..6fa90bcd7016 100644 --- a/fs/bcachefs/btree_iter.c +++ b/fs/bcachefs/btree_iter.c @@ -3087,8 +3087,6 @@ void bch2_trans_put(struct btree_trans *trans) srcu_read_unlock(&c->btree_trans_barrier, trans->srcu_idx); } - bch2_journal_preres_put(&c->journal, &trans->journal_preres); - kfree(trans->extra_journal_entries.data); if (trans->fs_usage_deltas) { diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c index 9b78f78a75b5..37fbf22de8fc 100644 --- a/fs/bcachefs/btree_key_cache.c +++ b/fs/bcachefs/btree_key_cache.c @@ -89,10 +89,13 @@ static void bkey_cached_free(struct btree_key_cache *bc, ck->btree_trans_barrier_seq = start_poll_synchronize_srcu(&c->btree_trans_barrier); - if (ck->c.lock.readers) + if (ck->c.lock.readers) { list_move_tail(&ck->list, &bc->freed_pcpu); - else + bc->nr_freed_pcpu++; + } else { list_move_tail(&ck->list, &bc->freed_nonpcpu); + bc->nr_freed_nonpcpu++; + } atomic_long_inc(&bc->nr_freed); kfree(ck->k); @@ -109,6 +112,8 @@ static void __bkey_cached_move_to_freelist_ordered(struct btree_key_cache *bc, { struct bkey_cached *pos; + bc->nr_freed_nonpcpu++; + list_for_each_entry_reverse(pos, &bc->freed_nonpcpu, list) { if (ULONG_CMP_GE(ck->btree_trans_barrier_seq, pos->btree_trans_barrier_seq)) { @@ -158,6 +163,7 @@ static void bkey_cached_move_to_freelist(struct btree_key_cache *bc, #else mutex_lock(&bc->lock); list_move_tail(&ck->list, &bc->freed_nonpcpu); + bc->nr_freed_nonpcpu++; mutex_unlock(&bc->lock); #endif } else { @@ -217,6 +223,7 @@ bkey_cached_alloc(struct btree_trans *trans, struct btree_path *path, f->nr < ARRAY_SIZE(f->objs) / 2) { ck = list_last_entry(&bc->freed_nonpcpu, struct bkey_cached, list); list_del_init(&ck->list); + bc->nr_freed_nonpcpu--; f->objs[f->nr++] = ck; } @@ -229,6 +236,7 @@ bkey_cached_alloc(struct btree_trans *trans, struct btree_path *path, if (!list_empty(&bc->freed_nonpcpu)) { ck = list_last_entry(&bc->freed_nonpcpu, struct bkey_cached, list); list_del_init(&ck->list); + bc->nr_freed_nonpcpu--; } mutex_unlock(&bc->lock); #endif @@ -664,7 +672,6 @@ static int btree_key_cache_flush_pos(struct btree_trans *trans, goto out; bch2_journal_pin_drop(j, &ck->journal); - bch2_journal_preres_put(j, &ck->res); BUG_ON(!btree_node_locked(c_iter.path, 0)); @@ -762,18 +769,6 @@ bool bch2_btree_insert_key_cached(struct btree_trans *trans, BUG_ON(insert->k.u64s > ck->u64s); - if (likely(!(flags & BTREE_INSERT_JOURNAL_REPLAY))) { - int difference; - - BUG_ON(jset_u64s(insert->k.u64s) > trans->journal_preres.u64s); - - difference = jset_u64s(insert->k.u64s) - ck->res.u64s; - if (difference > 0) { - trans->journal_preres.u64s -= difference; - ck->res.u64s += difference; - } - } - bkey_copy(ck->k, insert); ck->valid = true; @@ -850,6 +845,8 @@ static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink, * Newest freed entries are at the end of the list - once we hit one * that's too new to be freed, we can bail out: */ + scanned += bc->nr_freed_nonpcpu; + list_for_each_entry_safe(ck, t, &bc->freed_nonpcpu, list) { if (!poll_state_synchronize_srcu(&c->btree_trans_barrier, ck->btree_trans_barrier_seq)) @@ -859,13 +856,15 @@ static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink, six_lock_exit(&ck->c.lock); kmem_cache_free(bch2_key_cache, ck); atomic_long_dec(&bc->nr_freed); - scanned++; freed++; + bc->nr_freed_nonpcpu--; } if (scanned >= nr) goto out; + scanned += bc->nr_freed_pcpu; + list_for_each_entry_safe(ck, t, &bc->freed_pcpu, list) { if (!poll_state_synchronize_srcu(&c->btree_trans_barrier, ck->btree_trans_barrier_seq)) @@ -875,8 +874,8 @@ static unsigned long bch2_btree_key_cache_scan(struct shrinker *shrink, six_lock_exit(&ck->c.lock); kmem_cache_free(bch2_key_cache, ck); atomic_long_dec(&bc->nr_freed); - scanned++; freed++; + bc->nr_freed_pcpu--; } if (scanned >= nr) @@ -982,6 +981,9 @@ void bch2_fs_btree_key_cache_exit(struct btree_key_cache *bc) } #endif + BUG_ON(list_count_nodes(&bc->freed_pcpu) != bc->nr_freed_pcpu); + BUG_ON(list_count_nodes(&bc->freed_nonpcpu) != bc->nr_freed_nonpcpu); + list_splice(&bc->freed_pcpu, &items); list_splice(&bc->freed_nonpcpu, &items); @@ -991,7 +993,6 @@ void bch2_fs_btree_key_cache_exit(struct btree_key_cache *bc) cond_resched(); bch2_journal_pin_drop(&c->journal, &ck->journal); - bch2_journal_preres_put(&c->journal, &ck->res); list_del(&ck->list); kfree(ck->k); diff --git a/fs/bcachefs/btree_key_cache_types.h b/fs/bcachefs/btree_key_cache_types.h new file mode 100644 index 000000000000..290e4e57df5b --- /dev/null +++ b/fs/bcachefs/btree_key_cache_types.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BCACHEFS_BTREE_KEY_CACHE_TYPES_H +#define _BCACHEFS_BTREE_KEY_CACHE_TYPES_H + +struct btree_key_cache_freelist { + struct bkey_cached *objs[16]; + unsigned nr; +}; + +struct btree_key_cache { + struct mutex lock; + struct rhashtable table; + bool table_init_done; + + struct list_head freed_pcpu; + size_t nr_freed_pcpu; + struct list_head freed_nonpcpu; + size_t nr_freed_nonpcpu; + + struct shrinker *shrink; + unsigned shrink_iter; + struct btree_key_cache_freelist __percpu *pcpu_freed; + + atomic_long_t nr_freed; + atomic_long_t nr_keys; + atomic_long_t nr_dirty; +}; + +struct bkey_cached_key { + u32 btree_id; + struct bpos pos; +} __packed __aligned(4); + +#endif /* _BCACHEFS_BTREE_KEY_CACHE_TYPES_H */ diff --git a/fs/bcachefs/btree_trans_commit.c b/fs/bcachefs/btree_trans_commit.c index decad7b66c59..12907beda98c 100644 --- a/fs/bcachefs/btree_trans_commit.c +++ b/fs/bcachefs/btree_trans_commit.c @@ -78,6 +78,53 @@ inline void bch2_btree_node_prep_for_write(struct btree_trans *trans, bch2_btree_init_next(trans, b); } +static noinline int trans_lock_write_fail(struct btree_trans *trans, struct btree_insert_entry *i) +{ + while (--i >= trans->updates) { + if (same_leaf_as_prev(trans, i)) + continue; + + bch2_btree_node_unlock_write(trans, i->path, insert_l(i)->b); + } + + trace_and_count(trans->c, trans_restart_would_deadlock_write, trans); + return btree_trans_restart(trans, BCH_ERR_transaction_restart_would_deadlock_write); +} + +static inline int bch2_trans_lock_write(struct btree_trans *trans) +{ + struct btree_insert_entry *i; + + EBUG_ON(trans->write_locked); + + trans_for_each_update(trans, i) { + if (same_leaf_as_prev(trans, i)) + continue; + + if (bch2_btree_node_lock_write(trans, i->path, &insert_l(i)->b->c)) + return trans_lock_write_fail(trans, i); + + if (!i->cached) + bch2_btree_node_prep_for_write(trans, i->path, insert_l(i)->b); + } + + trans->write_locked = true; + return 0; +} + +static inline void bch2_trans_unlock_write(struct btree_trans *trans) +{ + if (likely(trans->write_locked)) { + struct btree_insert_entry *i; + + trans_for_each_update(trans, i) + if (!same_leaf_as_prev(trans, i)) + bch2_btree_node_unlock_write_inlined(trans, i->path, + insert_l(i)->b); + trans->write_locked = false; + } +} + /* Inserting into a given leaf node (last stage of insert): */ /* Handle overwrites and do insert, for non extents: */ @@ -276,17 +323,6 @@ static inline void btree_insert_entry_checks(struct btree_trans *trans, bch2_snapshot_is_internal_node(trans->c, i->k->k.p.snapshot)); } -static noinline int -bch2_trans_journal_preres_get_cold(struct btree_trans *trans, unsigned flags, - unsigned long trace_ip) -{ - return drop_locks_do(trans, - bch2_journal_preres_get(&trans->c->journal, - &trans->journal_preres, - trans->journal_preres_u64s, - (flags & BCH_WATERMARK_MASK))); -} - static __always_inline int bch2_trans_journal_res_get(struct btree_trans *trans, unsigned flags) { @@ -321,6 +357,45 @@ static inline int btree_key_can_insert(struct btree_trans *trans, return 0; } +noinline static int +btree_key_can_insert_cached_slowpath(struct btree_trans *trans, unsigned flags, + struct btree_path *path, unsigned new_u64s) +{ + struct bch_fs *c = trans->c; + struct btree_insert_entry *i; + struct bkey_cached *ck = (void *) path->l[0].b; + struct bkey_i *new_k; + int ret; + + bch2_trans_unlock_write(trans); + bch2_trans_unlock(trans); + + new_k = kmalloc(new_u64s * sizeof(u64), GFP_KERNEL); + if (!new_k) { + bch_err(c, "error allocating memory for key cache key, btree %s u64s %u", + bch2_btree_id_str(path->btree_id), new_u64s); + return -BCH_ERR_ENOMEM_btree_key_cache_insert; + } + + ret = bch2_trans_relock(trans) ?: + bch2_trans_lock_write(trans); + if (unlikely(ret)) { + kfree(new_k); + return ret; + } + + memcpy(new_k, ck->k, ck->u64s * sizeof(u64)); + + trans_for_each_update(trans, i) + if (i->old_v == &ck->k->v) + i->old_v = &new_k->v; + + kfree(ck->k); + ck->u64s = new_u64s; + ck->k = new_k; + return 0; +} + static int btree_key_can_insert_cached(struct btree_trans *trans, unsigned flags, struct btree_path *path, unsigned u64s) { @@ -347,12 +422,9 @@ static int btree_key_can_insert_cached(struct btree_trans *trans, unsigned flags return 0; new_u64s = roundup_pow_of_two(u64s); - new_k = krealloc(ck->k, new_u64s * sizeof(u64), GFP_NOFS); - if (!new_k) { - bch_err(c, "error allocating memory for key cache key, btree %s u64s %u", - bch2_btree_id_str(path->btree_id), new_u64s); - return -BCH_ERR_ENOMEM_btree_key_cache_insert; - } + new_k = krealloc(ck->k, new_u64s * sizeof(u64), GFP_NOWAIT); + if (unlikely(!new_k)) + return btree_key_can_insert_cached_slowpath(trans, flags, path, new_u64s); trans_for_each_update(trans, i) if (i->old_v == &ck->k->v) @@ -732,37 +804,6 @@ revert_fs_usage: return ret; } -static noinline int trans_lock_write_fail(struct btree_trans *trans, struct btree_insert_entry *i) -{ - while (--i >= trans->updates) { - if (same_leaf_as_prev(trans, i)) - continue; - - bch2_btree_node_unlock_write(trans, i->path, insert_l(i)->b); - } - - trace_and_count(trans->c, trans_restart_would_deadlock_write, trans); - return btree_trans_restart(trans, BCH_ERR_transaction_restart_would_deadlock_write); -} - -static inline int trans_lock_write(struct btree_trans *trans) -{ - struct btree_insert_entry *i; - - trans_for_each_update(trans, i) { - if (same_leaf_as_prev(trans, i)) - continue; - - if (bch2_btree_node_lock_write(trans, i->path, &insert_l(i)->b->c)) - return trans_lock_write_fail(trans, i); - - if (!i->cached) - bch2_btree_node_prep_for_write(trans, i->path, insert_l(i)->b); - } - - return 0; -} - static noinline void bch2_drop_overwrites_from_journal(struct btree_trans *trans) { struct btree_insert_entry *i; @@ -830,15 +871,7 @@ static inline int do_bch2_trans_commit(struct btree_trans *trans, unsigned flags } } - ret = bch2_journal_preres_get(&c->journal, - &trans->journal_preres, trans->journal_preres_u64s, - (flags & BCH_WATERMARK_MASK)|JOURNAL_RES_GET_NONBLOCK); - if (unlikely(ret == -BCH_ERR_journal_preres_get_blocked)) - ret = bch2_trans_journal_preres_get_cold(trans, flags, trace_ip); - if (unlikely(ret)) - return ret; - - ret = trans_lock_write(trans); + ret = bch2_trans_lock_write(trans); if (unlikely(ret)) return ret; @@ -847,10 +880,7 @@ static inline int do_bch2_trans_commit(struct btree_trans *trans, unsigned flags if (!ret && unlikely(trans->journal_replay_not_finished)) bch2_drop_overwrites_from_journal(trans); - trans_for_each_update(trans, i) - if (!same_leaf_as_prev(trans, i)) - bch2_btree_node_unlock_write_inlined(trans, i->path, - insert_l(i)->b); + bch2_trans_unlock_write(trans); if (!ret && trans->journal_pin) bch2_journal_pin_add(&c->journal, trans->journal_res.seq, @@ -1003,7 +1033,6 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags) struct bch_fs *c = trans->c; struct btree_insert_entry *i = NULL; struct btree_write_buffered_key *wb; - unsigned u64s; int ret = 0; if (!trans->nr_updates && @@ -1063,13 +1092,8 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags) EBUG_ON(test_bit(BCH_FS_CLEAN_SHUTDOWN, &c->flags)); - memset(&trans->journal_preres, 0, sizeof(trans->journal_preres)); - trans->journal_u64s = trans->extra_journal_entries.nr; - trans->journal_preres_u64s = 0; - trans->journal_transaction_names = READ_ONCE(c->opts.journal_transaction_names); - if (trans->journal_transaction_names) trans->journal_u64s += jset_u64s(JSET_ENTRY_LOG_U64s); @@ -1085,16 +1109,11 @@ int __bch2_trans_commit(struct btree_trans *trans, unsigned flags) if (i->key_cache_already_flushed) continue; - /* we're going to journal the key being updated: */ - u64s = jset_u64s(i->k->k.u64s); - if (i->cached && - likely(!(flags & BTREE_INSERT_JOURNAL_REPLAY))) - trans->journal_preres_u64s += u64s; - if (i->flags & BTREE_UPDATE_NOJOURNAL) continue; - trans->journal_u64s += u64s; + /* we're going to journal the key being updated: */ + trans->journal_u64s += jset_u64s(i->k->k.u64s); /* and we're also going to log the overwrite: */ if (trans->journal_transaction_names) @@ -1126,8 +1145,6 @@ retry: trace_and_count(c, transaction_commit, trans, _RET_IP_); out: - bch2_journal_preres_put(&c->journal, &trans->journal_preres); - if (likely(!(flags & BTREE_INSERT_NOCHECK_RW))) bch2_write_ref_put(c, BCH_WRITE_REF_trans); out_reset: diff --git a/fs/bcachefs/btree_types.h b/fs/bcachefs/btree_types.h index 941841a0c5bf..60453ba86c4b 100644 --- a/fs/bcachefs/btree_types.h +++ b/fs/bcachefs/btree_types.h @@ -5,7 +5,7 @@ #include <linux/list.h> #include <linux/rhashtable.h> -//#include "bkey_methods.h" +#include "btree_key_cache_types.h" #include "buckets_types.h" #include "darray.h" #include "errcode.h" @@ -312,31 +312,6 @@ struct btree_iter { #endif }; -struct btree_key_cache_freelist { - struct bkey_cached *objs[16]; - unsigned nr; -}; - -struct btree_key_cache { - struct mutex lock; - struct rhashtable table; - bool table_init_done; - struct list_head freed_pcpu; - struct list_head freed_nonpcpu; - struct shrinker *shrink; - unsigned shrink_iter; - struct btree_key_cache_freelist __percpu *pcpu_freed; - - atomic_long_t nr_freed; - atomic_long_t nr_keys; - atomic_long_t nr_dirty; -}; - -struct bkey_cached_key { - u32 btree_id; - struct bpos pos; -} __packed __aligned(4); - #define BKEY_CACHED_ACCESSED 0 #define BKEY_CACHED_DIRTY 1 @@ -352,7 +327,6 @@ struct bkey_cached { struct rhash_head hash; struct list_head list; - struct journal_preres res; struct journal_entry_pin journal; u64 seq; @@ -389,11 +363,7 @@ struct btree_insert_entry { unsigned long ip_allocated; }; -#ifndef CONFIG_LOCKDEP #define BTREE_ITER_MAX 64 -#else -#define BTREE_ITER_MAX 32 -#endif struct btree_trans_commit_hook; typedef int (btree_trans_commit_hook_fn)(struct btree_trans *, struct btree_trans_commit_hook *); @@ -434,6 +404,7 @@ struct btree_trans { bool journal_transaction_names:1; bool journal_replay_not_finished:1; bool notrace_relock_fail:1; + bool write_locked:1; enum bch_errcode restarted:16; u32 restart_count; unsigned long last_begin_ip; @@ -465,11 +436,9 @@ struct btree_trans { struct journal_entry_pin *journal_pin; struct journal_res journal_res; - struct journal_preres journal_preres; u64 *journal_seq; struct disk_reservation *disk_res; unsigned journal_u64s; - unsigned journal_preres_u64s; struct replicas_delta_list *fs_usage_deltas; }; diff --git a/fs/bcachefs/btree_update_interior.c b/fs/bcachefs/btree_update_interior.c index 39c2db68123b..76f27bc9fa24 100644 --- a/fs/bcachefs/btree_update_interior.c +++ b/fs/bcachefs/btree_update_interior.c @@ -513,8 +513,6 @@ static void bch2_btree_update_free(struct btree_update *as, struct btree_trans * up_read(&c->gc_lock); as->took_gc_lock = false; - bch2_journal_preres_put(&c->journal, &as->journal_preres); - bch2_journal_pin_drop(&c->journal, &as->journal); bch2_journal_pin_flush(&c->journal, &as->journal); bch2_disk_reservation_put(c, &as->disk_res); @@ -734,8 +732,6 @@ err: bch2_journal_pin_drop(&c->journal, &as->journal); - bch2_journal_preres_put(&c->journal, &as->journal_preres); - mutex_lock(&c->btree_interior_update_lock); for (i = 0; i < as->nr_new_nodes; i++) { b = as->new_nodes[i]; @@ -1047,7 +1043,6 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path, unsigned nr_nodes[2] = { 0, 0 }; unsigned update_level = level; enum bch_watermark watermark = flags & BCH_WATERMARK_MASK; - unsigned journal_flags = 0; int ret = 0; u32 restart_count = trans->restart_count; @@ -1061,10 +1056,6 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path, flags &= ~BCH_WATERMARK_MASK; flags |= watermark; - if (flags & BTREE_INSERT_JOURNAL_RECLAIM) - journal_flags |= JOURNAL_RES_GET_NONBLOCK; - journal_flags |= watermark; - while (1) { nr_nodes[!!update_level] += 1 + split; update_level++; @@ -1129,27 +1120,6 @@ bch2_btree_update_start(struct btree_trans *trans, struct btree_path *path, if (ret) goto err; - ret = bch2_journal_preres_get(&c->journal, &as->journal_preres, - BTREE_UPDATE_JOURNAL_RES, - journal_flags|JOURNAL_RES_GET_NONBLOCK); - if (ret) { - if (flags & BTREE_INSERT_JOURNAL_RECLAIM) { - ret = -BCH_ERR_journal_reclaim_would_deadlock; - goto err; - } - - ret = drop_locks_do(trans, - bch2_journal_preres_get(&c->journal, &as->journal_preres, - BTREE_UPDATE_JOURNAL_RES, - journal_flags)); - if (ret == -BCH_ERR_journal_preres_get_blocked) { - trace_and_count(c, trans_restart_journal_preres_get, trans, _RET_IP_, journal_flags); - ret = btree_trans_restart(trans, BCH_ERR_transaction_restart_journal_preres_get); - } - if (ret) - goto err; - } - ret = bch2_disk_reservation_get(c, &as->disk_res, (nr_nodes[0] + nr_nodes[1]) * btree_sectors(c), c->opts.metadata_replicas, diff --git a/fs/bcachefs/btree_update_interior.h b/fs/bcachefs/btree_update_interior.h index 4df21512d640..031076e75fa1 100644 --- a/fs/bcachefs/btree_update_interior.h +++ b/fs/bcachefs/btree_update_interior.h @@ -55,7 +55,6 @@ struct btree_update { unsigned update_level; struct disk_reservation disk_res; - struct journal_preres journal_preres; /* * BTREE_INTERIOR_UPDATING_NODE: diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c index 0771a6d880bf..5ed66202c226 100644 --- a/fs/bcachefs/data_update.c +++ b/fs/bcachefs/data_update.c @@ -239,6 +239,34 @@ restart_drop_extra_replicas: next_pos = insert->k.p; + /* + * Check for nonce offset inconsistency: + * This is debug code - we've been seeing this bug rarely, and + * it's been hard to reproduce, so this should give us some more + * information when it does occur: + */ + struct printbuf err = PRINTBUF; + int invalid = bch2_bkey_invalid(c, bkey_i_to_s_c(insert), __btree_node_type(0, m->btree_id), 0, &err); + printbuf_exit(&err); + + if (invalid) { + struct printbuf buf = PRINTBUF; + + prt_str(&buf, "about to insert invalid key in data update path"); + prt_str(&buf, "\nold: "); + bch2_bkey_val_to_text(&buf, c, old); + prt_str(&buf, "\nk: "); + bch2_bkey_val_to_text(&buf, c, k); + prt_str(&buf, "\nnew: "); + bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(insert)); + + bch2_print_string_as_lines(KERN_ERR, buf.buf); + printbuf_exit(&buf); + + bch2_fatal_error(c); + goto out; + } + ret = bch2_insert_snapshot_whiteouts(trans, m->btree_id, k.k->p, bkey_start_pos(&insert->k)) ?: bch2_insert_snapshot_whiteouts(trans, m->btree_id, diff --git a/fs/bcachefs/disk_groups.c b/fs/bcachefs/disk_groups.c index d613695abf9f..4d0cb0ccff32 100644 --- a/fs/bcachefs/disk_groups.c +++ b/fs/bcachefs/disk_groups.c @@ -555,6 +555,7 @@ void bch2_target_to_text(struct printbuf *out, struct bch_fs *c, unsigned v) case TARGET_DEV: { struct bch_dev *ca; + out->atomic++; rcu_read_lock(); ca = t.dev < c->sb.nr_devices ? rcu_dereference(c->devs[t.dev]) @@ -570,6 +571,7 @@ void bch2_target_to_text(struct printbuf *out, struct bch_fs *c, unsigned v) } rcu_read_unlock(); + out->atomic--; break; } case TARGET_GROUP: @@ -580,7 +582,7 @@ void bch2_target_to_text(struct printbuf *out, struct bch_fs *c, unsigned v) } } -void bch2_target_to_text_sb(struct printbuf *out, struct bch_sb *sb, unsigned v) +static void bch2_target_to_text_sb(struct printbuf *out, struct bch_sb *sb, unsigned v) { struct target t = target_decode(v); diff --git a/fs/bcachefs/ec.c b/fs/bcachefs/ec.c index 875f7c5a6fca..2a77de18c004 100644 --- a/fs/bcachefs/ec.c +++ b/fs/bcachefs/ec.c @@ -1373,6 +1373,15 @@ ec_new_stripe_head_alloc(struct bch_fs *c, unsigned target, h->nr_active_devs++; rcu_read_unlock(); + + /* + * If we only have redundancy + 1 devices, we're better off with just + * replication: + */ + if (h->nr_active_devs < h->redundancy + 2) + bch_err(c, "insufficient devices available to create stripe (have %u, need %u) - mismatched bucket sizes?", + h->nr_active_devs, h->redundancy + 2); + list_add(&h->list, &c->ec_stripe_head_list); return h; } @@ -1424,6 +1433,11 @@ __bch2_ec_stripe_head_get(struct btree_trans *trans, h = ec_new_stripe_head_alloc(c, target, algo, redundancy, watermark); found: + if (!IS_ERR_OR_NULL(h) && + h->nr_active_devs < h->redundancy + 2) { + mutex_unlock(&h->lock); + h = NULL; + } mutex_unlock(&c->ec_stripe_head_lock); return h; } @@ -1681,8 +1695,6 @@ struct ec_stripe_head *bch2_ec_stripe_head_get(struct btree_trans *trans, int ret; h = __bch2_ec_stripe_head_get(trans, target, algo, redundancy, watermark); - if (!h) - bch_err(c, "no stripe head"); if (IS_ERR_OR_NULL(h)) return h; diff --git a/fs/bcachefs/fs-io-pagecache.c b/fs/bcachefs/fs-io-pagecache.c index 8bd9bcdd27f7..ff664fd0d8ef 100644 --- a/fs/bcachefs/fs-io-pagecache.c +++ b/fs/bcachefs/fs-io-pagecache.c @@ -13,7 +13,7 @@ int bch2_filemap_get_contig_folios_d(struct address_space *mapping, loff_t start, u64 end, - int fgp_flags, gfp_t gfp, + fgf_t fgp_flags, gfp_t gfp, folios *fs) { struct folio *f; diff --git a/fs/bcachefs/fs-io-pagecache.h b/fs/bcachefs/fs-io-pagecache.h index a2222ad586e9..27f712ae37a6 100644 --- a/fs/bcachefs/fs-io-pagecache.h +++ b/fs/bcachefs/fs-io-pagecache.h @@ -7,7 +7,7 @@ typedef DARRAY(struct folio *) folios; int bch2_filemap_get_contig_folios_d(struct address_space *, loff_t, - u64, int, gfp_t, folios *); + u64, fgf_t, gfp_t, folios *); int bch2_write_invalidate_inode_pages_range(struct address_space *, loff_t, loff_t); /* diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c index 166d8d8abe68..8ef817304e4a 100644 --- a/fs/bcachefs/fs.c +++ b/fs/bcachefs/fs.c @@ -1922,10 +1922,7 @@ out: return dget(sb->s_root); err_put_super: - sb->s_fs_info = NULL; - c->vfs_sb = NULL; deactivate_locked_super(sb); - bch2_fs_stop(c); return ERR_PTR(bch2_err_class(ret)); } @@ -1933,11 +1930,8 @@ static void bch2_kill_sb(struct super_block *sb) { struct bch_fs *c = sb->s_fs_info; - if (c) - c->vfs_sb = NULL; generic_shutdown_super(sb); - if (c) - bch2_fs_free(c); + bch2_fs_free(c); } static struct file_system_type bcache_fs_type = { diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c index 9f3e9bd3d767..e0c5cd119acc 100644 --- a/fs/bcachefs/fsck.c +++ b/fs/bcachefs/fsck.c @@ -2220,7 +2220,7 @@ static int nlink_cmp(const void *_l, const void *_r) const struct nlink *l = _l; const struct nlink *r = _r; - return cmp_int(l->inum, r->inum) ?: cmp_int(l->snapshot, r->snapshot); + return cmp_int(l->inum, r->inum); } static void inc_link(struct bch_fs *c, struct snapshots_seen *s, diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c index def77f2d8802..c7849b0753e7 100644 --- a/fs/bcachefs/inode.c +++ b/fs/bcachefs/inode.c @@ -1134,7 +1134,7 @@ static int may_delete_deleted_inode(struct btree_trans *trans, * unlinked inodes in the snapshot leaves: */ *need_another_pass = true; - return 0; + goto out; } ret = 1; @@ -1169,8 +1169,10 @@ again: */ for_each_btree_key(trans, iter, BTREE_ID_deleted_inodes, POS_MIN, BTREE_ITER_PREFETCH|BTREE_ITER_ALL_SNAPSHOTS, k, ret) { - ret = lockrestart_do(trans, may_delete_deleted_inode(trans, &iter, k.k->p, - &need_another_pass)); + ret = commit_do(trans, NULL, NULL, + BTREE_INSERT_NOFAIL| + BTREE_INSERT_LAZY_RW, + may_delete_deleted_inode(trans, &iter, k.k->p, &need_another_pass)); if (ret < 0) break; diff --git a/fs/bcachefs/io_write.c b/fs/bcachefs/io_write.c index f02b3f7d26a0..d704a8f829c8 100644 --- a/fs/bcachefs/io_write.c +++ b/fs/bcachefs/io_write.c @@ -795,7 +795,7 @@ static int bch2_write_decrypt(struct bch_write_op *op) * checksum: */ csum = bch2_checksum_bio(c, op->crc.csum_type, nonce, &op->wbio.bio); - if (bch2_crc_cmp(op->crc.csum, csum)) + if (bch2_crc_cmp(op->crc.csum, csum) && !c->opts.no_data_io) return -EIO; ret = bch2_encrypt_bio(c, op->crc.csum_type, nonce, &op->wbio.bio); diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c index 5b5d69f2316b..23a9b7845d11 100644 --- a/fs/bcachefs/journal.c +++ b/fs/bcachefs/journal.c @@ -526,36 +526,6 @@ int bch2_journal_res_get_slowpath(struct journal *j, struct journal_res *res, return ret; } -/* journal_preres: */ - -static bool journal_preres_available(struct journal *j, - struct journal_preres *res, - unsigned new_u64s, - unsigned flags) -{ - bool ret = bch2_journal_preres_get_fast(j, res, new_u64s, flags, true); - - if (!ret && mutex_trylock(&j->reclaim_lock)) { - bch2_journal_reclaim(j); - mutex_unlock(&j->reclaim_lock); - } - - return ret; -} - -int __bch2_journal_preres_get(struct journal *j, - struct journal_preres *res, - unsigned new_u64s, - unsigned flags) -{ - int ret; - - closure_wait_event(&j->preres_wait, - (ret = bch2_journal_error(j)) || - journal_preres_available(j, res, new_u64s, flags)); - return ret; -} - /* journal_entry_res: */ void bch2_journal_entry_res_resize(struct journal *j, @@ -1306,7 +1276,6 @@ void __bch2_journal_debug_to_text(struct printbuf *out, struct journal *j) prt_printf(out, "last_seq:\t\t%llu\n", journal_last_seq(j)); prt_printf(out, "last_seq_ondisk:\t%llu\n", j->last_seq_ondisk); prt_printf(out, "flushed_seq_ondisk:\t%llu\n", j->flushed_seq_ondisk); - prt_printf(out, "prereserved:\t\t%u/%u\n", j->prereserved.reserved, j->prereserved.remaining); prt_printf(out, "watermark:\t\t%s\n", bch2_watermarks[j->watermark]); prt_printf(out, "each entry reserved:\t%u\n", j->entry_u64s_reserved); prt_printf(out, "nr flush writes:\t%llu\n", j->nr_flush_writes); diff --git a/fs/bcachefs/journal.h b/fs/bcachefs/journal.h index 011711e99c8d..c85d01cf4948 100644 --- a/fs/bcachefs/journal.h +++ b/fs/bcachefs/journal.h @@ -395,104 +395,6 @@ out: return 0; } -/* journal_preres: */ - -static inline void journal_set_watermark(struct journal *j) -{ - union journal_preres_state s = READ_ONCE(j->prereserved); - unsigned watermark = BCH_WATERMARK_stripe; - - if (fifo_free(&j->pin) < j->pin.size / 4) - watermark = max_t(unsigned, watermark, BCH_WATERMARK_copygc); - if (fifo_free(&j->pin) < j->pin.size / 8) - watermark = max_t(unsigned, watermark, BCH_WATERMARK_reclaim); - - if (s.reserved > s.remaining) - watermark = max_t(unsigned, watermark, BCH_WATERMARK_copygc); - if (!s.remaining) - watermark = max_t(unsigned, watermark, BCH_WATERMARK_reclaim); - - if (watermark == j->watermark) - return; - - swap(watermark, j->watermark); - if (watermark > j->watermark) - journal_wake(j); -} - -static inline void bch2_journal_preres_put(struct journal *j, - struct journal_preres *res) -{ - union journal_preres_state s = { .reserved = res->u64s }; - - if (!res->u64s) - return; - - s.v = atomic64_sub_return(s.v, &j->prereserved.counter); - res->u64s = 0; - - if (unlikely(s.waiting)) { - clear_bit(ilog2((((union journal_preres_state) { .waiting = 1 }).v)), - (unsigned long *) &j->prereserved.v); - closure_wake_up(&j->preres_wait); - } - - if (s.reserved <= s.remaining && j->watermark) - journal_set_watermark(j); -} - -int __bch2_journal_preres_get(struct journal *, - struct journal_preres *, unsigned, unsigned); - -static inline int bch2_journal_preres_get_fast(struct journal *j, - struct journal_preres *res, - unsigned new_u64s, - unsigned flags, - bool set_waiting) -{ - int d = new_u64s - res->u64s; - union journal_preres_state old, new; - u64 v = atomic64_read(&j->prereserved.counter); - enum bch_watermark watermark = flags & BCH_WATERMARK_MASK; - int ret; - - do { - old.v = new.v = v; - ret = 0; - - if (watermark == BCH_WATERMARK_reclaim || - new.reserved + d < new.remaining) { - new.reserved += d; - ret = 1; - } else if (set_waiting && !new.waiting) - new.waiting = true; - else - return 0; - } while ((v = atomic64_cmpxchg(&j->prereserved.counter, - old.v, new.v)) != old.v); - - if (ret) - res->u64s += d; - return ret; -} - -static inline int bch2_journal_preres_get(struct journal *j, - struct journal_preres *res, - unsigned new_u64s, - unsigned flags) -{ - if (new_u64s <= res->u64s) - return 0; - - if (bch2_journal_preres_get_fast(j, res, new_u64s, flags, false)) - return 0; - - if (flags & JOURNAL_RES_GET_NONBLOCK) - return -BCH_ERR_journal_preres_get_blocked; - - return __bch2_journal_preres_get(j, res, new_u64s, flags); -} - /* journal_entry_res: */ void bch2_journal_entry_res_resize(struct journal *, diff --git a/fs/bcachefs/journal_io.c b/fs/bcachefs/journal_io.c index f4bc2cdbfdd7..786a09285509 100644 --- a/fs/bcachefs/journal_io.c +++ b/fs/bcachefs/journal_io.c @@ -1079,6 +1079,12 @@ found: if (ja->bucket_seq[ja->cur_idx] && ja->sectors_free == ca->mi.bucket_size) { +#if 0 + /* + * Debug code for ZNS support, where we (probably) want to be + * correlated where we stopped in the journal to the zone write + * points: + */ bch_err(c, "ja->sectors_free == ca->mi.bucket_size"); bch_err(c, "cur_idx %u/%u", ja->cur_idx, ja->nr); for (i = 0; i < 3; i++) { @@ -1086,6 +1092,7 @@ found: bch_err(c, "bucket_seq[%u] = %llu", idx, ja->bucket_seq[idx]); } +#endif ja->sectors_free = 0; } diff --git a/fs/bcachefs/journal_reclaim.c b/fs/bcachefs/journal_reclaim.c index 9a584aaaa2eb..e63c6eda86af 100644 --- a/fs/bcachefs/journal_reclaim.c +++ b/fs/bcachefs/journal_reclaim.c @@ -50,16 +50,21 @@ unsigned bch2_journal_dev_buckets_available(struct journal *j, return available; } -static void journal_set_remaining(struct journal *j, unsigned u64s_remaining) +static inline void journal_set_watermark(struct journal *j, bool low_on_space) { - union journal_preres_state old, new; - u64 v = atomic64_read(&j->prereserved.counter); + unsigned watermark = BCH_WATERMARK_stripe; - do { - old.v = new.v = v; - new.remaining = u64s_remaining; - } while ((v = atomic64_cmpxchg(&j->prereserved.counter, - old.v, new.v)) != old.v); + if (low_on_space) + watermark = max_t(unsigned, watermark, BCH_WATERMARK_reclaim); + if (fifo_free(&j->pin) < j->pin.size / 4) + watermark = max_t(unsigned, watermark, BCH_WATERMARK_reclaim); + + if (watermark == j->watermark) + return; + + swap(watermark, j->watermark); + if (watermark > j->watermark) + journal_wake(j); } static struct journal_space @@ -162,7 +167,6 @@ void bch2_journal_space_available(struct journal *j) struct bch_fs *c = container_of(j, struct bch_fs, journal); struct bch_dev *ca; unsigned clean, clean_ondisk, total; - s64 u64s_remaining = 0; unsigned max_entry_size = min(j->buf[0].buf_size >> 9, j->buf[1].buf_size >> 9); unsigned i, nr_online = 0, nr_devs_want; @@ -222,16 +226,10 @@ void bch2_journal_space_available(struct journal *j) else clear_bit(JOURNAL_MAY_SKIP_FLUSH, &j->flags); - u64s_remaining = (u64) clean << 6; - u64s_remaining -= (u64) total << 3; - u64s_remaining = max(0LL, u64s_remaining); - u64s_remaining /= 4; - u64s_remaining = min_t(u64, u64s_remaining, U32_MAX); + journal_set_watermark(j, clean * 4 <= total); out: j->cur_entry_sectors = !ret ? j->space[journal_space_discarded].next_entry : 0; j->cur_entry_error = ret; - journal_set_remaining(j, u64s_remaining); - journal_set_watermark(j); if (!ret) journal_wake(j); @@ -555,11 +553,6 @@ static u64 journal_seq_to_flush(struct journal *j) /* Try to keep the journal at most half full: */ nr_buckets = ja->nr / 2; - /* And include pre-reservations: */ - nr_buckets += DIV_ROUND_UP(j->prereserved.reserved, - (ca->mi.bucket_size << 6) - - journal_entry_overhead(j)); - nr_buckets = min(nr_buckets, ja->nr); bucket_to_flush = (ja->cur_idx + nr_buckets) % ja->nr; @@ -638,10 +631,7 @@ static int __bch2_journal_reclaim(struct journal *j, bool direct, bool kicked) msecs_to_jiffies(c->opts.journal_reclaim_delay))) min_nr = 1; - if (j->prereserved.reserved * 4 > j->prereserved.remaining) - min_nr = 1; - - if (fifo_free(&j->pin) <= 32) + if (j->watermark != BCH_WATERMARK_stripe) min_nr = 1; if (atomic_read(&c->btree_cache.dirty) * 2 > c->btree_cache.used) @@ -652,8 +642,6 @@ static int __bch2_journal_reclaim(struct journal *j, bool direct, bool kicked) trace_and_count(c, journal_reclaim_start, c, direct, kicked, min_nr, min_key_cache, - j->prereserved.reserved, - j->prereserved.remaining, atomic_read(&c->btree_cache.dirty), c->btree_cache.used, atomic_long_read(&c->btree_key_cache.nr_dirty), diff --git a/fs/bcachefs/journal_types.h b/fs/bcachefs/journal_types.h index 42504e16acb6..a756b69582e3 100644 --- a/fs/bcachefs/journal_types.h +++ b/fs/bcachefs/journal_types.h @@ -76,14 +76,6 @@ struct journal_res { u64 seq; }; -/* - * For reserving space in the journal prior to getting a reservation on a - * particular journal entry: - */ -struct journal_preres { - unsigned u64s; -}; - union journal_res_state { struct { atomic64_t counter; @@ -104,22 +96,6 @@ union journal_res_state { }; }; -union journal_preres_state { - struct { - atomic64_t counter; - }; - - struct { - u64 v; - }; - - struct { - u64 waiting:1, - reserved:31, - remaining:32; - }; -}; - /* bytes: */ #define JOURNAL_ENTRY_SIZE_MIN (64U << 10) /* 64k */ #define JOURNAL_ENTRY_SIZE_MAX (4U << 20) /* 4M */ @@ -180,8 +156,6 @@ struct journal { union journal_res_state reservations; enum bch_watermark watermark; - union journal_preres_state prereserved; - } __aligned(SMP_CACHE_BYTES); unsigned long flags; diff --git a/fs/bcachefs/six.c b/fs/bcachefs/six.c index b775cf0fb7cb..97790445e67a 100644 --- a/fs/bcachefs/six.c +++ b/fs/bcachefs/six.c @@ -163,8 +163,11 @@ static int __do_six_trylock(struct six_lock *lock, enum six_lock_type type, this_cpu_sub(*lock->readers, !ret); preempt_enable(); - if (!ret && (old & SIX_LOCK_WAITING_write)) - ret = -1 - SIX_LOCK_write; + if (!ret) { + smp_mb(); + if (atomic_read(&lock->state) & SIX_LOCK_WAITING_write) + ret = -1 - SIX_LOCK_write; + } } else if (type == SIX_LOCK_write && lock->readers) { if (try) { atomic_add(SIX_LOCK_HELD_write, &lock->state); diff --git a/fs/bcachefs/subvolume_types.h b/fs/bcachefs/subvolume_types.h index 86833445af20..2d2e66a4e468 100644 --- a/fs/bcachefs/subvolume_types.h +++ b/fs/bcachefs/subvolume_types.h @@ -20,7 +20,7 @@ struct snapshot_t { }; struct snapshot_table { - struct snapshot_t s[0]; + DECLARE_FLEX_ARRAY(struct snapshot_t, s); }; typedef struct { diff --git a/fs/bcachefs/trace.h b/fs/bcachefs/trace.h index 893304a1f06e..7857671159b4 100644 --- a/fs/bcachefs/trace.h +++ b/fs/bcachefs/trace.h @@ -196,10 +196,9 @@ DEFINE_EVENT(bio, journal_write, TRACE_EVENT(journal_reclaim_start, TP_PROTO(struct bch_fs *c, bool direct, bool kicked, u64 min_nr, u64 min_key_cache, - u64 prereserved, u64 prereserved_total, u64 btree_cache_dirty, u64 btree_cache_total, u64 btree_key_cache_dirty, u64 btree_key_cache_total), - TP_ARGS(c, direct, kicked, min_nr, min_key_cache, prereserved, prereserved_total, + TP_ARGS(c, direct, kicked, min_nr, min_key_cache, btree_cache_dirty, btree_cache_total, btree_key_cache_dirty, btree_key_cache_total), @@ -209,8 +208,6 @@ TRACE_EVENT(journal_reclaim_start, __field(bool, kicked ) __field(u64, min_nr ) __field(u64, min_key_cache ) - __field(u64, prereserved ) - __field(u64, prereserved_total ) __field(u64, btree_cache_dirty ) __field(u64, btree_cache_total ) __field(u64, btree_key_cache_dirty ) @@ -223,22 +220,18 @@ TRACE_EVENT(journal_reclaim_start, __entry->kicked = kicked; __entry->min_nr = min_nr; __entry->min_key_cache = min_key_cache; - __entry->prereserved = prereserved; - __entry->prereserved_total = prereserved_total; __entry->btree_cache_dirty = btree_cache_dirty; __entry->btree_cache_total = btree_cache_total; __entry->btree_key_cache_dirty = btree_key_cache_dirty; __entry->btree_key_cache_total = btree_key_cache_total; ), - TP_printk("%d,%d direct %u kicked %u min %llu key cache %llu prereserved %llu/%llu btree cache %llu/%llu key cache %llu/%llu", + TP_printk("%d,%d direct %u kicked %u min %llu key cache %llu btree cache %llu/%llu key cache %llu/%llu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->direct, __entry->kicked, __entry->min_nr, __entry->min_key_cache, - __entry->prereserved, - __entry->prereserved_total, __entry->btree_cache_dirty, __entry->btree_cache_total, __entry->btree_key_cache_dirty, diff --git a/fs/bcachefs/xattr.c b/fs/bcachefs/xattr.c index a39ff0c296ec..79d982674c18 100644 --- a/fs/bcachefs/xattr.c +++ b/fs/bcachefs/xattr.c @@ -552,6 +552,14 @@ static int bch2_xattr_bcachefs_set(const struct xattr_handler *handler, s.v = v + 1; s.defined = true; } else { + /* + * Check if this option was set on the parent - if so, switched + * back to inheriting from the parent: + * + * rename() also has to deal with keeping inherited options up + * to date - see bch2_reinherit_attrs() + */ + spin_lock(&dentry->d_lock); if (!IS_ROOT(dentry)) { struct bch_inode_info *dir = to_bch_ei(d_inode(dentry->d_parent)); @@ -560,6 +568,7 @@ static int bch2_xattr_bcachefs_set(const struct xattr_handler *handler, } else { s.v = 0; } + spin_unlock(&dentry->d_lock); s.defined = false; } diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig index e540648dedc2..1d318f85232d 100644 --- a/fs/erofs/Kconfig +++ b/fs/erofs/Kconfig @@ -21,7 +21,7 @@ config EROFS_FS performance under extremely memory pressure without extra cost. See the documentation at <file:Documentation/filesystems/erofs.rst> - for more details. + and the web pages at <https://erofs.docs.kernel.org> for more details. If unsure, say N. diff --git a/fs/erofs/data.c b/fs/erofs/data.c index 029c761670bf..c98aeda8abb2 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -220,7 +220,7 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) up_read(&devs->rwsem); return 0; } - map->m_bdev = dif->bdev_handle->bdev; + map->m_bdev = dif->bdev_handle ? dif->bdev_handle->bdev : NULL; map->m_daxdev = dif->dax_dev; map->m_dax_part_off = dif->dax_part_off; map->m_fscache = dif->fscache; @@ -238,7 +238,8 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) if (map->m_pa >= startoff && map->m_pa < startoff + length) { map->m_pa -= startoff; - map->m_bdev = dif->bdev_handle->bdev; + map->m_bdev = dif->bdev_handle ? + dif->bdev_handle->bdev : NULL; map->m_daxdev = dif->dax_dev; map->m_dax_part_off = dif->dax_part_off; map->m_fscache = dif->fscache; diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c index b8ad05b4509d..14a79d3226ab 100644 --- a/fs/erofs/inode.c +++ b/fs/erofs/inode.c @@ -15,11 +15,11 @@ static void *erofs_read_inode(struct erofs_buf *buf, struct erofs_sb_info *sbi = EROFS_SB(sb); struct erofs_inode *vi = EROFS_I(inode); const erofs_off_t inode_loc = erofs_iloc(inode); - erofs_blk_t blkaddr, nblks = 0; void *kaddr; struct erofs_inode_compact *dic; struct erofs_inode_extended *die, *copied = NULL; + union erofs_inode_i_u iu; unsigned int ifmt; int err; @@ -35,9 +35,8 @@ static void *erofs_read_inode(struct erofs_buf *buf, dic = kaddr + *ofs; ifmt = le16_to_cpu(dic->i_format); - if (ifmt & ~EROFS_I_ALL) { - erofs_err(inode->i_sb, "unsupported i_format %u of nid %llu", + erofs_err(sb, "unsupported i_format %u of nid %llu", ifmt, vi->nid); err = -EOPNOTSUPP; goto err_out; @@ -45,7 +44,7 @@ static void *erofs_read_inode(struct erofs_buf *buf, vi->datalayout = erofs_inode_datalayout(ifmt); if (vi->datalayout >= EROFS_INODE_DATALAYOUT_MAX) { - erofs_err(inode->i_sb, "unsupported datalayout %u of nid %llu", + erofs_err(sb, "unsupported datalayout %u of nid %llu", vi->datalayout, vi->nid); err = -EOPNOTSUPP; goto err_out; @@ -82,40 +81,15 @@ static void *erofs_read_inode(struct erofs_buf *buf, vi->xattr_isize = erofs_xattr_ibody_size(die->i_xattr_icount); inode->i_mode = le16_to_cpu(die->i_mode); - switch (inode->i_mode & S_IFMT) { - case S_IFREG: - case S_IFDIR: - case S_IFLNK: - vi->raw_blkaddr = le32_to_cpu(die->i_u.raw_blkaddr); - break; - case S_IFCHR: - case S_IFBLK: - inode->i_rdev = - new_decode_dev(le32_to_cpu(die->i_u.rdev)); - break; - case S_IFIFO: - case S_IFSOCK: - inode->i_rdev = 0; - break; - default: - goto bogusimode; - } + iu = die->i_u; i_uid_write(inode, le32_to_cpu(die->i_uid)); i_gid_write(inode, le32_to_cpu(die->i_gid)); set_nlink(inode, le32_to_cpu(die->i_nlink)); - - /* extended inode has its own timestamp */ + /* each extended inode has its own timestamp */ inode_set_ctime(inode, le64_to_cpu(die->i_mtime), le32_to_cpu(die->i_mtime_nsec)); inode->i_size = le64_to_cpu(die->i_size); - - /* total blocks for compressed files */ - if (erofs_inode_is_data_compressed(vi->datalayout)) - nblks = le32_to_cpu(die->i_u.compressed_blocks); - else if (vi->datalayout == EROFS_INODE_CHUNK_BASED) - /* fill chunked inode summary info */ - vi->chunkformat = le16_to_cpu(die->i_u.c.format); kfree(copied); copied = NULL; break; @@ -125,49 +99,51 @@ static void *erofs_read_inode(struct erofs_buf *buf, vi->xattr_isize = erofs_xattr_ibody_size(dic->i_xattr_icount); inode->i_mode = le16_to_cpu(dic->i_mode); - switch (inode->i_mode & S_IFMT) { - case S_IFREG: - case S_IFDIR: - case S_IFLNK: - vi->raw_blkaddr = le32_to_cpu(dic->i_u.raw_blkaddr); - break; - case S_IFCHR: - case S_IFBLK: - inode->i_rdev = - new_decode_dev(le32_to_cpu(dic->i_u.rdev)); - break; - case S_IFIFO: - case S_IFSOCK: - inode->i_rdev = 0; - break; - default: - goto bogusimode; - } + iu = dic->i_u; i_uid_write(inode, le16_to_cpu(dic->i_uid)); i_gid_write(inode, le16_to_cpu(dic->i_gid)); set_nlink(inode, le16_to_cpu(dic->i_nlink)); - /* use build time for compact inodes */ inode_set_ctime(inode, sbi->build_time, sbi->build_time_nsec); inode->i_size = le32_to_cpu(dic->i_size); - if (erofs_inode_is_data_compressed(vi->datalayout)) - nblks = le32_to_cpu(dic->i_u.compressed_blocks); - else if (vi->datalayout == EROFS_INODE_CHUNK_BASED) - vi->chunkformat = le16_to_cpu(dic->i_u.c.format); break; default: - erofs_err(inode->i_sb, - "unsupported on-disk inode version %u of nid %llu", + erofs_err(sb, "unsupported on-disk inode version %u of nid %llu", erofs_inode_version(ifmt), vi->nid); err = -EOPNOTSUPP; goto err_out; } - if (vi->datalayout == EROFS_INODE_CHUNK_BASED) { + switch (inode->i_mode & S_IFMT) { + case S_IFREG: + case S_IFDIR: + case S_IFLNK: + vi->raw_blkaddr = le32_to_cpu(iu.raw_blkaddr); + break; + case S_IFCHR: + case S_IFBLK: + inode->i_rdev = new_decode_dev(le32_to_cpu(iu.rdev)); + break; + case S_IFIFO: + case S_IFSOCK: + inode->i_rdev = 0; + break; + default: + erofs_err(sb, "bogus i_mode (%o) @ nid %llu", inode->i_mode, + vi->nid); + err = -EFSCORRUPTED; + goto err_out; + } + + /* total blocks for compressed files */ + if (erofs_inode_is_data_compressed(vi->datalayout)) { + nblks = le32_to_cpu(iu.compressed_blocks); + } else if (vi->datalayout == EROFS_INODE_CHUNK_BASED) { + /* fill chunked inode summary info */ + vi->chunkformat = le16_to_cpu(iu.c.format); if (vi->chunkformat & ~EROFS_CHUNK_FORMAT_ALL) { - erofs_err(inode->i_sb, - "unsupported chunk format %x of nid %llu", + erofs_err(sb, "unsupported chunk format %x of nid %llu", vi->chunkformat, vi->nid); err = -EOPNOTSUPP; goto err_out; @@ -191,10 +167,6 @@ static void *erofs_read_inode(struct erofs_buf *buf, inode->i_blocks = nblks << (sb->s_blocksize_bits - 9); return kaddr; -bogusimode: - erofs_err(inode->i_sb, "bogus i_mode (%o) @ nid %llu", - inode->i_mode, vi->nid); - err = -EFSCORRUPTED; err_out: DBG_BUGON(1); kfree(copied); diff --git a/fs/nfsd/cache.h b/fs/nfsd/cache.h index 929248c6ca84..4cbe0434cbb8 100644 --- a/fs/nfsd/cache.h +++ b/fs/nfsd/cache.h @@ -84,8 +84,8 @@ int nfsd_net_reply_cache_init(struct nfsd_net *nn); void nfsd_net_reply_cache_destroy(struct nfsd_net *nn); int nfsd_reply_cache_init(struct nfsd_net *); void nfsd_reply_cache_shutdown(struct nfsd_net *); -int nfsd_cache_lookup(struct svc_rqst *rqstp, - struct nfsd_cacherep **cacherep); +int nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start, + unsigned int len, struct nfsd_cacherep **cacherep); void nfsd_cache_update(struct svc_rqst *rqstp, struct nfsd_cacherep *rp, int cachetype, __be32 *statp); int nfsd_reply_cache_stats_show(struct seq_file *m, void *v); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 4045c852a450..40415929e2ae 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -2804,7 +2804,7 @@ static int client_opens_release(struct inode *inode, struct file *file) /* XXX: alternatively, we could get/drop in seq start/stop */ drop_client(clp); - return 0; + return seq_release(inode, file); } static const struct file_operations client_states_fops = { diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index fd56a52aa5fb..d3273a396659 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -369,33 +369,52 @@ nfsd_reply_cache_scan(struct shrinker *shrink, struct shrink_control *sc) return freed; } -/* - * Walk an xdr_buf and get a CRC for at most the first RC_CSUMLEN bytes +/** + * nfsd_cache_csum - Checksum incoming NFS Call arguments + * @buf: buffer containing a whole RPC Call message + * @start: starting byte of the NFS Call header + * @remaining: size of the NFS Call header, in bytes + * + * Compute a weak checksum of the leading bytes of an NFS procedure + * call header to help verify that a retransmitted Call matches an + * entry in the duplicate reply cache. + * + * To avoid assumptions about how the RPC message is laid out in + * @buf and what else it might contain (eg, a GSS MIC suffix), the + * caller passes us the exact location and length of the NFS Call + * header. + * + * Returns a 32-bit checksum value, as defined in RFC 793. */ -static __wsum -nfsd_cache_csum(struct svc_rqst *rqstp) +static __wsum nfsd_cache_csum(struct xdr_buf *buf, unsigned int start, + unsigned int remaining) { + unsigned int base, len; + struct xdr_buf subbuf; + __wsum csum = 0; + void *p; int idx; - unsigned int base; - __wsum csum; - struct xdr_buf *buf = &rqstp->rq_arg; - const unsigned char *p = buf->head[0].iov_base; - size_t csum_len = min_t(size_t, buf->head[0].iov_len + buf->page_len, - RC_CSUMLEN); - size_t len = min(buf->head[0].iov_len, csum_len); + + if (remaining > RC_CSUMLEN) + remaining = RC_CSUMLEN; + if (xdr_buf_subsegment(buf, &subbuf, start, remaining)) + return csum; /* rq_arg.head first */ - csum = csum_partial(p, len, 0); - csum_len -= len; + if (subbuf.head[0].iov_len) { + len = min_t(unsigned int, subbuf.head[0].iov_len, remaining); + csum = csum_partial(subbuf.head[0].iov_base, len, csum); + remaining -= len; + } /* Continue into page array */ - idx = buf->page_base / PAGE_SIZE; - base = buf->page_base & ~PAGE_MASK; - while (csum_len) { - p = page_address(buf->pages[idx]) + base; - len = min_t(size_t, PAGE_SIZE - base, csum_len); + idx = subbuf.page_base / PAGE_SIZE; + base = subbuf.page_base & ~PAGE_MASK; + while (remaining) { + p = page_address(subbuf.pages[idx]) + base; + len = min_t(unsigned int, PAGE_SIZE - base, remaining); csum = csum_partial(p, len, csum); - csum_len -= len; + remaining -= len; base = 0; ++idx; } @@ -466,6 +485,8 @@ out: /** * nfsd_cache_lookup - Find an entry in the duplicate reply cache * @rqstp: Incoming Call to find + * @start: starting byte in @rqstp->rq_arg of the NFS Call header + * @len: size of the NFS Call header, in bytes * @cacherep: OUT: DRC entry for this request * * Try to find an entry matching the current call in the cache. When none @@ -479,7 +500,8 @@ out: * %RC_REPLY: Reply from cache * %RC_DROPIT: Do not process the request further */ -int nfsd_cache_lookup(struct svc_rqst *rqstp, struct nfsd_cacherep **cacherep) +int nfsd_cache_lookup(struct svc_rqst *rqstp, unsigned int start, + unsigned int len, struct nfsd_cacherep **cacherep) { struct nfsd_net *nn; struct nfsd_cacherep *rp, *found; @@ -495,7 +517,7 @@ int nfsd_cache_lookup(struct svc_rqst *rqstp, struct nfsd_cacherep **cacherep) goto out; } - csum = nfsd_cache_csum(rqstp); + csum = nfsd_cache_csum(&rqstp->rq_arg, start, len); /* * Since the common case is a cache miss followed by an insert, @@ -641,24 +663,17 @@ void nfsd_cache_update(struct svc_rqst *rqstp, struct nfsd_cacherep *rp, return; } -/* - * Copy cached reply to current reply buffer. Should always fit. - * FIXME as reply is in a page, we should just attach the page, and - * keep a refcount.... - */ static int nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *data) { - struct kvec *vec = &rqstp->rq_res.head[0]; - - if (vec->iov_len + data->iov_len > PAGE_SIZE) { - printk(KERN_WARNING "nfsd: cached reply too large (%zd).\n", - data->iov_len); - return 0; - } - memcpy((char*)vec->iov_base + vec->iov_len, data->iov_base, data->iov_len); - vec->iov_len += data->iov_len; - return 1; + __be32 *p; + + p = xdr_reserve_space(&rqstp->rq_res_stream, data->iov_len); + if (unlikely(!p)) + return false; + memcpy(p, data->iov_base, data->iov_len); + xdr_commit_encode(&rqstp->rq_res_stream); + return true; } /* diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index d6122bb2d167..fe61d9bbcc1f 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -981,6 +981,8 @@ int nfsd_dispatch(struct svc_rqst *rqstp) const struct svc_procedure *proc = rqstp->rq_procinfo; __be32 *statp = rqstp->rq_accept_statp; struct nfsd_cacherep *rp; + unsigned int start, len; + __be32 *nfs_reply; /* * Give the xdr decoder a chance to change this if it wants @@ -988,6 +990,13 @@ int nfsd_dispatch(struct svc_rqst *rqstp) */ rqstp->rq_cachetype = proc->pc_cachetype; + /* + * ->pc_decode advances the argument stream past the NFS + * Call header, so grab the header's starting location and + * size now for the call to nfsd_cache_lookup(). + */ + start = xdr_stream_pos(&rqstp->rq_arg_stream); + len = xdr_stream_remaining(&rqstp->rq_arg_stream); if (!proc->pc_decode(rqstp, &rqstp->rq_arg_stream)) goto out_decode_err; @@ -1001,7 +1010,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp) smp_store_release(&rqstp->rq_status_counter, rqstp->rq_status_counter | 1); rp = NULL; - switch (nfsd_cache_lookup(rqstp, &rp)) { + switch (nfsd_cache_lookup(rqstp, start, len, &rp)) { case RC_DOIT: break; case RC_REPLY: @@ -1010,6 +1019,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp) goto out_dropit; } + nfs_reply = xdr_inline_decode(&rqstp->rq_res_stream, 0); *statp = proc->pc_func(rqstp); if (test_bit(RQ_DROPME, &rqstp->rq_flags)) goto out_update_drop; @@ -1023,7 +1033,7 @@ int nfsd_dispatch(struct svc_rqst *rqstp) */ smp_store_release(&rqstp->rq_status_counter, rqstp->rq_status_counter + 1); - nfsd_cache_update(rqstp, rp, rqstp->rq_cachetype, statp + 1); + nfsd_cache_update(rqstp, rp, rqstp->rq_cachetype, nfs_reply); out_cached_reply: return 1; diff --git a/fs/overlayfs/params.c b/fs/overlayfs/params.c index ddab9ea267d1..3fe2dde1598f 100644 --- a/fs/overlayfs/params.c +++ b/fs/overlayfs/params.c @@ -430,7 +430,7 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc) struct ovl_fs_context *ctx = fc->fs_private; struct ovl_fs_context_layer *l; char *dup = NULL, *iter; - ssize_t nr_lower = 0, nr = 0, nr_data = 0; + ssize_t nr_lower, nr; bool data_layer = false; /* @@ -482,6 +482,7 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc) iter = dup; l = ctx->lower; for (nr = 0; nr < nr_lower; nr++, l++) { + ctx->nr++; memset(l, 0, sizeof(*l)); err = ovl_mount_dir(iter, &l->path); @@ -498,10 +499,10 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc) goto out_put; if (data_layer) - nr_data++; + ctx->nr_data++; /* Calling strchr() again would overrun. */ - if ((nr + 1) == nr_lower) + if (ctx->nr == nr_lower) break; err = -EINVAL; @@ -511,7 +512,7 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc) * This is a regular layer so we require that * there are no data layers. */ - if ((ctx->nr_data + nr_data) > 0) { + if (ctx->nr_data > 0) { pr_err("regular lower layers cannot follow data lower layers"); goto out_put; } @@ -524,8 +525,6 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc) data_layer = true; iter++; } - ctx->nr = nr_lower; - ctx->nr_data += nr_data; kfree(dup); return 0; diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index 50a201e9cd39..c3f020ca13a8 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -978,7 +978,7 @@ int ovl_set_protattr(struct inode *inode, struct dentry *upper, return 0; } -/** +/* * Caller must hold a reference to inode to prevent it from being freed while * it is marked inuse. */ diff --git a/fs/smb/client/cifs_spnego.c b/fs/smb/client/cifs_spnego.c index 6f3285f1dfee..af7849e5974f 100644 --- a/fs/smb/client/cifs_spnego.c +++ b/fs/smb/client/cifs_spnego.c @@ -64,8 +64,8 @@ struct key_type cifs_spnego_key_type = { * strlen(";sec=ntlmsspi") */ #define MAX_MECH_STR_LEN 13 -/* strlen of "host=" */ -#define HOST_KEY_LEN 5 +/* strlen of ";host=" */ +#define HOST_KEY_LEN 6 /* strlen of ";ip4=" or ";ip6=" */ #define IP_KEY_LEN 5 diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 57c2a7df3457..f896f60c924b 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -2065,6 +2065,12 @@ void __cifs_put_smb_ses(struct cifs_ses *ses) ses->chans[i].server = NULL; } + /* we now account for primary channel in iface->refcount */ + if (ses->chans[0].iface) { + kref_put(&ses->chans[0].iface->refcount, release_iface); + ses->chans[0].server = NULL; + } + sesInfoFree(ses); cifs_put_tcp_session(server, 0); } diff --git a/fs/smb/client/sess.c b/fs/smb/client/sess.c index 0bb2ac929061..8b2d7c1ca428 100644 --- a/fs/smb/client/sess.c +++ b/fs/smb/client/sess.c @@ -322,28 +322,32 @@ cifs_disable_secondary_channels(struct cifs_ses *ses) iface = ses->chans[i].iface; server = ses->chans[i].server; + /* + * remove these references first, since we need to unlock + * the chan_lock here, since iface_lock is a higher lock + */ + ses->chans[i].iface = NULL; + ses->chans[i].server = NULL; + spin_unlock(&ses->chan_lock); + if (iface) { spin_lock(&ses->iface_lock); kref_put(&iface->refcount, release_iface); - ses->chans[i].iface = NULL; iface->num_channels--; if (iface->weight_fulfilled) iface->weight_fulfilled--; spin_unlock(&ses->iface_lock); } - spin_unlock(&ses->chan_lock); - if (server && !server->terminate) { - server->terminate = true; - cifs_signal_cifsd_for_reconnect(server, false); - } - spin_lock(&ses->chan_lock); - if (server) { - ses->chans[i].server = NULL; + if (!server->terminate) { + server->terminate = true; + cifs_signal_cifsd_for_reconnect(server, false); + } cifs_put_tcp_session(server, false); } + spin_lock(&ses->chan_lock); } done: diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c index 84ea67301303..5a3ca62d2f07 100644 --- a/fs/smb/client/smb2transport.c +++ b/fs/smb/client/smb2transport.c @@ -458,6 +458,8 @@ generate_smb3signingkey(struct cifs_ses *ses, ptriplet->encryption.context, ses->smb3encryptionkey, SMB3_ENC_DEC_KEY_SIZE); + if (rc) + return rc; rc = generate_key(ses, ptriplet->decryption.label, ptriplet->decryption.context, ses->smb3decryptionkey, @@ -466,9 +468,6 @@ generate_smb3signingkey(struct cifs_ses *ses, return rc; } - if (rc) - return rc; - #ifdef CONFIG_CIFS_DEBUG_DUMP_KEYS cifs_dbg(VFS, "%s: dumping generated AES session keys\n", __func__); /* diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig index ed0bc8cbc703..567fb37274d3 100644 --- a/fs/xfs/Kconfig +++ b/fs/xfs/Kconfig @@ -147,7 +147,7 @@ config XFS_ONLINE_SCRUB_STATS bool "XFS online metadata check usage data collection" default y depends on XFS_ONLINE_SCRUB - select XFS_DEBUG + select DEBUG_FS help If you say Y here, the kernel will gather usage data about the online metadata check subsystem. This includes the number diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 3069194527dd..100ab5931b31 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -2275,16 +2275,37 @@ xfs_alloc_min_freelist( ASSERT(mp->m_alloc_maxlevels > 0); + /* + * For a btree shorter than the maximum height, the worst case is that + * every level gets split and a new level is added, then while inserting + * another entry to refill the AGFL, every level under the old root gets + * split again. This is: + * + * (full height split reservation) + (AGFL refill split height) + * = (current height + 1) + (current height - 1) + * = (new height) + (new height - 2) + * = 2 * new height - 2 + * + * For a btree of maximum height, the worst case is that every level + * under the root gets split, then while inserting another entry to + * refill the AGFL, every level under the root gets split again. This is + * also: + * + * 2 * (current height - 1) + * = 2 * (new height - 1) + * = 2 * new height - 2 + */ + /* space needed by-bno freespace btree */ min_free = min_t(unsigned int, levels[XFS_BTNUM_BNOi] + 1, - mp->m_alloc_maxlevels); + mp->m_alloc_maxlevels) * 2 - 2; /* space needed by-size freespace btree */ min_free += min_t(unsigned int, levels[XFS_BTNUM_CNTi] + 1, - mp->m_alloc_maxlevels); + mp->m_alloc_maxlevels) * 2 - 2; /* space needed reverse mapping used space btree */ if (xfs_has_rmapbt(mp)) min_free += min_t(unsigned int, levels[XFS_BTNUM_RMAPi] + 1, - mp->m_rmap_maxlevels); + mp->m_rmap_maxlevels) * 2 - 2; return min_free; } diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c index bcfb6a4203cd..f71679ce23b9 100644 --- a/fs/xfs/libxfs/xfs_defer.c +++ b/fs/xfs/libxfs/xfs_defer.c @@ -245,21 +245,18 @@ xfs_defer_create_intents( return ret; } -/* Abort all the intents that were committed. */ STATIC void -xfs_defer_trans_abort( - struct xfs_trans *tp, - struct list_head *dop_pending) +xfs_defer_pending_abort( + struct xfs_mount *mp, + struct list_head *dop_list) { struct xfs_defer_pending *dfp; const struct xfs_defer_op_type *ops; - trace_xfs_defer_trans_abort(tp, _RET_IP_); - /* Abort intent items that don't have a done item. */ - list_for_each_entry(dfp, dop_pending, dfp_list) { + list_for_each_entry(dfp, dop_list, dfp_list) { ops = defer_op_types[dfp->dfp_type]; - trace_xfs_defer_pending_abort(tp->t_mountp, dfp); + trace_xfs_defer_pending_abort(mp, dfp); if (dfp->dfp_intent && !dfp->dfp_done) { ops->abort_intent(dfp->dfp_intent); dfp->dfp_intent = NULL; @@ -267,6 +264,16 @@ xfs_defer_trans_abort( } } +/* Abort all the intents that were committed. */ +STATIC void +xfs_defer_trans_abort( + struct xfs_trans *tp, + struct list_head *dop_pending) +{ + trace_xfs_defer_trans_abort(tp, _RET_IP_); + xfs_defer_pending_abort(tp->t_mountp, dop_pending); +} + /* * Capture resources that the caller said not to release ("held") when the * transaction commits. Caller is responsible for zero-initializing @dres. @@ -756,12 +763,13 @@ xfs_defer_ops_capture( /* Release all resources that we used to capture deferred ops. */ void -xfs_defer_ops_capture_free( +xfs_defer_ops_capture_abort( struct xfs_mount *mp, struct xfs_defer_capture *dfc) { unsigned short i; + xfs_defer_pending_abort(mp, &dfc->dfc_dfops); xfs_defer_cancel_list(mp, &dfc->dfc_dfops); for (i = 0; i < dfc->dfc_held.dr_bufs; i++) @@ -802,7 +810,7 @@ xfs_defer_ops_capture_and_commit( /* Commit the transaction and add the capture structure to the list. */ error = xfs_trans_commit(tp); if (error) { - xfs_defer_ops_capture_free(mp, dfc); + xfs_defer_ops_capture_abort(mp, dfc); return error; } diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h index 114a3a4930a3..8788ad5f6a73 100644 --- a/fs/xfs/libxfs/xfs_defer.h +++ b/fs/xfs/libxfs/xfs_defer.h @@ -121,7 +121,7 @@ int xfs_defer_ops_capture_and_commit(struct xfs_trans *tp, struct list_head *capture_list); void xfs_defer_ops_continue(struct xfs_defer_capture *d, struct xfs_trans *tp, struct xfs_defer_resources *dres); -void xfs_defer_ops_capture_free(struct xfs_mount *mp, +void xfs_defer_ops_capture_abort(struct xfs_mount *mp, struct xfs_defer_capture *d); void xfs_defer_resources_rele(struct xfs_defer_resources *dres); diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 543f3748c2a3..137a65bda95d 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -510,6 +510,9 @@ xfs_dinode_verify( if (mode && nextents + naextents > nblocks) return __this_address; + if (nextents + naextents == 0 && nblocks != 0) + return __this_address; + if (S_ISDIR(mode) && nextents > mp->m_dir_geo->max_extents) return __this_address; diff --git a/fs/xfs/xfs_inode_item_recover.c b/fs/xfs/xfs_inode_item_recover.c index 0e5dba2343ea..144198a6b270 100644 --- a/fs/xfs/xfs_inode_item_recover.c +++ b/fs/xfs/xfs_inode_item_recover.c @@ -286,6 +286,7 @@ xlog_recover_inode_commit_pass2( struct xfs_log_dinode *ldip; uint isize; int need_free = 0; + xfs_failaddr_t fa; if (item->ri_buf[0].i_len == sizeof(struct xfs_inode_log_format)) { in_f = item->ri_buf[0].i_addr; @@ -369,24 +370,26 @@ xlog_recover_inode_commit_pass2( * superblock flag to determine whether we need to look at di_flushiter * to skip replay when the on disk inode is newer than the log one */ - if (!xfs_has_v3inodes(mp) && - ldip->di_flushiter < be16_to_cpu(dip->di_flushiter)) { - /* - * Deal with the wrap case, DI_MAX_FLUSH is less - * than smaller numbers - */ - if (be16_to_cpu(dip->di_flushiter) == DI_MAX_FLUSH && - ldip->di_flushiter < (DI_MAX_FLUSH >> 1)) { - /* do nothing */ - } else { - trace_xfs_log_recover_inode_skip(log, in_f); - error = 0; - goto out_release; + if (!xfs_has_v3inodes(mp)) { + if (ldip->di_flushiter < be16_to_cpu(dip->di_flushiter)) { + /* + * Deal with the wrap case, DI_MAX_FLUSH is less + * than smaller numbers + */ + if (be16_to_cpu(dip->di_flushiter) == DI_MAX_FLUSH && + ldip->di_flushiter < (DI_MAX_FLUSH >> 1)) { + /* do nothing */ + } else { + trace_xfs_log_recover_inode_skip(log, in_f); + error = 0; + goto out_release; + } } + + /* Take the opportunity to reset the flush iteration count */ + ldip->di_flushiter = 0; } - /* Take the opportunity to reset the flush iteration count */ - ldip->di_flushiter = 0; if (unlikely(S_ISREG(ldip->di_mode))) { if ((ldip->di_format != XFS_DINODE_FMT_EXTENTS) && @@ -528,8 +531,19 @@ out_owner_change: (dip->di_mode != 0)) error = xfs_recover_inode_owner_change(mp, dip, in_f, buffer_list); - /* re-generate the checksum. */ + /* re-generate the checksum and validate the recovered inode. */ xfs_dinode_calc_crc(log->l_mp, dip); + fa = xfs_dinode_verify(log->l_mp, in_f->ilf_ino, dip); + if (fa) { + XFS_CORRUPTION_ERROR( + "Bad dinode after recovery", + XFS_ERRLEVEL_LOW, mp, dip, sizeof(*dip)); + xfs_alert(mp, + "Metadata corruption detected at %pS, inode 0x%llx", + fa, in_f->ilf_ino); + error = -EFSCORRUPTED; + goto out_release; + } ASSERT(bp->b_mount == mp); bp->b_flags |= _XBF_LOGRECOVERY; diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 51c100c86177..ee206facf0dc 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -1893,9 +1893,7 @@ xlog_write_iclog( * the buffer manually, the code needs to be kept in sync * with the I/O completion path. */ - xlog_state_done_syncing(iclog); - up(&iclog->ic_sema); - return; + goto sync; } /* @@ -1925,20 +1923,17 @@ xlog_write_iclog( * avoid shutdown re-entering this path and erroring out again. */ if (log->l_targ != log->l_mp->m_ddev_targp && - blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev)) { - xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR); - return; - } + blkdev_issue_flush(log->l_mp->m_ddev_targp->bt_bdev)) + goto shutdown; } if (iclog->ic_flags & XLOG_ICL_NEED_FUA) iclog->ic_bio.bi_opf |= REQ_FUA; iclog->ic_flags &= ~(XLOG_ICL_NEED_FLUSH | XLOG_ICL_NEED_FUA); - if (xlog_map_iclog_data(&iclog->ic_bio, iclog->ic_data, count)) { - xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR); - return; - } + if (xlog_map_iclog_data(&iclog->ic_bio, iclog->ic_data, count)) + goto shutdown; + if (is_vmalloc_addr(iclog->ic_data)) flush_kernel_vmap_range(iclog->ic_data, count); @@ -1959,6 +1954,12 @@ xlog_write_iclog( } submit_bio(&iclog->ic_bio); + return; +shutdown: + xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR); +sync: + xlog_state_done_syncing(iclog); + up(&iclog->ic_sema); } /* diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c index 13b94d2e605b..a1e18b24971a 100644 --- a/fs/xfs/xfs_log_recover.c +++ b/fs/xfs/xfs_log_recover.c @@ -2511,7 +2511,7 @@ xlog_abort_defer_ops( list_for_each_entry_safe(dfc, next, capture_list, dfc_list) { list_del_init(&dfc->dfc_list); - xfs_defer_ops_capture_free(mp, dfc); + xfs_defer_ops_capture_abort(mp, dfc); } } diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 658edee8381d..e5b62dc28466 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -784,6 +784,7 @@ xfs_reflink_end_cow_extent( } } del = got; + xfs_trim_extent(&del, *offset_fsb, end_fsb - *offset_fsb); /* Grab the corresponding mapping in the data fork. */ nmaps = 1; diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h index 995513fa2690..0655aa5b57b2 100644 --- a/include/asm-generic/qspinlock.h +++ b/include/asm-generic/qspinlock.h @@ -70,7 +70,7 @@ static __always_inline int queued_spin_is_locked(struct qspinlock *lock) */ static __always_inline int queued_spin_value_unlocked(struct qspinlock lock) { - return !atomic_read(&lock.val); + return !lock.val.counter; } /** diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 39edc76f436e..d99a636d36a7 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -301,6 +301,17 @@ struct bpf_func_state { struct tnum callback_ret_range; bool in_async_callback_fn; bool in_exception_callback_fn; + /* For callback calling functions that limit number of possible + * callback executions (e.g. bpf_loop) keeps track of current + * simulated iteration number. + * Value in frame N refers to number of times callback with frame + * N+1 was simulated, e.g. for the following call: + * + * bpf_loop(..., fn, ...); | suppose current frame is N + * | fn would be simulated in frame N+1 + * | number of simulations is tracked in frame N + */ + u32 callback_depth; /* The following fields should be last. See copy_func_state() */ int acquired_refs; @@ -400,6 +411,7 @@ struct bpf_verifier_state { struct bpf_idx_pair *jmp_history; u32 jmp_history_cnt; u32 dfs_depth; + u32 callback_unroll_depth; }; #define bpf_get_spilled_reg(slot, frame, mask) \ @@ -511,6 +523,10 @@ struct bpf_insn_aux_data { * this instruction, regardless of any heuristics */ bool force_checkpoint; + /* true if instruction is a call to a helper function that + * accepts callback function as a parameter. + */ + bool calls_callback; }; #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */ diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index d305db70674b..efc0c0b07efb 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -195,6 +195,7 @@ enum cpuhp_state { CPUHP_AP_ARM_CORESIGHT_CTI_STARTING, CPUHP_AP_ARM64_ISNDEP_STARTING, CPUHP_AP_SMPCFD_DYING, + CPUHP_AP_HRTIMERS_DYING, CPUHP_AP_X86_TBOOT_DYING, CPUHP_AP_ARM_CACHE_B15_RAC_DYING, CPUHP_AP_ONLINE, diff --git a/include/linux/export-internal.h b/include/linux/export-internal.h index 45fca09b2319..69501e0ec239 100644 --- a/include/linux/export-internal.h +++ b/include/linux/export-internal.h @@ -50,9 +50,7 @@ " .previous" "\n" \ ) -#ifdef CONFIG_IA64 -#define KSYM_FUNC(name) @fptr(name) -#elif defined(CONFIG_PARISC) && defined(CONFIG_64BIT) +#if defined(CONFIG_PARISC) && defined(CONFIG_64BIT) #define KSYM_FUNC(name) P%name #else #define KSYM_FUNC(name) name diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 0ee140176f10..f2044d5a652b 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -531,9 +531,9 @@ extern void sysrq_timer_list_show(void); int hrtimers_prepare_cpu(unsigned int cpu); #ifdef CONFIG_HOTPLUG_CPU -int hrtimers_dead_cpu(unsigned int cpu); +int hrtimers_cpu_dying(unsigned int cpu); #else -#define hrtimers_dead_cpu NULL +#define hrtimers_cpu_dying NULL #endif #endif diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2d840d7056f2..e87caa81f70c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1797,6 +1797,13 @@ enum netdev_ml_priv_type { ML_PRIV_CAN, }; +enum netdev_stat_type { + NETDEV_PCPU_STAT_NONE, + NETDEV_PCPU_STAT_LSTATS, /* struct pcpu_lstats */ + NETDEV_PCPU_STAT_TSTATS, /* struct pcpu_sw_netstats */ + NETDEV_PCPU_STAT_DSTATS, /* struct pcpu_dstats */ +}; + /** * struct net_device - The DEVICE structure. * @@ -1991,10 +1998,14 @@ enum netdev_ml_priv_type { * * @ml_priv: Mid-layer private * @ml_priv_type: Mid-layer private type - * @lstats: Loopback statistics - * @tstats: Tunnel statistics - * @dstats: Dummy statistics - * @vstats: Virtual ethernet statistics + * + * @pcpu_stat_type: Type of device statistics which the core should + * allocate/free: none, lstats, tstats, dstats. none + * means the driver is handling statistics allocation/ + * freeing internally. + * @lstats: Loopback statistics: packets, bytes + * @tstats: Tunnel statistics: RX/TX packets, RX/TX bytes + * @dstats: Dummy statistics: RX/TX/drop packets, RX/TX bytes * * @garp_port: GARP * @mrp_port: MRP @@ -2354,6 +2365,7 @@ struct net_device { void *ml_priv; enum netdev_ml_priv_type ml_priv_type; + enum netdev_stat_type pcpu_stat_type:8; union { struct pcpu_lstats __percpu *lstats; struct pcpu_sw_netstats __percpu *tstats; @@ -2755,6 +2767,16 @@ struct pcpu_sw_netstats { struct u64_stats_sync syncp; } __aligned(4 * sizeof(u64)); +struct pcpu_dstats { + u64 rx_packets; + u64 rx_bytes; + u64 rx_drops; + u64 tx_packets; + u64 tx_bytes; + u64 tx_drops; + struct u64_stats_sync syncp; +} __aligned(8 * sizeof(u64)); + struct pcpu_lstats { u64_stats_t packets; u64_stats_t bytes; diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index afb028c54f33..5547ba68e6e4 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -843,11 +843,11 @@ struct perf_event { }; /* - * ,-----------------------[1:n]----------------------. - * V V - * perf_event_context <-[1:n]-> perf_event_pmu_context <--- perf_event - * ^ ^ | | - * `--------[1:n]---------' `-[n:1]-> pmu <-[1:n]-' + * ,-----------------------[1:n]------------------------. + * V V + * perf_event_context <-[1:n]-> perf_event_pmu_context <-[1:n]- perf_event + * | | + * `--[n:1]-> pmu <-[1:n]--' * * * struct perf_event_pmu_context lifetime is refcount based and RCU freed @@ -865,6 +865,9 @@ struct perf_event { * ctx->mutex pinning the configuration. Since we hold a reference on * group_leader (through the filedesc) it can't go away, therefore it's * associated pmu_ctx must exist and cannot change due to ctx->mutex. + * + * perf_event holds a refcount on perf_event_context + * perf_event holds a refcount on perf_event_pmu_context */ struct perf_event_pmu_context { struct pmu *pmu; diff --git a/include/net/netkit.h b/include/net/netkit.h index 0ba2e6b847ca..9ec0163739f4 100644 --- a/include/net/netkit.h +++ b/include/net/netkit.h @@ -10,6 +10,7 @@ int netkit_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); int netkit_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int netkit_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog); int netkit_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); +INDIRECT_CALLABLE_DECLARE(struct net_device *netkit_peer_dev(struct net_device *dev)); #else static inline int netkit_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) @@ -34,5 +35,10 @@ static inline int netkit_prog_query(const union bpf_attr *attr, { return -EINVAL; } + +static inline struct net_device *netkit_peer_dev(struct net_device *dev) +{ + return NULL; +} #endif /* CONFIG_NETKIT */ #endif /* __NET_NETKIT_H */ diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h index 4c53a5ef6257..f7e537f64db4 100644 --- a/include/trace/events/rxrpc.h +++ b/include/trace/events/rxrpc.h @@ -328,7 +328,7 @@ E_(rxrpc_rtt_tx_ping, "PING") #define rxrpc_rtt_rx_traces \ - EM(rxrpc_rtt_rx_cancel, "CNCL") \ + EM(rxrpc_rtt_rx_other_ack, "OACK") \ EM(rxrpc_rtt_rx_obsolete, "OBSL") \ EM(rxrpc_rtt_rx_lost, "LOST") \ EM(rxrpc_rtt_rx_ping_response, "PONG") \ diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c index f04a43044d91..976e9500f651 100644 --- a/io_uring/fdinfo.c +++ b/io_uring/fdinfo.c @@ -145,13 +145,8 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f) if (has_lock && (ctx->flags & IORING_SETUP_SQPOLL)) { struct io_sq_data *sq = ctx->sq_data; - if (mutex_trylock(&sq->lock)) { - if (sq->thread) { - sq_pid = task_pid_nr(sq->thread); - sq_cpu = task_cpu(sq->thread); - } - mutex_unlock(&sq->lock); - } + sq_pid = sq->task_pid; + sq_cpu = sq->sq_cpu; } seq_printf(m, "SqThread:\t%d\n", sq_pid); diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c index bd6c2c7959a5..65b5dbe3c850 100644 --- a/io_uring/sqpoll.c +++ b/io_uring/sqpoll.c @@ -214,6 +214,7 @@ static bool io_sqd_handle_event(struct io_sq_data *sqd) did_sig = get_signal(&ksig); cond_resched(); mutex_lock(&sqd->lock); + sqd->sq_cpu = raw_smp_processor_id(); } return did_sig || test_bit(IO_SQ_THREAD_SHOULD_STOP, &sqd->state); } @@ -229,10 +230,15 @@ static int io_sq_thread(void *data) snprintf(buf, sizeof(buf), "iou-sqp-%d", sqd->task_pid); set_task_comm(current, buf); - if (sqd->sq_cpu != -1) + /* reset to our pid after we've set task_comm, for fdinfo */ + sqd->task_pid = current->pid; + + if (sqd->sq_cpu != -1) { set_cpus_allowed_ptr(current, cpumask_of(sqd->sq_cpu)); - else + } else { set_cpus_allowed_ptr(current, cpu_online_mask); + sqd->sq_cpu = raw_smp_processor_id(); + } mutex_lock(&sqd->lock); while (1) { @@ -261,6 +267,7 @@ static int io_sq_thread(void *data) mutex_unlock(&sqd->lock); cond_resched(); mutex_lock(&sqd->lock); + sqd->sq_cpu = raw_smp_processor_id(); } continue; } @@ -294,6 +301,7 @@ static int io_sq_thread(void *data) mutex_unlock(&sqd->lock); schedule(); mutex_lock(&sqd->lock); + sqd->sq_cpu = raw_smp_processor_id(); } list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) atomic_andnot(IORING_SQ_NEED_WAKEUP, diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 91e82e34b51e..7a98cd176a12 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -531,7 +531,7 @@ int audit_exe_compare(struct task_struct *tsk, struct audit_fsnotify_mark *mark) if (tsk != current) return 0; - if (WARN_ON_ONCE(!current->mm)) + if (!current->mm) return 0; exe_file = get_mm_exe_file(current->mm); if (!exe_file) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1340921ea311..405da1f9e724 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -465,13 +465,12 @@ static bool is_dynptr_ref_function(enum bpf_func_id func_id) return func_id == BPF_FUNC_dynptr_data; } -static bool is_callback_calling_kfunc(u32 btf_id); +static bool is_sync_callback_calling_kfunc(u32 btf_id); static bool is_bpf_throw_kfunc(struct bpf_insn *insn); -static bool is_callback_calling_function(enum bpf_func_id func_id) +static bool is_sync_callback_calling_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_for_each_map_elem || - func_id == BPF_FUNC_timer_set_callback || func_id == BPF_FUNC_find_vma || func_id == BPF_FUNC_loop || func_id == BPF_FUNC_user_ringbuf_drain; @@ -482,6 +481,18 @@ static bool is_async_callback_calling_function(enum bpf_func_id func_id) return func_id == BPF_FUNC_timer_set_callback; } +static bool is_callback_calling_function(enum bpf_func_id func_id) +{ + return is_sync_callback_calling_function(func_id) || + is_async_callback_calling_function(func_id); +} + +static bool is_sync_callback_calling_insn(struct bpf_insn *insn) +{ + return (bpf_helper_call(insn) && is_sync_callback_calling_function(insn->imm)) || + (bpf_pseudo_kfunc_call(insn) && is_sync_callback_calling_kfunc(insn->imm)); +} + static bool is_storage_get_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_sk_storage_get || @@ -1348,6 +1359,7 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, dst_state->first_insn_idx = src->first_insn_idx; dst_state->last_insn_idx = src->last_insn_idx; dst_state->dfs_depth = src->dfs_depth; + dst_state->callback_unroll_depth = src->callback_unroll_depth; dst_state->used_as_loop_entry = src->used_as_loop_entry; for (i = 0; i <= src->curframe; i++) { dst = dst_state->frame[i]; @@ -3131,13 +3143,11 @@ static void mark_insn_zext(struct bpf_verifier_env *env, reg->subreg_def = DEF_NOT_SUBREG; } -static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, - enum reg_arg_type t) +static int __check_reg_arg(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno, + enum reg_arg_type t) { - struct bpf_verifier_state *vstate = env->cur_state; - struct bpf_func_state *state = vstate->frame[vstate->curframe]; struct bpf_insn *insn = env->prog->insnsi + env->insn_idx; - struct bpf_reg_state *reg, *regs = state->regs; + struct bpf_reg_state *reg; bool rw64; if (regno >= MAX_BPF_REG) { @@ -3178,6 +3188,15 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, return 0; } +static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, + enum reg_arg_type t) +{ + struct bpf_verifier_state *vstate = env->cur_state; + struct bpf_func_state *state = vstate->frame[vstate->curframe]; + + return __check_reg_arg(env, state->regs, regno, t); +} + static void mark_jmp_point(struct bpf_verifier_env *env, int idx) { env->insn_aux_data[idx].jmp_point = true; @@ -3416,6 +3435,8 @@ static void fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask) } } +static bool calls_callback(struct bpf_verifier_env *env, int insn_idx); + /* For given verifier state backtrack_insn() is called from the last insn to * the first insn. Its purpose is to compute a bitmask of registers and * stack slots that needs precision in the parent verifier state. @@ -3591,16 +3612,13 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, return -EFAULT; return 0; } - } else if ((bpf_helper_call(insn) && - is_callback_calling_function(insn->imm) && - !is_async_callback_calling_function(insn->imm)) || - (bpf_pseudo_kfunc_call(insn) && is_callback_calling_kfunc(insn->imm))) { - /* callback-calling helper or kfunc call, which means - * we are exiting from subprog, but unlike the subprog - * call handling above, we shouldn't propagate - * precision of r1-r5 (if any requested), as they are - * not actually arguments passed directly to callback - * subprogs + } else if (is_sync_callback_calling_insn(insn) && idx != subseq_idx - 1) { + /* exit from callback subprog to callback-calling helper or + * kfunc call. Use idx/subseq_idx check to discern it from + * straight line code backtracking. + * Unlike the subprog call handling above, we shouldn't + * propagate precision of r1-r5 (if any requested), as they are + * not actually arguments passed directly to callback subprogs */ if (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) { verbose(env, "BUG regs %x\n", bt_reg_mask(bt)); @@ -3635,10 +3653,18 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx, } else if (opcode == BPF_EXIT) { bool r0_precise; + /* Backtracking to a nested function call, 'idx' is a part of + * the inner frame 'subseq_idx' is a part of the outer frame. + * In case of a regular function call, instructions giving + * precision to registers R1-R5 should have been found already. + * In case of a callback, it is ok to have R1-R5 marked for + * backtracking, as these registers are set by the function + * invoking callback. + */ + if (subseq_idx >= 0 && calls_callback(env, subseq_idx)) + for (i = BPF_REG_1; i <= BPF_REG_5; i++) + bt_clear_reg(bt, i); if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) { - /* if backtracing was looking for registers R1-R5 - * they should have been found already. - */ verbose(env, "BUG regs %x\n", bt_reg_mask(bt)); WARN_ONCE(1, "verifier backtracking bug"); return -EFAULT; @@ -9090,7 +9116,7 @@ static void clear_caller_saved_regs(struct bpf_verifier_env *env, /* after the call registers r0 - r5 were scratched */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, regs, caller_saved[i]); - check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); + __check_reg_arg(env, regs, caller_saved[i], DST_OP_NO_MARK); } } @@ -9103,11 +9129,10 @@ static int set_callee_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, int insn_idx); -static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, - int *insn_idx, int subprog, - set_callee_state_fn set_callee_state_cb) +static int setup_func_entry(struct bpf_verifier_env *env, int subprog, int callsite, + set_callee_state_fn set_callee_state_cb, + struct bpf_verifier_state *state) { - struct bpf_verifier_state *state = env->cur_state; struct bpf_func_state *caller, *callee; int err; @@ -9117,54 +9142,72 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -E2BIG; } - caller = state->frame[state->curframe]; if (state->frame[state->curframe + 1]) { verbose(env, "verifier bug. Frame %d already allocated\n", state->curframe + 1); return -EFAULT; } + caller = state->frame[state->curframe]; + callee = kzalloc(sizeof(*callee), GFP_KERNEL); + if (!callee) + return -ENOMEM; + state->frame[state->curframe + 1] = callee; + + /* callee cannot access r0, r6 - r9 for reading and has to write + * into its own stack before reading from it. + * callee can read/write into caller's stack + */ + init_func_state(env, callee, + /* remember the callsite, it will be used by bpf_exit */ + callsite, + state->curframe + 1 /* frameno within this callchain */, + subprog /* subprog number within this prog */); + /* Transfer references to the callee */ + err = copy_reference_state(callee, caller); + err = err ?: set_callee_state_cb(env, caller, callee, callsite); + if (err) + goto err_out; + + /* only increment it after check_reg_arg() finished */ + state->curframe++; + + return 0; + +err_out: + free_func_state(callee); + state->frame[state->curframe + 1] = NULL; + return err; +} + +static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *insn, + int insn_idx, int subprog, + set_callee_state_fn set_callee_state_cb) +{ + struct bpf_verifier_state *state = env->cur_state, *callback_state; + struct bpf_func_state *caller, *callee; + int err; + + caller = state->frame[state->curframe]; err = btf_check_subprog_call(env, subprog, caller->regs); if (err == -EFAULT) return err; - if (subprog_is_global(env, subprog)) { - if (err) { - verbose(env, "Caller passes invalid args into func#%d\n", - subprog); - return err; - } else { - if (env->log.level & BPF_LOG_LEVEL) - verbose(env, - "Func#%d is global and valid. Skipping.\n", - subprog); - clear_caller_saved_regs(env, caller->regs); - - /* All global functions return a 64-bit SCALAR_VALUE */ - mark_reg_unknown(env, caller->regs, BPF_REG_0); - caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG; - - /* continue with next insn after call */ - return 0; - } - } /* set_callee_state is used for direct subprog calls, but we are * interested in validating only BPF helpers that can call subprogs as * callbacks */ - if (set_callee_state_cb != set_callee_state) { - env->subprog_info[subprog].is_cb = true; - if (bpf_pseudo_kfunc_call(insn) && - !is_callback_calling_kfunc(insn->imm)) { - verbose(env, "verifier bug: kfunc %s#%d not marked as callback-calling\n", - func_id_name(insn->imm), insn->imm); - return -EFAULT; - } else if (!bpf_pseudo_kfunc_call(insn) && - !is_callback_calling_function(insn->imm)) { /* helper */ - verbose(env, "verifier bug: helper %s#%d not marked as callback-calling\n", - func_id_name(insn->imm), insn->imm); - return -EFAULT; - } + env->subprog_info[subprog].is_cb = true; + if (bpf_pseudo_kfunc_call(insn) && + !is_sync_callback_calling_kfunc(insn->imm)) { + verbose(env, "verifier bug: kfunc %s#%d not marked as callback-calling\n", + func_id_name(insn->imm), insn->imm); + return -EFAULT; + } else if (!bpf_pseudo_kfunc_call(insn) && + !is_callback_calling_function(insn->imm)) { /* helper */ + verbose(env, "verifier bug: helper %s#%d not marked as callback-calling\n", + func_id_name(insn->imm), insn->imm); + return -EFAULT; } if (insn->code == (BPF_JMP | BPF_CALL) && @@ -9175,53 +9218,83 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn /* there is no real recursion here. timer callbacks are async */ env->subprog_info[subprog].is_async_cb = true; async_cb = push_async_cb(env, env->subprog_info[subprog].start, - *insn_idx, subprog); + insn_idx, subprog); if (!async_cb) return -EFAULT; callee = async_cb->frame[0]; callee->async_entry_cnt = caller->async_entry_cnt + 1; /* Convert bpf_timer_set_callback() args into timer callback args */ - err = set_callee_state_cb(env, caller, callee, *insn_idx); + err = set_callee_state_cb(env, caller, callee, insn_idx); if (err) return err; + return 0; + } + + /* for callback functions enqueue entry to callback and + * proceed with next instruction within current frame. + */ + callback_state = push_stack(env, env->subprog_info[subprog].start, insn_idx, false); + if (!callback_state) + return -ENOMEM; + + err = setup_func_entry(env, subprog, insn_idx, set_callee_state_cb, + callback_state); + if (err) + return err; + + callback_state->callback_unroll_depth++; + callback_state->frame[callback_state->curframe - 1]->callback_depth++; + caller->callback_depth = 0; + return 0; +} + +static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, + int *insn_idx) +{ + struct bpf_verifier_state *state = env->cur_state; + struct bpf_func_state *caller; + int err, subprog, target_insn; + + target_insn = *insn_idx + insn->imm + 1; + subprog = find_subprog(env, target_insn); + if (subprog < 0) { + verbose(env, "verifier bug. No program starts at insn %d\n", target_insn); + return -EFAULT; + } + + caller = state->frame[state->curframe]; + err = btf_check_subprog_call(env, subprog, caller->regs); + if (err == -EFAULT) + return err; + if (subprog_is_global(env, subprog)) { + if (err) { + verbose(env, "Caller passes invalid args into func#%d\n", subprog); + return err; + } + + if (env->log.level & BPF_LOG_LEVEL) + verbose(env, "Func#%d is global and valid. Skipping.\n", subprog); clear_caller_saved_regs(env, caller->regs); + + /* All global functions return a 64-bit SCALAR_VALUE */ mark_reg_unknown(env, caller->regs, BPF_REG_0); caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG; + /* continue with next insn after call */ return 0; } - callee = kzalloc(sizeof(*callee), GFP_KERNEL); - if (!callee) - return -ENOMEM; - state->frame[state->curframe + 1] = callee; - - /* callee cannot access r0, r6 - r9 for reading and has to write - * into its own stack before reading from it. - * callee can read/write into caller's stack + /* for regular function entry setup new frame and continue + * from that frame. */ - init_func_state(env, callee, - /* remember the callsite, it will be used by bpf_exit */ - *insn_idx /* callsite */, - state->curframe + 1 /* frameno within this callchain */, - subprog /* subprog number within this prog */); - - /* Transfer references to the callee */ - err = copy_reference_state(callee, caller); + err = setup_func_entry(env, subprog, *insn_idx, set_callee_state, state); if (err) - goto err_out; - - err = set_callee_state_cb(env, caller, callee, *insn_idx); - if (err) - goto err_out; + return err; clear_caller_saved_regs(env, caller->regs); - /* only increment it after check_reg_arg() finished */ - state->curframe++; - /* and go analyze first insn of the callee */ *insn_idx = env->subprog_info[subprog].start - 1; @@ -9229,14 +9302,10 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn verbose(env, "caller:\n"); print_verifier_state(env, caller, true); verbose(env, "callee:\n"); - print_verifier_state(env, callee, true); + print_verifier_state(env, state->frame[state->curframe], true); } - return 0; -err_out: - free_func_state(callee); - state->frame[state->curframe + 1] = NULL; - return err; + return 0; } int map_set_for_each_callback_args(struct bpf_verifier_env *env, @@ -9280,22 +9349,6 @@ static int set_callee_state(struct bpf_verifier_env *env, return 0; } -static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, - int *insn_idx) -{ - int subprog, target_insn; - - target_insn = *insn_idx + insn->imm + 1; - subprog = find_subprog(env, target_insn); - if (subprog < 0) { - verbose(env, "verifier bug. No program starts at insn %d\n", - target_insn); - return -EFAULT; - } - - return __check_func_call(env, insn, insn_idx, subprog, set_callee_state); -} - static int set_map_elem_callback_state(struct bpf_verifier_env *env, struct bpf_func_state *caller, struct bpf_func_state *callee, @@ -9488,9 +9541,10 @@ static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env) static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) { - struct bpf_verifier_state *state = env->cur_state; + struct bpf_verifier_state *state = env->cur_state, *prev_st; struct bpf_func_state *caller, *callee; struct bpf_reg_state *r0; + bool in_callback_fn; int err; callee = state->frame[state->curframe]; @@ -9519,6 +9573,11 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) verbose_invalid_scalar(env, r0, &range, "callback return", "R0"); return -EINVAL; } + if (!calls_callback(env, callee->callsite)) { + verbose(env, "BUG: in callback at %d, callsite %d !calls_callback\n", + *insn_idx, callee->callsite); + return -EFAULT; + } } else { /* return to the caller whatever r0 had in the callee */ caller->regs[BPF_REG_0] = *r0; @@ -9536,7 +9595,16 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) return err; } - *insn_idx = callee->callsite + 1; + /* for callbacks like bpf_loop or bpf_for_each_map_elem go back to callsite, + * there function call logic would reschedule callback visit. If iteration + * converges is_state_visited() would prune that visit eventually. + */ + in_callback_fn = callee->in_callback_fn; + if (in_callback_fn) + *insn_idx = callee->callsite; + else + *insn_idx = callee->callsite + 1; + if (env->log.level & BPF_LOG_LEVEL) { verbose(env, "returning from callee:\n"); print_verifier_state(env, callee, true); @@ -9547,6 +9615,24 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) * bpf_throw, this will be done by copy_verifier_state for extra frames. */ free_func_state(callee); state->frame[state->curframe--] = NULL; + + /* for callbacks widen imprecise scalars to make programs like below verify: + * + * struct ctx { int i; } + * void cb(int idx, struct ctx *ctx) { ctx->i++; ... } + * ... + * struct ctx = { .i = 0; } + * bpf_loop(100, cb, &ctx, 0); + * + * This is similar to what is done in process_iter_next_call() for open + * coded iterators. + */ + prev_st = in_callback_fn ? find_prev_entry(env, state, *insn_idx) : NULL; + if (prev_st) { + err = widen_imprecise_scalars(env, prev_st, state); + if (err) + return err; + } return 0; } @@ -9952,24 +10038,37 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn } break; case BPF_FUNC_for_each_map_elem: - err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, - set_map_elem_callback_state); + err = push_callback_call(env, insn, insn_idx, meta.subprogno, + set_map_elem_callback_state); break; case BPF_FUNC_timer_set_callback: - err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, - set_timer_callback_state); + err = push_callback_call(env, insn, insn_idx, meta.subprogno, + set_timer_callback_state); break; case BPF_FUNC_find_vma: - err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, - set_find_vma_callback_state); + err = push_callback_call(env, insn, insn_idx, meta.subprogno, + set_find_vma_callback_state); break; case BPF_FUNC_snprintf: err = check_bpf_snprintf_call(env, regs); break; case BPF_FUNC_loop: update_loop_inline_state(env, meta.subprogno); - err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, - set_loop_callback_state); + /* Verifier relies on R1 value to determine if bpf_loop() iteration + * is finished, thus mark it precise. + */ + err = mark_chain_precision(env, BPF_REG_1); + if (err) + return err; + if (cur_func(env)->callback_depth < regs[BPF_REG_1].umax_value) { + err = push_callback_call(env, insn, insn_idx, meta.subprogno, + set_loop_callback_state); + } else { + cur_func(env)->callback_depth = 0; + if (env->log.level & BPF_LOG_LEVEL2) + verbose(env, "frame%d bpf_loop iteration limit reached\n", + env->cur_state->curframe); + } break; case BPF_FUNC_dynptr_from_mem: if (regs[BPF_REG_1].type != PTR_TO_MAP_VALUE) { @@ -10065,8 +10164,8 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn break; } case BPF_FUNC_user_ringbuf_drain: - err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, - set_user_ringbuf_callback_state); + err = push_callback_call(env, insn, insn_idx, meta.subprogno, + set_user_ringbuf_callback_state); break; } @@ -10965,7 +11064,7 @@ static bool is_bpf_graph_api_kfunc(u32 btf_id) btf_id == special_kfunc_list[KF_bpf_refcount_acquire_impl]; } -static bool is_callback_calling_kfunc(u32 btf_id) +static bool is_sync_callback_calling_kfunc(u32 btf_id) { return btf_id == special_kfunc_list[KF_bpf_rbtree_add_impl]; } @@ -11727,6 +11826,21 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, return -EACCES; } + /* Check the arguments */ + err = check_kfunc_args(env, &meta, insn_idx); + if (err < 0) + return err; + + if (meta.func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) { + err = push_callback_call(env, insn, insn_idx, meta.subprogno, + set_rbtree_add_callback_state); + if (err) { + verbose(env, "kfunc %s#%d failed callback verification\n", + func_name, meta.func_id); + return err; + } + } + rcu_lock = is_kfunc_bpf_rcu_read_lock(&meta); rcu_unlock = is_kfunc_bpf_rcu_read_unlock(&meta); @@ -11762,10 +11876,6 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, return -EINVAL; } - /* Check the arguments */ - err = check_kfunc_args(env, &meta, insn_idx); - if (err < 0) - return err; /* In case of release function, we get register number of refcounted * PTR_TO_BTF_ID in bpf_kfunc_arg_meta, do the release now. */ @@ -11799,16 +11909,6 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, } } - if (meta.func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) { - err = __check_func_call(env, insn, insn_idx_p, meta.subprogno, - set_rbtree_add_callback_state); - if (err) { - verbose(env, "kfunc %s#%d failed callback verification\n", - func_name, meta.func_id); - return err; - } - } - if (meta.func_id == special_kfunc_list[KF_bpf_throw]) { if (!bpf_jit_supports_exceptions()) { verbose(env, "JIT does not support calling kfunc %s#%d\n", @@ -15079,6 +15179,15 @@ static bool is_force_checkpoint(struct bpf_verifier_env *env, int insn_idx) return env->insn_aux_data[insn_idx].force_checkpoint; } +static void mark_calls_callback(struct bpf_verifier_env *env, int idx) +{ + env->insn_aux_data[idx].calls_callback = true; +} + +static bool calls_callback(struct bpf_verifier_env *env, int insn_idx) +{ + return env->insn_aux_data[insn_idx].calls_callback; +} enum { DONE_EXPLORING = 0, @@ -15192,6 +15301,21 @@ static int visit_insn(int t, struct bpf_verifier_env *env) * async state will be pushed for further exploration. */ mark_prune_point(env, t); + /* For functions that invoke callbacks it is not known how many times + * callback would be called. Verifier models callback calling functions + * by repeatedly visiting callback bodies and returning to origin call + * instruction. + * In order to stop such iteration verifier needs to identify when a + * state identical some state from a previous iteration is reached. + * Check below forces creation of checkpoint before callback calling + * instruction to allow search for such identical states. + */ + if (is_sync_callback_calling_insn(insn)) { + mark_calls_callback(env, t); + mark_force_checkpoint(env, t); + mark_prune_point(env, t); + mark_jmp_point(env, t); + } if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { struct bpf_kfunc_call_arg_meta meta; @@ -16661,10 +16785,16 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) } goto skip_inf_loop_check; } + if (calls_callback(env, insn_idx)) { + if (states_equal(env, &sl->state, cur, true)) + goto hit; + goto skip_inf_loop_check; + } /* attempt to detect infinite loop to avoid unnecessary doomed work */ if (states_maybe_looping(&sl->state, cur) && states_equal(env, &sl->state, cur, false) && - !iter_active_depths_differ(&sl->state, cur)) { + !iter_active_depths_differ(&sl->state, cur) && + sl->state.callback_unroll_depth == cur->callback_unroll_depth) { verbose_linfo(env, insn_idx, "; "); verbose(env, "infinite loop detected at insn %d\n", insn_idx); verbose(env, "cur state:"); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 4e610863cc37..8f3cef1a4d8a 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3898,14 +3898,6 @@ static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of, return psi_trigger_poll(&ctx->psi.trigger, of->file, pt); } -static int cgroup_pressure_open(struct kernfs_open_file *of) -{ - if (of->file->f_mode & FMODE_WRITE && !capable(CAP_SYS_RESOURCE)) - return -EPERM; - - return 0; -} - static void cgroup_pressure_release(struct kernfs_open_file *of) { struct cgroup_file_ctx *ctx = of->priv; @@ -5312,7 +5304,6 @@ static struct cftype cgroup_psi_files[] = { { .name = "io.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_IO]), - .open = cgroup_pressure_open, .seq_show = cgroup_io_pressure_show, .write = cgroup_io_pressure_write, .poll = cgroup_pressure_poll, @@ -5321,7 +5312,6 @@ static struct cftype cgroup_psi_files[] = { { .name = "memory.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_MEM]), - .open = cgroup_pressure_open, .seq_show = cgroup_memory_pressure_show, .write = cgroup_memory_pressure_write, .poll = cgroup_pressure_poll, @@ -5330,7 +5320,6 @@ static struct cftype cgroup_psi_files[] = { { .name = "cpu.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_CPU]), - .open = cgroup_pressure_open, .seq_show = cgroup_cpu_pressure_show, .write = cgroup_cpu_pressure_write, .poll = cgroup_pressure_poll, @@ -5340,7 +5329,6 @@ static struct cftype cgroup_psi_files[] = { { .name = "irq.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_IRQ]), - .open = cgroup_pressure_open, .seq_show = cgroup_irq_pressure_show, .write = cgroup_irq_pressure_write, .poll = cgroup_pressure_poll, diff --git a/kernel/cpu.c b/kernel/cpu.c index 9e4c6780adde..a86972a91991 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -2113,7 +2113,7 @@ static struct cpuhp_step cpuhp_hp_states[] = { [CPUHP_HRTIMERS_PREPARE] = { .name = "hrtimers:prepare", .startup.single = hrtimers_prepare_cpu, - .teardown.single = hrtimers_dead_cpu, + .teardown.single = NULL, }, [CPUHP_SMPCFD_PREPARE] = { .name = "smpcfd:prepare", @@ -2205,6 +2205,12 @@ static struct cpuhp_step cpuhp_hp_states[] = { .startup.single = NULL, .teardown.single = smpcfd_dying_cpu, }, + [CPUHP_AP_HRTIMERS_DYING] = { + .name = "hrtimers:dying", + .startup.single = NULL, + .teardown.single = hrtimers_cpu_dying, + }, + /* Entry state on starting. Interrupts enabled from here on. Transient * state for synchronsization */ [CPUHP_AP_ONLINE] = { diff --git a/kernel/events/core.c b/kernel/events/core.c index 683dc086ef10..b704d83a28b2 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4828,6 +4828,11 @@ find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx, void *task_ctx_data = NULL; if (!ctx->task) { + /* + * perf_pmu_migrate_context() / __perf_pmu_install_event() + * relies on the fact that find_get_pmu_context() cannot fail + * for CPU contexts. + */ struct perf_cpu_pmu_context *cpc; cpc = per_cpu_ptr(pmu->cpu_pmu_context, event->cpu); @@ -12889,6 +12894,9 @@ static void __perf_pmu_install_event(struct pmu *pmu, int cpu, struct perf_event *event) { struct perf_event_pmu_context *epc; + struct perf_event_context *old_ctx = event->ctx; + + get_ctx(ctx); /* normally find_get_context() */ event->cpu = cpu; epc = find_get_pmu_context(pmu, ctx, event); @@ -12897,6 +12905,11 @@ static void __perf_pmu_install_event(struct pmu *pmu, if (event->state >= PERF_EVENT_STATE_OFF) event->state = PERF_EVENT_STATE_INACTIVE; perf_install_in_context(ctx, event, cpu); + + /* + * Now that event->ctx is updated and visible, put the old ctx. + */ + put_ctx(old_ctx); } static void __perf_pmu_install(struct perf_event_context *ctx, @@ -12935,6 +12948,10 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu) struct perf_event_context *src_ctx, *dst_ctx; LIST_HEAD(events); + /* + * Since per-cpu context is persistent, no need to grab an extra + * reference. + */ src_ctx = &per_cpu_ptr(&perf_cpu_context, src_cpu)->ctx; dst_ctx = &per_cpu_ptr(&perf_cpu_context, dst_cpu)->ctx; diff --git a/kernel/futex/core.c b/kernel/futex/core.c index 52695c59d041..dad981a865b8 100644 --- a/kernel/futex/core.c +++ b/kernel/futex/core.c @@ -700,7 +700,8 @@ retry: owner = uval & FUTEX_TID_MASK; if (pending_op && !pi && !owner) { - futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY); + futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1, + FUTEX_BITSET_MATCH_ANY); return 0; } @@ -752,8 +753,10 @@ retry: * Wake robust non-PI futexes here. The wakeup of * PI futexes happens in exit_pi_state(): */ - if (!pi && (uval & FUTEX_WAITERS)) - futex_wake(uaddr, 1, 1, FUTEX_BITSET_MATCH_ANY); + if (!pi && (uval & FUTEX_WAITERS)) { + futex_wake(uaddr, FLAGS_SIZE_32 | FLAGS_SHARED, 1, + FUTEX_BITSET_MATCH_ANY); + } return 0; } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 2048138ce54b..d7a3c63a2171 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3666,41 +3666,140 @@ static inline void dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { } #endif +static void reweight_eevdf(struct cfs_rq *cfs_rq, struct sched_entity *se, + unsigned long weight) +{ + unsigned long old_weight = se->load.weight; + u64 avruntime = avg_vruntime(cfs_rq); + s64 vlag, vslice; + + /* + * VRUNTIME + * ======== + * + * COROLLARY #1: The virtual runtime of the entity needs to be + * adjusted if re-weight at !0-lag point. + * + * Proof: For contradiction assume this is not true, so we can + * re-weight without changing vruntime at !0-lag point. + * + * Weight VRuntime Avg-VRuntime + * before w v V + * after w' v' V' + * + * Since lag needs to be preserved through re-weight: + * + * lag = (V - v)*w = (V'- v')*w', where v = v' + * ==> V' = (V - v)*w/w' + v (1) + * + * Let W be the total weight of the entities before reweight, + * since V' is the new weighted average of entities: + * + * V' = (WV + w'v - wv) / (W + w' - w) (2) + * + * by using (1) & (2) we obtain: + * + * (WV + w'v - wv) / (W + w' - w) = (V - v)*w/w' + v + * ==> (WV-Wv+Wv+w'v-wv)/(W+w'-w) = (V - v)*w/w' + v + * ==> (WV - Wv)/(W + w' - w) + v = (V - v)*w/w' + v + * ==> (V - v)*W/(W + w' - w) = (V - v)*w/w' (3) + * + * Since we are doing at !0-lag point which means V != v, we + * can simplify (3): + * + * ==> W / (W + w' - w) = w / w' + * ==> Ww' = Ww + ww' - ww + * ==> W * (w' - w) = w * (w' - w) + * ==> W = w (re-weight indicates w' != w) + * + * So the cfs_rq contains only one entity, hence vruntime of + * the entity @v should always equal to the cfs_rq's weighted + * average vruntime @V, which means we will always re-weight + * at 0-lag point, thus breach assumption. Proof completed. + * + * + * COROLLARY #2: Re-weight does NOT affect weighted average + * vruntime of all the entities. + * + * Proof: According to corollary #1, Eq. (1) should be: + * + * (V - v)*w = (V' - v')*w' + * ==> v' = V' - (V - v)*w/w' (4) + * + * According to the weighted average formula, we have: + * + * V' = (WV - wv + w'v') / (W - w + w') + * = (WV - wv + w'(V' - (V - v)w/w')) / (W - w + w') + * = (WV - wv + w'V' - Vw + wv) / (W - w + w') + * = (WV + w'V' - Vw) / (W - w + w') + * + * ==> V'*(W - w + w') = WV + w'V' - Vw + * ==> V' * (W - w) = (W - w) * V (5) + * + * If the entity is the only one in the cfs_rq, then reweight + * always occurs at 0-lag point, so V won't change. Or else + * there are other entities, hence W != w, then Eq. (5) turns + * into V' = V. So V won't change in either case, proof done. + * + * + * So according to corollary #1 & #2, the effect of re-weight + * on vruntime should be: + * + * v' = V' - (V - v) * w / w' (4) + * = V - (V - v) * w / w' + * = V - vl * w / w' + * = V - vl' + */ + if (avruntime != se->vruntime) { + vlag = (s64)(avruntime - se->vruntime); + vlag = div_s64(vlag * old_weight, weight); + se->vruntime = avruntime - vlag; + } + + /* + * DEADLINE + * ======== + * + * When the weight changes, the virtual time slope changes and + * we should adjust the relative virtual deadline accordingly. + * + * d' = v' + (d - v)*w/w' + * = V' - (V - v)*w/w' + (d - v)*w/w' + * = V - (V - v)*w/w' + (d - v)*w/w' + * = V + (d - V)*w/w' + */ + vslice = (s64)(se->deadline - avruntime); + vslice = div_s64(vslice * old_weight, weight); + se->deadline = avruntime + vslice; +} + static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, unsigned long weight) { - unsigned long old_weight = se->load.weight; + bool curr = cfs_rq->curr == se; if (se->on_rq) { /* commit outstanding execution time */ - if (cfs_rq->curr == se) + if (curr) update_curr(cfs_rq); else - avg_vruntime_sub(cfs_rq, se); + __dequeue_entity(cfs_rq, se); update_load_sub(&cfs_rq->load, se->load.weight); } dequeue_load_avg(cfs_rq, se); - update_load_set(&se->load, weight); - if (!se->on_rq) { /* * Because we keep se->vlag = V - v_i, while: lag_i = w_i*(V - v_i), * we need to scale se->vlag when w_i changes. */ - se->vlag = div_s64(se->vlag * old_weight, weight); + se->vlag = div_s64(se->vlag * se->load.weight, weight); } else { - s64 deadline = se->deadline - se->vruntime; - /* - * When the weight changes, the virtual time slope changes and - * we should adjust the relative virtual deadline accordingly. - */ - deadline = div_s64(deadline * old_weight, weight); - se->deadline = se->vruntime + deadline; - if (se != cfs_rq->curr) - min_deadline_cb_propagate(&se->run_node, NULL); + reweight_eevdf(cfs_rq, se, weight); } + update_load_set(&se->load, weight); + #ifdef CONFIG_SMP do { u32 divider = get_pelt_divider(&se->avg); @@ -3712,8 +3811,17 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, enqueue_load_avg(cfs_rq, se); if (se->on_rq) { update_load_add(&cfs_rq->load, se->load.weight); - if (cfs_rq->curr != se) - avg_vruntime_add(cfs_rq, se); + if (!curr) { + /* + * The entity's vruntime has been adjusted, so let's check + * whether the rq-wide min_vruntime needs updated too. Since + * the calculations above require stable min_vruntime rather + * than up-to-date one, we do the update at the end of the + * reweight process. + */ + __enqueue_entity(cfs_rq, se); + update_min_vruntime(cfs_rq); + } } } @@ -3857,14 +3965,11 @@ static void update_cfs_group(struct sched_entity *se) #ifndef CONFIG_SMP shares = READ_ONCE(gcfs_rq->tg->shares); - - if (likely(se->load.weight == shares)) - return; #else - shares = calc_group_shares(gcfs_rq); + shares = calc_group_shares(gcfs_rq); #endif - - reweight_entity(cfs_rq_of(se), se, shares); + if (unlikely(se->load.weight != shares)) + reweight_entity(cfs_rq_of(se), se, shares); } #else /* CONFIG_FAIR_GROUP_SCHED */ @@ -11079,12 +11184,16 @@ static int should_we_balance(struct lb_env *env) continue; } - /* Are we the first idle CPU? */ + /* + * Are we the first idle core in a non-SMT domain or higher, + * or the first idle CPU in a SMT domain? + */ return cpu == env->dst_cpu; } - if (idle_smt == env->dst_cpu) - return true; + /* Are we the first idle CPU with busy siblings? */ + if (idle_smt != -1) + return idle_smt == env->dst_cpu; /* Are we the first CPU of this group ? */ return group_balance_cpu(sg) == env->dst_cpu; diff --git a/kernel/sys.c b/kernel/sys.c index 420d9cb9cc8e..e219fcfa112d 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2394,6 +2394,10 @@ static inline int prctl_set_mdwe(unsigned long bits, unsigned long arg3, if (bits & PR_MDWE_NO_INHERIT && !(bits & PR_MDWE_REFUSE_EXEC_GAIN)) return -EINVAL; + /* PARISC cannot allow mdwe as it needs writable stacks */ + if (IS_ENABLED(CONFIG_PARISC)) + return -EINVAL; + current_bits = get_current_mdwe(); if (current_bits && current_bits != bits) return -EPERM; /* Cannot unset the flags */ diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 238262e4aba7..760793998cdd 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -2219,29 +2219,22 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, } } -int hrtimers_dead_cpu(unsigned int scpu) +int hrtimers_cpu_dying(unsigned int dying_cpu) { struct hrtimer_cpu_base *old_base, *new_base; - int i; + int i, ncpu = cpumask_first(cpu_active_mask); - BUG_ON(cpu_online(scpu)); - tick_cancel_sched_timer(scpu); + tick_cancel_sched_timer(dying_cpu); + + old_base = this_cpu_ptr(&hrtimer_bases); + new_base = &per_cpu(hrtimer_bases, ncpu); - /* - * this BH disable ensures that raise_softirq_irqoff() does - * not wakeup ksoftirqd (and acquire the pi-lock) while - * holding the cpu_base lock - */ - local_bh_disable(); - local_irq_disable(); - old_base = &per_cpu(hrtimer_bases, scpu); - new_base = this_cpu_ptr(&hrtimer_bases); /* * The caller is globally serialized and nobody else * takes two locks at once, deadlock is not possible. */ - raw_spin_lock(&new_base->lock); - raw_spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); + raw_spin_lock(&old_base->lock); + raw_spin_lock_nested(&new_base->lock, SINGLE_DEPTH_NESTING); for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { migrate_hrtimer_list(&old_base->clock_base[i], @@ -2252,15 +2245,13 @@ int hrtimers_dead_cpu(unsigned int scpu) * The migration might have changed the first expiring softirq * timer on this CPU. Update it. */ - hrtimer_update_softirq_timer(new_base, false); + __hrtimer_get_next_event(new_base, HRTIMER_ACTIVE_SOFT); + /* Tell the other CPU to retrigger the next event */ + smp_call_function_single(ncpu, retrigger_next_event, NULL, 0); - raw_spin_unlock(&old_base->lock); raw_spin_unlock(&new_base->lock); + raw_spin_unlock(&old_base->lock); - /* Check, if we got expired work to do */ - __hrtimer_peek_ahead_timers(); - local_irq_enable(); - local_bh_enable(); return 0; } diff --git a/mm/damon/core.c b/mm/damon/core.c index 630077d95dc6..6262d55904e7 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -924,7 +924,7 @@ static bool __damos_filter_out(struct damon_ctx *ctx, struct damon_target *t, matched = true; break; default: - break; + return false; } return matched == filter->matching; diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c index 45bd0fd4a8b1..be667236b8e6 100644 --- a/mm/damon/sysfs-schemes.c +++ b/mm/damon/sysfs-schemes.c @@ -162,6 +162,9 @@ damon_sysfs_scheme_regions_alloc(void) struct damon_sysfs_scheme_regions *regions = kmalloc(sizeof(*regions), GFP_KERNEL); + if (!regions) + return NULL; + regions->kobj = (struct kobject){}; INIT_LIST_HEAD(®ions->regions_list); regions->nr_regions = 0; @@ -1823,6 +1826,8 @@ static int damon_sysfs_before_damos_apply(struct damon_ctx *ctx, return 0; region = damon_sysfs_scheme_region_alloc(r); + if (!region) + return 0; list_add_tail(®ion->list, &sysfs_regions->regions_list); sysfs_regions->nr_regions++; if (kobject_init_and_add(®ion->kobj, diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index e27846708b5a..7472404456aa 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -1172,7 +1172,7 @@ static int damon_sysfs_update_target(struct damon_target *target, struct damon_ctx *ctx, struct damon_sysfs_target *sys_target) { - int err; + int err = 0; if (damon_target_has_pid(ctx)) { err = damon_sysfs_update_target_pid(target, sys_target->pid); @@ -1203,8 +1203,10 @@ static int damon_sysfs_set_targets(struct damon_ctx *ctx, damon_for_each_target_safe(t, next, ctx) { if (i < sysfs_targets->nr) { - damon_sysfs_update_target(t, ctx, + err = damon_sysfs_update_target(t, ctx, sysfs_targets->targets_arr[i]); + if (err) + return err; } else { if (damon_target_has_pid(ctx)) put_pid(t->pid); diff --git a/mm/filemap.c b/mm/filemap.c index 9710f43a89ac..32eedf3afd45 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3443,7 +3443,7 @@ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf, * handled in the specific fault path, and it'll prohibit the * fault-around logic. */ - if (!pte_none(vmf->pte[count])) + if (!pte_none(ptep_get(&vmf->pte[count]))) goto skip; count++; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index f31f02472396..4f542444a91f 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2769,13 +2769,15 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) int nr = folio_nr_pages(folio); xas_split(&xas, folio, folio_order(folio)); - if (folio_test_swapbacked(folio)) { - __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, - -nr); - } else { - __lruvec_stat_mod_folio(folio, NR_FILE_THPS, - -nr); - filemap_nr_thps_dec(mapping); + if (folio_test_pmd_mappable(folio)) { + if (folio_test_swapbacked(folio)) { + __lruvec_stat_mod_folio(folio, + NR_SHMEM_THPS, -nr); + } else { + __lruvec_stat_mod_folio(folio, + NR_FILE_THPS, -nr); + filemap_nr_thps_dec(mapping); + } } } @@ -468,7 +468,7 @@ static int break_ksm_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long nex page = pfn_swap_entry_to_page(entry); } /* return 1 if the page is an normal ksm page or KSM-placed zero page */ - ret = (page && PageKsm(page)) || is_ksm_zero_pte(*pte); + ret = (page && PageKsm(page)) || is_ksm_zero_pte(ptent); pte_unmap_unlock(pte, ptl); return ret; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 774bd6e21e27..1c1061df9cd1 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2936,7 +2936,8 @@ void mem_cgroup_commit_charge(struct folio *folio, struct mem_cgroup *memcg) * Moreover, it should not come from DMA buffer and is not readily * reclaimable. So those GFP bits should be masked off. */ -#define OBJCGS_CLEAR_MASK (__GFP_DMA | __GFP_RECLAIMABLE | __GFP_ACCOUNT) +#define OBJCGS_CLEAR_MASK (__GFP_DMA | __GFP_RECLAIMABLE | \ + __GFP_ACCOUNT | __GFP_NOFAIL) /* * mod_objcg_mlstate() may be called with irq enabled, so diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 96d9eae5c7cc..0b6ca553bebe 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -312,7 +312,7 @@ static int mfill_atomic_pte_poison(pmd_t *dst_pmd, ret = -EEXIST; /* Refuse to overwrite any PTE, even a PTE marker (e.g. UFFD WP). */ - if (!pte_none(*dst_pte)) + if (!pte_none(ptep_get(dst_pte))) goto out_unlock; set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte); diff --git a/mm/util.c b/mm/util.c index aa01f6ea5a75..744b4d7e3fae 100644 --- a/mm/util.c +++ b/mm/util.c @@ -414,6 +414,15 @@ static int mmap_is_legacy(struct rlimit *rlim_stack) static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack) { +#ifdef CONFIG_STACK_GROWSUP + /* + * For an upwards growing stack the calculation is much simpler. + * Memory for the maximum stack size is reserved at the top of the + * task. mmap_base starts directly below the stack and grows + * downwards. + */ + return PAGE_ALIGN_DOWN(mmap_upper_limit(rlim_stack) - rnd); +#else unsigned long gap = rlim_stack->rlim_cur; unsigned long pad = stack_guard_gap; @@ -431,6 +440,7 @@ static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack) gap = MAX_GAP; return PAGE_ALIGN(STACK_TOP - gap - rnd); +#endif } void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) diff --git a/net/core/dev.c b/net/core/dev.c index 0bdc6bf758f3..3950ced396b5 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -10051,6 +10051,54 @@ void netif_tx_stop_all_queues(struct net_device *dev) } EXPORT_SYMBOL(netif_tx_stop_all_queues); +static int netdev_do_alloc_pcpu_stats(struct net_device *dev) +{ + void __percpu *v; + + /* Drivers implementing ndo_get_peer_dev must support tstat + * accounting, so that skb_do_redirect() can bump the dev's + * RX stats upon network namespace switch. + */ + if (dev->netdev_ops->ndo_get_peer_dev && + dev->pcpu_stat_type != NETDEV_PCPU_STAT_TSTATS) + return -EOPNOTSUPP; + + switch (dev->pcpu_stat_type) { + case NETDEV_PCPU_STAT_NONE: + return 0; + case NETDEV_PCPU_STAT_LSTATS: + v = dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats); + break; + case NETDEV_PCPU_STAT_TSTATS: + v = dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + break; + case NETDEV_PCPU_STAT_DSTATS: + v = dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats); + break; + default: + return -EINVAL; + } + + return v ? 0 : -ENOMEM; +} + +static void netdev_do_free_pcpu_stats(struct net_device *dev) +{ + switch (dev->pcpu_stat_type) { + case NETDEV_PCPU_STAT_NONE: + return; + case NETDEV_PCPU_STAT_LSTATS: + free_percpu(dev->lstats); + break; + case NETDEV_PCPU_STAT_TSTATS: + free_percpu(dev->tstats); + break; + case NETDEV_PCPU_STAT_DSTATS: + free_percpu(dev->dstats); + break; + } +} + /** * register_netdevice() - register a network device * @dev: device to register @@ -10111,9 +10159,13 @@ int register_netdevice(struct net_device *dev) goto err_uninit; } + ret = netdev_do_alloc_pcpu_stats(dev); + if (ret) + goto err_uninit; + ret = dev_index_reserve(net, dev->ifindex); if (ret < 0) - goto err_uninit; + goto err_free_pcpu; dev->ifindex = ret; /* Transfer changeable features to wanted_features and enable @@ -10219,6 +10271,8 @@ err_uninit_notify: call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev); err_ifindex_release: dev_index_release(net, dev->ifindex); +err_free_pcpu: + netdev_do_free_pcpu_stats(dev); err_uninit: if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); @@ -10471,6 +10525,7 @@ void netdev_run_todo(void) WARN_ON(rcu_access_pointer(dev->ip_ptr)); WARN_ON(rcu_access_pointer(dev->ip6_ptr)); + netdev_do_free_pcpu_stats(dev); if (dev->priv_destructor) dev->priv_destructor(dev); if (dev->needs_free_netdev) diff --git a/net/core/filter.c b/net/core/filter.c index 383f96b0a1c7..7e4d7c3bcc84 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -81,6 +81,7 @@ #include <net/xdp.h> #include <net/mptcp.h> #include <net/netfilter/nf_conntrack_bpf.h> +#include <net/netkit.h> #include <linux/un.h> #include "dev.h" @@ -2468,6 +2469,16 @@ static const struct bpf_func_proto bpf_clone_redirect_proto = { DEFINE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info); EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info); +static struct net_device *skb_get_peer_dev(struct net_device *dev) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (likely(ops->ndo_get_peer_dev)) + return INDIRECT_CALL_1(ops->ndo_get_peer_dev, + netkit_peer_dev, dev); + return NULL; +} + int skb_do_redirect(struct sk_buff *skb) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); @@ -2481,17 +2492,15 @@ int skb_do_redirect(struct sk_buff *skb) if (unlikely(!dev)) goto out_drop; if (flags & BPF_F_PEER) { - const struct net_device_ops *ops = dev->netdev_ops; - - if (unlikely(!ops->ndo_get_peer_dev || - !skb_at_tc_ingress(skb))) + if (unlikely(!skb_at_tc_ingress(skb))) goto out_drop; - dev = ops->ndo_get_peer_dev(dev); + dev = skb_get_peer_dev(dev); if (unlikely(!dev || !(dev->flags & IFF_UP) || net_eq(net, dev_net(dev)))) goto out_drop; skb->dev = dev; + dev_sw_netstats_rx_add(dev, skb->len); return -EAGAIN; } return flags & BPF_F_NEIGH ? diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index f01aee832aab..7d0e7aaa71e0 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -1481,5 +1481,6 @@ static void __exit inet_diag_exit(void) module_init(inet_diag_init); module_exit(inet_diag_exit); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("INET/INET6: socket monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2 /* AF_INET */); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 10 /* AF_INET6 */); diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c index 63a40e4b678f..fe2140c8375c 100644 --- a/net/ipv4/raw_diag.c +++ b/net/ipv4/raw_diag.c @@ -257,5 +257,6 @@ static void __exit raw_diag_exit(void) module_init(raw_diag_init); module_exit(raw_diag_exit); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("RAW socket monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-255 /* AF_INET - IPPROTO_RAW */); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 10-255 /* AF_INET6 - IPPROTO_RAW */); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 3290a4442b4a..16615d107cf0 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -780,7 +780,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow goto reject_redirect; } - n = __ipv4_neigh_lookup(rt->dst.dev, new_gw); + n = __ipv4_neigh_lookup(rt->dst.dev, (__force u32)new_gw); if (!n) n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev); if (!IS_ERR(n)) { diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index 01b50fa79189..4cbe4b44425a 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -247,4 +247,5 @@ static void __exit tcp_diag_exit(void) module_init(tcp_diag_init); module_exit(tcp_diag_exit); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("TCP socket monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-6 /* AF_INET - IPPROTO_TCP */); diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index de3f2d31f510..dc41a22ee80e 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -296,5 +296,6 @@ static void __exit udp_diag_exit(void) module_init(udp_diag_init); module_exit(udp_diag_exit); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("UDP socket monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-17 /* AF_INET - IPPROTO_UDP */); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-136 /* AF_INET - IPPROTO_UDPLITE */); diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c index 8df1bdb647e2..5409c2ea3f57 100644 --- a/net/mptcp/mptcp_diag.c +++ b/net/mptcp/mptcp_diag.c @@ -245,4 +245,5 @@ static void __exit mptcp_diag_exit(void) module_init(mptcp_diag_init); module_exit(mptcp_diag_exit); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("MPTCP socket monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-262 /* AF_INET - IPPROTO_MPTCP */); diff --git a/net/packet/diag.c b/net/packet/diag.c index f6b200cb3c06..9a7980e3309d 100644 --- a/net/packet/diag.c +++ b/net/packet/diag.c @@ -262,4 +262,5 @@ static void __exit packet_diag_exit(void) module_init(packet_diag_init); module_exit(packet_diag_exit); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("PACKET socket monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 17 /* AF_PACKET */); diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index 981ca5b98bcb..1d95f8bc769f 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -73,6 +73,7 @@ static void rxrpc_destroy_client_conn_ids(struct rxrpc_local *local) static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_call *call, gfp_t gfp) { + static atomic_t rxrpc_bundle_id; struct rxrpc_bundle *bundle; bundle = kzalloc(sizeof(*bundle), gfp); @@ -85,6 +86,7 @@ static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_call *call, bundle->upgrade = test_bit(RXRPC_CALL_UPGRADE, &call->flags); bundle->service_id = call->dest_srx.srx_service; bundle->security_level = call->security_level; + bundle->debug_id = atomic_inc_return(&rxrpc_bundle_id); refcount_set(&bundle->ref, 1); atomic_set(&bundle->active, 1); INIT_LIST_HEAD(&bundle->waiting_calls); @@ -105,7 +107,8 @@ struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *bundle, static void rxrpc_free_bundle(struct rxrpc_bundle *bundle) { - trace_rxrpc_bundle(bundle->debug_id, 1, rxrpc_bundle_free); + trace_rxrpc_bundle(bundle->debug_id, refcount_read(&bundle->ref), + rxrpc_bundle_free); rxrpc_put_peer(bundle->peer, rxrpc_peer_put_bundle); key_put(bundle->key); kfree(bundle); @@ -239,7 +242,6 @@ dont_reuse: */ int rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t gfp) { - static atomic_t rxrpc_bundle_id; struct rxrpc_bundle *bundle, *candidate; struct rxrpc_local *local = call->local; struct rb_node *p, **pp, *parent; @@ -306,7 +308,6 @@ int rxrpc_look_up_bundle(struct rxrpc_call *call, gfp_t gfp) } _debug("new bundle"); - candidate->debug_id = atomic_inc_return(&rxrpc_bundle_id); rb_link_node(&candidate->local_node, parent, pp); rb_insert_color(&candidate->local_node, &local->client_bundles); call->bundle = rxrpc_get_bundle(candidate, rxrpc_bundle_get_client_call); diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index 030d64f282f3..92495e73b869 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -643,12 +643,8 @@ static void rxrpc_complete_rtt_probe(struct rxrpc_call *call, clear_bit(i + RXRPC_CALL_RTT_PEND_SHIFT, &call->rtt_avail); smp_mb(); /* Read data before setting avail bit */ set_bit(i, &call->rtt_avail); - if (type != rxrpc_rtt_rx_cancel) - rxrpc_peer_add_rtt(call, type, i, acked_serial, ack_serial, - sent_at, resp_time); - else - trace_rxrpc_rtt_rx(call, rxrpc_rtt_rx_cancel, i, - orig_serial, acked_serial, 0, 0); + rxrpc_peer_add_rtt(call, type, i, acked_serial, ack_serial, + sent_at, resp_time); matched = true; } @@ -801,28 +797,21 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) summary.ack_reason, nr_acks); rxrpc_inc_stat(call->rxnet, stat_rx_acks[ack.reason]); - switch (ack.reason) { - case RXRPC_ACK_PING_RESPONSE: - rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, - rxrpc_rtt_rx_ping_response); - break; - case RXRPC_ACK_REQUESTED: - rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, - rxrpc_rtt_rx_requested_ack); - break; - default: - if (acked_serial != 0) + if (acked_serial != 0) { + switch (ack.reason) { + case RXRPC_ACK_PING_RESPONSE: rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, - rxrpc_rtt_rx_cancel); - break; - } - - if (ack.reason == RXRPC_ACK_PING) { - rxrpc_send_ACK(call, RXRPC_ACK_PING_RESPONSE, ack_serial, - rxrpc_propose_ack_respond_to_ping); - } else if (sp->hdr.flags & RXRPC_REQUEST_ACK) { - rxrpc_send_ACK(call, RXRPC_ACK_REQUESTED, ack_serial, - rxrpc_propose_ack_respond_to_ack); + rxrpc_rtt_rx_ping_response); + break; + case RXRPC_ACK_REQUESTED: + rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, + rxrpc_rtt_rx_requested_ack); + break; + default: + rxrpc_complete_rtt_probe(call, skb->tstamp, acked_serial, ack_serial, + rxrpc_rtt_rx_other_ack); + break; + } } /* If we get an EXCEEDS_WINDOW ACK from the server, it probably @@ -835,7 +824,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_is_client_call(call)) { rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, 0, -ENETRESET); - return; + goto send_response; } /* If we get an OUT_OF_SEQUENCE ACK from the server, that can also @@ -849,7 +838,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_is_client_call(call)) { rxrpc_set_call_completion(call, RXRPC_CALL_REMOTELY_ABORTED, 0, -ENETRESET); - return; + goto send_response; } /* Discard any out-of-order or duplicate ACKs (outside lock). */ @@ -857,7 +846,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) trace_rxrpc_rx_discard_ack(call->debug_id, ack_serial, first_soft_ack, call->acks_first_seq, prev_pkt, call->acks_prev_seq); - return; + goto send_response; } info.rxMTU = 0; @@ -897,7 +886,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) case RXRPC_CALL_SERVER_AWAIT_ACK: break; default: - return; + goto send_response; } if (before(hard_ack, call->acks_hard_ack) || @@ -909,7 +898,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) if (after(hard_ack, call->acks_hard_ack)) { if (rxrpc_rotate_tx_window(call, hard_ack, &summary)) { rxrpc_end_tx_phase(call, false, rxrpc_eproto_unexpected_ack); - return; + goto send_response; } } @@ -927,6 +916,14 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) rxrpc_propose_ack_ping_for_lost_reply); rxrpc_congestion_management(call, skb, &summary, acked_serial); + +send_response: + if (ack.reason == RXRPC_ACK_PING) + rxrpc_send_ACK(call, RXRPC_ACK_PING_RESPONSE, ack_serial, + rxrpc_propose_ack_respond_to_ping); + else if (sp->hdr.flags & RXRPC_REQUEST_ACK) + rxrpc_send_ACK(call, RXRPC_ACK_REQUESTED, ack_serial, + rxrpc_propose_ack_respond_to_ack); } /* diff --git a/net/sctp/diag.c b/net/sctp/diag.c index c3d6b92dd386..eb05131ff1dd 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -527,4 +527,5 @@ static void __exit sctp_diag_exit(void) module_init(sctp_diag_init); module_exit(sctp_diag_exit); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("SCTP socket monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-132); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index da97f946b79b..2a1388841951 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -598,8 +598,12 @@ static int smcr_clnt_conf_first_link(struct smc_sock *smc) struct smc_llc_qentry *qentry; int rc; - /* receive CONFIRM LINK request from server over RoCE fabric */ - qentry = smc_llc_wait(link->lgr, NULL, SMC_LLC_WAIT_TIME, + /* Receive CONFIRM LINK request from server over RoCE fabric. + * Increasing the client's timeout by twice as much as the server's + * timeout by default can temporarily avoid decline messages of + * both sides crossing or colliding + */ + qentry = smc_llc_wait(link->lgr, NULL, 2 * SMC_LLC_WAIT_TIME, SMC_LLC_CONFIRM_LINK); if (!qentry) { struct smc_clc_msg_decline dclc; diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index 7ff2152971a5..a584613aca12 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -268,5 +268,6 @@ static void __exit smc_diag_exit(void) module_init(smc_diag_init); module_exit(smc_diag_exit); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("SMC socket monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 43 /* AF_SMC */); MODULE_ALIAS_GENL_FAMILY(SMCR_GENL_FAMILY_NAME); diff --git a/net/tipc/diag.c b/net/tipc/diag.c index 73137f4aeb68..18733451c9e0 100644 --- a/net/tipc/diag.c +++ b/net/tipc/diag.c @@ -113,4 +113,5 @@ module_init(tipc_diag_init); module_exit(tipc_diag_exit); MODULE_LICENSE("Dual BSD/GPL"); +MODULE_DESCRIPTION("TIPC socket monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, AF_TIPC); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index a78e8e722409..316f76187962 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1232,11 +1232,14 @@ void tls_sw_splice_eof(struct socket *sock) lock_sock(sk); retry: + /* same checks as in tls_sw_push_pending_record() */ rec = ctx->open_rec; if (!rec) goto unlock; msg_pl = &rec->msg_plaintext; + if (msg_pl->sg.size == 0) + goto unlock; /* Check the BPF advisor and perform transmission. */ ret = bpf_exec_tx_verdict(msg_pl, sk, false, TLS_RECORD_TYPE_DATA, diff --git a/net/unix/diag.c b/net/unix/diag.c index 616b55c5b890..bec09a3a1d44 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -339,4 +339,5 @@ static void __exit unix_diag_exit(void) module_init(unix_diag_init); module_exit(unix_diag_exit); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("UNIX socket monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 1 /* AF_LOCAL */); diff --git a/net/vmw_vsock/diag.c b/net/vmw_vsock/diag.c index a2823b1c5e28..2e29994f92ff 100644 --- a/net/vmw_vsock/diag.c +++ b/net/vmw_vsock/diag.c @@ -174,5 +174,6 @@ static void __exit vsock_diag_exit(void) module_init(vsock_diag_init); module_exit(vsock_diag_exit); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("VMware Virtual Sockets monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 40 /* AF_VSOCK */); diff --git a/net/xdp/xsk_diag.c b/net/xdp/xsk_diag.c index 22b36c8143cf..9f8955367275 100644 --- a/net/xdp/xsk_diag.c +++ b/net/xdp/xsk_diag.c @@ -211,4 +211,5 @@ static void __exit xsk_diag_exit(void) module_init(xsk_diag_init); module_exit(xsk_diag_exit); MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("XDP socket monitoring via SOCK_DIAG"); MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, AF_XDP); diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib index 68d0134bdbf9..1a965fe68e01 100644 --- a/scripts/Makefile.lib +++ b/scripts/Makefile.lib @@ -487,14 +487,14 @@ UIMAGE_OPTS-y ?= UIMAGE_TYPE ?= kernel UIMAGE_LOADADDR ?= arch_must_set_this UIMAGE_ENTRYADDR ?= $(UIMAGE_LOADADDR) -UIMAGE_NAME ?= 'Linux-$(KERNELRELEASE)' +UIMAGE_NAME ?= Linux-$(KERNELRELEASE) quiet_cmd_uimage = UIMAGE $@ cmd_uimage = $(BASH) $(MKIMAGE) -A $(UIMAGE_ARCH) -O linux \ -C $(UIMAGE_COMPRESSION) $(UIMAGE_OPTS-y) \ -T $(UIMAGE_TYPE) \ -a $(UIMAGE_LOADADDR) -e $(UIMAGE_ENTRYADDR) \ - -n $(UIMAGE_NAME) -d $< $@ + -n '$(UIMAGE_NAME)' -d $< $@ # XZ # --------------------------------------------------------------------------- diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c index 0572330bf8a7..a76925b46ce6 100644 --- a/scripts/kconfig/symbol.c +++ b/scripts/kconfig/symbol.c @@ -122,9 +122,9 @@ static long long sym_get_range_val(struct symbol *sym, int base) static void sym_validate_range(struct symbol *sym) { struct property *prop; + struct symbol *range_sym; int base; long long val, val2; - char str[64]; switch (sym->type) { case S_INT: @@ -140,17 +140,15 @@ static void sym_validate_range(struct symbol *sym) if (!prop) return; val = strtoll(sym->curr.val, NULL, base); - val2 = sym_get_range_val(prop->expr->left.sym, base); + range_sym = prop->expr->left.sym; + val2 = sym_get_range_val(range_sym, base); if (val >= val2) { - val2 = sym_get_range_val(prop->expr->right.sym, base); + range_sym = prop->expr->right.sym; + val2 = sym_get_range_val(range_sym, base); if (val <= val2) return; } - if (sym->type == S_INT) - sprintf(str, "%lld", val2); - else - sprintf(str, "0x%llx", val2); - sym->curr.val = xstrdup(str); + sym->curr.val = range_sym->curr.val; } static void sym_set_changed(struct symbol *sym) diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c index 973b5e5ae2dd..cb6406f485a9 100644 --- a/scripts/mod/modpost.c +++ b/scripts/mod/modpost.c @@ -1383,13 +1383,15 @@ static void section_rela(struct module *mod, struct elf_info *elf, const Elf_Rela *rela; for (rela = start; rela < stop; rela++) { + Elf_Sym *tsym; Elf_Addr taddr, r_offset; unsigned int r_type, r_sym; r_offset = TO_NATIVE(rela->r_offset); get_rel_type_and_sym(elf, rela->r_info, &r_type, &r_sym); - taddr = TO_NATIVE(rela->r_addend); + tsym = elf->symtab_start + r_sym; + taddr = tsym->st_value + TO_NATIVE(rela->r_addend); switch (elf->hdr->e_machine) { case EM_RISCV: @@ -1404,7 +1406,7 @@ static void section_rela(struct module *mod, struct elf_info *elf, break; } - check_section_mismatch(mod, elf, elf->symtab_start + r_sym, + check_section_mismatch(mod, elf, tsym, fsecndx, fromsec, r_offset, taddr); } } diff --git a/sound/pci/hda/cs35l56_hda_i2c.c b/sound/pci/hda/cs35l56_hda_i2c.c index 757a4d193e0f..a9ef6d86de83 100644 --- a/sound/pci/hda/cs35l56_hda_i2c.c +++ b/sound/pci/hda/cs35l56_hda_i2c.c @@ -21,6 +21,10 @@ static int cs35l56_hda_i2c_probe(struct i2c_client *clt) return -ENOMEM; cs35l56->base.dev = &clt->dev; + +#ifdef CS35L56_WAKE_HOLD_TIME_US + cs35l56->base.can_hibernate = true; +#endif cs35l56->base.regmap = devm_regmap_init_i2c(clt, &cs35l56_regmap_i2c); if (IS_ERR(cs35l56->base.regmap)) { ret = PTR_ERR(cs35l56->base.regmap); diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c index 03264915c618..db90feb49c16 100644 --- a/sound/pci/hda/hda_intel.c +++ b/sound/pci/hda/hda_intel.c @@ -2135,6 +2135,9 @@ static int azx_probe(struct pci_dev *pci, if (chip->driver_caps & AZX_DCAPS_I915_COMPONENT) { err = snd_hdac_i915_init(azx_bus(chip)); if (err < 0) { + if (err == -EPROBE_DEFER) + goto out_free; + /* if the controller is bound only with HDMI/DP * (for HSW and BDW), we need to abort the probe; * for other chips, still continue probing as other diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 669ae3d6e447..5618b1d9bfd1 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -9832,6 +9832,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8898, "HP EliteBook 845 G8 Notebook PC", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x103c, 0x88d0, "HP Pavilion 15-eh1xxx (mainboard 88D0)", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8902, "HP OMEN 16", ALC285_FIXUP_HP_MUTE_LED), + SND_PCI_QUIRK(0x103c, 0x890e, "HP 255 G8 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x8919, "HP Pavilion Aero Laptop 13-be0xxx", ALC287_FIXUP_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x896d, "HP ZBook Firefly 16 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x896e, "HP EliteBook x360 830 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), @@ -9867,6 +9868,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8abb, "HP ZBook Firefly 14 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad1, "HP EliteBook 840 14 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8ad2, "HP EliteBook 860 16 inch G9 Notebook PC", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8b2f, "HP 255 15.6 inch G10 Notebook PC", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x8b42, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b43, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8b44, "HP", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), @@ -9900,12 +9902,16 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x8c70, "HP EliteBook 835 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c71, "HP EliteBook 845 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x8c72, "HP EliteBook 865 G11", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8ca4, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), + SND_PCI_QUIRK(0x103c, 0x8cf5, "HP ZBook Studio 16", ALC245_FIXUP_CS35L41_SPI_4_HP_GPIO_LED), SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300), SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x1043, 0x10a1, "ASUS UX391UA", ALC294_FIXUP_ASUS_SPK), SND_PCI_QUIRK(0x1043, 0x10c0, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC), SND_PCI_QUIRK(0x1043, 0x10d0, "ASUS X540LA/X540LJ", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1043, 0x10d3, "ASUS K6500ZC", ALC294_FIXUP_ASUS_SPK), SND_PCI_QUIRK(0x1043, 0x115d, "Asus 1015E", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x1043, 0x11c0, "ASUS X556UR", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x125e, "ASUS Q524UQK", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), @@ -9944,13 +9950,17 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x19e1, "ASUS UX581LV", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE), SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW), SND_PCI_QUIRK(0x1043, 0x1a30, "ASUS X705UD", ALC256_FIXUP_ASUS_MIC), + SND_PCI_QUIRK(0x1043, 0x1a63, "ASUS UX3405MA", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1a83, "ASUS UM5302LA", ALC294_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1a8f, "ASUS UX582ZS", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1b11, "ASUS UX431DA", ALC294_FIXUP_ASUS_COEF_1B), SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC), SND_PCI_QUIRK(0x1043, 0x1b93, "ASUS G614JVR/JIR", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE), + SND_PCI_QUIRK(0x1043, 0x1c03, "ASUS UM3406HA", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST), + SND_PCI_QUIRK(0x1043, 0x1c33, "ASUS UX5304MA", ALC245_FIXUP_CS35L41_SPI_2), + SND_PCI_QUIRK(0x1043, 0x1c43, "ASUS UX8406MA", ALC245_FIXUP_CS35L41_SPI_2), SND_PCI_QUIRK(0x1043, 0x1c62, "ASUS GU603", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x1c92, "ASUS ROG Strix G15", ALC285_FIXUP_ASUS_G533Z_PINS), SND_PCI_QUIRK(0x1043, 0x1c9f, "ASUS G614JI", ALC285_FIXUP_ASUS_HEADSET_MIC), @@ -10821,22 +10831,6 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = { {0x12, 0x90a60130}, {0x17, 0x90170110}, {0x21, 0x03211020}), - SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, - {0x14, 0x90170110}, - {0x21, 0x04211020}), - SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, - {0x14, 0x90170110}, - {0x21, 0x04211030}), - SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, - ALC295_STANDARD_PINS, - {0x17, 0x21014020}, - {0x18, 0x21a19030}), - SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, - ALC295_STANDARD_PINS, - {0x17, 0x21014040}, - {0x18, 0x21a19050}), - SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, - ALC295_STANDARD_PINS), SND_HDA_PIN_QUIRK(0x10ec0298, 0x1028, "Dell", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE, ALC298_STANDARD_PINS, {0x17, 0x90170110}), @@ -10880,6 +10874,9 @@ static const struct snd_hda_pin_quirk alc269_fallback_pin_fixup_tbl[] = { SND_HDA_PIN_QUIRK(0x10ec0289, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, {0x19, 0x40000000}, {0x1b, 0x40000000}), + SND_HDA_PIN_QUIRK(0x10ec0295, 0x1028, "Dell", ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, + {0x19, 0x40000000}, + {0x1b, 0x40000000}), SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, {0x19, 0x40000000}, {0x1a, 0x40000000}), diff --git a/tools/hv/hv_kvp_daemon.c b/tools/hv/hv_kvp_daemon.c index 264eeb9c46a9..318e2dad27e0 100644 --- a/tools/hv/hv_kvp_daemon.c +++ b/tools/hv/hv_kvp_daemon.c @@ -1421,7 +1421,7 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val) if (error) goto setval_error; - if (new_val->addr_family == ADDR_FAMILY_IPV6) { + if (new_val->addr_family & ADDR_FAMILY_IPV6) { error = fprintf(nmfile, "\n[ipv6]\n"); if (error < 0) goto setval_error; @@ -1455,14 +1455,18 @@ static int kvp_set_ip_info(char *if_name, struct hv_kvp_ipaddr_value *new_val) if (error < 0) goto setval_error; - error = fprintf(nmfile, "gateway=%s\n", (char *)new_val->gate_way); - if (error < 0) - goto setval_error; - - error = fprintf(nmfile, "dns=%s\n", (char *)new_val->dns_addr); - if (error < 0) - goto setval_error; + /* we do not want ipv4 addresses in ipv6 section and vice versa */ + if (is_ipv6 != is_ipv4((char *)new_val->gate_way)) { + error = fprintf(nmfile, "gateway=%s\n", (char *)new_val->gate_way); + if (error < 0) + goto setval_error; + } + if (is_ipv6 != is_ipv4((char *)new_val->dns_addr)) { + error = fprintf(nmfile, "dns=%s\n", (char *)new_val->dns_addr); + if (error < 0) + goto setval_error; + } fclose(nmfile); fclose(ifcfg_file); diff --git a/tools/hv/hv_set_ifconfig.sh b/tools/hv/hv_set_ifconfig.sh index ae5a7a8249a2..440a91b35823 100755 --- a/tools/hv/hv_set_ifconfig.sh +++ b/tools/hv/hv_set_ifconfig.sh @@ -53,7 +53,7 @@ # or "manual" if no boot-time protocol should be used) # # address1=ipaddr1/plen -# address=ipaddr2/plen +# address2=ipaddr2/plen # # gateway=gateway1;gateway2 # @@ -61,7 +61,7 @@ # # [ipv6] # address1=ipaddr1/plen -# address2=ipaddr1/plen +# address2=ipaddr2/plen # # gateway=gateway1;gateway2 # diff --git a/tools/net/ynl/Makefile.deps b/tools/net/ynl/Makefile.deps index 64d139400db1..3110f84dd029 100644 --- a/tools/net/ynl/Makefile.deps +++ b/tools/net/ynl/Makefile.deps @@ -18,4 +18,4 @@ CFLAGS_devlink:=$(call get_hdr_inc,_LINUX_DEVLINK_H_,devlink.h) CFLAGS_ethtool:=$(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_H_,ethtool_netlink.h) CFLAGS_handshake:=$(call get_hdr_inc,_LINUX_HANDSHAKE_H,handshake.h) CFLAGS_netdev:=$(call get_hdr_inc,_LINUX_NETDEV_H,netdev.h) -CFLAGS_nfsd:=$(call get_hdr_inc,_LINUX_NFSD_H,nfsd.h) +CFLAGS_nfsd:=$(call get_hdr_inc,_LINUX_NFSD_NETLINK_H,nfsd_netlink.h) diff --git a/tools/net/ynl/generated/devlink-user.c b/tools/net/ynl/generated/devlink-user.c index bc5065bd99b2..c12ca87ca2bb 100644 --- a/tools/net/ynl/generated/devlink-user.c +++ b/tools/net/ynl/generated/devlink-user.c @@ -15,7 +15,7 @@ /* Enums */ static const char * const devlink_op_strmap[] = { [3] = "get", - [7] = "port-get", + // skip "port-get", duplicate reply value [DEVLINK_CMD_PORT_NEW] = "port-new", [13] = "sb-get", [17] = "sb-pool-get", diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py index c4003a83cd5d..3bd6b928c14f 100755 --- a/tools/net/ynl/ynl-gen-c.py +++ b/tools/net/ynl/ynl-gen-c.py @@ -1505,6 +1505,12 @@ def put_op_name(family, cw): cw.block_start(line=f"static const char * const {map_name}[] =") for op_name, op in family.msgs.items(): if op.rsp_value: + # Make sure we don't add duplicated entries, if multiple commands + # produce the same response in legacy families. + if family.rsp_by_value[op.rsp_value] != op: + cw.p(f'// skip "{op_name}", duplicate reply value') + continue + if op.req_value == op.rsp_value: cw.p(f'[{op.enum_name}] = "{op_name}",') else: diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 9a10512e3407..7a334377f92b 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -211,9 +211,6 @@ int *fd_instr_count_percpu; struct timeval interval_tv = { 5, 0 }; struct timespec interval_ts = { 5, 0 }; -/* Save original CPU model */ -unsigned int model_orig; - unsigned int num_iterations; unsigned int header_iterations; unsigned int debug; @@ -224,24 +221,16 @@ unsigned int rapl_joules; unsigned int summary_only; unsigned int list_header_only; unsigned int dump_only; -unsigned int do_snb_cstates; -unsigned int do_knl_cstates; -unsigned int do_slm_cstates; -unsigned int use_c1_residency_msr; unsigned int has_aperf; unsigned int has_epb; unsigned int has_turbo; unsigned int is_hybrid; -unsigned int do_irtl_snb; -unsigned int do_irtl_hsw; unsigned int units = 1000000; /* MHz etc */ unsigned int genuine_intel; unsigned int authentic_amd; unsigned int hygon_genuine; unsigned int max_level, max_extended_level; unsigned int has_invariant_tsc; -unsigned int do_nhm_platform_info; -unsigned int no_MSR_MISC_PWR_MGMT; unsigned int aperf_mperf_multiplier = 1; double bclk; double base_hz; @@ -250,7 +239,6 @@ double tsc_tweak = 1.0; unsigned int show_pkg_only; unsigned int show_core_only; char *output_buffer, *outp; -unsigned int do_rapl; unsigned int do_dts; unsigned int do_ptm; unsigned int do_ipc; @@ -261,65 +249,686 @@ unsigned int gfx_cur_mhz; unsigned int gfx_act_mhz; unsigned int tj_max; unsigned int tj_max_override; -int tcc_offset_bits; double rapl_power_units, rapl_time_units; double rapl_dram_energy_units, rapl_energy_units; double rapl_joule_counter_range; -unsigned int do_core_perf_limit_reasons; -unsigned int has_automatic_cstate_conversion; -unsigned int dis_cstate_prewake; -unsigned int do_gfx_perf_limit_reasons; -unsigned int do_ring_perf_limit_reasons; unsigned int crystal_hz; unsigned long long tsc_hz; int base_cpu; -double discover_bclk(unsigned int family, unsigned int model); unsigned int has_hwp; /* IA32_PM_ENABLE, IA32_HWP_CAPABILITIES */ /* IA32_HWP_REQUEST, IA32_HWP_STATUS */ unsigned int has_hwp_notify; /* IA32_HWP_INTERRUPT */ unsigned int has_hwp_activity_window; /* IA32_HWP_REQUEST[bits 41:32] */ unsigned int has_hwp_epp; /* IA32_HWP_REQUEST[bits 31:24] */ unsigned int has_hwp_pkg; /* IA32_HWP_REQUEST_PKG */ -unsigned int has_misc_feature_control; unsigned int first_counter_read = 1; int ignore_stdin; -#define RAPL_PKG (1 << 0) - /* 0x610 MSR_PKG_POWER_LIMIT */ - /* 0x611 MSR_PKG_ENERGY_STATUS */ -#define RAPL_PKG_PERF_STATUS (1 << 1) - /* 0x613 MSR_PKG_PERF_STATUS */ -#define RAPL_PKG_POWER_INFO (1 << 2) - /* 0x614 MSR_PKG_POWER_INFO */ - -#define RAPL_DRAM (1 << 3) - /* 0x618 MSR_DRAM_POWER_LIMIT */ - /* 0x619 MSR_DRAM_ENERGY_STATUS */ -#define RAPL_DRAM_PERF_STATUS (1 << 4) - /* 0x61b MSR_DRAM_PERF_STATUS */ -#define RAPL_DRAM_POWER_INFO (1 << 5) - /* 0x61c MSR_DRAM_POWER_INFO */ - -#define RAPL_CORES_POWER_LIMIT (1 << 6) - /* 0x638 MSR_PP0_POWER_LIMIT */ -#define RAPL_CORE_POLICY (1 << 7) - /* 0x63a MSR_PP0_POLICY */ - -#define RAPL_GFX (1 << 8) - /* 0x640 MSR_PP1_POWER_LIMIT */ - /* 0x641 MSR_PP1_ENERGY_STATUS */ - /* 0x642 MSR_PP1_POLICY */ - -#define RAPL_CORES_ENERGY_STATUS (1 << 9) - /* 0x639 MSR_PP0_ENERGY_STATUS */ -#define RAPL_PER_CORE_ENERGY (1 << 10) - /* Indicates cores energy collection is per-core, - * not per-package. */ -#define RAPL_AMD_F17H (1 << 11) - /* 0xc0010299 MSR_RAPL_PWR_UNIT */ - /* 0xc001029a MSR_CORE_ENERGY_STAT */ - /* 0xc001029b MSR_PKG_ENERGY_STAT */ -#define RAPL_CORES (RAPL_CORES_ENERGY_STATUS | RAPL_CORES_POWER_LIMIT) +int get_msr(int cpu, off_t offset, unsigned long long *msr); + +/* Model specific support Start */ + +/* List of features that may diverge among different platforms */ +struct platform_features { + bool has_msr_misc_feature_control; /* MSR_MISC_FEATURE_CONTROL */ + bool has_msr_misc_pwr_mgmt; /* MSR_MISC_PWR_MGMT */ + bool has_nhm_msrs; /* MSR_PLATFORM_INFO, MSR_IA32_TEMPERATURE_TARGET, MSR_SMI_COUNT, MSR_PKG_CST_CONFIG_CONTROL, MSR_IA32_POWER_CTL, TRL MSRs */ + bool has_config_tdp; /* MSR_CONFIG_TDP_NOMINAL/LEVEL_1/LEVEL_2/CONTROL, MSR_TURBO_ACTIVATION_RATIO */ + int bclk_freq; /* CPU base clock */ + int crystal_freq; /* Crystal clock to use when not available from CPUID.15 */ + int supported_cstates; /* Core cstates and Package cstates supported */ + int cst_limit; /* MSR_PKG_CST_CONFIG_CONTROL */ + bool has_cst_auto_convension; /* AUTOMATIC_CSTATE_CONVERSION bit in MSR_PKG_CST_CONFIG_CONTROL */ + bool has_irtl_msrs; /* MSR_PKGC3/PKGC6/PKGC7/PKGC8/PKGC9/PKGC10_IRTL */ + bool has_msr_core_c1_res; /* MSR_CORE_C1_RES */ + bool has_msr_module_c6_res_ms; /* MSR_MODULE_C6_RES_MS */ + bool has_msr_c6_demotion_policy_config; /* MSR_CC6_DEMOTION_POLICY_CONFIG/MSR_MC6_DEMOTION_POLICY_CONFIG */ + bool has_msr_atom_pkg_c6_residency; /* MSR_ATOM_PKG_C6_RESIDENCY */ + bool has_msr_knl_core_c6_residency; /* MSR_KNL_CORE_C6_RESIDENCY */ + bool has_ext_cst_msrs; /* MSR_PKG_WEIGHTED_CORE_C0_RES/MSR_PKG_ANY_CORE_C0_RES/MSR_PKG_ANY_GFXE_C0_RES/MSR_PKG_BOTH_CORE_GFXE_C0_RES */ + bool has_cst_prewake_bit; /* Cstate prewake bit in MSR_IA32_POWER_CTL */ + int trl_msrs; /* MSR_TURBO_RATIO_LIMIT/LIMIT1/LIMIT2/SECONDARY, Atom TRL MSRs */ + int plr_msrs; /* MSR_CORE/GFX/RING_PERF_LIMIT_REASONS */ + int rapl_msrs; /* RAPL PKG/DRAM/CORE/GFX MSRs, AMD RAPL MSRs */ + bool has_per_core_rapl; /* Indicates cores energy collection is per-core, not per-package. AMD specific for now */ + bool has_rapl_divisor; /* Divisor for Energy unit raw value from MSR_RAPL_POWER_UNIT */ + bool has_fixed_rapl_unit; /* Fixed Energy Unit used for DRAM RAPL Domain */ + int rapl_quirk_tdp; /* Hardcoded TDP value when cannot be retrieved from hardware */ + int tcc_offset_bits; /* TCC Offset bits in MSR_IA32_TEMPERATURE_TARGET */ + bool enable_tsc_tweak; /* Use CPU Base freq instead of TSC freq for aperf/mperf counter */ + bool need_perf_multiplier; /* mperf/aperf multiplier */ +}; + +struct platform_data { + unsigned int model; + const struct platform_features *features; +}; + +/* For BCLK */ +enum bclk_freq { + BCLK_100MHZ = 1, + BCLK_133MHZ, + BCLK_SLV, +}; + +#define SLM_BCLK_FREQS 5 +double slm_freq_table[SLM_BCLK_FREQS] = { 83.3, 100.0, 133.3, 116.7, 80.0 }; + +double slm_bclk(void) +{ + unsigned long long msr = 3; + unsigned int i; + double freq; + + if (get_msr(base_cpu, MSR_FSB_FREQ, &msr)) + fprintf(outf, "SLM BCLK: unknown\n"); + + i = msr & 0xf; + if (i >= SLM_BCLK_FREQS) { + fprintf(outf, "SLM BCLK[%d] invalid\n", i); + i = 3; + } + freq = slm_freq_table[i]; + + if (!quiet) + fprintf(outf, "SLM BCLK: %.1f Mhz\n", freq); + + return freq; +} + +/* For Package cstate limit */ +enum package_cstate_limit { + CST_LIMIT_NHM = 1, + CST_LIMIT_SNB, + CST_LIMIT_HSW, + CST_LIMIT_SKX, + CST_LIMIT_ICX, + CST_LIMIT_SLV, + CST_LIMIT_AMT, + CST_LIMIT_KNL, + CST_LIMIT_GMT, +}; + +/* For Turbo Ratio Limit MSRs */ +enum turbo_ratio_limit_msrs { + TRL_BASE = BIT(0), + TRL_LIMIT1 = BIT(1), + TRL_LIMIT2 = BIT(2), + TRL_ATOM = BIT(3), + TRL_KNL = BIT(4), + TRL_CORECOUNT = BIT(5), +}; + +/* For Perf Limit Reason MSRs */ +enum perf_limit_reason_msrs { + PLR_CORE = BIT(0), + PLR_GFX = BIT(1), + PLR_RING = BIT(2), +}; + +/* For RAPL MSRs */ +enum rapl_msrs { + RAPL_PKG_POWER_LIMIT = BIT(0), /* 0x610 MSR_PKG_POWER_LIMIT */ + RAPL_PKG_ENERGY_STATUS = BIT(1), /* 0x611 MSR_PKG_ENERGY_STATUS */ + RAPL_PKG_PERF_STATUS = BIT(2), /* 0x613 MSR_PKG_PERF_STATUS */ + RAPL_PKG_POWER_INFO = BIT(3), /* 0x614 MSR_PKG_POWER_INFO */ + RAPL_DRAM_POWER_LIMIT = BIT(4), /* 0x618 MSR_DRAM_POWER_LIMIT */ + RAPL_DRAM_ENERGY_STATUS = BIT(5), /* 0x619 MSR_DRAM_ENERGY_STATUS */ + RAPL_DRAM_PERF_STATUS = BIT(6), /* 0x61b MSR_DRAM_PERF_STATUS */ + RAPL_DRAM_POWER_INFO = BIT(7), /* 0x61c MSR_DRAM_POWER_INFO */ + RAPL_CORE_POWER_LIMIT = BIT(8), /* 0x638 MSR_PP0_POWER_LIMIT */ + RAPL_CORE_ENERGY_STATUS = BIT(9), /* 0x639 MSR_PP0_ENERGY_STATUS */ + RAPL_CORE_POLICY = BIT(10), /* 0x63a MSR_PP0_POLICY */ + RAPL_GFX_POWER_LIMIT = BIT(11), /* 0x640 MSR_PP1_POWER_LIMIT */ + RAPL_GFX_ENERGY_STATUS = BIT(12), /* 0x641 MSR_PP1_ENERGY_STATUS */ + RAPL_GFX_POLICY = BIT(13), /* 0x642 MSR_PP1_POLICY */ + RAPL_AMD_PWR_UNIT = BIT(14), /* 0xc0010299 MSR_AMD_RAPL_POWER_UNIT */ + RAPL_AMD_CORE_ENERGY_STAT = BIT(15), /* 0xc001029a MSR_AMD_CORE_ENERGY_STATUS */ + RAPL_AMD_PKG_ENERGY_STAT = BIT(16), /* 0xc001029b MSR_AMD_PKG_ENERGY_STATUS */ +}; + +#define RAPL_PKG (RAPL_PKG_ENERGY_STATUS | RAPL_PKG_POWER_LIMIT) +#define RAPL_DRAM (RAPL_DRAM_ENERGY_STATUS | RAPL_DRAM_POWER_LIMIT) +#define RAPL_CORE (RAPL_CORE_ENERGY_STATUS | RAPL_CORE_POWER_LIMIT) +#define RAPL_GFX (RAPL_GFX_POWER_LIMIT | RAPL_GFX_ENERGY_STATUS) + +#define RAPL_PKG_ALL (RAPL_PKG | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO) +#define RAPL_DRAM_ALL (RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_DRAM_POWER_INFO) +#define RAPL_CORE_ALL (RAPL_CORE | RAPL_CORE_POLICY) +#define RAPL_GFX_ALL (RAPL_GFX | RAPL_GFX_POLIGY) + +#define RAPL_AMD_F17H (RAPL_AMD_PWR_UNIT | RAPL_AMD_CORE_ENERGY_STAT | RAPL_AMD_PKG_ENERGY_STAT) + +/* For Cstates */ +enum cstates { + CC1 = BIT(0), + CC3 = BIT(1), + CC6 = BIT(2), + CC7 = BIT(3), + PC2 = BIT(4), + PC3 = BIT(5), + PC6 = BIT(6), + PC7 = BIT(7), + PC8 = BIT(8), + PC9 = BIT(9), + PC10 = BIT(10), +}; + +static const struct platform_features nhm_features = { + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .bclk_freq = BCLK_133MHZ, + .supported_cstates = CC1 | CC3 | CC6 | PC3 | PC6, + .cst_limit = CST_LIMIT_NHM, + .trl_msrs = TRL_BASE, +}; + +static const struct platform_features nhx_features = { + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .bclk_freq = BCLK_133MHZ, + .supported_cstates = CC1 | CC3 | CC6 | PC3 | PC6, + .cst_limit = CST_LIMIT_NHM, +}; + +static const struct platform_features snb_features = { + .has_msr_misc_feature_control = 1, + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .bclk_freq = BCLK_100MHZ, + .supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7, + .cst_limit = CST_LIMIT_SNB, + .has_irtl_msrs = 1, + .trl_msrs = TRL_BASE, + .rapl_msrs = RAPL_PKG | RAPL_CORE_ALL | RAPL_GFX | RAPL_PKG_POWER_INFO, +}; + +static const struct platform_features snx_features = { + .has_msr_misc_feature_control = 1, + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .bclk_freq = BCLK_100MHZ, + .supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7, + .cst_limit = CST_LIMIT_SNB, + .has_irtl_msrs = 1, + .trl_msrs = TRL_BASE, + .rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM_ALL, +}; + +static const struct platform_features ivb_features = { + .has_msr_misc_feature_control = 1, + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .has_config_tdp = 1, + .bclk_freq = BCLK_100MHZ, + .supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7, + .cst_limit = CST_LIMIT_SNB, + .has_irtl_msrs = 1, + .trl_msrs = TRL_BASE, + .rapl_msrs = RAPL_PKG | RAPL_CORE_ALL | RAPL_GFX | RAPL_PKG_POWER_INFO, +}; + +static const struct platform_features ivx_features = { + .has_msr_misc_feature_control = 1, + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .bclk_freq = BCLK_100MHZ, + .supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7, + .cst_limit = CST_LIMIT_SNB, + .has_irtl_msrs = 1, + .trl_msrs = TRL_BASE | TRL_LIMIT1, + .rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM_ALL, +}; + +static const struct platform_features hsw_features = { + .has_msr_misc_feature_control = 1, + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .has_config_tdp = 1, + .bclk_freq = BCLK_100MHZ, + .supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7, + .cst_limit = CST_LIMIT_HSW, + .has_irtl_msrs = 1, + .trl_msrs = TRL_BASE, + .plr_msrs = PLR_CORE | PLR_GFX | PLR_RING, + .rapl_msrs = RAPL_PKG | RAPL_CORE_ALL | RAPL_GFX | RAPL_PKG_POWER_INFO, +}; + +static const struct platform_features hsx_features = { + .has_msr_misc_feature_control = 1, + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .has_config_tdp = 1, + .bclk_freq = BCLK_100MHZ, + .supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7, + .cst_limit = CST_LIMIT_HSW, + .has_irtl_msrs = 1, + .trl_msrs = TRL_BASE | TRL_LIMIT1 | TRL_LIMIT2, + .plr_msrs = PLR_CORE | PLR_RING, + .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL, + .has_fixed_rapl_unit = 1, +}; + +static const struct platform_features hswl_features = { + .has_msr_misc_feature_control = 1, + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .has_config_tdp = 1, + .bclk_freq = BCLK_100MHZ, + .supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7 | PC8 | PC9 | PC10, + .cst_limit = CST_LIMIT_HSW, + .has_irtl_msrs = 1, + .trl_msrs = TRL_BASE, + .plr_msrs = PLR_CORE | PLR_GFX | PLR_RING, + .rapl_msrs = RAPL_PKG | RAPL_CORE_ALL | RAPL_GFX | RAPL_PKG_POWER_INFO, +}; + +static const struct platform_features hswg_features = { + .has_msr_misc_feature_control = 1, + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .has_config_tdp = 1, + .bclk_freq = BCLK_100MHZ, + .supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7, + .cst_limit = CST_LIMIT_HSW, + .has_irtl_msrs = 1, + .trl_msrs = TRL_BASE, + .plr_msrs = PLR_CORE | PLR_GFX | PLR_RING, + .rapl_msrs = RAPL_PKG | RAPL_CORE_ALL | RAPL_GFX | RAPL_PKG_POWER_INFO, +}; + +static const struct platform_features bdw_features = { + .has_msr_misc_feature_control = 1, + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .has_config_tdp = 1, + .bclk_freq = BCLK_100MHZ, + .supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7 | PC8 | PC9 | PC10, + .cst_limit = CST_LIMIT_HSW, + .has_irtl_msrs = 1, + .trl_msrs = TRL_BASE, + .rapl_msrs = RAPL_PKG | RAPL_CORE_ALL | RAPL_GFX | RAPL_PKG_POWER_INFO, +}; + +static const struct platform_features bdwg_features = { + .has_msr_misc_feature_control = 1, + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .has_config_tdp = 1, + .bclk_freq = BCLK_100MHZ, + .supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7, + .cst_limit = CST_LIMIT_HSW, + .has_irtl_msrs = 1, + .trl_msrs = TRL_BASE, + .rapl_msrs = RAPL_PKG | RAPL_CORE_ALL | RAPL_GFX | RAPL_PKG_POWER_INFO, +}; + +static const struct platform_features bdx_features = { + .has_msr_misc_feature_control = 1, + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .has_config_tdp = 1, + .bclk_freq = BCLK_100MHZ, + .supported_cstates = CC1 | CC3 | CC6 | PC2 | PC3 | PC6, + .cst_limit = CST_LIMIT_HSW, + .has_irtl_msrs = 1, + .has_cst_auto_convension = 1, + .trl_msrs = TRL_BASE, + .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL, + .has_fixed_rapl_unit = 1, +}; + +static const struct platform_features skl_features = { + .has_msr_misc_feature_control = 1, + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .has_config_tdp = 1, + .bclk_freq = BCLK_100MHZ, + .crystal_freq = 24000000, + .supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7 | PC8 | PC9 | PC10, + .cst_limit = CST_LIMIT_HSW, + .has_irtl_msrs = 1, + .has_ext_cst_msrs = 1, + .trl_msrs = TRL_BASE, + .tcc_offset_bits = 6, + .rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_GFX, + .enable_tsc_tweak = 1, +}; + +static const struct platform_features cnl_features = { + .has_msr_misc_feature_control = 1, + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .has_config_tdp = 1, + .bclk_freq = BCLK_100MHZ, + .supported_cstates = CC1 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7 | PC8 | PC9 | PC10, + .cst_limit = CST_LIMIT_HSW, + .has_irtl_msrs = 1, + .has_msr_core_c1_res = 1, + .has_ext_cst_msrs = 1, + .trl_msrs = TRL_BASE, + .tcc_offset_bits = 6, + .rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_GFX, + .enable_tsc_tweak = 1, +}; + +static const struct platform_features adl_features = { + .has_msr_misc_feature_control = 1, + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .has_config_tdp = 1, + .bclk_freq = BCLK_100MHZ, + .supported_cstates = CC1 | CC6 | CC7 | PC2 | PC3 | PC6 | PC8 | PC10, + .cst_limit = CST_LIMIT_HSW, + .has_irtl_msrs = 1, + .has_msr_core_c1_res = 1, + .has_ext_cst_msrs = 1, + .trl_msrs = TRL_BASE, + .tcc_offset_bits = 6, + .rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_GFX, + .enable_tsc_tweak = 1, +}; + +static const struct platform_features skx_features = { + .has_msr_misc_feature_control = 1, + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .has_config_tdp = 1, + .bclk_freq = BCLK_100MHZ, + .supported_cstates = CC1 | CC6 | PC2 | PC6, + .cst_limit = CST_LIMIT_SKX, + .has_irtl_msrs = 1, + .has_cst_auto_convension = 1, + .trl_msrs = TRL_BASE | TRL_CORECOUNT, + .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL, + .has_fixed_rapl_unit = 1, +}; + +static const struct platform_features icx_features = { + .has_msr_misc_feature_control = 1, + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .has_config_tdp = 1, + .bclk_freq = BCLK_100MHZ, + .supported_cstates = CC1 | CC6 | PC2 | PC6, + .cst_limit = CST_LIMIT_ICX, + .has_irtl_msrs = 1, + .has_cst_prewake_bit = 1, + .trl_msrs = TRL_BASE | TRL_CORECOUNT, + .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL, + .has_fixed_rapl_unit = 1, +}; + +static const struct platform_features spr_features = { + .has_msr_misc_feature_control = 1, + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .has_config_tdp = 1, + .bclk_freq = BCLK_100MHZ, + .supported_cstates = CC1 | CC6 | PC2 | PC6, + .cst_limit = CST_LIMIT_SKX, + .has_msr_core_c1_res = 1, + .has_irtl_msrs = 1, + .has_cst_prewake_bit = 1, + .trl_msrs = TRL_BASE | TRL_CORECOUNT, + .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL, +}; + +static const struct platform_features srf_features = { + .has_msr_misc_feature_control = 1, + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .has_config_tdp = 1, + .bclk_freq = BCLK_100MHZ, + .supported_cstates = CC1 | CC6 | PC2 | PC6, + .cst_limit = CST_LIMIT_SKX, + .has_msr_core_c1_res = 1, + .has_msr_module_c6_res_ms = 1, + .has_irtl_msrs = 1, + .has_cst_prewake_bit = 1, + .trl_msrs = TRL_BASE | TRL_CORECOUNT, + .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL, +}; + +static const struct platform_features grr_features = { + .has_msr_misc_feature_control = 1, + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .has_config_tdp = 1, + .bclk_freq = BCLK_100MHZ, + .supported_cstates = CC1 | CC6, + .cst_limit = CST_LIMIT_SKX, + .has_msr_core_c1_res = 1, + .has_msr_module_c6_res_ms = 1, + .has_irtl_msrs = 1, + .has_cst_prewake_bit = 1, + .trl_msrs = TRL_BASE | TRL_CORECOUNT, + .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL, +}; + +static const struct platform_features slv_features = { + .has_nhm_msrs = 1, + .bclk_freq = BCLK_SLV, + .supported_cstates = CC1 | CC6 | PC6, + .cst_limit = CST_LIMIT_SLV, + .has_msr_core_c1_res = 1, + .has_msr_module_c6_res_ms = 1, + .has_msr_c6_demotion_policy_config = 1, + .has_msr_atom_pkg_c6_residency = 1, + .trl_msrs = TRL_ATOM, + .rapl_msrs = RAPL_PKG | RAPL_CORE, + .has_rapl_divisor = 1, + .rapl_quirk_tdp = 30, +}; + +static const struct platform_features slvd_features = { + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .bclk_freq = BCLK_SLV, + .supported_cstates = CC1 | CC6 | PC3 | PC6, + .cst_limit = CST_LIMIT_SLV, + .has_msr_atom_pkg_c6_residency = 1, + .trl_msrs = TRL_BASE, + .rapl_msrs = RAPL_PKG | RAPL_CORE, + .rapl_quirk_tdp = 30, +}; + +static const struct platform_features amt_features = { + .has_nhm_msrs = 1, + .bclk_freq = BCLK_133MHZ, + .supported_cstates = CC1 | CC3 | CC6 | PC3 | PC6, + .cst_limit = CST_LIMIT_AMT, + .trl_msrs = TRL_BASE, +}; + +static const struct platform_features gmt_features = { + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .bclk_freq = BCLK_100MHZ, + .crystal_freq = 19200000, + .supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7 | PC8 | PC9 | PC10, + .cst_limit = CST_LIMIT_GMT, + .has_irtl_msrs = 1, + .trl_msrs = TRL_BASE | TRL_CORECOUNT, + .rapl_msrs = RAPL_PKG | RAPL_PKG_POWER_INFO, +}; + +static const struct platform_features gmtd_features = { + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .bclk_freq = BCLK_100MHZ, + .crystal_freq = 25000000, + .supported_cstates = CC1 | CC6 | PC2 | PC6, + .cst_limit = CST_LIMIT_GMT, + .has_irtl_msrs = 1, + .has_msr_core_c1_res = 1, + .trl_msrs = TRL_BASE | TRL_CORECOUNT, + .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL | RAPL_CORE_ENERGY_STATUS, +}; + +static const struct platform_features gmtp_features = { + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .bclk_freq = BCLK_100MHZ, + .crystal_freq = 19200000, + .supported_cstates = CC1 | CC3 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7 | PC8 | PC9 | PC10, + .cst_limit = CST_LIMIT_GMT, + .has_irtl_msrs = 1, + .trl_msrs = TRL_BASE, + .rapl_msrs = RAPL_PKG | RAPL_PKG_POWER_INFO, +}; + +static const struct platform_features tmt_features = { + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .bclk_freq = BCLK_100MHZ, + .supported_cstates = CC1 | CC6 | CC7 | PC2 | PC3 | PC6 | PC7 | PC8 | PC9 | PC10, + .cst_limit = CST_LIMIT_GMT, + .has_irtl_msrs = 1, + .trl_msrs = TRL_BASE, + .rapl_msrs = RAPL_PKG_ALL | RAPL_CORE_ALL | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_GFX, + .enable_tsc_tweak = 1, +}; + +static const struct platform_features tmtd_features = { + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .bclk_freq = BCLK_100MHZ, + .supported_cstates = CC1 | CC6, + .cst_limit = CST_LIMIT_GMT, + .has_irtl_msrs = 1, + .trl_msrs = TRL_BASE | TRL_CORECOUNT, + .rapl_msrs = RAPL_PKG_ALL, +}; + +static const struct platform_features knl_features = { + .has_msr_misc_pwr_mgmt = 1, + .has_nhm_msrs = 1, + .has_config_tdp = 1, + .bclk_freq = BCLK_100MHZ, + .supported_cstates = CC1 | CC6 | PC3 | PC6, + .cst_limit = CST_LIMIT_KNL, + .has_msr_knl_core_c6_residency = 1, + .trl_msrs = TRL_KNL, + .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL, + .has_fixed_rapl_unit = 1, + .need_perf_multiplier = 1, +}; + +static const struct platform_features default_features = { +}; + +static const struct platform_features amd_features_with_rapl = { + .rapl_msrs = RAPL_AMD_F17H, + .has_per_core_rapl = 1, + .rapl_quirk_tdp = 280, /* This is the max stock TDP of HEDT/Server Fam17h+ chips */ +}; + +static const struct platform_data turbostat_pdata[] = { + { INTEL_FAM6_NEHALEM, &nhm_features }, + { INTEL_FAM6_NEHALEM_G, &nhm_features }, + { INTEL_FAM6_NEHALEM_EP, &nhm_features }, + { INTEL_FAM6_NEHALEM_EX, &nhx_features }, + { INTEL_FAM6_WESTMERE, &nhm_features }, + { INTEL_FAM6_WESTMERE_EP, &nhm_features }, + { INTEL_FAM6_WESTMERE_EX, &nhx_features }, + { INTEL_FAM6_SANDYBRIDGE, &snb_features }, + { INTEL_FAM6_SANDYBRIDGE_X, &snx_features }, + { INTEL_FAM6_IVYBRIDGE, &ivb_features }, + { INTEL_FAM6_IVYBRIDGE_X, &ivx_features }, + { INTEL_FAM6_HASWELL, &hsw_features }, + { INTEL_FAM6_HASWELL_X, &hsx_features }, + { INTEL_FAM6_HASWELL_L, &hswl_features }, + { INTEL_FAM6_HASWELL_G, &hswg_features }, + { INTEL_FAM6_BROADWELL, &bdw_features }, + { INTEL_FAM6_BROADWELL_G, &bdwg_features }, + { INTEL_FAM6_BROADWELL_X, &bdx_features }, + { INTEL_FAM6_BROADWELL_D, &bdx_features }, + { INTEL_FAM6_SKYLAKE_L, &skl_features }, + { INTEL_FAM6_SKYLAKE, &skl_features }, + { INTEL_FAM6_SKYLAKE_X, &skx_features }, + { INTEL_FAM6_KABYLAKE_L, &skl_features }, + { INTEL_FAM6_KABYLAKE, &skl_features }, + { INTEL_FAM6_COMETLAKE, &skl_features }, + { INTEL_FAM6_COMETLAKE_L, &skl_features }, + { INTEL_FAM6_CANNONLAKE_L, &cnl_features }, + { INTEL_FAM6_ICELAKE_X, &icx_features }, + { INTEL_FAM6_ICELAKE_D, &icx_features }, + { INTEL_FAM6_ICELAKE_L, &cnl_features }, + { INTEL_FAM6_ICELAKE_NNPI, &cnl_features }, + { INTEL_FAM6_ROCKETLAKE, &cnl_features }, + { INTEL_FAM6_TIGERLAKE_L, &cnl_features }, + { INTEL_FAM6_TIGERLAKE, &cnl_features }, + { INTEL_FAM6_SAPPHIRERAPIDS_X, &spr_features }, + { INTEL_FAM6_EMERALDRAPIDS_X, &spr_features }, + { INTEL_FAM6_GRANITERAPIDS_X, &spr_features }, + { INTEL_FAM6_LAKEFIELD, &cnl_features }, + { INTEL_FAM6_ALDERLAKE, &adl_features }, + { INTEL_FAM6_ALDERLAKE_L, &adl_features }, + { INTEL_FAM6_RAPTORLAKE, &adl_features }, + { INTEL_FAM6_RAPTORLAKE_P, &adl_features }, + { INTEL_FAM6_RAPTORLAKE_S, &adl_features }, + { INTEL_FAM6_METEORLAKE, &cnl_features }, + { INTEL_FAM6_METEORLAKE_L, &cnl_features }, + { INTEL_FAM6_ARROWLAKE, &cnl_features }, + { INTEL_FAM6_LUNARLAKE_M, &cnl_features }, + { INTEL_FAM6_ATOM_SILVERMONT, &slv_features }, + { INTEL_FAM6_ATOM_SILVERMONT_D, &slvd_features }, + { INTEL_FAM6_ATOM_AIRMONT, &amt_features }, + { INTEL_FAM6_ATOM_GOLDMONT, &gmt_features }, + { INTEL_FAM6_ATOM_GOLDMONT_D, &gmtd_features }, + { INTEL_FAM6_ATOM_GOLDMONT_PLUS, &gmtp_features }, + { INTEL_FAM6_ATOM_TREMONT_D, &tmtd_features }, + { INTEL_FAM6_ATOM_TREMONT, &tmt_features }, + { INTEL_FAM6_ATOM_TREMONT_L, &tmt_features }, + { INTEL_FAM6_ATOM_GRACEMONT, &adl_features }, + { INTEL_FAM6_ATOM_CRESTMONT_X, &srf_features }, + { INTEL_FAM6_ATOM_CRESTMONT, &grr_features }, + { INTEL_FAM6_XEON_PHI_KNL, &knl_features }, + { INTEL_FAM6_XEON_PHI_KNM, &knl_features }, + /* + * Missing support for + * INTEL_FAM6_ICELAKE + * INTEL_FAM6_ATOM_SILVERMONT_MID + * INTEL_FAM6_ATOM_AIRMONT_MID + * INTEL_FAM6_ATOM_AIRMONT_NP + */ + { 0, NULL }, +}; + +static const struct platform_features *platform; + +void probe_platform_features(unsigned int family, unsigned int model) +{ + int i; + + platform = &default_features; + + if (authentic_amd || hygon_genuine) { + if (max_extended_level >= 0x80000007) { + unsigned int eax, ebx, ecx, edx; + + __cpuid(0x80000007, eax, ebx, ecx, edx); + /* RAPL (Fam 17h+) */ + if ((edx & (1 << 14)) && family >= 0x17) + platform = &amd_features_with_rapl; + } + return; + } + + if (!genuine_intel || family != 6) + return; + + for (i = 0; turbostat_pdata[i].features; i++) { + if (turbostat_pdata[i].model == model) { + platform = turbostat_pdata[i].features; + return; + } + } +} + +/* Model specific support End */ + #define TJMAX_DEFAULT 100 /* MSRs that are not yet in the kernel-provided header. */ @@ -333,8 +942,8 @@ int backwards_count; char *progname; #define CPU_SUBSET_MAXCPUS 1024 /* need to use before probe... */ -cpu_set_t *cpu_present_set, *cpu_affinity_set, *cpu_subset; -size_t cpu_present_setsize, cpu_affinity_setsize, cpu_subset_size; +cpu_set_t *cpu_present_set, *cpu_effective_set, *cpu_allowed_set, *cpu_affinity_set, *cpu_subset; +size_t cpu_present_setsize, cpu_effective_setsize, cpu_allowed_setsize, cpu_affinity_setsize, cpu_subset_size; #define MAX_ADDED_COUNTERS 8 #define MAX_ADDED_THREAD_COUNTERS 24 #define BITMASK_SIZE 32 @@ -355,12 +964,11 @@ struct thread_data { unsigned int x2apic_id; unsigned int flags; bool is_atom; -#define CPU_IS_FIRST_THREAD_IN_CORE 0x2 -#define CPU_IS_FIRST_CORE_IN_PACKAGE 0x4 unsigned long long counter[MAX_ADDED_THREAD_COUNTERS]; } *thread_even, *thread_odd; struct core_data { + int base_cpu; unsigned long long c3; unsigned long long c6; unsigned long long c7; @@ -373,6 +981,7 @@ struct core_data { } *core_even, *core_odd; struct pkg_data { + int base_cpu; unsigned long long pc2; unsigned long long pc3; unsigned long long pc6; @@ -456,7 +1065,7 @@ off_t idx_to_offset(int idx) switch (idx) { case IDX_PKG_ENERGY: - if (do_rapl & RAPL_AMD_F17H) + if (platform->rapl_msrs & RAPL_AMD_F17H) offset = MSR_PKG_ENERGY_STAT; else offset = MSR_PKG_ENERGY_STATUS; @@ -516,17 +1125,17 @@ int idx_valid(int idx) { switch (idx) { case IDX_PKG_ENERGY: - return do_rapl & (RAPL_PKG | RAPL_AMD_F17H); + return platform->rapl_msrs & (RAPL_PKG | RAPL_AMD_F17H); case IDX_DRAM_ENERGY: - return do_rapl & RAPL_DRAM; + return platform->rapl_msrs & RAPL_DRAM; case IDX_PP0_ENERGY: - return do_rapl & RAPL_CORES_ENERGY_STATUS; + return platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS; case IDX_PP1_ENERGY: - return do_rapl & RAPL_GFX; + return platform->rapl_msrs & RAPL_GFX; case IDX_PKG_PERF: - return do_rapl & RAPL_PKG_PERF_STATUS; + return platform->rapl_msrs & RAPL_PKG_PERF_STATUS; case IDX_DRAM_PERF: - return do_rapl & RAPL_DRAM_PERF_STATUS; + return platform->rapl_msrs & RAPL_DRAM_PERF_STATUS; default: return 0; } @@ -563,6 +1172,9 @@ struct topo_params { int num_die; int num_cpus; int num_cores; + int allowed_packages; + int allowed_cpus; + int allowed_cores; int max_cpu_num; int max_node_num; int nodes_per_pkg; @@ -575,7 +1187,7 @@ struct timeval tv_even, tv_odd, tv_delta; int *irq_column_2_cpu; /* /proc/interrupts column numbers */ int *irqs_per_cpu; /* indexed by cpu_num */ -void setup_all_buffers(void); +void setup_all_buffers(bool startup); char *sys_lpi_file; char *sys_lpi_file_sysfs = "/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us"; @@ -586,6 +1198,11 @@ int cpu_is_not_present(int cpu) return !CPU_ISSET_S(cpu, cpu_present_setsize, cpu_present_set); } +int cpu_is_not_allowed(int cpu) +{ + return !CPU_ISSET_S(cpu, cpu_allowed_setsize, cpu_allowed_set); +} + /* * run func(thread, core, package) in topology order * skip non-present cpus @@ -603,10 +1220,9 @@ int for_all_cpus(int (func) (struct thread_data *, struct core_data *, struct pk struct thread_data *t; struct core_data *c; struct pkg_data *p; - t = GET_THREAD(thread_base, thread_no, core_no, node_no, pkg_no); - if (cpu_is_not_present(t->cpu_id)) + if (cpu_is_not_allowed(t->cpu_id)) continue; c = GET_CORE(core_base, core_no, node_no, pkg_no); @@ -622,6 +1238,25 @@ int for_all_cpus(int (func) (struct thread_data *, struct core_data *, struct pk return 0; } +int is_cpu_first_thread_in_core(struct thread_data *t, struct core_data *c, struct pkg_data *p) +{ + UNUSED(p); + + return ((int)t->cpu_id == c->base_cpu || c->base_cpu < 0); +} + +int is_cpu_first_core_in_package(struct thread_data *t, struct core_data *c, struct pkg_data *p) +{ + UNUSED(c); + + return ((int)t->cpu_id == p->base_cpu || p->base_cpu < 0); +} + +int is_cpu_first_thread_in_package(struct thread_data *t, struct core_data *c, struct pkg_data *p) +{ + return is_cpu_first_thread_in_core(t, c, p) && is_cpu_first_core_in_package(t, c, p); +} + int cpu_migrate(int cpu) { CPU_ZERO_S(cpu_affinity_setsize, cpu_affinity_set); @@ -904,11 +1539,11 @@ void print_header(char *delim) if (DO_BIC(BIC_CORE_THROT_CNT)) outp += sprintf(outp, "%sCoreThr", (printed++ ? delim : "")); - if (do_rapl && !rapl_joules) { - if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY)) + if (platform->rapl_msrs && !rapl_joules) { + if (DO_BIC(BIC_CorWatt) && platform->has_per_core_rapl) outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : "")); - } else if (do_rapl && rapl_joules) { - if (DO_BIC(BIC_Cor_J) && (do_rapl & RAPL_PER_CORE_ENERGY)) + } else if (platform->rapl_msrs && rapl_joules) { + if (DO_BIC(BIC_Cor_J) && platform->has_per_core_rapl) outp += sprintf(outp, "%sCor_J", (printed++ ? delim : "")); } @@ -966,10 +1601,10 @@ void print_header(char *delim) if (DO_BIC(BIC_SYS_LPI)) outp += sprintf(outp, "%sSYS%%LPI", (printed++ ? delim : "")); - if (do_rapl && !rapl_joules) { + if (platform->rapl_msrs && !rapl_joules) { if (DO_BIC(BIC_PkgWatt)) outp += sprintf(outp, "%sPkgWatt", (printed++ ? delim : "")); - if (DO_BIC(BIC_CorWatt) && !(do_rapl & RAPL_PER_CORE_ENERGY)) + if (DO_BIC(BIC_CorWatt) && !platform->has_per_core_rapl) outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : "")); if (DO_BIC(BIC_GFXWatt)) outp += sprintf(outp, "%sGFXWatt", (printed++ ? delim : "")); @@ -979,10 +1614,10 @@ void print_header(char *delim) outp += sprintf(outp, "%sPKG_%%", (printed++ ? delim : "")); if (DO_BIC(BIC_RAM__)) outp += sprintf(outp, "%sRAM_%%", (printed++ ? delim : "")); - } else if (do_rapl && rapl_joules) { + } else if (platform->rapl_msrs && rapl_joules) { if (DO_BIC(BIC_Pkg_J)) outp += sprintf(outp, "%sPkg_J", (printed++ ? delim : "")); - if (DO_BIC(BIC_Cor_J) && !(do_rapl & RAPL_PER_CORE_ENERGY)) + if (DO_BIC(BIC_Cor_J) && !platform->has_per_core_rapl) outp += sprintf(outp, "%sCor_J", (printed++ ? delim : "")); if (DO_BIC(BIC_GFX_J)) outp += sprintf(outp, "%sGFX_J", (printed++ ? delim : "")); @@ -1106,11 +1741,11 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data int printed = 0; /* if showing only 1st thread in core and this isn't one, bail out */ - if (show_core_only && !(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) + if (show_core_only && !is_cpu_first_thread_in_core(t, c, p)) return 0; /* if showing only 1st thread in pkg and this isn't one, bail out */ - if (show_pkg_only && !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) + if (show_pkg_only && !is_cpu_first_core_in_package(t, c, p)) return 0; /*if not summary line and --cpu is used */ @@ -1244,7 +1879,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * t->c1 / tsc); /* print per-core data only for 1st thread in core */ - if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) + if (!is_cpu_first_thread_in_core(t, c, p)) goto done; if (DO_BIC(BIC_CPU_c3)) @@ -1284,14 +1919,14 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data fmt8 = "%s%.2f"; - if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY)) + if (DO_BIC(BIC_CorWatt) && platform->has_per_core_rapl) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units / interval_float); - if (DO_BIC(BIC_Cor_J) && (do_rapl & RAPL_PER_CORE_ENERGY)) + if (DO_BIC(BIC_Cor_J) && platform->has_per_core_rapl) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), c->core_energy * rapl_energy_units); /* print per-package data only for 1st core in package */ - if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) + if (!is_cpu_first_core_in_package(t, c, p)) goto done; /* PkgTmp */ @@ -1352,7 +1987,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units / interval_float); - if (DO_BIC(BIC_CorWatt) && !(do_rapl & RAPL_PER_CORE_ENERGY)) + if (DO_BIC(BIC_CorWatt) && !platform->has_per_core_rapl) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units / interval_float); if (DO_BIC(BIC_GFXWatt)) @@ -1364,7 +1999,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data p->energy_dram * rapl_dram_energy_units / interval_float); if (DO_BIC(BIC_Pkg_J)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units); - if (DO_BIC(BIC_Cor_J) && !(do_rapl & RAPL_PER_CORE_ENERGY)) + if (DO_BIC(BIC_Cor_J) && !platform->has_per_core_rapl) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units); if (DO_BIC(BIC_GFX_J)) outp += sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_gfx * rapl_energy_units); @@ -1527,7 +2162,7 @@ void delta_core(struct core_data *new, struct core_data *old) int soft_c1_residency_display(int bic) { - if (!DO_BIC(BIC_CPU_c1) || use_c1_residency_msr) + if (!DO_BIC(BIC_CPU_c1) || platform->has_msr_core_c1_res) return 0; return DO_BIC_READ(bic); @@ -1567,7 +2202,8 @@ int delta_thread(struct thread_data *new, struct thread_data *old, struct core_d old->c1 = new->c1 - old->c1; - if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) || soft_c1_residency_display(BIC_Avg_MHz)) { + if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) || DO_BIC(BIC_IPC) + || soft_c1_residency_display(BIC_Avg_MHz)) { if ((new->aperf > old->aperf) && (new->mperf > old->mperf)) { old->aperf = new->aperf - old->aperf; old->mperf = new->mperf - old->mperf; @@ -1576,7 +2212,7 @@ int delta_thread(struct thread_data *new, struct thread_data *old, struct core_d } } - if (use_c1_residency_msr) { + if (platform->has_msr_core_c1_res) { /* * Some models have a dedicated C1 residency MSR, * which should be more accurate than the derivation below. @@ -1626,7 +2262,7 @@ int delta_cpu(struct thread_data *t, struct core_data *c, int retval = 0; /* calculate core delta only for 1st thread in core */ - if (t->flags & CPU_IS_FIRST_THREAD_IN_CORE) + if (is_cpu_first_thread_in_core(t, c, p)) delta_core(c, c2); /* always calculate thread delta */ @@ -1635,7 +2271,7 @@ int delta_cpu(struct thread_data *t, struct core_data *c, return retval; /* calculate package delta only for 1st core in package */ - if (t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE) + if (is_cpu_first_core_in_package(t, c, p)) retval = delta_package(p, p2); return retval; @@ -1663,9 +2299,6 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data t->irq_count = 0; t->smi_count = 0; - /* tells format_counters to dump all fields from this set */ - t->flags = CPU_IS_FIRST_THREAD_IN_CORE | CPU_IS_FIRST_CORE_IN_PACKAGE; - c->c3 = 0; c->c6 = 0; c->c7 = 0; @@ -1749,7 +2382,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) } /* sum per-core values only for 1st thread in core */ - if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) + if (!is_cpu_first_thread_in_core(t, c, p)) return 0; average.cores.c3 += c->c3; @@ -1769,7 +2402,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) } /* sum per-pkg values only for 1st core in pkg */ - if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) + if (!is_cpu_first_core_in_package(t, c, p)) return 0; if (DO_BIC(BIC_Totl_c0)) @@ -1834,40 +2467,40 @@ void compute_average(struct thread_data *t, struct core_data *c, struct pkg_data /* Use the global time delta for the average. */ average.threads.tv_delta = tv_delta; - average.threads.tsc /= topo.num_cpus; - average.threads.aperf /= topo.num_cpus; - average.threads.mperf /= topo.num_cpus; - average.threads.instr_count /= topo.num_cpus; - average.threads.c1 /= topo.num_cpus; + average.threads.tsc /= topo.allowed_cpus; + average.threads.aperf /= topo.allowed_cpus; + average.threads.mperf /= topo.allowed_cpus; + average.threads.instr_count /= topo.allowed_cpus; + average.threads.c1 /= topo.allowed_cpus; if (average.threads.irq_count > 9999999) sums_need_wide_columns = 1; - average.cores.c3 /= topo.num_cores; - average.cores.c6 /= topo.num_cores; - average.cores.c7 /= topo.num_cores; - average.cores.mc6_us /= topo.num_cores; + average.cores.c3 /= topo.allowed_cores; + average.cores.c6 /= topo.allowed_cores; + average.cores.c7 /= topo.allowed_cores; + average.cores.mc6_us /= topo.allowed_cores; if (DO_BIC(BIC_Totl_c0)) - average.packages.pkg_wtd_core_c0 /= topo.num_packages; + average.packages.pkg_wtd_core_c0 /= topo.allowed_packages; if (DO_BIC(BIC_Any_c0)) - average.packages.pkg_any_core_c0 /= topo.num_packages; + average.packages.pkg_any_core_c0 /= topo.allowed_packages; if (DO_BIC(BIC_GFX_c0)) - average.packages.pkg_any_gfxe_c0 /= topo.num_packages; + average.packages.pkg_any_gfxe_c0 /= topo.allowed_packages; if (DO_BIC(BIC_CPUGFX)) - average.packages.pkg_both_core_gfxe_c0 /= topo.num_packages; + average.packages.pkg_both_core_gfxe_c0 /= topo.allowed_packages; - average.packages.pc2 /= topo.num_packages; + average.packages.pc2 /= topo.allowed_packages; if (DO_BIC(BIC_Pkgpc3)) - average.packages.pc3 /= topo.num_packages; + average.packages.pc3 /= topo.allowed_packages; if (DO_BIC(BIC_Pkgpc6)) - average.packages.pc6 /= topo.num_packages; + average.packages.pc6 /= topo.allowed_packages; if (DO_BIC(BIC_Pkgpc7)) - average.packages.pc7 /= topo.num_packages; + average.packages.pc7 /= topo.allowed_packages; - average.packages.pc8 /= topo.num_packages; - average.packages.pc9 /= topo.num_packages; - average.packages.pc10 /= topo.num_packages; + average.packages.pc8 /= topo.allowed_packages; + average.packages.pc9 /= topo.allowed_packages; + average.packages.pc10 /= topo.allowed_packages; for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) @@ -1877,7 +2510,7 @@ void compute_average(struct thread_data *t, struct core_data *c, struct pkg_data sums_need_wide_columns = 1; continue; } - average.threads.counter[i] /= topo.num_cpus; + average.threads.counter[i] /= topo.allowed_cpus; } for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) @@ -1886,7 +2519,7 @@ void compute_average(struct thread_data *t, struct core_data *c, struct pkg_data if (average.cores.counter[i] > 9999999) sums_need_wide_columns = 1; } - average.cores.counter[i] /= topo.num_cores; + average.cores.counter[i] /= topo.allowed_cores; } for (i = 0, mp = sys.pp; mp; i++, mp = mp->next) { if (mp->format == FORMAT_RAW) @@ -1895,7 +2528,7 @@ void compute_average(struct thread_data *t, struct core_data *c, struct pkg_data if (average.packages.counter[i] > 9999999) sums_need_wide_columns = 1; } - average.packages.counter[i] /= topo.num_packages; + average.packages.counter[i] /= topo.allowed_packages; } } @@ -2092,7 +2725,8 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) retry: t->tsc = rdtsc(); /* we are running on local CPU of interest */ - if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) || soft_c1_residency_display(BIC_Avg_MHz)) { + if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) || DO_BIC(BIC_IPC) + || soft_c1_residency_display(BIC_Avg_MHz)) { unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time; /* @@ -2158,7 +2792,7 @@ retry: return -5; t->smi_count = msr & 0xFFFFFFFF; } - if (DO_BIC(BIC_CPU_c1) && use_c1_residency_msr) { + if (DO_BIC(BIC_CPU_c1) && platform->has_msr_core_c1_res) { if (get_msr(cpu, MSR_CORE_C1_RES, &t->c1)) return -6; } @@ -2169,7 +2803,7 @@ retry: } /* collect core counters only for 1st thread in core */ - if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) + if (!is_cpu_first_thread_in_core(t, c, p)) goto done; if (DO_BIC(BIC_CPU_c3) || soft_c1_residency_display(BIC_CPU_c3)) { @@ -2177,10 +2811,10 @@ retry: return -6; } - if ((DO_BIC(BIC_CPU_c6) || soft_c1_residency_display(BIC_CPU_c6)) && !do_knl_cstates) { + if ((DO_BIC(BIC_CPU_c6) || soft_c1_residency_display(BIC_CPU_c6)) && !platform->has_msr_knl_core_c6_residency) { if (get_msr(cpu, MSR_CORE_C6_RESIDENCY, &c->c6)) return -7; - } else if (do_knl_cstates || soft_c1_residency_display(BIC_CPU_c6)) { + } else if (platform->has_msr_knl_core_c6_residency && soft_c1_residency_display(BIC_CPU_c6)) { if (get_msr(cpu, MSR_KNL_CORE_C6_RESIDENCY, &c->c6)) return -7; } @@ -2212,7 +2846,7 @@ retry: if (DO_BIC(BIC_CORE_THROT_CNT)) get_core_throt_cnt(cpu, &c->core_throt_cnt); - if (do_rapl & RAPL_AMD_F17H) { + if (platform->rapl_msrs & RAPL_AMD_F17H) { if (get_msr(cpu, MSR_CORE_ENERGY_STAT, &msr)) return -14; c->core_energy = msr & 0xFFFFFFFF; @@ -2224,7 +2858,7 @@ retry: } /* collect package counters only for 1st core in package */ - if (!(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) + if (!is_cpu_first_core_in_package(t, c, p)) goto done; if (DO_BIC(BIC_Totl_c0)) { @@ -2247,7 +2881,7 @@ retry: if (get_msr(cpu, MSR_PKG_C3_RESIDENCY, &p->pc3)) return -9; if (DO_BIC(BIC_Pkgpc6)) { - if (do_slm_cstates) { + if (platform->has_msr_atom_pkg_c6_residency) { if (get_msr(cpu, MSR_ATOM_PKG_C6_RESIDENCY, &p->pc6)) return -10; } else { @@ -2277,37 +2911,37 @@ retry: if (DO_BIC(BIC_SYS_LPI)) p->sys_lpi = cpuidle_cur_sys_lpi_us; - if (do_rapl & RAPL_PKG) { + if (platform->rapl_msrs & RAPL_PKG) { if (get_msr_sum(cpu, MSR_PKG_ENERGY_STATUS, &msr)) return -13; p->energy_pkg = msr; } - if (do_rapl & RAPL_CORES_ENERGY_STATUS) { + if (platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS) { if (get_msr_sum(cpu, MSR_PP0_ENERGY_STATUS, &msr)) return -14; p->energy_cores = msr; } - if (do_rapl & RAPL_DRAM) { + if (platform->rapl_msrs & RAPL_DRAM) { if (get_msr_sum(cpu, MSR_DRAM_ENERGY_STATUS, &msr)) return -15; p->energy_dram = msr; } - if (do_rapl & RAPL_GFX) { + if (platform->rapl_msrs & RAPL_GFX) { if (get_msr_sum(cpu, MSR_PP1_ENERGY_STATUS, &msr)) return -16; p->energy_gfx = msr; } - if (do_rapl & RAPL_PKG_PERF_STATUS) { + if (platform->rapl_msrs & RAPL_PKG_PERF_STATUS) { if (get_msr_sum(cpu, MSR_PKG_PERF_STATUS, &msr)) return -16; p->rapl_pkg_perf_status = msr; } - if (do_rapl & RAPL_DRAM_PERF_STATUS) { + if (platform->rapl_msrs & RAPL_DRAM_PERF_STATUS) { if (get_msr_sum(cpu, MSR_DRAM_PERF_STATUS, &msr)) return -16; p->rapl_dram_perf_status = msr; } - if (do_rapl & RAPL_AMD_F17H) { + if (platform->rapl_msrs & RAPL_AMD_F17H) { if (get_msr_sum(cpu, MSR_PKG_ENERGY_STAT, &msr)) return -13; p->energy_pkg = msr; @@ -2414,18 +3048,58 @@ int icx_pkg_cstate_limits[16] = PCLRSV, PCLRSV }; -static void calculate_tsc_tweak() +void probe_cst_limit(void) { - tsc_tweak = base_hz / tsc_hz; -} + unsigned long long msr; + int *pkg_cstate_limits; + + if (!platform->has_nhm_msrs) + return; + + switch (platform->cst_limit) { + case CST_LIMIT_NHM: + pkg_cstate_limits = nhm_pkg_cstate_limits; + break; + case CST_LIMIT_SNB: + pkg_cstate_limits = snb_pkg_cstate_limits; + break; + case CST_LIMIT_HSW: + pkg_cstate_limits = hsw_pkg_cstate_limits; + break; + case CST_LIMIT_SKX: + pkg_cstate_limits = skx_pkg_cstate_limits; + break; + case CST_LIMIT_ICX: + pkg_cstate_limits = icx_pkg_cstate_limits; + break; + case CST_LIMIT_SLV: + pkg_cstate_limits = slv_pkg_cstate_limits; + break; + case CST_LIMIT_AMT: + pkg_cstate_limits = amt_pkg_cstate_limits; + break; + case CST_LIMIT_KNL: + pkg_cstate_limits = phi_pkg_cstate_limits; + break; + case CST_LIMIT_GMT: + pkg_cstate_limits = glm_pkg_cstate_limits; + break; + default: + return; + } -void prewake_cstate_probe(unsigned int family, unsigned int model); + get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr); + pkg_cstate_limit = pkg_cstate_limits[msr & 0xF]; +} -static void dump_nhm_platform_info(void) +static void dump_platform_info(void) { unsigned long long msr; unsigned int ratio; + if (!platform->has_nhm_msrs) + return; + get_msr(base_cpu, MSR_PLATFORM_INFO, &msr); fprintf(outf, "cpu%d: MSR_PLATFORM_INFO: 0x%08llx\n", base_cpu, msr); @@ -2435,19 +3109,27 @@ static void dump_nhm_platform_info(void) ratio = (msr >> 8) & 0xFF; fprintf(outf, "%d * %.1f = %.1f MHz base frequency\n", ratio, bclk, ratio * bclk); +} + +static void dump_power_ctl(void) +{ + unsigned long long msr; + + if (!platform->has_nhm_msrs) + return; get_msr(base_cpu, MSR_IA32_POWER_CTL, &msr); fprintf(outf, "cpu%d: MSR_IA32_POWER_CTL: 0x%08llx (C1E auto-promotion: %sabled)\n", base_cpu, msr, msr & 0x2 ? "EN" : "DIS"); /* C-state Pre-wake Disable (CSTATE_PREWAKE_DISABLE) */ - if (dis_cstate_prewake) + if (platform->has_cst_prewake_bit) fprintf(outf, "C-state Pre-wake: %sabled\n", msr & 0x40000000 ? "DIS" : "EN"); return; } -static void dump_hsw_turbo_ratio_limits(void) +static void dump_turbo_ratio_limit2(void) { unsigned long long msr; unsigned int ratio; @@ -2466,7 +3148,7 @@ static void dump_hsw_turbo_ratio_limits(void) return; } -static void dump_ivt_turbo_ratio_limits(void) +static void dump_turbo_ratio_limit1(void) { unsigned long long msr; unsigned int ratio; @@ -2509,29 +3191,7 @@ static void dump_ivt_turbo_ratio_limits(void) return; } -int has_turbo_ratio_group_limits(int family, int model) -{ - - if (!genuine_intel) - return 0; - - if (family != 6) - return 0; - - switch (model) { - case INTEL_FAM6_ATOM_GOLDMONT: - case INTEL_FAM6_SKYLAKE_X: - case INTEL_FAM6_ICELAKE_X: - case INTEL_FAM6_SAPPHIRERAPIDS_X: - case INTEL_FAM6_ATOM_GOLDMONT_D: - case INTEL_FAM6_ATOM_TREMONT_D: - return 1; - default: - return 0; - } -} - -static void dump_turbo_ratio_limits(int trl_msr_offset, int family, int model) +static void dump_turbo_ratio_limits(int trl_msr_offset) { unsigned long long msr, core_counts; int shift; @@ -2540,7 +3200,7 @@ static void dump_turbo_ratio_limits(int trl_msr_offset, int family, int model) fprintf(outf, "cpu%d: MSR_%sTURBO_RATIO_LIMIT: 0x%08llx\n", base_cpu, trl_msr_offset == MSR_SECONDARY_TURBO_RATIO_LIMIT ? "SECONDARY_" : "", msr); - if (has_turbo_ratio_group_limits(family, model)) { + if (platform->trl_msrs & TRL_CORECOUNT) { get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT1, &core_counts); fprintf(outf, "cpu%d: MSR_TURBO_RATIO_LIMIT1: 0x%08llx\n", base_cpu, core_counts); } else { @@ -2657,10 +3317,13 @@ static void dump_knl_turbo_ratio_limits(void) ratio[i], bclk, ratio[i] * bclk, cores[i]); } -static void dump_nhm_cst_cfg(void) +static void dump_cst_cfg(void) { unsigned long long msr; + if (!platform->has_nhm_msrs) + return; + get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr); fprintf(outf, "cpu%d: MSR_PKG_CST_CONFIG_CONTROL: 0x%08llx", base_cpu, msr); @@ -2673,7 +3336,7 @@ static void dump_nhm_cst_cfg(void) (msr & (1 << 15)) ? "" : "UN", (unsigned int)msr & 0xF, pkg_cstate_limit_strings[pkg_cstate_limit]); #define AUTOMATIC_CSTATE_CONVERSION (1UL << 16) - if (has_automatic_cstate_conversion) { + if (platform->has_cst_auto_convension) { fprintf(outf, ", automatic c-state conversion=%s", (msr & AUTOMATIC_CSTATE_CONVERSION) ? "on" : "off"); } @@ -2730,39 +3393,50 @@ void print_irtl(void) { unsigned long long msr; - get_msr(base_cpu, MSR_PKGC3_IRTL, &msr); - fprintf(outf, "cpu%d: MSR_PKGC3_IRTL: 0x%08llx (", base_cpu, msr); - fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT", - (msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]); - - get_msr(base_cpu, MSR_PKGC6_IRTL, &msr); - fprintf(outf, "cpu%d: MSR_PKGC6_IRTL: 0x%08llx (", base_cpu, msr); - fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT", - (msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]); + if (!platform->has_irtl_msrs) + return; - get_msr(base_cpu, MSR_PKGC7_IRTL, &msr); - fprintf(outf, "cpu%d: MSR_PKGC7_IRTL: 0x%08llx (", base_cpu, msr); - fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT", - (msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]); + if (platform->supported_cstates & PC3) { + get_msr(base_cpu, MSR_PKGC3_IRTL, &msr); + fprintf(outf, "cpu%d: MSR_PKGC3_IRTL: 0x%08llx (", base_cpu, msr); + fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT", + (msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]); + } - if (!do_irtl_hsw) - return; + if (platform->supported_cstates & PC6) { + get_msr(base_cpu, MSR_PKGC6_IRTL, &msr); + fprintf(outf, "cpu%d: MSR_PKGC6_IRTL: 0x%08llx (", base_cpu, msr); + fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT", + (msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]); + } - get_msr(base_cpu, MSR_PKGC8_IRTL, &msr); - fprintf(outf, "cpu%d: MSR_PKGC8_IRTL: 0x%08llx (", base_cpu, msr); - fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT", - (msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]); + if (platform->supported_cstates & PC7) { + get_msr(base_cpu, MSR_PKGC7_IRTL, &msr); + fprintf(outf, "cpu%d: MSR_PKGC7_IRTL: 0x%08llx (", base_cpu, msr); + fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT", + (msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]); + } - get_msr(base_cpu, MSR_PKGC9_IRTL, &msr); - fprintf(outf, "cpu%d: MSR_PKGC9_IRTL: 0x%08llx (", base_cpu, msr); - fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT", - (msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]); + if (platform->supported_cstates & PC8) { + get_msr(base_cpu, MSR_PKGC8_IRTL, &msr); + fprintf(outf, "cpu%d: MSR_PKGC8_IRTL: 0x%08llx (", base_cpu, msr); + fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT", + (msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]); + } - get_msr(base_cpu, MSR_PKGC10_IRTL, &msr); - fprintf(outf, "cpu%d: MSR_PKGC10_IRTL: 0x%08llx (", base_cpu, msr); - fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT", - (msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]); + if (platform->supported_cstates & PC9) { + get_msr(base_cpu, MSR_PKGC9_IRTL, &msr); + fprintf(outf, "cpu%d: MSR_PKGC9_IRTL: 0x%08llx (", base_cpu, msr); + fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT", + (msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]); + } + if (platform->supported_cstates & PC10) { + get_msr(base_cpu, MSR_PKGC10_IRTL, &msr); + fprintf(outf, "cpu%d: MSR_PKGC10_IRTL: 0x%08llx (", base_cpu, msr); + fprintf(outf, "%svalid, %lld ns)\n", msr & (1 << 15) ? "" : "NOT", + (msr & 0x3FF) * irtl_time_units[(msr >> 10) & 0x3]); + } } void free_fd_percpu(void) @@ -2785,6 +3459,14 @@ void free_all_buffers(void) cpu_present_set = NULL; cpu_present_setsize = 0; + CPU_FREE(cpu_effective_set); + cpu_effective_set = NULL; + cpu_effective_setsize = 0; + + CPU_FREE(cpu_allowed_set); + cpu_allowed_set = NULL; + cpu_allowed_setsize = 0; + CPU_FREE(cpu_affinity_set); cpu_affinity_set = NULL; cpu_affinity_setsize = 0; @@ -2927,6 +3609,59 @@ int get_physical_node_id(struct cpu_topology *thiscpu) return -1; } +static int parse_cpu_str(char *cpu_str, cpu_set_t *cpu_set, int cpu_set_size) +{ + unsigned int start, end; + char *next = cpu_str; + + while (next && *next) { + + if (*next == '-') /* no negative cpu numbers */ + return 1; + + start = strtoul(next, &next, 10); + + if (start >= CPU_SUBSET_MAXCPUS) + return 1; + CPU_SET_S(start, cpu_set_size, cpu_set); + + if (*next == '\0' || *next == '\n') + break; + + if (*next == ',') { + next += 1; + continue; + } + + if (*next == '-') { + next += 1; /* start range */ + } else if (*next == '.') { + next += 1; + if (*next == '.') + next += 1; /* start range */ + else + return 1; + } + + end = strtoul(next, &next, 10); + if (end <= start) + return 1; + + while (++start <= end) { + if (start >= CPU_SUBSET_MAXCPUS) + return 1; + CPU_SET_S(start, cpu_set_size, cpu_set); + } + + if (*next == ',') + next += 1; + else if (*next != '\0' && *next != '\n') + return 1; + } + + return 0; +} + int get_thread_siblings(struct cpu_topology *thiscpu) { char path[80], character; @@ -2998,7 +3733,7 @@ int for_all_cpus_2(int (func) (struct thread_data *, struct core_data *, t = GET_THREAD(thread_base, thread_no, core_no, node_no, pkg_no); - if (cpu_is_not_present(t->cpu_id)) + if (cpu_is_not_allowed(t->cpu_id)) continue; t2 = GET_THREAD(thread_base2, thread_no, core_no, node_no, pkg_no); @@ -3050,11 +3785,51 @@ int for_all_proc_cpus(int (func) (int)) return 0; } +#define PATH_EFFECTIVE_CPUS "/sys/fs/cgroup/cpuset.cpus.effective" + +static char cpu_effective_str[1024]; + +static int update_effective_str(bool startup) +{ + FILE *fp; + char *pos; + char buf[1024]; + int ret; + + if (cpu_effective_str[0] == '\0' && !startup) + return 0; + + fp = fopen(PATH_EFFECTIVE_CPUS, "r"); + if (!fp) + return 0; + + pos = fgets(buf, 1024, fp); + if (!pos) + err(1, "%s: file read failed\n", PATH_EFFECTIVE_CPUS); + + fclose(fp); + + ret = strncmp(cpu_effective_str, buf, 1024); + if (!ret) + return 0; + + strncpy(cpu_effective_str, buf, 1024); + return 1; +} + +static void update_effective_set(bool startup) +{ + update_effective_str(startup); + + if (parse_cpu_str(cpu_effective_str, cpu_effective_set, cpu_effective_setsize)) + err(1, "%s: cpu str malformat %s\n", PATH_EFFECTIVE_CPUS, cpu_effective_str); +} + void re_initialize(void) { free_all_buffers(); - setup_all_buffers(); - fprintf(outf, "turbostat: re-initialized with num_cpus %d\n", topo.num_cpus); + setup_all_buffers(false); + fprintf(outf, "turbostat: re-initialized with num_cpus %d, allowed_cpus %d\n", topo.num_cpus, topo.allowed_cpus); } void set_max_cpu_num(void) @@ -3191,8 +3966,8 @@ int snapshot_gfx_rc6_ms(void) /* * snapshot_gfx_mhz() * - * record snapshot of - * /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz + * fall back to /sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz + * when /sys/class/drm/card0/gt_cur_freq_mhz is not available. * * return 1 if config change requires a restart, else return 0 */ @@ -3201,9 +3976,11 @@ int snapshot_gfx_mhz(void) static FILE *fp; int retval; - if (fp == NULL) - fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", "r"); - else { + if (fp == NULL) { + fp = fopen("/sys/class/drm/card0/gt_cur_freq_mhz", "r"); + if (!fp) + fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", "r"); + } else { rewind(fp); fflush(fp); } @@ -3218,8 +3995,8 @@ int snapshot_gfx_mhz(void) /* * snapshot_gfx_cur_mhz() * - * record snapshot of - * /sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz + * fall back to /sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz + * when /sys/class/drm/card0/gt_act_freq_mhz is not available. * * return 1 if config change requires a restart, else return 0 */ @@ -3228,9 +4005,11 @@ int snapshot_gfx_act_mhz(void) static FILE *fp; int retval; - if (fp == NULL) - fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", "r"); - else { + if (fp == NULL) { + fp = fopen("/sys/class/drm/card0/gt_act_freq_mhz", "r"); + if (!fp) + fp = fopen_or_die("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", "r"); + } else { rewind(fp); fflush(fp); } @@ -3562,6 +4341,10 @@ restart: re_initialize(); goto restart; } + if (update_effective_str(false)) { + re_initialize(); + goto restart; + } do_sleep(); if (snapshot_proc_sysfs_files()) goto restart; @@ -3674,395 +4457,31 @@ void check_permissions(void) exit(-6); } -/* - * NHM adds support for additional MSRs: - * - * MSR_SMI_COUNT 0x00000034 - * - * MSR_PLATFORM_INFO 0x000000ce - * MSR_PKG_CST_CONFIG_CONTROL 0x000000e2 - * - * MSR_MISC_PWR_MGMT 0x000001aa - * - * MSR_PKG_C3_RESIDENCY 0x000003f8 - * MSR_PKG_C6_RESIDENCY 0x000003f9 - * MSR_CORE_C3_RESIDENCY 0x000003fc - * MSR_CORE_C6_RESIDENCY 0x000003fd - * - * Side effect: - * sets global pkg_cstate_limit to decode MSR_PKG_CST_CONFIG_CONTROL - * sets has_misc_feature_control - */ -int probe_nhm_msrs(unsigned int family, unsigned int model) +void probe_bclk(void) { unsigned long long msr; unsigned int base_ratio; - int *pkg_cstate_limits; - if (!genuine_intel) - return 0; - - if (family != 6) - return 0; - - bclk = discover_bclk(family, model); + if (!platform->has_nhm_msrs) + return; - switch (model) { - case INTEL_FAM6_NEHALEM: /* Core i7 and i5 Processor - Clarksfield, Lynnfield, Jasper Forest */ - case INTEL_FAM6_NEHALEM_EX: /* Nehalem-EX Xeon - Beckton */ - pkg_cstate_limits = nhm_pkg_cstate_limits; - break; - case INTEL_FAM6_SANDYBRIDGE: /* SNB */ - case INTEL_FAM6_SANDYBRIDGE_X: /* SNB Xeon */ - case INTEL_FAM6_IVYBRIDGE: /* IVB */ - case INTEL_FAM6_IVYBRIDGE_X: /* IVB Xeon */ - pkg_cstate_limits = snb_pkg_cstate_limits; - has_misc_feature_control = 1; - break; - case INTEL_FAM6_HASWELL: /* HSW */ - case INTEL_FAM6_HASWELL_G: /* HSW */ - case INTEL_FAM6_HASWELL_X: /* HSX */ - case INTEL_FAM6_HASWELL_L: /* HSW */ - case INTEL_FAM6_BROADWELL: /* BDW */ - case INTEL_FAM6_BROADWELL_G: /* BDW */ - case INTEL_FAM6_BROADWELL_X: /* BDX */ - case INTEL_FAM6_SKYLAKE_L: /* SKL */ - case INTEL_FAM6_CANNONLAKE_L: /* CNL */ - pkg_cstate_limits = hsw_pkg_cstate_limits; - has_misc_feature_control = 1; - break; - case INTEL_FAM6_SKYLAKE_X: /* SKX */ - case INTEL_FAM6_SAPPHIRERAPIDS_X: /* SPR */ - pkg_cstate_limits = skx_pkg_cstate_limits; - has_misc_feature_control = 1; - break; - case INTEL_FAM6_ICELAKE_X: /* ICX */ - pkg_cstate_limits = icx_pkg_cstate_limits; - has_misc_feature_control = 1; - break; - case INTEL_FAM6_ATOM_SILVERMONT: /* BYT */ - no_MSR_MISC_PWR_MGMT = 1; - /* FALLTHRU */ - case INTEL_FAM6_ATOM_SILVERMONT_D: /* AVN */ - pkg_cstate_limits = slv_pkg_cstate_limits; - break; - case INTEL_FAM6_ATOM_AIRMONT: /* AMT */ - pkg_cstate_limits = amt_pkg_cstate_limits; - no_MSR_MISC_PWR_MGMT = 1; - break; - case INTEL_FAM6_XEON_PHI_KNL: /* PHI */ - pkg_cstate_limits = phi_pkg_cstate_limits; - break; - case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ - case INTEL_FAM6_ATOM_GOLDMONT_PLUS: - case INTEL_FAM6_ATOM_GOLDMONT_D: /* DNV */ - case INTEL_FAM6_ATOM_TREMONT: /* EHL */ - case INTEL_FAM6_ATOM_TREMONT_D: /* JVL */ - pkg_cstate_limits = glm_pkg_cstate_limits; - break; - default: - return 0; - } - get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr); - pkg_cstate_limit = pkg_cstate_limits[msr & 0xF]; + if (platform->bclk_freq == BCLK_100MHZ) + bclk = 100.00; + else if (platform->bclk_freq == BCLK_133MHZ) + bclk = 133.33; + else if (platform->bclk_freq == BCLK_SLV) + bclk = slm_bclk(); + else + return; get_msr(base_cpu, MSR_PLATFORM_INFO, &msr); base_ratio = (msr >> 8) & 0xFF; base_hz = base_ratio * bclk * 1000000; has_base_hz = 1; - return 1; -} - -/* - * SLV client has support for unique MSRs: - * - * MSR_CC6_DEMOTION_POLICY_CONFIG - * MSR_MC6_DEMOTION_POLICY_CONFIG - */ - -int has_slv_msrs(unsigned int family, unsigned int model) -{ - if (!genuine_intel) - return 0; - - if (family != 6) - return 0; - - switch (model) { - case INTEL_FAM6_ATOM_SILVERMONT: - case INTEL_FAM6_ATOM_SILVERMONT_MID: - case INTEL_FAM6_ATOM_AIRMONT_MID: - return 1; - } - return 0; -} - -int is_dnv(unsigned int family, unsigned int model) -{ - - if (!genuine_intel) - return 0; - - if (family != 6) - return 0; - - switch (model) { - case INTEL_FAM6_ATOM_GOLDMONT_D: - return 1; - } - return 0; -} - -int is_bdx(unsigned int family, unsigned int model) -{ - - if (!genuine_intel) - return 0; - - if (family != 6) - return 0; - - switch (model) { - case INTEL_FAM6_BROADWELL_X: - return 1; - } - return 0; -} - -int is_skx(unsigned int family, unsigned int model) -{ - - if (!genuine_intel) - return 0; - - if (family != 6) - return 0; - - switch (model) { - case INTEL_FAM6_SKYLAKE_X: - return 1; - } - return 0; -} - -int is_icx(unsigned int family, unsigned int model) -{ - - if (!genuine_intel) - return 0; - - if (family != 6) - return 0; - - switch (model) { - case INTEL_FAM6_ICELAKE_X: - return 1; - } - return 0; -} - -int is_spr(unsigned int family, unsigned int model) -{ - - if (!genuine_intel) - return 0; - - if (family != 6) - return 0; - - switch (model) { - case INTEL_FAM6_SAPPHIRERAPIDS_X: - return 1; - } - return 0; -} - -int is_ehl(unsigned int family, unsigned int model) -{ - if (!genuine_intel) - return 0; - - if (family != 6) - return 0; - - switch (model) { - case INTEL_FAM6_ATOM_TREMONT: - return 1; - } - return 0; -} - -int is_jvl(unsigned int family, unsigned int model) -{ - if (!genuine_intel) - return 0; - - if (family != 6) - return 0; - - switch (model) { - case INTEL_FAM6_ATOM_TREMONT_D: - return 1; - } - return 0; -} - -int has_turbo_ratio_limit(unsigned int family, unsigned int model) -{ - if (has_slv_msrs(family, model)) - return 0; - - if (family != 6) - return 0; - - switch (model) { - /* Nehalem compatible, but do not include turbo-ratio limit support */ - case INTEL_FAM6_NEHALEM_EX: /* Nehalem-EX Xeon - Beckton */ - case INTEL_FAM6_XEON_PHI_KNL: /* PHI - Knights Landing (different MSR definition) */ - return 0; - default: - return 1; - } -} - -int has_atom_turbo_ratio_limit(unsigned int family, unsigned int model) -{ - if (has_slv_msrs(family, model)) - return 1; - - return 0; -} - -int has_ivt_turbo_ratio_limit(unsigned int family, unsigned int model) -{ - if (!genuine_intel) - return 0; - if (family != 6) - return 0; - - switch (model) { - case INTEL_FAM6_IVYBRIDGE_X: /* IVB Xeon */ - case INTEL_FAM6_HASWELL_X: /* HSW Xeon */ - return 1; - default: - return 0; - } -} - -int has_hsw_turbo_ratio_limit(unsigned int family, unsigned int model) -{ - if (!genuine_intel) - return 0; - - if (family != 6) - return 0; - - switch (model) { - case INTEL_FAM6_HASWELL_X: /* HSW Xeon */ - return 1; - default: - return 0; - } -} - -int has_knl_turbo_ratio_limit(unsigned int family, unsigned int model) -{ - if (!genuine_intel) - return 0; - - if (family != 6) - return 0; - - switch (model) { - case INTEL_FAM6_XEON_PHI_KNL: /* Knights Landing */ - return 1; - default: - return 0; - } -} - -int has_glm_turbo_ratio_limit(unsigned int family, unsigned int model) -{ - if (!genuine_intel) - return 0; - - if (family != 6) - return 0; - - switch (model) { - case INTEL_FAM6_ATOM_GOLDMONT: - case INTEL_FAM6_SKYLAKE_X: - case INTEL_FAM6_ICELAKE_X: - case INTEL_FAM6_SAPPHIRERAPIDS_X: - return 1; - default: - return 0; - } -} - -int has_config_tdp(unsigned int family, unsigned int model) -{ - if (!genuine_intel) - return 0; - - if (family != 6) - return 0; - - switch (model) { - case INTEL_FAM6_IVYBRIDGE: /* IVB */ - case INTEL_FAM6_HASWELL: /* HSW */ - case INTEL_FAM6_HASWELL_X: /* HSX */ - case INTEL_FAM6_HASWELL_L: /* HSW */ - case INTEL_FAM6_HASWELL_G: /* HSW */ - case INTEL_FAM6_BROADWELL: /* BDW */ - case INTEL_FAM6_BROADWELL_G: /* BDW */ - case INTEL_FAM6_BROADWELL_X: /* BDX */ - case INTEL_FAM6_SKYLAKE_L: /* SKL */ - case INTEL_FAM6_CANNONLAKE_L: /* CNL */ - case INTEL_FAM6_SKYLAKE_X: /* SKX */ - case INTEL_FAM6_ICELAKE_X: /* ICX */ - case INTEL_FAM6_SAPPHIRERAPIDS_X: /* SPR */ - case INTEL_FAM6_XEON_PHI_KNL: /* Knights Landing */ - return 1; - default: - return 0; - } -} - -/* - * tcc_offset_bits: - * 0: Tcc Offset not supported (Default) - * 6: Bit 29:24 of MSR_PLATFORM_INFO - * 4: Bit 27:24 of MSR_PLATFORM_INFO - */ -void check_tcc_offset(int model) -{ - unsigned long long msr; - - if (!genuine_intel) - return; - - switch (model) { - case INTEL_FAM6_SKYLAKE_L: - case INTEL_FAM6_SKYLAKE: - case INTEL_FAM6_KABYLAKE_L: - case INTEL_FAM6_KABYLAKE: - case INTEL_FAM6_ICELAKE_L: - case INTEL_FAM6_ICELAKE: - case INTEL_FAM6_TIGERLAKE_L: - case INTEL_FAM6_TIGERLAKE: - case INTEL_FAM6_COMETLAKE: - if (!get_msr(base_cpu, MSR_PLATFORM_INFO, &msr)) { - msr = (msr >> 30) & 1; - if (msr) - tcc_offset_bits = 6; - } - return; - default: - return; - } + if (platform->enable_tsc_tweak) + tsc_tweak = base_hz / tsc_hz; } static void remove_underbar(char *s) @@ -4078,44 +4497,37 @@ static void remove_underbar(char *s) *to = 0; } -static void dump_turbo_ratio_info(unsigned int family, unsigned int model) +static void dump_turbo_ratio_info(void) { if (!has_turbo) return; - if (has_hsw_turbo_ratio_limit(family, model)) - dump_hsw_turbo_ratio_limits(); + if (!platform->has_nhm_msrs) + return; + + if (platform->trl_msrs & TRL_LIMIT2) + dump_turbo_ratio_limit2(); - if (has_ivt_turbo_ratio_limit(family, model)) - dump_ivt_turbo_ratio_limits(); + if (platform->trl_msrs & TRL_LIMIT1) + dump_turbo_ratio_limit1(); - if (has_turbo_ratio_limit(family, model)) { - dump_turbo_ratio_limits(MSR_TURBO_RATIO_LIMIT, family, model); + if (platform->trl_msrs & TRL_BASE) { + dump_turbo_ratio_limits(MSR_TURBO_RATIO_LIMIT); if (is_hybrid) - dump_turbo_ratio_limits(MSR_SECONDARY_TURBO_RATIO_LIMIT, family, model); + dump_turbo_ratio_limits(MSR_SECONDARY_TURBO_RATIO_LIMIT); } - if (has_atom_turbo_ratio_limit(family, model)) + if (platform->trl_msrs & TRL_ATOM) dump_atom_turbo_ratio_limits(); - if (has_knl_turbo_ratio_limit(family, model)) + if (platform->trl_msrs & TRL_KNL) dump_knl_turbo_ratio_limits(); - if (has_config_tdp(family, model)) + if (platform->has_config_tdp) dump_config_tdp(); } -static void dump_cstate_pstate_config_info(unsigned int family, unsigned int model) -{ - if (!do_nhm_platform_info) - return; - - dump_nhm_platform_info(); - dump_turbo_ratio_info(family, model); - dump_nhm_cst_cfg(); -} - static int read_sysfs_int(char *path) { FILE *input; @@ -4152,7 +4564,7 @@ static void dump_sysfs_file(char *path) fprintf(outf, "%s: %s", strrchr(path, '/') + 1, cpuidle_buf); } -static void intel_uncore_frequency_probe(void) +static void probe_intel_uncore_frequency(void) { int i, j; char path[128]; @@ -4163,6 +4575,10 @@ static void intel_uncore_frequency_probe(void) if (access("/sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00", R_OK)) return; + /* Cluster level sysfs not supported yet. */ + if (!access("/sys/devices/system/cpu/intel_uncore_frequency/uncore00", R_OK)) + return; + if (!access("/sys/devices/system/cpu/intel_uncore_frequency/package_00_die_00/current_freq_khz", R_OK)) BIC_PRESENT(BIC_UNCORE_MHZ); @@ -4194,6 +4610,20 @@ static void intel_uncore_frequency_probe(void) } } +static void probe_graphics(void) +{ + if (!access("/sys/class/drm/card0/power/rc6_residency_ms", R_OK)) + BIC_PRESENT(BIC_GFX_rc6); + + if (!access("/sys/class/drm/card0/gt_cur_freq_mhz", R_OK) || + !access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK)) + BIC_PRESENT(BIC_GFXMHz); + + if (!access("/sys/class/drm/card0/gt_act_freq_mhz", R_OK) || + !access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK)) + BIC_PRESENT(BIC_GFXACTMHz); +} + static void dump_sysfs_cstate_config(void) { char path[64]; @@ -4310,7 +4740,7 @@ int print_epb(struct thread_data *t, struct core_data *c, struct pkg_data *p) cpu = t->cpu_id; /* EPB is per-package */ - if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) + if (!is_cpu_first_thread_in_package(t, c, p)) return 0; if (cpu_migrate(cpu)) { @@ -4359,7 +4789,7 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p) cpu = t->cpu_id; /* MSR_HWP_CAPABILITIES is per-package */ - if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) + if (!is_cpu_first_thread_in_package(t, c, p)) return 0; if (cpu_migrate(cpu)) { @@ -4442,7 +4872,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data cpu = t->cpu_id; /* per-package */ - if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) + if (!is_cpu_first_thread_in_package(t, c, p)) return 0; if (cpu_migrate(cpu)) { @@ -4450,7 +4880,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data return -1; } - if (do_core_perf_limit_reasons) { + if (platform->plr_msrs & PLR_CORE) { get_msr(cpu, MSR_CORE_PERF_LIMIT_REASONS, &msr); fprintf(outf, "cpu%d: MSR_CORE_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr); fprintf(outf, " (Active: %s%s%s%s%s%s%s%s%s%s%s%s%s%s)", @@ -4483,7 +4913,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data (msr & 1 << 17) ? "ThermStatus, " : "", (msr & 1 << 16) ? "PROCHOT, " : ""); } - if (do_gfx_perf_limit_reasons) { + if (platform->plr_msrs & PLR_GFX) { get_msr(cpu, MSR_GFX_PERF_LIMIT_REASONS, &msr); fprintf(outf, "cpu%d: MSR_GFX_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr); fprintf(outf, " (Active: %s%s%s%s%s%s%s%s)", @@ -4503,7 +4933,7 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data (msr & 1 << 25) ? "GFXPwr, " : "", (msr & 1 << 26) ? "PkgPwrL1, " : "", (msr & 1 << 27) ? "PkgPwrL2, " : ""); } - if (do_ring_perf_limit_reasons) { + if (platform->plr_msrs & PLR_RING) { get_msr(cpu, MSR_RING_PERF_LIMIT_REASONS, &msr); fprintf(outf, "cpu%d: MSR_RING_PERF_LIMIT_REASONS, 0x%08llx", cpu, msr); fprintf(outf, " (Active: %s%s%s%s%s%s)", @@ -4525,208 +4955,74 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data #define RAPL_POWER_GRANULARITY 0x7FFF /* 15 bit power granularity */ #define RAPL_TIME_GRANULARITY 0x3F /* 6 bit time granularity */ -double get_tdp_intel(unsigned int model) +double get_quirk_tdp(void) { - unsigned long long msr; + if (platform->rapl_quirk_tdp) + return platform->rapl_quirk_tdp; - if (do_rapl & RAPL_PKG_POWER_INFO) - if (!get_msr(base_cpu, MSR_PKG_POWER_INFO, &msr)) - return ((msr >> 0) & RAPL_POWER_GRANULARITY) * rapl_power_units; - - switch (model) { - case INTEL_FAM6_ATOM_SILVERMONT: - case INTEL_FAM6_ATOM_SILVERMONT_D: - return 30.0; - default: - return 135.0; - } + return 135.0; } -double get_tdp_amd(unsigned int family) +double get_tdp_intel(void) { - UNUSED(family); + unsigned long long msr; - /* This is the max stock TDP of HEDT/Server Fam17h+ chips */ - return 280.0; + if (platform->rapl_msrs & RAPL_PKG_POWER_INFO) + if (!get_msr(base_cpu, MSR_PKG_POWER_INFO, &msr)) + return ((msr >> 0) & RAPL_POWER_GRANULARITY) * rapl_power_units; + return get_quirk_tdp(); } -/* - * rapl_dram_energy_units_probe() - * Energy units are either hard-coded, or come from RAPL Energy Unit MSR. - */ -static double rapl_dram_energy_units_probe(int model, double rapl_energy_units) +double get_tdp_amd(void) { - /* only called for genuine_intel, family 6 */ - - switch (model) { - case INTEL_FAM6_HASWELL_X: /* HSX */ - case INTEL_FAM6_BROADWELL_X: /* BDX */ - case INTEL_FAM6_SKYLAKE_X: /* SKX */ - case INTEL_FAM6_XEON_PHI_KNL: /* KNL */ - case INTEL_FAM6_ICELAKE_X: /* ICX */ - return (rapl_dram_energy_units = 15.3 / 1000000); - default: - return (rapl_energy_units); - } + return get_quirk_tdp(); } -void rapl_probe_intel(unsigned int family, unsigned int model) +void rapl_probe_intel(void) { unsigned long long msr; unsigned int time_unit; double tdp; - if (family != 6) - return; - - switch (model) { - case INTEL_FAM6_SANDYBRIDGE: - case INTEL_FAM6_IVYBRIDGE: - case INTEL_FAM6_HASWELL: /* HSW */ - case INTEL_FAM6_HASWELL_L: /* HSW */ - case INTEL_FAM6_HASWELL_G: /* HSW */ - case INTEL_FAM6_BROADWELL: /* BDW */ - case INTEL_FAM6_BROADWELL_G: /* BDW */ - do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_GFX | RAPL_PKG_POWER_INFO; - if (rapl_joules) { - BIC_PRESENT(BIC_Pkg_J); - BIC_PRESENT(BIC_Cor_J); - BIC_PRESENT(BIC_GFX_J); - } else { - BIC_PRESENT(BIC_PkgWatt); - BIC_PRESENT(BIC_CorWatt); - BIC_PRESENT(BIC_GFXWatt); - } - break; - case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ - case INTEL_FAM6_ATOM_GOLDMONT_PLUS: - do_rapl = RAPL_PKG | RAPL_PKG_POWER_INFO; - if (rapl_joules) - BIC_PRESENT(BIC_Pkg_J); - else - BIC_PRESENT(BIC_PkgWatt); - break; - case INTEL_FAM6_ATOM_TREMONT: /* EHL */ - do_rapl = - RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS - | RAPL_GFX | RAPL_PKG_POWER_INFO; - if (rapl_joules) { - BIC_PRESENT(BIC_Pkg_J); - BIC_PRESENT(BIC_Cor_J); - BIC_PRESENT(BIC_RAM_J); - BIC_PRESENT(BIC_GFX_J); - } else { - BIC_PRESENT(BIC_PkgWatt); - BIC_PRESENT(BIC_CorWatt); - BIC_PRESENT(BIC_RAMWatt); - BIC_PRESENT(BIC_GFXWatt); - } - break; - case INTEL_FAM6_ATOM_TREMONT_D: /* JVL */ - do_rapl = RAPL_PKG | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO; - BIC_PRESENT(BIC_PKG__); - if (rapl_joules) - BIC_PRESENT(BIC_Pkg_J); - else - BIC_PRESENT(BIC_PkgWatt); - break; - case INTEL_FAM6_SKYLAKE_L: /* SKL */ - case INTEL_FAM6_CANNONLAKE_L: /* CNL */ - do_rapl = - RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS - | RAPL_GFX | RAPL_PKG_POWER_INFO; - BIC_PRESENT(BIC_PKG__); - BIC_PRESENT(BIC_RAM__); - if (rapl_joules) { + if (rapl_joules) { + if (platform->rapl_msrs & RAPL_PKG_ENERGY_STATUS) BIC_PRESENT(BIC_Pkg_J); + if (platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS) BIC_PRESENT(BIC_Cor_J); + if (platform->rapl_msrs & RAPL_DRAM_ENERGY_STATUS) BIC_PRESENT(BIC_RAM_J); + if (platform->rapl_msrs & RAPL_GFX_ENERGY_STATUS) BIC_PRESENT(BIC_GFX_J); - } else { + } else { + if (platform->rapl_msrs & RAPL_PKG_ENERGY_STATUS) BIC_PRESENT(BIC_PkgWatt); + if (platform->rapl_msrs & RAPL_CORE_ENERGY_STATUS) BIC_PRESENT(BIC_CorWatt); + if (platform->rapl_msrs & RAPL_DRAM_ENERGY_STATUS) BIC_PRESENT(BIC_RAMWatt); + if (platform->rapl_msrs & RAPL_GFX_ENERGY_STATUS) BIC_PRESENT(BIC_GFXWatt); - } - break; - case INTEL_FAM6_HASWELL_X: /* HSX */ - case INTEL_FAM6_BROADWELL_X: /* BDX */ - case INTEL_FAM6_SKYLAKE_X: /* SKX */ - case INTEL_FAM6_ICELAKE_X: /* ICX */ - case INTEL_FAM6_SAPPHIRERAPIDS_X: /* SPR */ - case INTEL_FAM6_XEON_PHI_KNL: /* KNL */ - do_rapl = - RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | - RAPL_PKG_POWER_INFO; - BIC_PRESENT(BIC_PKG__); - BIC_PRESENT(BIC_RAM__); - if (rapl_joules) { - BIC_PRESENT(BIC_Pkg_J); - BIC_PRESENT(BIC_RAM_J); - } else { - BIC_PRESENT(BIC_PkgWatt); - BIC_PRESENT(BIC_RAMWatt); - } - break; - case INTEL_FAM6_SANDYBRIDGE_X: - case INTEL_FAM6_IVYBRIDGE_X: - do_rapl = - RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_PKG_PERF_STATUS | - RAPL_DRAM_PERF_STATUS | RAPL_PKG_POWER_INFO; - BIC_PRESENT(BIC_PKG__); - BIC_PRESENT(BIC_RAM__); - if (rapl_joules) { - BIC_PRESENT(BIC_Pkg_J); - BIC_PRESENT(BIC_Cor_J); - BIC_PRESENT(BIC_RAM_J); - } else { - BIC_PRESENT(BIC_PkgWatt); - BIC_PRESENT(BIC_CorWatt); - BIC_PRESENT(BIC_RAMWatt); - } - break; - case INTEL_FAM6_ATOM_SILVERMONT: /* BYT */ - case INTEL_FAM6_ATOM_SILVERMONT_D: /* AVN */ - do_rapl = RAPL_PKG | RAPL_CORES; - if (rapl_joules) { - BIC_PRESENT(BIC_Pkg_J); - BIC_PRESENT(BIC_Cor_J); - } else { - BIC_PRESENT(BIC_PkgWatt); - BIC_PRESENT(BIC_CorWatt); - } - break; - case INTEL_FAM6_ATOM_GOLDMONT_D: /* DNV */ - do_rapl = - RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | - RAPL_PKG_POWER_INFO | RAPL_CORES_ENERGY_STATUS; + } + + if (platform->rapl_msrs & RAPL_PKG_PERF_STATUS) BIC_PRESENT(BIC_PKG__); + if (platform->rapl_msrs & RAPL_DRAM_PERF_STATUS) BIC_PRESENT(BIC_RAM__); - if (rapl_joules) { - BIC_PRESENT(BIC_Pkg_J); - BIC_PRESENT(BIC_Cor_J); - BIC_PRESENT(BIC_RAM_J); - } else { - BIC_PRESENT(BIC_PkgWatt); - BIC_PRESENT(BIC_CorWatt); - BIC_PRESENT(BIC_RAMWatt); - } - break; - default: - return; - } /* units on package 0, verify later other packages match */ if (get_msr(base_cpu, MSR_RAPL_POWER_UNIT, &msr)) return; rapl_power_units = 1.0 / (1 << (msr & 0xF)); - if (model == INTEL_FAM6_ATOM_SILVERMONT) + if (platform->has_rapl_divisor) rapl_energy_units = 1.0 * (1 << (msr >> 8 & 0x1F)) / 1000000; else rapl_energy_units = 1.0 / (1 << (msr >> 8 & 0x1F)); - rapl_dram_energy_units = rapl_dram_energy_units_probe(model, rapl_energy_units); + if (platform->has_fixed_rapl_unit) + rapl_dram_energy_units = (15.3 / 1000000); + else + rapl_dram_energy_units = rapl_energy_units; time_unit = msr >> 16 & 0xF; if (time_unit == 0) @@ -4734,32 +5030,18 @@ void rapl_probe_intel(unsigned int family, unsigned int model) rapl_time_units = 1.0 / (1 << (time_unit)); - tdp = get_tdp_intel(model); + tdp = get_tdp_intel(); rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp; if (!quiet) fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp); } -void rapl_probe_amd(unsigned int family, unsigned int model) +void rapl_probe_amd(void) { unsigned long long msr; - unsigned int eax, ebx, ecx, edx; - unsigned int has_rapl = 0; double tdp; - UNUSED(model); - - if (max_extended_level >= 0x80000007) { - __cpuid(0x80000007, eax, ebx, ecx, edx); - /* RAPL (Fam 17h+) */ - has_rapl = edx & (1 << 14); - } - - if (!has_rapl || family < 0x17) - return; - - do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY; if (rapl_joules) { BIC_PRESENT(BIC_Pkg_J); BIC_PRESENT(BIC_Cor_J); @@ -4775,128 +5057,13 @@ void rapl_probe_amd(unsigned int family, unsigned int model) rapl_energy_units = ldexp(1.0, -(msr >> 8 & 0x1f)); rapl_power_units = ldexp(1.0, -(msr & 0xf)); - tdp = get_tdp_amd(family); + tdp = get_tdp_amd(); rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp; if (!quiet) fprintf(outf, "RAPL: %.0f sec. Joule Counter Range, at %.0f Watts\n", rapl_joule_counter_range, tdp); } -/* - * rapl_probe() - * - * sets do_rapl, rapl_power_units, rapl_energy_units, rapl_time_units - */ -void rapl_probe(unsigned int family, unsigned int model) -{ - if (genuine_intel) - rapl_probe_intel(family, model); - if (authentic_amd || hygon_genuine) - rapl_probe_amd(family, model); -} - -void perf_limit_reasons_probe(unsigned int family, unsigned int model) -{ - if (!genuine_intel) - return; - - if (family != 6) - return; - - switch (model) { - case INTEL_FAM6_HASWELL: /* HSW */ - case INTEL_FAM6_HASWELL_L: /* HSW */ - case INTEL_FAM6_HASWELL_G: /* HSW */ - do_gfx_perf_limit_reasons = 1; - /* FALLTHRU */ - case INTEL_FAM6_HASWELL_X: /* HSX */ - do_core_perf_limit_reasons = 1; - do_ring_perf_limit_reasons = 1; - default: - return; - } -} - -void automatic_cstate_conversion_probe(unsigned int family, unsigned int model) -{ - if (family != 6) - return; - - switch (model) { - case INTEL_FAM6_BROADWELL_X: - case INTEL_FAM6_SKYLAKE_X: - has_automatic_cstate_conversion = 1; - } -} - -void prewake_cstate_probe(unsigned int family, unsigned int model) -{ - if (is_icx(family, model) || is_spr(family, model)) - dis_cstate_prewake = 1; -} - -int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p) -{ - unsigned long long msr; - unsigned int dts, dts2; - int cpu; - - UNUSED(c); - UNUSED(p); - - if (!(do_dts || do_ptm)) - return 0; - - cpu = t->cpu_id; - - /* DTS is per-core, no need to print for each thread */ - if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) - return 0; - - if (cpu_migrate(cpu)) { - fprintf(outf, "print_thermal: Could not migrate to CPU %d\n", cpu); - return -1; - } - - if (do_ptm && (t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) { - if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr)) - return 0; - - dts = (msr >> 16) & 0x7F; - fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_STATUS: 0x%08llx (%d C)\n", cpu, msr, tj_max - dts); - - if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, &msr)) - return 0; - - dts = (msr >> 16) & 0x7F; - dts2 = (msr >> 8) & 0x7F; - fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n", - cpu, msr, tj_max - dts, tj_max - dts2); - } - - if (do_dts && debug) { - unsigned int resolution; - - if (get_msr(cpu, MSR_IA32_THERM_STATUS, &msr)) - return 0; - - dts = (msr >> 16) & 0x7F; - resolution = (msr >> 27) & 0xF; - fprintf(outf, "cpu%d: MSR_IA32_THERM_STATUS: 0x%08llx (%d C +/- %d)\n", - cpu, msr, tj_max - dts, resolution); - - if (get_msr(cpu, MSR_IA32_THERM_INTERRUPT, &msr)) - return 0; - - dts = (msr >> 16) & 0x7F; - dts2 = (msr >> 8) & 0x7F; - fprintf(outf, "cpu%d: MSR_IA32_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n", - cpu, msr, tj_max - dts, tj_max - dts2); - } - - return 0; -} - void print_power_limit_msr(int cpu, unsigned long long msr, char *label) { fprintf(outf, "cpu%d: %s: %sabled (%0.3f Watts, %f sec, clamp %sabled)\n", @@ -4918,11 +5085,11 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) UNUSED(c); UNUSED(p); - if (!do_rapl) + if (!platform->rapl_msrs) return 0; /* RAPL counters are per package, so print only for 1st thread/package */ - if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) + if (!is_cpu_first_thread_in_package(t, c, p)) return 0; cpu = t->cpu_id; @@ -4931,7 +5098,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) return -1; } - if (do_rapl & RAPL_AMD_F17H) { + if (platform->rapl_msrs & RAPL_AMD_F17H) { msr_name = "MSR_RAPL_PWR_UNIT"; if (get_msr(cpu, MSR_RAPL_PWR_UNIT, &msr)) return -1; @@ -4944,7 +5111,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) fprintf(outf, "cpu%d: %s: 0x%08llx (%f Watts, %f Joules, %f sec.)\n", cpu, msr_name, msr, rapl_power_units, rapl_energy_units, rapl_time_units); - if (do_rapl & RAPL_PKG_POWER_INFO) { + if (platform->rapl_msrs & RAPL_PKG_POWER_INFO) { if (get_msr(cpu, MSR_PKG_POWER_INFO, &msr)) return -5; @@ -4957,7 +5124,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) ((msr >> 48) & RAPL_TIME_GRANULARITY) * rapl_time_units); } - if (do_rapl & RAPL_PKG) { + if (platform->rapl_msrs & RAPL_PKG) { if (get_msr(cpu, MSR_PKG_POWER_LIMIT, &msr)) return -9; @@ -4981,7 +5148,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) cpu, ((msr >> 0) & 0x1FFF) * rapl_power_units, (msr >> 31) & 1 ? "" : "UN"); } - if (do_rapl & RAPL_DRAM_POWER_INFO) { + if (platform->rapl_msrs & RAPL_DRAM_POWER_INFO) { if (get_msr(cpu, MSR_DRAM_POWER_INFO, &msr)) return -6; @@ -4992,7 +5159,7 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) ((msr >> 32) & RAPL_POWER_GRANULARITY) * rapl_power_units, ((msr >> 48) & RAPL_TIME_GRANULARITY) * rapl_time_units); } - if (do_rapl & RAPL_DRAM) { + if (platform->rapl_msrs & RAPL_DRAM) { if (get_msr(cpu, MSR_DRAM_POWER_LIMIT, &msr)) return -9; fprintf(outf, "cpu%d: MSR_DRAM_POWER_LIMIT: 0x%08llx (%slocked)\n", @@ -5000,20 +5167,20 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) print_power_limit_msr(cpu, msr, "DRAM Limit"); } - if (do_rapl & RAPL_CORE_POLICY) { + if (platform->rapl_msrs & RAPL_CORE_POLICY) { if (get_msr(cpu, MSR_PP0_POLICY, &msr)) return -7; fprintf(outf, "cpu%d: MSR_PP0_POLICY: %lld\n", cpu, msr & 0xF); } - if (do_rapl & RAPL_CORES_POWER_LIMIT) { + if (platform->rapl_msrs & RAPL_CORE_POWER_LIMIT) { if (get_msr(cpu, MSR_PP0_POWER_LIMIT, &msr)) return -9; fprintf(outf, "cpu%d: MSR_PP0_POWER_LIMIT: 0x%08llx (%slocked)\n", cpu, msr, (msr >> 31) & 1 ? "" : "UN"); print_power_limit_msr(cpu, msr, "Cores Limit"); } - if (do_rapl & RAPL_GFX) { + if (platform->rapl_msrs & RAPL_GFX) { if (get_msr(cpu, MSR_PP1_POLICY, &msr)) return -8; @@ -5029,217 +5196,24 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p) } /* - * SNB adds support for additional MSRs: + * probe_rapl() * - * MSR_PKG_C7_RESIDENCY 0x000003fa - * MSR_CORE_C7_RESIDENCY 0x000003fe - * MSR_PKG_C2_RESIDENCY 0x0000060d + * sets rapl_power_units, rapl_energy_units, rapl_time_units */ - -int has_snb_msrs(unsigned int family, unsigned int model) +void probe_rapl(void) { - if (!genuine_intel) - return 0; - - if (family != 6) - return 0; - - switch (model) { - case INTEL_FAM6_SANDYBRIDGE: - case INTEL_FAM6_SANDYBRIDGE_X: - case INTEL_FAM6_IVYBRIDGE: /* IVB */ - case INTEL_FAM6_IVYBRIDGE_X: /* IVB Xeon */ - case INTEL_FAM6_HASWELL: /* HSW */ - case INTEL_FAM6_HASWELL_X: /* HSW */ - case INTEL_FAM6_HASWELL_L: /* HSW */ - case INTEL_FAM6_HASWELL_G: /* HSW */ - case INTEL_FAM6_BROADWELL: /* BDW */ - case INTEL_FAM6_BROADWELL_G: /* BDW */ - case INTEL_FAM6_BROADWELL_X: /* BDX */ - case INTEL_FAM6_SKYLAKE_L: /* SKL */ - case INTEL_FAM6_CANNONLAKE_L: /* CNL */ - case INTEL_FAM6_SKYLAKE_X: /* SKX */ - case INTEL_FAM6_ICELAKE_X: /* ICX */ - case INTEL_FAM6_SAPPHIRERAPIDS_X: /* SPR */ - case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ - case INTEL_FAM6_ATOM_GOLDMONT_PLUS: - case INTEL_FAM6_ATOM_GOLDMONT_D: /* DNV */ - case INTEL_FAM6_ATOM_TREMONT: /* EHL */ - case INTEL_FAM6_ATOM_TREMONT_D: /* JVL */ - return 1; - } - return 0; -} - -/* - * HSW ULT added support for C8/C9/C10 MSRs: - * - * MSR_PKG_C8_RESIDENCY 0x00000630 - * MSR_PKG_C9_RESIDENCY 0x00000631 - * MSR_PKG_C10_RESIDENCY 0x00000632 - * - * MSR_PKGC8_IRTL 0x00000633 - * MSR_PKGC9_IRTL 0x00000634 - * MSR_PKGC10_IRTL 0x00000635 - * - */ -int has_c8910_msrs(unsigned int family, unsigned int model) -{ - if (!genuine_intel) - return 0; - - if (family != 6) - return 0; - - switch (model) { - case INTEL_FAM6_HASWELL_L: /* HSW */ - case INTEL_FAM6_BROADWELL: /* BDW */ - case INTEL_FAM6_SKYLAKE_L: /* SKL */ - case INTEL_FAM6_CANNONLAKE_L: /* CNL */ - case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ - case INTEL_FAM6_ATOM_GOLDMONT_PLUS: - case INTEL_FAM6_ATOM_TREMONT: /* EHL */ - return 1; - } - return 0; -} - -/* - * SKL adds support for additional MSRS: - * - * MSR_PKG_WEIGHTED_CORE_C0_RES 0x00000658 - * MSR_PKG_ANY_CORE_C0_RES 0x00000659 - * MSR_PKG_ANY_GFXE_C0_RES 0x0000065A - * MSR_PKG_BOTH_CORE_GFXE_C0_RES 0x0000065B - */ -int has_skl_msrs(unsigned int family, unsigned int model) -{ - if (!genuine_intel) - return 0; - - if (family != 6) - return 0; - - switch (model) { - case INTEL_FAM6_SKYLAKE_L: /* SKL */ - case INTEL_FAM6_CANNONLAKE_L: /* CNL */ - return 1; - } - return 0; -} - -int is_slm(unsigned int family, unsigned int model) -{ - if (!genuine_intel) - return 0; - - if (family != 6) - return 0; - - switch (model) { - case INTEL_FAM6_ATOM_SILVERMONT: /* BYT */ - case INTEL_FAM6_ATOM_SILVERMONT_D: /* AVN */ - return 1; - } - return 0; -} - -int is_knl(unsigned int family, unsigned int model) -{ - if (!genuine_intel) - return 0; - - if (family != 6) - return 0; - - switch (model) { - case INTEL_FAM6_XEON_PHI_KNL: /* KNL */ - return 1; - } - return 0; -} - -int is_cnl(unsigned int family, unsigned int model) -{ - if (!genuine_intel) - return 0; - - if (family != 6) - return 0; - - switch (model) { - case INTEL_FAM6_CANNONLAKE_L: /* CNL */ - return 1; - } - - return 0; -} - -unsigned int get_aperf_mperf_multiplier(unsigned int family, unsigned int model) -{ - if (is_knl(family, model)) - return 1024; - return 1; -} - -#define SLM_BCLK_FREQS 5 -double slm_freq_table[SLM_BCLK_FREQS] = { 83.3, 100.0, 133.3, 116.7, 80.0 }; - -double slm_bclk(void) -{ - unsigned long long msr = 3; - unsigned int i; - double freq; - - if (get_msr(base_cpu, MSR_FSB_FREQ, &msr)) - fprintf(outf, "SLM BCLK: unknown\n"); - - i = msr & 0xf; - if (i >= SLM_BCLK_FREQS) { - fprintf(outf, "SLM BCLK[%d] invalid\n", i); - i = 3; - } - freq = slm_freq_table[i]; - - if (!quiet) - fprintf(outf, "SLM BCLK: %.1f Mhz\n", freq); - - return freq; -} - -double discover_bclk(unsigned int family, unsigned int model) -{ - if (has_snb_msrs(family, model) || is_knl(family, model)) - return 100.00; - else if (is_slm(family, model)) - return slm_bclk(); - else - return 133.33; -} - -int get_cpu_type(struct thread_data *t, struct core_data *c, struct pkg_data *p) -{ - unsigned int eax, ebx, ecx, edx; - - UNUSED(c); - UNUSED(p); - - if (!genuine_intel) - return 0; + if (!platform->rapl_msrs) + return; - if (cpu_migrate(t->cpu_id)) { - fprintf(outf, "Could not migrate to CPU %d\n", t->cpu_id); - return -1; - } + if (genuine_intel) + rapl_probe_intel(); + if (authentic_amd || hygon_genuine) + rapl_probe_amd(); - if (max_level < 0x1a) - return 0; + if (quiet) + return; - __cpuid(0x1a, eax, ebx, ecx, edx); - eax = (eax >> 24) & 0xFF; - if (eax == 0x20) - t->is_atom = true; - return 0; + for_all_cpus(print_rapl, ODD_COUNTERS); } /* @@ -5268,7 +5242,7 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk return 0; /* this is a per-package concept */ - if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE) || !(t->flags & CPU_IS_FIRST_CORE_IN_PACKAGE)) + if (!is_cpu_first_thread_in_package(t, c, p)) return 0; cpu = t->cpu_id; @@ -5284,7 +5258,7 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk } /* Temperature Target MSR is Nehalem and newer only */ - if (!do_nhm_platform_info) + if (!platform->has_nhm_msrs) goto guess; if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr)) @@ -5293,20 +5267,18 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk tcc_default = (msr >> 16) & 0xFF; if (!quiet) { - switch (tcc_offset_bits) { - case 4: - tcc_offset = (msr >> 24) & 0xF; - fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C) (%d default - %d offset)\n", - cpu, msr, tcc_default - tcc_offset, tcc_default, tcc_offset); - break; - case 6: - tcc_offset = (msr >> 24) & 0x3F; + int bits = platform->tcc_offset_bits; + unsigned long long enabled = 0; + + if (bits && !get_msr(base_cpu, MSR_PLATFORM_INFO, &enabled)) + enabled = (enabled >> 30) & 1; + + if (bits && enabled) { + tcc_offset = (msr >> 24) & GENMASK(bits - 1, 0); fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C) (%d default - %d offset)\n", cpu, msr, tcc_default - tcc_offset, tcc_default, tcc_offset); - break; - default: + } else { fprintf(outf, "cpu%d: MSR_IA32_TEMPERATURE_TARGET: 0x%08llx (%d C)\n", cpu, msr, tcc_default); - break; } } @@ -5324,6 +5296,108 @@ guess: return 0; } +int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p) +{ + unsigned long long msr; + unsigned int dts, dts2; + int cpu; + + UNUSED(c); + UNUSED(p); + + if (!(do_dts || do_ptm)) + return 0; + + cpu = t->cpu_id; + + /* DTS is per-core, no need to print for each thread */ + if (!is_cpu_first_thread_in_core(t, c, p)) + return 0; + + if (cpu_migrate(cpu)) { + fprintf(outf, "print_thermal: Could not migrate to CPU %d\n", cpu); + return -1; + } + + if (do_ptm && is_cpu_first_core_in_package(t, c, p)) { + if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS, &msr)) + return 0; + + dts = (msr >> 16) & 0x7F; + fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_STATUS: 0x%08llx (%d C)\n", cpu, msr, tj_max - dts); + + if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, &msr)) + return 0; + + dts = (msr >> 16) & 0x7F; + dts2 = (msr >> 8) & 0x7F; + fprintf(outf, "cpu%d: MSR_IA32_PACKAGE_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n", + cpu, msr, tj_max - dts, tj_max - dts2); + } + + if (do_dts && debug) { + unsigned int resolution; + + if (get_msr(cpu, MSR_IA32_THERM_STATUS, &msr)) + return 0; + + dts = (msr >> 16) & 0x7F; + resolution = (msr >> 27) & 0xF; + fprintf(outf, "cpu%d: MSR_IA32_THERM_STATUS: 0x%08llx (%d C +/- %d)\n", + cpu, msr, tj_max - dts, resolution); + + if (get_msr(cpu, MSR_IA32_THERM_INTERRUPT, &msr)) + return 0; + + dts = (msr >> 16) & 0x7F; + dts2 = (msr >> 8) & 0x7F; + fprintf(outf, "cpu%d: MSR_IA32_THERM_INTERRUPT: 0x%08llx (%d C, %d C)\n", + cpu, msr, tj_max - dts, tj_max - dts2); + } + + return 0; +} + +void probe_thermal(void) +{ + if (!access("/sys/devices/system/cpu/cpu0/thermal_throttle/core_throttle_count", R_OK)) + BIC_PRESENT(BIC_CORE_THROT_CNT); + else + BIC_NOT_PRESENT(BIC_CORE_THROT_CNT); + + for_all_cpus(set_temperature_target, ODD_COUNTERS); + + if (quiet) + return; + + for_all_cpus(print_thermal, ODD_COUNTERS); +} + +int get_cpu_type(struct thread_data *t, struct core_data *c, struct pkg_data *p) +{ + unsigned int eax, ebx, ecx, edx; + + UNUSED(c); + UNUSED(p); + + if (!genuine_intel) + return 0; + + if (cpu_migrate(t->cpu_id)) { + fprintf(outf, "Could not migrate to CPU %d\n", t->cpu_id); + return -1; + } + + if (max_level < 0x1a) + return 0; + + __cpuid(0x1a, eax, ebx, ecx, edx); + eax = (eax >> 24) & 0xFF; + if (eax == 0x20) + t->is_atom = true; + return 0; +} + void decode_feature_control_msr(void) { unsigned long long msr; @@ -5354,7 +5428,7 @@ void decode_misc_feature_control(void) { unsigned long long msr; - if (!has_misc_feature_control) + if (!platform->has_msr_misc_feature_control) return; if (!get_msr(base_cpu, MSR_MISC_FEATURE_CONTROL, &msr)) @@ -5375,10 +5449,7 @@ void decode_misc_pwr_mgmt_msr(void) { unsigned long long msr; - if (!do_nhm_platform_info) - return; - - if (no_MSR_MISC_PWR_MGMT) + if (!platform->has_msr_misc_pwr_mgmt) return; if (!get_msr(base_cpu, MSR_MISC_PWR_MGMT, &msr)) @@ -5397,6 +5468,9 @@ void decode_c6_demotion_policy_msr(void) { unsigned long long msr; + if (!platform->has_msr_c6_demotion_policy_config) + return; + if (!get_msr(base_cpu, MSR_CC6_DEMOTION_POLICY_CONFIG, &msr)) fprintf(outf, "cpu%d: MSR_CC6_DEMOTION_POLICY_CONFIG: 0x%08llx (%sable-CC6-Demotion)\n", base_cpu, msr, msr & (1 << 0) ? "EN" : "DIS"); @@ -5406,67 +5480,6 @@ void decode_c6_demotion_policy_msr(void) base_cpu, msr, msr & (1 << 0) ? "EN" : "DIS"); } -/* - * When models are the same, for the purpose of turbostat, reuse - */ -unsigned int intel_model_duplicates(unsigned int model) -{ - - switch (model) { - case INTEL_FAM6_NEHALEM_EP: /* Core i7, Xeon 5500 series - Bloomfield, Gainstown NHM-EP */ - case INTEL_FAM6_NEHALEM: /* Core i7 and i5 Processor - Clarksfield, Lynnfield, Jasper Forest */ - case 0x1F: /* Core i7 and i5 Processor - Nehalem */ - case INTEL_FAM6_WESTMERE: /* Westmere Client - Clarkdale, Arrandale */ - case INTEL_FAM6_WESTMERE_EP: /* Westmere EP - Gulftown */ - return INTEL_FAM6_NEHALEM; - - case INTEL_FAM6_NEHALEM_EX: /* Nehalem-EX Xeon - Beckton */ - case INTEL_FAM6_WESTMERE_EX: /* Westmere-EX Xeon - Eagleton */ - return INTEL_FAM6_NEHALEM_EX; - - case INTEL_FAM6_XEON_PHI_KNM: - return INTEL_FAM6_XEON_PHI_KNL; - - case INTEL_FAM6_BROADWELL_X: - case INTEL_FAM6_BROADWELL_D: /* BDX-DE */ - return INTEL_FAM6_BROADWELL_X; - - case INTEL_FAM6_SKYLAKE_L: - case INTEL_FAM6_SKYLAKE: - case INTEL_FAM6_KABYLAKE_L: - case INTEL_FAM6_KABYLAKE: - case INTEL_FAM6_COMETLAKE_L: - case INTEL_FAM6_COMETLAKE: - return INTEL_FAM6_SKYLAKE_L; - - case INTEL_FAM6_ICELAKE_L: - case INTEL_FAM6_ICELAKE_NNPI: - case INTEL_FAM6_TIGERLAKE_L: - case INTEL_FAM6_TIGERLAKE: - case INTEL_FAM6_ROCKETLAKE: - case INTEL_FAM6_LAKEFIELD: - case INTEL_FAM6_ALDERLAKE: - case INTEL_FAM6_ALDERLAKE_L: - case INTEL_FAM6_ATOM_GRACEMONT: - case INTEL_FAM6_RAPTORLAKE: - case INTEL_FAM6_RAPTORLAKE_P: - case INTEL_FAM6_RAPTORLAKE_S: - case INTEL_FAM6_METEORLAKE: - case INTEL_FAM6_METEORLAKE_L: - return INTEL_FAM6_CANNONLAKE_L; - - case INTEL_FAM6_ATOM_TREMONT_L: - return INTEL_FAM6_ATOM_TREMONT; - - case INTEL_FAM6_ICELAKE_D: - return INTEL_FAM6_ICELAKE_X; - - case INTEL_FAM6_EMERALDRAPIDS_X: - return INTEL_FAM6_SAPPHIRERAPIDS_X; - } - return model; -} - void print_dev_latency(void) { char *path = "/dev/cpu_dma_latency"; @@ -5510,6 +5523,101 @@ void linux_perf_init(void) BIC_PRESENT(BIC_IPC); } +void probe_cstates(void) +{ + probe_cst_limit(); + + if (platform->supported_cstates & CC1) + BIC_PRESENT(BIC_CPU_c1); + + if (platform->supported_cstates & CC3) + BIC_PRESENT(BIC_CPU_c3); + + if (platform->supported_cstates & CC6) + BIC_PRESENT(BIC_CPU_c6); + + if (platform->supported_cstates & CC7) + BIC_PRESENT(BIC_CPU_c7); + + if (platform->supported_cstates & PC2 && (pkg_cstate_limit >= PCL__2)) + BIC_PRESENT(BIC_Pkgpc2); + + if (platform->supported_cstates & PC3 && (pkg_cstate_limit >= PCL__3)) + BIC_PRESENT(BIC_Pkgpc3); + + if (platform->supported_cstates & PC6 && (pkg_cstate_limit >= PCL__6)) + BIC_PRESENT(BIC_Pkgpc6); + + if (platform->supported_cstates & PC7 && (pkg_cstate_limit >= PCL__7)) + BIC_PRESENT(BIC_Pkgpc7); + + if (platform->supported_cstates & PC8 && (pkg_cstate_limit >= PCL__8)) + BIC_PRESENT(BIC_Pkgpc8); + + if (platform->supported_cstates & PC9 && (pkg_cstate_limit >= PCL__9)) + BIC_PRESENT(BIC_Pkgpc9); + + if (platform->supported_cstates & PC10 && (pkg_cstate_limit >= PCL_10)) + BIC_PRESENT(BIC_Pkgpc10); + + if (platform->has_msr_module_c6_res_ms) + BIC_PRESENT(BIC_Mod_c6); + + if (platform->has_ext_cst_msrs) { + BIC_PRESENT(BIC_Totl_c0); + BIC_PRESENT(BIC_Any_c0); + BIC_PRESENT(BIC_GFX_c0); + BIC_PRESENT(BIC_CPUGFX); + } + + if (quiet) + return; + + dump_power_ctl(); + dump_cst_cfg(); + decode_c6_demotion_policy_msr(); + print_dev_latency(); + dump_sysfs_cstate_config(); + print_irtl(); +} + +void probe_lpi(void) +{ + if (!access("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", R_OK)) + BIC_PRESENT(BIC_CPU_LPI); + else + BIC_NOT_PRESENT(BIC_CPU_LPI); + + if (!access(sys_lpi_file_sysfs, R_OK)) { + sys_lpi_file = sys_lpi_file_sysfs; + BIC_PRESENT(BIC_SYS_LPI); + } else if (!access(sys_lpi_file_debugfs, R_OK)) { + sys_lpi_file = sys_lpi_file_debugfs; + BIC_PRESENT(BIC_SYS_LPI); + } else { + sys_lpi_file_sysfs = NULL; + BIC_NOT_PRESENT(BIC_SYS_LPI); + } + +} + +void probe_pstates(void) +{ + probe_bclk(); + + if (quiet) + return; + + dump_platform_info(); + dump_turbo_ratio_info(); + dump_sysfs_pstate_config(); + decode_misc_pwr_mgmt_msr(); + + for_all_cpus(print_hwp, ODD_COUNTERS); + for_all_cpus(print_epb, ODD_COUNTERS); + for_all_cpus(print_perf_limit, ODD_COUNTERS); +} + void process_cpuid() { unsigned int eax, ebx, ecx, edx; @@ -5569,10 +5677,8 @@ void process_cpuid() edx_flags & (1 << 22) ? "ACPI-TM" : "-", edx_flags & (1 << 28) ? "HT" : "-", edx_flags & (1 << 29) ? "TM" : "-"); } - if (genuine_intel) { - model_orig = model; - model = intel_model_duplicates(model); - } + + probe_platform_features(family, model); if (!(edx_flags & (1 << 5))) errx(1, "CPUID: no MSR"); @@ -5656,26 +5762,12 @@ void process_cpuid() __cpuid(0x15, eax_crystal, ebx_tsc, crystal_hz, edx); if (ebx_tsc != 0) { - if (!quiet && (ebx != 0)) fprintf(outf, "CPUID(0x15): eax_crystal: %d ebx_tsc: %d ecx_crystal_hz: %d\n", eax_crystal, ebx_tsc, crystal_hz); if (crystal_hz == 0) - switch (model) { - case INTEL_FAM6_SKYLAKE_L: /* SKL */ - crystal_hz = 24000000; /* 24.0 MHz */ - break; - case INTEL_FAM6_ATOM_GOLDMONT_D: /* DNV */ - crystal_hz = 25000000; /* 25.0 MHz */ - break; - case INTEL_FAM6_ATOM_GOLDMONT: /* BXT */ - case INTEL_FAM6_ATOM_GOLDMONT_PLUS: - crystal_hz = 19200000; /* 19.2 MHz */ - break; - default: - crystal_hz = 0; - } + crystal_hz = platform->crystal_freq; if (crystal_hz) { tsc_hz = (unsigned long long)crystal_hz *ebx_tsc / eax_crystal; @@ -5700,147 +5792,33 @@ void process_cpuid() } if (has_aperf) - aperf_mperf_multiplier = get_aperf_mperf_multiplier(family, model); + aperf_mperf_multiplier = platform->need_perf_multiplier ? 1024 : 1; BIC_PRESENT(BIC_IRQ); BIC_PRESENT(BIC_TSC_MHz); +} - if (probe_nhm_msrs(family, model)) { - do_nhm_platform_info = 1; - BIC_PRESENT(BIC_CPU_c1); - BIC_PRESENT(BIC_CPU_c3); - BIC_PRESENT(BIC_CPU_c6); - BIC_PRESENT(BIC_SMI); - } - do_snb_cstates = has_snb_msrs(family, model); - - if (do_snb_cstates) - BIC_PRESENT(BIC_CPU_c7); - - do_irtl_snb = has_snb_msrs(family, model); - if (do_snb_cstates && (pkg_cstate_limit >= PCL__2)) - BIC_PRESENT(BIC_Pkgpc2); - if (pkg_cstate_limit >= PCL__3) - BIC_PRESENT(BIC_Pkgpc3); - if (pkg_cstate_limit >= PCL__6) - BIC_PRESENT(BIC_Pkgpc6); - if (do_snb_cstates && (pkg_cstate_limit >= PCL__7)) - BIC_PRESENT(BIC_Pkgpc7); - if (has_slv_msrs(family, model)) { - BIC_NOT_PRESENT(BIC_Pkgpc2); - BIC_NOT_PRESENT(BIC_Pkgpc3); - BIC_PRESENT(BIC_Pkgpc6); - BIC_NOT_PRESENT(BIC_Pkgpc7); - BIC_PRESENT(BIC_Mod_c6); - use_c1_residency_msr = 1; - } - if (is_jvl(family, model)) { - BIC_NOT_PRESENT(BIC_CPU_c3); - BIC_NOT_PRESENT(BIC_CPU_c7); - BIC_NOT_PRESENT(BIC_Pkgpc2); - BIC_NOT_PRESENT(BIC_Pkgpc3); - BIC_NOT_PRESENT(BIC_Pkgpc6); - BIC_NOT_PRESENT(BIC_Pkgpc7); - } - if (is_dnv(family, model)) { - BIC_PRESENT(BIC_CPU_c1); - BIC_NOT_PRESENT(BIC_CPU_c3); - BIC_NOT_PRESENT(BIC_Pkgpc3); - BIC_NOT_PRESENT(BIC_CPU_c7); - BIC_NOT_PRESENT(BIC_Pkgpc7); - use_c1_residency_msr = 1; - } - if (is_skx(family, model) || is_icx(family, model) || is_spr(family, model)) { - BIC_NOT_PRESENT(BIC_CPU_c3); - BIC_NOT_PRESENT(BIC_Pkgpc3); - BIC_NOT_PRESENT(BIC_CPU_c7); - BIC_NOT_PRESENT(BIC_Pkgpc7); - } - if (is_bdx(family, model)) { - BIC_NOT_PRESENT(BIC_CPU_c7); - BIC_NOT_PRESENT(BIC_Pkgpc7); - } - if (has_c8910_msrs(family, model)) { - if (pkg_cstate_limit >= PCL__8) - BIC_PRESENT(BIC_Pkgpc8); - if (pkg_cstate_limit >= PCL__9) - BIC_PRESENT(BIC_Pkgpc9); - if (pkg_cstate_limit >= PCL_10) - BIC_PRESENT(BIC_Pkgpc10); - } - do_irtl_hsw = has_c8910_msrs(family, model); - if (has_skl_msrs(family, model)) { - BIC_PRESENT(BIC_Totl_c0); - BIC_PRESENT(BIC_Any_c0); - BIC_PRESENT(BIC_GFX_c0); - BIC_PRESENT(BIC_CPUGFX); - } - do_slm_cstates = is_slm(family, model); - do_knl_cstates = is_knl(family, model); - - if (do_slm_cstates || do_knl_cstates || is_cnl(family, model) || is_ehl(family, model)) - BIC_NOT_PRESENT(BIC_CPU_c3); - - if (!quiet) - decode_misc_pwr_mgmt_msr(); - - if (!quiet && has_slv_msrs(family, model)) - decode_c6_demotion_policy_msr(); - - rapl_probe(family, model); - perf_limit_reasons_probe(family, model); - automatic_cstate_conversion_probe(family, model); - - check_tcc_offset(model_orig); - - if (!quiet) - dump_cstate_pstate_config_info(family, model); - intel_uncore_frequency_probe(); - - if (!quiet) - print_dev_latency(); - if (!quiet) - dump_sysfs_cstate_config(); - if (!quiet) - dump_sysfs_pstate_config(); +void probe_pm_features(void) +{ + probe_pstates(); - if (has_skl_msrs(family, model) || is_ehl(family, model)) - calculate_tsc_tweak(); + probe_cstates(); - if (!access("/sys/class/drm/card0/power/rc6_residency_ms", R_OK)) - BIC_PRESENT(BIC_GFX_rc6); + probe_lpi(); - if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK)) - BIC_PRESENT(BIC_GFXMHz); + probe_intel_uncore_frequency(); - if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_act_freq_mhz", R_OK)) - BIC_PRESENT(BIC_GFXACTMHz); + probe_graphics(); - if (!access("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", R_OK)) - BIC_PRESENT(BIC_CPU_LPI); - else - BIC_NOT_PRESENT(BIC_CPU_LPI); + probe_rapl(); - if (!access("/sys/devices/system/cpu/cpu0/thermal_throttle/core_throttle_count", R_OK)) - BIC_PRESENT(BIC_CORE_THROT_CNT); - else - BIC_NOT_PRESENT(BIC_CORE_THROT_CNT); + probe_thermal(); - if (!access(sys_lpi_file_sysfs, R_OK)) { - sys_lpi_file = sys_lpi_file_sysfs; - BIC_PRESENT(BIC_SYS_LPI); - } else if (!access(sys_lpi_file_debugfs, R_OK)) { - sys_lpi_file = sys_lpi_file_debugfs; - BIC_PRESENT(BIC_SYS_LPI); - } else { - sys_lpi_file_sysfs = NULL; - BIC_NOT_PRESENT(BIC_SYS_LPI); - } + if (platform->has_nhm_msrs) + BIC_PRESENT(BIC_SMI); if (!quiet) decode_misc_feature_control(); - - return; } /* @@ -5855,7 +5833,7 @@ int dir_filter(const struct dirent *dirp) return 0; } -void topology_probe() +void topology_probe(bool startup) { int i; int max_core_id = 0; @@ -5888,14 +5866,62 @@ void topology_probe() for_all_proc_cpus(mark_cpu_present); /* - * Validate that all cpus in cpu_subset are also in cpu_present_set + * Allocate and initialize cpu_effective_set + */ + cpu_effective_set = CPU_ALLOC((topo.max_cpu_num + 1)); + if (cpu_effective_set == NULL) + err(3, "CPU_ALLOC"); + cpu_effective_setsize = CPU_ALLOC_SIZE((topo.max_cpu_num + 1)); + CPU_ZERO_S(cpu_effective_setsize, cpu_effective_set); + update_effective_set(startup); + + /* + * Allocate and initialize cpu_allowed_set + */ + cpu_allowed_set = CPU_ALLOC((topo.max_cpu_num + 1)); + if (cpu_allowed_set == NULL) + err(3, "CPU_ALLOC"); + cpu_allowed_setsize = CPU_ALLOC_SIZE((topo.max_cpu_num + 1)); + CPU_ZERO_S(cpu_allowed_setsize, cpu_allowed_set); + + /* + * Validate and update cpu_allowed_set. + * + * Make sure all cpus in cpu_subset are also in cpu_present_set during startup. + * Give a warning when cpus in cpu_subset become unavailable at runtime. + * Give a warning when cpus are not effective because of cgroup setting. + * + * cpu_allowed_set is the intersection of cpu_present_set/cpu_effective_set/cpu_subset. */ for (i = 0; i < CPU_SUBSET_MAXCPUS; ++i) { - if (CPU_ISSET_S(i, cpu_subset_size, cpu_subset)) - if (!CPU_ISSET_S(i, cpu_present_setsize, cpu_present_set)) - err(1, "cpu%d not present", i); + if (cpu_subset && !CPU_ISSET_S(i, cpu_subset_size, cpu_subset)) + continue; + + if (!CPU_ISSET_S(i, cpu_present_setsize, cpu_present_set)) { + if (cpu_subset) { + /* cpus in cpu_subset must be in cpu_present_set during startup */ + if (startup) + err(1, "cpu%d not present", i); + else + fprintf(stderr, "cpu%d not present\n", i); + } + continue; + } + + if (CPU_COUNT_S(cpu_effective_setsize, cpu_effective_set)) { + if (!CPU_ISSET_S(i, cpu_effective_setsize, cpu_effective_set)) { + fprintf(stderr, "cpu%d not effective\n", i); + continue; + } + } + + CPU_SET_S(i, cpu_allowed_setsize, cpu_allowed_set); } + if (!CPU_COUNT_S(cpu_allowed_setsize, cpu_allowed_set)) + err(-ENODEV, "No valid cpus found"); + sched_setaffinity(0, cpu_allowed_setsize, cpu_allowed_set); + /* * Allocate and initialize cpu_affinity_set */ @@ -6009,15 +6035,19 @@ void allocate_counters(struct thread_data **t, struct core_data **c, struct pkg_ if (*c == NULL) goto error; - for (i = 0; i < num_cores; i++) + for (i = 0; i < num_cores; i++) { (*c)[i].core_id = -1; + (*c)[i].base_cpu = -1; + } *p = calloc(topo.num_packages, sizeof(struct pkg_data)); if (*p == NULL) goto error; - for (i = 0; i < topo.num_packages; i++) + for (i = 0; i < topo.num_packages; i++) { (*p)[i].package_id = i; + (*p)[i].base_cpu = -1; + } return; error: @@ -6050,10 +6080,11 @@ void init_counter(struct thread_data *thread_base, struct core_data *core_base, p = GET_PKG(pkg_base, pkg_id); t->cpu_id = cpu_id; - if (thread_id == 0) { - t->flags |= CPU_IS_FIRST_THREAD_IN_CORE; - if (cpu_is_first_core_in_package(cpu_id)) - t->flags |= CPU_IS_FIRST_CORE_IN_PACKAGE; + if (!cpu_is_not_allowed(cpu_id)) { + if (c->base_cpu < 0) + c->base_cpu = t->cpu_id; + if (p->base_cpu < 0) + p->base_cpu = t->cpu_id; } c->core_id = core_id; @@ -6093,59 +6124,64 @@ void allocate_irq_buffers(void) err(-1, "calloc %d", topo.max_cpu_num + 1); } -void setup_all_buffers(void) +int update_topo(struct thread_data *t, struct core_data *c, struct pkg_data *p) +{ + topo.allowed_cpus++; + if ((int)t->cpu_id == c->base_cpu) + topo.allowed_cores++; + if ((int)t->cpu_id == p->base_cpu) + topo.allowed_packages++; + + return 0; +} + +void topology_update(void) { - topology_probe(); + topo.allowed_cpus = 0; + topo.allowed_cores = 0; + topo.allowed_packages = 0; + for_all_cpus(update_topo, ODD_COUNTERS); +} +void setup_all_buffers(bool startup) +{ + topology_probe(startup); allocate_irq_buffers(); allocate_fd_percpu(); allocate_counters(&thread_even, &core_even, &package_even); allocate_counters(&thread_odd, &core_odd, &package_odd); allocate_output_buffer(); for_all_proc_cpus(initialize_counters); + topology_update(); } void set_base_cpu(void) { - base_cpu = sched_getcpu(); - if (base_cpu < 0) - err(-ENODEV, "No valid cpus found"); + int i; - if (debug > 1) - fprintf(outf, "base_cpu = %d\n", base_cpu); + for (i = 0; i < topo.max_cpu_num + 1; ++i) { + if (cpu_is_not_allowed(i)) + continue; + base_cpu = i; + if (debug > 1) + fprintf(outf, "base_cpu = %d\n", base_cpu); + return; + } + err(-ENODEV, "No valid cpus found"); } void turbostat_init() { - setup_all_buffers(); + setup_all_buffers(true); set_base_cpu(); check_dev_msr(); check_permissions(); process_cpuid(); + probe_pm_features(); linux_perf_init(); - if (!quiet) - for_all_cpus(print_hwp, ODD_COUNTERS); - - if (!quiet) - for_all_cpus(print_epb, ODD_COUNTERS); - - if (!quiet) - for_all_cpus(print_perf_limit, ODD_COUNTERS); - - if (!quiet) - for_all_cpus(print_rapl, ODD_COUNTERS); - - for_all_cpus(set_temperature_target, ODD_COUNTERS); - for_all_cpus(get_cpu_type, ODD_COUNTERS); for_all_cpus(get_cpu_type, EVEN_COUNTERS); - if (!quiet) - for_all_cpus(print_thermal, ODD_COUNTERS); - - if (!quiet && do_irtl_snb) - print_irtl(); - if (DO_BIC(BIC_IPC)) (void)get_instr_count_fd(base_cpu); } @@ -6160,8 +6196,6 @@ int fork_it(char **argv) first_counter_read = 0; if (status) exit(status); - /* clear affinity side-effect of get_counters() */ - sched_setaffinity(0, cpu_present_setsize, cpu_present_set); gettimeofday(&tv_even, (struct timezone *)NULL); child_pid = fork(); @@ -6225,7 +6259,7 @@ int get_and_dump_counters(void) void print_version() { - fprintf(outf, "turbostat version 2023.03.17 - Len Brown <lenb@kernel.org>\n"); + fprintf(outf, "turbostat version 2023.11.07 - Len Brown <lenb@kernel.org>\n"); } #define COMMAND_LINE_SIZE 2048 @@ -6508,9 +6542,6 @@ void probe_sysfs(void) */ void parse_cpu_command(char *optarg) { - unsigned int start, end; - char *next; - if (!strcmp(optarg, "core")) { if (cpu_subset) goto error; @@ -6533,52 +6564,8 @@ void parse_cpu_command(char *optarg) CPU_ZERO_S(cpu_subset_size, cpu_subset); - next = optarg; - - while (next && *next) { - - if (*next == '-') /* no negative cpu numbers */ - goto error; - - start = strtoul(next, &next, 10); - - if (start >= CPU_SUBSET_MAXCPUS) - goto error; - CPU_SET_S(start, cpu_subset_size, cpu_subset); - - if (*next == '\0') - break; - - if (*next == ',') { - next += 1; - continue; - } - - if (*next == '-') { - next += 1; /* start range */ - } else if (*next == '.') { - next += 1; - if (*next == '.') - next += 1; /* start range */ - else - goto error; - } - - end = strtoul(next, &next, 10); - if (end <= start) - goto error; - - while (++start <= end) { - if (start >= CPU_SUBSET_MAXCPUS) - goto error; - CPU_SET_S(start, cpu_subset_size, cpu_subset); - } - - if (*next == ',') - next += 1; - else if (*next != '\0') - goto error; - } + if (parse_cpu_str(optarg, cpu_subset, cpu_subset_size)) + goto error; return; @@ -6719,6 +6706,19 @@ void cmdline(int argc, char **argv) int main(int argc, char **argv) { + int fd, ret; + + fd = open("/sys/fs/cgroup/cgroup.procs", O_WRONLY); + if (fd < 0) + goto skip_cgroup_setting; + + ret = write(fd, "0\n", 2); + if (ret == -1) + perror("Can't update cgroup\n"); + + close(fd); + +skip_cgroup_setting: outf = stderr; cmdline(argc, argv); diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c index 6ee22c3b251a..518f143c5b0f 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c @@ -24,6 +24,7 @@ #include "test_progs.h" #include "network_helpers.h" +#include "netlink_helpers.h" #include "test_tc_neigh_fib.skel.h" #include "test_tc_neigh.skel.h" #include "test_tc_peer.skel.h" @@ -110,11 +111,17 @@ static void netns_setup_namespaces_nofail(const char *verb) } } +enum dev_mode { + MODE_VETH, + MODE_NETKIT, +}; + struct netns_setup_result { - int ifindex_veth_src; - int ifindex_veth_src_fwd; - int ifindex_veth_dst; - int ifindex_veth_dst_fwd; + enum dev_mode dev_mode; + int ifindex_src; + int ifindex_src_fwd; + int ifindex_dst; + int ifindex_dst_fwd; }; static int get_ifaddr(const char *name, char *ifaddr) @@ -137,58 +144,110 @@ static int get_ifaddr(const char *name, char *ifaddr) return 0; } +static int create_netkit(int mode, char *prim, char *peer) +{ + struct rtattr *linkinfo, *data, *peer_info; + struct rtnl_handle rth = { .fd = -1 }; + const char *type = "netkit"; + struct { + struct nlmsghdr n; + struct ifinfomsg i; + char buf[1024]; + } req = {}; + int err; + + err = rtnl_open(&rth, 0); + if (!ASSERT_OK(err, "open_rtnetlink")) + return err; + + memset(&req, 0, sizeof(req)); + req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)); + req.n.nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE | NLM_F_EXCL; + req.n.nlmsg_type = RTM_NEWLINK; + req.i.ifi_family = AF_UNSPEC; + + addattr_l(&req.n, sizeof(req), IFLA_IFNAME, prim, strlen(prim)); + linkinfo = addattr_nest(&req.n, sizeof(req), IFLA_LINKINFO); + addattr_l(&req.n, sizeof(req), IFLA_INFO_KIND, type, strlen(type)); + data = addattr_nest(&req.n, sizeof(req), IFLA_INFO_DATA); + addattr32(&req.n, sizeof(req), IFLA_NETKIT_MODE, mode); + peer_info = addattr_nest(&req.n, sizeof(req), IFLA_NETKIT_PEER_INFO); + req.n.nlmsg_len += sizeof(struct ifinfomsg); + addattr_l(&req.n, sizeof(req), IFLA_IFNAME, peer, strlen(peer)); + addattr_nest_end(&req.n, peer_info); + addattr_nest_end(&req.n, data); + addattr_nest_end(&req.n, linkinfo); + + err = rtnl_talk(&rth, &req.n, NULL); + ASSERT_OK(err, "talk_rtnetlink"); + rtnl_close(&rth); + return err; +} + static int netns_setup_links_and_routes(struct netns_setup_result *result) { struct nstoken *nstoken = NULL; - char veth_src_fwd_addr[IFADDR_STR_LEN+1] = {}; - - SYS(fail, "ip link add veth_src type veth peer name veth_src_fwd"); - SYS(fail, "ip link add veth_dst type veth peer name veth_dst_fwd"); + char src_fwd_addr[IFADDR_STR_LEN+1] = {}; + int err; - SYS(fail, "ip link set veth_dst_fwd address " MAC_DST_FWD); - SYS(fail, "ip link set veth_dst address " MAC_DST); + if (result->dev_mode == MODE_VETH) { + SYS(fail, "ip link add src type veth peer name src_fwd"); + SYS(fail, "ip link add dst type veth peer name dst_fwd"); + + SYS(fail, "ip link set dst_fwd address " MAC_DST_FWD); + SYS(fail, "ip link set dst address " MAC_DST); + } else if (result->dev_mode == MODE_NETKIT) { + err = create_netkit(NETKIT_L3, "src", "src_fwd"); + if (!ASSERT_OK(err, "create_ifindex_src")) + goto fail; + err = create_netkit(NETKIT_L3, "dst", "dst_fwd"); + if (!ASSERT_OK(err, "create_ifindex_dst")) + goto fail; + } - if (get_ifaddr("veth_src_fwd", veth_src_fwd_addr)) + if (get_ifaddr("src_fwd", src_fwd_addr)) goto fail; - result->ifindex_veth_src = if_nametoindex("veth_src"); - if (!ASSERT_GT(result->ifindex_veth_src, 0, "ifindex_veth_src")) + result->ifindex_src = if_nametoindex("src"); + if (!ASSERT_GT(result->ifindex_src, 0, "ifindex_src")) goto fail; - result->ifindex_veth_src_fwd = if_nametoindex("veth_src_fwd"); - if (!ASSERT_GT(result->ifindex_veth_src_fwd, 0, "ifindex_veth_src_fwd")) + result->ifindex_src_fwd = if_nametoindex("src_fwd"); + if (!ASSERT_GT(result->ifindex_src_fwd, 0, "ifindex_src_fwd")) goto fail; - result->ifindex_veth_dst = if_nametoindex("veth_dst"); - if (!ASSERT_GT(result->ifindex_veth_dst, 0, "ifindex_veth_dst")) + result->ifindex_dst = if_nametoindex("dst"); + if (!ASSERT_GT(result->ifindex_dst, 0, "ifindex_dst")) goto fail; - result->ifindex_veth_dst_fwd = if_nametoindex("veth_dst_fwd"); - if (!ASSERT_GT(result->ifindex_veth_dst_fwd, 0, "ifindex_veth_dst_fwd")) + result->ifindex_dst_fwd = if_nametoindex("dst_fwd"); + if (!ASSERT_GT(result->ifindex_dst_fwd, 0, "ifindex_dst_fwd")) goto fail; - SYS(fail, "ip link set veth_src netns " NS_SRC); - SYS(fail, "ip link set veth_src_fwd netns " NS_FWD); - SYS(fail, "ip link set veth_dst_fwd netns " NS_FWD); - SYS(fail, "ip link set veth_dst netns " NS_DST); + SYS(fail, "ip link set src netns " NS_SRC); + SYS(fail, "ip link set src_fwd netns " NS_FWD); + SYS(fail, "ip link set dst_fwd netns " NS_FWD); + SYS(fail, "ip link set dst netns " NS_DST); /** setup in 'src' namespace */ nstoken = open_netns(NS_SRC); if (!ASSERT_OK_PTR(nstoken, "setns src")) goto fail; - SYS(fail, "ip addr add " IP4_SRC "/32 dev veth_src"); - SYS(fail, "ip addr add " IP6_SRC "/128 dev veth_src nodad"); - SYS(fail, "ip link set dev veth_src up"); + SYS(fail, "ip addr add " IP4_SRC "/32 dev src"); + SYS(fail, "ip addr add " IP6_SRC "/128 dev src nodad"); + SYS(fail, "ip link set dev src up"); - SYS(fail, "ip route add " IP4_DST "/32 dev veth_src scope global"); - SYS(fail, "ip route add " IP4_NET "/16 dev veth_src scope global"); - SYS(fail, "ip route add " IP6_DST "/128 dev veth_src scope global"); + SYS(fail, "ip route add " IP4_DST "/32 dev src scope global"); + SYS(fail, "ip route add " IP4_NET "/16 dev src scope global"); + SYS(fail, "ip route add " IP6_DST "/128 dev src scope global"); - SYS(fail, "ip neigh add " IP4_DST " dev veth_src lladdr %s", - veth_src_fwd_addr); - SYS(fail, "ip neigh add " IP6_DST " dev veth_src lladdr %s", - veth_src_fwd_addr); + if (result->dev_mode == MODE_VETH) { + SYS(fail, "ip neigh add " IP4_DST " dev src lladdr %s", + src_fwd_addr); + SYS(fail, "ip neigh add " IP6_DST " dev src lladdr %s", + src_fwd_addr); + } close_netns(nstoken); @@ -201,15 +260,15 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result) * needs v4 one in order to start ARP probing. IP4_NET route is added * to the endpoints so that the ARP processing will reply. */ - SYS(fail, "ip addr add " IP4_SLL "/32 dev veth_src_fwd"); - SYS(fail, "ip addr add " IP4_DLL "/32 dev veth_dst_fwd"); - SYS(fail, "ip link set dev veth_src_fwd up"); - SYS(fail, "ip link set dev veth_dst_fwd up"); + SYS(fail, "ip addr add " IP4_SLL "/32 dev src_fwd"); + SYS(fail, "ip addr add " IP4_DLL "/32 dev dst_fwd"); + SYS(fail, "ip link set dev src_fwd up"); + SYS(fail, "ip link set dev dst_fwd up"); - SYS(fail, "ip route add " IP4_SRC "/32 dev veth_src_fwd scope global"); - SYS(fail, "ip route add " IP6_SRC "/128 dev veth_src_fwd scope global"); - SYS(fail, "ip route add " IP4_DST "/32 dev veth_dst_fwd scope global"); - SYS(fail, "ip route add " IP6_DST "/128 dev veth_dst_fwd scope global"); + SYS(fail, "ip route add " IP4_SRC "/32 dev src_fwd scope global"); + SYS(fail, "ip route add " IP6_SRC "/128 dev src_fwd scope global"); + SYS(fail, "ip route add " IP4_DST "/32 dev dst_fwd scope global"); + SYS(fail, "ip route add " IP6_DST "/128 dev dst_fwd scope global"); close_netns(nstoken); @@ -218,16 +277,18 @@ static int netns_setup_links_and_routes(struct netns_setup_result *result) if (!ASSERT_OK_PTR(nstoken, "setns dst")) goto fail; - SYS(fail, "ip addr add " IP4_DST "/32 dev veth_dst"); - SYS(fail, "ip addr add " IP6_DST "/128 dev veth_dst nodad"); - SYS(fail, "ip link set dev veth_dst up"); + SYS(fail, "ip addr add " IP4_DST "/32 dev dst"); + SYS(fail, "ip addr add " IP6_DST "/128 dev dst nodad"); + SYS(fail, "ip link set dev dst up"); - SYS(fail, "ip route add " IP4_SRC "/32 dev veth_dst scope global"); - SYS(fail, "ip route add " IP4_NET "/16 dev veth_dst scope global"); - SYS(fail, "ip route add " IP6_SRC "/128 dev veth_dst scope global"); + SYS(fail, "ip route add " IP4_SRC "/32 dev dst scope global"); + SYS(fail, "ip route add " IP4_NET "/16 dev dst scope global"); + SYS(fail, "ip route add " IP6_SRC "/128 dev dst scope global"); - SYS(fail, "ip neigh add " IP4_SRC " dev veth_dst lladdr " MAC_DST_FWD); - SYS(fail, "ip neigh add " IP6_SRC " dev veth_dst lladdr " MAC_DST_FWD); + if (result->dev_mode == MODE_VETH) { + SYS(fail, "ip neigh add " IP4_SRC " dev dst lladdr " MAC_DST_FWD); + SYS(fail, "ip neigh add " IP6_SRC " dev dst lladdr " MAC_DST_FWD); + } close_netns(nstoken); @@ -293,23 +354,23 @@ static int netns_load_bpf(const struct bpf_program *src_prog, const struct bpf_program *chk_prog, const struct netns_setup_result *setup_result) { - LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_src_fwd); - LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_dst_fwd); + LIBBPF_OPTS(bpf_tc_hook, qdisc_src_fwd); + LIBBPF_OPTS(bpf_tc_hook, qdisc_dst_fwd); int err; - /* tc qdisc add dev veth_src_fwd clsact */ - QDISC_CLSACT_CREATE(&qdisc_veth_src_fwd, setup_result->ifindex_veth_src_fwd); - /* tc filter add dev veth_src_fwd ingress bpf da src_prog */ - XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_INGRESS, src_prog, 0); - /* tc filter add dev veth_src_fwd egress bpf da chk_prog */ - XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_EGRESS, chk_prog, 0); + /* tc qdisc add dev src_fwd clsact */ + QDISC_CLSACT_CREATE(&qdisc_src_fwd, setup_result->ifindex_src_fwd); + /* tc filter add dev src_fwd ingress bpf da src_prog */ + XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_INGRESS, src_prog, 0); + /* tc filter add dev src_fwd egress bpf da chk_prog */ + XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_EGRESS, chk_prog, 0); - /* tc qdisc add dev veth_dst_fwd clsact */ - QDISC_CLSACT_CREATE(&qdisc_veth_dst_fwd, setup_result->ifindex_veth_dst_fwd); - /* tc filter add dev veth_dst_fwd ingress bpf da dst_prog */ - XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_INGRESS, dst_prog, 0); - /* tc filter add dev veth_dst_fwd egress bpf da chk_prog */ - XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_EGRESS, chk_prog, 0); + /* tc qdisc add dev dst_fwd clsact */ + QDISC_CLSACT_CREATE(&qdisc_dst_fwd, setup_result->ifindex_dst_fwd); + /* tc filter add dev dst_fwd ingress bpf da dst_prog */ + XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_INGRESS, dst_prog, 0); + /* tc filter add dev dst_fwd egress bpf da chk_prog */ + XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_EGRESS, chk_prog, 0); return 0; fail: @@ -539,10 +600,10 @@ done: static int netns_load_dtime_bpf(struct test_tc_dtime *skel, const struct netns_setup_result *setup_result) { - LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_src_fwd); - LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_dst_fwd); - LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_src); - LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_dst); + LIBBPF_OPTS(bpf_tc_hook, qdisc_src_fwd); + LIBBPF_OPTS(bpf_tc_hook, qdisc_dst_fwd); + LIBBPF_OPTS(bpf_tc_hook, qdisc_src); + LIBBPF_OPTS(bpf_tc_hook, qdisc_dst); struct nstoken *nstoken; int err; @@ -550,58 +611,58 @@ static int netns_load_dtime_bpf(struct test_tc_dtime *skel, nstoken = open_netns(NS_SRC); if (!ASSERT_OK_PTR(nstoken, "setns " NS_SRC)) return -1; - /* tc qdisc add dev veth_src clsact */ - QDISC_CLSACT_CREATE(&qdisc_veth_src, setup_result->ifindex_veth_src); - /* tc filter add dev veth_src ingress bpf da ingress_host */ - XGRESS_FILTER_ADD(&qdisc_veth_src, BPF_TC_INGRESS, skel->progs.ingress_host, 0); - /* tc filter add dev veth_src egress bpf da egress_host */ - XGRESS_FILTER_ADD(&qdisc_veth_src, BPF_TC_EGRESS, skel->progs.egress_host, 0); + /* tc qdisc add dev src clsact */ + QDISC_CLSACT_CREATE(&qdisc_src, setup_result->ifindex_src); + /* tc filter add dev src ingress bpf da ingress_host */ + XGRESS_FILTER_ADD(&qdisc_src, BPF_TC_INGRESS, skel->progs.ingress_host, 0); + /* tc filter add dev src egress bpf da egress_host */ + XGRESS_FILTER_ADD(&qdisc_src, BPF_TC_EGRESS, skel->progs.egress_host, 0); close_netns(nstoken); /* setup ns_dst tc progs */ nstoken = open_netns(NS_DST); if (!ASSERT_OK_PTR(nstoken, "setns " NS_DST)) return -1; - /* tc qdisc add dev veth_dst clsact */ - QDISC_CLSACT_CREATE(&qdisc_veth_dst, setup_result->ifindex_veth_dst); - /* tc filter add dev veth_dst ingress bpf da ingress_host */ - XGRESS_FILTER_ADD(&qdisc_veth_dst, BPF_TC_INGRESS, skel->progs.ingress_host, 0); - /* tc filter add dev veth_dst egress bpf da egress_host */ - XGRESS_FILTER_ADD(&qdisc_veth_dst, BPF_TC_EGRESS, skel->progs.egress_host, 0); + /* tc qdisc add dev dst clsact */ + QDISC_CLSACT_CREATE(&qdisc_dst, setup_result->ifindex_dst); + /* tc filter add dev dst ingress bpf da ingress_host */ + XGRESS_FILTER_ADD(&qdisc_dst, BPF_TC_INGRESS, skel->progs.ingress_host, 0); + /* tc filter add dev dst egress bpf da egress_host */ + XGRESS_FILTER_ADD(&qdisc_dst, BPF_TC_EGRESS, skel->progs.egress_host, 0); close_netns(nstoken); /* setup ns_fwd tc progs */ nstoken = open_netns(NS_FWD); if (!ASSERT_OK_PTR(nstoken, "setns " NS_FWD)) return -1; - /* tc qdisc add dev veth_dst_fwd clsact */ - QDISC_CLSACT_CREATE(&qdisc_veth_dst_fwd, setup_result->ifindex_veth_dst_fwd); - /* tc filter add dev veth_dst_fwd ingress prio 100 bpf da ingress_fwdns_prio100 */ - XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_INGRESS, + /* tc qdisc add dev dst_fwd clsact */ + QDISC_CLSACT_CREATE(&qdisc_dst_fwd, setup_result->ifindex_dst_fwd); + /* tc filter add dev dst_fwd ingress prio 100 bpf da ingress_fwdns_prio100 */ + XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_INGRESS, skel->progs.ingress_fwdns_prio100, 100); - /* tc filter add dev veth_dst_fwd ingress prio 101 bpf da ingress_fwdns_prio101 */ - XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_INGRESS, + /* tc filter add dev dst_fwd ingress prio 101 bpf da ingress_fwdns_prio101 */ + XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_INGRESS, skel->progs.ingress_fwdns_prio101, 101); - /* tc filter add dev veth_dst_fwd egress prio 100 bpf da egress_fwdns_prio100 */ - XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_EGRESS, + /* tc filter add dev dst_fwd egress prio 100 bpf da egress_fwdns_prio100 */ + XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_EGRESS, skel->progs.egress_fwdns_prio100, 100); - /* tc filter add dev veth_dst_fwd egress prio 101 bpf da egress_fwdns_prio101 */ - XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_EGRESS, + /* tc filter add dev dst_fwd egress prio 101 bpf da egress_fwdns_prio101 */ + XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_EGRESS, skel->progs.egress_fwdns_prio101, 101); - /* tc qdisc add dev veth_src_fwd clsact */ - QDISC_CLSACT_CREATE(&qdisc_veth_src_fwd, setup_result->ifindex_veth_src_fwd); - /* tc filter add dev veth_src_fwd ingress prio 100 bpf da ingress_fwdns_prio100 */ - XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_INGRESS, + /* tc qdisc add dev src_fwd clsact */ + QDISC_CLSACT_CREATE(&qdisc_src_fwd, setup_result->ifindex_src_fwd); + /* tc filter add dev src_fwd ingress prio 100 bpf da ingress_fwdns_prio100 */ + XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_INGRESS, skel->progs.ingress_fwdns_prio100, 100); - /* tc filter add dev veth_src_fwd ingress prio 101 bpf da ingress_fwdns_prio101 */ - XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_INGRESS, + /* tc filter add dev src_fwd ingress prio 101 bpf da ingress_fwdns_prio101 */ + XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_INGRESS, skel->progs.ingress_fwdns_prio101, 101); - /* tc filter add dev veth_src_fwd egress prio 100 bpf da egress_fwdns_prio100 */ - XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_EGRESS, + /* tc filter add dev src_fwd egress prio 100 bpf da egress_fwdns_prio100 */ + XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_EGRESS, skel->progs.egress_fwdns_prio100, 100); - /* tc filter add dev veth_src_fwd egress prio 101 bpf da egress_fwdns_prio101 */ - XGRESS_FILTER_ADD(&qdisc_veth_src_fwd, BPF_TC_EGRESS, + /* tc filter add dev src_fwd egress prio 101 bpf da egress_fwdns_prio101 */ + XGRESS_FILTER_ADD(&qdisc_src_fwd, BPF_TC_EGRESS, skel->progs.egress_fwdns_prio101, 101); close_netns(nstoken); return 0; @@ -777,8 +838,8 @@ static void test_tc_redirect_dtime(struct netns_setup_result *setup_result) if (!ASSERT_OK_PTR(skel, "test_tc_dtime__open")) return; - skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd; - skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd; + skel->rodata->IFINDEX_SRC = setup_result->ifindex_src_fwd; + skel->rodata->IFINDEX_DST = setup_result->ifindex_dst_fwd; err = test_tc_dtime__load(skel); if (!ASSERT_OK(err, "test_tc_dtime__load")) @@ -868,8 +929,8 @@ static void test_tc_redirect_neigh(struct netns_setup_result *setup_result) if (!ASSERT_OK_PTR(skel, "test_tc_neigh__open")) goto done; - skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd; - skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd; + skel->rodata->IFINDEX_SRC = setup_result->ifindex_src_fwd; + skel->rodata->IFINDEX_DST = setup_result->ifindex_dst_fwd; err = test_tc_neigh__load(skel); if (!ASSERT_OK(err, "test_tc_neigh__load")) @@ -904,8 +965,8 @@ static void test_tc_redirect_peer(struct netns_setup_result *setup_result) if (!ASSERT_OK_PTR(skel, "test_tc_peer__open")) goto done; - skel->rodata->IFINDEX_SRC = setup_result->ifindex_veth_src_fwd; - skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd; + skel->rodata->IFINDEX_SRC = setup_result->ifindex_src_fwd; + skel->rodata->IFINDEX_DST = setup_result->ifindex_dst_fwd; err = test_tc_peer__load(skel); if (!ASSERT_OK(err, "test_tc_peer__load")) @@ -996,7 +1057,7 @@ static int tun_relay_loop(int src_fd, int target_fd) static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result) { LIBBPF_OPTS(bpf_tc_hook, qdisc_tun_fwd); - LIBBPF_OPTS(bpf_tc_hook, qdisc_veth_dst_fwd); + LIBBPF_OPTS(bpf_tc_hook, qdisc_dst_fwd); struct test_tc_peer *skel = NULL; struct nstoken *nstoken = NULL; int err; @@ -1045,7 +1106,7 @@ static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result) goto fail; skel->rodata->IFINDEX_SRC = ifindex; - skel->rodata->IFINDEX_DST = setup_result->ifindex_veth_dst_fwd; + skel->rodata->IFINDEX_DST = setup_result->ifindex_dst_fwd; err = test_tc_peer__load(skel); if (!ASSERT_OK(err, "test_tc_peer__load")) @@ -1053,19 +1114,19 @@ static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result) /* Load "tc_src_l3" to the tun_fwd interface to redirect packets * towards dst, and "tc_dst" to redirect packets - * and "tc_chk" on veth_dst_fwd to drop non-redirected packets. + * and "tc_chk" on dst_fwd to drop non-redirected packets. */ /* tc qdisc add dev tun_fwd clsact */ QDISC_CLSACT_CREATE(&qdisc_tun_fwd, ifindex); /* tc filter add dev tun_fwd ingress bpf da tc_src_l3 */ XGRESS_FILTER_ADD(&qdisc_tun_fwd, BPF_TC_INGRESS, skel->progs.tc_src_l3, 0); - /* tc qdisc add dev veth_dst_fwd clsact */ - QDISC_CLSACT_CREATE(&qdisc_veth_dst_fwd, setup_result->ifindex_veth_dst_fwd); - /* tc filter add dev veth_dst_fwd ingress bpf da tc_dst_l3 */ - XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_INGRESS, skel->progs.tc_dst_l3, 0); - /* tc filter add dev veth_dst_fwd egress bpf da tc_chk */ - XGRESS_FILTER_ADD(&qdisc_veth_dst_fwd, BPF_TC_EGRESS, skel->progs.tc_chk, 0); + /* tc qdisc add dev dst_fwd clsact */ + QDISC_CLSACT_CREATE(&qdisc_dst_fwd, setup_result->ifindex_dst_fwd); + /* tc filter add dev dst_fwd ingress bpf da tc_dst_l3 */ + XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_INGRESS, skel->progs.tc_dst_l3, 0); + /* tc filter add dev dst_fwd egress bpf da tc_chk */ + XGRESS_FILTER_ADD(&qdisc_dst_fwd, BPF_TC_EGRESS, skel->progs.tc_chk, 0); /* Setup route and neigh tables */ SYS(fail, "ip -netns " NS_SRC " addr add dev tun_src " IP4_TUN_SRC "/24"); @@ -1074,17 +1135,17 @@ static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result) SYS(fail, "ip -netns " NS_SRC " addr add dev tun_src " IP6_TUN_SRC "/64 nodad"); SYS(fail, "ip -netns " NS_FWD " addr add dev tun_fwd " IP6_TUN_FWD "/64 nodad"); - SYS(fail, "ip -netns " NS_SRC " route del " IP4_DST "/32 dev veth_src scope global"); + SYS(fail, "ip -netns " NS_SRC " route del " IP4_DST "/32 dev src scope global"); SYS(fail, "ip -netns " NS_SRC " route add " IP4_DST "/32 via " IP4_TUN_FWD " dev tun_src scope global"); - SYS(fail, "ip -netns " NS_DST " route add " IP4_TUN_SRC "/32 dev veth_dst scope global"); - SYS(fail, "ip -netns " NS_SRC " route del " IP6_DST "/128 dev veth_src scope global"); + SYS(fail, "ip -netns " NS_DST " route add " IP4_TUN_SRC "/32 dev dst scope global"); + SYS(fail, "ip -netns " NS_SRC " route del " IP6_DST "/128 dev src scope global"); SYS(fail, "ip -netns " NS_SRC " route add " IP6_DST "/128 via " IP6_TUN_FWD " dev tun_src scope global"); - SYS(fail, "ip -netns " NS_DST " route add " IP6_TUN_SRC "/128 dev veth_dst scope global"); + SYS(fail, "ip -netns " NS_DST " route add " IP6_TUN_SRC "/128 dev dst scope global"); - SYS(fail, "ip -netns " NS_DST " neigh add " IP4_TUN_SRC " dev veth_dst lladdr " MAC_DST_FWD); - SYS(fail, "ip -netns " NS_DST " neigh add " IP6_TUN_SRC " dev veth_dst lladdr " MAC_DST_FWD); + SYS(fail, "ip -netns " NS_DST " neigh add " IP4_TUN_SRC " dev dst lladdr " MAC_DST_FWD); + SYS(fail, "ip -netns " NS_DST " neigh add " IP6_TUN_SRC " dev dst lladdr " MAC_DST_FWD); if (!ASSERT_OK(set_forwarding(false), "disable forwarding")) goto fail; @@ -1106,9 +1167,9 @@ fail: close_netns(nstoken); } -#define RUN_TEST(name) \ +#define RUN_TEST(name, mode) \ ({ \ - struct netns_setup_result setup_result; \ + struct netns_setup_result setup_result = { .dev_mode = mode, }; \ if (test__start_subtest(#name)) \ if (ASSERT_OK(netns_setup_namespaces("add"), "setup namespaces")) { \ if (ASSERT_OK(netns_setup_links_and_routes(&setup_result), \ @@ -1122,11 +1183,13 @@ static void *test_tc_redirect_run_tests(void *arg) { netns_setup_namespaces_nofail("delete"); - RUN_TEST(tc_redirect_peer); - RUN_TEST(tc_redirect_peer_l3); - RUN_TEST(tc_redirect_neigh); - RUN_TEST(tc_redirect_neigh_fib); - RUN_TEST(tc_redirect_dtime); + RUN_TEST(tc_redirect_peer, MODE_VETH); + RUN_TEST(tc_redirect_peer, MODE_NETKIT); + RUN_TEST(tc_redirect_peer_l3, MODE_VETH); + RUN_TEST(tc_redirect_peer_l3, MODE_NETKIT); + RUN_TEST(tc_redirect_neigh, MODE_VETH); + RUN_TEST(tc_redirect_neigh_fib, MODE_VETH); + RUN_TEST(tc_redirect_dtime, MODE_VETH); return NULL; } diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index e5c61aa6604a..5cfa7a6316b6 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -31,6 +31,7 @@ #include "verifier_helper_restricted.skel.h" #include "verifier_helper_value_access.skel.h" #include "verifier_int_ptr.skel.h" +#include "verifier_iterating_callbacks.skel.h" #include "verifier_jeq_infer_not_null.skel.h" #include "verifier_ld_ind.skel.h" #include "verifier_ldsx.skel.h" @@ -139,6 +140,7 @@ void test_verifier_helper_packet_access(void) { RUN(verifier_helper_packet_acces void test_verifier_helper_restricted(void) { RUN(verifier_helper_restricted); } void test_verifier_helper_value_access(void) { RUN(verifier_helper_value_access); } void test_verifier_int_ptr(void) { RUN(verifier_int_ptr); } +void test_verifier_iterating_callbacks(void) { RUN(verifier_iterating_callbacks); } void test_verifier_jeq_infer_not_null(void) { RUN(verifier_jeq_infer_not_null); } void test_verifier_ld_ind(void) { RUN(verifier_ld_ind); } void test_verifier_ldsx(void) { RUN(verifier_ldsx); } diff --git a/tools/testing/selftests/bpf/progs/bpf_loop_bench.c b/tools/testing/selftests/bpf/progs/bpf_loop_bench.c index 4ce76eb064c4..d461746fd3c1 100644 --- a/tools/testing/selftests/bpf/progs/bpf_loop_bench.c +++ b/tools/testing/selftests/bpf/progs/bpf_loop_bench.c @@ -15,13 +15,16 @@ static int empty_callback(__u32 index, void *data) return 0; } +static int outer_loop(__u32 index, void *data) +{ + bpf_loop(nr_loops, empty_callback, NULL, 0); + __sync_add_and_fetch(&hits, nr_loops); + return 0; +} + SEC("fentry/" SYS_PREFIX "sys_getpgid") int benchmark(void *ctx) { - for (int i = 0; i < 1000; i++) { - bpf_loop(nr_loops, empty_callback, NULL, 0); - - __sync_add_and_fetch(&hits, nr_loops); - } + bpf_loop(1000, outer_loop, NULL, 0); return 0; } diff --git a/tools/testing/selftests/bpf/progs/cb_refs.c b/tools/testing/selftests/bpf/progs/cb_refs.c index 76d661b20e87..56c764df8196 100644 --- a/tools/testing/selftests/bpf/progs/cb_refs.c +++ b/tools/testing/selftests/bpf/progs/cb_refs.c @@ -33,6 +33,7 @@ int underflow_prog(void *ctx) if (!p) return 0; bpf_for_each_map_elem(&array_map, cb1, &p, 0); + bpf_kfunc_call_test_release(p); return 0; } diff --git a/tools/testing/selftests/bpf/progs/exceptions_fail.c b/tools/testing/selftests/bpf/progs/exceptions_fail.c index 4c39e920dac2..8c0ef2742208 100644 --- a/tools/testing/selftests/bpf/progs/exceptions_fail.c +++ b/tools/testing/selftests/bpf/progs/exceptions_fail.c @@ -171,6 +171,7 @@ int reject_with_rbtree_add_throw(void *ctx) return 0; bpf_spin_lock(&lock); bpf_rbtree_add(&rbtree, &f->node, rbless); + bpf_spin_unlock(&lock); return 0; } @@ -214,6 +215,7 @@ int reject_with_cb_reference(void *ctx) if (!f) return 0; bpf_loop(5, subprog_cb_ref, NULL, 0); + bpf_obj_drop(f); return 0; } diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h index e02cfd380746..40df2cc26eaf 100644 --- a/tools/testing/selftests/bpf/progs/strobemeta.h +++ b/tools/testing/selftests/bpf/progs/strobemeta.h @@ -24,9 +24,11 @@ struct task_struct {}; #define STACK_TABLE_EPOCH_SHIFT 20 #define STROBE_MAX_STR_LEN 1 #define STROBE_MAX_CFGS 32 +#define READ_MAP_VAR_PAYLOAD_CAP \ + ((1 + STROBE_MAX_MAP_ENTRIES * 2) * STROBE_MAX_STR_LEN) #define STROBE_MAX_PAYLOAD \ (STROBE_MAX_STRS * STROBE_MAX_STR_LEN + \ - STROBE_MAX_MAPS * (1 + STROBE_MAX_MAP_ENTRIES * 2) * STROBE_MAX_STR_LEN) + STROBE_MAX_MAPS * READ_MAP_VAR_PAYLOAD_CAP) struct strobe_value_header { /* @@ -355,7 +357,7 @@ static __always_inline uint64_t read_str_var(struct strobemeta_cfg *cfg, size_t idx, void *tls_base, struct strobe_value_generic *value, struct strobemeta_payload *data, - void *payload) + size_t off) { void *location; uint64_t len; @@ -366,7 +368,7 @@ static __always_inline uint64_t read_str_var(struct strobemeta_cfg *cfg, return 0; bpf_probe_read_user(value, sizeof(struct strobe_value_generic), location); - len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN, value->ptr); + len = bpf_probe_read_user_str(&data->payload[off], STROBE_MAX_STR_LEN, value->ptr); /* * if bpf_probe_read_user_str returns error (<0), due to casting to * unsinged int, it will become big number, so next check is @@ -378,14 +380,14 @@ static __always_inline uint64_t read_str_var(struct strobemeta_cfg *cfg, return 0; data->str_lens[idx] = len; - return len; + return off + len; } -static __always_inline void *read_map_var(struct strobemeta_cfg *cfg, - size_t idx, void *tls_base, - struct strobe_value_generic *value, - struct strobemeta_payload *data, - void *payload) +static __always_inline uint64_t read_map_var(struct strobemeta_cfg *cfg, + size_t idx, void *tls_base, + struct strobe_value_generic *value, + struct strobemeta_payload *data, + size_t off) { struct strobe_map_descr* descr = &data->map_descrs[idx]; struct strobe_map_raw map; @@ -397,11 +399,11 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg, location = calc_location(&cfg->map_locs[idx], tls_base); if (!location) - return payload; + return off; bpf_probe_read_user(value, sizeof(struct strobe_value_generic), location); if (bpf_probe_read_user(&map, sizeof(struct strobe_map_raw), value->ptr)) - return payload; + return off; descr->id = map.id; descr->cnt = map.cnt; @@ -410,10 +412,10 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg, data->req_meta_valid = 1; } - len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN, map.tag); + len = bpf_probe_read_user_str(&data->payload[off], STROBE_MAX_STR_LEN, map.tag); if (len <= STROBE_MAX_STR_LEN) { descr->tag_len = len; - payload += len; + off += len; } #ifdef NO_UNROLL @@ -426,22 +428,22 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg, break; descr->key_lens[i] = 0; - len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN, + len = bpf_probe_read_user_str(&data->payload[off], STROBE_MAX_STR_LEN, map.entries[i].key); if (len <= STROBE_MAX_STR_LEN) { descr->key_lens[i] = len; - payload += len; + off += len; } descr->val_lens[i] = 0; - len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN, + len = bpf_probe_read_user_str(&data->payload[off], STROBE_MAX_STR_LEN, map.entries[i].val); if (len <= STROBE_MAX_STR_LEN) { descr->val_lens[i] = len; - payload += len; + off += len; } } - return payload; + return off; } #ifdef USE_BPF_LOOP @@ -455,14 +457,20 @@ struct read_var_ctx { struct strobemeta_payload *data; void *tls_base; struct strobemeta_cfg *cfg; - void *payload; + size_t payload_off; /* value gets mutated */ struct strobe_value_generic *value; enum read_type type; }; -static int read_var_callback(__u32 index, struct read_var_ctx *ctx) +static int read_var_callback(__u64 index, struct read_var_ctx *ctx) { + /* lose precision info for ctx->payload_off, verifier won't track + * double xor, barrier_var() is needed to force clang keep both xors. + */ + ctx->payload_off ^= index; + barrier_var(ctx->payload_off); + ctx->payload_off ^= index; switch (ctx->type) { case READ_INT_VAR: if (index >= STROBE_MAX_INTS) @@ -472,14 +480,18 @@ static int read_var_callback(__u32 index, struct read_var_ctx *ctx) case READ_MAP_VAR: if (index >= STROBE_MAX_MAPS) return 1; - ctx->payload = read_map_var(ctx->cfg, index, ctx->tls_base, - ctx->value, ctx->data, ctx->payload); + if (ctx->payload_off > sizeof(ctx->data->payload) - READ_MAP_VAR_PAYLOAD_CAP) + return 1; + ctx->payload_off = read_map_var(ctx->cfg, index, ctx->tls_base, + ctx->value, ctx->data, ctx->payload_off); break; case READ_STR_VAR: if (index >= STROBE_MAX_STRS) return 1; - ctx->payload += read_str_var(ctx->cfg, index, ctx->tls_base, - ctx->value, ctx->data, ctx->payload); + if (ctx->payload_off > sizeof(ctx->data->payload) - STROBE_MAX_STR_LEN) + return 1; + ctx->payload_off = read_str_var(ctx->cfg, index, ctx->tls_base, + ctx->value, ctx->data, ctx->payload_off); break; } return 0; @@ -501,7 +513,8 @@ static void *read_strobe_meta(struct task_struct *task, pid_t pid = bpf_get_current_pid_tgid() >> 32; struct strobe_value_generic value = {0}; struct strobemeta_cfg *cfg; - void *tls_base, *payload; + size_t payload_off; + void *tls_base; cfg = bpf_map_lookup_elem(&strobemeta_cfgs, &pid); if (!cfg) @@ -509,7 +522,7 @@ static void *read_strobe_meta(struct task_struct *task, data->int_vals_set_mask = 0; data->req_meta_valid = 0; - payload = data->payload; + payload_off = 0; /* * we don't have struct task_struct definition, it should be: * tls_base = (void *)task->thread.fsbase; @@ -522,7 +535,7 @@ static void *read_strobe_meta(struct task_struct *task, .tls_base = tls_base, .value = &value, .data = data, - .payload = payload, + .payload_off = 0, }; int err; @@ -540,6 +553,11 @@ static void *read_strobe_meta(struct task_struct *task, err = bpf_loop(STROBE_MAX_MAPS, read_var_callback, &ctx, 0); if (err != STROBE_MAX_MAPS) return NULL; + + payload_off = ctx.payload_off; + /* this should not really happen, here only to satisfy verifer */ + if (payload_off > sizeof(data->payload)) + payload_off = sizeof(data->payload); #else #ifdef NO_UNROLL #pragma clang loop unroll(disable) @@ -555,7 +573,7 @@ static void *read_strobe_meta(struct task_struct *task, #pragma unroll #endif /* NO_UNROLL */ for (int i = 0; i < STROBE_MAX_STRS; ++i) { - payload += read_str_var(cfg, i, tls_base, &value, data, payload); + payload_off = read_str_var(cfg, i, tls_base, &value, data, payload_off); } #ifdef NO_UNROLL #pragma clang loop unroll(disable) @@ -563,7 +581,7 @@ static void *read_strobe_meta(struct task_struct *task, #pragma unroll #endif /* NO_UNROLL */ for (int i = 0; i < STROBE_MAX_MAPS; ++i) { - payload = read_map_var(cfg, i, tls_base, &value, data, payload); + payload_off = read_map_var(cfg, i, tls_base, &value, data, payload_off); } #endif /* USE_BPF_LOOP */ @@ -571,7 +589,7 @@ static void *read_strobe_meta(struct task_struct *task, * return pointer right after end of payload, so it's possible to * calculate exact amount of useful data that needs to be sent */ - return payload; + return &data->payload[payload_off]; } SEC("raw_tracepoint/kfree_skb") diff --git a/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c new file mode 100644 index 000000000000..5905e036e0ea --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_iterating_callbacks.c @@ -0,0 +1,242 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 8); + __type(key, __u32); + __type(value, __u64); +} map SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_USER_RINGBUF); + __uint(max_entries, 8); +} ringbuf SEC(".maps"); + +struct vm_area_struct; +struct bpf_map; + +struct buf_context { + char *buf; +}; + +struct num_context { + __u64 i; + __u64 j; +}; + +__u8 choice_arr[2] = { 0, 1 }; + +static int unsafe_on_2nd_iter_cb(__u32 idx, struct buf_context *ctx) +{ + if (idx == 0) { + ctx->buf = (char *)(0xDEAD); + return 0; + } + + if (bpf_probe_read_user(ctx->buf, 8, (void *)(0xBADC0FFEE))) + return 1; + + return 0; +} + +SEC("?raw_tp") +__failure __msg("R1 type=scalar expected=fp") +int unsafe_on_2nd_iter(void *unused) +{ + char buf[4]; + struct buf_context loop_ctx = { .buf = buf }; + + bpf_loop(100, unsafe_on_2nd_iter_cb, &loop_ctx, 0); + return 0; +} + +static int unsafe_on_zero_iter_cb(__u32 idx, struct num_context *ctx) +{ + ctx->i = 0; + return 0; +} + +SEC("?raw_tp") +__failure __msg("invalid access to map value, value_size=2 off=32 size=1") +int unsafe_on_zero_iter(void *unused) +{ + struct num_context loop_ctx = { .i = 32 }; + + bpf_loop(100, unsafe_on_zero_iter_cb, &loop_ctx, 0); + return choice_arr[loop_ctx.i]; +} + +static int widening_cb(__u32 idx, struct num_context *ctx) +{ + ++ctx->i; + return 0; +} + +SEC("?raw_tp") +__success +int widening(void *unused) +{ + struct num_context loop_ctx = { .i = 0, .j = 1 }; + + bpf_loop(100, widening_cb, &loop_ctx, 0); + /* loop_ctx.j is not changed during callback iteration, + * verifier should not apply widening to it. + */ + return choice_arr[loop_ctx.j]; +} + +static int loop_detection_cb(__u32 idx, struct num_context *ctx) +{ + for (;;) {} + return 0; +} + +SEC("?raw_tp") +__failure __msg("infinite loop detected") +int loop_detection(void *unused) +{ + struct num_context loop_ctx = { .i = 0 }; + + bpf_loop(100, loop_detection_cb, &loop_ctx, 0); + return 0; +} + +static __always_inline __u64 oob_state_machine(struct num_context *ctx) +{ + switch (ctx->i) { + case 0: + ctx->i = 1; + break; + case 1: + ctx->i = 32; + break; + } + return 0; +} + +static __u64 for_each_map_elem_cb(struct bpf_map *map, __u32 *key, __u64 *val, void *data) +{ + return oob_state_machine(data); +} + +SEC("?raw_tp") +__failure __msg("invalid access to map value, value_size=2 off=32 size=1") +int unsafe_for_each_map_elem(void *unused) +{ + struct num_context loop_ctx = { .i = 0 }; + + bpf_for_each_map_elem(&map, for_each_map_elem_cb, &loop_ctx, 0); + return choice_arr[loop_ctx.i]; +} + +static __u64 ringbuf_drain_cb(struct bpf_dynptr *dynptr, void *data) +{ + return oob_state_machine(data); +} + +SEC("?raw_tp") +__failure __msg("invalid access to map value, value_size=2 off=32 size=1") +int unsafe_ringbuf_drain(void *unused) +{ + struct num_context loop_ctx = { .i = 0 }; + + bpf_user_ringbuf_drain(&ringbuf, ringbuf_drain_cb, &loop_ctx, 0); + return choice_arr[loop_ctx.i]; +} + +static __u64 find_vma_cb(struct task_struct *task, struct vm_area_struct *vma, void *data) +{ + return oob_state_machine(data); +} + +SEC("?raw_tp") +__failure __msg("invalid access to map value, value_size=2 off=32 size=1") +int unsafe_find_vma(void *unused) +{ + struct task_struct *task = bpf_get_current_task_btf(); + struct num_context loop_ctx = { .i = 0 }; + + bpf_find_vma(task, 0, find_vma_cb, &loop_ctx, 0); + return choice_arr[loop_ctx.i]; +} + +static int iter_limit_cb(__u32 idx, struct num_context *ctx) +{ + ctx->i++; + return 0; +} + +SEC("?raw_tp") +__success +int bpf_loop_iter_limit_ok(void *unused) +{ + struct num_context ctx = { .i = 0 }; + + bpf_loop(1, iter_limit_cb, &ctx, 0); + return choice_arr[ctx.i]; +} + +SEC("?raw_tp") +__failure __msg("invalid access to map value, value_size=2 off=2 size=1") +int bpf_loop_iter_limit_overflow(void *unused) +{ + struct num_context ctx = { .i = 0 }; + + bpf_loop(2, iter_limit_cb, &ctx, 0); + return choice_arr[ctx.i]; +} + +static int iter_limit_level2a_cb(__u32 idx, struct num_context *ctx) +{ + ctx->i += 100; + return 0; +} + +static int iter_limit_level2b_cb(__u32 idx, struct num_context *ctx) +{ + ctx->i += 10; + return 0; +} + +static int iter_limit_level1_cb(__u32 idx, struct num_context *ctx) +{ + ctx->i += 1; + bpf_loop(1, iter_limit_level2a_cb, ctx, 0); + bpf_loop(1, iter_limit_level2b_cb, ctx, 0); + return 0; +} + +/* Check that path visiting every callback function once had been + * reached by verifier. Variables 'ctx{1,2}i' below serve as flags, + * with each decimal digit corresponding to a callback visit marker. + */ +SEC("socket") +__success __retval(111111) +int bpf_loop_iter_limit_nested(void *unused) +{ + struct num_context ctx1 = { .i = 0 }; + struct num_context ctx2 = { .i = 0 }; + __u64 a, b, c; + + bpf_loop(1, iter_limit_level1_cb, &ctx1, 0); + bpf_loop(1, iter_limit_level1_cb, &ctx2, 0); + a = ctx1.i; + b = ctx2.i; + /* Force 'ctx1.i' and 'ctx2.i' precise. */ + c = choice_arr[(a + b) % 2]; + /* This makes 'c' zero, but neither clang nor verifier know it. */ + c /= 10; + /* Make sure that verifier does not visit 'impossible' states: + * enumerate all possible callback visit masks. + */ + if (a != 0 && a != 1 && a != 11 && a != 101 && a != 111 && + b != 0 && b != 1 && b != 11 && b != 101 && b != 111) + asm volatile ("r0 /= 0;" ::: "r0"); + return 1000 * a + b + c; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c index db6b3143338b..f61d623b1ce8 100644 --- a/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c +++ b/tools/testing/selftests/bpf/progs/verifier_subprog_precision.c @@ -119,15 +119,41 @@ __naked int global_subprog_result_precise(void) SEC("?raw_tp") __success __log_level(2) +/* First simulated path does not include callback body, + * r1 and r4 are always precise for bpf_loop() calls. + */ +__msg("9: (85) call bpf_loop#181") +__msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1") +__msg("mark_precise: frame0: parent state regs=r4 stack=:") +__msg("mark_precise: frame0: last_idx 8 first_idx 0 subseq_idx 9") +__msg("mark_precise: frame0: regs=r4 stack= before 8: (b7) r4 = 0") +__msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1") +__msg("mark_precise: frame0: parent state regs=r1 stack=:") +__msg("mark_precise: frame0: last_idx 8 first_idx 0 subseq_idx 9") +__msg("mark_precise: frame0: regs=r1 stack= before 8: (b7) r4 = 0") +__msg("mark_precise: frame0: regs=r1 stack= before 7: (b7) r3 = 0") +__msg("mark_precise: frame0: regs=r1 stack= before 6: (bf) r2 = r8") +__msg("mark_precise: frame0: regs=r1 stack= before 5: (bf) r1 = r6") +__msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3") +/* r6 precision propagation */ __msg("14: (0f) r1 += r6") -__msg("mark_precise: frame0: last_idx 14 first_idx 10") +__msg("mark_precise: frame0: last_idx 14 first_idx 9") __msg("mark_precise: frame0: regs=r6 stack= before 13: (bf) r1 = r7") __msg("mark_precise: frame0: regs=r6 stack= before 12: (27) r6 *= 4") __msg("mark_precise: frame0: regs=r6 stack= before 11: (25) if r6 > 0x3 goto pc+4") __msg("mark_precise: frame0: regs=r6 stack= before 10: (bf) r6 = r0") -__msg("mark_precise: frame0: parent state regs=r0 stack=:") -__msg("mark_precise: frame0: last_idx 18 first_idx 0") -__msg("mark_precise: frame0: regs=r0 stack= before 18: (95) exit") +__msg("mark_precise: frame0: regs=r0 stack= before 9: (85) call bpf_loop") +/* State entering callback body popped from states stack */ +__msg("from 9 to 17: frame1:") +__msg("17: frame1: R1=scalar() R2=0 R10=fp0 cb") +__msg("17: (b7) r0 = 0") +__msg("18: (95) exit") +__msg("returning from callee:") +__msg("to caller at 9:") +__msg("frame 0: propagating r1,r4") +__msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1") +__msg("mark_precise: frame0: regs=r1,r4 stack= before 18: (95) exit") +__msg("from 18 to 9: safe") __naked int callback_result_precise(void) { asm volatile ( @@ -233,20 +259,36 @@ __naked int parent_callee_saved_reg_precise_global(void) SEC("?raw_tp") __success __log_level(2) +/* First simulated path does not include callback body */ __msg("12: (0f) r1 += r6") -__msg("mark_precise: frame0: last_idx 12 first_idx 10") +__msg("mark_precise: frame0: last_idx 12 first_idx 9") __msg("mark_precise: frame0: regs=r6 stack= before 11: (bf) r1 = r7") __msg("mark_precise: frame0: regs=r6 stack= before 10: (27) r6 *= 4") +__msg("mark_precise: frame0: regs=r6 stack= before 9: (85) call bpf_loop") __msg("mark_precise: frame0: parent state regs=r6 stack=:") -__msg("mark_precise: frame0: last_idx 16 first_idx 0") -__msg("mark_precise: frame0: regs=r6 stack= before 16: (95) exit") -__msg("mark_precise: frame1: regs= stack= before 15: (b7) r0 = 0") -__msg("mark_precise: frame1: regs= stack= before 9: (85) call bpf_loop#181") +__msg("mark_precise: frame0: last_idx 8 first_idx 0 subseq_idx 9") __msg("mark_precise: frame0: regs=r6 stack= before 8: (b7) r4 = 0") __msg("mark_precise: frame0: regs=r6 stack= before 7: (b7) r3 = 0") __msg("mark_precise: frame0: regs=r6 stack= before 6: (bf) r2 = r8") __msg("mark_precise: frame0: regs=r6 stack= before 5: (b7) r1 = 1") __msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3") +/* State entering callback body popped from states stack */ +__msg("from 9 to 15: frame1:") +__msg("15: frame1: R1=scalar() R2=0 R10=fp0 cb") +__msg("15: (b7) r0 = 0") +__msg("16: (95) exit") +__msg("returning from callee:") +__msg("to caller at 9:") +/* r1, r4 are always precise for bpf_loop(), + * r6 was marked before backtracking to callback body. + */ +__msg("frame 0: propagating r1,r4,r6") +__msg("mark_precise: frame0: last_idx 9 first_idx 9 subseq_idx -1") +__msg("mark_precise: frame0: regs=r1,r4,r6 stack= before 16: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 15: (b7) r0 = 0") +__msg("mark_precise: frame1: regs= stack= before 9: (85) call bpf_loop") +__msg("mark_precise: frame0: parent state regs= stack=:") +__msg("from 16 to 9: safe") __naked int parent_callee_saved_reg_precise_with_callback(void) { asm volatile ( @@ -373,22 +415,38 @@ __naked int parent_stack_slot_precise_global(void) SEC("?raw_tp") __success __log_level(2) +/* First simulated path does not include callback body */ __msg("14: (0f) r1 += r6") -__msg("mark_precise: frame0: last_idx 14 first_idx 11") +__msg("mark_precise: frame0: last_idx 14 first_idx 10") __msg("mark_precise: frame0: regs=r6 stack= before 13: (bf) r1 = r7") __msg("mark_precise: frame0: regs=r6 stack= before 12: (27) r6 *= 4") __msg("mark_precise: frame0: regs=r6 stack= before 11: (79) r6 = *(u64 *)(r10 -8)") +__msg("mark_precise: frame0: regs= stack=-8 before 10: (85) call bpf_loop") __msg("mark_precise: frame0: parent state regs= stack=-8:") -__msg("mark_precise: frame0: last_idx 18 first_idx 0") -__msg("mark_precise: frame0: regs= stack=-8 before 18: (95) exit") -__msg("mark_precise: frame1: regs= stack= before 17: (b7) r0 = 0") -__msg("mark_precise: frame1: regs= stack= before 10: (85) call bpf_loop#181") +__msg("mark_precise: frame0: last_idx 9 first_idx 0 subseq_idx 10") __msg("mark_precise: frame0: regs= stack=-8 before 9: (b7) r4 = 0") __msg("mark_precise: frame0: regs= stack=-8 before 8: (b7) r3 = 0") __msg("mark_precise: frame0: regs= stack=-8 before 7: (bf) r2 = r8") __msg("mark_precise: frame0: regs= stack=-8 before 6: (bf) r1 = r6") __msg("mark_precise: frame0: regs= stack=-8 before 5: (7b) *(u64 *)(r10 -8) = r6") __msg("mark_precise: frame0: regs=r6 stack= before 4: (b7) r6 = 3") +/* State entering callback body popped from states stack */ +__msg("from 10 to 17: frame1:") +__msg("17: frame1: R1=scalar() R2=0 R10=fp0 cb") +__msg("17: (b7) r0 = 0") +__msg("18: (95) exit") +__msg("returning from callee:") +__msg("to caller at 10:") +/* r1, r4 are always precise for bpf_loop(), + * fp-8 was marked before backtracking to callback body. + */ +__msg("frame 0: propagating r1,r4,fp-8") +__msg("mark_precise: frame0: last_idx 10 first_idx 10 subseq_idx -1") +__msg("mark_precise: frame0: regs=r1,r4 stack=-8 before 18: (95) exit") +__msg("mark_precise: frame1: regs= stack= before 17: (b7) r0 = 0") +__msg("mark_precise: frame1: regs= stack= before 10: (85) call bpf_loop#181") +__msg("mark_precise: frame0: parent state regs= stack=:") +__msg("from 18 to 10: safe") __naked int parent_stack_slot_precise_with_callback(void) { asm volatile ( diff --git a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c index e959336c7a73..80f620602d50 100644 --- a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c +++ b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c @@ -53,6 +53,8 @@ #define DEFAULT_TTL 64 #define MAX_ALLOWED_PORTS 8 +#define MAX_PACKET_OFF 0xffff + #define swap(a, b) \ do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0) @@ -183,63 +185,76 @@ static __always_inline __u32 tcp_clock_ms(void) } struct tcpopt_context { - __u8 *ptr; - __u8 *end; + void *data; void *data_end; __be32 *tsecr; __u8 wscale; bool option_timestamp; bool option_sack; + __u32 off; }; -static int tscookie_tcpopt_parse(struct tcpopt_context *ctx) +static __always_inline u8 *next(struct tcpopt_context *ctx, __u32 sz) { - __u8 opcode, opsize; + __u64 off = ctx->off; + __u8 *data; - if (ctx->ptr >= ctx->end) - return 1; - if (ctx->ptr >= ctx->data_end) - return 1; + /* Verifier forbids access to packet when offset exceeds MAX_PACKET_OFF */ + if (off > MAX_PACKET_OFF - sz) + return NULL; - opcode = ctx->ptr[0]; + data = ctx->data + off; + barrier_var(data); + if (data + sz >= ctx->data_end) + return NULL; - if (opcode == TCPOPT_EOL) - return 1; - if (opcode == TCPOPT_NOP) { - ++ctx->ptr; - return 0; - } + ctx->off += sz; + return data; +} - if (ctx->ptr + 1 >= ctx->end) - return 1; - if (ctx->ptr + 1 >= ctx->data_end) +static int tscookie_tcpopt_parse(struct tcpopt_context *ctx) +{ + __u8 *opcode, *opsize, *wscale, *tsecr; + __u32 off = ctx->off; + + opcode = next(ctx, 1); + if (!opcode) return 1; - opsize = ctx->ptr[1]; - if (opsize < 2) + + if (*opcode == TCPOPT_EOL) return 1; + if (*opcode == TCPOPT_NOP) + return 0; - if (ctx->ptr + opsize > ctx->end) + opsize = next(ctx, 1); + if (!opsize || *opsize < 2) return 1; - switch (opcode) { + switch (*opcode) { case TCPOPT_WINDOW: - if (opsize == TCPOLEN_WINDOW && ctx->ptr + TCPOLEN_WINDOW <= ctx->data_end) - ctx->wscale = ctx->ptr[2] < TCP_MAX_WSCALE ? ctx->ptr[2] : TCP_MAX_WSCALE; + wscale = next(ctx, 1); + if (!wscale) + return 1; + if (*opsize == TCPOLEN_WINDOW) + ctx->wscale = *wscale < TCP_MAX_WSCALE ? *wscale : TCP_MAX_WSCALE; break; case TCPOPT_TIMESTAMP: - if (opsize == TCPOLEN_TIMESTAMP && ctx->ptr + TCPOLEN_TIMESTAMP <= ctx->data_end) { + tsecr = next(ctx, 4); + if (!tsecr) + return 1; + if (*opsize == TCPOLEN_TIMESTAMP) { ctx->option_timestamp = true; /* Client's tsval becomes our tsecr. */ - *ctx->tsecr = get_unaligned((__be32 *)(ctx->ptr + 2)); + *ctx->tsecr = get_unaligned((__be32 *)tsecr); } break; case TCPOPT_SACK_PERM: - if (opsize == TCPOLEN_SACK_PERM) + if (*opsize == TCPOLEN_SACK_PERM) ctx->option_sack = true; break; } - ctx->ptr += opsize; + ctx->off = off + *opsize; return 0; } @@ -256,16 +271,21 @@ static int tscookie_tcpopt_parse_batch(__u32 index, void *context) static __always_inline bool tscookie_init(struct tcphdr *tcp_header, __u16 tcp_len, __be32 *tsval, - __be32 *tsecr, void *data_end) + __be32 *tsecr, void *data, void *data_end) { struct tcpopt_context loop_ctx = { - .ptr = (__u8 *)(tcp_header + 1), - .end = (__u8 *)tcp_header + tcp_len, + .data = data, .data_end = data_end, .tsecr = tsecr, .wscale = TS_OPT_WSCALE_MASK, .option_timestamp = false, .option_sack = false, + /* Note: currently verifier would track .off as unbound scalar. + * In case if verifier would at some point get smarter and + * compute bounded value for this var, beware that it might + * hinder bpf_loop() convergence validation. + */ + .off = (__u8 *)(tcp_header + 1) - (__u8 *)data, }; u32 cookie; @@ -635,7 +655,7 @@ static __always_inline int syncookie_handle_syn(struct header_pointers *hdr, cookie = (__u32)value; if (tscookie_init((void *)hdr->tcp, hdr->tcp_len, - &tsopt_buf[0], &tsopt_buf[1], data_end)) + &tsopt_buf[0], &tsopt_buf[1], data, data_end)) tsopt = tsopt_buf; /* Check that there is enough space for a SYNACK. It also covers diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index cc920c79ff1c..4ff10ea61461 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -45,3 +45,4 @@ mdwe_test gup_longterm mkdirty va_high_addr_switch +hugetlb_fault_after_madv diff --git a/tools/testing/selftests/mm/pagemap_ioctl.c b/tools/testing/selftests/mm/pagemap_ioctl.c index 0161fb49fc6e..befab43719ba 100644 --- a/tools/testing/selftests/mm/pagemap_ioctl.c +++ b/tools/testing/selftests/mm/pagemap_ioctl.c @@ -94,19 +94,19 @@ int init_uffd(void) uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK | UFFD_USER_MODE_ONLY); if (uffd == -1) - ksft_exit_fail_msg("uffd syscall failed\n"); + return uffd; uffdio_api.api = UFFD_API; uffdio_api.features = UFFD_FEATURE_WP_UNPOPULATED | UFFD_FEATURE_WP_ASYNC | UFFD_FEATURE_WP_HUGETLBFS_SHMEM; if (ioctl(uffd, UFFDIO_API, &uffdio_api)) - ksft_exit_fail_msg("UFFDIO_API\n"); + return -1; if (!(uffdio_api.api & UFFDIO_REGISTER_MODE_WP) || !(uffdio_api.features & UFFD_FEATURE_WP_UNPOPULATED) || !(uffdio_api.features & UFFD_FEATURE_WP_ASYNC) || !(uffdio_api.features & UFFD_FEATURE_WP_HUGETLBFS_SHMEM)) - ksft_exit_fail_msg("UFFDIO_API error %llu\n", uffdio_api.api); + return -1; return 0; } @@ -1151,7 +1151,7 @@ int sanity_tests(void) /* 9. Memory mapped file */ fd = open(__FILE__, O_RDONLY); if (fd < 0) - ksft_exit_fail_msg("%s Memory mapped file\n"); + ksft_exit_fail_msg("%s Memory mapped file\n", __func__); ret = stat(__FILE__, &sbuf); if (ret < 0) @@ -1159,7 +1159,7 @@ int sanity_tests(void) fmem = mmap(NULL, sbuf.st_size, PROT_READ, MAP_PRIVATE, fd, 0); if (fmem == MAP_FAILED) - ksft_exit_fail_msg("error nomem %ld %s\n", errno, strerror(errno)); + ksft_exit_fail_msg("error nomem %d %s\n", errno, strerror(errno)); tmp_buf = malloc(sbuf.st_size); memcpy(tmp_buf, fmem, sbuf.st_size); @@ -1189,7 +1189,7 @@ int sanity_tests(void) fmem = mmap(NULL, buf_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); if (fmem == MAP_FAILED) - ksft_exit_fail_msg("error nomem %ld %s\n", errno, strerror(errno)); + ksft_exit_fail_msg("error nomem %d %s\n", errno, strerror(errno)); wp_init(fmem, buf_size); wp_addr_range(fmem, buf_size); @@ -1479,6 +1479,10 @@ int main(void) struct stat sbuf; ksft_print_header(); + + if (init_uffd()) + return ksft_exit_pass(); + ksft_set_plan(115); page_size = getpagesize(); @@ -1488,9 +1492,6 @@ int main(void) if (pagemap_fd < 0) return -EINVAL; - if (init_uffd()) - ksft_exit_fail_msg("uffd init failed\n"); - /* 1. Sanity testing */ sanity_tests_sd(); @@ -1595,7 +1596,7 @@ int main(void) fmem = mmap(NULL, sbuf.st_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); if (fmem == MAP_FAILED) - ksft_exit_fail_msg("error nomem %ld %s\n", errno, strerror(errno)); + ksft_exit_fail_msg("error nomem %d %s\n", errno, strerror(errno)); wp_init(fmem, sbuf.st_size); wp_addr_range(fmem, sbuf.st_size); @@ -1623,7 +1624,7 @@ int main(void) fmem = mmap(NULL, buf_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0); if (fmem == MAP_FAILED) - ksft_exit_fail_msg("error nomem %ld %s\n", errno, strerror(errno)); + ksft_exit_fail_msg("error nomem %d %s\n", errno, strerror(errno)); wp_init(fmem, buf_size); wp_addr_range(fmem, buf_size); diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index cc16f6ca8533..00757445278e 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -223,9 +223,12 @@ CATEGORY="hugetlb" run_test ./hugepage-mremap CATEGORY="hugetlb" run_test ./hugepage-vmemmap CATEGORY="hugetlb" run_test ./hugetlb-madvise +nr_hugepages_tmp=$(cat /proc/sys/vm/nr_hugepages) # For this test, we need one and just one huge page echo 1 > /proc/sys/vm/nr_hugepages CATEGORY="hugetlb" run_test ./hugetlb_fault_after_madv +# Restore the previous number of huge pages, since further tests rely on it +echo "$nr_hugepages_tmp" > /proc/sys/vm/nr_hugepages if test_selected "hugetlb"; then echo "NOTE: These hugetlb tests provide minimal coverage. Use" diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 5f2b3f6c0d74..38be9706c45f 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -859,7 +859,7 @@ kci_test_gretap() run_cmd ip -netns "$testns" addr add dev "$DEV_NS" 10.1.1.100/24 - run_cmd ip -netns "$testns" link set dev $DEV_NS ups + run_cmd ip -netns "$testns" link set dev $DEV_NS up run_cmd ip -netns "$testns" link del "$DEV_NS" # test external mode diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index 5b0e93f9996c..01fa816868bc 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -353,11 +353,12 @@ static void test_stream_msg_peek_server(const struct test_opts *opts) } #define SOCK_BUF_SIZE (2 * 1024 * 1024) -#define MAX_MSG_SIZE (32 * 1024) +#define MAX_MSG_PAGES 4 static void test_seqpacket_msg_bounds_client(const struct test_opts *opts) { unsigned long curr_hash; + size_t max_msg_size; int page_size; int msg_count; int fd; @@ -373,7 +374,8 @@ static void test_seqpacket_msg_bounds_client(const struct test_opts *opts) curr_hash = 0; page_size = getpagesize(); - msg_count = SOCK_BUF_SIZE / MAX_MSG_SIZE; + max_msg_size = MAX_MSG_PAGES * page_size; + msg_count = SOCK_BUF_SIZE / max_msg_size; for (int i = 0; i < msg_count; i++) { size_t buf_size; @@ -383,7 +385,7 @@ static void test_seqpacket_msg_bounds_client(const struct test_opts *opts) /* Use "small" buffers and "big" buffers. */ if (i & 1) buf_size = page_size + - (rand() % (MAX_MSG_SIZE - page_size)); + (rand() % (max_msg_size - page_size)); else buf_size = 1 + (rand() % page_size); @@ -429,7 +431,6 @@ static void test_seqpacket_msg_bounds_server(const struct test_opts *opts) unsigned long remote_hash; unsigned long curr_hash; int fd; - char buf[MAX_MSG_SIZE]; struct msghdr msg = {0}; struct iovec iov = {0}; @@ -457,8 +458,13 @@ static void test_seqpacket_msg_bounds_server(const struct test_opts *opts) control_writeln("SRVREADY"); /* Wait, until peer sends whole data. */ control_expectln("SENDDONE"); - iov.iov_base = buf; - iov.iov_len = sizeof(buf); + iov.iov_len = MAX_MSG_PAGES * getpagesize(); + iov.iov_base = malloc(iov.iov_len); + if (!iov.iov_base) { + perror("malloc"); + exit(EXIT_FAILURE); + } + msg.msg_iov = &iov; msg.msg_iovlen = 1; @@ -483,6 +489,7 @@ static void test_seqpacket_msg_bounds_server(const struct test_opts *opts) curr_hash += hash_djb2(msg.msg_iov[0].iov_base, recv_size); } + free(iov.iov_base); close(fd); remote_hash = control_readulong(); |